statediffing service squashed commit

.github/workflows/checks.yml

@@ -0,0 +1,15 @@
+name: checks
+
+on: [pull_request]
+
+jobs:
+  linter-check:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/setup-go@v3
+        with:
+          go-version: "1.19"
+          check-latest: true
+      - uses: actions/checkout@v2
+      - name: Run linter
+        run: go run build/ci.go lint

.github/workflows/manual_binary_publish.yaml

@@ -0,0 +1,21 @@
+name: MANUAL Override Publish geth binary to release
+on:
+  workflow_dispatch:
+    inputs:
+      giteaPublishTag:
+        description: 'Package to publish TO on gitea; e.g. v1.10.25-statediff-4.2.1-alpha'
+        required: true
+      cercContainerTag:
+        description: 'Tagged Container to extract geth binary FROM'
+        required: true
+jobs:
+  build:
+    name: Manual override publish of geth binary FROM tagged release TO TAGGED package on git.vdb.to
+    runs-on: ubuntu-latest
+    steps:
+      - name: Copy ethereum binary file
+        run: docker run --rm --entrypoint cat git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{ github.event.inputs.cercContainerTag }} /usr/local/bin/geth > geth-linux-amd64
+      - name: curl
+        uses: enflo/curl-action@master
+        with:
+          curl: --user cerccicd:${{ secrets.GITEA_TOKEN }} --upload-file geth-linux-amd64 https://git.vdb.to/api/packages/cerc-io/generic/go-ethereum/${{ github.event.inputs.giteaPublishTag }}/geth-linux-amd64

.github/workflows/manual_publish.yaml

@@ -0,0 +1,21 @@
+name: MANUAL Override Publish geth binary to release
+on:
+  workflow_dispatch:
+    inputs:
+      giteaPublishTag:
+        description: 'Package to publish TO on gitea; e.g. v1.10.25-statediff-4.2.1-alpha'
+        required: true
+      cercContainerTag:
+        description: 'Tagged Container to extract geth binary FROM'
+        required: true
+jobs:
+  build:
+    name: Manual override publish of geth binary FROM tagged release TO TAGGED package on git.vdb.to
+    runs-on: ubuntu-latest
+    steps:
+      - name: Copy ethereum binary file
+        run: docker run --rm --entrypoint cat git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{ github.event.inputs.cercContainerTag }} /usr/local/bin/geth > geth-linux-amd64
+      - name: curl
+        uses: enflo/curl-action@master
+        with:
+          curl: --user circcicd:${{ secrets.GITEA_TOKEN }} --upload-file geth-linux-amd64 https://git.vdb.to/api/packages/cerc-io/generic/go-ethereum/${{ github.event.inputs.giteaPublishTag }}/geth-linux-amd64

.github/workflows/on-pr.yml

@@ -0,0 +1,7 @@
+name: Build and test
+
+on: [pull_request]
+
+jobs:
+  run-tests:
+    uses: ./.github/workflows/tests.yml

.github/workflows/publish.yaml

@@ -0,0 +1,36 @@
+name: Publish geth to release
+on:
+  release:
+    types: [published]
+jobs:
+  run-tests:
+    uses: ./.github/workflows/tests.yml
+  build:
+    name: Run docker build and publish
+    needs: run-tests
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Run docker build
+        run: docker build -t cerc-io/go-ethereum -f Dockerfile .
+      - name: Get the version
+        id: vars
+        run: |
+          echo ::set-output name=sha::$(echo ${GITHUB_SHA:0:7})
+          echo ::set-output name=tag::$(echo ${GITHUB_REF#refs/tags/})
+      - name: Tag docker image
+        run: docker tag cerc-io/go-ethereum git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{steps.vars.outputs.sha}}
+      - name: Tag docker image
+        run: docker tag git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{steps.vars.outputs.sha}} git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{steps.vars.outputs.tag}}
+      - name: Docker Login
+        run: echo ${{ secrets.GITEA_TOKEN }} | docker login https://git.vdb.to -u cerccicd --password-stdin
+      - name: Docker Push
+        run: docker push git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{steps.vars.outputs.sha}}
+      - name: Docker Push TAGGED
+        run: docker push git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{steps.vars.outputs.tag}}
+      - name: Copy ethereum binary file
+        run: docker run --rm --entrypoint cat git.vdb.to/cerc-io/go-ethereum/go-ethereum:${{steps.vars.outputs.sha}} /usr/local/bin/geth > geth-linux-amd64
+      - name: curl
+        uses: enflo/curl-action@master
+        with:
+          curl: --user cerccicd:${{ secrets.GITEA_TOKEN }} --upload-file geth-linux-amd64 https://git.vdb.to/api/packages/cerc-io/generic/go-ethereum/${{steps.vars.outputs.tag}}/geth-linux-amd64

.github/workflows/tests.yml

@@ -0,0 +1,139 @@
+name: Tests for Geth that are used in multiple jobs.
+
+on:
+  workflow_call:
+
+env:
+  stack-orchestrator-ref: ${{ github.event.inputs.stack-orchestrator-ref  || 'e62830c982d4dfc5f3c1c2b12c1754a7e9b538f1'}}
+  ipld-eth-db-ref: ${{ github.event.inputs.ipld-ethcl-db-ref  || '167cfbfb202d387aed2c9950e18c45a66f87821d' }}
+  GOPATH: /tmp/go
+
+jobs:
+  build:
+    name: Run docker build
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+      - name: Run docker build
+        run: docker build -t cerc-io/go-ethereum .
+
+  geth-unit-test:
+    name: Run geth unit test
+    runs-on: ubuntu-latest
+    env:
+      GO111MODULE: on
+    steps:
+      - name: Create GOPATH
+        run: mkdir -p /tmp/go
+
+      - uses: actions/setup-go@v3
+        with:
+          go-version: "1.19"
+          check-latest: true
+
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Run unit tests
+        run: |
+          make test
+
+  statediff-unit-test:
+    name: Run state diff unit test
+    runs-on: ubuntu-latest
+    steps:
+      - name: Create GOPATH
+        run: mkdir -p /tmp/go
+
+      - uses: actions/setup-go@v3
+        with:
+          go-version: "1.19"
+          check-latest: true
+
+      - name: Checkout code
+        uses: actions/checkout@v2
+
+      - name: Run docker compose
+        run: |
+          docker-compose up -d
+      - name: Give the migration a few seconds
+        run: sleep 30;
+
+      - name: Run unit tests
+        run: make statedifftest
+
+  private-network-test:
+    name: Start Geth in a private network.
+    runs-on: ubuntu-latest
+    steps:
+      - name: Create GOPATH
+        run: mkdir -p /tmp/go
+
+      - uses: actions/setup-go@v3
+        with:
+          go-version: "1.19"
+          check-latest: true
+
+      - name: Checkout code
+        uses: actions/checkout@v3
+        with:
+          path: "./go-ethereum"
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ env.stack-orchestrator-ref }}
+          path: "./stack-orchestrator/"
+          repository: cerc-io/mshaw_stack_hack
+          fetch-depth: 0
+
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{ env.ipld-eth-db-ref }}
+          repository: cerc-io/ipld-eth-db
+          path: "./ipld-eth-db/"
+          fetch-depth: 0
+
+      - name: Create config file
+        run: |
+          echo vulcanize_ipld_eth_db=$GITHUB_WORKSPACE/ipld-eth-db/ > $GITHUB_WORKSPACE/config.sh
+          echo vulcanize_go_ethereum=$GITHUB_WORKSPACE/go-ethereum/ >> $GITHUB_WORKSPACE/config.sh
+          echo db_write=true >> $GITHUB_WORKSPACE/config.sh
+          echo genesis_file_path=start-up-files/go-ethereum/genesis.json >> $GITHUB_WORKSPACE/config.sh
+          cat $GITHUB_WORKSPACE/config.sh
+      - name: Compile Geth
+        run: |
+          cd $GITHUB_WORKSPACE/stack-orchestrator/helper-scripts
+          ./compile-geth.sh -e docker -p $GITHUB_WORKSPACE/config.sh
+          cd -
+      - name: Run docker compose
+        run: |
+          docker-compose  \
+          -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-go-ethereum.yml" \
+          -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-db-sharding.yml" \
+          --env-file $GITHUB_WORKSPACE/config.sh \
+          up -d --build
+      - name: Make sure the /root/transaction_info/STATEFUL_TEST_DEPLOYED_ADDRESS exists within a certain time frame.
+        shell: bash
+        run: |
+          COUNT=0
+          ATTEMPTS=15
+          docker logs local_go-ethereum_1
+          docker compose -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-db-sharding.yml" -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-go-ethereum.yml" exec go-ethereum ps aux
+          until $(docker compose -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-db-sharding.yml" -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-go-ethereum.yml" cp go-ethereum:/root/transaction_info/STATEFUL_TEST_DEPLOYED_ADDRESS ./STATEFUL_TEST_DEPLOYED_ADDRESS) || [[ $COUNT -eq $ATTEMPTS ]]; do echo -e "$(( COUNT++ ))... \c"; sleep 10; done
+          [[ $COUNT -eq $ATTEMPTS ]] && echo "Could not find the successful contract deployment" && (exit 1)
+          cat ./STATEFUL_TEST_DEPLOYED_ADDRESS
+          echo "Address length: `wc ./STATEFUL_TEST_DEPLOYED_ADDRESS`"
+          sleep 15;
+      - name: Create a new transaction.
+        shell: bash
+        run: |
+          docker logs local_go-ethereum_1
+          docker compose -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-db-sharding.yml" -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-go-ethereum.yml" exec go-ethereum /bin/bash /root/transaction_info/NEW_TRANSACTION
+          echo $?
+      - name: Make sure we see entries in the header table
+        shell: bash
+        run: |
+          rows=$(docker compose -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-db-sharding.yml" -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-go-ethereum.yml" exec ipld-eth-db psql -U vdbm -d vulcanize_testing  -AXqtc "SELECT COUNT(*) FROM eth.header_cids")
+          [[ "$rows" -lt "1" ]] && echo "We could not find any rows in postgres table." && (exit 1)
+          echo $rows
+          docker compose -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-db-sharding.yml" -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-go-ethereum.yml" exec ipld-eth-db psql -U vdbm -d vulcanize_testing  -AXqtc "SELECT * FROM eth.header_cids"

.gitignore

@@ -47,4 +47,16 @@ profile.cov
 /dashboard/assets/package-lock.json
 
 **/yarn-error.log
-logs/
+logs/
+foundry/deployments/local-private-network/geth-linux-amd64
+foundry/projects/local-private-network/geth-linux-amd64
+
+# Helpful repos
+related-repositories/foundry-test/**
+related-repositories/hive/**
+related-repositories/ipld-eth-db/**
+statediff/indexer/database/sql/statediffing_test_file.sql
+statediff/statediffing_test_file.sql
+statediff/known_gaps.sql
+related-repositories/foundry-test/
+related-repositories/ipld-eth-db/

.gitmodules

@@ -5,4 +5,4 @@
 [submodule "evm-benchmarks"]
 	path = tests/evm-benchmarks
 	url = https://github.com/ipsilon/evm-benchmarks
-	shallow = true
+	shallow = true

Dockerfile.amd64

@@ -0,0 +1,7 @@
+# Build Geth in a stock Go builder container
+FROM golang:1.15.5 as builder
+
+#RUN apk add --no-cache make gcc musl-dev linux-headers git
+
+ADD . /go-ethereum
+RUN cd /go-ethereum && make geth

Jenkinsfile

@@ -0,0 +1,50 @@
+pipeline {
+    agent any
+
+    stages {
+        stage('Build') {
+            steps {
+                script{
+                    docker.withRegistry('https://git.vdb.to'){
+                        echo 'Building geth image...'
+                        //def geth_image = docker.build("cerc-io/go-ethereum:jenkinscicd")
+                        echo 'built geth image'
+                    }
+                }
+            }
+        }
+        stage('Test') {
+            agent {
+                docker {
+                    image 'cerc-io/foundation:jenkinscicd'
+                    //image 'cerc-io/foundation_alpine:jenkinscicd'
+                }
+            }
+
+            environment {
+                GO111MODULE = "on"
+                CGO_ENABLED = 1
+                //GOPATH = "${JENKINS_HOME}/jobs/${JOB_NAME}/builds/${BUILD_ID}"
+                //GOPATH = "/go"
+                GOPATH = "/tmp/go"
+                //GOMODCACHE = "/go/pkg/mod"
+                GOCACHE = "${WORKSPACE}/.cache/go-build"
+                GOENV = "${WORKSPACE}/.config/go/env"
+                GOMODCACHE = "/tmp/go/pkg/mod"
+                GOWORK=""
+                //GOFLAGS=""
+
+            }
+            steps {
+                echo 'Testing ...'
+                //sh '/usr/local/go/bin/go test -p 1 -v ./...'
+                sh 'make test'
+            }
+        }
+        stage('Packaging') {
+            steps {
+                echo 'Packaging ...'
+            }
+        }
+    }
+}

Makefile

@@ -4,10 +4,31 @@
 
 .PHONY: geth android ios evm all test clean
 
+BIN = $(GOPATH)/bin
+
+## Migration tool
+GOOSE = $(BIN)/goose
+$(BIN)/goose:
+	go get -u github.com/pressly/goose/cmd/goose
+
 GOBIN = ./build/bin
 GO ?= latest
 GORUN = env GO111MODULE=on go run
 
+#Database
+HOST_NAME = localhost
+PORT = 5432
+USER = vdbm
+PASSWORD = password
+
+# Set env variable
+# `PGPASSWORD` is used by `createdb` and `dropdb`
+export PGPASSWORD=$(PASSWORD)
+
+#Test
+TEST_DB = cerc_testing
+TEST_CONNECT_STRING = postgresql://$(USER):$(PASSWORD)@$(HOST_NAME):$(PORT)/$(TEST_DB)?sslmode=disable
+
 geth:
 	$(GORUN) build/ci.go install ./cmd/geth
 	@echo "Done building."
@@ -36,3 +57,13 @@ devtools:
 	env GOBIN= go install ./cmd/abigen
 	@type "solc" 2> /dev/null || echo 'Please install solc'
 	@type "protoc" 2> /dev/null || echo 'Please install protoc'
+
+.PHONY: statedifftest
+statedifftest: | $(GOOSE)
+	GO111MODULE=on go get github.com/stretchr/testify/assert@v1.7.0
+	GO111MODULE=on MODE=statediff go test -p 1 ./statediff/... -v
+
+.PHONY: statediff_filewriting_test
+statediff_filetest: | $(GOOSE)
+	GO111MODULE=on go get github.com/stretchr/testify/assert@v1.7.0
+	GO111MODULE=on MODE=statediff STATEDIFF_DB=file go test -p 1 ./statediff/... -v

README.md

@@ -2,9 +2,7 @@
 
 Official Golang execution layer implementation of the Ethereum protocol.
 
-[![API Reference](
+[![API Reference](https://camo.githubusercontent.com/915b7be44ada53c290eb157634330494ebe3e30a/68747470733a2f2f676f646f632e6f72672f6769746875622e636f6d2f676f6c616e672f6764646f3f7374617475732e737667)](https://pkg.go.dev/github.com/ethereum/go-ethereum?tab=doc)
-https://camo.githubusercontent.com/915b7be44ada53c290eb157634330494ebe3e30a/68747470733a2f2f676f646f632e6f72672f6769746875622e636f6d2f676f6c616e672f6764646f3f7374617475732e737667
-)](https://pkg.go.dev/github.com/ethereum/go-ethereum?tab=doc)
 [![Go Report Card](https://goreportcard.com/badge/github.com/ethereum/go-ethereum)](https://goreportcard.com/report/github.com/ethereum/go-ethereum)
 [![Travis](https://travis-ci.com/ethereum/go-ethereum.svg?branch=master)](https://travis-ci.com/ethereum/go-ethereum)
 [![Discord](https://img.shields.io/badge/discord-join%20chat-blue.svg)](https://discord.gg/nthXNEv)
@@ -12,6 +10,21 @@ https://camo.githubusercontent.com/915b7be44ada53c290eb157634330494ebe3e30a/6874
 Automated builds are available for stable releases and the unstable master branch. Binary
 archives are published at https://geth.ethereum.org/downloads/.
 
+## Vulcanize Specific
+
+This section captures components specific to vulcanize.
+
+### Branching Structure
+
+We currently follow the following branching structure.
+
+1. Create a branch: `v1.10.18-statediff-vX` --> feature/some-feature`
+2. Create a PR upstream: `feature/some-feature` --> `v1.10.18-statediff-vX`
+3. When a release is ready, create a release branch: `v1.10.18-statediff-vX` --> `v1.10.18-statediff-X.Y.Z`
+4. When `v1.10.18-statediff-vX` is stable, merge it to `statediff`.
+
+This process is subject to change.
+
 ## Building the source
 
 For prerequisites and detailed build instructions please read the [Installation Instructions](https://geth.ethereum.org/docs/getting-started/installing-geth).
@@ -55,10 +68,10 @@ on how you can run your own `geth` instance.
 
 Minimum:
 
-* CPU with 2+ cores
+- CPU with 2+ cores
-* 4GB RAM
+- 4GB RAM
-* 1TB free storage space to sync the Mainnet
+- 1TB free storage space to sync the Mainnet
-* 8 MBit/sec download Internet service
+- 8 MBit/sec download Internet service
 
 Recommended:
 
@@ -121,12 +134,12 @@ Specifying the `--goerli` flag, however, will reconfigure your `geth` instance a
 crossing over between the main network and test network, you should always
 use separate accounts for play and real money. Unless you manually move
 accounts, `geth` will by default correctly separate the two networks and will not make any
-accounts available between them.*
+accounts available between them._
 
 ### Full node on the Rinkeby test network
 
 Go Ethereum also supports connecting to the older proof-of-authority based test network
-called [*Rinkeby*](https://www.rinkeby.io) which is operated by members of the community.
+called [_Rinkeby_](https://www.rinkeby.io) which is operated by members of the community.
 
 ```shell
 $ geth --rinkeby console
@@ -148,7 +161,7 @@ export your existing configuration:
 $ geth --your-favourite-flags dumpconfig
 ```
 
-*Note: This works only with `geth` v1.6.0 and above.*
+_Note: This works only with `geth` v1.6.0 and above._
 
 #### Docker quick start
 
@@ -288,8 +301,8 @@ that other nodes can use to connect to it and exchange peer information. Make su
 replace the displayed IP address information (most probably `[::]`) with your externally
 accessible IP to get the actual `enode` URL.
 
-*Note: You could also use a full-fledged `geth` node as a bootnode, but it's the less
+_Note: You could also use a full-fledged `geth` node as a bootnode, but it's the less
-recommended way.*
+recommended way._
 
 #### Starting up your member nodes
 
@@ -303,8 +316,8 @@ do also specify a custom `--datadir` flag.
 $ geth --datadir=path/to/custom/data/folder --bootnodes=<bootnode-enode-url-from-above>
 ```
 
-*Note: Since your network will be completely cut off from the main and test networks, you'll
+_Note: Since your network will be completely cut off from the main and test networks, you'll
-also need to configure a miner to process transactions and create new blocks for you.*
+also need to configure a miner to process transactions and create new blocks for you._
 
 #### Running a private miner
 
@@ -338,13 +351,13 @@ and merge procedures quick and simple.
 
 Please make sure your contributions adhere to our coding guidelines:
 
- * Code must adhere to the official Go [formatting](https://golang.org/doc/effective_go.html#formatting)
+- Code must adhere to the official Go [formatting](https://golang.org/doc/effective_go.html#formatting)
-   guidelines (i.e. uses [gofmt](https://golang.org/cmd/gofmt/)).
+  guidelines (i.e. uses [gofmt](https://golang.org/cmd/gofmt/)).
- * Code must be documented adhering to the official Go [commentary](https://golang.org/doc/effective_go.html#commentary)
+- Code must be documented adhering to the official Go [commentary](https://golang.org/doc/effective_go.html#commentary)
-   guidelines.
+  guidelines.
- * Pull requests need to be based on and opened against the `master` branch.
+- Pull requests need to be based on and opened against the `master` branch.
- * Commit messages should be prefixed with the package(s) they modify.
+- Commit messages should be prefixed with the package(s) they modify.
-   * E.g. "eth, rpc: make trace configs optional"
+  - E.g. "eth, rpc: make trace configs optional"
 
 Please see the [Developers' Guide](https://geth.ethereum.org/docs/developers/geth-developer/dev-guide)
 for more details on configuring your environment, managing project dependencies, and

cmd/geth/config.go

@@ -18,10 +18,12 @@ package main
 
 import (
 	"bufio"
+	"context"
 	"errors"
 	"fmt"
 	"os"
 	"reflect"
+	"time"
 	"unicode"
 
 	"github.com/urfave/cli/v2"
@@ -40,6 +42,12 @@ import (
 	"github.com/ethereum/go-ethereum/metrics"
 	"github.com/ethereum/go-ethereum/node"
 	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/statediff"
+	dumpdb "github.com/ethereum/go-ethereum/statediff/indexer/database/dump"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/file"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
 	"github.com/naoina/toml"
 )
 
@@ -151,6 +159,9 @@ func makeConfigNode(ctx *cli.Context) (*node.Node, gethConfig) {
 		cfg.Ethstats.URL = ctx.String(utils.EthStatsURLFlag.Name)
 	}
 	applyMetricConfig(ctx, &cfg)
+	if ctx.Bool(utils.StateDiffFlag.Name) {
+		cfg.Eth.Diffing = true
+	}
 
 	return stack, cfg
 }
@@ -167,7 +178,113 @@ func makeFullNode(ctx *cli.Context) (*node.Node, ethapi.Backend) {
 	// Configure log filter RPC API.
 	filterSystem := utils.RegisterFilterAPI(stack, backend, &cfg.Eth)
 
-	// Configure GraphQL if requested.
+	if ctx.Bool(utils.StateDiffFlag.Name) {
+		var indexerConfig interfaces.Config
+		var clientName, nodeID string
+		if ctx.IsSet(utils.StateDiffWritingFlag.Name) {
+			clientName = ctx.String(utils.StateDiffDBClientNameFlag.Name)
+			if ctx.IsSet(utils.StateDiffDBNodeIDFlag.Name) {
+				nodeID = ctx.String(utils.StateDiffDBNodeIDFlag.Name)
+			} else {
+				utils.Fatalf("Must specify node ID for statediff DB output")
+			}
+
+			dbTypeStr := ctx.String(utils.StateDiffDBTypeFlag.Name)
+			dbType, err := shared.ResolveDBType(dbTypeStr)
+			if err != nil {
+				utils.Fatalf("%v", err)
+			}
+			switch dbType {
+			case shared.FILE:
+				fileModeStr := ctx.String(utils.StateDiffFileMode.Name)
+				fileMode, err := file.ResolveFileMode(fileModeStr)
+				if err != nil {
+					utils.Fatalf("%v", err)
+				}
+
+				indexerConfig = file.Config{
+					Mode:                     fileMode,
+					OutputDir:                ctx.String(utils.StateDiffFileCsvDir.Name),
+					FilePath:                 ctx.String(utils.StateDiffFilePath.Name),
+					WatchedAddressesFilePath: ctx.String(utils.StateDiffWatchedAddressesFilePath.Name),
+				}
+			case shared.POSTGRES:
+				driverTypeStr := ctx.String(utils.StateDiffDBDriverTypeFlag.Name)
+				driverType, err := postgres.ResolveDriverType(driverTypeStr)
+				if err != nil {
+					utils.Fatalf("%v", err)
+				}
+				pgConfig := postgres.Config{
+					Hostname:     ctx.String(utils.StateDiffDBHostFlag.Name),
+					Port:         ctx.Int(utils.StateDiffDBPortFlag.Name),
+					DatabaseName: ctx.String(utils.StateDiffDBNameFlag.Name),
+					Username:     ctx.String(utils.StateDiffDBUserFlag.Name),
+					Password:     ctx.String(utils.StateDiffDBPasswordFlag.Name),
+					ID:           nodeID,
+					ClientName:   clientName,
+					Driver:       driverType,
+				}
+				if ctx.IsSet(utils.StateDiffUpsert.Name) {
+					pgConfig.Upsert = ctx.Bool(utils.StateDiffUpsert.Name)
+				}
+				if ctx.IsSet(utils.StateDiffDBMinConns.Name) {
+					pgConfig.MinConns = ctx.Int(utils.StateDiffDBMinConns.Name)
+				}
+				if ctx.IsSet(utils.StateDiffDBMaxConns.Name) {
+					pgConfig.MaxConns = ctx.Int(utils.StateDiffDBMaxConns.Name)
+				}
+				if ctx.IsSet(utils.StateDiffDBMaxIdleConns.Name) {
+					pgConfig.MaxIdle = ctx.Int(utils.StateDiffDBMaxIdleConns.Name)
+				}
+				if ctx.IsSet(utils.StateDiffDBMaxConnLifetime.Name) {
+					pgConfig.MaxConnLifetime = time.Duration(ctx.Duration(utils.StateDiffDBMaxConnLifetime.Name).Seconds())
+				}
+				if ctx.IsSet(utils.StateDiffDBMaxConnIdleTime.Name) {
+					pgConfig.MaxConnIdleTime = time.Duration(ctx.Duration(utils.StateDiffDBMaxConnIdleTime.Name).Seconds())
+				}
+				if ctx.IsSet(utils.StateDiffDBConnTimeout.Name) {
+					pgConfig.ConnTimeout = time.Duration(ctx.Duration(utils.StateDiffDBConnTimeout.Name).Seconds())
+				}
+				if ctx.IsSet(utils.StateDiffLogStatements.Name) {
+					pgConfig.LogStatements = ctx.Bool(utils.StateDiffLogStatements.Name)
+				}
+				if ctx.IsSet(utils.StateDiffCopyFrom.Name) {
+					pgConfig.CopyFrom = ctx.Bool(utils.StateDiffCopyFrom.Name)
+				}
+				indexerConfig = pgConfig
+			case shared.DUMP:
+				dumpTypeStr := ctx.String(utils.StateDiffDBDumpDst.Name)
+				dumpType, err := dumpdb.ResolveDumpType(dumpTypeStr)
+				if err != nil {
+					utils.Fatalf("%v", err)
+				}
+				switch dumpType {
+				case dumpdb.STDERR:
+					indexerConfig = dumpdb.Config{Dump: os.Stdout}
+				case dumpdb.STDOUT:
+					indexerConfig = dumpdb.Config{Dump: os.Stderr}
+				case dumpdb.DISCARD:
+					indexerConfig = dumpdb.Config{Dump: dumpdb.NewDiscardWriterCloser()}
+				default:
+					utils.Fatalf("unrecognized dump destination: %s", dumpType)
+				}
+			default:
+				utils.Fatalf("unrecognized database type: %s", dbType)
+			}
+		}
+		p := statediff.Config{
+			IndexerConfig:   indexerConfig,
+			ID:              nodeID,
+			ClientName:      clientName,
+			Context:         context.Background(),
+			EnableWriteLoop: ctx.Bool(utils.StateDiffWritingFlag.Name),
+			NumWorkers:      ctx.Uint(utils.StateDiffWorkersFlag.Name),
+			WaitForSync:     ctx.Bool(utils.StateDiffWaitForSync.Name),
+		}
+		utils.RegisterStateDiffService(stack, eth, &cfg.Eth, p, backend)
+	}
+
+	// Configure GraphQL if requested
 	if ctx.IsSet(utils.GraphQLEnabledFlag.Name) {
 		utils.RegisterGraphQLService(stack, backend, filterSystem, &cfg.Node)
 	}

cmd/geth/main.go

@@ -149,6 +149,33 @@ var (
 		utils.GpoMaxGasPriceFlag,
 		utils.GpoIgnoreGasPriceFlag,
 		utils.MinerNotifyFullFlag,
+		utils.StateDiffFlag,
+		utils.StateDiffDBTypeFlag,
+		utils.StateDiffDBDriverTypeFlag,
+		utils.StateDiffDBDumpDst,
+		utils.StateDiffDBNameFlag,
+		utils.StateDiffDBPasswordFlag,
+		utils.StateDiffDBUserFlag,
+		utils.StateDiffDBHostFlag,
+		utils.StateDiffDBPortFlag,
+		utils.StateDiffDBMaxConnLifetime,
+		utils.StateDiffDBMaxConnIdleTime,
+		utils.StateDiffDBMaxConns,
+		utils.StateDiffDBMinConns,
+		utils.StateDiffDBMaxIdleConns,
+		utils.StateDiffDBConnTimeout,
+		utils.StateDiffDBNodeIDFlag,
+		utils.StateDiffDBClientNameFlag,
+		utils.StateDiffWritingFlag,
+		utils.StateDiffWorkersFlag,
+		utils.StateDiffFileMode,
+		utils.StateDiffFileCsvDir,
+		utils.StateDiffFilePath,
+		utils.StateDiffWaitForSync,
+		utils.StateDiffWatchedAddressesFilePath,
+		utils.StateDiffUpsert,
+		utils.StateDiffLogStatements,
+		utils.StateDiffCopyFrom,
 		configFileFlag,
 	}, utils.NetworkFlags, utils.DatabasePathFlags)
 

cmd/utils/flags.go

@@ -74,6 +74,8 @@ import (
 	"github.com/ethereum/go-ethereum/params"
 	"github.com/ethereum/go-ethereum/rlp"
 	"github.com/ethereum/go-ethereum/rpc"
+	"github.com/ethereum/go-ethereum/statediff"
+
 	pcsclite "github.com/gballet/go-libpcsclite"
 	gopsutil "github.com/shirou/gopsutil/mem"
 	"github.com/urfave/cli/v2"
@@ -994,6 +996,130 @@ Please note that --` + MetricsHTTPFlag.Name + ` must be set to start the server.
 		Value:    metrics.DefaultConfig.InfluxDBOrganization,
 		Category: flags.MetricsCategory,
 	}
+
+	StateDiffFlag = &cli.BoolFlag{
+		Name:     "statediff",
+		Usage:    "Enables the processing of state diffs between each block",
+		Category: flags.MiscCategory,
+	}
+	StateDiffDBTypeFlag = &cli.StringFlag{
+		Name:  "statediff.db.type",
+		Usage: "Statediff database type (current options: postgres, file, dump)",
+		Value: "postgres",
+	}
+	StateDiffDBDriverTypeFlag = &cli.StringFlag{
+		Name:  "statediff.db.driver",
+		Usage: "Statediff database driver type",
+		Value: "pgx",
+	}
+	StateDiffDBDumpDst = &cli.StringFlag{
+		Name:  "statediff.dump.dst",
+		Usage: "Statediff database dump destination (default is stdout)",
+		Value: "stdout",
+	}
+	StateDiffDBHostFlag = &cli.StringFlag{
+		Name:  "statediff.db.host",
+		Usage: "Statediff database hostname/ip",
+		Value: "localhost",
+	}
+	StateDiffDBPortFlag = &cli.IntFlag{
+		Name:  "statediff.db.port",
+		Usage: "Statediff database port",
+		Value: 5432,
+	}
+	StateDiffDBNameFlag = &cli.StringFlag{
+		Name:  "statediff.db.name",
+		Usage: "Statediff database name",
+	}
+	StateDiffDBPasswordFlag = &cli.StringFlag{
+		Name:  "statediff.db.password",
+		Usage: "Statediff database password",
+	}
+	StateDiffDBUserFlag = &cli.StringFlag{
+		Name:  "statediff.db.user",
+		Usage: "Statediff database username",
+		Value: "postgres",
+	}
+	StateDiffDBMaxConnLifetime = &cli.DurationFlag{
+		Name:  "statediff.db.maxconnlifetime",
+		Usage: "Statediff database maximum connection lifetime (in seconds)",
+	}
+	StateDiffDBMaxConnIdleTime = &cli.DurationFlag{
+		Name:  "statediff.db.maxconnidletime",
+		Usage: "Statediff database maximum connection idle time (in seconds)",
+	}
+	StateDiffDBMaxConns = &cli.IntFlag{
+		Name:  "statediff.db.maxconns",
+		Usage: "Statediff database maximum connections",
+	}
+	StateDiffDBMinConns = &cli.IntFlag{
+		Name:  "statediff.db.minconns",
+		Usage: "Statediff database minimum connections",
+	}
+	StateDiffDBMaxIdleConns = &cli.IntFlag{
+		Name:  "statediff.db.maxidleconns",
+		Usage: "Statediff database maximum idle connections",
+	}
+	StateDiffDBConnTimeout = &cli.DurationFlag{
+		Name:  "statediff.db.conntimeout",
+		Usage: "Statediff database connection timeout (in seconds)",
+	}
+	StateDiffDBNodeIDFlag = &cli.StringFlag{
+		Name:  "statediff.db.nodeid",
+		Usage: "Node ID to use when writing state diffs to database",
+	}
+	StateDiffFileMode = &cli.StringFlag{
+		Name:  "statediff.file.mode",
+		Usage: "Statediff file writing mode (current options: csv, sql)",
+		Value: "csv",
+	}
+	StateDiffFileCsvDir = &cli.StringFlag{
+		Name:  "statediff.file.csvdir",
+		Usage: "Full path of output directory to write statediff data out to when operating in csv file mode",
+	}
+	StateDiffFilePath = &cli.StringFlag{
+		Name:  "statediff.file.path",
+		Usage: "Full path (including filename) to write statediff data out to when operating in sql file mode",
+	}
+	StateDiffWatchedAddressesFilePath = &cli.StringFlag{
+		Name:  "statediff.file.wapath",
+		Usage: "Full path (including filename) to write statediff watched addresses out to when operating in file mode",
+	}
+	StateDiffDBClientNameFlag = &cli.StringFlag{
+		Name:  "statediff.db.clientname",
+		Usage: "Client name to use when writing state diffs to database",
+		Value: "go-ethereum",
+	}
+	StateDiffUpsert = &cli.BoolFlag{
+		Name:  "statediff.db.upsert",
+		Usage: "Should the statediff service overwrite data existing in the database?",
+		Value: false,
+	}
+	StateDiffLogStatements = &cli.BoolFlag{
+		Name:  "statediff.db.logstatements",
+		Usage: "Should the statediff service log all database statements? (Note: pgx only)",
+		Value: false,
+	}
+
+	StateDiffCopyFrom = &cli.BoolFlag{
+		Name:  "statediff.db.copyfrom",
+		Usage: "Should the statediff service use COPY FROM for multiple inserts? (Note: pgx only)",
+		Value: false,
+	}
+
+	StateDiffWritingFlag = &cli.BoolFlag{
+		Name:  "statediff.writing",
+		Usage: "Activates progressive writing of state diffs to database as new block are synced",
+	}
+	StateDiffWorkersFlag = &cli.UintFlag{
+		Name:  "statediff.workers",
+		Usage: "Number of concurrent workers to use during statediff processing (default 1)",
+		Value: 1,
+	}
+	StateDiffWaitForSync = &cli.BoolFlag{
+		Name:  "statediff.waitforsync",
+		Usage: "Should the statediff service wait for geth to catch up to the head of the chain?",
+	}
 )
 
 var (
@@ -1246,6 +1372,10 @@ func setWS(ctx *cli.Context, cfg *node.Config) {
 	if ctx.IsSet(WSPathPrefixFlag.Name) {
 		cfg.WSPathPrefix = ctx.String(WSPathPrefixFlag.Name)
 	}
+
+	if ctx.Bool(StateDiffFlag.Name) {
+		cfg.WSModules = append(cfg.WSModules, "statediff")
+	}
 }
 
 // setIPC creates an IPC path configuration from the set command line flags,
@@ -2017,6 +2147,15 @@ func RegisterEthService(stack *node.Node, cfg *ethconfig.Config) (ethapi.Backend
 	return backend.APIBackend, backend
 }
 
+// RegisterLesEthService adds an Ethereum les client to the stack.
+func RegisterLesEthService(stack *node.Node, cfg *eth.Config) *les.LightEthereum {
+	backend, err := les.New(stack, cfg)
+	if err != nil {
+		Fatalf("Failed to register the Ethereum service: %v", err)
+	}
+	return backend
+}
+
 // RegisterEthStatsService configures the Ethereum Stats daemon and adds it to the node.
 func RegisterEthStatsService(stack *node.Node, backend ethapi.Backend, url string) {
 	if err := ethstats.New(stack, backend, backend.Engine(), url); err != nil {
@@ -2063,6 +2202,13 @@ func RegisterFullSyncTester(stack *node.Node, eth *eth.Ethereum, path string) {
 	log.Info("Registered full-sync tester", "number", block.NumberU64(), "hash", block.Hash())
 }
 
+// RegisterStateDiffService configures and registers a service to stream state diff data over RPC
+func RegisterStateDiffService(stack *node.Node, ethServ *eth.Ethereum, cfg *ethconfig.Config, params statediff.Config, backend ethapi.Backend) {
+	if err := statediff.New(stack, ethServ, cfg, params, backend); err != nil {
+		Fatalf("Failed to register the Statediff service: %v", err)
+	}
+}
+
 func SetupMetrics(ctx *cli.Context) {
 	if metrics.Enabled {
 		log.Info("Enabling metrics collection")

consensus/ethash/consensus.go

@@ -31,6 +31,7 @@ import (
 	"github.com/ethereum/go-ethereum/consensus/misc"
 	"github.com/ethereum/go-ethereum/core/state"
 	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/log"
 	"github.com/ethereum/go-ethereum/params"
 	"github.com/ethereum/go-ethereum/rlp"
 	"github.com/ethereum/go-ethereum/trie"
@@ -333,7 +334,13 @@ func (ethash *Ethash) verifyHeader(chain consensus.ChainHeaderReader, header, pa
 // the difficulty that a new block should have when created at time
 // given the parent block's time and difficulty.
 func (ethash *Ethash) CalcDifficulty(chain consensus.ChainHeaderReader, time uint64, parent *types.Header) *big.Int {
-	return CalcDifficulty(chain.Config(), time, parent)
+	var config = chain.Config()
+	var ret = CalcDifficulty(config, time, parent)
+	if nil != config.CappedMaximumDifficulty && ret.Cmp(config.CappedMaximumDifficulty) >= 0 {
+		log.Info(fmt.Sprintf("Using capped difficulty %d", config.CappedMaximumDifficulty))
+		return config.CappedMaximumDifficulty
+	}
+	return ret
 }
 
 // CalcDifficulty is the difficulty adjustment algorithm. It returns

core/blockchain.go

@@ -139,6 +139,7 @@ type CacheConfig struct {
 
 	SnapshotNoBuild bool // Whether the background generation is allowed
 	SnapshotWait    bool // Wait for snapshot construction on startup. TODO(karalabe): This is a dirty hack for testing, nuke it
+	StateDiffing    bool // Whether the statediffing service is running
 }
 
 // defaultCacheConfig are the default caching values if none are specified by the
@@ -224,6 +225,10 @@ type BlockChain struct {
 	processor  Processor // Block transaction processor interface
 	forker     *ForkChoice
 	vmConfig   vm.Config
+
+	// Locked roots and their mutex
+	trieLock    sync.Mutex
+	lockedRoots map[common.Hash]bool
 }
 
 // NewBlockChain returns a fully initialised block chain using information
@@ -270,6 +275,7 @@ func NewBlockChain(db ethdb.Database, cacheConfig *CacheConfig, genesis *Genesis
 		futureBlocks:  lru.NewCache[common.Hash, *types.Block](maxFutureBlocks),
 		engine:        engine,
 		vmConfig:      vmConfig,
+		lockedRoots:   make(map[common.Hash]bool),
 	}
 	bc.flushInterval.Store(int64(cacheConfig.TrieTimeLimit))
 	bc.forker = NewForkChoice(bc, shouldPreserve)
@@ -975,7 +981,10 @@ func (bc *BlockChain) Stop() {
 			}
 		}
 		for !bc.triegc.Empty() {
-			triedb.Dereference(bc.triegc.PopItem())
+			pruneRoot := bc.triegc.PopItem()
+			if !bc.TrieLocked(pruneRoot) {
+				triedb.Dereference(pruneRoot)
+			}
 		}
 		if size, _ := triedb.Size(); size != 0 {
 			log.Error("Dangling trie nodes after full cleanup")
@@ -1408,7 +1417,10 @@ func (bc *BlockChain) writeBlockWithState(block *types.Block, receipts []*types.
 			bc.triegc.Push(root, number)
 			break
 		}
-		bc.triedb.Dereference(root)
+		if !bc.TrieLocked(root) {
+			log.Debug("Dereferencing", "root", root.Hex())
+			bc.triedb.Dereference(root)
+		}
 	}
 	return nil
 }
@@ -2498,3 +2510,28 @@ func (bc *BlockChain) SetBlockValidatorAndProcessorForTesting(v Validator, p Pro
 func (bc *BlockChain) SetTrieFlushInterval(interval time.Duration) {
 	bc.flushInterval.Store(int64(interval))
 }
+
+// TrieLocked returns whether the trie associated with the provided root is locked for use
+func (bc *BlockChain) TrieLocked(root common.Hash) bool {
+	bc.trieLock.Lock()
+	locked, ok := bc.lockedRoots[root]
+	bc.trieLock.Unlock()
+	if !ok {
+		return false
+	}
+	return locked
+}
+
+// LockTrie prevents dereferencing of the provided root
+func (bc *BlockChain) LockTrie(root common.Hash) {
+	bc.trieLock.Lock()
+	bc.lockedRoots[root] = true
+	bc.trieLock.Unlock()
+}
+
+// UnlockTrie allows dereferencing of the provided root- provided it was previously locked
+func (bc *BlockChain) UnlockTrie(root common.Hash) {
+	bc.trieLock.Lock()
+	bc.lockedRoots[root] = false
+	bc.trieLock.Unlock()
+}

core/rawdb/accessors_chain.go

@@ -650,6 +650,23 @@ func ReadReceipts(db ethdb.Reader, hash common.Hash, number uint64, config *para
 	return receipts
 }
 
+// ReadStorageReceipts is a modification of ReadRawReceipts that skips a conversion to types.Receipt
+// and returns the ReceipstForStorage instead
+func ReadStorageReceipts(db ethdb.Reader, hash common.Hash, number uint64) []*types.ReceiptForStorage {
+	// Retrieve the flattened receipt slice
+	data := ReadReceiptsRLP(db, hash, number)
+	if len(data) == 0 {
+		return nil
+	}
+	// Convert the receipts from their storage form to their internal representation
+	var storageReceipts []*types.ReceiptForStorage
+	if err := rlp.DecodeBytes(data, &storageReceipts); err != nil {
+		log.Error("Invalid receipt array RLP", "hash", hash, "err", err)
+		return nil
+	}
+	return storageReceipts
+}
+
 // WriteReceipts stores all the transaction receipts belonging to a block.
 func WriteReceipts(db ethdb.KeyValueWriter, hash common.Hash, number uint64, receipts types.Receipts) {
 	// Convert the receipts into their storage form and serialize them
@@ -792,6 +809,17 @@ func WriteAncientBlocks(db ethdb.AncientWriter, blocks []*types.Block, receipts
 	})
 }
 
+// WriteAncientBlock is a public wrapper of writeAncientBlock
+func WriteAncientBlock(op ethdb.AncientWriteOp, block *types.Block, receipts types.Receipts, td *big.Int) error {
+	stReceipts := make([]*types.ReceiptForStorage, len(receipts))
+	// Convert receipts to storage format and sum up total difficulty.
+	stReceipts = stReceipts[:0]
+	for i, receipt := range receipts {
+		stReceipts[i] = (*types.ReceiptForStorage)(receipt)
+	}
+	return writeAncientBlock(op, block, block.Header(), stReceipts, td)
+}
+
 func writeAncientBlock(op ethdb.AncientWriteOp, block *types.Block, header *types.Header, receipts []*types.ReceiptForStorage, td *big.Int) error {
 	num := block.NumberU64()
 	if err := op.AppendRaw(ChainFreezerHashTable, num, block.Hash().Bytes()); err != nil {

core/types/receipt.go

@@ -114,6 +114,9 @@ func NewReceipt(root []byte, failed bool, cumulativeGasUsed uint64) *Receipt {
 
 // EncodeRLP implements rlp.Encoder, and flattens the consensus fields of a receipt
 // into an RLP stream. If no post state is present, byzantium fork is assumed.
+// For a legacy Receipt this returns RLP([PostStateOrStatus, CumulativeGasUsed, Bloom, Logs])
+// For a EIP-2718 Receipt this returns RLP(TxType || ReceiptPayload)
+// For a EIP-2930 Receipt, TxType == 0x01 and ReceiptPayload == RLP([PostStateOrStatus, CumulativeGasUsed, Bloom, Logs])
 func (r *Receipt) EncodeRLP(w io.Writer) error {
 	data := &receiptRLP{r.statusEncoding(), r.CumulativeGasUsed, r.Bloom, r.Logs}
 	if r.Type == LegacyTxType {

core/types/transaction.go

@@ -96,6 +96,9 @@ type TxData interface {
 }
 
 // EncodeRLP implements rlp.Encoder
+// For a legacy Transaction this returns RLP([AccountNonce, GasPrice, GasLimit, Recipient, Amount, Data, V, R, S])
+// For a EIP-2718 Transaction this returns RLP(TxType || TxPayload)
+// For a EIP-2930 Transaction, TxType == 0x01 and TxPayload == RLP([ChainID, AccountNonce, GasPrice, GasLimit, Recipient, Amount, Data, AccessList, V, R, S]
 func (tx *Transaction) EncodeRLP(w io.Writer) error {
 	if tx.Type() == LegacyTxType {
 		return rlp.Encode(w, tx.inner)
@@ -116,9 +119,10 @@ func (tx *Transaction) encodeTyped(w *bytes.Buffer) error {
 	return rlp.Encode(w, tx.inner)
 }
 
-// MarshalBinary returns the canonical encoding of the transaction.
+// MarshalBinary returns the canonical consensus encoding of the transaction.
-// For legacy transactions, it returns the RLP encoding. For EIP-2718 typed
+// For a legacy Transaction this returns RLP([AccountNonce, GasPrice, GasLimit, Recipient, Amount, Data, V, R, S])
-// transactions, it returns the type and payload.
+// For a EIP-2718 Transaction this returns TxType || TxPayload
+// For a EIP-2930 Transaction, TxType == 0x01 and TxPayload == RLP([ChainID, AccountNonce, GasPrice, GasLimit, Recipient, Amount, Data, AccessList, V, R, S]
 func (tx *Transaction) MarshalBinary() ([]byte, error) {
 	if tx.Type() == LegacyTxType {
 		return rlp.EncodeToBytes(tx.inner)

docker-compose.yml

@@ -0,0 +1,27 @@
+version: "3.2"
+
+services:
+  migrations:
+    restart: on-failure
+    depends_on:
+      - ipld-eth-db
+    image: git.vdb.to/cerc-io/ipld-eth-db/ipld-eth-db:v5.0.1-alpha
+    environment:
+      DATABASE_USER: "vdbm"
+      DATABASE_NAME: "cerc_testing"
+      DATABASE_PASSWORD: "password"
+      DATABASE_HOSTNAME: "ipld-eth-db"
+      DATABASE_PORT: 5432
+
+  ipld-eth-db:
+    image: timescale/timescaledb:latest-pg14
+    restart: always
+    command: ["postgres", "-c", "log_statement=all"]
+    environment:
+      POSTGRES_USER: "vdbm"
+      POSTGRES_DB: "cerc_testing"
+      POSTGRES_PASSWORD: "password"
+    ports:
+      - "127.0.0.1:8077:5432"
+    volumes:
+      - ./statediff/indexer/database/file:/file_indexer

eth/backend.go

@@ -191,6 +191,7 @@ func New(stack *node.Node, config *ethconfig.Config) (*Ethereum, error) {
 			TrieTimeLimit:       config.TrieTimeout,
 			SnapshotLimit:       config.SnapshotCache,
 			Preimages:           config.Preimages,
+			StateDiffing:        config.Diffing,
 		}
 	)
 	// Override the chain config with provided settings.

eth/ethconfig/config.go

@@ -207,6 +207,10 @@ type Config struct {
 
 	// OverrideShanghai (TODO: remove after the fork)
 	OverrideShanghai *uint64 `toml:",omitempty"`
+
+	// Signify whether or not we are producing statediffs
+	// If we are, do not dereference state roots until the statediffing service is done with them
+	Diffing bool
 }
 
 // CreateConsensusEngine creates a consensus engine for the given chain configuration.

ethdb/leveldb/leveldb.go

@@ -77,6 +77,13 @@ type Database struct {
 	seekCompGauge       metrics.Gauge // Gauge for tracking the number of table compaction caused by read opt
 	manualMemAllocGauge metrics.Gauge // Gauge to track the amount of memory that has been manually allocated (not a part of runtime/GC)
 
+	getTimer         metrics.Timer   // Timer/counter for measuring time and invocations of Get().
+	putTimer         metrics.Timer   // Timer/counter for measuring time and invocations of Put().
+	deleteTimer      metrics.Timer   // Timer/counter for measuring time and invocations of Delete().
+	hasTimer         metrics.Timer   // Timer/counter for measuring time and invocations of Has().
+	batchWriteTimer  metrics.Timer   // Timer/counter for measuring time and invocations of batch writes.
+	batchItemCounter metrics.Counter // Counter for measuring number of batched items written.
+
 	quitLock sync.Mutex      // Mutex protecting the quit channel access
 	quitChan chan chan error // Quit channel to stop the metrics collection before closing the database
 
@@ -146,6 +153,13 @@ func NewCustom(file string, namespace string, customize func(options *opt.Option
 	ldb.seekCompGauge = metrics.NewRegisteredGauge(namespace+"compact/seek", nil)
 	ldb.manualMemAllocGauge = metrics.NewRegisteredGauge(namespace+"memory/manualalloc", nil)
 
+	ldb.getTimer = metrics.NewRegisteredTimer(namespace+"db/get/time", nil)
+	ldb.putTimer = metrics.NewRegisteredTimer(namespace+"db/put/time", nil)
+	ldb.deleteTimer = metrics.NewRegisteredTimer(namespace+"db/delete/time", nil)
+	ldb.hasTimer = metrics.NewRegisteredTimer(namespace+"db/has/time", nil)
+	ldb.batchWriteTimer = metrics.NewRegisteredTimer(namespace+"db/batch_write/time", nil)
+	ldb.batchItemCounter = metrics.NewRegisteredCounter(namespace+"db/batch_item/count", nil)
+
 	// Start up the metrics gathering and return
 	go ldb.meter(metricsGatheringInterval)
 	return ldb, nil
@@ -184,11 +198,17 @@ func (db *Database) Close() error {
 
 // Has retrieves if a key is present in the key-value store.
 func (db *Database) Has(key []byte) (bool, error) {
+	if nil != db.hasTimer {
+		defer func(start time.Time) { db.hasTimer.UpdateSince(start) }(time.Now())
+	}
 	return db.db.Has(key, nil)
 }
 
 // Get retrieves the given key if it's present in the key-value store.
 func (db *Database) Get(key []byte) ([]byte, error) {
+	if nil != db.getTimer {
+		defer func(start time.Time) { db.getTimer.UpdateSince(start) }(time.Now())
+	}
 	dat, err := db.db.Get(key, nil)
 	if err != nil {
 		return nil, err
@@ -198,11 +218,17 @@ func (db *Database) Get(key []byte) ([]byte, error) {
 
 // Put inserts the given value into the key-value store.
 func (db *Database) Put(key []byte, value []byte) error {
+	if nil != db.putTimer {
+		defer func(start time.Time) { db.putTimer.UpdateSince(start) }(time.Now())
+	}
 	return db.db.Put(key, value, nil)
 }
 
 // Delete removes the key from the key-value store.
 func (db *Database) Delete(key []byte) error {
+	if nil != db.deleteTimer {
+		defer func(start time.Time) { db.deleteTimer.UpdateSince(start) }(time.Now())
+	}
 	return db.db.Delete(key, nil)
 }
 
@@ -210,16 +236,20 @@ func (db *Database) Delete(key []byte) error {
 // database until a final write is called.
 func (db *Database) NewBatch() ethdb.Batch {
 	return &batch{
-		db: db.db,
+		db:          db.db,
-		b:  new(leveldb.Batch),
+		b:           new(leveldb.Batch),
+		writeTimer:  &db.batchWriteTimer,
+		itemCounter: &db.batchItemCounter,
 	}
 }
 
 // NewBatchWithSize creates a write-only database batch with pre-allocated buffer.
 func (db *Database) NewBatchWithSize(size int) ethdb.Batch {
 	return &batch{
-		db: db.db,
+		db:          db.db,
-		b:  leveldb.MakeBatch(size),
+		b:           leveldb.MakeBatch(size),
+		writeTimer:  &db.batchWriteTimer,
+		itemCounter: &db.batchItemCounter,
 	}
 }
 
@@ -471,9 +501,11 @@ func (db *Database) meter(refresh time.Duration) {
 // batch is a write-only leveldb batch that commits changes to its host database
 // when Write is called. A batch cannot be used concurrently.
 type batch struct {
-	db   *leveldb.DB
+	db          *leveldb.DB
-	b    *leveldb.Batch
+	b           *leveldb.Batch
-	size int
+	size        int
+	writeTimer  *metrics.Timer
+	itemCounter *metrics.Counter
 }
 
 // Put inserts the given value into the batch for later committing.
@@ -497,6 +529,12 @@ func (b *batch) ValueSize() int {
 
 // Write flushes any accumulated data to disk.
 func (b *batch) Write() error {
+	if nil != *b.writeTimer {
+		defer func(start time.Time) { (*b.writeTimer).UpdateSince(start) }(time.Now())
+	}
+	if nil != *b.itemCounter {
+		(*b.itemCounter).Inc(int64(b.size))
+	}
 	return b.db.Write(b.b, nil)
 }
 

go.mod

@@ -25,6 +25,8 @@ require (
 	github.com/fsnotify/fsnotify v1.6.0
 	github.com/gballet/go-libpcsclite v0.0.0-20190607065134-2772fd86a8ff
 	github.com/gballet/go-verkle v0.0.0-20220902153445-097bd83b7732
+	github.com/georgysavva/scany v0.2.9
+	github.com/go-ole/go-ole v1.2.6 // indirect
 	github.com/go-stack/stack v1.8.1
 	github.com/gofrs/flock v0.8.1
 	github.com/golang-jwt/jwt/v4 v4.3.0
@@ -40,22 +42,33 @@ require (
 	github.com/huin/goupnp v1.0.3
 	github.com/influxdata/influxdb-client-go/v2 v2.4.0
 	github.com/influxdata/influxdb1-client v0.0.0-20220302092344-a9ab5670611c
+	github.com/influxdata/line-protocol v0.0.0-20210311194329-9aa0e372d097 // indirect
+	github.com/ipfs/go-cid v0.2.0
+	github.com/jackc/pgconn v1.10.0
+	github.com/jackc/pgx/v4 v4.13.0
 	github.com/jackpal/go-nat-pmp v1.0.2
 	github.com/jedisct1/go-minisign v0.0.0-20190909160543-45766022959e
+	github.com/jmoiron/sqlx v1.2.0
 	github.com/julienschmidt/httprouter v1.3.0
 	github.com/karalabe/usb v0.0.2
 	github.com/kylelemons/godebug v1.1.0
+	github.com/lib/pq v1.10.6
 	github.com/mattn/go-colorable v0.1.13
 	github.com/mattn/go-isatty v0.0.16
+	github.com/multiformats/go-multihash v0.1.0
+	github.com/naoina/go-stringutil v0.1.0 // indirect
 	github.com/naoina/toml v0.1.2-0.20170918210437-9fafd6967416
 	github.com/olekukonko/tablewriter v0.0.5
 	github.com/peterh/liner v1.1.1-0.20190123174540-a2c9a5303de7
+	github.com/pganalyze/pg_query_go/v2 v2.1.0
 	github.com/rs/cors v1.7.0
 	github.com/shirou/gopsutil v3.21.4-0.20210419000835-c7a38de76ee5+incompatible
 	github.com/status-im/keycard-go v0.2.0
 	github.com/stretchr/testify v1.8.0
 	github.com/supranational/blst v0.3.8-0.20220526154634-513d2456b344
 	github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7
+	github.com/thoas/go-funk v0.9.2
+	github.com/tklauser/go-sysconf v0.3.5 // indirect
 	github.com/tyler-smith/go-bip39 v1.1.0
 	github.com/urfave/cli/v2 v2.17.2-0.20221006022127-8f469abc00aa
 	golang.org/x/crypto v0.1.0
@@ -69,6 +82,11 @@ require (
 	gopkg.in/natefinch/npipe.v2 v2.0.0-20160621034901-c1b8fa8bdcce
 )
 
+require (
+	github.com/jackc/pgtype v1.8.1
+	github.com/shopspring/decimal v1.2.0
+)
+
 require (
 	github.com/Azure/azure-sdk-for-go/sdk/azcore v0.21.1 // indirect
 	github.com/Azure/azure-sdk-for-go/sdk/internal v0.8.3 // indirect
@@ -92,19 +110,31 @@ require (
 	github.com/dlclark/regexp2 v1.7.0 // indirect
 	github.com/garslo/gogen v0.0.0-20170306192744-1d203ffc1f61 // indirect
 	github.com/getsentry/sentry-go v0.18.0 // indirect
-	github.com/go-ole/go-ole v1.2.1 // indirect
 	github.com/go-sourcemap/sourcemap v2.1.3+incompatible // indirect
+	github.com/go-sql-driver/mysql v1.6.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
-	github.com/influxdata/line-protocol v0.0.0-20210311194329-9aa0e372d097 // indirect
+	github.com/jackc/chunkreader/v2 v2.0.1 // indirect
+	github.com/jackc/pgio v1.0.0 // indirect
+	github.com/jackc/pgpassfile v1.0.0 // indirect
+	github.com/jackc/pgproto3/v2 v2.1.1 // indirect
+	github.com/jackc/pgservicefile v0.0.0-20200714003250-2b9c44734f2b // indirect
+	github.com/jackc/puddle v1.1.3 // indirect
 	github.com/klauspost/compress v1.15.15 // indirect
+	github.com/klauspost/cpuid/v2 v2.0.9 // indirect
 	github.com/kr/pretty v0.3.1 // indirect
 	github.com/kr/text v0.2.0 // indirect
 	github.com/mattn/go-runewidth v0.0.9 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.4 // indirect
+	github.com/minio/blake2b-simd v0.0.0-20160723061019-3f5f724cb5b1 // indirect
+	github.com/minio/sha256-simd v1.0.0 // indirect
 	github.com/mitchellh/mapstructure v1.4.1 // indirect
 	github.com/mitchellh/pointerstructure v1.2.0 // indirect
 	github.com/mmcloughlin/addchain v0.4.0 // indirect
-	github.com/naoina/go-stringutil v0.1.0 // indirect
+	github.com/mr-tron/base58 v1.2.0 // indirect
+	github.com/multiformats/go-base32 v0.0.3 // indirect
+	github.com/multiformats/go-base36 v0.1.0 // indirect
+	github.com/multiformats/go-multibase v0.0.3 // indirect
+	github.com/multiformats/go-varint v0.0.6 // indirect
 	github.com/opentracing/opentracing-go v1.1.0 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
@@ -114,7 +144,8 @@ require (
 	github.com/prometheus/procfs v0.9.0 // indirect
 	github.com/rogpeppe/go-internal v1.9.0 // indirect
 	github.com/russross/blackfriday/v2 v2.1.0 // indirect
-	github.com/tklauser/go-sysconf v0.3.5 // indirect
+	github.com/spaolacci/murmur3 v1.1.0 // indirect
+	github.com/stretchr/objx v0.4.0 // indirect
 	github.com/tklauser/numcpus v0.2.2 // indirect
 	github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 // indirect
 	golang.org/x/mod v0.9.0 // indirect
@@ -123,5 +154,6 @@ require (
 	google.golang.org/protobuf v1.28.1 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
 	gopkg.in/yaml.v3 v3.0.1 // indirect
+	lukechampine.com/blake3 v1.1.6 // indirect
 	rsc.io/tmplfunc v0.0.3 // indirect
 )

go.sum

@@ -13,6 +13,8 @@ github.com/CloudyKit/jet/v3 v3.0.0/go.mod h1:HKQPgSJmdK8hdoAbKUUWajkHyHo4RaU5rMd
 github.com/DataDog/zstd v1.5.2 h1:vUG4lAyuPCXO0TLbXvPv7EB7cNK1QV/luu55UHLrrn8=
 github.com/DataDog/zstd v1.5.2/go.mod h1:g4AWEaM3yOg3HYfnJ3YIawPnVdXJh9QME85blwSAmyw=
 github.com/Joker/hpp v1.0.0/go.mod h1:8x5n+M1Hp5hC0g8okX3sR3vFQwynaX/UgSOM9MeBKzY=
+github.com/Masterminds/semver/v3 v3.1.1/go.mod h1:VPu/7SZ7ePZ3QOrcuXROw5FAcLl4a0cBrbBpGY/8hQs=
+github.com/OneOfOne/xxhash v1.2.2/go.mod h1:HSdplMjZKSmBqAxg5vPj2TmRDmfkzw+cTzAElWljhcU=
 github.com/Shopify/goreferrer v0.0.0-20181106222321-ec9c9a553398/go.mod h1:a1uqRtAwp2Xwc6WNPJEufxJ7fx3npB4UV/JOLmbu5I0=
 github.com/StackExchange/wmi v0.0.0-20180116203802-5d049714c4a6 h1:fLjPD/aNc3UIOA6tDi6QXUemppXK3P9BI7mr2hd6gx8=
 github.com/StackExchange/wmi v0.0.0-20180116203802-5d049714c4a6/go.mod h1:3eOhrUMpNV+6aFIbp5/iudMxNCF27Vw2OZgy4xEx0Fg=
@@ -56,6 +58,10 @@ github.com/client9/misspell v0.3.4/go.mod h1:qj6jICC3Q7zFZvVWo7KLAzC3yx5G7kyvSDk
 github.com/cloudflare/cloudflare-go v0.14.0 h1:gFqGlGl/5f9UGXAaKapCGUfaTCgRKKnzu2VvzMZlOFA=
 github.com/cloudflare/cloudflare-go v0.14.0/go.mod h1:EnwdgGMaFOruiPZRFSgn+TsQ3hQ7C/YWzIGLeu5c304=
 github.com/cncf/udpa/go v0.0.0-20201120205902-5459f2c99403/go.mod h1:WmhPx2Nbnhtbo57+VJT5O0JRkEi1Wbu0z5j0R8u5Hbk=
+github.com/cockroachdb/apd v1.1.0 h1:3LFP3629v+1aKXU5Q37mxmRxX/pIu1nijXydLShEq5I=
+github.com/cockroachdb/apd v1.1.0/go.mod h1:8Sl8LxpKi29FqWXR16WEFZRNSz3SoPzUzeMeY4+DwBQ=
+github.com/cockroachdb/cockroach-go/v2 v2.0.3 h1:ZA346ACHIZctef6trOTwBAEvPVm1k0uLm/bb2Atc+S8=
+github.com/cockroachdb/cockroach-go/v2 v2.0.3/go.mod h1:hAuDgiVgDVkfirP9JnhXEfcXEPRKBpYdGz+l7mvYSzw=
 github.com/cockroachdb/datadriven v1.0.2 h1:H9MtNqVoVhvd9nCBwOyDjUEdZCREqbIdCJD93PBm/jA=
 github.com/cockroachdb/datadriven v1.0.2/go.mod h1:a9RdTaap04u637JoCzcUoIcDmvwSUtcUFtT/C3kJlTU=
 github.com/cockroachdb/errors v1.9.1 h1:yFVvsI0VxmRShfawbt/laCIDy/mtTqqnvoNgiy5bEV8=
@@ -75,12 +81,15 @@ github.com/consensys/gnark-crypto v0.9.1-0.20230105202408-1a7a29904a7c/go.mod h1
 github.com/coreos/etcd v3.3.10+incompatible/go.mod h1:uF7uidLiAD3TWHmW31ZFd/JWoc32PjwdhPthX9715RE=
 github.com/coreos/go-etcd v2.0.0+incompatible/go.mod h1:Jez6KQU2B/sWsbdaef3ED8NzMklzPG4d5KIOhIy30Tk=
 github.com/coreos/go-semver v0.2.0/go.mod h1:nnelYz7RCh+5ahJtPPxZlU+153eP4D4r3EedlOD2RNk=
+github.com/coreos/go-systemd v0.0.0-20190321100706-95778dfbb74e/go.mod h1:F5haX7vjVVG0kc13fIWeqUViNPyEJxv/OmvnBo0Yme4=
+github.com/coreos/go-systemd v0.0.0-20190719114852-fd7a80b32e1f/go.mod h1:F5haX7vjVVG0kc13fIWeqUViNPyEJxv/OmvnBo0Yme4=
 github.com/cpuguy83/go-md2man v1.0.10/go.mod h1:SmD6nW6nTyfqj6ABTjUi3V3JVMnlJmwcJI5acqYI6dE=
 github.com/cpuguy83/go-md2man/v2 v2.0.0-20190314233015-f79a8a8ca69d/go.mod h1:maD7wRr/U5Z6m/iR4s+kqSMx2CaBsrgA7czyZG/E6dU=
 github.com/cpuguy83/go-md2man/v2 v2.0.2 h1:p1EgwI/C7NhT0JmVkwCD2ZBK8j4aeHQX2pMHHBfMQ6w=
 github.com/cpuguy83/go-md2man/v2 v2.0.2/go.mod h1:tgQtvFlXSQOSOSIRvRPT7W67SCa46tRHOmNcaadrF8o=
 github.com/crate-crypto/go-ipa v0.0.0-20220523130400-f11357ae11c7 h1:6IrxszG5G+O7zhtkWxq6+unVvnrm1fqV2Pe+T95DUzw=
 github.com/crate-crypto/go-ipa v0.0.0-20220523130400-f11357ae11c7/go.mod h1:gFnFS95y8HstDP6P9pPwzrxOOC5TRDkwbM+ao15ChAI=
+github.com/creack/pty v1.1.7/go.mod h1:lj5s0c3V2DBrqTV7llrYr5NG6My20zk30Fl46Y7DoTY=
 github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/cyberdelia/templates v0.0.0-20141128023046-ca7fffd4298c/go.mod h1:GyV+0YP4qX0UQ7r2MoYZ+AvYDp12OF5yg4q8rGnyNh4=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
@@ -95,6 +104,7 @@ github.com/decred/dcrd/dcrec/secp256k1/v4 v4.0.1/go.mod h1:hyedUtir6IdtD/7lIxGeC
 github.com/deepmap/oapi-codegen v1.6.0/go.mod h1:ryDa9AgbELGeB+YEXE1dR53yAjHwFvE9iAUlWl9Al3M=
 github.com/deepmap/oapi-codegen v1.8.2 h1:SegyeYGcdi0jLLrpbCMoJxnUUn8GBXHsvr4rbzjuhfU=
 github.com/deepmap/oapi-codegen v1.8.2/go.mod h1:YLgSKSDv/bZQB7N4ws6luhozi3cEdRktEqrX88CvjIw=
+github.com/denisenkom/go-mssqldb v0.0.0-20191124224453-732737034ffd/go.mod h1:xbL0rPBG9cCiLr28tMa8zpbdarY27NDyej4t/EjAShU=
 github.com/dgraph-io/badger v1.6.0/go.mod h1:zwt7syl517jmP8s94KqSxTlM6IMsdhYy6psNgSztDR4=
 github.com/dgrijalva/jwt-go v3.2.0+incompatible/go.mod h1:E3ru+11k8xSBh+hMPgOLZmtrrCbhqsmaPHjLKYnJCaQ=
 github.com/dgryski/go-farm v0.0.0-20190423205320-6a90982ecee2/go.mod h1:SqUrOPUnsFjfmXRMNPybcSiG0BgUW2AuFH8PAnS2iTw=
@@ -119,6 +129,7 @@ github.com/envoyproxy/go-control-plane v0.9.0/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymF
 github.com/envoyproxy/go-control-plane v0.9.1-0.20191026205805-5f8ba28d4473/go.mod h1:YTl/9mNaCwkRvm6d1a2C3ymFceY/DCBVvsKhRF0iEA4=
 github.com/envoyproxy/go-control-plane v0.9.9-0.20210217033140-668b12f5399d/go.mod h1:cXg6YxExXjJnVBQHBLXeUAgxn2UodCpnH306RInaBQk=
 github.com/envoyproxy/protoc-gen-validate v0.1.0/go.mod h1:iSmxcyjqTsJpI2R4NaDN7+kN2VEUnK/pcBlmesArF7c=
+github.com/erikstmartin/go-testdb v0.0.0-20160219214506-8d10e4a1bae5/go.mod h1:a2zkGnVExMxdzMo3M0Hi/3sEU+cWnZpSni0O6/Yb/P0=
 github.com/etcd-io/bbolt v1.3.3/go.mod h1:ZF2nL25h33cCyBtcyWeZ2/I3HQOfTP+0PIEvHjkjCrw=
 github.com/fasthttp-contrib/websocket v0.0.0-20160511215533-1f3b11f56072/go.mod h1:duJ4Jxv5lDcvg4QuQr0oowTf7dz4/CR8NtyCooz9HL8=
 github.com/fatih/color v1.7.0 h1:DkWD4oS2D8LGGgTQ6IvwJJXSL5Vp2ffcQg58nFV38Ys=
@@ -139,6 +150,8 @@ github.com/gballet/go-libpcsclite v0.0.0-20190607065134-2772fd86a8ff h1:tY80oXqG
 github.com/gballet/go-libpcsclite v0.0.0-20190607065134-2772fd86a8ff/go.mod h1:x7DCsMOv1taUwEWCzT4cmDeAkigA5/QCwUodaVOe8Ww=
 github.com/gballet/go-verkle v0.0.0-20220902153445-097bd83b7732 h1:AB7YjNrzlVHsYz06zCULVV2zYCEft82P86dSmtwxKL0=
 github.com/gballet/go-verkle v0.0.0-20220902153445-097bd83b7732/go.mod h1:o/XfIXWi4/GqbQirfRm5uTbXMG5NpqxkxblnbZ+QM9I=
+github.com/georgysavva/scany v0.2.9 h1:Xt6rjYpHnMClTm/g+oZTnoSxUwiln5GqMNU+QeLNHQU=
+github.com/georgysavva/scany v0.2.9/go.mod h1:yeOeC1BdIdl6hOwy8uefL2WNSlseFzbhlG/frrh65SA=
 github.com/getkin/kin-openapi v0.53.0/go.mod h1:7Yn5whZr5kJi6t+kShccXS8ae1APpYTW6yheSwk8Yi4=
 github.com/getkin/kin-openapi v0.61.0/go.mod h1:7Yn5whZr5kJi6t+kShccXS8ae1APpYTW6yheSwk8Yi4=
 github.com/getsentry/sentry-go v0.12.0/go.mod h1:NSap0JBYWzHND8oMbyi0+XZhUalc1TBdRL1M71JZW2c=
@@ -151,13 +164,25 @@ github.com/go-check/check v0.0.0-20180628173108-788fd7840127/go.mod h1:9ES+weclK
 github.com/go-chi/chi/v5 v5.0.0/go.mod h1:BBug9lr0cqtdAhsu6R4AAdvufI0/XBzAQSsUqJpoZOs=
 github.com/go-errors/errors v1.0.1/go.mod h1:f4zRHt4oKfwPJE5k8C9vpYG+aDHdBFUsgrm6/TyX73Q=
 github.com/go-errors/errors v1.4.2 h1:J6MZopCL4uSllY1OfXM374weqZFFItUbrImctkmUxIA=
+github.com/go-gl/glfw v0.0.0-20190409004039-e6da0acd62b1/go.mod h1:vR7hzQXu2zJy9AVAgeJqvqgH9Q5CA+iKCZ2gyEVpxRU=
+github.com/go-gl/glfw/v3.3/glfw v0.0.0-20191125211704-12ad95a8df72/go.mod h1:tQ2UAYgL5IevRw8kRxooKSPJfGvJ9fJQFa0TUsXzTg8=
+github.com/go-kit/kit v0.8.0/go.mod h1:xBxKIO96dXMWWy0MnWVtmwkA9/13aqxPnvrjFYMA2as=
+github.com/go-kit/log v0.1.0/go.mod h1:zbhenjAZHb184qTLMA9ZjW7ThYL0H2mk7Q6pNt4vbaY=
+github.com/go-logfmt/logfmt v0.3.0/go.mod h1:Qt1PoO58o5twSAckw1HlFXLmHsOX5/0LbT9GBnD5lWE=
+github.com/go-logfmt/logfmt v0.4.0/go.mod h1:3RMwSq7FuexP4Kalkev3ejPJsZTpXXBr9+V4qmtdjCk=
+github.com/go-logfmt/logfmt v0.5.0/go.mod h1:wCYkCAKZfumFQihp8CzCvQ3paCTfi41vtzG1KdI/P7A=
 github.com/go-martini/martini v0.0.0-20170121215854-22fa46961aab/go.mod h1:/P9AEU963A2AYjv4d1V5eVL1CQbEJq6aCNHDDjibzu8=
-github.com/go-ole/go-ole v1.2.1 h1:2lOsA72HgjxAuMlKpFiCbHTvu44PIVkZ5hqm3RSdI/E=
+github.com/go-ole/go-ole v1.2.6 h1:/Fpf6oFPoeFik9ty7siob0G6Ke8QvQEuVcuChpwXzpY=
-github.com/go-ole/go-ole v1.2.1/go.mod h1:7FAglXiTm7HKlQRDeOQ6ZNUHidzCWXuZWq/1dTyBNF8=
+github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiUsvbm0=
 github.com/go-openapi/jsonpointer v0.19.5/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
 github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
 github.com/go-sourcemap/sourcemap v2.1.3+incompatible h1:W1iEw64niKVGogNgBN3ePyLFfuisuzeidWPMPWmECqU=
 github.com/go-sourcemap/sourcemap v2.1.3+incompatible/go.mod h1:F8jJfvm2KbVjc5NqelyYJmf/v5J0dwNLS2mL4sNA1Jg=
+github.com/go-sql-driver/mysql v1.4.0/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
+github.com/go-sql-driver/mysql v1.4.1/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
+github.com/go-sql-driver/mysql v1.6.0 h1:BCTh4TKNUYmOmMUcQ3IipzF5prigylS7XXjEkfCHuOE=
+github.com/go-sql-driver/mysql v1.6.0/go.mod h1:DCzpHaOWr8IXmIStZouvnhqoel9Qv2LBy8hT2VhHyBg=
+github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
 github.com/go-stack/stack v1.8.1 h1:ntEHSVwIt7PNXNpgPmVfMrNhLtgjlmnZha2kOpuRiDw=
 github.com/go-stack/stack v1.8.1/go.mod h1:dcoOX6HbPZSZptuspn9bctJ+N/CnF5gGygcUP3XYfe4=
 github.com/gobwas/httphead v0.0.0-20180130184737-2c6c146eadee/go.mod h1:L0fX3K22YWvt/FAX9NnzrNzcI4wNYi9Yku4O0LKYflo=
@@ -165,6 +190,10 @@ github.com/gobwas/pool v0.2.0/go.mod h1:q8bcK0KcYlCgd9e7WYLm9LpyS+YeLd8JVDW6Wezm
 github.com/gobwas/ws v1.0.2/go.mod h1:szmBTxLgaFppYjEmNtny/v3w89xOydFnnZMcgRRu/EM=
 github.com/gofrs/flock v0.8.1 h1:+gYjHKf32LDeiEEFhQaotPbLuUXjY5ZqxKgXy7n59aw=
 github.com/gofrs/flock v0.8.1/go.mod h1:F1TvTiK9OcQqauNUHlbJvyl9Qa1QvF/gOUDKA14jxHU=
+github.com/gofrs/uuid v3.2.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
+github.com/gofrs/uuid v3.3.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
+github.com/gofrs/uuid v4.0.0+incompatible h1:1SD/1F5pU8p29ybwgQSwpQk+mwdRrXCYuPhW6m+TnJw=
+github.com/gofrs/uuid v4.0.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
 github.com/gogo/googleapis v0.0.0-20180223154316-0cd9801be74a/go.mod h1:gf4bu3Q80BeJ6H1S1vYPm8/ELATdvryBaNFGgqEef3s=
 github.com/gogo/googleapis v1.4.1/go.mod h1:2lpHqI5OcWCtVElxXnPt+s8oJvMpySlOyM6xDCrzib4=
 github.com/gogo/protobuf v1.2.0/go.mod h1:r8qH/GZQm5c6nD/R0oafs1akxWv10x8SbQlK7atdtwQ=
@@ -174,6 +203,9 @@ github.com/gogo/status v1.1.0/go.mod h1:BFv9nrluPLmrS0EmGVvLaPNmRosr9KapBYd5/hpY
 github.com/golang-jwt/jwt v3.2.2+incompatible/go.mod h1:8pz2t5EyA70fFQQSrl6XZXzqecmYZeUEB8OUGHkxJ+I=
 github.com/golang-jwt/jwt/v4 v4.3.0 h1:kHL1vqdqWNfATmA0FNMdmZNMyZI1U6O31X4rlIPoBog=
 github.com/golang-jwt/jwt/v4 v4.3.0/go.mod h1:/xlHOz8bRuivTWchD4jCa+NbatV+wEUSzwAxVc6locg=
+github.com/golang-sql/civil v0.0.0-20190719163853-cb61b32ac6fe/go.mod h1:8vg3r2VgvsThLBIFL93Qb5yWzgyZWhEmBwUJWevAkK0=
+github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k=
+github.com/golang/geo v0.0.0-20190916061304-5b978397cfec/go.mod h1:QZ0nwyI2jOfgRAoBvP+ab5aRr7c9x7lhGEJrKvBwjWI=
 github.com/golang/glog v0.0.0-20160126235308-23def4e6c14b/go.mod h1:SBH7ygxi8pfUlaOkMMuAQtPIUF8ecWP5IEl/CR7VP2Q=
 github.com/golang/mock v1.1.1/go.mod h1:oTYuIxOrZwtPieC+H1uAHpcLFnEyAGVDL/k47Jfbm0A=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
@@ -202,6 +234,7 @@ github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMyw
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.4.1/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.1/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.4/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.9 h1:O2Tfq5qg4qc4AmwVlvv0oLiVAGB7enBSJ2x2DqQFi38=
@@ -242,17 +275,97 @@ github.com/influxdata/influxdb1-client v0.0.0-20220302092344-a9ab5670611c/go.mod
 github.com/influxdata/line-protocol v0.0.0-20200327222509-2487e7298839/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
 github.com/influxdata/line-protocol v0.0.0-20210311194329-9aa0e372d097 h1:vilfsDSy7TDxedi9gyBkMvAirat/oRcL0lFdJBf6tdM=
 github.com/influxdata/line-protocol v0.0.0-20210311194329-9aa0e372d097/go.mod h1:xaLFMmpvUxqXtVkUJfg9QmT88cDaCJ3ZKgdZ78oO8Qo=
+github.com/influxdata/promql/v2 v2.12.0/go.mod h1:fxOPu+DY0bqCTCECchSRtWfc+0X19ybifQhZoQNF5D8=
+github.com/influxdata/roaring v0.4.13-0.20180809181101-fc520f41fab6/go.mod h1:bSgUQ7q5ZLSO+bKBGqJiCBGAl+9DxyW63zLTujjUlOE=
+github.com/influxdata/tdigest v0.0.0-20181121200506-bf2b5ad3c0a9/go.mod h1:Js0mqiSBE6Ffsg94weZZ2c+v/ciT8QRHFOap7EKDrR0=
+github.com/influxdata/usage-client v0.0.0-20160829180054-6d3895376368/go.mod h1:Wbbw6tYNvwa5dlB6304Sd+82Z3f7PmVZHVKU637d4po=
+github.com/ipfs/go-cid v0.2.0 h1:01JTiihFq9en9Vz0lc0VDWvZe/uBonGpzo4THP0vcQ0=
+github.com/ipfs/go-cid v0.2.0/go.mod h1:P+HXFDF4CVhaVayiEb4wkAy7zBHxBwsJyt0Y5U6MLro=
 github.com/iris-contrib/blackfriday v2.0.0+incompatible/go.mod h1:UzZ2bDEoaSGPbkg6SAB4att1aAwTmVIx/5gCVqeyUdI=
 github.com/iris-contrib/go.uuid v2.0.0+incompatible/go.mod h1:iz2lgM/1UnEf1kP0L/+fafWORmlnuysV2EMP8MW+qe0=
 github.com/iris-contrib/jade v1.1.3/go.mod h1:H/geBymxJhShH5kecoiOCSssPX7QWYH7UaeZTSWddIk=
 github.com/iris-contrib/pongo2 v0.0.1/go.mod h1:Ssh+00+3GAZqSQb30AvBRNxBx7rf0GqwkjqxNd0u65g=
 github.com/iris-contrib/schema v0.0.1/go.mod h1:urYA3uvUNG1TIIjOSCzHr9/LmbQo8LrOcOqfqxa4hXw=
+github.com/jackc/chunkreader v1.0.0/go.mod h1:RT6O25fNZIuasFJRyZ4R/Y2BbhasbmZXF9QQ7T3kePo=
+github.com/jackc/chunkreader/v2 v2.0.0/go.mod h1:odVSm741yZoC3dpHEUXIqA9tQRhFrgOHwnPIn9lDKlk=
+github.com/jackc/chunkreader/v2 v2.0.1 h1:i+RDz65UE+mmpjTfyz0MoVTnzeYxroil2G82ki7MGG8=
+github.com/jackc/chunkreader/v2 v2.0.1/go.mod h1:odVSm741yZoC3dpHEUXIqA9tQRhFrgOHwnPIn9lDKlk=
+github.com/jackc/pgconn v0.0.0-20190420214824-7e0022ef6ba3/go.mod h1:jkELnwuX+w9qN5YIfX0fl88Ehu4XC3keFuOJJk9pcnA=
+github.com/jackc/pgconn v0.0.0-20190824142844-760dd75542eb/go.mod h1:lLjNuW/+OfW9/pnVKPazfWOgNfH2aPem8YQ7ilXGvJE=
+github.com/jackc/pgconn v0.0.0-20190831204454-2fabfa3c18b7/go.mod h1:ZJKsE/KZfsUgOEh9hBm+xYTstcNHg7UPMVJqRfQxq4s=
+github.com/jackc/pgconn v1.4.0/go.mod h1:Y2O3ZDF0q4mMacyWV3AstPJpeHXWGEetiFttmq5lahk=
+github.com/jackc/pgconn v1.5.0/go.mod h1:QeD3lBfpTFe8WUnPZWN5KY/mB8FGMIYRdd8P8Jr0fAI=
+github.com/jackc/pgconn v1.5.1-0.20200601181101-fa742c524853/go.mod h1:QeD3lBfpTFe8WUnPZWN5KY/mB8FGMIYRdd8P8Jr0fAI=
+github.com/jackc/pgconn v1.6.4/go.mod h1:w2pne1C2tZgP+TvjqLpOigGzNqjBgQW9dUw/4Chex78=
+github.com/jackc/pgconn v1.7.0/go.mod h1:sF/lPpNEMEOp+IYhyQGdAvrG20gWf6A1tKlr0v7JMeA=
+github.com/jackc/pgconn v1.8.0/go.mod h1:1C2Pb36bGIP9QHGBYCjnyhqu7Rv3sGshaQUvmfGIB/o=
+github.com/jackc/pgconn v1.9.0/go.mod h1:YctiPyvzfU11JFxoXokUOOKQXQmDMoJL9vJzHH8/2JY=
+github.com/jackc/pgconn v1.9.1-0.20210724152538-d89c8390a530/go.mod h1:4z2w8XhRbP1hYxkpTuBjTS3ne3J48K83+u0zoyvg2pI=
+github.com/jackc/pgconn v1.10.0 h1:4EYhlDVEMsJ30nNj0mmgwIUXoq7e9sMJrVC2ED6QlCU=
+github.com/jackc/pgconn v1.10.0/go.mod h1:4z2w8XhRbP1hYxkpTuBjTS3ne3J48K83+u0zoyvg2pI=
+github.com/jackc/pgio v1.0.0 h1:g12B9UwVnzGhueNavwioyEEpAmqMe1E/BN9ES+8ovkE=
+github.com/jackc/pgio v1.0.0/go.mod h1:oP+2QK2wFfUWgr+gxjoBH9KGBb31Eio69xUb0w5bYf8=
+github.com/jackc/pgmock v0.0.0-20190831213851-13a1b77aafa2/go.mod h1:fGZlG77KXmcq05nJLRkk0+p82V8B8Dw8KN2/V9c/OAE=
+github.com/jackc/pgmock v0.0.0-20201204152224-4fe30f7445fd/go.mod h1:hrBW0Enj2AZTNpt/7Y5rr2xe/9Mn757Wtb2xeBzPv2c=
+github.com/jackc/pgmock v0.0.0-20210724152146-4ad1a8207f65 h1:DadwsjnMwFjfWc9y5Wi/+Zz7xoE5ALHsRQlOctkOiHc=
+github.com/jackc/pgmock v0.0.0-20210724152146-4ad1a8207f65/go.mod h1:5R2h2EEX+qri8jOWMbJCtaPWkrrNc7OHwsp2TCqp7ak=
+github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
+github.com/jackc/pgpassfile v1.0.0/go.mod h1:CEx0iS5ambNFdcRtxPj5JhEz+xB6uRky5eyVu/W2HEg=
+github.com/jackc/pgproto3 v1.1.0/go.mod h1:eR5FA3leWg7p9aeAqi37XOTgTIbkABlvcPB3E5rlc78=
+github.com/jackc/pgproto3/v2 v2.0.0-alpha1.0.20190420180111-c116219b62db/go.mod h1:bhq50y+xrl9n5mRYyCBFKkpRVTLYJVWeCc+mEAI3yXA=
+github.com/jackc/pgproto3/v2 v2.0.0-alpha1.0.20190609003834-432c2951c711/go.mod h1:uH0AWtUmuShn0bcesswc4aBTWGvw0cAxIJp+6OB//Wg=
+github.com/jackc/pgproto3/v2 v2.0.0-rc3/go.mod h1:ryONWYqW6dqSg1Lw6vXNMXoBJhpzvWKnT95C46ckYeM=
+github.com/jackc/pgproto3/v2 v2.0.0-rc3.0.20190831210041-4c03ce451f29/go.mod h1:ryONWYqW6dqSg1Lw6vXNMXoBJhpzvWKnT95C46ckYeM=
+github.com/jackc/pgproto3/v2 v2.0.1/go.mod h1:WfJCnwN3HIg9Ish/j3sgWXnAfK8A9Y0bwXYU5xKaEdA=
+github.com/jackc/pgproto3/v2 v2.0.2/go.mod h1:WfJCnwN3HIg9Ish/j3sgWXnAfK8A9Y0bwXYU5xKaEdA=
+github.com/jackc/pgproto3/v2 v2.0.5/go.mod h1:WfJCnwN3HIg9Ish/j3sgWXnAfK8A9Y0bwXYU5xKaEdA=
+github.com/jackc/pgproto3/v2 v2.0.6/go.mod h1:WfJCnwN3HIg9Ish/j3sgWXnAfK8A9Y0bwXYU5xKaEdA=
+github.com/jackc/pgproto3/v2 v2.1.1 h1:7PQ/4gLoqnl87ZxL7xjO0DR5gYuviDCZxQJsUlFW1eI=
+github.com/jackc/pgproto3/v2 v2.1.1/go.mod h1:WfJCnwN3HIg9Ish/j3sgWXnAfK8A9Y0bwXYU5xKaEdA=
+github.com/jackc/pgservicefile v0.0.0-20200307190119-3430c5407db8/go.mod h1:vsD4gTJCa9TptPL8sPkXrLZ+hDuNrZCnj29CQpr4X1E=
+github.com/jackc/pgservicefile v0.0.0-20200714003250-2b9c44734f2b h1:C8S2+VttkHFdOOCXJe+YGfa4vHYwlt4Zx+IVXQ97jYg=
+github.com/jackc/pgservicefile v0.0.0-20200714003250-2b9c44734f2b/go.mod h1:vsD4gTJCa9TptPL8sPkXrLZ+hDuNrZCnj29CQpr4X1E=
+github.com/jackc/pgtype v0.0.0-20190421001408-4ed0de4755e0/go.mod h1:hdSHsc1V01CGwFsrv11mJRHWJ6aifDLfdV3aVjFF0zg=
+github.com/jackc/pgtype v0.0.0-20190824184912-ab885b375b90/go.mod h1:KcahbBH1nCMSo2DXpzsoWOAfFkdEtEJpPbVLq8eE+mc=
+github.com/jackc/pgtype v0.0.0-20190828014616-a8802b16cc59/go.mod h1:MWlu30kVJrUS8lot6TQqcg7mtthZ9T0EoIBFiJcmcyw=
+github.com/jackc/pgtype v1.2.0/go.mod h1:5m2OfMh1wTK7x+Fk952IDmI4nw3nPrvtQdM0ZT4WpC0=
+github.com/jackc/pgtype v1.3.0/go.mod h1:b0JqxHvPmljG+HQ5IsvQ0yqeSi4nGcDTVjFoiLDb0Ik=
+github.com/jackc/pgtype v1.3.1-0.20200510190516-8cd94a14c75a/go.mod h1:vaogEUkALtxZMCH411K+tKzNpwzCKU+AnPzBKZ+I+Po=
+github.com/jackc/pgtype v1.3.1-0.20200606141011-f6355165a91c/go.mod h1:cvk9Bgu/VzJ9/lxTO5R5sf80p0DiucVtN7ZxvaC4GmQ=
+github.com/jackc/pgtype v1.4.2/go.mod h1:JCULISAZBFGrHaOXIIFiyfzW5VY0GRitRr8NeJsrdig=
+github.com/jackc/pgtype v1.8.1-0.20210724151600-32e20a603178/go.mod h1:C516IlIV9NKqfsMCXTdChteoXmwgUceqaLfjg2e3NlM=
+github.com/jackc/pgtype v1.8.1 h1:9k0IXtdJXHJbyAWQgbWr1lU+MEhPXZz6RIXxfR5oxXs=
+github.com/jackc/pgtype v1.8.1/go.mod h1:LUMuVrfsFfdKGLw+AFFVv6KtHOFMwRgDDzBt76IqCA4=
+github.com/jackc/pgx v3.6.2+incompatible/go.mod h1:0ZGrqGqkRlliWnWB4zKnWtjbSWbGkVEFm4TeybAXq+I=
+github.com/jackc/pgx/v4 v4.0.0-20190420224344-cc3461e65d96/go.mod h1:mdxmSJJuR08CZQyj1PVQBHy9XOp5p8/SHH6a0psbY9Y=
+github.com/jackc/pgx/v4 v4.0.0-20190421002000-1b8f0016e912/go.mod h1:no/Y67Jkk/9WuGR0JG/JseM9irFbnEPbuWV2EELPNuM=
+github.com/jackc/pgx/v4 v4.0.0-pre1.0.20190824185557-6972a5742186/go.mod h1:X+GQnOEnf1dqHGpw7JmHqHc1NxDoalibchSk9/RWuDc=
+github.com/jackc/pgx/v4 v4.5.0/go.mod h1:EpAKPLdnTorwmPUUsqrPxy5fphV18j9q3wrfRXgo+kA=
+github.com/jackc/pgx/v4 v4.6.0/go.mod h1:vPh43ZzxijXUVJ+t/EmXBtFmbFVO72cuneCT9oAlxAg=
+github.com/jackc/pgx/v4 v4.6.1-0.20200510190926-94ba730bb1e9/go.mod h1:t3/cdRQl6fOLDxqtlyhe9UWgfIi9R8+8v8GKV5TRA/o=
+github.com/jackc/pgx/v4 v4.6.1-0.20200606145419-4e5062306904/go.mod h1:ZDaNWkt9sW1JMiNn0kdYBaLelIhw7Pg4qd+Vk6tw7Hg=
+github.com/jackc/pgx/v4 v4.8.1/go.mod h1:4HOLxrl8wToZJReD04/yB20GDwf4KBYETvlHciCnwW0=
+github.com/jackc/pgx/v4 v4.12.1-0.20210724153913-640aa07df17c/go.mod h1:1QD0+tgSXP7iUjYm9C1NxKhny7lq6ee99u/z+IHFcgs=
+github.com/jackc/pgx/v4 v4.13.0 h1:JCjhT5vmhMAf/YwBHLvrBn4OGdIQBiFG6ym8Zmdx570=
+github.com/jackc/pgx/v4 v4.13.0/go.mod h1:9P4X524sErlaxj0XSGZk7s+LD0eOyu1ZDUrrpznYDF0=
+github.com/jackc/puddle v0.0.0-20190413234325-e4ced69a3a2b/go.mod h1:m4B5Dj62Y0fbyuIc15OsIqK0+JU8nkqQjsgx7dvjSWk=
+github.com/jackc/puddle v0.0.0-20190608224051-11cab39313c9/go.mod h1:m4B5Dj62Y0fbyuIc15OsIqK0+JU8nkqQjsgx7dvjSWk=
+github.com/jackc/puddle v1.1.0/go.mod h1:m4B5Dj62Y0fbyuIc15OsIqK0+JU8nkqQjsgx7dvjSWk=
+github.com/jackc/puddle v1.1.1/go.mod h1:m4B5Dj62Y0fbyuIc15OsIqK0+JU8nkqQjsgx7dvjSWk=
+github.com/jackc/puddle v1.1.2/go.mod h1:m4B5Dj62Y0fbyuIc15OsIqK0+JU8nkqQjsgx7dvjSWk=
+github.com/jackc/puddle v1.1.3 h1:JnPg/5Q9xVJGfjsO5CPUOjnJps1JaRUm8I9FXVCFK94=
+github.com/jackc/puddle v1.1.3/go.mod h1:m4B5Dj62Y0fbyuIc15OsIqK0+JU8nkqQjsgx7dvjSWk=
 github.com/jackpal/go-nat-pmp v1.0.2 h1:KzKSgb7qkJvOUTqYl9/Hg/me3pWgBmERKrTGD7BdWus=
 github.com/jackpal/go-nat-pmp v1.0.2/go.mod h1:QPH045xvCAeXUZOxsnwmrtiCoxIr9eob+4orBN1SBKc=
 github.com/jedisct1/go-minisign v0.0.0-20190909160543-45766022959e h1:UvSe12bq+Uj2hWd8aOlwPmoZ+CITRFrdit+sDGfAg8U=
 github.com/jedisct1/go-minisign v0.0.0-20190909160543-45766022959e/go.mod h1:G1CVv03EnqU1wYL2dFwXxW2An0az9JTl/ZsqXQeBlkU=
+github.com/jinzhu/gorm v1.9.12/go.mod h1:vhTjlKSJUTWNtcbQtrMBFCxy7eXTzeCAzfL5fBZT/Qs=
+github.com/jinzhu/inflection v1.0.0/go.mod h1:h+uFLlag+Qp1Va5pdKtLDYj+kHp5pxUVkryuEj+Srlc=
+github.com/jinzhu/now v1.0.1/go.mod h1:d3SSVoowX0Lcu0IBviAWJpolVfI5UJVZZ7cO71lE/z8=
 github.com/jmespath/go-jmespath v0.4.0/go.mod h1:T8mJZnbsbmF+m6zOOFylbeCJqk5+pHWvzYPziyZiYoo=
 github.com/jmespath/go-jmespath/internal/testify v1.5.1/go.mod h1:L3OGu8Wl2/fWfCI6z80xFu9LTZmf1ZRjMHUOPmWr69U=
+github.com/jmoiron/sqlx v1.2.0 h1:41Ip0zITnmWNR/vHV+S4m+VoUivnWY5E4OJfLZjCJMA=
+github.com/jmoiron/sqlx v1.2.0/go.mod h1:1FEQNm3xlJgrMD+FBdI9+xvCksHtbpVBBw5dYhBSsks=
 github.com/json-iterator/go v1.1.6/go.mod h1:+SdeFBvtyEkXs7REEP0seUULqWtbJapLOCVDaaPEHmU=
 github.com/json-iterator/go v1.1.9/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/jtolds/gls v4.20.0+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
@@ -273,12 +386,21 @@ github.com/klauspost/compress v1.9.7/go.mod h1:RyIbtBH6LamlWaDj8nUwkbUhJ87Yi3uG0
 github.com/klauspost/compress v1.15.15 h1:EF27CXIuDsYJ6mmvtBRlEuB2UVOqHG1tAXgZ7yIO+lw=
 github.com/klauspost/compress v1.15.15/go.mod h1:ZcK2JAFqKOpnBlxcLsJzYfrS9X1akm9fHZNnD9+Vo/4=
 github.com/klauspost/cpuid v1.2.1/go.mod h1:Pj4uuM528wm8OyEC2QMXAi2YiTZ96dNQPGgoMS4s3ek=
+github.com/klauspost/cpuid/v2 v2.0.4/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
+github.com/klauspost/cpuid/v2 v2.0.9 h1:lgaqFMSdTdQYdZ04uHyN2d/eKdOMyi2YLSvlQIBFYa4=
+github.com/klauspost/cpuid/v2 v2.0.9/go.mod h1:FInQzS24/EEf25PyTYn52gqo7WaD8xa0213Md/qVLRg=
+github.com/klauspost/crc32 v0.0.0-20161016154125-cb6bfca970f6/go.mod h1:+ZoRqAPRLkC4NPOvfYeR5KNOrY6TD+/sAC3HXPZgDYg=
+github.com/klauspost/pgzip v1.0.2-0.20170402124221-0bf5dcad4ada/go.mod h1:Ch1tH69qFZu15pkjo5kYi6mth2Zzwzt50oCQKQE9RUs=
+github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
+github.com/konsorten/go-windows-terminal-sequences v1.0.2/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
+github.com/kr/logfmt v0.0.0-20140226030751-b84e30acd515/go.mod h1:+0opPa2QZZtGFBFZlji/RkVcI2GknAs/DXo4wKdlNEc=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
 github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
 github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
+github.com/kr/pty v1.1.8/go.mod h1:O1sed60cT9XZ5uDucP5qwvh+TE3NnUj51EiZO/lmSfw=
 github.com/kr/text v0.1.0/go.mod h1:4Jbv+DJW3UT/LiOwJeYQe1efqtUx/iVham/4vfdArNI=
 github.com/kr/text v0.2.0 h1:5Nx0Ya0ZqY2ygV366QzturHI13Jq95ApcVaJBhpS+AY=
 github.com/kr/text v0.2.0/go.mod h1:eLer722TekiGuMkidMxC/pM04lWEeraHUUmBw8l2grE=
@@ -289,16 +411,30 @@ github.com/labstack/echo/v4 v4.5.0/go.mod h1:czIriw4a0C1dFun+ObrXp7ok03xON0N1awS
 github.com/labstack/gommon v0.3.0/go.mod h1:MULnywXg0yavhxWKc+lOruYdAhDwPK9wf0OL7NoOu+k=
 github.com/leanovate/gopter v0.2.9 h1:fQjYxZaynp97ozCzfOyOuAGOU4aU/z37zf/tOujFk7c=
 github.com/leanovate/gopter v0.2.9/go.mod h1:U2L/78B+KVFIx2VmW6onHJQzXtFb+p5y3y2Sh+Jxxv8=
+github.com/lib/pq v1.0.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
+github.com/lib/pq v1.1.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
+github.com/lib/pq v1.1.1/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
+github.com/lib/pq v1.2.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
+github.com/lib/pq v1.3.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
+github.com/lib/pq v1.4.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
+github.com/lib/pq v1.10.2/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
+github.com/lib/pq v1.10.6 h1:jbk+ZieJ0D7EVGJYpL9QTz7/YW6UHbmdnZWYyK5cdBs=
+github.com/lib/pq v1.10.6/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
 github.com/magiconair/properties v1.8.0/go.mod h1:PppfXfuXeibc/6YijjN8zIbojt8czPbwD3XqdrwzmxQ=
 github.com/mailru/easyjson v0.0.0-20190614124828-94de47d64c63/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/mailru/easyjson v0.0.0-20190626092158-b2ccc519800e/go.mod h1:C1wdFJiN94OJF2b5HbByQZoLdCWB1Yqtg26g4irojpc=
 github.com/matryer/moq v0.0.0-20190312154309-6cfb0558e1bd/go.mod h1:9ELz6aaclSIGnZBoaSLZ3NAl1VTufbOrXBPvtcy6WiQ=
+github.com/mattn/go-colorable v0.0.9/go.mod h1:9vuHe8Xs5qXnSaW/c/ABM9alt+Vo+STaOChaDxuIBZU=
+github.com/mattn/go-colorable v0.1.1/go.mod h1:FuOcm+DKB9mbwrcAfNl7/TZVBZ6rcnceauSikq3lYCQ=
 github.com/mattn/go-colorable v0.1.2/go.mod h1:U0ppj6V5qS13XJ6of8GYAs25YV2eR4EVcfRqFIhoBtE=
+github.com/mattn/go-colorable v0.1.6/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
 github.com/mattn/go-colorable v0.1.7/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
 github.com/mattn/go-colorable v0.1.8/go.mod h1:u6P/XSegPjTcexA+o6vUJrdnUu04hMope9wVRipJSqc=
 github.com/mattn/go-colorable v0.1.11/go.mod h1:u5H1YNBxpqRaxsYJYSkiCWKzEfiAb1Gb520KVy5xxl4=
 github.com/mattn/go-colorable v0.1.13 h1:fFA4WZxdEF4tXPZVKMLwD8oUnCTTo08duU7wxecdEvA=
 github.com/mattn/go-colorable v0.1.13/go.mod h1:7S9/ev0klgBDR4GtXTXX8a3vIGJpMovkB8vQcUbaXHg=
+github.com/mattn/go-isatty v0.0.4/go.mod h1:M+lRXTBqGeGNdLjl/ufCoiOlB5xdOkqRJdNxMWT7Zi4=
+github.com/mattn/go-isatty v0.0.5/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/go-isatty v0.0.7/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/go-isatty v0.0.8/go.mod h1:Iq45c/XA43vh69/j3iqttzPXn0bhXyGjM0Hdxcsrc5s=
 github.com/mattn/go-isatty v0.0.9/go.mod h1:YNRxwqDuOph6SZLI9vUUz6OYw3QyUt7WiY2yME+cCiQ=
@@ -309,11 +445,20 @@ github.com/mattn/go-isatty v0.0.16/go.mod h1:kYGgaQfpe5nmfYZH+SKPsOc2e4SrIfOl2e/
 github.com/mattn/go-runewidth v0.0.3/go.mod h1:LwmH8dsx7+W8Uxz3IHJYH5QSwggIsqBzpuz5H//U1FU=
 github.com/mattn/go-runewidth v0.0.9 h1:Lm995f3rfxdpd6TSmuVCHVb/QhupuXlYr8sCI/QdE+0=
 github.com/mattn/go-runewidth v0.0.9/go.mod h1:H031xJmbD/WCDINGzjvQ9THkh0rPKHF+m2gUSrubnMI=
+github.com/mattn/go-sqlite3 v1.9.0/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
+github.com/mattn/go-sqlite3 v1.11.0/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
+github.com/mattn/go-sqlite3 v2.0.1+incompatible h1:xQ15muvnzGBHpIpdrNi1DA5x0+TcBZzsIDwmw9uTHzw=
+github.com/mattn/go-sqlite3 v2.0.1+incompatible/go.mod h1:FPy6KqzDD04eiIsT53CuJW3U88zkxoIYsOqkbpncsNc=
+github.com/mattn/go-tty v0.0.0-20180907095812-13ff1204f104/go.mod h1:XPvLUNfbS4fJH25nqRHfWLMa1ONC8Amw+mIA639KxkE=
 github.com/mattn/goveralls v0.0.2/go.mod h1:8d1ZMHsd7fW6IRPKQh46F2WRpyib5/X4FOpevwGNQEw=
 github.com/matttproud/golang_protobuf_extensions v1.0.4 h1:mmDVorXM7PCGKw94cs5zkfA9PSy5pEvNWRP0ET0TIVo=
 github.com/matttproud/golang_protobuf_extensions v1.0.4/go.mod h1:BSXmuO+STAnVfrANrmjBb36TMTDstsz7MSK+HVaYKv4=
 github.com/mediocregopher/radix/v3 v3.4.2/go.mod h1:8FL3F6UQRXHXIBSPUs5h0RybMF8i4n7wVopoX3x7Bv8=
 github.com/microcosm-cc/bluemonday v1.0.2/go.mod h1:iVP4YcDBq+n/5fb23BhYFvIMq/leAFZyRl6bYmGDlGc=
+github.com/minio/blake2b-simd v0.0.0-20160723061019-3f5f724cb5b1 h1:lYpkrQH5ajf0OXOcUbGjvZxxijuBwbbmlSxLiuofa+g=
+github.com/minio/blake2b-simd v0.0.0-20160723061019-3f5f724cb5b1/go.mod h1:pD8RvIylQ358TN4wwqatJ8rNavkEINozVn9DtGI3dfQ=
+github.com/minio/sha256-simd v1.0.0 h1:v1ta+49hkWZyvaKwrQB8elexRqm6Y0aMLjCNsrYxo6g=
+github.com/minio/sha256-simd v1.0.0/go.mod h1:OuYzVNI5vcoYIAmbIvHPl3N3jUzVedXbKy5RFepssQM=
 github.com/mitchellh/go-homedir v1.1.0/go.mod h1:SfyaCUpYCn1Vlf4IUYiD9fPX4A5wJrkLzIz1N1q0pr0=
 github.com/mitchellh/mapstructure v1.1.2/go.mod h1:FVVH3fgwuzCH5S8UJGiWEs2h04kUh9fWfEaFds41c1Y=
 github.com/mitchellh/mapstructure v1.4.1 h1:CpVNEelQCZBooIPDn+AR3NpivK/TIKU8bDxdASFVQag=
@@ -329,6 +474,21 @@ github.com/modern-go/reflect2 v0.0.0-20180701023420-4b7aa43c6742/go.mod h1:bx2lN
 github.com/modern-go/reflect2 v1.0.1/go.mod h1:bx2lNnkwVCuqBIxFjflWJWanXIb3RllmbCylyMrvgv0=
 github.com/modocache/gover v0.0.0-20171022184752-b58185e213c5/go.mod h1:caMODM3PzxT8aQXRPkAt8xlV/e7d7w8GM5g0fa5F0D8=
 github.com/moul/http2curl v1.0.0/go.mod h1:8UbvGypXm98wA/IqH45anm5Y2Z6ep6O31QGOAZ3H0fQ=
+github.com/mr-tron/base58 v1.1.0/go.mod h1:xcD2VGqlgYjBdcBLw+TuYLr8afG+Hj8g2eTVqeSzSU8=
+github.com/mr-tron/base58 v1.2.0 h1:T/HDJBh4ZCPbU39/+c3rRvE0uKBQlU27+QI8LJ4t64o=
+github.com/mr-tron/base58 v1.2.0/go.mod h1:BinMc/sQntlIE1frQmRFPUoPA1Zkr8VRgBdjWI2mNwc=
+github.com/mschoch/smat v0.0.0-20160514031455-90eadee771ae/go.mod h1:qAyveg+e4CE+eKJXWVjKXM4ck2QobLqTDytGJbLLhJg=
+github.com/multiformats/go-base32 v0.0.3 h1:tw5+NhuwaOjJCC5Pp82QuXbrmLzWg7uxlMFp8Nq/kkI=
+github.com/multiformats/go-base32 v0.0.3/go.mod h1:pLiuGC8y0QR3Ue4Zug5UzK9LjgbkL8NSQj0zQ5Nz/AA=
+github.com/multiformats/go-base36 v0.1.0 h1:JR6TyF7JjGd3m6FbLU2cOxhC0Li8z8dLNGQ89tUg4F4=
+github.com/multiformats/go-base36 v0.1.0/go.mod h1:kFGE83c6s80PklsHO9sRn2NCoffoRdUUOENyW/Vv6sM=
+github.com/multiformats/go-multibase v0.0.3 h1:l/B6bJDQjvQ5G52jw4QGSYeOTZoAwIO77RblWplfIqk=
+github.com/multiformats/go-multibase v0.0.3/go.mod h1:5+1R4eQrT3PkYZ24C3W2Ue2tPwIdYQD509ZjSb5y9Oc=
+github.com/multiformats/go-multihash v0.1.0 h1:CgAgwqk3//SVEw3T+6DqI4mWMyRuDwZtOWcJT0q9+EA=
+github.com/multiformats/go-multihash v0.1.0/go.mod h1:RJlXsxt6vHGaia+S8We0ErjhojtKzPP2AH4+kYM7k84=
+github.com/multiformats/go-varint v0.0.6 h1:gk85QWKxh3TazbLxED/NlDVv8+q+ReFJk7Y2W/KhfNY=
+github.com/multiformats/go-varint v0.0.6/go.mod h1:3Ls8CIEsrijN6+B7PbrXRPxHRPuXSrVKRY101jdMZYE=
+github.com/mwitkow/go-conntrack v0.0.0-20161129095857-cc309e4a2223/go.mod h1:qRWi+5nqEBWmkhHvq77mSJWrCKwh8bxhgT7d/eI7P4U=
 github.com/naoina/go-stringutil v0.1.0 h1:rCUeRUHjBjGTSHl0VC00jUPLz8/F9dDzYI70Hzifhks=
 github.com/naoina/go-stringutil v0.1.0/go.mod h1:XJ2SJL9jCtBh+P9q5btrd/Ylo8XwT/h1USek5+NqSA0=
 github.com/naoina/toml v0.1.2-0.20170918210437-9fafd6967416 h1:shk/vn9oCoOTmwcouEdwIeOtOGA/ELRUw/GwvxwfT+0=
@@ -354,6 +514,10 @@ github.com/opentracing/opentracing-go v1.1.0/go.mod h1:UkNAQd3GIcIGf0SeVgPpRdFSt
 github.com/pelletier/go-toml v1.2.0/go.mod h1:5z9KED0ma1S8pY6P1sdut58dfprrGBbd/94hg7ilaic=
 github.com/peterh/liner v1.1.1-0.20190123174540-a2c9a5303de7 h1:oYW+YCJ1pachXTQmzR3rNLYGGz4g/UgFcjb28p/viDM=
 github.com/peterh/liner v1.1.1-0.20190123174540-a2c9a5303de7/go.mod h1:CRroGNssyjTd/qIG2FyxByd2S8JEAZXBl4qUrZf8GS0=
+github.com/pganalyze/pg_query_go/v2 v2.1.0 h1:donwPZ4G/X+kMs7j5eYtKjdziqyOLVp3pkUrzb9lDl8=
+github.com/pganalyze/pg_query_go/v2 v2.1.0/go.mod h1:XAxmVqz1tEGqizcQ3YSdN90vCOHBWjJi8URL1er5+cA=
+github.com/philhofer/fwd v1.0.0/go.mod h1:gk3iGcWd9+svBvR0sR+KPcfE+RNWozjowpeBVG3ZVNU=
+github.com/pierrec/lz4 v2.0.5+incompatible/go.mod h1:pdkljMzZIN41W+lC3N2tnIh5sFi+IEE17M5jbnwPHcY=
 github.com/pingcap/errors v0.11.4 h1:lFuQV/oaUMGcD2tqt+01ROSmJs75VG1ToEOkZIZ4nE4=
 github.com/pingcap/errors v0.11.4/go.mod h1:Oi8TUi2kEtXXLMJk9l1cGmz20kV3TaQ0usTwv5KuLY8=
 github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
@@ -377,18 +541,35 @@ github.com/rogpeppe/go-internal v1.9.0 h1:73kH8U+JUqXU8lRuOHeVHaa/SZPifC7BkcraZV
 github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
 github.com/rs/cors v1.7.0 h1:+88SsELBHx5r+hZ8TCkggzSstaWNbDvThkVK8H6f9ik=
 github.com/rs/cors v1.7.0/go.mod h1:gFx+x8UowdsKA9AchylcLynDq+nNFfI8FkUZdN/jGCU=
+github.com/rs/xid v1.2.1/go.mod h1:+uKXf+4Djp6Md1KODXJxgGQPKngRmWyn10oCKFzNHOQ=
+github.com/rs/zerolog v1.13.0/go.mod h1:YbFCdg8HfsridGWAh22vktObvhZbQsZXe4/zB0OKkWU=
+github.com/rs/zerolog v1.15.0/go.mod h1:xYTKnLHcpfU2225ny5qZjxnj9NvkumZYjJHlAThCjNc=
 github.com/russross/blackfriday v1.5.2/go.mod h1:JO/DiYxRf+HjHt06OyowR9PTA263kcR/rfWxYHBV53g=
 github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/russross/blackfriday/v2 v2.1.0 h1:JIOH55/0cWyOuilr9/qlrm0BSXldqnqwMsf35Ld67mk=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/ryanuber/columnize v2.1.0+incompatible/go.mod h1:sm1tb6uqfes/u+d4ooFouqFdy9/2g9QGwK3SQygK0Ts=
+github.com/satori/go.uuid v1.2.0/go.mod h1:dA0hQrYB0VpLJoorglMZABFdXlWrHn1NEOzdhQKdks0=
 github.com/schollz/closestmatch v2.1.0+incompatible/go.mod h1:RtP1ddjLong6gTkbtmuhtR2uUrrJOpYzYRvbcPAid+g=
 github.com/sergi/go-diff v1.0.0/go.mod h1:0CfEIISq7TuYL3j771MWULgwwjU+GofnZX9QAmXWZgo=
 github.com/shirou/gopsutil v3.21.4-0.20210419000835-c7a38de76ee5+incompatible h1:Bn1aCHHRnjv4Bl16T8rcaFjYSrGrIZvpiGO6P3Q4GpU=
 github.com/shirou/gopsutil v3.21.4-0.20210419000835-c7a38de76ee5+incompatible/go.mod h1:5b4v6he4MtMOwMlS0TUMTu2PcXUg8+E1lC7eC3UO/RA=
+github.com/shopspring/decimal v0.0.0-20180709203117-cd690d0c9e24/go.mod h1:M+9NzErvs504Cn4c5DxATwIqPbtswREoFCre64PpcG4=
+github.com/shopspring/decimal v0.0.0-20200227202807-02e2044944cc/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
+github.com/shopspring/decimal v0.0.0-20200419222939-1884f454f8ea/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
+github.com/shopspring/decimal v1.2.0 h1:abSATXmQEYyShuxI4/vyW3tV1MrKAJzCZ/0zLUXYbsQ=
+github.com/shopspring/decimal v1.2.0/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFRcu2hWCYk4o=
 github.com/shurcooL/sanitized_anchor_name v1.0.0/go.mod h1:1NzhyTcUVG4SuEtjjoZeVRXNmyL/1OwPU0+IJeTBvfc=
 github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
 github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
+github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
+github.com/sirupsen/logrus v1.4.1/go.mod h1:ni0Sbl8bgC9z8RoU9G6nDWqqs/fq4eDPysMBDgk/93Q=
+github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
+github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
+github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
+github.com/spaolacci/murmur3 v0.0.0-20180118202830-f09979ecbc72/go.mod h1:JwIasOWyU6f++ZhiEuf87xNszmSA2myDM2Kzu9HwQUA=
+github.com/spaolacci/murmur3 v1.1.0 h1:7c1g84S4BPRrfL5Xrdp6fOJ206sU9y293DDHaoy0bLI=
+github.com/spaolacci/murmur3 v1.1.0/go.mod h1:JwIasOWyU6f++ZhiEuf87xNszmSA2myDM2Kzu9HwQUA=
 github.com/spf13/afero v1.1.2/go.mod h1:j4pytiNVoe2o6bmDsKpLACNPDBIoEAkihy7loJ1B0CQ=
 github.com/spf13/cast v1.3.0/go.mod h1:Qx5cxh0v+4UWYiBimWS+eyWzqEqokIECu5etghLkUJE=
 github.com/spf13/cobra v0.0.5/go.mod h1:3K3wKZymM7VvHMDS9+Akkh4K60UwM26emMESw8tLCHU=
@@ -398,6 +579,9 @@ github.com/spf13/viper v1.3.2/go.mod h1:ZiWeW+zYFKm7srdB9IoDzzZXaJaI5eL9QjNiN/DM
 github.com/status-im/keycard-go v0.2.0 h1:QDLFswOQu1r5jsycloeQh3bVU8n/NatHHaZobtDnDzA=
 github.com/status-im/keycard-go v0.2.0/go.mod h1:wlp8ZLbsmrF6g6WjugPAx+IzoLrkdf9+mHxBEeo3Hbg=
 github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.1.1/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
+github.com/stretchr/objx v0.2.0/go.mod h1:qt09Ya8vawLte6SNmTgCsAVtYtaKzEcn8ATUoHMkEqE=
+github.com/stretchr/objx v0.4.0 h1:M2gUjqZET1qApGOWNSnZ49BAIMX4F/1plDv3+l31EJ4=
 github.com/stretchr/objx v0.4.0/go.mod h1:YvHI0jy2hoMjB+UWwv71VJQ9isScKT/TqJzVSSt89Yw=
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
@@ -411,6 +595,9 @@ github.com/supranational/blst v0.3.8-0.20220526154634-513d2456b344 h1:m+8fKfQwCA
 github.com/supranational/blst v0.3.8-0.20220526154634-513d2456b344/go.mod h1:jZJtfjgudtNl4en1tzwPIV3KjUnQUvG3/j+w+fVonLw=
 github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7 h1:epCh84lMvA70Z7CTTCmYQn2CKbY8j86K7/FAIr141uY=
 github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7/go.mod h1:q4W45IWZaF22tdD+VEXcAWRA037jwmWEB5VWYORlTpc=
+github.com/thoas/go-funk v0.9.2 h1:oKlNYv0AY5nyf9g+/GhMgS/UO2ces0QRdPKwkhY3VCk=
+github.com/thoas/go-funk v0.9.2/go.mod h1:+IWnUfUmFO1+WVYQWQtIJHeRRdaIyyYglZN7xzUPe4Q=
+github.com/tinylib/msgp v1.0.2/go.mod h1:+d+yLhGm8mzTaHzB+wgMYrodPfmZrzkirds8fDWklFE=
 github.com/tklauser/go-sysconf v0.3.5 h1:uu3Xl4nkLzQfXNsWn15rPc/HQCJKObbt1dKJeWp3vU4=
 github.com/tklauser/go-sysconf v0.3.5/go.mod h1:MkWzOF4RMCshBAMXuhXJs64Rte09mITnppBXY/rYEFI=
 github.com/tklauser/numcpus v0.2.2 h1:oyhllyrScuYI6g+h/zUvNXNp1wy7x8qQy3t/piefldA=
@@ -445,14 +632,44 @@ github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9dec
 github.com/yuin/goldmark v1.3.5/go.mod h1:mwnBkeHKe2W/ZEtQ+71ViKU8L12m81fl3OWwC1Zlc8k=
 golang.org/x/crypto v0.0.0-20181203042331-505ab145d0a9/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+github.com/zenazn/goji v0.9.0/go.mod h1:7S9M489iMyHBNxwZnk9/EHS098H4/F6TATF2mIxtB1Q=
+go.opencensus.io v0.21.0/go.mod h1:mSImk1erAIZhrmZN+AvHh14ztQfjbGwt4TtuofqLduU=
+go.opencensus.io v0.22.0/go.mod h1:+kGneAE2xo2IficOXnaByMWTGM9T73dGwxeWcUqIpI8=
+go.opencensus.io v0.22.2/go.mod h1:yxeiOL68Rb0Xd1ddK5vPZ/oVn4vY4Ynel7k9FzqtOIw=
+go.uber.org/atomic v1.3.2/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
+go.uber.org/atomic v1.4.0/go.mod h1:gD2HeocX3+yG+ygLZcrzQJaqmWj9AIm7n08wl/qW/PE=
+go.uber.org/atomic v1.5.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ=
+go.uber.org/atomic v1.6.0/go.mod h1:sABNBOSYdrvTF6hTgEIbc7YasKWGhgEQZyfxyTvoXHQ=
+go.uber.org/multierr v1.1.0/go.mod h1:wR5kodmAFQ0UK8QlbwjlSNy0Z68gJhDJUG5sjR94q/0=
+go.uber.org/multierr v1.3.0/go.mod h1:VgVr7evmIr6uPjLBxg28wmKNXyqE9akIJ5XnfpiKl+4=
+go.uber.org/multierr v1.5.0/go.mod h1:FeouvMocqHpRaaGuG9EjoKcStLC43Zu/fmqdUMPcKYU=
+go.uber.org/tools v0.0.0-20190618225709-2cfd321de3ee/go.mod h1:vJERXedbb3MVM5f9Ejo0C68/HhF8uaILCdgjnY+goOA=
+go.uber.org/zap v1.9.1/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
+go.uber.org/zap v1.10.0/go.mod h1:vwi/ZaCAaUcBkycHslxD9B2zi4UTXhF60s6SWpuDF0Q=
+go.uber.org/zap v1.13.0/go.mod h1:zwrFLgMcdUuIBviXEYEH1YKNaOBnKXsx2IPda5bBwHM=
+golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
+golang.org/x/crypto v0.0.0-20181203042331-505ab145d0a9/go.mod h1:6SG95UA2DQfeDnfUPMdvaQW0Q7yPrPDi9nlGo2tz2b4=
+golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20190325154230-a5d413f7728c/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
+golang.org/x/crypto v0.0.0-20190411191339-88737f569e3a/go.mod h1:WFFai1msRO1wXaEeE5yQxYXgSfI8pQAWXbQop6sCtWE=
+golang.org/x/crypto v0.0.0-20190510104115-cbcb75029529/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20190605123033-f99c8df09eb5/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20190701094942-4def268fd1a4/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20190820162420-60c769a6c586/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20190909091759-094676da4a83/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20190911031432-227b76d455e7/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
+golang.org/x/crypto v0.0.0-20191205180655-e7c4368fe9dd/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20191227163750-53104e6ec876/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
+golang.org/x/crypto v0.0.0-20200323165209-0ec3e9974c59/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
 golang.org/x/crypto v0.0.0-20200820211705-5c72a883971a/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
+golang.org/x/crypto v0.0.0-20201203163018-be400aefbc4c/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
 golang.org/x/crypto v0.0.0-20201221181555-eec23a3978ad/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
+golang.org/x/crypto v0.0.0-20210220033148-5ea612d1eb83/go.mod h1:jdWPYTVW3xRLrWPugEBEK3UY2ZEsg3UU495nc5E+M+I=
 golang.org/x/crypto v0.0.0-20210322153248-0c34fe9e7dc2/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
+golang.org/x/crypto v0.0.0-20210616213533-5ff15b29337e/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
 golang.org/x/crypto v0.1.0 h1:MDRAIl0xIo9Io2xV565hzXHw3zVseKrJKodhohM5CjU=
 golang.org/x/crypto v0.1.0/go.mod h1:RecgLatLF4+eUMCP1PoPZQb+cVrJcOPbHkTkbkB9sbw=
@@ -479,6 +696,8 @@ golang.org/x/net v0.0.0-20190327091125-710a502c58a2/go.mod h1:t9HGtf8HONx5eT2rtn
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190503192946-f4e77d36d62c/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20190724013045-ca1201d0de80/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20190813141303-74dc4d7220e7/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20190827160401-ba9fcec4b297/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20191209160850-c0dbc17a3553/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
@@ -513,9 +732,19 @@ golang.org/x/sys v0.0.0-20181205085412-a5c9d58dba9a/go.mod h1:STP8DvDyc/dI5b8T5h
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190222072716-a9d3bda3a223/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190312061237-fead79001313/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190403152447-81d4e9dc473e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190502145724-3ef323f4f1fd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190507160741-ecd444e8653b/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190606165138-5da285871e9c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190624142023-c5567b49c5d0/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190626221950-04f50cda93cb/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190813064441-fde4db37ae7a/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190826190057-c7b8b68b1456/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20190904154756-749cb33beabd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191005200804-aed5e4c7ecf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191026070338-33540a1f6037/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20191120155948-bd437916bb0e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -528,6 +757,7 @@ golang.org/x/sys v0.0.0-20200826173525-f9321e4c35a6/go.mod h1:h1NjWce9XRLGQEsW7w
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210124154548-22da62e12c0c/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210309074719-68d13333faf2/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210316164454-77fc1eacc6aa/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210324051608-47abb6519492/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20210330210617-4fbd30eecc44/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -569,12 +799,37 @@ golang.org/x/tools v0.0.0-20190328211700-ab21143f2384/go.mod h1:LCzVGOaR6xXOjkQ3
 golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20190425150028-36563e24a262/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.0.0-20190425163242-31fd60d6bfdc/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.0.0-20190506145303-2d16b83fe98c/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.0.0-20190524140312-2c0ae7006135/go.mod h1:RgjU9mgBXZiqYHBnxXauZ1Gv1EHHAz9KjViQ78xBX0Q=
+golang.org/x/tools v0.0.0-20190606124116-d0a3d012864b/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
+golang.org/x/tools v0.0.0-20190621195816-6e04913cbbac/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
+golang.org/x/tools v0.0.0-20190628153133-6cdbf07be9d0/go.mod h1:/rFqwRUd4F7ZHNgwSSTFct+R/Kf4OFW1sUzUTQQTgfc=
+golang.org/x/tools v0.0.0-20190816200558-6889da9d5479/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20190823170909-c4a336ef6a2f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20190911174233-4f2ddba30aff/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191012152004-8de300cfc20a/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191029041327-9cc4af7d6b2c/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191029190741-b9c20aec41a5/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191113191852-77e3bb0ad9e7/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191115202509-3a792d9c32b2/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191125144606-a911d9008d1f/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
+golang.org/x/tools v0.0.0-20191216173652-a0e659d51361/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20191227053925-7b8e75db28f4/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200103221440-774c71fcf114/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
+golang.org/x/tools v0.0.0-20200108203644-89082a384178/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
 golang.org/x/tools v0.0.0-20200130002326-2f3ba24bd6e7/go.mod h1:TB2adYChydJhpapKDTa4BR/hXlZSLoq2Wpct/0txZ28=
 golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.1.3/go.mod h1:o0xws9oXOQQZyjljx8fwUC0k7L1pTE6eaCbjGeHmOkk=
 golang.org/x/tools v0.7.0 h1:W4OVu8VVOaIO0yzWMNdepAulS7YfoS3Zabrm8DOXXU4=
 golang.org/x/tools v0.7.0/go.mod h1:4pg6aUX35JBAogB10C9AtvVL+qowtN4pT3CGSQex14s=
+golang.org/x/tools v0.2.0 h1:G6AHpWxTMGY1KyEYoAQ5WTtIekUUvDNjan3ugu60JvE=
+golang.org/x/tools v0.2.0/go.mod h1:y4OqIKeOV/fWJetJ8bXPU1sEVniLMIyDAZWeHdV+NTA=
+golang.org/x/xerrors v0.0.0-20190410155217-1f06c39b4373/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
+golang.org/x/xerrors v0.0.0-20190513163551-3ee3066db522/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -616,6 +871,7 @@ gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/fsnotify.v1 v1.4.7/go.mod h1:Tz8NjZHkW78fSQdbUxIjBTcgA1z1m8ZHf0WmKUhAMys=
 gopkg.in/go-playground/assert.v1 v1.2.1/go.mod h1:9RXL0bg/zibRAgZUYszZSwO/z8Y/a8bDuhia5mkpMnE=
 gopkg.in/go-playground/validator.v8 v8.18.2/go.mod h1:RX2a/7Ha8BgOhfk7j780h4/u/RRjR0eouCJSH80/M2Y=
+gopkg.in/inconshreveable/log15.v2 v2.0.0-20180818164646-67afb5ed74ec/go.mod h1:aPpfJ7XW+gOuirDoZ8gHhLh3kZ1B08FtV2bbmy7Jv3s=
 gopkg.in/ini.v1 v1.51.1/go.mod h1:pNLf8WUiyNEtQjuu5G5vTm06TEv9tsIgeAvK8hOrP4k=
 gopkg.in/mgo.v2 v2.0.0-20180705113604-9856a29383ce/go.mod h1:yeKp02qBN3iKW1OzL3MGk2IdtZzaj7SFntXj72NppTA=
 gopkg.in/natefinch/lumberjack.v2 v2.0.0 h1:1Lc07Kr7qY4U2YPouBjpCLxpiyxIVoxqXgkXLknAOE8=
@@ -639,5 +895,10 @@ gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 honnef.co/go/tools v0.0.0-20190102054323-c2f93a96b099/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
 honnef.co/go/tools v0.0.0-20190523083050-ea95bdfd59fc/go.mod h1:rf3lG4BRIbNafJWhAfAdb/ePZxsR/4RtNHQocxwk9r4=
+honnef.co/go/tools v0.0.1-2019.2.3/go.mod h1:a3bituU0lyd329TUQxRnasdCoJDkEUEAqEt0JzvZhAg=
+lukechampine.com/blake3 v1.1.6 h1:H3cROdztr7RCfoaTpGZFQsrqvweFLrqS73j7L7cmR5c=
+lukechampine.com/blake3 v1.1.6/go.mod h1:tkKEOtDkNtklkXtLNEOGNq5tcV90tJiA1vAA12R78LA=
+rsc.io/binaryregexp v0.2.0/go.mod h1:qTv7/COck+e2FymRvadv62gMdZztPaShugOCi3I+8D8=
+rsc.io/pdf v0.1.1/go.mod h1:n8OzWcQ6Sp37PL01nO98y4iUCRdTGarVfzxY20ICaU4=
 rsc.io/tmplfunc v0.0.3 h1:53XFQh69AfOa8Tw0Jm7t+GV7KZhOi6jzsCzTtKbMvzU=
 rsc.io/tmplfunc v0.0.3/go.mod h1:AG3sTPzElb1Io3Yg4voV9AGZJuleGAwaVRxL9M49PhA=

metrics/prometheus/collector.go

@@ -86,6 +86,9 @@ func (c *collector) addTimer(name string, m metrics.Timer) {
 		c.writeSummaryPercentile(name, strconv.FormatFloat(pv[i], 'f', -1, 64), ps[i])
 	}
 	c.buff.WriteRune('\n')
+
+	c.buff.WriteString(fmt.Sprintf(typeGaugeTpl, mutateKey(name+"_total")))
+	c.buff.WriteString(fmt.Sprintf(keyValueTpl, mutateKey(name+"_total"), m.Total()))
 }
 
 func (c *collector) addResettingTimer(name string, m metrics.ResettingTimer) {

metrics/prometheus/collector_test.go

@@ -99,6 +99,9 @@ test_timer {quantile="0.99"} 1.2e+08
 test_timer {quantile="0.999"} 1.2e+08
 test_timer {quantile="0.9999"} 1.2e+08
 
+# TYPE test_timer_total gauge
+test_timer_total 230000000
+
 # TYPE test_resetting_timer_count counter
 test_resetting_timer_count 6
 

metrics/timer.go

@@ -25,6 +25,7 @@ type Timer interface {
 	Update(time.Duration)
 	UpdateSince(time.Time)
 	Variance() float64
+	Total() int64
 }
 
 // GetOrRegisterTimer returns an existing Timer or constructs and registers a
@@ -47,6 +48,7 @@ func NewCustomTimer(h Histogram, m Meter) Timer {
 	return &StandardTimer{
 		histogram: h,
 		meter:     m,
+		total:     NewCounter(),
 	}
 }
 
@@ -72,6 +74,7 @@ func NewTimer() Timer {
 	return &StandardTimer{
 		histogram: NewHistogram(NewExpDecaySample(1028, 0.015)),
 		meter:     NewMeter(),
+		total:     NewCounter(),
 	}
 }
 
@@ -134,11 +137,15 @@ func (NilTimer) UpdateSince(time.Time) {}
 // Variance is a no-op.
 func (NilTimer) Variance() float64 { return 0.0 }
 
+// Total is a no-op.
+func (NilTimer) Total() int64 { return int64(0) }
+
 // StandardTimer is the standard implementation of a Timer and uses a Histogram
 // and Meter.
 type StandardTimer struct {
 	histogram Histogram
 	meter     Meter
+	total     Counter
 	mutex     sync.Mutex
 }
 
@@ -200,6 +207,7 @@ func (t *StandardTimer) Snapshot() Timer {
 	return &TimerSnapshot{
 		histogram: t.histogram.Snapshot().(*HistogramSnapshot),
 		meter:     t.meter.Snapshot().(*MeterSnapshot),
+		total:     t.total.Snapshot().(CounterSnapshot),
 	}
 }
 
@@ -231,14 +239,12 @@ func (t *StandardTimer) Update(d time.Duration) {
 	defer t.mutex.Unlock()
 	t.histogram.Update(int64(d))
 	t.meter.Mark(1)
+	t.total.Inc(int64(d))
 }
 
 // Record the duration of an event that started at a time and ends now.
 func (t *StandardTimer) UpdateSince(ts time.Time) {
-	t.mutex.Lock()
+	t.Update(time.Since(ts))
-	defer t.mutex.Unlock()
-	t.histogram.Update(int64(time.Since(ts)))
-	t.meter.Mark(1)
 }
 
 // Variance returns the variance of the values in the sample.
@@ -246,10 +252,18 @@ func (t *StandardTimer) Variance() float64 {
 	return t.histogram.Variance()
 }
 
+// Total returns the total time the timer has run in nanoseconds.
+// This differs from Sum in that it is a simple counter, not based
+// on a histogram Sample.
+func (t *StandardTimer) Total() int64 {
+	return t.total.Count()
+}
+
 // TimerSnapshot is a read-only copy of another Timer.
 type TimerSnapshot struct {
 	histogram *HistogramSnapshot
 	meter     *MeterSnapshot
+	total     CounterSnapshot
 }
 
 // Count returns the number of events recorded at the time the snapshot was
@@ -324,3 +338,6 @@ func (*TimerSnapshot) UpdateSince(time.Time) {
 // Variance returns the variance of the values at the time the snapshot was
 // taken.
 func (t *TimerSnapshot) Variance() float64 { return t.histogram.Variance() }
+
+// Total returns the total time the timer has run in nanoseconds.
+func (t *TimerSnapshot) Total() int64 { return t.total.Count() }

params/config.go

@@ -434,6 +434,9 @@ type ChainConfig struct {
 	// the network that triggers the consensus upgrade.
 	TerminalTotalDifficulty *big.Int `json:"terminalTotalDifficulty,omitempty"`
 
+	// Cap the maximum total difficulty (for testnet use only).
+	CappedMaximumDifficulty *big.Int `json:"cappedMaximumDifficulty,omitempty"`
+
 	// TerminalTotalDifficultyPassed is a flag specifying that the network already
 	// passed the terminal total difficulty. Its purpose is to disable legacy sync
 	// even without having seen the TTD locally (safer long term).
@@ -476,7 +479,11 @@ func (c *ChainConfig) Description() string {
 	switch {
 	case c.Ethash != nil:
 		if c.TerminalTotalDifficulty == nil {
-			banner += "Consensus: Ethash (proof-of-work)\n"
+			if nil == c.CappedMaximumDifficulty {
+				banner += "Consensus: Ethash (proof-of-work)\n"
+			} else {
+				banner += fmt.Sprintf("Consensus: Ethash (proof-of-work, capped difficulty at %d)\n", c.CappedMaximumDifficulty)
+			}
 		} else if !c.TerminalTotalDifficultyPassed {
 			banner += "Consensus: Beacon (proof-of-stake), merging from Ethash (proof-of-work)\n"
 		} else {
@@ -491,7 +498,11 @@ func (c *ChainConfig) Description() string {
 			banner += "Consensus: Beacon (proof-of-stake), merged from Clique (proof-of-authority)\n"
 		}
 	default:
-		banner += "Consensus: unknown\n"
+		if nil == c.CappedMaximumDifficulty {
+			banner += "Consensus: unknown\n"
+		} else {
+			banner += fmt.Sprintf("Consensus: unknown (capped difficulty at %d)\n", c.CappedMaximumDifficulty)
+		}
 	}
 	banner += "\n"
 

params/version.go

@@ -21,10 +21,10 @@ import (
 )
 
 const (
-	VersionMajor = 1        // Major version component of the current release
+	VersionMajor = 1                       // Major version component of the current release
-	VersionMinor = 11       // Minor version component of the current release
+	VersionMinor = 11                      // Minor version component of the current release
-	VersionPatch = 6        // Patch version component of the current release
+	VersionPatch = 6                       // Patch version component of the current release
-	VersionMeta  = "stable" // Version metadata to append to the version string
+	VersionMeta  = "stable" 			   // Version metadata to append to the version string
 )
 
 // Version holds the textual version string.

rpc/http.go

@@ -33,7 +33,7 @@ import (
 )
 
 const (
-	maxRequestContentLength = 1024 * 1024 * 5
+	maxRequestContentLength = 1024 * 1024 * 12
 	contentType             = "application/json"
 )
 

scripts/run_unit_test.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+
+set -e
+
+mkdir -p out
+
+# Remove existing docker-tsdb directory
+rm -rf out/docker-tsdb/
+
+# Copy over files to setup TimescaleDB
+ID=$(docker create cerc-io/ipld-eth-db:v5.0.1-alpha)
+docker cp $ID:/app/docker-tsdb out/docker-tsdb/
+docker rm -v $ID
+
+# Spin up TimescaleDB
+docker-compose -f out/docker-tsdb/docker-compose.test.yml -f docker-compose.yml up ipld-eth-db
+sleep 45
+
+# Run unit tests
+go clean -testcache
+make statedifftest
+
+# Clean up
+docker-compose -f out/docker-tsdb/docker-compose.test.yml -f docker-compose.yml down --remove-orphans --volumes
+rm -rf out/docker-tsdb/

statediff/README.md

@@ -0,0 +1,320 @@
+# Statediff
+
+This package provides an auxiliary service that asynchronously processes state diff objects from chain events,
+either relaying the state objects to RPC subscribers or writing them directly to Postgres as IPLD objects.
+
+It also exposes RPC endpoints for fetching or writing to Postgres the state diff at a specific block height
+or for a specific block hash, this operates on historical block and state data and so depends on a complete state archive.
+
+Data is emitted in this differential format in order to make it feasible to IPLD-ize and index the _entire_ Ethereum state
+(including intermediate state and storage trie nodes). If this state diff process is ran continuously from genesis,
+the entire state at any block can be materialized from the cumulative differentials up to that point.
+
+## Statediff object
+
+A state diff `StateObject` is the collection of all the state and storage trie nodes that have been updated in a given block.
+For convenience, we also associate these nodes with the block number and hash, and optionally the set of code hashes and code for any
+contracts deployed in this block.
+
+A complete state diff `StateObject` will include all state and storage intermediate nodes, which is necessary for generating proofs and for
+traversing the tries.
+
+```go
+// StateObject is a collection of state (and linked storage nodes) as well as the associated block number, block hash,
+// and a set of code hashes and their code
+type StateObject struct {
+	BlockNumber       *big.Int                `json:"blockNumber"     gencodec:"required"`
+	BlockHash         common.Hash             `json:"blockHash"       gencodec:"required"`
+	Nodes             []StateNode             `json:"nodes"           gencodec:"required"`
+	CodeAndCodeHashes []CodeAndCodeHash       `json:"codeMapping"`
+}
+
+// StateNode holds the data for a single state diff node
+type StateNode struct {
+	NodeType     NodeType      `json:"nodeType"        gencodec:"required"`
+	Path         []byte        `json:"path"            gencodec:"required"`
+	NodeValue    []byte        `json:"value"           gencodec:"required"`
+	StorageNodes []StorageNode `json:"storage"`
+	LeafKey      []byte        `json:"leafKey"`
+}
+
+// StorageNode holds the data for a single storage diff node
+type StorageNode struct {
+	NodeType  NodeType `json:"nodeType"        gencodec:"required"`
+	Path      []byte   `json:"path"            gencodec:"required"`
+	NodeValue []byte   `json:"value"           gencodec:"required"`
+	LeafKey   []byte   `json:"leafKey"`
+}
+
+// CodeAndCodeHash struct for holding codehash => code mappings
+// we can't use an actual map because they are not rlp serializable
+type CodeAndCodeHash struct {
+	Hash common.Hash `json:"codeHash"`
+	Code []byte      `json:"code"`
+}
+```
+
+These objects are packed into a `Payload` structure which can additionally associate the `StateObject`
+with the block (header, uncles, and transactions), receipts, and total difficulty.
+This `Payload` encapsulates all of the differential data at a given block, and allows us to index the entire Ethereum data structure
+as hash-linked IPLD objects.
+
+```go
+// Payload packages the data to send to state diff subscriptions
+type Payload struct {
+	BlockRlp        []byte   `json:"blockRlp"`
+	TotalDifficulty *big.Int `json:"totalDifficulty"`
+	ReceiptsRlp     []byte   `json:"receiptsRlp"`
+	StateObjectRlp  []byte   `json:"stateObjectRlp"    gencodec:"required"`
+
+	encoded []byte
+	err     error
+}
+```
+
+## Usage
+
+This state diffing service runs as an auxiliary service concurrent to the regular syncing process of the geth node.
+
+### CLI configuration
+
+This service introduces a CLI flag namespace `statediff`
+
+`--statediff` flag is used to turn on the service
+
+`--statediff.writing` is used to tell the service to write state diff objects it produces from synced ChainEvents directly to a configured Postgres database
+
+`--statediff.workers` is used to set the number of concurrent workers to process state diff objects and write them into the database
+
+`--statediff.db.type` is the type of database we write out to (current options: postgres, dump, file)
+
+`--statediff.dump.dst` is the destination to write to when operating in database dump mode (stdout, stderr, discard)
+
+`--statediff.db.driver` is the specific driver to use for the database (current options for postgres: pgx and sqlx)
+
+`--statediff.db.host` is the hostname/ip to dial to connect to the database
+
+`--statediff.db.port` is the port to dial to connect to the database
+
+`--statediff.db.name` is the name of the database to connect to
+
+`--statediff.db.user` is the user to connect to the database as
+
+`--statediff.db.password` is the password to use to connect to the database
+
+`--statediff.db.conntimeout` is the connection timeout (in seconds)
+
+`--statediff.db.maxconns` is the maximum number of database connections
+
+`--statediff.db.minconns` is the minimum number of database connections
+
+`--statediff.db.maxidleconns` is the maximum number of idle connections
+
+`--statediff.db.maxconnidletime` is the maximum lifetime for an idle connection (in seconds)
+
+`--statediff.db.maxconnlifetime` is the maximum lifetime for a connection (in seconds)
+
+`--statediff.db.nodeid` is the node id to use in the Postgres database
+
+`--statediff.db.clientname` is the client name to use in the Postgres database
+
+`--statediff.db.upsert` whether or not the service, when operating in a direct database writing mode, should overwrite any existing conflicting data
+
+`--statediff.file.path` full path (including filename) to write statediff data out to when operating in file mode
+
+`--statediff.file.wapath` full path (including filename) to write statediff watched addresses out to when operating in file mode
+
+The service can only operate in full sync mode (`--syncmode=full`), but only the historical RPC endpoints require an archive node (`--gcmode=archive`)
+
+e.g.
+`./build/bin/geth --syncmode=full --gcmode=archive --statediff --statediff.writing --statediff.db.type=postgres --statediff.db.driver=sqlx --statediff.db.host=localhost --statediff.db.port=5432 --statediff.db.name=cerc_testing --statediff.db.user=postgres --statediff.db.nodeid=nodeid --statediff.db.clientname=clientname`
+
+When operating in `--statediff.db.type=file` mode, the service will write SQL statements out to the file designated by
+`--statediff.file.path`. Please note that it writes out SQL statements with all `ON CONFLICT` constraint checks dropped.
+This is done so that we can scale out the production of the SQL statements horizontally, merge the separate SQL files produced,
+de-duplicate using unix tools (`sort statediff.sql | uniq` or `sort -u statediff.sql`), bulk load using psql
+(`psql db_name --set ON_ERROR_STOP=on -f statediff.sql`), and then add our primary and foreign key constraints and indexes
+back afterwards.
+
+### RPC endpoints
+
+The state diffing service exposes both a WS subscription endpoint, and a number of HTTP unary endpoints.
+
+Each of these endpoints requires a set of parameters provided by the caller
+
+```go
+// Params is used to carry in parameters from subscribing/requesting clients configuration
+type Params struct {
+	IntermediateStateNodes   bool
+	IntermediateStorageNodes bool
+	IncludeBlock             bool
+	IncludeReceipts          bool
+	IncludeTD                bool
+	IncludeCode              bool
+	WatchedAddresses         []common.Address
+}
+```
+
+Using these params we can tell the service whether to include state and/or storage intermediate nodes; whether
+to include the associated block (header, uncles, and transactions); whether to include the associated receipts;
+whether to include the total difficulty for this block; whether to include the set of code hashes and code for
+contracts deployed in this block; whether to limit the diffing process to a list of specific addresses.
+
+#### Subscription endpoint
+
+A websocket supporting RPC endpoint is exposed for subscribing to state diff `StateObjects` that come off the head of the chain while the geth node syncs.
+
+```go
+// Stream is a subscription endpoint that fires off state diff payloads as they are created
+Stream(ctx context.Context, params Params) (*rpc.Subscription, error)
+```
+
+To expose this endpoint the node needs to have the websocket server turned on (`--ws`),
+and the `statediff` namespace exposed (`--ws.api=statediff`).
+
+Go code subscriptions to this endpoint can be created using the `rpc.Client.Subscribe()` method,
+with the "statediff" namespace, a `statediff.Payload` channel, and the name of the statediff api's rpc method: "stream".
+
+e.g.
+
+```go
+
+cli, err := rpc.Dial("ipcPathOrWsURL")
+if err != nil {
+	// handle error
+}
+stateDiffPayloadChan := make(chan statediff.Payload, 20000)
+methodName := "stream"
+params := statediff.Params{
+    IncludeBlock:             true,
+    IncludeTD:                true,
+    IncludeReceipts:          true,
+    IntermediateStorageNodes: true,
+    IntermediateStateNodes:   true,
+}
+rpcSub, err := cli.Subscribe(context.Background(), statediff.APIName, stateDiffPayloadChan, methodName, params)
+if err != nil {
+	// handle error
+}
+for {
+	select {
+	case stateDiffPayload := <- stateDiffPayloadChan:
+            // process the payload
+        case err := <- rpcSub.Err():
+    	    // handle rpc subscription error
+        }
+}
+```
+
+#### Unary endpoints
+
+The service also exposes unary RPC endpoints for retrieving the state diff `StateObject` for a specific block height/hash.
+
+```go
+// StateDiffAt returns a state diff payload at the specific blockheight
+StateDiffAt(ctx context.Context, blockNumber uint64, params Params) (*Payload, error)
+
+// StateDiffFor returns a state diff payload for the specific blockhash
+StateDiffFor(ctx context.Context, blockHash common.Hash, params Params) (*Payload, error)
+```
+
+To expose this endpoint the node needs to have the HTTP server turned on (`--http`),
+and the `statediff` namespace exposed (`--http.api=statediff`).
+
+### Direct indexing into Postgres
+
+If `--statediff.writing` is set, the service will convert the state diff `StateObject` data into IPLD objects, persist them directly to Postgres,
+and generate secondary indexes around the IPLD data.
+
+The schema and migrations for this Postgres database are provided in `statediff/db/`.
+
+#### Postgres setup
+
+We use [pressly/goose](https://github.com/pressly/goose) as our Postgres migration manager.
+You can also load the Postgres schema directly into a database using
+
+`psql database_name < schema.sql`
+
+This will only work on a version 12.4 Postgres database.
+
+#### Schema overview
+
+Our Postgres schemas are built around a single IPFS backing Postgres IPLD blockstore table (`ipld.blocks`) that conforms with [go-ds-sql](https://github.com/ipfs/go-ds-sql/blob/master/postgres/postgres.go).
+All IPLD objects are stored in this table, where `key` is the blockstore-prefixed multihash key for the IPLD object and `data` contains
+the bytes for the IPLD block (in the case of all Ethereum IPLDs, this is the RLP byte encoding of the Ethereum object).
+
+The IPLD objects in this table can be traversed using an IPLD DAG interface, but since this table only maps multihash to raw IPLD object
+it is not particularly useful for searching through the data by looking up Ethereum objects by their constituent fields
+(e.g. by block number, tx source/recipient, state/storage trie node path). To improve the accessibility of these objects
+we create an Ethereum [advanced data layout](https://github.com/ipld/specs#schemas-and-advanced-data-layouts) (ADL) by generating secondary
+indexes on top of the raw IPLDs in other Postgres tables.
+
+These secondary index tables fall under the `eth` schema and follow an `{objectType}_cids` naming convention.
+These tables provide a view into individual fields of the underlying Ethereum IPLD objects, allowing lookups on these fields, and reference the raw IPLD objects stored in `ipld.blocks`
+by foreign keys to their multihash keys.
+Additionally, these tables maintain the hash-linked nature of Ethereum objects to one another. E.g. a storage trie node entry in the `storage_cids`
+table contains a `state_id` foreign key which references the `id` for the `state_cids` entry that contains the state leaf node for the contract that storage node belongs to,
+and in turn that `state_cids` entry contains a `header_id` foreign key which references the `id` of the `header_cids` entry that contains the header for the block these state and storage nodes were updated (diffed).
+
+### Optimization
+
+On mainnet this process is extremely IO intensive and requires significant resources to allow it to keep up with the head of the chain.
+The state diff processing time for a specific block is dependent on the number and complexity of the state changes that occur in a block and
+the number of updated state nodes that are available in the in-memory cache vs must be retrieved from disc.
+
+If memory permits, one means of improving the efficiency of this process is to increase the in-memory trie cache allocation.
+This can be done by increasing the overall `--cache` allocation and/or by increasing the % of the cache allocated to trie
+usage with `--cache.trie`.
+
+## Versioning, Branches, Rebasing, and Releasing
+
+Internal tagged releases are maintained for building the latest version of statediffing geth or using it as a go mod dependency.
+When a new core go-ethereum version is released, statediffing geth is rebased onto and adjusted to work with the new tag.
+
+We want to maintain a complete record of our git history, but in order to make frequent and timely rebases feasible we also
+need to be able to squash our work before performing a rebase. To this end we retain multiple branches with partial incremental history that culminate in
+the full incremental history.
+
+### Versioning
+
+Example: `v1.10.16-statediff-3.0.2`
+
+- The first section, `v1.10.16`, corresponds to the release of the root branch this version is rebased onto (e.g., [](https://github.com/ethereum/go-ethereum/releases/tag/v1.10.16)[https://github.com/ethereum/go-ethereum/releases/tag/v1.10.16](https://github.com/ethereum/go-ethereum/releases/tag/v1.10.16))
+- The second section, `3.0.2`, corresponds to the version of our statediffing code. The major version here (3) should always correspond with the major version of the `ipld-eth-db` schema version it works with (e.g., [](https://github.com/cerc-io/ipld-eth-db/releases/tag/v3.0.6)[https://github.com/vulcanize/ipld-eth-db/releases/tag/v3.0.6](https://github.com/vulcanize/ipld-eth-db/releases/tag/v3.0.6)); it is only bumped when we bump the major version of the schema.
+  - The major version of the schema is only bumped when a breaking change is made to the schema.
+  - The minor version is bumped when a new feature is added, or a fix is performed that breaks or updates the statediffing API or CLI in some way.
+  - The patch version is bumped whenever minor fixes/patches/features are done that don’t change/break API/CLI compatibility.
+- We are very strict about the first section and the major version of the statediffing code, but some discretion is required when deciding to bump minor versus patch version of the statediffing code.
+
+The statediff version is included in the `VersionMeta` in params/version.go
+
+### Branches
+
+We maintain two official kinds of branches:
+
+Major Branch: `{Root Version}-statediff`
+Major branches retain the cumulative state of all changes made before the latest root version rebase and track the full incremental history of changes made between the latest root version rebase and the next.
+Aside from creating the branch by performing the rebase described in the section below, these branches are never worked off of or committed to directly.
+
+Feature Branch: `{Root Version}-statediff-{Statediff Version}`
+Feature branches are checked out from a major branch in order to work on a new feature or fix for the statediffing code.
+The statediff version of a feature branch is the new version it affects on the major branch when merged. Internal tagged releases
+are cut against these branches after they are merged back to the major branch.
+
+If a developer is unsure what version their patch should affect, they should remain working on an unofficial branch. From there
+they can open a PR against the targeted root branch and be directed to the appropriate feature version and branch.
+
+### Rebasing
+
+When a new root tagged release comes out we rebase our statediffing code on top of the new tag using the following process:
+
+1. Checkout a new major branch for the tag from the current major branch
+2. On the new major branch, squash all our commits since the last major rebase
+3. On the new major branch, perform the rebase against the new tag
+4. Push the new major branch to the remote
+5. From the new major branch, checkout a new feature branch based on the new major version and the last statediff version
+6. On this new feature branch, add the new major branch to the .github/workflows/on-master.yml list of "on push" branches
+7. On this new feature branch, make any fixes/adjustments required for all statediffing geth tests to pass
+8. PR this feature branch into the new major branch, this PR will trigger CI tests and builds.
+9. After merging PR, rebase feature branch onto major branch
+10. Cut a new release targeting the feature branch, this release should have the new root version but the same statediff version as the last release

statediff/api.go

@@ -0,0 +1,206 @@
+// Copyright 2019 The go-ethereum Authors
+// This file is part of the go-ethereum library.
+//
+// The go-ethereum library is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Lesser General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// The go-ethereum library is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Lesser General Public License for more details.
+//
+// You should have received a copy of the GNU Lesser General Public License
+// along with the go-ethereum library. If not, see <http://www.gnu.org/licenses/>.
+
+package statediff
+
+import (
+	"context"
+
+	"github.com/ethereum/go-ethereum/statediff/types"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/ethereum/go-ethereum/rpc"
+)
+
+// APIName is the namespace used for the state diffing service API
+const APIName = "statediff"
+
+// APIVersion is the version of the state diffing service API
+const APIVersion = "0.0.1"
+
+// PublicStateDiffAPI provides an RPC subscription interface
+// that can be used to stream out state diffs as they
+// are produced by a full node
+type PublicStateDiffAPI struct {
+	sds IService
+}
+
+// NewPublicStateDiffAPI creates an rpc subscription interface for the underlying statediff service
+func NewPublicStateDiffAPI(sds IService) *PublicStateDiffAPI {
+	return &PublicStateDiffAPI{
+		sds: sds,
+	}
+}
+
+// Stream is the public method to setup a subscription that fires off statediff service payloads as they are created
+func (api *PublicStateDiffAPI) Stream(ctx context.Context, params Params) (*rpc.Subscription, error) {
+	// ensure that the RPC connection supports subscriptions
+	notifier, supported := rpc.NotifierFromContext(ctx)
+	if !supported {
+		return nil, rpc.ErrNotificationsUnsupported
+	}
+
+	// create subscription and start waiting for events
+	rpcSub := notifier.CreateSubscription()
+
+	go func() {
+		// subscribe to events from the statediff service
+		payloadChannel := make(chan Payload, chainEventChanSize)
+		quitChan := make(chan bool, 1)
+		api.sds.Subscribe(rpcSub.ID, payloadChannel, quitChan, params)
+		// loop and await payloads and relay them to the subscriber with the notifier
+		for {
+			select {
+			case payload := <-payloadChannel:
+				if err := notifier.Notify(rpcSub.ID, payload); err != nil {
+					log.Error("Failed to send state diff packet; error: " + err.Error())
+					if err := api.sds.Unsubscribe(rpcSub.ID); err != nil {
+						log.Error("Failed to unsubscribe from the state diff service; error: " + err.Error())
+					}
+					return
+				}
+			case err := <-rpcSub.Err():
+				if err != nil {
+					log.Error("State diff service rpcSub error: " + err.Error())
+					err = api.sds.Unsubscribe(rpcSub.ID)
+					if err != nil {
+						log.Error("Failed to unsubscribe from the state diff service; error: " + err.Error())
+					}
+					return
+				}
+			case <-quitChan:
+				// don't need to unsubscribe, service does so before sending the quit signal
+				return
+			}
+		}
+	}()
+
+	return rpcSub, nil
+}
+
+// StateDiffAt returns a state diff payload at the specific blockheight
+func (api *PublicStateDiffAPI) StateDiffAt(ctx context.Context, blockNumber uint64, params Params) (*Payload, error) {
+	return api.sds.StateDiffAt(blockNumber, params)
+}
+
+// StateDiffFor returns a state diff payload for the specific blockhash
+func (api *PublicStateDiffAPI) StateDiffFor(ctx context.Context, blockHash common.Hash, params Params) (*Payload, error) {
+	return api.sds.StateDiffFor(blockHash, params)
+}
+
+// StreamCodeAndCodeHash writes all of the codehash=>code pairs out to a websocket channel
+func (api *PublicStateDiffAPI) StreamCodeAndCodeHash(ctx context.Context, blockNumber uint64) (*rpc.Subscription, error) {
+	// ensure that the RPC connection supports subscriptions
+	notifier, supported := rpc.NotifierFromContext(ctx)
+	if !supported {
+		return nil, rpc.ErrNotificationsUnsupported
+	}
+
+	// create subscription and start waiting for events
+	rpcSub := notifier.CreateSubscription()
+	payloadChan := make(chan types.CodeAndCodeHash, chainEventChanSize)
+	quitChan := make(chan bool)
+	api.sds.StreamCodeAndCodeHash(blockNumber, payloadChan, quitChan)
+	go func() {
+		for {
+			select {
+			case payload := <-payloadChan:
+				if err := notifier.Notify(rpcSub.ID, payload); err != nil {
+					log.Error("Failed to send code and codehash packet", "err", err)
+					return
+				}
+			case err := <-rpcSub.Err():
+				log.Error("State diff service rpcSub error", "err", err)
+				return
+			case <-quitChan:
+				return
+			}
+		}
+	}()
+
+	return rpcSub, nil
+}
+
+// WriteStateDiffAt writes a state diff object directly to DB at the specific blockheight
+func (api *PublicStateDiffAPI) WriteStateDiffAt(ctx context.Context, blockNumber uint64, params Params) JobID {
+	var err error
+	start, logger := countApiRequestBegin("writeStateDiffAt", blockNumber)
+	defer countApiRequestEnd(start, logger, err)
+
+	return api.sds.WriteStateDiffAt(blockNumber, params)
+}
+
+// WriteStateDiffFor writes a state diff object directly to DB for the specific block hash
+func (api *PublicStateDiffAPI) WriteStateDiffFor(ctx context.Context, blockHash common.Hash, params Params) error {
+	var err error
+	start, logger := countApiRequestBegin("writeStateDiffFor", blockHash.Hex())
+	defer countApiRequestEnd(start, logger, err)
+
+	err = api.sds.WriteStateDiffFor(blockHash, params)
+	return err
+}
+
+// WatchAddress changes the list of watched addresses to which the direct indexing is restricted according to given operation
+func (api *PublicStateDiffAPI) WatchAddress(operation types.OperationType, args []types.WatchAddressArg) error {
+	return api.sds.WatchAddress(operation, args)
+}
+
+// StreamWrites sets up a subscription that streams the status of completed calls to WriteStateDiff*
+func (api *PublicStateDiffAPI) StreamWrites(ctx context.Context) (*rpc.Subscription, error) {
+	// ensure that the RPC connection supports subscriptions
+	notifier, supported := rpc.NotifierFromContext(ctx)
+	if !supported {
+		return nil, rpc.ErrNotificationsUnsupported
+	}
+
+	// create subscription and start waiting for events
+	rpcSub := notifier.CreateSubscription()
+
+	go func() {
+		// subscribe to events from the statediff service
+		statusChan := make(chan JobStatus, chainEventChanSize)
+		quitChan := make(chan bool, 1)
+		api.sds.SubscribeWriteStatus(rpcSub.ID, statusChan, quitChan)
+
+		var err error
+		defer func() {
+			if err = api.sds.UnsubscribeWriteStatus(rpcSub.ID); err != nil {
+				log.Error("Failed to unsubscribe from job status stream: " + err.Error())
+			}
+		}()
+		// loop and await payloads and relay them to the subscriber with the notifier
+		for {
+			select {
+			case status := <-statusChan:
+				if err = notifier.Notify(rpcSub.ID, status); err != nil {
+					log.Error("Failed to send job status; error: " + err.Error())
+					return
+				}
+			case err = <-rpcSub.Err():
+				if err != nil {
+					log.Error("statediff_StreamWrites RPC subscription error: " + err.Error())
+					return
+				}
+			case <-quitChan:
+				// don't need to unsubscribe, service does so before sending the quit signal
+				return
+			}
+		}
+	}()
+
+	return rpcSub, nil
+}

statediff/builder.go

@@ -0,0 +1,670 @@
+// Copyright 2019 The go-ethereum Authors
+// This file is part of the go-ethereum library.
+//
+// The go-ethereum library is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Lesser General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+//
+// The go-ethereum library is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU Lesser General Public License for more details.
+//
+// You should have received a copy of the GNU Lesser General Public License
+// along with the go-ethereum library. If not, see <http://www.gnu.org/licenses/>.
+
+// Contains a batch of utility type declarations used by the tests. As the node
+// operates on unique types, a lot of them are needed to check various features.
+
+package statediff
+
+import (
+	"bytes"
+	"fmt"
+	"time"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/core/state"
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/crypto"
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/ethereum/go-ethereum/rlp"
+	metrics2 "github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	ipld2 "github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+	"github.com/ethereum/go-ethereum/statediff/trie_helpers"
+	types2 "github.com/ethereum/go-ethereum/statediff/types"
+	"github.com/ethereum/go-ethereum/trie"
+)
+
+var (
+	emptyNode, _      = rlp.EncodeToBytes(&[]byte{})
+	emptyContractRoot = crypto.Keccak256Hash(emptyNode)
+	nullCodeHash      = crypto.Keccak256Hash([]byte{}).Bytes()
+	nullNodeHash      = common.Hex2Bytes("0000000000000000000000000000000000000000000000000000000000000000")
+)
+
+// Builder interface exposes the method for building a state diff between two blocks
+type Builder interface {
+	BuildStateDiffObject(args Args, params Params) (types2.StateObject, error)
+	WriteStateDiffObject(args Args, params Params, output types2.StateNodeSink, ipldOutput types2.IPLDSink) error
+}
+
+type StateDiffBuilder struct {
+	StateCache state.Database
+}
+
+type IterPair struct {
+	Older, Newer trie.NodeIterator
+}
+
+func StateNodeAppender(nodes *[]types2.StateLeafNode) types2.StateNodeSink {
+	return func(node types2.StateLeafNode) error {
+		*nodes = append(*nodes, node)
+		return nil
+	}
+}
+func StorageNodeAppender(nodes *[]types2.StorageLeafNode) types2.StorageNodeSink {
+	return func(node types2.StorageLeafNode) error {
+		*nodes = append(*nodes, node)
+		return nil
+	}
+}
+func IPLDMappingAppender(iplds *[]types2.IPLD) types2.IPLDSink {
+	return func(c types2.IPLD) error {
+		*iplds = append(*iplds, c)
+		return nil
+	}
+}
+
+// NewBuilder is used to create a statediff builder
+func NewBuilder(stateCache state.Database) Builder {
+	return &StateDiffBuilder{
+		StateCache: stateCache, // state cache is safe for concurrent reads
+	}
+}
+
+// BuildStateDiffObject builds a statediff object from two blocks and the provided parameters
+func (sdb *StateDiffBuilder) BuildStateDiffObject(args Args, params Params) (types2.StateObject, error) {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.BuildStateDiffObjectTimer)
+	var stateNodes []types2.StateLeafNode
+	var iplds []types2.IPLD
+	err := sdb.WriteStateDiffObject(args, params, StateNodeAppender(&stateNodes), IPLDMappingAppender(&iplds))
+	if err != nil {
+		return types2.StateObject{}, err
+	}
+	return types2.StateObject{
+		BlockHash:   args.BlockHash,
+		BlockNumber: args.BlockNumber,
+		Nodes:       stateNodes,
+		IPLDs:       iplds,
+	}, nil
+}
+
+// WriteStateDiffObject writes a statediff object to output sinks
+func (sdb *StateDiffBuilder) WriteStateDiffObject(args Args, params Params, output types2.StateNodeSink,
+	ipldOutput types2.IPLDSink) error {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.WriteStateDiffObjectTimer)
+	// Load tries for old and new states
+	oldTrie, err := sdb.StateCache.OpenTrie(args.OldStateRoot)
+	if err != nil {
+		return fmt.Errorf("error creating trie for oldStateRoot: %v", err)
+	}
+	newTrie, err := sdb.StateCache.OpenTrie(args.NewStateRoot)
+	if err != nil {
+		return fmt.Errorf("error creating trie for newStateRoot: %v", err)
+	}
+
+	// we do two state trie iterations:
+	// 		one for new/updated nodes,
+	// 		one for deleted/updated nodes;
+	// prepare 2 iterator instances for each task
+	iterPairs := []IterPair{
+		{
+			Older: oldTrie.NodeIterator([]byte{}),
+			Newer: newTrie.NodeIterator([]byte{}),
+		},
+		{
+			Older: oldTrie.NodeIterator([]byte{}),
+			Newer: newTrie.NodeIterator([]byte{}),
+		},
+	}
+
+	logger := log.New("hash", args.BlockHash.Hex(), "number", args.BlockNumber)
+	return sdb.BuildStateDiffWithIntermediateStateNodes(iterPairs, params, output, ipldOutput, logger)
+}
+
+func (sdb *StateDiffBuilder) BuildStateDiffWithIntermediateStateNodes(iterPairs []IterPair, params Params,
+	output types2.StateNodeSink, ipldOutput types2.IPLDSink, logger log.Logger) error {
+	logger.Debug("statediff BEGIN BuildStateDiffWithIntermediateStateNodes")
+	defer metrics2.ReportAndUpdateDuration("statediff END BuildStateDiffWithIntermediateStateNodes", time.Now(), logger, metrics2.IndexerMetrics.BuildStateDiffWithIntermediateStateNodesTimer)
+	// collect a slice of all the nodes that were touched and exist at B (B-A)
+	// a map of their leafkey to all the accounts that were touched and exist at B
+	// and a slice of all the paths for the nodes in both of the above sets
+	diffAccountsAtB, err := sdb.createdAndUpdatedState(
+		iterPairs[0].Older, iterPairs[0].Newer, params.watchedAddressesLeafPaths, ipldOutput, logger)
+	if err != nil {
+		return fmt.Errorf("error collecting createdAndUpdatedNodes: %v", err)
+	}
+
+	// collect a slice of all the nodes that existed at a path in A that doesn't exist in B
+	// a map of their leafkey to all the accounts that were touched and exist at A
+	diffAccountsAtA, err := sdb.deletedOrUpdatedState(
+		iterPairs[1].Older, iterPairs[1].Newer, diffAccountsAtB,
+		params.watchedAddressesLeafPaths, output, logger)
+	if err != nil {
+		return fmt.Errorf("error collecting deletedOrUpdatedNodes: %v", err)
+	}
+
+	// collect and sort the leafkey keys for both account mappings into a slice
+	t := time.Now()
+	createKeys := trie_helpers.SortKeys(diffAccountsAtB)
+	deleteKeys := trie_helpers.SortKeys(diffAccountsAtA)
+	logger.Debug(fmt.Sprintf("statediff BuildStateDiffWithIntermediateStateNodes sort duration=%dms", time.Since(t).Milliseconds()))
+
+	// and then find the intersection of these keys
+	// these are the leafkeys for the accounts which exist at both A and B but are different
+	// this also mutates the passed in createKeys and deleteKeys, removing the intersection keys
+	// and leaving the truly created or deleted keys in place
+	t = time.Now()
+	updatedKeys := trie_helpers.FindIntersection(createKeys, deleteKeys)
+	logger.Debug(fmt.Sprintf("statediff BuildStateDiffWithIntermediateStateNodes intersection count=%d duration=%dms",
+		len(updatedKeys),
+		time.Since(t).Milliseconds()))
+
+	// build the diff nodes for the updated accounts using the mappings at both A and B as directed by the keys found as the intersection of the two
+	err = sdb.buildAccountUpdates(diffAccountsAtB, diffAccountsAtA, updatedKeys, output, ipldOutput, logger)
+	if err != nil {
+		return fmt.Errorf("error building diff for updated accounts: %v", err)
+	}
+	// build the diff nodes for created accounts
+	err = sdb.buildAccountCreations(diffAccountsAtB, output, ipldOutput, logger)
+	if err != nil {
+		return fmt.Errorf("error building diff for created accounts: %v", err)
+	}
+	return nil
+}
+
+// createdAndUpdatedState returns
+// a slice of all the intermediate nodes that exist in a different state at B than A
+// a mapping of their leafkeys to all the accounts that exist in a different state at B than A
+// and a slice of the paths for all of the nodes included in both
+func (sdb *StateDiffBuilder) createdAndUpdatedState(a, b trie.NodeIterator,
+	watchedAddressesLeafPaths [][]byte, output types2.IPLDSink, logger log.Logger) (types2.AccountMap, error) {
+	logger.Debug("statediff BEGIN createdAndUpdatedState")
+	defer metrics2.ReportAndUpdateDuration("statediff END createdAndUpdatedState", time.Now(), logger, metrics2.IndexerMetrics.CreatedAndUpdatedStateTimer)
+	diffAccountsAtB := make(types2.AccountMap)
+	watchingAddresses := len(watchedAddressesLeafPaths) > 0
+
+	it, itCount := trie.NewDifferenceIterator(a, b)
+	for it.Next(true) {
+		// ignore node if it is not along paths of interest
+		if watchingAddresses && !isValidPrefixPath(watchedAddressesLeafPaths, it.Path()) {
+			continue
+		}
+		// index values by leaf key
+		if it.Leaf() {
+			// if it is a "value" node, we will index the value by leaf key
+			accountW, err := sdb.processStateValueNode(it, watchedAddressesLeafPaths)
+			if err != nil {
+				return nil, err
+			}
+			if accountW == nil {
+				continue
+			}
+			// for now, just add it to diffAccountsAtB
+			// we will compare to diffAccountsAtA to determine which diffAccountsAtB
+			// were creations and which were updates and also identify accounts that were removed going A->B
+			diffAccountsAtB[common.Bytes2Hex(accountW.LeafKey)] = *accountW
+		} else { // trie nodes will be written to blockstore only
+			// reminder that this includes leaf nodes, since the geth iterator.Leaf() actually signifies a "value" node
+			if bytes.Equal(it.Hash().Bytes(), nullNodeHash) {
+				continue
+			}
+			nodeVal := make([]byte, len(it.NodeBlob()))
+			copy(nodeVal, it.NodeBlob())
+			if len(watchedAddressesLeafPaths) > 0 {
+				var elements []interface{}
+				if err := rlp.DecodeBytes(nodeVal, &elements); err != nil {
+					return nil, err
+				}
+				ok, err := isLeaf(elements)
+				if err != nil {
+					return nil, err
+				}
+				if ok {
+					nodePath := make([]byte, len(it.Path()))
+					copy(nodePath, it.Path())
+					partialPath := trie.CompactToHex(elements[0].([]byte))
+					valueNodePath := append(nodePath, partialPath...)
+					if !isWatchedAddress(watchedAddressesLeafPaths, valueNodePath) {
+						continue
+					}
+				}
+			}
+			nodeHash := make([]byte, len(it.Hash().Bytes()))
+			copy(nodeHash, it.Hash().Bytes())
+			if err := output(types2.IPLD{
+				CID:     ipld2.Keccak256ToCid(ipld2.MEthStateTrie, nodeHash).String(),
+				Content: nodeVal,
+			}); err != nil {
+				return nil, err
+			}
+		}
+	}
+	logger.Debug("statediff COUNTS createdAndUpdatedStateWithIntermediateNodes", "it", itCount, "diffAccountsAtB", len(diffAccountsAtB))
+	metrics2.IndexerMetrics.DifferenceIteratorCounter.Inc(int64(*itCount))
+	return diffAccountsAtB, it.Error()
+}
+
+// reminder: it.Leaf() == true when the iterator is positioned at a "value node" which is not something that actually exists in an MMPT
+func (sdb *StateDiffBuilder) processStateValueNode(it trie.NodeIterator, watchedAddressesLeafPaths [][]byte) (*types2.AccountWrapper, error) {
+	// skip if it is not a watched address
+	// If we aren't watching any specific addresses, we are watching everything
+	if len(watchedAddressesLeafPaths) > 0 && !isWatchedAddress(watchedAddressesLeafPaths, it.Path()) {
+		return nil, nil
+	}
+
+	// created vs updated is important for leaf nodes since we need to diff their storage
+	// so we need to map all changed accounts at B to their leafkey, since account can change pathes but not leafkey
+	var account types.StateAccount
+	accountRLP := make([]byte, len(it.LeafBlob()))
+	copy(accountRLP, it.LeafBlob())
+	if err := rlp.DecodeBytes(accountRLP, &account); err != nil {
+		return nil, fmt.Errorf("error decoding account for leaf value at leaf key %x\nerror: %v", it.LeafKey(), err)
+	}
+	leafKey := make([]byte, len(it.LeafKey()))
+	copy(leafKey, it.LeafKey())
+
+	// since this is a "value node", we need to move up to the "parent" node which is the actual leaf node
+	// it should be in the fastcache since it necessarily was recently accessed to reach the current node
+	parentNodeRLP, err := sdb.StateCache.TrieDB().Node(it.Parent())
+	if err != nil {
+		return nil, err
+	}
+	return &types2.AccountWrapper{
+		LeafKey: leafKey,
+		Account: &account,
+		CID:     ipld2.Keccak256ToCid(ipld2.MEthStateTrie, crypto.Keccak256(parentNodeRLP)).String(),
+	}, nil
+}
+
+// deletedOrUpdatedState returns a slice of all the pathes that are emptied at B
+// and a mapping of their leafkeys to all the accounts that exist in a different state at A than B
+func (sdb *StateDiffBuilder) deletedOrUpdatedState(a, b trie.NodeIterator, diffAccountsAtB types2.AccountMap,
+	watchedAddressesLeafPaths [][]byte, output types2.StateNodeSink, logger log.Logger) (types2.AccountMap, error) {
+	logger.Debug("statediff BEGIN deletedOrUpdatedState")
+	defer metrics2.ReportAndUpdateDuration("statediff END deletedOrUpdatedState", time.Now(), logger, metrics2.IndexerMetrics.DeletedOrUpdatedStateTimer)
+	diffAccountAtA := make(types2.AccountMap)
+	watchingAddresses := len(watchedAddressesLeafPaths) > 0
+
+	it, _ := trie.NewDifferenceIterator(b, a)
+	for it.Next(true) {
+		// ignore node if it is not along paths of interest
+		if watchingAddresses && !isValidPrefixPath(watchedAddressesLeafPaths, it.Path()) {
+			continue
+		}
+
+		if it.Leaf() {
+			accountW, err := sdb.processStateValueNode(it, watchedAddressesLeafPaths)
+			if err != nil {
+				return nil, err
+			}
+			if accountW == nil {
+				continue
+			}
+			leafKey := common.Bytes2Hex(accountW.LeafKey)
+			diffAccountAtA[leafKey] = *accountW
+			// if this node's leaf key did not show up in diffAccountsAtB
+			// that means the account was deleted
+			// in that case, emit an empty "removed" diff state node
+			// include empty "removed" diff storage nodes for all the storage slots
+			if _, ok := diffAccountsAtB[leafKey]; !ok {
+				diff := types2.StateLeafNode{
+					AccountWrapper: types2.AccountWrapper{
+						Account: nil,
+						LeafKey: accountW.LeafKey,
+						CID:     shared.RemovedNodeStateCID,
+					},
+					Removed: true,
+				}
+
+				storageDiff := make([]types2.StorageLeafNode, 0)
+				err := sdb.buildRemovedAccountStorageNodes(accountW.Account.Root, StorageNodeAppender(&storageDiff))
+				if err != nil {
+					return nil, fmt.Errorf("failed building storage diffs for removed state account with key %x\r\nerror: %v", leafKey, err)
+				}
+				diff.StorageDiff = storageDiff
+				if err := output(diff); err != nil {
+					return nil, err
+				}
+			}
+		}
+	}
+	return diffAccountAtA, it.Error()
+}
+
+// buildAccountUpdates uses the account diffs maps for A => B and B => A and the known intersection of their leafkeys
+// to generate the statediff node objects for all of the accounts that existed at both A and B but in different states
+// needs to be called before building account creations and deletions as this mutates
+// those account maps to remove the accounts which were updated
+func (sdb *StateDiffBuilder) buildAccountUpdates(creations, deletions types2.AccountMap, updatedKeys []string,
+	output types2.StateNodeSink, ipldOutput types2.IPLDSink, logger log.Logger) error {
+	logger.Debug("statediff BEGIN buildAccountUpdates", "creations", len(creations), "deletions", len(deletions), "updatedKeys", len(updatedKeys))
+	defer metrics2.ReportAndUpdateDuration("statediff END buildAccountUpdates ", time.Now(), logger, metrics2.IndexerMetrics.BuildAccountUpdatesTimer)
+	var err error
+	for _, key := range updatedKeys {
+		createdAcc := creations[key]
+		deletedAcc := deletions[key]
+		storageDiff := make([]types2.StorageLeafNode, 0)
+		if deletedAcc.Account != nil && createdAcc.Account != nil {
+			oldSR := deletedAcc.Account.Root
+			newSR := createdAcc.Account.Root
+			err = sdb.buildStorageNodesIncremental(
+				oldSR, newSR, StorageNodeAppender(&storageDiff), ipldOutput)
+			if err != nil {
+				return fmt.Errorf("failed building incremental storage diffs for account with leafkey %s\r\nerror: %v", key, err)
+			}
+		}
+		if err = output(types2.StateLeafNode{
+			AccountWrapper: createdAcc,
+			Removed:        false,
+			StorageDiff:    storageDiff,
+		}); err != nil {
+			return err
+		}
+		delete(creations, key)
+		delete(deletions, key)
+	}
+
+	return nil
+}
+
+// buildAccountCreations returns the statediff node objects for all the accounts that exist at B but not at A
+// it also returns the code and codehash for created contract accounts
+func (sdb *StateDiffBuilder) buildAccountCreations(accounts types2.AccountMap, output types2.StateNodeSink,
+	ipldOutput types2.IPLDSink, logger log.Logger) error {
+	logger.Debug("statediff BEGIN buildAccountCreations")
+	defer metrics2.ReportAndUpdateDuration("statediff END buildAccountCreations", time.Now(), logger, metrics2.IndexerMetrics.BuildAccountCreationsTimer)
+	for _, val := range accounts {
+		diff := types2.StateLeafNode{
+			AccountWrapper: val,
+			Removed:        false,
+		}
+		if !bytes.Equal(val.Account.CodeHash, nullCodeHash) {
+			// For contract creations, any storage node contained is a diff
+			storageDiff := make([]types2.StorageLeafNode, 0)
+			err := sdb.buildStorageNodesEventual(val.Account.Root, StorageNodeAppender(&storageDiff), ipldOutput)
+			if err != nil {
+				return fmt.Errorf("failed building eventual storage diffs for node with leaf key %x\r\nerror: %v", val.LeafKey, err)
+			}
+			diff.StorageDiff = storageDiff
+			// emit codehash => code mappings for contract
+			codeHash := common.BytesToHash(val.Account.CodeHash)
+			code, err := sdb.StateCache.ContractCode(common.Hash{}, codeHash)
+			if err != nil {
+				return fmt.Errorf("failed to retrieve code for codehash %s\r\n error: %v", codeHash.String(), err)
+			}
+			if err := ipldOutput(types2.IPLD{
+				CID:     ipld2.Keccak256ToCid(ipld2.RawBinary, codeHash.Bytes()).String(),
+				Content: code,
+			}); err != nil {
+				return err
+			}
+		}
+		if err := output(diff); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// buildStorageNodesEventual builds the storage diff node objects for a created account
+// i.e. it returns all the storage nodes at this state, since there is no previous state
+func (sdb *StateDiffBuilder) buildStorageNodesEventual(sr common.Hash, output types2.StorageNodeSink,
+	ipldOutput types2.IPLDSink) error {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.BuildStorageNodesEventualTimer)
+	if bytes.Equal(sr.Bytes(), emptyContractRoot.Bytes()) {
+		return nil
+	}
+	log.Debug("Storage Root For Eventual Diff", "root", sr.Hex())
+	sTrie, err := sdb.StateCache.OpenTrie(sr)
+	if err != nil {
+		log.Info("error in build storage diff eventual", "error", err)
+		return err
+	}
+	it := sTrie.NodeIterator(make([]byte, 0))
+	err = sdb.buildStorageNodesFromTrie(it, output, ipldOutput)
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+// buildStorageNodesFromTrie returns all the storage diff node objects in the provided node interator
+// including intermediate nodes can be turned on or off
+func (sdb *StateDiffBuilder) buildStorageNodesFromTrie(it trie.NodeIterator, output types2.StorageNodeSink,
+	ipldOutput types2.IPLDSink) error {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.BuildStorageNodesFromTrieTimer)
+	for it.Next(true) {
+		if it.Leaf() {
+			storageLeafNode, err := sdb.processStorageValueNode(it)
+			if err != nil {
+				return err
+			}
+			if err := output(storageLeafNode); err != nil {
+				return err
+			}
+		} else {
+			nodeVal := make([]byte, len(it.NodeBlob()))
+			copy(nodeVal, it.NodeBlob())
+			nodeHash := make([]byte, len(it.Hash().Bytes()))
+			copy(nodeHash, it.Hash().Bytes())
+			if err := ipldOutput(types2.IPLD{
+				CID:     ipld2.Keccak256ToCid(ipld2.MEthStorageTrie, nodeHash).String(),
+				Content: nodeVal,
+			}); err != nil {
+				return err
+			}
+		}
+	}
+	return it.Error()
+}
+
+// reminder: it.Leaf() == true when the iterator is positioned at a "value node" which is not something that actually exists in an MMPT
+func (sdb *StateDiffBuilder) processStorageValueNode(it trie.NodeIterator) (types2.StorageLeafNode, error) {
+	// skip if it is not a watched address
+	leafKey := make([]byte, len(it.LeafKey()))
+	copy(leafKey, it.LeafKey())
+	value := make([]byte, len(it.LeafBlob()))
+	copy(value, it.LeafBlob())
+
+	// since this is a "value node", we need to move up to the "parent" node which is the actual leaf node
+	// it should be in the fastcache since it necessarily was recently accessed to reach the current node
+	parentNodeRLP, err := sdb.StateCache.TrieDB().Node(it.Parent())
+	if err != nil {
+		return types2.StorageLeafNode{}, err
+	}
+
+	return types2.StorageLeafNode{
+		LeafKey: leafKey,
+		Value:   value,
+		CID:     ipld2.Keccak256ToCid(ipld2.MEthStorageTrie, crypto.Keccak256(parentNodeRLP)).String(),
+	}, nil
+}
+
+// buildRemovedAccountStorageNodes builds the "removed" diffs for all the storage nodes for a destroyed account
+func (sdb *StateDiffBuilder) buildRemovedAccountStorageNodes(sr common.Hash, output types2.StorageNodeSink) error {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.BuildRemovedAccountStorageNodesTimer)
+	if bytes.Equal(sr.Bytes(), emptyContractRoot.Bytes()) {
+		return nil
+	}
+	log.Debug("Storage Root For Removed Diffs", "root", sr.Hex())
+	sTrie, err := sdb.StateCache.OpenTrie(sr)
+	if err != nil {
+		log.Info("error in build removed account storage diffs", "error", err)
+		return err
+	}
+	it := sTrie.NodeIterator(make([]byte, 0))
+	err = sdb.buildRemovedStorageNodesFromTrie(it, output)
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+// buildRemovedStorageNodesFromTrie returns diffs for all the storage nodes in the provided node interator
+func (sdb *StateDiffBuilder) buildRemovedStorageNodesFromTrie(it trie.NodeIterator, output types2.StorageNodeSink) error {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.BuildRemovedStorageNodesFromTrieTimer)
+	for it.Next(true) {
+		if it.Leaf() { // only leaf values are indexed, don't need to demarcate removed intermediate nodes
+			leafKey := make([]byte, len(it.LeafKey()))
+			copy(leafKey, it.LeafKey())
+			if err := output(types2.StorageLeafNode{
+				CID:     shared.RemovedNodeStorageCID,
+				Removed: true,
+				LeafKey: leafKey,
+				Value:   []byte{},
+			}); err != nil {
+				return err
+			}
+		}
+	}
+	return it.Error()
+}
+
+// buildStorageNodesIncremental builds the storage diff node objects for all nodes that exist in a different state at B than A
+func (sdb *StateDiffBuilder) buildStorageNodesIncremental(oldSR common.Hash, newSR common.Hash, output types2.StorageNodeSink,
+	ipldOutput types2.IPLDSink) error {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.BuildStorageNodesIncrementalTimer)
+	if bytes.Equal(newSR.Bytes(), oldSR.Bytes()) {
+		return nil
+	}
+	log.Trace("Storage Roots for Incremental Diff", "old", oldSR.Hex(), "new", newSR.Hex())
+	oldTrie, err := sdb.StateCache.OpenTrie(oldSR)
+	if err != nil {
+		return err
+	}
+	newTrie, err := sdb.StateCache.OpenTrie(newSR)
+	if err != nil {
+		return err
+	}
+
+	diffSlotsAtB, err := sdb.createdAndUpdatedStorage(
+		oldTrie.NodeIterator([]byte{}), newTrie.NodeIterator([]byte{}), output, ipldOutput)
+	if err != nil {
+		return err
+	}
+	err = sdb.deletedOrUpdatedStorage(oldTrie.NodeIterator([]byte{}), newTrie.NodeIterator([]byte{}),
+		diffSlotsAtB, output)
+	if err != nil {
+		return err
+	}
+	return nil
+}
+
+func (sdb *StateDiffBuilder) createdAndUpdatedStorage(a, b trie.NodeIterator, output types2.StorageNodeSink,
+	ipldOutput types2.IPLDSink) (map[string]bool, error) {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.CreatedAndUpdatedStorageTimer)
+	diffSlotsAtB := make(map[string]bool)
+	it, _ := trie.NewDifferenceIterator(a, b)
+	for it.Next(true) {
+		if it.Leaf() {
+			storageLeafNode, err := sdb.processStorageValueNode(it)
+			if err != nil {
+				return nil, err
+			}
+			if err := output(storageLeafNode); err != nil {
+				return nil, err
+			}
+			diffSlotsAtB[common.Bytes2Hex(storageLeafNode.LeafKey)] = true
+		} else {
+			if bytes.Equal(it.Hash().Bytes(), nullNodeHash) {
+				continue
+			}
+			nodeVal := make([]byte, len(it.NodeBlob()))
+			copy(nodeVal, it.NodeBlob())
+			nodeHash := make([]byte, len(it.Hash().Bytes()))
+			copy(nodeHash, it.Hash().Bytes())
+			if err := ipldOutput(types2.IPLD{
+				CID:     ipld2.Keccak256ToCid(ipld2.MEthStorageTrie, nodeHash).String(),
+				Content: nodeVal,
+			}); err != nil {
+				return nil, err
+			}
+		}
+	}
+	return diffSlotsAtB, it.Error()
+}
+
+func (sdb *StateDiffBuilder) deletedOrUpdatedStorage(a, b trie.NodeIterator, diffSlotsAtB map[string]bool, output types2.StorageNodeSink) error {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.DeletedOrUpdatedStorageTimer)
+	it, _ := trie.NewDifferenceIterator(b, a)
+	for it.Next(true) {
+		if it.Leaf() {
+			leafKey := make([]byte, len(it.LeafKey()))
+			copy(leafKey, it.LeafKey())
+			// if this node's leaf key did not show up in diffSlotsAtB
+			// that means the storage slot was vacated
+			// in that case, emit an empty "removed" diff storage node
+			if _, ok := diffSlotsAtB[common.Bytes2Hex(leafKey)]; !ok {
+				if err := output(types2.StorageLeafNode{
+					CID:     shared.RemovedNodeStorageCID,
+					Removed: true,
+					LeafKey: leafKey,
+					Value:   []byte{},
+				}); err != nil {
+					return err
+				}
+			}
+		}
+	}
+	return it.Error()
+}
+
+// isValidPrefixPath is used to check if a node at currentPath is a parent | ancestor to one of the addresses the builder is configured to watch
+func isValidPrefixPath(watchedAddressesLeafPaths [][]byte, currentPath []byte) bool {
+	for _, watchedAddressPath := range watchedAddressesLeafPaths {
+		if bytes.HasPrefix(watchedAddressPath, currentPath) {
+			return true
+		}
+	}
+
+	return false
+}
+
+// isWatchedAddress is used to check if a state account corresponds to one of the addresses the builder is configured to watch
+func isWatchedAddress(watchedAddressesLeafPaths [][]byte, valueNodePath []byte) bool {
+	defer metrics2.UpdateDuration(time.Now(), metrics2.IndexerMetrics.IsWatchedAddressTimer)
+	for _, watchedAddressPath := range watchedAddressesLeafPaths {
+		if bytes.Equal(watchedAddressPath, valueNodePath) {
+			return true
+		}
+	}
+
+	return false
+}
+
+// isLeaf checks if the node we are at is a leaf
+func isLeaf(elements []interface{}) (bool, error) {
+	if len(elements) > 2 {
+		return false, nil
+	}
+	if len(elements) < 2 {
+		return false, fmt.Errorf("node cannot be less than two elements in length")
+	}
+	switch elements[0].([]byte)[0] / 16 {
+	case '\x00':
+		return false, nil
+	case '\x01':
+		return false, nil
+	case '\x02':
+		return true, nil
+	case '\x03':
+		return true, nil
+	default:
+		return false, fmt.Errorf("unknown hex prefix")
+	}
+}

statediff/config.go

@@ -0,0 +1,87 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package statediff
+
+import (
+	"context"
+	"math/big"
+	"sync"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/crypto"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+)
+
+// Config contains instantiation parameters for the state diffing service
+type Config struct {
+	// The configuration used for the stateDiff Indexer
+	IndexerConfig interfaces.Config
+	// A unique ID used for this service
+	ID string
+	// Name for the client this service is running
+	ClientName string
+	// Whether to enable writing state diffs directly to track blockchain head
+	EnableWriteLoop bool
+	// Size of the worker pool
+	NumWorkers uint
+	// Should the statediff service wait until geth has synced to the head of the blockchain?
+	WaitForSync bool
+	// Context
+	Context context.Context
+}
+
+// Params contains config parameters for the state diff builder
+type Params struct {
+	IncludeBlock              bool
+	IncludeReceipts           bool
+	IncludeTD                 bool
+	IncludeCode               bool
+	WatchedAddresses          []common.Address
+	watchedAddressesLeafPaths [][]byte
+}
+
+// ComputeWatchedAddressesLeafPaths populates a slice with paths (hex_encoding(Keccak256)) of each of the WatchedAddresses
+func (p *Params) ComputeWatchedAddressesLeafPaths() {
+	p.watchedAddressesLeafPaths = make([][]byte, len(p.WatchedAddresses))
+	for i, address := range p.WatchedAddresses {
+		p.watchedAddressesLeafPaths[i] = keybytesToHex(crypto.Keccak256(address.Bytes()))
+	}
+}
+
+// ParamsWithMutex allows to lock the parameters while they are being updated | read from
+type ParamsWithMutex struct {
+	Params
+	sync.RWMutex
+}
+
+// Args bundles the arguments for the state diff builder
+type Args struct {
+	OldStateRoot, NewStateRoot, BlockHash common.Hash
+	BlockNumber                           *big.Int
+}
+
+// https://github.com/ethereum/go-ethereum/blob/master/trie/encoding.go#L97
+func keybytesToHex(str []byte) []byte {
+	l := len(str)*2 + 1
+	var nibbles = make([]byte, l)
+	for i, b := range str {
+		nibbles[i*2] = b / 16
+		nibbles[i*2+1] = b % 16
+	}
+	nibbles[l-1] = 16
+	return nibbles
+}

statediff/docs/KnownGaps.md

@@ -0,0 +1,17 @@
+# Overview
+
+This document will provide some insight into the `known_gaps` table, their use cases, and implementation. Please refer to the [following PR](https://github.com/vulcanize/go-ethereum/pull/217) and the [following epic](https://github.com/vulcanize/ops/issues/143) to grasp their inception.
+
+![known gaps](diagrams/KnownGapsProcess.png)
+
+# Use Cases
+
+The known gaps table is updated when the following events occur:
+
+1. At start up we check the latest block from the `eth.headers_cid` table. We compare the first block that we are processing with the latest block from the DB. If they are not one unit of expectedDifference away from each other, add the gap between the two blocks.
+2. If there is any error in processing a block (db connection, deadlock, etc), add that block to the knownErrorBlocks slice, when the next block is successfully written, write this slice into the DB.
+
+# Glossary
+
+1. `expectedDifference (number)` - This number indicates what the difference between two blocks should be. If we are capturing all events on a geth node then this number would be `1`. But once we scale nodes, the `expectedDifference` might be `2` or greater.
+2. `processingKey (number)` - This number can be used to keep track of different geth nodes and their specific `expectedDifference`.

statediff/docs/README.md

@@ -0,0 +1,3 @@
+# Overview
+
+This folder keeps tracks of random documents as they relate to the `statediff` service.

statediff/docs/database.md

@@ -0,0 +1,21 @@
+# Overview
+
+This document will go through some notes on the database component of the statediff service.
+
+# Components
+
+- Indexer: The indexer creates IPLD and DB models to insert to the Postgres DB. It performs the insert utilizing and atomic function.
+- Builder: The builder constructs the statediff object that needs to be inserted.
+- Known Gaps: Captures any gaps that might have occured and either writes them to the DB, local sql file, to prometeus, or a local error.
+
+# Making Code Changes
+
+## Adding a New Function to the Indexer
+
+If you want to implement a new feature for adding data to the database. Keep the following in mind:
+
+1. You need to handle `sql`, `file`, and `dump`.
+   1. `sql` - Contains the code needed to write directly to the `sql` db.
+   2. `file` - Contains all the code required to write the SQL statements to a file.
+   3. `dump` - Contains all the code for outputting events to the console.
+2. You will have to add it to the `interfaces.StateDiffIndexer` interface.

statediff/helpers.go

@@ -0,0 +1,63 @@
+// VulcanizeDB
+// Copyright © 2022 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package statediff
+
+import (
+	"encoding/json"
+	"fmt"
+	"os"
+
+	"github.com/ethereum/go-ethereum/log"
+
+	"github.com/ethereum/go-ethereum/params"
+)
+
+// LoadConfig loads chain config from json file
+func LoadConfig(chainConfigPath string) (*params.ChainConfig, error) {
+	file, err := os.Open(chainConfigPath)
+	if err != nil {
+		log.Error(fmt.Sprintf("Failed to read chain config file: %v", err))
+
+		return nil, err
+	}
+	defer file.Close()
+
+	chainConfig := new(params.ChainConfig)
+	if err := json.NewDecoder(file).Decode(chainConfig); err != nil {
+		log.Error(fmt.Sprintf("invalid chain config file: %v", err))
+
+		return nil, err
+	}
+
+	log.Info(fmt.Sprintf("Using chain config from %s file. Content %+v", chainConfigPath, chainConfig))
+
+	return chainConfig, nil
+}
+
+// ChainConfig returns the appropriate ethereum chain config for the provided chain id
+func ChainConfig(chainID uint64) (*params.ChainConfig, error) {
+	switch chainID {
+	case 1:
+		return params.MainnetChainConfig, nil
+	case 4:
+		return params.RinkebyChainConfig, nil
+	case 5:
+		return params.GoerliChainConfig, nil
+	default:
+		return nil, fmt.Errorf("chain config for chainid %d not available", chainID)
+	}
+}

statediff/indexer/constructor.go

@@ -0,0 +1,81 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package indexer
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/dump"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/file"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/node"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+)
+
+// NewStateDiffIndexer creates and returns an implementation of the StateDiffIndexer interface.
+func NewStateDiffIndexer(ctx context.Context, chainConfig *params.ChainConfig, nodeInfo node.Info, config interfaces.Config) (sql.Database, interfaces.StateDiffIndexer, error) {
+	switch config.Type() {
+	case shared.FILE:
+		log.Info("Starting statediff service in SQL file writing mode")
+		fc, ok := config.(file.Config)
+		if !ok {
+			return nil, nil, fmt.Errorf("file config is not the correct type: got %T, expected %T", config, file.Config{})
+		}
+		fc.NodeInfo = nodeInfo
+		ind, err := file.NewStateDiffIndexer(ctx, chainConfig, fc)
+		return nil, ind, err
+	case shared.POSTGRES:
+		log.Info("Starting statediff service in Postgres writing mode")
+		pgc, ok := config.(postgres.Config)
+		if !ok {
+			return nil, nil, fmt.Errorf("postgres config is not the correct type: got %T, expected %T", config, postgres.Config{})
+		}
+		var err error
+		var driver sql.Driver
+		switch pgc.Driver {
+		case postgres.PGX:
+			driver, err = postgres.NewPGXDriver(ctx, pgc, nodeInfo)
+			if err != nil {
+				return nil, nil, err
+			}
+		case postgres.SQLX:
+			driver, err = postgres.NewSQLXDriver(ctx, pgc, nodeInfo)
+			if err != nil {
+				return nil, nil, err
+			}
+		default:
+			return nil, nil, fmt.Errorf("unrecognized Postgres driver type: %s", pgc.Driver)
+		}
+		db := postgres.NewPostgresDB(driver, pgc.Upsert)
+		ind, err := sql.NewStateDiffIndexer(ctx, chainConfig, db)
+		return db, ind, err
+	case shared.DUMP:
+		log.Info("Starting statediff service in data dump mode")
+		dumpc, ok := config.(dump.Config)
+		if !ok {
+			return nil, nil, fmt.Errorf("dump config is not the correct type: got %T, expected %T", config, dump.Config{})
+		}
+		return nil, dump.NewStateDiffIndexer(chainConfig, dumpc), nil
+	default:
+		return nil, nil, fmt.Errorf("unrecognized database type: %s", config.Type())
+	}
+}

statediff/indexer/database/dump/batch_tx.go

@@ -0,0 +1,80 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package dump
+
+import (
+	"fmt"
+	"io"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+)
+
+// BatchTx wraps a void with the state necessary for building the tx concurrently during trie difference iteration
+type BatchTx struct {
+	BlockNumber string
+	dump        io.Writer
+	quit        chan struct{}
+	iplds       chan models.IPLDModel
+	ipldCache   models.IPLDBatch
+
+	submit func(blockTx *BatchTx, err error) error
+}
+
+// Submit satisfies indexer.AtomicTx
+func (tx *BatchTx) Submit(err error) error {
+	return tx.submit(tx, err)
+}
+
+func (tx *BatchTx) flush() error {
+	if _, err := fmt.Fprintf(tx.dump, "%+v\r\n", tx.ipldCache); err != nil {
+		return err
+	}
+	tx.ipldCache = models.IPLDBatch{}
+	return nil
+}
+
+// run in background goroutine to synchronize concurrent appends to the ipldCache
+func (tx *BatchTx) cache() {
+	for {
+		select {
+		case i := <-tx.iplds:
+			tx.ipldCache.Keys = append(tx.ipldCache.Keys, i.Key)
+			tx.ipldCache.Values = append(tx.ipldCache.Values, i.Data)
+		case <-tx.quit:
+			tx.ipldCache = models.IPLDBatch{}
+			return
+		}
+	}
+}
+
+func (tx *BatchTx) cacheDirect(key string, value []byte) {
+	tx.iplds <- models.IPLDModel{
+		BlockNumber: tx.BlockNumber,
+		Key:         key,
+		Data:        value,
+	}
+}
+
+func (tx *BatchTx) cacheIPLD(i ipld.IPLD) {
+	tx.iplds <- models.IPLDModel{
+		BlockNumber: tx.BlockNumber,
+		Key:         i.Cid().String(),
+		Data:        i.RawData(),
+	}
+}

statediff/indexer/database/dump/config.go

@@ -0,0 +1,79 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package dump
+
+import (
+	"fmt"
+	"io"
+	"strings"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+)
+
+// DumpType to explicitly type the dump destination
+type DumpType string
+
+const (
+	STDOUT  = "Stdout"
+	STDERR  = "Stderr"
+	DISCARD = "Discard"
+	UNKNOWN = "Unknown"
+)
+
+// ResolveDumpType resolves the dump type for the provided string
+func ResolveDumpType(str string) (DumpType, error) {
+	switch strings.ToLower(str) {
+	case "stdout", "out", "std out":
+		return STDOUT, nil
+	case "stderr", "err", "std err":
+		return STDERR, nil
+	case "discard", "void", "devnull", "dev null":
+		return DISCARD, nil
+	default:
+		return UNKNOWN, fmt.Errorf("unrecognized dump type: %s", str)
+	}
+}
+
+// Config for data dump
+type Config struct {
+	Dump io.WriteCloser
+}
+
+// Type satisfies interfaces.Config
+func (c Config) Type() shared.DBType {
+	return shared.DUMP
+}
+
+// NewDiscardWriterCloser returns a discardWrapper wrapping io.Discard
+func NewDiscardWriterCloser() io.WriteCloser {
+	return discardWrapper{blackhole: io.Discard}
+}
+
+// discardWrapper wraps io.Discard with io.Closer
+type discardWrapper struct {
+	blackhole io.Writer
+}
+
+// Write satisfies io.Writer
+func (dw discardWrapper) Write(b []byte) (int, error) {
+	return dw.blackhole.Write(b)
+}
+
+// Close satisfies io.Closer
+func (dw discardWrapper) Close() error {
+	return nil
+}

statediff/indexer/database/dump/indexer.go

@@ -0,0 +1,443 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package dump
+
+import (
+	"bytes"
+	"fmt"
+	"io"
+	"math/big"
+	"time"
+
+	"github.com/multiformats/go-multihash"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/crypto"
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/rlp"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+	sdtypes "github.com/ethereum/go-ethereum/statediff/types"
+)
+
+var _ interfaces.StateDiffIndexer = &StateDiffIndexer{}
+
+// StateDiffIndexer satisfies the indexer.StateDiffIndexer interface for ethereum statediff objects on top of a void
+type StateDiffIndexer struct {
+	dump        io.WriteCloser
+	chainConfig *params.ChainConfig
+}
+
+// NewStateDiffIndexer creates a void implementation of interfaces.StateDiffIndexer
+func NewStateDiffIndexer(chainConfig *params.ChainConfig, config Config) *StateDiffIndexer {
+	return &StateDiffIndexer{
+		dump:        config.Dump,
+		chainConfig: chainConfig,
+	}
+}
+
+// ReportDBMetrics has nothing to report for dump
+func (sdi *StateDiffIndexer) ReportDBMetrics(time.Duration, <-chan bool) {}
+
+// PushBlock pushes and indexes block data in sql, except state & storage nodes (includes header, uncles, transactions & receipts)
+// Returns an initiated DB transaction which must be Closed via defer to commit or rollback
+func (sdi *StateDiffIndexer) PushBlock(block *types.Block, receipts types.Receipts, totalDifficulty *big.Int) (interfaces.Batch, error) {
+	start, t := time.Now(), time.Now()
+	blockHash := block.Hash()
+	blockHashStr := blockHash.String()
+	height := block.NumberU64()
+	traceMsg := fmt.Sprintf("indexer stats for statediff at %d with hash %s:\r\n", height, blockHashStr)
+	transactions := block.Transactions()
+	// Derive any missing fields
+	if err := receipts.DeriveFields(sdi.chainConfig, blockHash, height, block.BaseFee(), transactions); err != nil {
+		return nil, err
+	}
+
+	// Generate the block iplds
+	headerNode, txNodes, rctNodes, logNodes, err := ipld.FromBlockAndReceipts(block, receipts)
+	if err != nil {
+		return nil, fmt.Errorf("error creating IPLD nodes from block and receipts: %v", err)
+	}
+
+	if len(txNodes) != len(rctNodes) {
+		return nil, fmt.Errorf("expected number of transactions (%d), receipts (%d)", len(txNodes), len(rctNodes))
+	}
+
+	// Calculate reward
+	var reward *big.Int
+	// in PoA networks block reward is 0
+	if sdi.chainConfig.Clique != nil {
+		reward = big.NewInt(0)
+	} else {
+		reward = shared.CalcEthBlockReward(block.Header(), block.Uncles(), block.Transactions(), receipts)
+	}
+	t = time.Now()
+
+	blockTx := &BatchTx{
+		BlockNumber: block.Number().String(),
+		dump:        sdi.dump,
+		iplds:       make(chan models.IPLDModel),
+		quit:        make(chan struct{}),
+		ipldCache:   models.IPLDBatch{},
+		submit: func(self *BatchTx, err error) error {
+			close(self.quit)
+			close(self.iplds)
+			tDiff := time.Since(t)
+			metrics.IndexerMetrics.StateStoreCodeProcessingTimer.Update(tDiff)
+			traceMsg += fmt.Sprintf("state, storage, and code storage processing time: %s\r\n", tDiff.String())
+			t = time.Now()
+			if err := self.flush(); err != nil {
+				traceMsg += fmt.Sprintf(" TOTAL PROCESSING DURATION: %s\r\n", time.Since(start).String())
+				log.Debug(traceMsg)
+				return err
+			}
+			tDiff = time.Since(t)
+			metrics.IndexerMetrics.PostgresCommitTimer.Update(tDiff)
+			traceMsg += fmt.Sprintf("postgres transaction commit duration: %s\r\n", tDiff.String())
+			traceMsg += fmt.Sprintf(" TOTAL PROCESSING DURATION: %s\r\n", time.Since(start).String())
+			log.Debug(traceMsg)
+			return err
+		},
+	}
+	go blockTx.cache()
+
+	tDiff := time.Since(t)
+	metrics.IndexerMetrics.FreePostgresTimer.Update(tDiff)
+
+	traceMsg += fmt.Sprintf("time spent waiting for free postgres tx: %s:\r\n", tDiff.String())
+	t = time.Now()
+
+	// Publish and index header, collect headerID
+	var headerID string
+	headerID, err = sdi.processHeader(blockTx, block.Header(), headerNode, reward, totalDifficulty)
+	if err != nil {
+		return nil, err
+	}
+	tDiff = time.Since(t)
+	metrics.IndexerMetrics.HeaderProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("header processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+	// Publish and index uncles
+	err = sdi.processUncles(blockTx, headerID, block.Number(), block.UncleHash(), block.Uncles())
+	if err != nil {
+		return nil, err
+	}
+	tDiff = time.Since(t)
+	metrics.IndexerMetrics.UncleProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("uncle processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+	// Publish and index receipts and txs
+	err = sdi.processReceiptsAndTxs(blockTx, processArgs{
+		headerID:    headerID,
+		blockNumber: block.Number(),
+		receipts:    receipts,
+		txs:         transactions,
+		rctNodes:    rctNodes,
+		txNodes:     txNodes,
+		logNodes:    logNodes,
+	})
+	if err != nil {
+		return nil, err
+	}
+	tDiff = time.Since(t)
+	metrics.IndexerMetrics.TxAndRecProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("tx and receipt processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+
+	return blockTx, err
+}
+
+// processHeader publishes and indexes a header IPLD in Postgres
+// it returns the headerID
+func (sdi *StateDiffIndexer) processHeader(tx *BatchTx, header *types.Header, headerNode ipld.IPLD, reward, td *big.Int) (string, error) {
+	tx.cacheIPLD(headerNode)
+
+	headerID := header.Hash().String()
+	mod := models.HeaderModel{
+		CID:             headerNode.Cid().String(),
+		ParentHash:      header.ParentHash.String(),
+		BlockNumber:     header.Number.String(),
+		BlockHash:       headerID,
+		TotalDifficulty: td.String(),
+		Reward:          reward.String(),
+		Bloom:           header.Bloom.Bytes(),
+		StateRoot:       header.Root.String(),
+		RctRoot:         header.ReceiptHash.String(),
+		TxRoot:          header.TxHash.String(),
+		UnclesHash:      header.UncleHash.String(),
+		Timestamp:       header.Time,
+		Coinbase:        header.Coinbase.String(),
+	}
+	_, err := fmt.Fprintf(sdi.dump, "%+v\r\n", mod)
+	return headerID, err
+}
+
+// processUncles publishes and indexes uncle IPLDs in Postgres
+func (sdi *StateDiffIndexer) processUncles(tx *BatchTx, headerID string, blockNumber *big.Int, unclesHash common.Hash, uncles []*types.Header) error {
+	// publish and index uncles
+	uncleEncoding, err := rlp.EncodeToBytes(uncles)
+	if err != nil {
+		return err
+	}
+	preparedHash := crypto.Keccak256Hash(uncleEncoding)
+	if !bytes.Equal(preparedHash.Bytes(), unclesHash.Bytes()) {
+		return fmt.Errorf("derived uncles hash (%s) does not match the hash in the header (%s)", preparedHash.Hex(), unclesHash.Hex())
+	}
+	unclesCID, err := ipld.RawdataToCid(ipld.MEthHeaderList, uncleEncoding, multihash.KECCAK_256)
+	if err != nil {
+		return err
+	}
+	tx.cacheDirect(unclesCID.String(), uncleEncoding)
+	for i, uncle := range uncles {
+		var uncleReward *big.Int
+		// in PoA networks uncle reward is 0
+		if sdi.chainConfig.Clique != nil {
+			uncleReward = big.NewInt(0)
+		} else {
+			uncleReward = shared.CalcUncleMinerReward(blockNumber.Uint64(), uncle.Number.Uint64())
+		}
+		uncle := models.UncleModel{
+			BlockNumber: blockNumber.String(),
+			HeaderID:    headerID,
+			CID:         unclesCID.String(),
+			ParentHash:  uncle.ParentHash.String(),
+			BlockHash:   uncle.Hash().String(),
+			Reward:      uncleReward.String(),
+			Index:       int64(i),
+		}
+		if _, err := fmt.Fprintf(sdi.dump, "%+v\r\n", uncle); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// processArgs bundles arguments to processReceiptsAndTxs
+type processArgs struct {
+	headerID    string
+	blockNumber *big.Int
+	receipts    types.Receipts
+	txs         types.Transactions
+	rctNodes    []*ipld.EthReceipt
+	txNodes     []*ipld.EthTx
+	logNodes    [][]*ipld.EthLog
+}
+
+// processReceiptsAndTxs publishes and indexes receipt and transaction IPLDs in Postgres
+func (sdi *StateDiffIndexer) processReceiptsAndTxs(tx *BatchTx, args processArgs) error {
+	// Process receipts and txs
+	signer := types.MakeSigner(sdi.chainConfig, args.blockNumber)
+	for i, receipt := range args.receipts {
+		txNode := args.txNodes[i]
+		tx.cacheIPLD(txNode)
+
+		// Indexing
+		// index tx
+		trx := args.txs[i]
+		trxID := trx.Hash().String()
+
+		var val string
+		if trx.Value() != nil {
+			val = trx.Value().String()
+		}
+
+		// derive sender for the tx that corresponds with this receipt
+		from, err := types.Sender(signer, trx)
+		if err != nil {
+			return fmt.Errorf("error deriving tx sender: %v", err)
+		}
+		txModel := models.TxModel{
+			BlockNumber: args.blockNumber.String(),
+			HeaderID:    args.headerID,
+			Dst:         shared.HandleZeroAddrPointer(trx.To()),
+			Src:         shared.HandleZeroAddr(from),
+			TxHash:      trxID,
+			Index:       int64(i),
+			CID:         txNode.Cid().String(),
+			Type:        trx.Type(),
+			Value:       val,
+		}
+		if _, err := fmt.Fprintf(sdi.dump, "%+v\r\n", txModel); err != nil {
+			return err
+		}
+
+		// this is the contract address if this receipt is for a contract creation tx
+		contract := shared.HandleZeroAddr(receipt.ContractAddress)
+
+		// index the receipt
+		rctModel := &models.ReceiptModel{
+			BlockNumber: args.blockNumber.String(),
+			HeaderID:    args.headerID,
+			TxID:        trxID,
+			Contract:    contract,
+			CID:         args.rctNodes[i].Cid().String(),
+		}
+		if len(receipt.PostState) == 0 {
+			rctModel.PostStatus = receipt.Status
+		} else {
+			rctModel.PostState = common.Bytes2Hex(receipt.PostState)
+		}
+
+		if _, err := fmt.Fprintf(sdi.dump, "%+v\r\n", rctModel); err != nil {
+			return err
+		}
+
+		logDataSet := make([]*models.LogsModel, len(receipt.Logs))
+		for idx, l := range receipt.Logs {
+			topicSet := make([]string, 4)
+			for ti, topic := range l.Topics {
+				topicSet[ti] = topic.Hex()
+			}
+
+			logDataSet[idx] = &models.LogsModel{
+				BlockNumber: args.blockNumber.String(),
+				HeaderID:    args.headerID,
+				ReceiptID:   trxID,
+				Address:     l.Address.String(),
+				Index:       int64(l.Index),
+				CID:         args.logNodes[i][idx].Cid().String(),
+				Topic0:      topicSet[0],
+				Topic1:      topicSet[1],
+				Topic2:      topicSet[2],
+				Topic3:      topicSet[3],
+			}
+		}
+
+		if _, err := fmt.Fprintf(sdi.dump, "%+v\r\n", logDataSet); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// PushStateNode publishes and indexes a state diff node object (including any child storage nodes) in the IPLD sql
+func (sdi *StateDiffIndexer) PushStateNode(batch interfaces.Batch, stateNode sdtypes.StateLeafNode, headerID string) error {
+	tx, ok := batch.(*BatchTx)
+	if !ok {
+		return fmt.Errorf("dump: batch is expected to be of type %T, got %T", &BatchTx{}, batch)
+	}
+	// publish the state node
+	var stateModel models.StateNodeModel
+	if stateNode.Removed {
+		// short circuit if it is a Removed node
+		// this assumes the db has been initialized and a ipld.blocks entry for the Removed node is present
+		stateModel = models.StateNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			CID:         shared.RemovedNodeStateCID,
+			Removed:     true,
+		}
+	} else {
+		stateModel = models.StateNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			CID:         stateNode.AccountWrapper.CID,
+			Removed:     false,
+			Balance:     stateNode.AccountWrapper.Account.Balance.String(),
+			Nonce:       stateNode.AccountWrapper.Account.Nonce,
+			CodeHash:    common.BytesToHash(stateNode.AccountWrapper.Account.CodeHash).String(),
+			StorageRoot: stateNode.AccountWrapper.Account.Root.String(),
+		}
+	}
+
+	// index the state node, collect the stateID to reference by FK
+	if _, err := fmt.Fprintf(sdi.dump, "%+v\r\n", stateModel); err != nil {
+		return err
+	}
+
+	// if there are any storage nodes associated with this node, publish and index them
+	for _, storageNode := range stateNode.StorageDiff {
+		if storageNode.Removed {
+			// short circuit if it is a Removed node
+			// this assumes the db has been initialized and a ipld.blocks entry for the Removed node is present
+			storageModel := models.StorageNodeModel{
+				BlockNumber: tx.BlockNumber,
+				HeaderID:    headerID,
+				StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+				StorageKey:  common.BytesToHash(storageNode.LeafKey).String(),
+				CID:         shared.RemovedNodeStorageCID,
+				Removed:     true,
+			}
+			if _, err := fmt.Fprintf(sdi.dump, "%+v\r\n", storageModel); err != nil {
+				return err
+			}
+			continue
+		}
+		storageModel := models.StorageNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			StorageKey:  common.BytesToHash(storageNode.LeafKey).String(),
+			CID:         storageNode.CID,
+			Removed:     false,
+			Value:       storageNode.Value,
+		}
+		if _, err := fmt.Fprintf(sdi.dump, "%+v\r\n", storageModel); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// PushIPLD publishes iplds to ipld.blocks
+func (sdi *StateDiffIndexer) PushIPLD(batch interfaces.Batch, ipld sdtypes.IPLD) error {
+	tx, ok := batch.(*BatchTx)
+	if !ok {
+		return fmt.Errorf("dump: batch is expected to be of type %T, got %T", &BatchTx{}, batch)
+	}
+	tx.cacheDirect(ipld.CID, ipld.Content)
+	return nil
+}
+
+// Close satisfies io.Closer
+func (sdi *StateDiffIndexer) Close() error {
+	return sdi.dump.Close()
+}
+
+// LoadWatchedAddresses satisfies the interfaces.StateDiffIndexer interface
+func (sdi *StateDiffIndexer) LoadWatchedAddresses() ([]common.Address, error) {
+	return nil, nil
+}
+
+// InsertWatchedAddresses satisfies the interfaces.StateDiffIndexer interface
+func (sdi *StateDiffIndexer) InsertWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) error {
+	return nil
+}
+
+// RemoveWatchedAddresses satisfies the interfaces.StateDiffIndexer interface
+func (sdi *StateDiffIndexer) RemoveWatchedAddresses(args []sdtypes.WatchAddressArg) error {
+	return nil
+}
+
+// SetWatchedAddresses satisfies the interfaces.StateDiffIndexer interface
+func (sdi *StateDiffIndexer) SetWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) error {
+	return nil
+}
+
+// ClearWatchedAddresses satisfies the interfaces.StateDiffIndexer interface
+func (sdi *StateDiffIndexer) ClearWatchedAddresses() error {
+	return nil
+}

statediff/indexer/database/file/batch_tx.go

@@ -0,0 +1,29 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file
+
+// BatchTx wraps a void with the state necessary for building the tx concurrently during trie difference iteration
+type BatchTx struct {
+	BlockNumber string
+
+	submit func(blockTx *BatchTx, err error) error
+}
+
+// Submit satisfies indexer.AtomicTx
+func (tx *BatchTx) Submit(err error) error {
+	return tx.submit(tx, err)
+}

statediff/indexer/database/file/config.go

@@ -0,0 +1,84 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file
+
+import (
+	"fmt"
+	"strings"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/node"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+)
+
+// FileMode to explicitly type the mode of file writer we are using
+type FileMode string
+
+const (
+	CSV     FileMode = "CSV"
+	SQL     FileMode = "SQL"
+	Unknown FileMode = "Unknown"
+)
+
+// ResolveFileMode resolves a FileMode from a provided string
+func ResolveFileMode(str string) (FileMode, error) {
+	switch strings.ToLower(str) {
+	case "csv":
+		return CSV, nil
+	case "sql":
+		return SQL, nil
+	default:
+		return Unknown, fmt.Errorf("unrecognized file type string: %s", str)
+	}
+}
+
+// Config holds params for writing out CSV or SQL files
+type Config struct {
+	Mode                     FileMode
+	OutputDir                string
+	FilePath                 string
+	WatchedAddressesFilePath string
+	NodeInfo                 node.Info
+}
+
+// Type satisfies interfaces.Config
+func (c Config) Type() shared.DBType {
+	return shared.FILE
+}
+
+var nodeInfo = node.Info{
+	GenesisBlock: "0xd4e56740f876aef8c010b86a40d5f56745a118d0906a34e69aec8c0db1cb8fa3",
+	NetworkID:    "1",
+	ChainID:      1,
+	ID:           "mockNodeID",
+	ClientName:   "go-ethereum",
+}
+
+// CSVTestConfig config for unit tests
+var CSVTestConfig = Config{
+	Mode:                     CSV,
+	OutputDir:                "./statediffing_test",
+	WatchedAddressesFilePath: "./statediffing_watched_addresses_test_file.csv",
+	NodeInfo:                 nodeInfo,
+}
+
+// SQLTestConfig config for unit tests
+var SQLTestConfig = Config{
+	Mode:                     SQL,
+	FilePath:                 "./statediffing_test_file.sql",
+	WatchedAddressesFilePath: "./statediffing_watched_addresses_test_file.sql",
+	NodeInfo:                 nodeInfo,
+}

statediff/indexer/database/file/csv_indexer_legacy_test.go

@@ -0,0 +1,118 @@
+// VulcanizeDB
+// Copyright © 2022 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file_test
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/file"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared/schema"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test_helpers"
+)
+
+const dbDirectory = "/file_indexer"
+const pgCopyStatement = `COPY %s FROM '%s' CSV`
+
+func setupLegacyCSVIndexer(t *testing.T) {
+	if _, err := os.Stat(file.CSVTestConfig.OutputDir); !errors.Is(err, os.ErrNotExist) {
+		err := os.RemoveAll(file.CSVTestConfig.OutputDir)
+		require.NoError(t, err)
+	}
+
+	ind, err = file.NewStateDiffIndexer(context.Background(), test.LegacyConfig, file.CSVTestConfig)
+	require.NoError(t, err)
+
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
+func setupLegacyCSV(t *testing.T) {
+	setupLegacyCSVIndexer(t)
+	test.SetupLegacyTestData(t, ind)
+}
+
+func dumpCSVFileData(t *testing.T) {
+	outputDir := filepath.Join(dbDirectory, file.CSVTestConfig.OutputDir)
+	workingDir, err := os.Getwd()
+	require.NoError(t, err)
+
+	localOutputDir := filepath.Join(workingDir, file.CSVTestConfig.OutputDir)
+
+	for _, tbl := range file.Tables {
+		err := test_helpers.DedupFile(file.TableFilePath(localOutputDir, tbl.Name))
+		require.NoError(t, err)
+
+		var stmt string
+		varcharColumns := tbl.VarcharColumns()
+		if len(varcharColumns) > 0 {
+			stmt = fmt.Sprintf(
+				pgCopyStatement+" FORCE NOT NULL %s",
+				tbl.Name,
+				file.TableFilePath(outputDir, tbl.Name),
+				strings.Join(varcharColumns, ", "),
+			)
+		} else {
+			stmt = fmt.Sprintf(pgCopyStatement, tbl.Name, file.TableFilePath(outputDir, tbl.Name))
+		}
+
+		_, err = db.Exec(context.Background(), stmt)
+		require.NoError(t, err)
+	}
+}
+
+func resetAndDumpWatchedAddressesCSVFileData(t *testing.T) {
+	test_helpers.TearDownDB(t, db)
+
+	outputFilePath := filepath.Join(dbDirectory, file.CSVTestConfig.WatchedAddressesFilePath)
+	stmt := fmt.Sprintf(pgCopyStatement, schema.TableWatchedAddresses.Name, outputFilePath)
+
+	_, err = db.Exec(context.Background(), stmt)
+	require.NoError(t, err)
+}
+
+func tearDownCSV(t *testing.T) {
+	test_helpers.TearDownDB(t, db)
+	require.NoError(t, db.Close())
+
+	require.NoError(t, os.RemoveAll(file.CSVTestConfig.OutputDir))
+
+	if err := os.Remove(file.CSVTestConfig.WatchedAddressesFilePath); !errors.Is(err, os.ErrNotExist) {
+		require.NoError(t, err)
+	}
+}
+
+func TestLegacyCSVFileIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs", func(t *testing.T) {
+		setupLegacyCSV(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestLegacyIndexer(t, db)
+	})
+}

statediff/indexer/database/file/csv_indexer_test.go

@@ -0,0 +1,255 @@
+// VulcanizeDB
+// Copyright © 2022 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file_test
+
+import (
+	"context"
+	"errors"
+	"math/big"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/file"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/mocks"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+)
+
+func setupCSVIndexer(t *testing.T) {
+	file.CSVTestConfig.OutputDir = "./statediffing_test"
+
+	if _, err := os.Stat(file.CSVTestConfig.OutputDir); !errors.Is(err, os.ErrNotExist) {
+		err := os.RemoveAll(file.CSVTestConfig.OutputDir)
+		require.NoError(t, err)
+	}
+
+	if _, err := os.Stat(file.CSVTestConfig.WatchedAddressesFilePath); !errors.Is(err, os.ErrNotExist) {
+		err := os.Remove(file.CSVTestConfig.WatchedAddressesFilePath)
+		require.NoError(t, err)
+	}
+
+	ind, err = file.NewStateDiffIndexer(context.Background(), mocks.TestConfig, file.CSVTestConfig)
+	require.NoError(t, err)
+
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
+func setupCSV(t *testing.T) {
+	setupCSVIndexer(t)
+	test.SetupTestData(t, ind)
+}
+
+func setupCSVNonCanonical(t *testing.T) {
+	setupCSVIndexer(t)
+	test.SetupTestDataNonCanonical(t, ind)
+}
+
+func TestCSVFileIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs in a single tx", func(t *testing.T) {
+		setupCSV(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexHeaderIPLDs(t, db)
+	})
+
+	t.Run("Publish and index transaction IPLDs in a single tx", func(t *testing.T) {
+		setupCSV(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexTransactionIPLDs(t, db)
+	})
+
+	t.Run("Publish and index log IPLDs for multiple receipt of a specific block", func(t *testing.T) {
+		setupCSV(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexLogIPLDs(t, db)
+	})
+
+	t.Run("Publish and index receipt IPLDs in a single tx", func(t *testing.T) {
+		setupCSV(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexReceiptIPLDs(t, db)
+	})
+
+	t.Run("Publish and index state IPLDs in a single tx", func(t *testing.T) {
+		setupCSV(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexStateIPLDs(t, db)
+	})
+
+	t.Run("Publish and index storage IPLDs in a single tx", func(t *testing.T) {
+		setupCSV(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexStorageIPLDs(t, db)
+	})
+}
+
+func TestCSVFileIndexerNonCanonical(t *testing.T) {
+	t.Run("Publish and index header", func(t *testing.T) {
+		setupCSVNonCanonical(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexHeaderNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index transactions", func(t *testing.T) {
+		setupCSVNonCanonical(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexTransactionsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index receipts", func(t *testing.T) {
+		setupCSVNonCanonical(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexReceiptsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index logs", func(t *testing.T) {
+		setupCSVNonCanonical(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexLogsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index state nodes", func(t *testing.T) {
+		setupCSVNonCanonical(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexStateNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index storage nodes", func(t *testing.T) {
+		setupCSVNonCanonical(t)
+		dumpCSVFileData(t)
+		defer tearDownCSV(t)
+
+		test.TestPublishAndIndexStorageNonCanonical(t, db)
+	})
+}
+
+func TestCSVFileWatchAddressMethods(t *testing.T) {
+	setupCSVIndexer(t)
+	defer tearDownCSV(t)
+
+	t.Run("Load watched addresses (empty table)", func(t *testing.T) {
+		test.TestLoadEmptyWatchedAddresses(t, ind)
+	})
+
+	t.Run("Insert watched addresses", func(t *testing.T) {
+		args := mocks.GetInsertWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt1)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestInsertWatchedAddresses(t, db)
+	})
+
+	t.Run("Insert watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetInsertAlreadyWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestInsertAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses", func(t *testing.T) {
+		args := mocks.GetRemoveWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestRemoveWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses (some non-watched)", func(t *testing.T) {
+		args := mocks.GetRemoveNonWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestRemoveNonWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses", func(t *testing.T) {
+		args := mocks.GetSetWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestSetWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetSetAlreadyWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt3)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestSetAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Load watched addresses", func(t *testing.T) {
+		test.TestLoadWatchedAddresses(t, ind)
+	})
+
+	t.Run("Clear watched addresses", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestClearWatchedAddresses(t, db)
+	})
+
+	t.Run("Clear watched addresses (empty table)", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesCSVFileData(t)
+
+		test.TestClearEmptyWatchedAddresses(t, db)
+	})
+}

statediff/indexer/database/file/csv_writer.go

@@ -0,0 +1,418 @@
+// VulcanizeDB
+// Copyright © 2022 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file
+
+import (
+	"encoding/csv"
+	"errors"
+	"fmt"
+	"math/big"
+	"os"
+	"path/filepath"
+	"strconv"
+
+	"github.com/thoas/go-funk"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+	nodeinfo "github.com/ethereum/go-ethereum/statediff/indexer/node"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared/schema"
+	sdtypes "github.com/ethereum/go-ethereum/statediff/types"
+)
+
+var (
+	Tables = []*schema.Table{
+		&schema.TableIPLDBlock,
+		&schema.TableNodeInfo,
+		&schema.TableHeader,
+		&schema.TableStateNode,
+		&schema.TableStorageNode,
+		&schema.TableUncle,
+		&schema.TableTransaction,
+		&schema.TableReceipt,
+		&schema.TableLog,
+	}
+)
+
+type tableRow struct {
+	table  schema.Table
+	values []interface{}
+}
+
+type CSVWriter struct {
+	// dir containing output files
+	dir string
+
+	writers                fileWriters
+	watchedAddressesWriter fileWriter
+
+	rows          chan tableRow
+	flushChan     chan struct{}
+	flushFinished chan struct{}
+	quitChan      chan struct{}
+	doneChan      chan struct{}
+}
+
+type fileWriter struct {
+	*csv.Writer
+	file *os.File
+}
+
+// fileWriters wraps the file writers for each output table
+type fileWriters map[string]fileWriter
+
+func newFileWriter(path string) (ret fileWriter, err error) {
+	file, err := os.OpenFile(path, os.O_WRONLY|os.O_CREATE|os.O_APPEND, 0644)
+	if err != nil {
+		return
+	}
+
+	ret = fileWriter{
+		Writer: csv.NewWriter(file),
+		file:   file,
+	}
+
+	return
+}
+
+func makeFileWriters(dir string, tables []*schema.Table) (fileWriters, error) {
+	if err := os.MkdirAll(dir, 0755); err != nil {
+		return nil, err
+	}
+	writers := fileWriters{}
+	for _, tbl := range tables {
+		w, err := newFileWriter(TableFilePath(dir, tbl.Name))
+		if err != nil {
+			return nil, err
+		}
+		writers[tbl.Name] = w
+	}
+	return writers, nil
+}
+
+func (tx fileWriters) write(tbl *schema.Table, args ...interface{}) error {
+	row := tbl.ToCsvRow(args...)
+	return tx[tbl.Name].Write(row)
+}
+
+func (tx fileWriters) close() error {
+	for _, w := range tx {
+		err := w.file.Close()
+		if err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func (tx fileWriters) flush() error {
+	for _, w := range tx {
+		w.Flush()
+		if err := w.Error(); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+func NewCSVWriter(path string, watchedAddressesFilePath string) (*CSVWriter, error) {
+	if err := os.MkdirAll(path, 0777); err != nil {
+		return nil, fmt.Errorf("unable to make MkdirAll for path: %s err: %s", path, err)
+	}
+
+	writers, err := makeFileWriters(path, Tables)
+	if err != nil {
+		return nil, err
+	}
+
+	watchedAddressesWriter, err := newFileWriter(watchedAddressesFilePath)
+	if err != nil {
+		return nil, err
+	}
+
+	csvWriter := &CSVWriter{
+		writers:                writers,
+		watchedAddressesWriter: watchedAddressesWriter,
+		dir:                    path,
+		rows:                   make(chan tableRow),
+		flushChan:              make(chan struct{}),
+		flushFinished:          make(chan struct{}),
+		quitChan:               make(chan struct{}),
+		doneChan:               make(chan struct{}),
+	}
+	return csvWriter, nil
+}
+
+func (csw *CSVWriter) Loop() {
+	go func() {
+		defer close(csw.doneChan)
+		for {
+			select {
+			case row := <-csw.rows:
+				err := csw.writers.write(&row.table, row.values...)
+				if err != nil {
+					panic(fmt.Sprintf("error writing csv buffer: %v", err))
+				}
+			case <-csw.quitChan:
+				if err := csw.writers.flush(); err != nil {
+					panic(fmt.Sprintf("error writing csv buffer to file: %v", err))
+				}
+				return
+			case <-csw.flushChan:
+				if err := csw.writers.flush(); err != nil {
+					panic(fmt.Sprintf("error writing csv buffer to file: %v", err))
+				}
+				csw.flushFinished <- struct{}{}
+			}
+		}
+	}()
+}
+
+// Flush sends a flush signal to the looping process
+func (csw *CSVWriter) Flush() {
+	csw.flushChan <- struct{}{}
+	<-csw.flushFinished
+}
+
+func TableFilePath(dir, name string) string { return filepath.Join(dir, name+".csv") }
+
+// Close satisfies io.Closer
+func (csw *CSVWriter) Close() error {
+	close(csw.quitChan)
+	<-csw.doneChan
+	close(csw.rows)
+	close(csw.flushChan)
+	close(csw.flushFinished)
+	return csw.writers.close()
+}
+
+func (csw *CSVWriter) upsertNode(node nodeinfo.Info) {
+	var values []interface{}
+	values = append(values, node.GenesisBlock, node.NetworkID, node.ID, node.ClientName, node.ChainID)
+	csw.rows <- tableRow{schema.TableNodeInfo, values}
+}
+
+func (csw *CSVWriter) upsertIPLD(ipld models.IPLDModel) {
+	var values []interface{}
+	values = append(values, ipld.BlockNumber, ipld.Key, ipld.Data)
+	csw.rows <- tableRow{schema.TableIPLDBlock, values}
+}
+
+func (csw *CSVWriter) upsertIPLDDirect(blockNumber, key string, value []byte) {
+	csw.upsertIPLD(models.IPLDModel{
+		BlockNumber: blockNumber,
+		Key:         key,
+		Data:        value,
+	})
+}
+
+func (csw *CSVWriter) upsertIPLDNode(blockNumber string, i ipld.IPLD) {
+	csw.upsertIPLD(models.IPLDModel{
+		BlockNumber: blockNumber,
+		Key:         i.Cid().String(),
+		Data:        i.RawData(),
+	})
+}
+
+func (csw *CSVWriter) upsertHeaderCID(header models.HeaderModel) {
+	var values []interface{}
+	values = append(values, header.BlockNumber, header.BlockHash, header.ParentHash, header.CID,
+		header.TotalDifficulty, header.NodeIDs, header.Reward, header.StateRoot, header.TxRoot,
+		header.RctRoot, header.UnclesHash, header.Bloom, strconv.FormatUint(header.Timestamp, 10), header.Coinbase)
+	csw.rows <- tableRow{schema.TableHeader, values}
+	metrics.IndexerMetrics.BlocksCounter.Inc(1)
+}
+
+func (csw *CSVWriter) upsertUncleCID(uncle models.UncleModel) {
+	var values []interface{}
+	values = append(values, uncle.BlockNumber, uncle.BlockHash, uncle.HeaderID, uncle.ParentHash, uncle.CID,
+		uncle.Reward, uncle.Index)
+	csw.rows <- tableRow{schema.TableUncle, values}
+}
+
+func (csw *CSVWriter) upsertTransactionCID(transaction models.TxModel) {
+	var values []interface{}
+	values = append(values, transaction.BlockNumber, transaction.HeaderID, transaction.TxHash, transaction.CID, transaction.Dst,
+		transaction.Src, transaction.Index, transaction.Type, transaction.Value)
+	csw.rows <- tableRow{schema.TableTransaction, values}
+	metrics.IndexerMetrics.TransactionsCounter.Inc(1)
+}
+
+func (csw *CSVWriter) upsertReceiptCID(rct *models.ReceiptModel) {
+	var values []interface{}
+	values = append(values, rct.BlockNumber, rct.HeaderID, rct.TxID, rct.CID, rct.Contract,
+		rct.PostState, rct.PostStatus)
+	csw.rows <- tableRow{schema.TableReceipt, values}
+	metrics.IndexerMetrics.ReceiptsCounter.Inc(1)
+}
+
+func (csw *CSVWriter) upsertLogCID(logs []*models.LogsModel) {
+	for _, l := range logs {
+		var values []interface{}
+		values = append(values, l.BlockNumber, l.HeaderID, l.CID, l.ReceiptID, l.Address, l.Index, l.Topic0,
+			l.Topic1, l.Topic2, l.Topic3)
+		csw.rows <- tableRow{schema.TableLog, values}
+		metrics.IndexerMetrics.LogsCounter.Inc(1)
+	}
+}
+
+func (csw *CSVWriter) upsertStateCID(stateNode models.StateNodeModel) {
+	balance := stateNode.Balance
+	if stateNode.Removed {
+		balance = "0"
+	}
+
+	var values []interface{}
+	values = append(values, stateNode.BlockNumber, stateNode.HeaderID, stateNode.StateKey, stateNode.CID,
+		true, balance, strconv.FormatUint(stateNode.Nonce, 10), stateNode.CodeHash, stateNode.StorageRoot, stateNode.Removed)
+	csw.rows <- tableRow{schema.TableStateNode, values}
+}
+
+func (csw *CSVWriter) upsertStorageCID(storageCID models.StorageNodeModel) {
+	var values []interface{}
+	values = append(values, storageCID.BlockNumber, storageCID.HeaderID, storageCID.StateKey, storageCID.StorageKey, storageCID.CID,
+		true, storageCID.Value, storageCID.Removed)
+	csw.rows <- tableRow{schema.TableStorageNode, values}
+}
+
+// LoadWatchedAddresses loads watched addresses from a file
+func (csw *CSVWriter) loadWatchedAddresses() ([]common.Address, error) {
+	watchedAddressesFilePath := csw.watchedAddressesWriter.file.Name()
+	// load csv rows from watched addresses file
+	rows, err := loadWatchedAddressesRows(watchedAddressesFilePath)
+	if err != nil {
+		return nil, err
+	}
+
+	// extract addresses from the csv rows
+	watchedAddresses := funk.Map(rows, func(row []string) common.Address {
+		// first column is for address in eth_meta.watched_addresses
+		addressString := row[0]
+
+		return common.HexToAddress(addressString)
+	}).([]common.Address)
+
+	return watchedAddresses, nil
+}
+
+// InsertWatchedAddresses inserts the given addresses in a file
+func (csw *CSVWriter) insertWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) error {
+	// load csv rows from watched addresses file
+	watchedAddresses, err := csw.loadWatchedAddresses()
+	if err != nil {
+		return err
+	}
+
+	// append rows for new addresses to existing csv file
+	for _, arg := range args {
+		// ignore if already watched
+		if funk.Contains(watchedAddresses, common.HexToAddress(arg.Address)) {
+			continue
+		}
+
+		var values []interface{}
+		values = append(values, arg.Address, strconv.FormatUint(arg.CreatedAt, 10), currentBlockNumber.String(), "0")
+		row := schema.TableWatchedAddresses.ToCsvRow(values...)
+
+		// writing directly instead of using rows channel as it needs to be flushed immediately
+		err = csw.watchedAddressesWriter.Write(row)
+		if err != nil {
+			return err
+		}
+	}
+
+	// watched addresses need to be flushed immediately to the file to keep them in sync with in-memory watched addresses
+	csw.watchedAddressesWriter.Flush()
+	err = csw.watchedAddressesWriter.Error()
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// RemoveWatchedAddresses removes the given watched addresses from a file
+func (csw *CSVWriter) removeWatchedAddresses(args []sdtypes.WatchAddressArg) error {
+	// load csv rows from watched addresses file
+	watchedAddressesFilePath := csw.watchedAddressesWriter.file.Name()
+	rows, err := loadWatchedAddressesRows(watchedAddressesFilePath)
+	if err != nil {
+		return err
+	}
+
+	// get rid of rows having addresses to be removed
+	filteredRows := funk.Filter(rows, func(row []string) bool {
+		return !funk.Contains(args, func(arg sdtypes.WatchAddressArg) bool {
+			// Compare first column in table for address
+			return arg.Address == row[0]
+		})
+	}).([][]string)
+
+	return dumpWatchedAddressesRows(csw.watchedAddressesWriter, filteredRows)
+}
+
+// SetWatchedAddresses clears and inserts the given addresses in a file
+func (csw *CSVWriter) setWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) error {
+	var rows [][]string
+	for _, arg := range args {
+		row := schema.TableWatchedAddresses.ToCsvRow(arg.Address, strconv.FormatUint(arg.CreatedAt, 10), currentBlockNumber.String(), "0")
+		rows = append(rows, row)
+	}
+
+	return dumpWatchedAddressesRows(csw.watchedAddressesWriter, rows)
+}
+
+// loadCSVWatchedAddresses loads csv rows from the given file
+func loadWatchedAddressesRows(filePath string) ([][]string, error) {
+	file, err := os.Open(filePath)
+	if err != nil {
+		if errors.Is(err, os.ErrNotExist) {
+			return [][]string{}, nil
+		}
+
+		return nil, fmt.Errorf("error opening watched addresses file: %v", err)
+	}
+
+	defer file.Close()
+	reader := csv.NewReader(file)
+
+	return reader.ReadAll()
+}
+
+// dumpWatchedAddressesRows dumps csv rows to the given file
+func dumpWatchedAddressesRows(watchedAddressesWriter fileWriter, filteredRows [][]string) error {
+	file := watchedAddressesWriter.file
+	file.Close()
+
+	file, err := os.Create(file.Name())
+	if err != nil {
+		return fmt.Errorf("error creating watched addresses file: %v", err)
+	}
+
+	watchedAddressesWriter.Writer = csv.NewWriter(file)
+	watchedAddressesWriter.file = file
+
+	for _, row := range filteredRows {
+		watchedAddressesWriter.Write(row)
+	}
+
+	watchedAddressesWriter.Flush()
+
+	return nil
+}

statediff/indexer/database/file/helpers.go

@@ -0,0 +1,60 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file
+
+import "bytes"
+
+// formatPostgresStringArray parses an array of strings into the proper Postgres string representation of that array
+func formatPostgresStringArray(a []string) string {
+	if a == nil {
+		return ""
+	}
+
+	if n := len(a); n > 0 {
+		// There will be at least two curly brackets, 2*N bytes of quotes,
+		// and N-1 bytes of delimiters.
+		b := make([]byte, 1, 1+3*n)
+		b[0] = '{'
+
+		b = appendArrayQuotedBytes(b, []byte(a[0]))
+		for i := 1; i < n; i++ {
+			b = append(b, ',')
+			b = appendArrayQuotedBytes(b, []byte(a[i]))
+		}
+
+		return string(append(b, '}'))
+	}
+
+	return "{}"
+}
+
+func appendArrayQuotedBytes(b, v []byte) []byte {
+	b = append(b, '"')
+	for {
+		i := bytes.IndexAny(v, `"\`)
+		if i < 0 {
+			b = append(b, v...)
+			break
+		}
+		if i > 0 {
+			b = append(b, v[:i]...)
+		}
+		b = append(b, '\\', v[i])
+		v = v[i+1:]
+	}
+	return append(b, '"')
+}

statediff/indexer/database/file/indexer.go

@@ -0,0 +1,492 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file
+
+import (
+	"bytes"
+	"context"
+	"errors"
+	"fmt"
+	"math/big"
+	"os"
+	"sync"
+	"sync/atomic"
+	"time"
+
+	"github.com/lib/pq"
+	"github.com/multiformats/go-multihash"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/crypto"
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/rlp"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+	sdtypes "github.com/ethereum/go-ethereum/statediff/types"
+)
+
+const defaultCSVOutputDir = "./statediff_output"
+const defaultSQLFilePath = "./statediff.sql"
+const defaultWatchedAddressesCSVFilePath = "./statediff-watched-addresses.csv"
+const defaultWatchedAddressesSQLFilePath = "./statediff-watched-addresses.sql"
+
+const watchedAddressesInsert = "INSERT INTO eth_meta.watched_addresses (address, created_at, watched_at) VALUES ('%s', '%d', '%d') ON CONFLICT (address) DO NOTHING;"
+
+var _ interfaces.StateDiffIndexer = &StateDiffIndexer{}
+
+// StateDiffIndexer satisfies the indexer.StateDiffIndexer interface for ethereum statediff objects on top of a void
+type StateDiffIndexer struct {
+	fileWriter       FileWriter
+	chainConfig      *params.ChainConfig
+	nodeID           string
+	wg               *sync.WaitGroup
+	removedCacheFlag *uint32
+}
+
+// NewStateDiffIndexer creates a void implementation of interfaces.StateDiffIndexer
+func NewStateDiffIndexer(ctx context.Context, chainConfig *params.ChainConfig, config Config) (*StateDiffIndexer, error) {
+	var err error
+	var writer FileWriter
+
+	watchedAddressesFilePath := config.WatchedAddressesFilePath
+
+	switch config.Mode {
+	case CSV:
+		outputDir := config.OutputDir
+		if outputDir == "" {
+			outputDir = defaultCSVOutputDir
+		}
+
+		if _, err := os.Stat(outputDir); !errors.Is(err, os.ErrNotExist) {
+			return nil, fmt.Errorf("cannot create output directory, directory (%s) already exists", outputDir)
+		}
+		log.Info("Writing statediff CSV files to directory", "file", outputDir)
+
+		if watchedAddressesFilePath == "" {
+			watchedAddressesFilePath = defaultWatchedAddressesCSVFilePath
+		}
+		log.Info("Writing watched addresses to file", "file", watchedAddressesFilePath)
+
+		writer, err = NewCSVWriter(outputDir, watchedAddressesFilePath)
+		if err != nil {
+			return nil, err
+		}
+	case SQL:
+		filePath := config.FilePath
+		if filePath == "" {
+			filePath = defaultSQLFilePath
+		}
+		if _, err := os.Stat(filePath); !errors.Is(err, os.ErrNotExist) {
+			return nil, fmt.Errorf("cannot create file, file (%s) already exists", filePath)
+		}
+		file, err := os.Create(filePath)
+		if err != nil {
+			return nil, fmt.Errorf("unable to create file (%s), err: %v", filePath, err)
+		}
+		log.Info("Writing statediff SQL statements to file", "file", filePath)
+
+		if watchedAddressesFilePath == "" {
+			watchedAddressesFilePath = defaultWatchedAddressesSQLFilePath
+		}
+		log.Info("Writing watched addresses to file", "file", watchedAddressesFilePath)
+
+		writer = NewSQLWriter(file, watchedAddressesFilePath)
+	default:
+		return nil, fmt.Errorf("unrecognized file mode: %s", config.Mode)
+	}
+
+	wg := new(sync.WaitGroup)
+	writer.Loop()
+	writer.upsertNode(config.NodeInfo)
+
+	return &StateDiffIndexer{
+		fileWriter:  writer,
+		chainConfig: chainConfig,
+		nodeID:      config.NodeInfo.ID,
+		wg:          wg,
+	}, nil
+}
+
+// ReportDBMetrics has nothing to report for dump
+func (sdi *StateDiffIndexer) ReportDBMetrics(time.Duration, <-chan bool) {}
+
+// PushBlock pushes and indexes block data in sql, except state & storage nodes (includes header, uncles, transactions & receipts)
+// Returns an initiated DB transaction which must be Closed via defer to commit or rollback
+func (sdi *StateDiffIndexer) PushBlock(block *types.Block, receipts types.Receipts, totalDifficulty *big.Int) (interfaces.Batch, error) {
+	sdi.removedCacheFlag = new(uint32)
+	start, t := time.Now(), time.Now()
+	blockHash := block.Hash()
+	blockHashStr := blockHash.String()
+	height := block.NumberU64()
+	traceMsg := fmt.Sprintf("indexer stats for statediff at %d with hash %s:\r\n", height, blockHashStr)
+	transactions := block.Transactions()
+	// Derive any missing fields
+	if err := receipts.DeriveFields(sdi.chainConfig, blockHash, height, block.BaseFee(), transactions); err != nil {
+		return nil, err
+	}
+
+	// Generate the block iplds
+	headerNode, txNodes, rctNodes, logNodes, err := ipld.FromBlockAndReceipts(block, receipts)
+	if err != nil {
+		return nil, fmt.Errorf("error creating IPLD nodes from block and receipts: %v", err)
+	}
+
+	if len(txNodes) != len(rctNodes) {
+		return nil, fmt.Errorf("expected number of transactions (%d), receipts (%d)", len(txNodes), len(rctNodes))
+	}
+
+	// Calculate reward
+	var reward *big.Int
+	// in PoA networks block reward is 0
+	if sdi.chainConfig.Clique != nil {
+		reward = big.NewInt(0)
+	} else {
+		reward = shared.CalcEthBlockReward(block.Header(), block.Uncles(), block.Transactions(), receipts)
+	}
+	t = time.Now()
+
+	blockTx := &BatchTx{
+		BlockNumber: block.Number().String(),
+		submit: func(self *BatchTx, err error) error {
+			tDiff := time.Since(t)
+			metrics.IndexerMetrics.StateStoreCodeProcessingTimer.Update(tDiff)
+			traceMsg += fmt.Sprintf("state, storage, and code storage processing time: %s\r\n", tDiff.String())
+			t = time.Now()
+			sdi.fileWriter.Flush()
+			tDiff = time.Since(t)
+			metrics.IndexerMetrics.PostgresCommitTimer.Update(tDiff)
+			traceMsg += fmt.Sprintf("postgres transaction commit duration: %s\r\n", tDiff.String())
+			traceMsg += fmt.Sprintf(" TOTAL PROCESSING DURATION: %s\r\n", time.Since(start).String())
+			log.Debug(traceMsg)
+			return err
+		},
+	}
+	tDiff := time.Since(t)
+	metrics.IndexerMetrics.FreePostgresTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("time spent waiting for free postgres tx: %s:\r\n", tDiff.String())
+	t = time.Now()
+
+	// write header, collect headerID
+	headerID := sdi.processHeader(block.Header(), headerNode, reward, totalDifficulty)
+	tDiff = time.Since(t)
+	metrics.IndexerMetrics.HeaderProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("header processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+
+	// write uncles
+	sdi.processUncles(headerID, block.Number(), block.UncleHash(), block.Uncles())
+	tDiff = time.Since(t)
+	metrics.IndexerMetrics.UncleProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("uncle processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+
+	// write receipts and txs
+	err = sdi.processReceiptsAndTxs(processArgs{
+		headerID:    headerID,
+		blockNumber: block.Number(),
+		receipts:    receipts,
+		txs:         transactions,
+		rctNodes:    rctNodes,
+		txNodes:     txNodes,
+		logNodes:    logNodes,
+	})
+	if err != nil {
+		return nil, err
+	}
+	tDiff = time.Since(t)
+	metrics.IndexerMetrics.TxAndRecProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("tx and receipt processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+
+	return blockTx, err
+}
+
+// processHeader write a header IPLD insert SQL stmt to a file
+// it returns the headerID
+func (sdi *StateDiffIndexer) processHeader(header *types.Header, headerNode ipld.IPLD, reward, td *big.Int) string {
+	sdi.fileWriter.upsertIPLDNode(header.Number.String(), headerNode)
+
+	var baseFee *string
+	if header.BaseFee != nil {
+		baseFee = new(string)
+		*baseFee = header.BaseFee.String()
+	}
+	headerID := header.Hash().String()
+	sdi.fileWriter.upsertHeaderCID(models.HeaderModel{
+		NodeIDs:         pq.StringArray([]string{sdi.nodeID}),
+		CID:             headerNode.Cid().String(),
+		ParentHash:      header.ParentHash.String(),
+		BlockNumber:     header.Number.String(),
+		BlockHash:       headerID,
+		TotalDifficulty: td.String(),
+		Reward:          reward.String(),
+		Bloom:           header.Bloom.Bytes(),
+		StateRoot:       header.Root.String(),
+		RctRoot:         header.ReceiptHash.String(),
+		TxRoot:          header.TxHash.String(),
+		UnclesHash:      header.UncleHash.String(),
+		Timestamp:       header.Time,
+		Coinbase:        header.Coinbase.String(),
+	})
+	return headerID
+}
+
+// processUncles publishes and indexes uncle IPLDs in Postgres
+func (sdi *StateDiffIndexer) processUncles(headerID string, blockNumber *big.Int, unclesHash common.Hash, uncles []*types.Header) error {
+	// publish and index uncles
+	uncleEncoding, err := rlp.EncodeToBytes(uncles)
+	if err != nil {
+		return err
+	}
+	preparedHash := crypto.Keccak256Hash(uncleEncoding)
+	if !bytes.Equal(preparedHash.Bytes(), unclesHash.Bytes()) {
+		return fmt.Errorf("derived uncles hash (%s) does not match the hash in the header (%s)", preparedHash.Hex(), unclesHash.Hex())
+	}
+	unclesCID, err := ipld.RawdataToCid(ipld.MEthHeaderList, uncleEncoding, multihash.KECCAK_256)
+	if err != nil {
+		return err
+	}
+	sdi.fileWriter.upsertIPLDDirect(blockNumber.String(), unclesCID.String(), uncleEncoding)
+	for i, uncle := range uncles {
+		var uncleReward *big.Int
+		// in PoA networks uncle reward is 0
+		if sdi.chainConfig.Clique != nil {
+			uncleReward = big.NewInt(0)
+		} else {
+			uncleReward = shared.CalcUncleMinerReward(blockNumber.Uint64(), uncle.Number.Uint64())
+		}
+		sdi.fileWriter.upsertUncleCID(models.UncleModel{
+			BlockNumber: blockNumber.String(),
+			HeaderID:    headerID,
+			CID:         unclesCID.String(),
+			ParentHash:  uncle.ParentHash.String(),
+			BlockHash:   uncle.Hash().String(),
+			Reward:      uncleReward.String(),
+			Index:       int64(i),
+		})
+	}
+	return nil
+}
+
+// processArgs bundles arguments to processReceiptsAndTxs
+type processArgs struct {
+	headerID    string
+	blockNumber *big.Int
+	receipts    types.Receipts
+	txs         types.Transactions
+	rctNodes    []*ipld.EthReceipt
+	txNodes     []*ipld.EthTx
+	logNodes    [][]*ipld.EthLog
+}
+
+// processReceiptsAndTxs writes receipt and tx IPLD insert SQL stmts to a file
+func (sdi *StateDiffIndexer) processReceiptsAndTxs(args processArgs) error {
+	// Process receipts and txs
+	signer := types.MakeSigner(sdi.chainConfig, args.blockNumber)
+	for i, receipt := range args.receipts {
+		txNode := args.txNodes[i]
+		sdi.fileWriter.upsertIPLDNode(args.blockNumber.String(), txNode)
+		sdi.fileWriter.upsertIPLDNode(args.blockNumber.String(), args.rctNodes[i])
+
+		// index tx
+		trx := args.txs[i]
+		txID := trx.Hash().String()
+
+		var val string
+		if trx.Value() != nil {
+			val = trx.Value().String()
+		}
+
+		// derive sender for the tx that corresponds with this receipt
+		from, err := types.Sender(signer, trx)
+		if err != nil {
+			return fmt.Errorf("error deriving tx sender: %v", err)
+		}
+		txModel := models.TxModel{
+			BlockNumber: args.blockNumber.String(),
+			HeaderID:    args.headerID,
+			Dst:         shared.HandleZeroAddrPointer(trx.To()),
+			Src:         shared.HandleZeroAddr(from),
+			TxHash:      txID,
+			Index:       int64(i),
+			CID:         txNode.Cid().String(),
+			Type:        trx.Type(),
+			Value:       val,
+		}
+		sdi.fileWriter.upsertTransactionCID(txModel)
+
+		// this is the contract address if this receipt is for a contract creation tx
+		contract := shared.HandleZeroAddr(receipt.ContractAddress)
+
+		// index receipt
+		rctModel := &models.ReceiptModel{
+			BlockNumber: args.blockNumber.String(),
+			HeaderID:    args.headerID,
+			TxID:        txID,
+			Contract:    contract,
+			CID:         args.rctNodes[i].Cid().String(),
+		}
+		if len(receipt.PostState) == 0 {
+			rctModel.PostStatus = receipt.Status
+		} else {
+			rctModel.PostState = common.BytesToHash(receipt.PostState).String()
+		}
+		sdi.fileWriter.upsertReceiptCID(rctModel)
+
+		// index logs
+		logDataSet := make([]*models.LogsModel, len(receipt.Logs))
+		for idx, l := range receipt.Logs {
+			sdi.fileWriter.upsertIPLDNode(args.blockNumber.String(), args.logNodes[i][idx])
+			topicSet := make([]string, 4)
+			for ti, topic := range l.Topics {
+				topicSet[ti] = topic.Hex()
+			}
+
+			logDataSet[idx] = &models.LogsModel{
+				BlockNumber: args.blockNumber.String(),
+				HeaderID:    args.headerID,
+				ReceiptID:   txID,
+				Address:     l.Address.String(),
+				Index:       int64(l.Index),
+				CID:         args.logNodes[i][idx].Cid().String(),
+				Topic0:      topicSet[0],
+				Topic1:      topicSet[1],
+				Topic2:      topicSet[2],
+				Topic3:      topicSet[3],
+			}
+		}
+		sdi.fileWriter.upsertLogCID(logDataSet)
+	}
+
+	return nil
+}
+
+// PushStateNode writes a state diff node object (including any child storage nodes) IPLD insert SQL stmt to a file
+func (sdi *StateDiffIndexer) PushStateNode(batch interfaces.Batch, stateNode sdtypes.StateLeafNode, headerID string) error {
+	tx, ok := batch.(*BatchTx)
+	if !ok {
+		return fmt.Errorf("file: batch is expected to be of type %T, got %T", &BatchTx{}, batch)
+	}
+	// publish the state node
+	var stateModel models.StateNodeModel
+	if stateNode.Removed {
+		if atomic.LoadUint32(sdi.removedCacheFlag) == 0 {
+			atomic.StoreUint32(sdi.removedCacheFlag, 1)
+			sdi.fileWriter.upsertIPLDDirect(tx.BlockNumber, shared.RemovedNodeStateCID, []byte{})
+		}
+		stateModel = models.StateNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			CID:         shared.RemovedNodeStateCID,
+			Removed:     true,
+		}
+	} else {
+		stateModel = models.StateNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			CID:         stateNode.AccountWrapper.CID,
+			Removed:     false,
+			Balance:     stateNode.AccountWrapper.Account.Balance.String(),
+			Nonce:       stateNode.AccountWrapper.Account.Nonce,
+			CodeHash:    common.BytesToHash(stateNode.AccountWrapper.Account.CodeHash).String(),
+			StorageRoot: stateNode.AccountWrapper.Account.Root.String(),
+		}
+	}
+
+	// index the state node
+	sdi.fileWriter.upsertStateCID(stateModel)
+
+	// if there are any storage nodes associated with this node, publish and index them
+	for _, storageNode := range stateNode.StorageDiff {
+		if storageNode.Removed {
+			if atomic.LoadUint32(sdi.removedCacheFlag) == 0 {
+				atomic.StoreUint32(sdi.removedCacheFlag, 1)
+				sdi.fileWriter.upsertIPLDDirect(tx.BlockNumber, shared.RemovedNodeStorageCID, []byte{})
+			}
+			storageModel := models.StorageNodeModel{
+				BlockNumber: tx.BlockNumber,
+				HeaderID:    headerID,
+				StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+				StorageKey:  common.BytesToHash(storageNode.LeafKey).String(),
+				CID:         shared.RemovedNodeStorageCID,
+				Removed:     true,
+				Value:       []byte{},
+			}
+			sdi.fileWriter.upsertStorageCID(storageModel)
+			continue
+		}
+		storageModel := models.StorageNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			StorageKey:  common.BytesToHash(storageNode.LeafKey).String(),
+			CID:         storageNode.CID,
+			Removed:     false,
+			Value:       storageNode.Value,
+		}
+		sdi.fileWriter.upsertStorageCID(storageModel)
+	}
+
+	return nil
+}
+
+// PushIPLD writes iplds to ipld.blocks
+func (sdi *StateDiffIndexer) PushIPLD(batch interfaces.Batch, ipld sdtypes.IPLD) error {
+	tx, ok := batch.(*BatchTx)
+	if !ok {
+		return fmt.Errorf("file: batch is expected to be of type %T, got %T", &BatchTx{}, batch)
+	}
+	sdi.fileWriter.upsertIPLDDirect(tx.BlockNumber, ipld.CID, ipld.Content)
+	return nil
+}
+
+// Close satisfies io.Closer
+func (sdi *StateDiffIndexer) Close() error {
+	return sdi.fileWriter.Close()
+}
+
+// LoadWatchedAddresses loads watched addresses from a file
+func (sdi *StateDiffIndexer) LoadWatchedAddresses() ([]common.Address, error) {
+	return sdi.fileWriter.loadWatchedAddresses()
+}
+
+// InsertWatchedAddresses inserts the given addresses in a file
+func (sdi *StateDiffIndexer) InsertWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) error {
+	return sdi.fileWriter.insertWatchedAddresses(args, currentBlockNumber)
+}
+
+// RemoveWatchedAddresses removes the given watched addresses from a file
+func (sdi *StateDiffIndexer) RemoveWatchedAddresses(args []sdtypes.WatchAddressArg) error {
+	return sdi.fileWriter.removeWatchedAddresses(args)
+}
+
+// SetWatchedAddresses clears and inserts the given addresses in a file
+func (sdi *StateDiffIndexer) SetWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) error {
+	return sdi.fileWriter.setWatchedAddresses(args, currentBlockNumber)
+}
+
+// ClearWatchedAddresses clears all the watched addresses from a file
+func (sdi *StateDiffIndexer) ClearWatchedAddresses() error {
+	return sdi.SetWatchedAddresses([]sdtypes.WatchAddressArg{}, big.NewInt(0))
+}

statediff/indexer/database/file/interfaces.go

@@ -0,0 +1,57 @@
+// VulcanizeDB
+// Copyright © 2022 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file
+
+import (
+	"math/big"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+	nodeinfo "github.com/ethereum/go-ethereum/statediff/indexer/node"
+	"github.com/ethereum/go-ethereum/statediff/types"
+)
+
+// Writer interface required by the file indexer
+type FileWriter interface {
+	// Methods used to control the writer
+	Loop()
+	Close() error
+	Flush()
+
+	// Methods to upsert ethereum data model objects
+	upsertNode(node nodeinfo.Info)
+	upsertHeaderCID(header models.HeaderModel)
+	upsertUncleCID(uncle models.UncleModel)
+	upsertTransactionCID(transaction models.TxModel)
+	upsertReceiptCID(rct *models.ReceiptModel)
+	upsertLogCID(logs []*models.LogsModel)
+	upsertStateCID(stateNode models.StateNodeModel)
+	upsertStorageCID(storageCID models.StorageNodeModel)
+	upsertIPLD(ipld models.IPLDModel)
+
+	// Methods to upsert IPLD in different ways
+	upsertIPLDDirect(blockNumber, key string, value []byte)
+	upsertIPLDNode(blockNumber string, i ipld.IPLD)
+
+	// Methods to read and write watched addresses
+	loadWatchedAddresses() ([]common.Address, error)
+	insertWatchedAddresses(args []types.WatchAddressArg, currentBlockNumber *big.Int) error
+	removeWatchedAddresses(args []types.WatchAddressArg) error
+	setWatchedAddresses(args []types.WatchAddressArg, currentBlockNumber *big.Int) error
+}

statediff/indexer/database/file/mainnet_tests/indexer_test.go

@@ -0,0 +1,112 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package mainnet_tests
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"math/big"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/file"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test_helpers"
+)
+
+var (
+	err       error
+	db        sql.Database
+	ind       interfaces.StateDiffIndexer
+	chainConf = params.MainnetChainConfig
+)
+
+func init() {
+	if os.Getenv("MODE") != "statediff" {
+		fmt.Println("Skipping statediff test")
+		os.Exit(0)
+	}
+	if os.Getenv("STATEDIFF_DB") != "file" {
+		fmt.Println("Skipping statediff .sql file writing mode test")
+		os.Exit(0)
+	}
+}
+
+func TestPushBlockAndState(t *testing.T) {
+	conf := test_helpers.GetTestConfig()
+
+	for _, blockNumber := range test_helpers.ProblemBlocks {
+		conf.BlockNumber = big.NewInt(blockNumber)
+		tb, trs, err := test_helpers.TestBlockAndReceipts(conf)
+		require.NoError(t, err)
+
+		testPushBlockAndState(t, tb, trs)
+	}
+
+	testBlock, testReceipts, err := test_helpers.TestBlockAndReceiptsFromEnv(conf)
+	require.NoError(t, err)
+
+	testPushBlockAndState(t, testBlock, testReceipts)
+}
+
+func testPushBlockAndState(t *testing.T, block *types.Block, receipts types.Receipts) {
+	t.Run("Test PushBlock and PushStateNode", func(t *testing.T) {
+		setupMainnetIndexer(t)
+		defer dumpData(t)
+		defer tearDown(t)
+
+		test.TestBlock(t, ind, block, receipts)
+	})
+}
+
+func setupMainnetIndexer(t *testing.T) {
+	if _, err := os.Stat(file.CSVTestConfig.FilePath); !errors.Is(err, os.ErrNotExist) {
+		err := os.Remove(file.CSVTestConfig.FilePath)
+		require.NoError(t, err)
+	}
+
+	ind, err = file.NewStateDiffIndexer(context.Background(), chainConf, file.CSVTestConfig)
+	require.NoError(t, err)
+
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
+func dumpData(t *testing.T) {
+	sqlFileBytes, err := os.ReadFile(file.CSVTestConfig.FilePath)
+	require.NoError(t, err)
+
+	_, err = db.Exec(context.Background(), string(sqlFileBytes))
+	require.NoError(t, err)
+}
+
+func tearDown(t *testing.T) {
+	test_helpers.TearDownDB(t, db)
+	require.NoError(t, db.Close())
+
+	require.NoError(t, os.Remove(file.CSVTestConfig.FilePath))
+}

statediff/indexer/database/file/sql_indexer_legacy_test.go

@@ -0,0 +1,101 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file_test
+
+import (
+	"context"
+	"errors"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/file"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test_helpers"
+)
+
+var (
+	db  sql.Database
+	err error
+	ind interfaces.StateDiffIndexer
+)
+
+func setupLegacySQLIndexer(t *testing.T) {
+	if _, err := os.Stat(file.SQLTestConfig.FilePath); !errors.Is(err, os.ErrNotExist) {
+		err := os.Remove(file.SQLTestConfig.FilePath)
+		require.NoError(t, err)
+	}
+
+	ind, err = file.NewStateDiffIndexer(context.Background(), test.LegacyConfig, file.SQLTestConfig)
+	require.NoError(t, err)
+
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
+func setupLegacySQL(t *testing.T) {
+	setupLegacySQLIndexer(t)
+	test.SetupLegacyTestData(t, ind)
+}
+
+func dumpFileData(t *testing.T) {
+	err := test_helpers.DedupFile(file.SQLTestConfig.FilePath)
+	require.NoError(t, err)
+
+	sqlFileBytes, err := os.ReadFile(file.SQLTestConfig.FilePath)
+	require.NoError(t, err)
+
+	_, err = db.Exec(context.Background(), string(sqlFileBytes))
+	require.NoError(t, err)
+}
+
+func resetAndDumpWatchedAddressesFileData(t *testing.T) {
+	test_helpers.TearDownDB(t, db)
+
+	sqlFileBytes, err := os.ReadFile(file.SQLTestConfig.WatchedAddressesFilePath)
+	require.NoError(t, err)
+
+	_, err = db.Exec(context.Background(), string(sqlFileBytes))
+	require.NoError(t, err)
+}
+
+func tearDown(t *testing.T) {
+	test_helpers.TearDownDB(t, db)
+	require.NoError(t, db.Close())
+
+	require.NoError(t, os.Remove(file.SQLTestConfig.FilePath))
+
+	if err := os.Remove(file.SQLTestConfig.WatchedAddressesFilePath); !errors.Is(err, os.ErrNotExist) {
+		require.NoError(t, err)
+	}
+}
+
+func TestLegacySQLFileIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs", func(t *testing.T) {
+		setupLegacySQL(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestLegacyIndexer(t, db)
+	})
+}

statediff/indexer/database/file/sql_indexer_test.go

@@ -0,0 +1,253 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file_test
+
+import (
+	"context"
+	"errors"
+	"math/big"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/file"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/mocks"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+)
+
+func setupIndexer(t *testing.T) {
+	if _, err := os.Stat(file.SQLTestConfig.FilePath); !errors.Is(err, os.ErrNotExist) {
+		err := os.Remove(file.SQLTestConfig.FilePath)
+		require.NoError(t, err)
+	}
+
+	if _, err := os.Stat(file.SQLTestConfig.WatchedAddressesFilePath); !errors.Is(err, os.ErrNotExist) {
+		err := os.Remove(file.SQLTestConfig.WatchedAddressesFilePath)
+		require.NoError(t, err)
+	}
+
+	ind, err = file.NewStateDiffIndexer(context.Background(), mocks.TestConfig, file.SQLTestConfig)
+	require.NoError(t, err)
+
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+}
+
+func setup(t *testing.T) {
+	setupIndexer(t)
+	test.SetupTestData(t, ind)
+}
+
+func setupSQLNonCanonical(t *testing.T) {
+	setupIndexer(t)
+	test.SetupTestDataNonCanonical(t, ind)
+}
+
+func TestSQLFileIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs in a single tx", func(t *testing.T) {
+		setup(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexHeaderIPLDs(t, db)
+	})
+
+	t.Run("Publish and index transaction IPLDs in a single tx", func(t *testing.T) {
+		setup(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexTransactionIPLDs(t, db)
+	})
+
+	t.Run("Publish and index log IPLDs for multiple receipt of a specific block", func(t *testing.T) {
+		setup(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexLogIPLDs(t, db)
+	})
+
+	t.Run("Publish and index receipt IPLDs in a single tx", func(t *testing.T) {
+		setup(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexReceiptIPLDs(t, db)
+	})
+
+	t.Run("Publish and index state IPLDs in a single tx", func(t *testing.T) {
+		setup(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexStateIPLDs(t, db)
+	})
+
+	t.Run("Publish and index storage IPLDs in a single tx", func(t *testing.T) {
+		setup(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexStorageIPLDs(t, db)
+	})
+}
+
+func TestSQLFileIndexerNonCanonical(t *testing.T) {
+	t.Run("Publish and index header", func(t *testing.T) {
+		setupSQLNonCanonical(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexHeaderNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index transactions", func(t *testing.T) {
+		setupSQLNonCanonical(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexTransactionsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index receipts", func(t *testing.T) {
+		setupSQLNonCanonical(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexReceiptsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index logs", func(t *testing.T) {
+		setupSQLNonCanonical(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexLogsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index state nodes", func(t *testing.T) {
+		setupSQLNonCanonical(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexStateNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index storage nodes", func(t *testing.T) {
+		setupSQLNonCanonical(t)
+		dumpFileData(t)
+		defer tearDown(t)
+
+		test.TestPublishAndIndexStorageNonCanonical(t, db)
+	})
+}
+
+func TestSQLFileWatchAddressMethods(t *testing.T) {
+	setupIndexer(t)
+	defer tearDown(t)
+
+	t.Run("Load watched addresses (empty table)", func(t *testing.T) {
+		test.TestLoadEmptyWatchedAddresses(t, ind)
+	})
+
+	t.Run("Insert watched addresses", func(t *testing.T) {
+		args := mocks.GetInsertWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt1)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestInsertWatchedAddresses(t, db)
+	})
+
+	t.Run("Insert watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetInsertAlreadyWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestInsertAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses", func(t *testing.T) {
+		args := mocks.GetRemoveWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestRemoveWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses (some non-watched)", func(t *testing.T) {
+		args := mocks.GetRemoveNonWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestRemoveNonWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses", func(t *testing.T) {
+		args := mocks.GetSetWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestSetWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetSetAlreadyWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt3)))
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestSetAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Load watched addresses", func(t *testing.T) {
+		test.TestLoadWatchedAddresses(t, ind)
+	})
+
+	t.Run("Clear watched addresses", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestClearWatchedAddresses(t, db)
+	})
+
+	t.Run("Clear watched addresses (empty table)", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		resetAndDumpWatchedAddressesFileData(t)
+
+		test.TestClearEmptyWatchedAddresses(t, db)
+	})
+}

statediff/indexer/database/file/sql_writer.go

@@ -0,0 +1,391 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package file
+
+import (
+	"bufio"
+	"errors"
+	"fmt"
+	"io"
+	"math/big"
+	"os"
+
+	pg_query "github.com/pganalyze/pg_query_go/v2"
+	"github.com/thoas/go-funk"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+	nodeinfo "github.com/ethereum/go-ethereum/statediff/indexer/node"
+	"github.com/ethereum/go-ethereum/statediff/types"
+)
+
+var (
+	pipeSize        = 65336 // min(linuxPipeSize, macOSPipeSize)
+	writeBufferSize = pipeSize * 16 * 96
+)
+
+// SQLWriter writes sql statements to a file
+type SQLWriter struct {
+	wc             io.WriteCloser
+	stmts          chan []byte
+	collatedStmt   []byte
+	collationIndex int
+
+	flushChan     chan struct{}
+	flushFinished chan struct{}
+	quitChan      chan struct{}
+	doneChan      chan struct{}
+
+	watchedAddressesFilePath string
+}
+
+// NewSQLWriter creates a new pointer to a Writer
+func NewSQLWriter(wc io.WriteCloser, watchedAddressesFilePath string) *SQLWriter {
+	return &SQLWriter{
+		wc:                       wc,
+		stmts:                    make(chan []byte),
+		collatedStmt:             make([]byte, writeBufferSize),
+		flushChan:                make(chan struct{}),
+		flushFinished:            make(chan struct{}),
+		quitChan:                 make(chan struct{}),
+		doneChan:                 make(chan struct{}),
+		watchedAddressesFilePath: watchedAddressesFilePath,
+	}
+}
+
+// Loop enables concurrent writes to the underlying os.File
+// since os.File does not buffer, it utilizes an internal buffer that is the size of a unix pipe
+// by using copy() and tracking the index/size of the buffer, we require only the initial memory allocation
+func (sqw *SQLWriter) Loop() {
+	sqw.collationIndex = 0
+	go func() {
+		defer close(sqw.doneChan)
+		var l int
+		for {
+			select {
+			case stmt := <-sqw.stmts:
+				l = len(stmt)
+				if sqw.collationIndex+l > writeBufferSize {
+					if err := sqw.flush(); err != nil {
+						panic(fmt.Sprintf("error writing sql stmts buffer to file: %v", err))
+					}
+					if l > writeBufferSize {
+						if _, err := sqw.wc.Write(stmt); err != nil {
+							panic(fmt.Sprintf("error writing large sql stmt to file: %v", err))
+						}
+						continue
+					}
+				}
+				copy(sqw.collatedStmt[sqw.collationIndex:sqw.collationIndex+l], stmt)
+				sqw.collationIndex += l
+			case <-sqw.quitChan:
+				if err := sqw.flush(); err != nil {
+					panic(fmt.Sprintf("error writing sql stmts buffer to file: %v", err))
+				}
+				return
+			case <-sqw.flushChan:
+				if err := sqw.flush(); err != nil {
+					panic(fmt.Sprintf("error writing sql stmts buffer to file: %v", err))
+				}
+				sqw.flushFinished <- struct{}{}
+			}
+		}
+	}()
+}
+
+// Close satisfies io.Closer
+func (sqw *SQLWriter) Close() error {
+	close(sqw.quitChan)
+	<-sqw.doneChan
+	close(sqw.stmts)
+	close(sqw.flushChan)
+	close(sqw.flushFinished)
+	return sqw.wc.Close()
+}
+
+// Flush sends a flush signal to the looping process
+func (sqw *SQLWriter) Flush() {
+	sqw.flushChan <- struct{}{}
+	<-sqw.flushFinished
+}
+
+func (sqw *SQLWriter) flush() error {
+	if _, err := sqw.wc.Write(sqw.collatedStmt[0:sqw.collationIndex]); err != nil {
+		return err
+	}
+	sqw.collationIndex = 0
+	return nil
+}
+
+const (
+	nodeInsert = "INSERT INTO nodes (genesis_block, network_id, node_id, client_name, chain_id) VALUES " +
+		"('%s', '%s', '%s', '%s', %d);\n"
+
+	ipldInsert = "INSERT INTO ipld.blocks (block_number, key, data) VALUES ('%s', '%s', '\\x%x');\n"
+
+	headerInsert = "INSERT INTO eth.header_cids (block_number, block_hash, parent_hash, cid, td, node_ids, reward, " +
+		"state_root, tx_root, receipt_root, uncles_hash, bloom, timestamp, coinbase) VALUES " +
+		"('%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '%s', '\\x%x', %d, '%s');\n"
+
+	uncleInsert = "INSERT INTO eth.uncle_cids (block_number, block_hash, header_id, parent_hash, cid, reward, index) VALUES " +
+		"('%s', '%s', '%s', '%s', '%s', '%s', %d);\n"
+
+	txInsert = "INSERT INTO eth.transaction_cids (block_number, header_id, tx_hash, cid, dst, src, index, tx_type, " +
+		"value) VALUES ('%s', '%s', '%s', '%s', '%s', '%s', %d, %d, '%s');\n"
+
+	rctInsert = "INSERT INTO eth.receipt_cids (block_number, header_id, tx_id, cid, contract, post_state, " +
+		"post_status) VALUES ('%s', '%s', '%s', '%s', '%s', '%s', %d);\n"
+
+	logInsert = "INSERT INTO eth.log_cids (block_number, header_id, cid, rct_id, address, index, topic0, topic1, topic2, " +
+		"topic3) VALUES ('%s', '%s', '%s', '%s', '%s', %d, '%s', '%s', '%s', '%s');\n"
+
+	stateInsert = "INSERT INTO eth.state_cids (block_number, header_id, state_leaf_key, cid, removed, diff, " +
+		"balance, nonce, code_hash, storage_root) VALUES ('%s', '%s', '%s', '%s', %t, %t, '%s', %d, '%s', '%s');\n"
+
+	storageInsert = "INSERT INTO eth.storage_cids (block_number, header_id, state_leaf_key, storage_leaf_key, cid, " +
+		"removed, diff, val) VALUES ('%s', '%s', '%s', '%s', '%s', %t, %t, '\\x%x');\n"
+)
+
+func (sqw *SQLWriter) upsertNode(node nodeinfo.Info) {
+	sqw.stmts <- []byte(fmt.Sprintf(nodeInsert, node.GenesisBlock, node.NetworkID, node.ID, node.ClientName, node.ChainID))
+}
+
+func (sqw *SQLWriter) upsertIPLD(ipld models.IPLDModel) {
+	sqw.stmts <- []byte(fmt.Sprintf(ipldInsert, ipld.BlockNumber, ipld.Key, ipld.Data))
+}
+
+func (sqw *SQLWriter) upsertIPLDDirect(blockNumber, key string, value []byte) {
+	sqw.upsertIPLD(models.IPLDModel{
+		BlockNumber: blockNumber,
+		Key:         key,
+		Data:        value,
+	})
+}
+
+func (sqw *SQLWriter) upsertIPLDNode(blockNumber string, i ipld.IPLD) {
+	sqw.upsertIPLD(models.IPLDModel{
+		BlockNumber: blockNumber,
+		Key:         i.Cid().String(),
+		Data:        i.RawData(),
+	})
+}
+
+func (sqw *SQLWriter) upsertHeaderCID(header models.HeaderModel) {
+	stmt := fmt.Sprintf(headerInsert, header.BlockNumber, header.BlockHash, header.ParentHash, header.CID,
+		header.TotalDifficulty, formatPostgresStringArray(header.NodeIDs), header.Reward, header.StateRoot, header.TxRoot,
+		header.RctRoot, header.UnclesHash, header.Bloom, header.Timestamp, header.Coinbase)
+	sqw.stmts <- []byte(stmt)
+	metrics.IndexerMetrics.BlocksCounter.Inc(1)
+}
+
+func (sqw *SQLWriter) upsertUncleCID(uncle models.UncleModel) {
+	sqw.stmts <- []byte(fmt.Sprintf(uncleInsert, uncle.BlockNumber, uncle.BlockHash, uncle.HeaderID, uncle.ParentHash, uncle.CID,
+		uncle.Reward, uncle.Index))
+}
+
+func (sqw *SQLWriter) upsertTransactionCID(transaction models.TxModel) {
+	sqw.stmts <- []byte(fmt.Sprintf(txInsert, transaction.BlockNumber, transaction.HeaderID, transaction.TxHash, transaction.CID, transaction.Dst,
+		transaction.Src, transaction.Index, transaction.Type, transaction.Value))
+	metrics.IndexerMetrics.TransactionsCounter.Inc(1)
+}
+
+func (sqw *SQLWriter) upsertReceiptCID(rct *models.ReceiptModel) {
+	sqw.stmts <- []byte(fmt.Sprintf(rctInsert, rct.BlockNumber, rct.HeaderID, rct.TxID, rct.CID, rct.Contract,
+		rct.PostState, rct.PostStatus))
+	metrics.IndexerMetrics.ReceiptsCounter.Inc(1)
+}
+
+func (sqw *SQLWriter) upsertLogCID(logs []*models.LogsModel) {
+	for _, l := range logs {
+		sqw.stmts <- []byte(fmt.Sprintf(logInsert, l.BlockNumber, l.HeaderID, l.CID, l.ReceiptID, l.Address, l.Index, l.Topic0,
+			l.Topic1, l.Topic2, l.Topic3))
+		metrics.IndexerMetrics.LogsCounter.Inc(1)
+	}
+}
+
+func (sqw *SQLWriter) upsertStateCID(stateNode models.StateNodeModel) {
+	balance := stateNode.Balance
+	if stateNode.Removed {
+		balance = "0"
+	}
+	sqw.stmts <- []byte(fmt.Sprintf(stateInsert, stateNode.BlockNumber, stateNode.HeaderID, stateNode.StateKey, stateNode.CID,
+		stateNode.Removed, true, balance, stateNode.Nonce, stateNode.CodeHash, stateNode.StorageRoot))
+}
+
+func (sqw *SQLWriter) upsertStorageCID(storageCID models.StorageNodeModel) {
+	sqw.stmts <- []byte(fmt.Sprintf(storageInsert, storageCID.BlockNumber, storageCID.HeaderID, storageCID.StateKey, storageCID.StorageKey, storageCID.CID,
+		storageCID.Removed, true, storageCID.Value))
+}
+
+// LoadWatchedAddresses loads watched addresses from a file
+func (sqw *SQLWriter) loadWatchedAddresses() ([]common.Address, error) {
+	// load sql statements from watched addresses file
+	stmts, err := loadWatchedAddressesStatements(sqw.watchedAddressesFilePath)
+	if err != nil {
+		return nil, err
+	}
+
+	// extract addresses from the sql statements
+	watchedAddresses := []common.Address{}
+	for _, stmt := range stmts {
+		addressString, err := parseWatchedAddressStatement(stmt)
+		if err != nil {
+			return nil, err
+		}
+		watchedAddresses = append(watchedAddresses, common.HexToAddress(addressString))
+	}
+
+	return watchedAddresses, nil
+}
+
+// InsertWatchedAddresses inserts the given addresses in a file
+func (sqw *SQLWriter) insertWatchedAddresses(args []types.WatchAddressArg, currentBlockNumber *big.Int) error {
+	// load sql statements from watched addresses file
+	stmts, err := loadWatchedAddressesStatements(sqw.watchedAddressesFilePath)
+	if err != nil {
+		return err
+	}
+
+	// get already watched addresses
+	var watchedAddresses []string
+	for _, stmt := range stmts {
+		addressString, err := parseWatchedAddressStatement(stmt)
+		if err != nil {
+			return err
+		}
+
+		watchedAddresses = append(watchedAddresses, addressString)
+	}
+
+	// append statements for new addresses to existing statements
+	for _, arg := range args {
+		// ignore if already watched
+		if funk.Contains(watchedAddresses, arg.Address) {
+			continue
+		}
+
+		stmt := fmt.Sprintf(watchedAddressesInsert, arg.Address, arg.CreatedAt, currentBlockNumber.Uint64())
+		stmts = append(stmts, stmt)
+	}
+
+	return dumpWatchedAddressesStatements(sqw.watchedAddressesFilePath, stmts)
+}
+
+// RemoveWatchedAddresses removes the given watched addresses from a file
+func (sqw *SQLWriter) removeWatchedAddresses(args []types.WatchAddressArg) error {
+	// load sql statements from watched addresses file
+	stmts, err := loadWatchedAddressesStatements(sqw.watchedAddressesFilePath)
+	if err != nil {
+		return err
+	}
+
+	// get rid of statements having addresses to be removed
+	var filteredStmts []string
+	for _, stmt := range stmts {
+		addressString, err := parseWatchedAddressStatement(stmt)
+		if err != nil {
+			return err
+		}
+
+		toRemove := funk.Contains(args, func(arg types.WatchAddressArg) bool {
+			return arg.Address == addressString
+		})
+
+		if !toRemove {
+			filteredStmts = append(filteredStmts, stmt)
+		}
+	}
+
+	return dumpWatchedAddressesStatements(sqw.watchedAddressesFilePath, filteredStmts)
+}
+
+// SetWatchedAddresses clears and inserts the given addresses in a file
+func (sqw *SQLWriter) setWatchedAddresses(args []types.WatchAddressArg, currentBlockNumber *big.Int) error {
+	var stmts []string
+	for _, arg := range args {
+		stmt := fmt.Sprintf(watchedAddressesInsert, arg.Address, arg.CreatedAt, currentBlockNumber.Uint64())
+		stmts = append(stmts, stmt)
+	}
+
+	return dumpWatchedAddressesStatements(sqw.watchedAddressesFilePath, stmts)
+}
+
+// loadWatchedAddressesStatements loads sql statements from the given file in a string slice
+func loadWatchedAddressesStatements(filePath string) ([]string, error) {
+	file, err := os.Open(filePath)
+	if err != nil {
+		if errors.Is(err, os.ErrNotExist) {
+			return []string{}, nil
+		}
+
+		return nil, fmt.Errorf("error opening watched addresses file: %v", err)
+	}
+	defer file.Close()
+
+	stmts := []string{}
+	scanner := bufio.NewScanner(file)
+	for scanner.Scan() {
+		stmts = append(stmts, scanner.Text())
+	}
+
+	if err := scanner.Err(); err != nil {
+		return nil, fmt.Errorf("error loading watched addresses: %v", err)
+	}
+
+	return stmts, nil
+}
+
+// dumpWatchedAddressesStatements dumps sql statements to the given file
+func dumpWatchedAddressesStatements(filePath string, stmts []string) error {
+	file, err := os.Create(filePath)
+	if err != nil {
+		return fmt.Errorf("error creating watched addresses file: %v", err)
+	}
+	defer file.Close()
+
+	for _, stmt := range stmts {
+		_, err := file.Write([]byte(stmt + "\n"))
+		if err != nil {
+			return fmt.Errorf("error inserting watched_addresses entry: %v", err)
+		}
+	}
+
+	return nil
+}
+
+// parseWatchedAddressStatement parses given sql insert statement to extract the address argument
+func parseWatchedAddressStatement(stmt string) (string, error) {
+	parseResult, err := pg_query.Parse(stmt)
+	if err != nil {
+		return "", fmt.Errorf("error parsing sql stmt: %v", err)
+	}
+
+	// extract address argument from parse output for a SQL statement of form
+	// "INSERT INTO eth_meta.watched_addresses (address, created_at, watched_at)
+	// VALUES ('0xabc', '123', '130') ON CONFLICT (address) DO NOTHING;"
+	addressString := parseResult.Stmts[0].Stmt.GetInsertStmt().
+		SelectStmt.GetSelectStmt().
+		ValuesLists[0].GetList().
+		Items[0].GetAConst().
+		GetVal().
+		GetString_().
+		Str
+
+	return addressString, nil
+}

statediff/indexer/database/metrics/metrics.go

@@ -0,0 +1,263 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package metrics
+
+import (
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/ethereum/go-ethereum/log"
+
+	"github.com/ethereum/go-ethereum/metrics"
+)
+
+const (
+	namespace = "statediff"
+)
+
+var (
+	IndexerMetrics = RegisterIndexerMetrics(metrics.DefaultRegistry)
+	DBMetrics      = RegisterDBMetrics(metrics.DefaultRegistry)
+)
+
+// Build a fully qualified metric name
+func metricName(subsystem, name string) string {
+	if name == "" {
+		return ""
+	}
+	parts := []string{namespace, name}
+	if subsystem != "" {
+		parts = []string{namespace, subsystem, name}
+	}
+	// Prometheus uses _ but geth metrics uses / and replaces
+	return strings.Join(parts, "/")
+}
+
+type IndexerMetricsHandles struct {
+	// The total number of processed BlocksCounter
+	BlocksCounter metrics.Counter
+	// The total number of processed transactions
+	TransactionsCounter metrics.Counter
+	// The total number of processed receipts
+	ReceiptsCounter metrics.Counter
+	// The total number of processed logs
+	LogsCounter metrics.Counter
+	// The total number of access list entries processed
+	AccessListEntriesCounter metrics.Counter
+	// Time spent waiting for free postgres tx
+	FreePostgresTimer metrics.Timer
+	// Postgres transaction commit duration
+	PostgresCommitTimer metrics.Timer
+	// Header processing time
+	HeaderProcessingTimer metrics.Timer
+	// Uncle processing time
+	UncleProcessingTimer metrics.Timer
+	// Tx and receipt processing time
+	TxAndRecProcessingTimer metrics.Timer
+	// State, storage, and code combined processing time
+	StateStoreCodeProcessingTimer metrics.Timer
+
+	// Fine-grained code timers
+	BuildStateDiffWithIntermediateStateNodesTimer    metrics.Timer
+	BuildStateDiffWithoutIntermediateStateNodesTimer metrics.Timer
+	CreatedAndUpdatedStateWithIntermediateNodesTimer metrics.Timer
+	DeletedOrUpdatedStateTimer                       metrics.Timer
+	BuildAccountUpdatesTimer                         metrics.Timer
+	BuildAccountCreationsTimer                       metrics.Timer
+	ResolveNodeTimer                                 metrics.Timer
+	SortKeysTimer                                    metrics.Timer
+	FindIntersectionTimer                            metrics.Timer
+	OutputTimer                                      metrics.Timer
+	IPLDOutputTimer                                  metrics.Timer
+	DifferenceIteratorNextTimer                      metrics.Timer
+	DifferenceIteratorCounter                        metrics.Counter
+	DeletedOrUpdatedStorageTimer                     metrics.Timer
+	CreatedAndUpdatedStorageTimer                    metrics.Timer
+	BuildStorageNodesIncrementalTimer                metrics.Timer
+	BuildStateTrieObjectTimer                        metrics.Timer
+	BuildStateTrieTimer                              metrics.Timer
+	BuildStateDiffObjectTimer                        metrics.Timer
+	WriteStateDiffObjectTimer                        metrics.Timer
+	CreatedAndUpdatedStateTimer                      metrics.Timer
+	BuildStorageNodesEventualTimer                   metrics.Timer
+	BuildStorageNodesFromTrieTimer                   metrics.Timer
+	BuildRemovedAccountStorageNodesTimer             metrics.Timer
+	BuildRemovedStorageNodesFromTrieTimer            metrics.Timer
+	IsWatchedAddressTimer                            metrics.Timer
+}
+
+func RegisterIndexerMetrics(reg metrics.Registry) IndexerMetricsHandles {
+	ctx := IndexerMetricsHandles{
+		BlocksCounter:                                    metrics.NewCounter(),
+		TransactionsCounter:                              metrics.NewCounter(),
+		ReceiptsCounter:                                  metrics.NewCounter(),
+		LogsCounter:                                      metrics.NewCounter(),
+		AccessListEntriesCounter:                         metrics.NewCounter(),
+		FreePostgresTimer:                                metrics.NewTimer(),
+		PostgresCommitTimer:                              metrics.NewTimer(),
+		HeaderProcessingTimer:                            metrics.NewTimer(),
+		UncleProcessingTimer:                             metrics.NewTimer(),
+		TxAndRecProcessingTimer:                          metrics.NewTimer(),
+		StateStoreCodeProcessingTimer:                    metrics.NewTimer(),
+		BuildStateDiffWithIntermediateStateNodesTimer:    metrics.NewTimer(),
+		BuildStateDiffWithoutIntermediateStateNodesTimer: metrics.NewTimer(),
+		CreatedAndUpdatedStateWithIntermediateNodesTimer: metrics.NewTimer(),
+		DeletedOrUpdatedStateTimer:                       metrics.NewTimer(),
+		BuildAccountUpdatesTimer:                         metrics.NewTimer(),
+		BuildAccountCreationsTimer:                       metrics.NewTimer(),
+		ResolveNodeTimer:                                 metrics.NewTimer(),
+		SortKeysTimer:                                    metrics.NewTimer(),
+		FindIntersectionTimer:                            metrics.NewTimer(),
+		OutputTimer:                                      metrics.NewTimer(),
+		IPLDOutputTimer:                                  metrics.NewTimer(),
+		DifferenceIteratorNextTimer:                      metrics.NewTimer(),
+		DifferenceIteratorCounter:                        metrics.NewCounter(),
+		DeletedOrUpdatedStorageTimer:                     metrics.NewTimer(),
+		CreatedAndUpdatedStorageTimer:                    metrics.NewTimer(),
+		BuildStorageNodesIncrementalTimer:                metrics.NewTimer(),
+		BuildStateTrieObjectTimer:                        metrics.NewTimer(),
+		BuildStateTrieTimer:                              metrics.NewTimer(),
+		BuildStateDiffObjectTimer:                        metrics.NewTimer(),
+		WriteStateDiffObjectTimer:                        metrics.NewTimer(),
+		CreatedAndUpdatedStateTimer:                      metrics.NewTimer(),
+		BuildStorageNodesEventualTimer:                   metrics.NewTimer(),
+		BuildStorageNodesFromTrieTimer:                   metrics.NewTimer(),
+		BuildRemovedAccountStorageNodesTimer:             metrics.NewTimer(),
+		BuildRemovedStorageNodesFromTrieTimer:            metrics.NewTimer(),
+		IsWatchedAddressTimer:                            metrics.NewTimer(),
+	}
+	subsys := "indexer"
+	reg.Register(metricName(subsys, "blocks"), ctx.BlocksCounter)
+	reg.Register(metricName(subsys, "transactions"), ctx.TransactionsCounter)
+	reg.Register(metricName(subsys, "receipts"), ctx.ReceiptsCounter)
+	reg.Register(metricName(subsys, "logs"), ctx.LogsCounter)
+	reg.Register(metricName(subsys, "access_list_entries"), ctx.AccessListEntriesCounter)
+	reg.Register(metricName(subsys, "t_free_postgres"), ctx.FreePostgresTimer)
+	reg.Register(metricName(subsys, "t_postgres_commit"), ctx.PostgresCommitTimer)
+	reg.Register(metricName(subsys, "t_header_processing"), ctx.HeaderProcessingTimer)
+	reg.Register(metricName(subsys, "t_uncle_processing"), ctx.UncleProcessingTimer)
+	reg.Register(metricName(subsys, "t_tx_receipt_processing"), ctx.TxAndRecProcessingTimer)
+	reg.Register(metricName(subsys, "t_state_store_code_processing"), ctx.StateStoreCodeProcessingTimer)
+	reg.Register(metricName(subsys, "t_build_statediff_with_intermediate_state_nodes"), ctx.BuildStateDiffWithIntermediateStateNodesTimer)
+	reg.Register(metricName(subsys, "t_build_statediff_without_intermediate_state_nodes"), ctx.BuildStateDiffWithoutIntermediateStateNodesTimer)
+	reg.Register(metricName(subsys, "t_created_and_update_state_with_intermediate_nodes"), ctx.CreatedAndUpdatedStateWithIntermediateNodesTimer)
+	reg.Register(metricName(subsys, "t_deleted_or_updated_state"), ctx.DeletedOrUpdatedStateTimer)
+	reg.Register(metricName(subsys, "t_build_account_updates"), ctx.BuildAccountUpdatesTimer)
+	reg.Register(metricName(subsys, "t_build_account_creations"), ctx.BuildAccountCreationsTimer)
+	reg.Register(metricName(subsys, "t_resolve_node"), ctx.ResolveNodeTimer)
+	reg.Register(metricName(subsys, "t_sort_keys"), ctx.SortKeysTimer)
+	reg.Register(metricName(subsys, "t_find_intersection"), ctx.FindIntersectionTimer)
+	reg.Register(metricName(subsys, "t_output_fn"), ctx.OutputTimer)
+	reg.Register(metricName(subsys, "t_ipld_output_fn"), ctx.IPLDOutputTimer)
+	reg.Register(metricName(subsys, "t_difference_iterator_next"), ctx.DifferenceIteratorNextTimer)
+	reg.Register(metricName(subsys, "difference_iterator_counter"), ctx.DifferenceIteratorCounter)
+	reg.Register(metricName(subsys, "t_created_and_updated_storage"), ctx.CreatedAndUpdatedStorageTimer)
+	reg.Register(metricName(subsys, "t_deleted_or_updated_storage"), ctx.DeletedOrUpdatedStorageTimer)
+	reg.Register(metricName(subsys, "t_build_storage_nodes_incremental"), ctx.BuildStorageNodesIncrementalTimer)
+	reg.Register(metricName(subsys, "t_build_state_trie_object"), ctx.BuildStateTrieObjectTimer)
+	reg.Register(metricName(subsys, "t_build_state_trie"), ctx.BuildStateTrieTimer)
+	reg.Register(metricName(subsys, "t_build_statediff_object"), ctx.BuildStateDiffObjectTimer)
+	reg.Register(metricName(subsys, "t_write_statediff_object"), ctx.WriteStateDiffObjectTimer)
+	reg.Register(metricName(subsys, "t_created_and_updated_state"), ctx.CreatedAndUpdatedStateTimer)
+	reg.Register(metricName(subsys, "t_build_storage_nodes_eventual"), ctx.BuildStorageNodesEventualTimer)
+	reg.Register(metricName(subsys, "t_build_storage_nodes_from_trie"), ctx.BuildStorageNodesFromTrieTimer)
+	reg.Register(metricName(subsys, "t_build_removed_accounts_storage_nodes"), ctx.BuildRemovedAccountStorageNodesTimer)
+	reg.Register(metricName(subsys, "t_build_removed_storage_nodes_from_trie"), ctx.BuildRemovedStorageNodesFromTrieTimer)
+	reg.Register(metricName(subsys, "t_is_watched_address"), ctx.IsWatchedAddressTimer)
+
+	log.Debug("Registering statediff indexer metrics.")
+	return ctx
+}
+
+type dbMetricsHandles struct {
+	// Maximum number of open connections to the sql
+	maxOpen metrics.Gauge
+	// The number of established connections both in use and idle
+	open metrics.Gauge
+	// The number of connections currently in use
+	inUse metrics.Gauge
+	// The number of idle connections
+	idle metrics.Gauge
+	// The total number of connections waited for
+	waitedFor metrics.Counter
+	// The total time blocked waiting for a new connection
+	blockedMilliseconds metrics.Counter
+	// The total number of connections closed due to SetMaxIdleConns
+	closedMaxIdle metrics.Counter
+	// The total number of connections closed due to SetConnMaxLifetime
+	closedMaxLifetime metrics.Counter
+}
+
+func RegisterDBMetrics(reg metrics.Registry) dbMetricsHandles {
+	ctx := dbMetricsHandles{
+		maxOpen:             metrics.NewGauge(),
+		open:                metrics.NewGauge(),
+		inUse:               metrics.NewGauge(),
+		idle:                metrics.NewGauge(),
+		waitedFor:           metrics.NewCounter(),
+		blockedMilliseconds: metrics.NewCounter(),
+		closedMaxIdle:       metrics.NewCounter(),
+		closedMaxLifetime:   metrics.NewCounter(),
+	}
+	subsys := "connections"
+	reg.Register(metricName(subsys, "max_open"), ctx.maxOpen)
+	reg.Register(metricName(subsys, "open"), ctx.open)
+	reg.Register(metricName(subsys, "in_use"), ctx.inUse)
+	reg.Register(metricName(subsys, "idle"), ctx.idle)
+	reg.Register(metricName(subsys, "waited_for"), ctx.waitedFor)
+	reg.Register(metricName(subsys, "blocked_milliseconds"), ctx.blockedMilliseconds)
+	reg.Register(metricName(subsys, "closed_max_idle"), ctx.closedMaxIdle)
+	reg.Register(metricName(subsys, "closed_max_lifetime"), ctx.closedMaxLifetime)
+
+	log.Debug("Registering statediff DB metrics.")
+	return ctx
+}
+
+// DbStats interface to accommodate different concrete sql stats types
+type DbStats interface {
+	MaxOpen() int64
+	Open() int64
+	InUse() int64
+	Idle() int64
+	WaitCount() int64
+	WaitDuration() time.Duration
+	MaxIdleClosed() int64
+	MaxLifetimeClosed() int64
+}
+
+func (met *dbMetricsHandles) Update(stats DbStats) {
+	met.maxOpen.Update(stats.MaxOpen())
+	met.open.Update(stats.Open())
+	met.inUse.Update(stats.InUse())
+	met.idle.Update(stats.Idle())
+	met.waitedFor.Inc(stats.WaitCount())
+	met.blockedMilliseconds.Inc(stats.WaitDuration().Milliseconds())
+	met.closedMaxIdle.Inc(stats.MaxIdleClosed())
+	met.closedMaxLifetime.Inc(stats.MaxLifetimeClosed())
+}
+
+func ReportAndUpdateDuration(msg string, start time.Time, logger log.Logger, timer metrics.Timer) {
+	since := UpdateDuration(start, timer)
+	logger.Debug(fmt.Sprintf("%s duration=%dms", msg, since.Milliseconds()))
+}
+
+func UpdateDuration(start time.Time, timer metrics.Timer) time.Duration {
+	since := time.Since(start)
+	timer.Update(since)
+	return since
+}

statediff/indexer/database/sql/batch_tx.go

@@ -0,0 +1,126 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package sql
+
+import (
+	"context"
+	"sync"
+	"sync/atomic"
+
+	"github.com/lib/pq"
+
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+)
+
+const startingCacheCapacity = 1024 * 24
+
+// BatchTx wraps a sql tx with the state necessary for building the tx concurrently during trie difference iteration
+type BatchTx struct {
+	BlockNumber      string
+	ctx              context.Context
+	dbtx             Tx
+	stm              string
+	quit             chan struct{}
+	iplds            chan models.IPLDModel
+	ipldCache        models.IPLDBatch
+	removedCacheFlag *uint32
+	// Tracks expected cache size and ensures cache is caught up before flush
+	cacheWg sync.WaitGroup
+
+	submit func(blockTx *BatchTx, err error) error
+}
+
+// Submit satisfies indexer.AtomicTx
+func (tx *BatchTx) Submit(err error) error {
+	return tx.submit(tx, err)
+}
+
+func (tx *BatchTx) flush() error {
+	tx.cacheWg.Wait()
+	_, err := tx.dbtx.Exec(tx.ctx, tx.stm, pq.Array(tx.ipldCache.BlockNumbers), pq.Array(tx.ipldCache.Keys),
+		pq.Array(tx.ipldCache.Values))
+	if err != nil {
+		log.Debug(insertError{"ipld.blocks", err, tx.stm,
+			struct {
+				blockNumbers []string
+				keys         []string
+				values       [][]byte
+			}{
+				tx.ipldCache.BlockNumbers,
+				tx.ipldCache.Keys,
+				tx.ipldCache.Values,
+			}}.Error())
+		return insertError{"ipld.blocks", err, tx.stm, "too many arguments; use debug mode for full list"}
+	}
+	tx.ipldCache = models.IPLDBatch{}
+	return nil
+}
+
+// run in background goroutine to synchronize concurrent appends to the ipldCache
+func (tx *BatchTx) cache() {
+	for {
+		select {
+		case i := <-tx.iplds:
+			tx.ipldCache.BlockNumbers = append(tx.ipldCache.BlockNumbers, i.BlockNumber)
+			tx.ipldCache.Keys = append(tx.ipldCache.Keys, i.Key)
+			tx.ipldCache.Values = append(tx.ipldCache.Values, i.Data)
+			tx.cacheWg.Done()
+		case <-tx.quit:
+			tx.ipldCache = models.IPLDBatch{}
+			return
+		}
+	}
+}
+
+func (tx *BatchTx) cacheDirect(key string, value []byte) {
+	tx.cacheWg.Add(1)
+	tx.iplds <- models.IPLDModel{
+		BlockNumber: tx.BlockNumber,
+		Key:         key,
+		Data:        value,
+	}
+}
+
+func (tx *BatchTx) cacheIPLD(i ipld.IPLD) {
+	tx.cacheWg.Add(1)
+	tx.iplds <- models.IPLDModel{
+		BlockNumber: tx.BlockNumber,
+		Key:         i.Cid().String(),
+		Data:        i.RawData(),
+	}
+}
+
+func (tx *BatchTx) cacheRemoved(key string, value []byte) {
+	if atomic.LoadUint32(tx.removedCacheFlag) == 0 {
+		atomic.StoreUint32(tx.removedCacheFlag, 1)
+		tx.cacheWg.Add(1)
+		tx.iplds <- models.IPLDModel{
+			BlockNumber: tx.BlockNumber,
+			Key:         key,
+			Data:        value,
+		}
+	}
+}
+
+// rollback sql transaction and log any error
+func rollback(ctx context.Context, tx Tx) {
+	if err := tx.Rollback(ctx); err != nil {
+		log.Error(err.Error())
+	}
+}

statediff/indexer/database/sql/indexer.go

@@ -0,0 +1,583 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+// Package sql provides an interface for pushing and indexing IPLD objects into a sql database
+// Metrics for reporting processing and connection stats are defined in ./metrics.go
+
+package sql
+
+import (
+	"bytes"
+	"context"
+	"fmt"
+	"math/big"
+	"time"
+
+	"github.com/multiformats/go-multihash"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/crypto"
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/ethereum/go-ethereum/metrics"
+	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/rlp"
+	metrics2 "github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/ipld"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+	sdtypes "github.com/ethereum/go-ethereum/statediff/types"
+)
+
+var _ interfaces.StateDiffIndexer = &StateDiffIndexer{}
+
+// StateDiffIndexer satisfies the indexer.StateDiffIndexer interface for ethereum statediff objects on top of an SQL sql
+type StateDiffIndexer struct {
+	ctx         context.Context
+	chainConfig *params.ChainConfig
+	dbWriter    *Writer
+}
+
+// NewStateDiffIndexer creates a sql implementation of interfaces.StateDiffIndexer
+func NewStateDiffIndexer(ctx context.Context, chainConfig *params.ChainConfig, db Database) (*StateDiffIndexer, error) {
+	return &StateDiffIndexer{
+		ctx:         ctx,
+		chainConfig: chainConfig,
+		dbWriter:    NewWriter(db),
+	}, nil
+}
+
+// ReportDBMetrics is a reporting function to run as goroutine
+func (sdi *StateDiffIndexer) ReportDBMetrics(delay time.Duration, quit <-chan bool) {
+	if !metrics.Enabled {
+		return
+	}
+	ticker := time.NewTicker(delay)
+	go func() {
+		for {
+			select {
+			case <-ticker.C:
+				metrics2.DBMetrics.Update(sdi.dbWriter.db.Stats())
+			case <-quit:
+				ticker.Stop()
+				return
+			}
+		}
+	}()
+}
+
+// PushBlock pushes and indexes block data in sql, except state & storage nodes (includes header, uncles, transactions & receipts)
+// Returns an initiated DB transaction which must be Closed via defer to commit or rollback
+func (sdi *StateDiffIndexer) PushBlock(block *types.Block, receipts types.Receipts, totalDifficulty *big.Int) (interfaces.Batch, error) {
+	start, t := time.Now(), time.Now()
+	blockHash := block.Hash()
+	blockHashStr := blockHash.String()
+	height := block.NumberU64()
+	traceMsg := fmt.Sprintf("indexer stats for statediff at %d with hash %s:\r\n", height, blockHashStr)
+	transactions := block.Transactions()
+	// Derive any missing fields
+	if err := receipts.DeriveFields(sdi.chainConfig, blockHash, height, block.BaseFee(), transactions); err != nil {
+		return nil, err
+	}
+
+	// Generate the block iplds
+	headerNode, txNodes, rctNodes, logNodes, err := ipld.FromBlockAndReceipts(block, receipts)
+	if err != nil {
+		return nil, fmt.Errorf("error creating IPLD nodes from block and receipts: %v", err)
+	}
+
+	if len(txNodes) != len(rctNodes) {
+		return nil, fmt.Errorf("expected number of transactions (%d), receipts (%d)", len(txNodes), len(rctNodes))
+	}
+
+	// Calculate reward
+	var reward *big.Int
+	// in PoA networks block reward is 0
+	if sdi.chainConfig.Clique != nil {
+		reward = big.NewInt(0)
+	} else {
+		reward = shared.CalcEthBlockReward(block.Header(), block.Uncles(), block.Transactions(), receipts)
+	}
+	t = time.Now()
+
+	// Begin new DB tx for everything
+	tx := NewDelayedTx(sdi.dbWriter.db)
+	defer func() {
+		if p := recover(); p != nil {
+			rollback(sdi.ctx, tx)
+			panic(p)
+		} else if err != nil {
+			rollback(sdi.ctx, tx)
+		}
+	}()
+	blockTx := &BatchTx{
+		removedCacheFlag: new(uint32),
+		ctx:              sdi.ctx,
+		BlockNumber:      block.Number().String(),
+		stm:              sdi.dbWriter.db.InsertIPLDsStm(),
+		iplds:            make(chan models.IPLDModel),
+		quit:             make(chan struct{}),
+		ipldCache: models.IPLDBatch{
+			BlockNumbers: make([]string, 0, startingCacheCapacity),
+			Keys:         make([]string, 0, startingCacheCapacity),
+			Values:       make([][]byte, 0, startingCacheCapacity),
+		},
+		dbtx: tx,
+		// handle transaction commit or rollback for any return case
+		submit: func(self *BatchTx, err error) error {
+			defer func() {
+				close(self.quit)
+				close(self.iplds)
+			}()
+			if p := recover(); p != nil {
+				log.Info("panic detected before tx submission, rolling back the tx", "panic", p)
+				rollback(sdi.ctx, tx)
+				panic(p)
+			} else if err != nil {
+				log.Info("error detected before tx submission, rolling back the tx", "error", err)
+				rollback(sdi.ctx, tx)
+			} else {
+				tDiff := time.Since(t)
+				metrics2.IndexerMetrics.StateStoreCodeProcessingTimer.Update(tDiff)
+				traceMsg += fmt.Sprintf("state, storage, and code storage processing time: %s\r\n", tDiff.String())
+				t = time.Now()
+				if err := self.flush(); err != nil {
+					rollback(sdi.ctx, tx)
+					traceMsg += fmt.Sprintf(" TOTAL PROCESSING DURATION: %s\r\n", time.Since(start).String())
+					log.Debug(traceMsg)
+					return err
+				}
+				err = tx.Commit(sdi.ctx)
+				tDiff = time.Since(t)
+				metrics2.IndexerMetrics.PostgresCommitTimer.Update(tDiff)
+				traceMsg += fmt.Sprintf("postgres transaction commit duration: %s\r\n", tDiff.String())
+			}
+			traceMsg += fmt.Sprintf(" TOTAL PROCESSING DURATION: %s\r\n", time.Since(start).String())
+			log.Debug(traceMsg)
+			return err
+		},
+	}
+	go blockTx.cache()
+
+	tDiff := time.Since(t)
+	metrics2.IndexerMetrics.FreePostgresTimer.Update(tDiff)
+
+	traceMsg += fmt.Sprintf("time spent waiting for free postgres tx: %s:\r\n", tDiff.String())
+	t = time.Now()
+
+	// Publish and index header, collect headerID
+	var headerID string
+	headerID, err = sdi.processHeader(blockTx, block.Header(), headerNode, reward, totalDifficulty)
+	if err != nil {
+		return nil, err
+	}
+	tDiff = time.Since(t)
+	metrics2.IndexerMetrics.HeaderProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("header processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+	// Publish and index uncles
+	err = sdi.processUncles(blockTx, headerID, block.Number(), block.UncleHash(), block.Uncles())
+	if err != nil {
+		return nil, err
+	}
+	tDiff = time.Since(t)
+	metrics2.IndexerMetrics.UncleProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("uncle processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+	// Publish and index receipts and txs
+	err = sdi.processReceiptsAndTxs(blockTx, processArgs{
+		headerID:    headerID,
+		blockNumber: block.Number(),
+		receipts:    receipts,
+		txs:         transactions,
+		rctNodes:    rctNodes,
+		txNodes:     txNodes,
+		logNodes:    logNodes,
+	})
+	if err != nil {
+		return nil, err
+	}
+	tDiff = time.Since(t)
+	metrics2.IndexerMetrics.TxAndRecProcessingTimer.Update(tDiff)
+	traceMsg += fmt.Sprintf("tx and receipt processing time: %s\r\n", tDiff.String())
+	t = time.Now()
+
+	return blockTx, err
+}
+
+// processHeader publishes and indexes a header IPLD in Postgres
+// it returns the headerID
+func (sdi *StateDiffIndexer) processHeader(tx *BatchTx, header *types.Header, headerNode ipld.IPLD, reward, td *big.Int) (string, error) {
+	tx.cacheIPLD(headerNode)
+
+	var baseFee *string
+	if header.BaseFee != nil {
+		baseFee = new(string)
+		*baseFee = header.BaseFee.String()
+	}
+	headerID := header.Hash().String()
+	// index header
+	return headerID, sdi.dbWriter.upsertHeaderCID(tx.dbtx, models.HeaderModel{
+		CID:             headerNode.Cid().String(),
+		ParentHash:      header.ParentHash.String(),
+		BlockNumber:     header.Number.String(),
+		BlockHash:       headerID,
+		TotalDifficulty: td.String(),
+		Reward:          reward.String(),
+		Bloom:           header.Bloom.Bytes(),
+		StateRoot:       header.Root.String(),
+		RctRoot:         header.ReceiptHash.String(),
+		TxRoot:          header.TxHash.String(),
+		UnclesHash:      header.UncleHash.String(),
+		Timestamp:       header.Time,
+		Coinbase:        header.Coinbase.String(),
+	})
+}
+
+// processUncles publishes and indexes uncle IPLDs in Postgres
+func (sdi *StateDiffIndexer) processUncles(tx *BatchTx, headerID string, blockNumber *big.Int, unclesHash common.Hash, uncles []*types.Header) error {
+	// publish and index uncles
+	uncleEncoding, err := rlp.EncodeToBytes(uncles)
+	if err != nil {
+		return err
+	}
+	preparedHash := crypto.Keccak256Hash(uncleEncoding)
+	if !bytes.Equal(preparedHash.Bytes(), unclesHash.Bytes()) {
+		return fmt.Errorf("derived uncles hash (%s) does not match the hash in the header (%s)", preparedHash.Hex(), unclesHash.Hex())
+	}
+	unclesCID, err := ipld.RawdataToCid(ipld.MEthHeaderList, uncleEncoding, multihash.KECCAK_256)
+	if err != nil {
+		return err
+	}
+	tx.cacheDirect(unclesCID.String(), uncleEncoding)
+	for i, uncle := range uncles {
+		var uncleReward *big.Int
+		// in PoA networks uncle reward is 0
+		if sdi.chainConfig.Clique != nil {
+			uncleReward = big.NewInt(0)
+		} else {
+			uncleReward = shared.CalcUncleMinerReward(blockNumber.Uint64(), uncle.Number.Uint64())
+		}
+		uncle := models.UncleModel{
+			BlockNumber: blockNumber.String(),
+			HeaderID:    headerID,
+			CID:         unclesCID.String(),
+			ParentHash:  uncle.ParentHash.String(),
+			BlockHash:   uncle.Hash().String(),
+			Reward:      uncleReward.String(),
+			Index:       int64(i),
+		}
+		if err := sdi.dbWriter.upsertUncleCID(tx.dbtx, uncle); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// processArgs bundles arguments to processReceiptsAndTxs
+type processArgs struct {
+	headerID    string
+	blockNumber *big.Int
+	receipts    types.Receipts
+	txs         types.Transactions
+	rctNodes    []*ipld.EthReceipt
+	txNodes     []*ipld.EthTx
+	logNodes    [][]*ipld.EthLog
+}
+
+// processReceiptsAndTxs publishes and indexes receipt and transaction IPLDs in Postgres
+func (sdi *StateDiffIndexer) processReceiptsAndTxs(tx *BatchTx, args processArgs) error {
+	// Process receipts and txs
+	signer := types.MakeSigner(sdi.chainConfig, args.blockNumber)
+	for i, receipt := range args.receipts {
+		txNode := args.txNodes[i]
+		tx.cacheIPLD(txNode)
+		tx.cacheIPLD(args.rctNodes[i])
+
+		// index tx
+		trx := args.txs[i]
+		txID := trx.Hash().String()
+
+		var val string
+		if trx.Value() != nil {
+			val = trx.Value().String()
+		}
+
+		// derive sender for the tx that corresponds with this receipt
+		from, err := types.Sender(signer, trx)
+		if err != nil {
+			return fmt.Errorf("error deriving tx sender: %v", err)
+		}
+		txModel := models.TxModel{
+			BlockNumber: args.blockNumber.String(),
+			HeaderID:    args.headerID,
+			Dst:         shared.HandleZeroAddrPointer(trx.To()),
+			Src:         shared.HandleZeroAddr(from),
+			TxHash:      txID,
+			Index:       int64(i),
+			CID:         txNode.Cid().String(),
+			Type:        trx.Type(),
+			Value:       val,
+		}
+		if err := sdi.dbWriter.upsertTransactionCID(tx.dbtx, txModel); err != nil {
+			return err
+		}
+
+		// this is the contract address if this receipt is for a contract creation tx
+		contract := shared.HandleZeroAddr(receipt.ContractAddress)
+
+		rctModel := &models.ReceiptModel{
+			BlockNumber: args.blockNumber.String(),
+			HeaderID:    args.headerID,
+			TxID:        txID,
+			Contract:    contract,
+			CID:         args.rctNodes[i].Cid().String(),
+		}
+		if len(receipt.PostState) == 0 {
+			rctModel.PostStatus = receipt.Status
+		} else {
+			rctModel.PostState = common.BytesToHash(receipt.PostState).String()
+		}
+
+		if err := sdi.dbWriter.upsertReceiptCID(tx.dbtx, rctModel); err != nil {
+			return err
+		}
+
+		// index logs
+		logDataSet := make([]*models.LogsModel, len(receipt.Logs))
+		for idx, l := range receipt.Logs {
+			tx.cacheIPLD(args.logNodes[i][idx])
+			topicSet := make([]string, 4)
+			for ti, topic := range l.Topics {
+				topicSet[ti] = topic.Hex()
+			}
+
+			logDataSet[idx] = &models.LogsModel{
+				BlockNumber: args.blockNumber.String(),
+				HeaderID:    args.headerID,
+				ReceiptID:   txID,
+				Address:     l.Address.String(),
+				Index:       int64(l.Index),
+				CID:         args.logNodes[i][idx].Cid().String(),
+				Topic0:      topicSet[0],
+				Topic1:      topicSet[1],
+				Topic2:      topicSet[2],
+				Topic3:      topicSet[3],
+			}
+		}
+
+		if err := sdi.dbWriter.upsertLogCID(tx.dbtx, logDataSet); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// PushStateNode publishes and indexes a state diff node object (including any child storage nodes) in the IPLD sql
+func (sdi *StateDiffIndexer) PushStateNode(batch interfaces.Batch, stateNode sdtypes.StateLeafNode, headerID string) error {
+	tx, ok := batch.(*BatchTx)
+	if !ok {
+		return fmt.Errorf("sql: batch is expected to be of type %T, got %T", &BatchTx{}, batch)
+	}
+	// publish the state node
+	var stateModel models.StateNodeModel
+	if stateNode.Removed {
+		tx.cacheRemoved(shared.RemovedNodeStateCID, []byte{})
+		stateModel = models.StateNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			CID:         shared.RemovedNodeStateCID,
+			Removed:     true,
+		}
+	} else {
+		stateModel = models.StateNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			CID:         stateNode.AccountWrapper.CID,
+			Removed:     false,
+			Balance:     stateNode.AccountWrapper.Account.Balance.String(),
+			Nonce:       stateNode.AccountWrapper.Account.Nonce,
+			CodeHash:    common.BytesToHash(stateNode.AccountWrapper.Account.CodeHash).String(),
+			StorageRoot: stateNode.AccountWrapper.Account.Root.String(),
+		}
+	}
+
+	// index the state node
+	if err := sdi.dbWriter.upsertStateCID(tx.dbtx, stateModel); err != nil {
+		return err
+	}
+
+	// if there are any storage nodes associated with this node, publish and index them
+	for _, storageNode := range stateNode.StorageDiff {
+		if storageNode.Removed {
+			tx.cacheRemoved(shared.RemovedNodeStorageCID, []byte{})
+			storageModel := models.StorageNodeModel{
+				BlockNumber: tx.BlockNumber,
+				HeaderID:    headerID,
+				StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+				StorageKey:  common.BytesToHash(storageNode.LeafKey).String(),
+				CID:         shared.RemovedNodeStorageCID,
+				Removed:     true,
+				Value:       []byte{},
+			}
+			if err := sdi.dbWriter.upsertStorageCID(tx.dbtx, storageModel); err != nil {
+				return err
+			}
+			continue
+		}
+		storageModel := models.StorageNodeModel{
+			BlockNumber: tx.BlockNumber,
+			HeaderID:    headerID,
+			StateKey:    common.BytesToHash(stateNode.AccountWrapper.LeafKey).String(),
+			StorageKey:  common.BytesToHash(storageNode.LeafKey).String(),
+			CID:         storageNode.CID,
+			Removed:     false,
+			Value:       storageNode.Value,
+		}
+		if err := sdi.dbWriter.upsertStorageCID(tx.dbtx, storageModel); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+// PushIPLD publishes iplds to ipld.blocks
+func (sdi *StateDiffIndexer) PushIPLD(batch interfaces.Batch, ipld sdtypes.IPLD) error {
+	tx, ok := batch.(*BatchTx)
+	if !ok {
+		return fmt.Errorf("sql: batch is expected to be of type %T, got %T", &BatchTx{}, batch)
+	}
+	tx.cacheDirect(ipld.CID, ipld.Content)
+	return nil
+}
+
+// Close satisfies io.Closer
+func (sdi *StateDiffIndexer) Close() error {
+	return sdi.dbWriter.Close()
+}
+
+// Update the known gaps table with the gap information.
+
+// LoadWatchedAddresses reads watched addresses from the database
+func (sdi *StateDiffIndexer) LoadWatchedAddresses() ([]common.Address, error) {
+	addressStrings := make([]string, 0)
+	pgStr := "SELECT address FROM eth_meta.watched_addresses"
+	err := sdi.dbWriter.db.Select(sdi.ctx, &addressStrings, pgStr)
+	if err != nil {
+		return nil, fmt.Errorf("error loading watched addresses: %v", err)
+	}
+
+	watchedAddresses := []common.Address{}
+	for _, addressString := range addressStrings {
+		watchedAddresses = append(watchedAddresses, common.HexToAddress(addressString))
+	}
+
+	return watchedAddresses, nil
+}
+
+// InsertWatchedAddresses inserts the given addresses in the database
+func (sdi *StateDiffIndexer) InsertWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) (err error) {
+	tx := NewDelayedTx(sdi.dbWriter.db)
+	defer func() {
+		if p := recover(); p != nil {
+			rollback(sdi.ctx, tx)
+			panic(p)
+		} else if err != nil {
+			rollback(sdi.ctx, tx)
+		} else {
+			err = tx.Commit(sdi.ctx)
+		}
+	}()
+
+	for _, arg := range args {
+		_, err = tx.Exec(sdi.ctx, `INSERT INTO eth_meta.watched_addresses (address, created_at, watched_at) VALUES ($1, $2, $3) ON CONFLICT (address) DO NOTHING`,
+			arg.Address, arg.CreatedAt, currentBlockNumber.Uint64())
+		if err != nil {
+			return fmt.Errorf("error inserting watched_addresses entry: %v", err)
+		}
+	}
+
+	return err
+}
+
+// RemoveWatchedAddresses removes the given watched addresses from the database
+func (sdi *StateDiffIndexer) RemoveWatchedAddresses(args []sdtypes.WatchAddressArg) (err error) {
+	tx := NewDelayedTx(sdi.dbWriter.db)
+	defer func() {
+		if p := recover(); p != nil {
+			rollback(sdi.ctx, tx)
+			panic(p)
+		} else if err != nil {
+			rollback(sdi.ctx, tx)
+		} else {
+			err = tx.Commit(sdi.ctx)
+		}
+	}()
+
+	for _, arg := range args {
+		_, err = tx.Exec(sdi.ctx, `DELETE FROM eth_meta.watched_addresses WHERE address = $1`, arg.Address)
+		if err != nil {
+			return fmt.Errorf("error removing watched_addresses entry: %v", err)
+		}
+	}
+
+	return err
+}
+
+// SetWatchedAddresses clears and inserts the given addresses in the database
+func (sdi *StateDiffIndexer) SetWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) (err error) {
+	tx := NewDelayedTx(sdi.dbWriter.db)
+	defer func() {
+		if p := recover(); p != nil {
+			rollback(sdi.ctx, tx)
+			panic(p)
+		} else if err != nil {
+			rollback(sdi.ctx, tx)
+		} else {
+			err = tx.Commit(sdi.ctx)
+		}
+	}()
+
+	_, err = tx.Exec(sdi.ctx, `DELETE FROM eth_meta.watched_addresses`)
+	if err != nil {
+		return fmt.Errorf("error setting watched_addresses table: %v", err)
+	}
+
+	for _, arg := range args {
+		_, err = tx.Exec(sdi.ctx, `INSERT INTO eth_meta.watched_addresses (address, created_at, watched_at) VALUES ($1, $2, $3) ON CONFLICT (address) DO NOTHING`,
+			arg.Address, arg.CreatedAt, currentBlockNumber.Uint64())
+		if err != nil {
+			return fmt.Errorf("error setting watched_addresses table: %v", err)
+		}
+	}
+
+	return err
+}
+
+// ClearWatchedAddresses clears all the watched addresses from the database
+func (sdi *StateDiffIndexer) ClearWatchedAddresses() error {
+	_, err := sdi.dbWriter.db.Exec(sdi.ctx, `DELETE FROM eth_meta.watched_addresses`)
+	if err != nil {
+		return fmt.Errorf("error clearing watched_addresses table: %v", err)
+	}
+
+	return nil
+}

statediff/indexer/database/sql/indexer_shared_test.go

@@ -0,0 +1,28 @@
+package sql_test
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test_helpers"
+)
+
+var (
+	db  sql.Database
+	err error
+	ind interfaces.StateDiffIndexer
+)
+
+func checkTxClosure(t *testing.T, idle, inUse, open int64) {
+	require.Equal(t, idle, db.Stats().Idle())
+	require.Equal(t, inUse, db.Stats().InUse())
+	require.Equal(t, open, db.Stats().Open())
+}
+
+func tearDown(t *testing.T) {
+	test_helpers.TearDownDB(t, db)
+	require.NoError(t, ind.Close())
+}

statediff/indexer/database/sql/interfaces.go

@@ -0,0 +1,88 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package sql
+
+import (
+	"context"
+	"io"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+)
+
+// Database interfaces required by the sql indexer
+type Database interface {
+	Driver
+	Statements
+}
+
+// Driver interface has all the methods required by a driver implementation to support the sql indexer
+type Driver interface {
+	UseCopyFrom() bool
+	QueryRow(ctx context.Context, sql string, args ...interface{}) ScannableRow
+	Exec(ctx context.Context, sql string, args ...interface{}) (Result, error)
+	Select(ctx context.Context, dest interface{}, query string, args ...interface{}) error
+	Get(ctx context.Context, dest interface{}, query string, args ...interface{}) error
+	Begin(ctx context.Context) (Tx, error)
+	Stats() metrics.DbStats
+	NodeID() string
+	Context() context.Context
+	io.Closer
+}
+
+// Statements interface to accommodate different SQL query syntax
+type Statements interface {
+	InsertHeaderStm() string
+	InsertUncleStm() string
+	InsertTxStm() string
+	InsertRctStm() string
+	InsertLogStm() string
+	InsertStateStm() string
+	InsertStorageStm() string
+	InsertIPLDStm() string
+	InsertIPLDsStm() string
+
+	// Table/column descriptions for use with CopyFrom and similar commands.
+	LogTableName() []string
+	LogColumnNames() []string
+	RctTableName() []string
+	RctColumnNames() []string
+	StateTableName() []string
+	StateColumnNames() []string
+	StorageTableName() []string
+	StorageColumnNames() []string
+	TxTableName() []string
+	TxColumnNames() []string
+}
+
+// Tx interface to accommodate different concrete SQL transaction types
+type Tx interface {
+	QueryRow(ctx context.Context, sql string, args ...interface{}) ScannableRow
+	Exec(ctx context.Context, sql string, args ...interface{}) (Result, error)
+	CopyFrom(ctx context.Context, tableName []string, columnNames []string, rows [][]interface{}) (int64, error)
+	Commit(ctx context.Context) error
+	Rollback(ctx context.Context) error
+}
+
+// ScannableRow interface to accommodate different concrete row types
+type ScannableRow interface {
+	Scan(dest ...interface{}) error
+}
+
+// Result interface to accommodate different concrete result types
+type Result interface {
+	RowsAffected() (int64, error)
+}

statediff/indexer/database/sql/lazy_tx.go

@@ -0,0 +1,106 @@
+package sql
+
+import (
+	"context"
+	"reflect"
+
+	"github.com/ethereum/go-ethereum/log"
+)
+
+// Changing this to 1 would make sure only sequential COPYs were combined.
+const copyFromCheckLimit = 100
+
+type DelayedTx struct {
+	cache []interface{}
+	db    Database
+}
+type cachedStmt struct {
+	sql  string
+	args []interface{}
+}
+
+type copyFrom struct {
+	tableName   []string
+	columnNames []string
+	rows        [][]interface{}
+}
+
+func (cf *copyFrom) appendRows(rows [][]interface{}) {
+	cf.rows = append(cf.rows, rows...)
+}
+
+func (cf *copyFrom) matches(tableName []string, columnNames []string) bool {
+	return reflect.DeepEqual(cf.tableName, tableName) && reflect.DeepEqual(cf.columnNames, columnNames)
+}
+
+func NewDelayedTx(db Database) *DelayedTx {
+	return &DelayedTx{db: db}
+}
+
+func (tx *DelayedTx) QueryRow(ctx context.Context, sql string, args ...interface{}) ScannableRow {
+	return tx.db.QueryRow(ctx, sql, args...)
+}
+
+func (tx *DelayedTx) findPrevCopyFrom(tableName []string, columnNames []string, limit int) (*copyFrom, int) {
+	for pos, count := len(tx.cache)-1, 0; pos >= 0 && count < limit; pos, count = pos-1, count+1 {
+		prevCopy, ok := tx.cache[pos].(*copyFrom)
+		if ok && prevCopy.matches(tableName, columnNames) {
+			return prevCopy, count
+		}
+	}
+	return nil, -1
+}
+
+func (tx *DelayedTx) CopyFrom(ctx context.Context, tableName []string, columnNames []string, rows [][]interface{}) (int64, error) {
+	if prevCopy, distance := tx.findPrevCopyFrom(tableName, columnNames, copyFromCheckLimit); nil != prevCopy {
+		log.Trace("statediff lazy_tx : Appending to COPY", "table", tableName,
+			"current", len(prevCopy.rows), "new", len(rows), "distance", distance)
+		prevCopy.appendRows(rows)
+	} else {
+		tx.cache = append(tx.cache, &copyFrom{tableName, columnNames, rows})
+	}
+
+	return 0, nil
+}
+
+func (tx *DelayedTx) Exec(ctx context.Context, sql string, args ...interface{}) (Result, error) {
+	tx.cache = append(tx.cache, cachedStmt{sql, args})
+	return nil, nil
+}
+
+func (tx *DelayedTx) Commit(ctx context.Context) error {
+	base, err := tx.db.Begin(ctx)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		if p := recover(); p != nil {
+			rollback(ctx, base)
+			panic(p)
+		} else if err != nil {
+			rollback(ctx, base)
+		}
+	}()
+	for _, item := range tx.cache {
+		switch item := item.(type) {
+		case *copyFrom:
+			_, err := base.CopyFrom(ctx, item.tableName, item.columnNames, item.rows)
+			if err != nil {
+				log.Error("COPY error", "table", item.tableName, "err", err)
+				return err
+			}
+		case cachedStmt:
+			_, err := base.Exec(ctx, item.sql, item.args...)
+			if err != nil {
+				return err
+			}
+		}
+	}
+	tx.cache = nil
+	return base.Commit(ctx)
+}
+
+func (tx *DelayedTx) Rollback(ctx context.Context) error {
+	tx.cache = nil
+	return nil
+}

statediff/indexer/database/sql/mainnet_tests/indexer_test.go

@@ -0,0 +1,95 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package mainnet_tests
+
+import (
+	"context"
+	"fmt"
+	"math/big"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test_helpers"
+)
+
+var (
+	err       error
+	db        sql.Database
+	ind       interfaces.StateDiffIndexer
+	chainConf = params.MainnetChainConfig
+)
+
+func init() {
+	if os.Getenv("MODE") != "statediff" {
+		fmt.Println("Skipping statediff test")
+		os.Exit(0)
+	}
+}
+
+func TestMainnetIndexer(t *testing.T) {
+	conf := test_helpers.GetTestConfig()
+
+	for _, blockNumber := range test_helpers.ProblemBlocks {
+		conf.BlockNumber = big.NewInt(blockNumber)
+		tb, trs, err := test_helpers.TestBlockAndReceipts(conf)
+		require.NoError(t, err)
+
+		testPushBlockAndState(t, tb, trs)
+	}
+
+	testBlock, testReceipts, err := test_helpers.TestBlockAndReceiptsFromEnv(conf)
+	require.NoError(t, err)
+
+	testPushBlockAndState(t, testBlock, testReceipts)
+}
+
+func testPushBlockAndState(t *testing.T, block *types.Block, receipts types.Receipts) {
+	t.Run("Test PushBlock and PushStateNode", func(t *testing.T) {
+		setupMainnetIndexer(t)
+		defer checkTxClosure(t, 0, 0, 0)
+		defer tearDown(t)
+
+		test.TestBlock(t, ind, block, receipts)
+	})
+}
+
+func setupMainnetIndexer(t *testing.T) {
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+	ind, err = sql.NewStateDiffIndexer(context.Background(), chainConf, db)
+}
+
+func checkTxClosure(t *testing.T, idle, inUse, open int64) {
+	require.Equal(t, idle, db.Stats().Idle())
+	require.Equal(t, inUse, db.Stats().InUse())
+	require.Equal(t, open, db.Stats().Open())
+}
+
+func tearDown(t *testing.T) {
+	test_helpers.TearDownDB(t, db)
+	require.NoError(t, ind.Close())
+}

statediff/indexer/database/sql/pgx_indexer_legacy_test.go

@@ -0,0 +1,52 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package sql_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+)
+
+func setupLegacyPGXIndexer(t *testing.T) {
+	db, err = postgres.SetupPGXDB(postgres.DefaultConfig)
+	if err != nil {
+		t.Fatal(err)
+	}
+	ind, err = sql.NewStateDiffIndexer(context.Background(), test.LegacyConfig, db)
+	require.NoError(t, err)
+}
+
+func setupLegacyPGX(t *testing.T) {
+	setupLegacyPGXIndexer(t)
+	test.SetupLegacyTestData(t, ind)
+}
+
+func TestLegacyPGXIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs", func(t *testing.T) {
+		setupLegacyPGX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestLegacyIndexer(t, db)
+	})
+}

statediff/indexer/database/sql/pgx_indexer_test.go

@@ -0,0 +1,245 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package sql_test
+
+import (
+	"context"
+	"math/big"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/mocks"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+)
+
+func setupPGXIndexer(t *testing.T, config postgres.Config) {
+	db, err = postgres.SetupPGXDB(config)
+	if err != nil {
+		t.Fatal(err)
+	}
+	ind, err = sql.NewStateDiffIndexer(context.Background(), mocks.TestConfig, db)
+	require.NoError(t, err)
+}
+
+func setupPGX(t *testing.T) {
+	setupPGXWithConfig(t, postgres.DefaultConfig)
+}
+
+func setupPGXWithConfig(t *testing.T, config postgres.Config) {
+	setupPGXIndexer(t, config)
+	test.SetupTestData(t, ind)
+}
+
+func setupPGXNonCanonical(t *testing.T) {
+	setupPGXIndexer(t, postgres.DefaultConfig)
+	test.SetupTestDataNonCanonical(t, ind)
+}
+
+// Test indexer for a canonical block
+func TestPGXIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs in a single tx", func(t *testing.T) {
+		setupPGX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexHeaderIPLDs(t, db)
+	})
+
+	t.Run("Publish and index transaction IPLDs in a single tx", func(t *testing.T) {
+		setupPGX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexTransactionIPLDs(t, db)
+	})
+
+	t.Run("Publish and index log IPLDs for multiple receipt of a specific block", func(t *testing.T) {
+		setupPGX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexLogIPLDs(t, db)
+	})
+
+	t.Run("Publish and index receipt IPLDs in a single tx", func(t *testing.T) {
+		setupPGX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexReceiptIPLDs(t, db)
+	})
+
+	t.Run("Publish and index state IPLDs in a single tx", func(t *testing.T) {
+		setupPGX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexStateIPLDs(t, db)
+	})
+
+	t.Run("Publish and index storage IPLDs in a single tx", func(t *testing.T) {
+		setupPGX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexStorageIPLDs(t, db)
+	})
+
+	t.Run("Publish and index with CopyFrom enabled.", func(t *testing.T) {
+		config := postgres.DefaultConfig
+		config.CopyFrom = true
+
+		setupPGXWithConfig(t, config)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexStateIPLDs(t, db)
+		test.TestPublishAndIndexStorageIPLDs(t, db)
+		test.TestPublishAndIndexReceiptIPLDs(t, db)
+		test.TestPublishAndIndexLogIPLDs(t, db)
+	})
+}
+
+// Test indexer for a canonical + a non-canonical block at London height + a non-canonical block at London height + 1
+func TestPGXIndexerNonCanonical(t *testing.T) {
+	t.Run("Publish and index header", func(t *testing.T) {
+		setupPGXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexHeaderNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index transactions", func(t *testing.T) {
+		setupPGXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexTransactionsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index receipts", func(t *testing.T) {
+		setupPGXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexReceiptsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index logs", func(t *testing.T) {
+		setupPGXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexLogsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index state nodes", func(t *testing.T) {
+		setupPGXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexStateNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index storage nodes", func(t *testing.T) {
+		setupPGXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 1, 0, 1)
+
+		test.TestPublishAndIndexStorageNonCanonical(t, db)
+	})
+}
+
+func TestPGXWatchAddressMethods(t *testing.T) {
+	setupPGXIndexer(t, postgres.DefaultConfig)
+	defer tearDown(t)
+	defer checkTxClosure(t, 1, 0, 1)
+
+	t.Run("Load watched addresses (empty table)", func(t *testing.T) {
+		test.TestLoadEmptyWatchedAddresses(t, ind)
+	})
+
+	t.Run("Insert watched addresses", func(t *testing.T) {
+		args := mocks.GetInsertWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt1)))
+		require.NoError(t, err)
+
+		test.TestInsertWatchedAddresses(t, db)
+	})
+
+	t.Run("Insert watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetInsertAlreadyWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		test.TestInsertAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses", func(t *testing.T) {
+		args := mocks.GetRemoveWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		test.TestRemoveWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses (some non-watched)", func(t *testing.T) {
+		args := mocks.GetRemoveNonWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		test.TestRemoveNonWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses", func(t *testing.T) {
+		args := mocks.GetSetWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		test.TestSetWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetSetAlreadyWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt3)))
+		require.NoError(t, err)
+
+		test.TestSetAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Load watched addresses", func(t *testing.T) {
+		test.TestLoadWatchedAddresses(t, ind)
+	})
+
+	t.Run("Clear watched addresses", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		test.TestClearWatchedAddresses(t, db)
+	})
+
+	t.Run("Clear watched addresses (empty table)", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		test.TestClearEmptyWatchedAddresses(t, db)
+	})
+}

statediff/indexer/database/sql/postgres/config.go

@@ -0,0 +1,139 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres
+
+import (
+	"fmt"
+	"os"
+	"strconv"
+	"strings"
+	"time"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+)
+
+// DriverType to explicitly type the kind of sql driver we are using
+type DriverType string
+
+const (
+	PGX     DriverType = "PGX"
+	SQLX    DriverType = "SQLX"
+	Unknown DriverType = "Unknown"
+)
+
+// Env variables
+const (
+	DATABASE_NAME     = "DATABASE_NAME"
+	DATABASE_HOSTNAME = "DATABASE_HOSTNAME"
+	DATABASE_PORT     = "DATABASE_PORT"
+	DATABASE_USER     = "DATABASE_USER"
+	DATABASE_PASSWORD = "DATABASE_PASSWORD"
+)
+
+// ResolveDriverType resolves a DriverType from a provided string
+func ResolveDriverType(str string) (DriverType, error) {
+	switch strings.ToLower(str) {
+	case "pgx", "pgxpool":
+		return PGX, nil
+	case "sqlx":
+		return SQLX, nil
+	default:
+		return Unknown, fmt.Errorf("unrecognized driver type string: %s", str)
+	}
+}
+
+// DefaultConfig are default parameters for connecting to a Postgres sql
+var DefaultConfig = Config{
+	Hostname:     "localhost",
+	Port:         8077,
+	DatabaseName: "cerc_testing",
+	Username:     "vdbm",
+	Password:     "password",
+}
+
+// Config holds params for a Postgres db
+type Config struct {
+	// conn string params
+	Hostname     string
+	Port         int
+	DatabaseName string
+	Username     string
+	Password     string
+
+	// conn settings
+	MaxConns        int
+	MaxIdle         int
+	MinConns        int
+	MaxConnIdleTime time.Duration
+	MaxConnLifetime time.Duration
+	ConnTimeout     time.Duration
+	LogStatements   bool
+
+	// node info params
+	ID         string
+	ClientName string
+
+	// driver type
+	Driver DriverType
+
+	// toggle on/off upserts
+	Upsert bool
+
+	// toggle on/off CopyFrom
+	CopyFrom bool
+}
+
+// Type satisfies interfaces.Config
+func (c Config) Type() shared.DBType {
+	return shared.POSTGRES
+}
+
+// DbConnectionString constructs and returns the connection string from the config
+func (c Config) DbConnectionString() string {
+	if len(c.Username) > 0 && len(c.Password) > 0 {
+		return fmt.Sprintf("postgresql://%s:%s@%s:%d/%s?sslmode=disable",
+			c.Username, c.Password, c.Hostname, c.Port, c.DatabaseName)
+	}
+	if len(c.Username) > 0 && len(c.Password) == 0 {
+		return fmt.Sprintf("postgresql://%s@%s:%d/%s?sslmode=disable",
+			c.Username, c.Hostname, c.Port, c.DatabaseName)
+	}
+	return fmt.Sprintf("postgresql://%s:%d/%s?sslmode=disable", c.Hostname, c.Port, c.DatabaseName)
+}
+
+func (c Config) WithEnv() (Config, error) {
+	if val := os.Getenv(DATABASE_NAME); val != "" {
+		c.DatabaseName = val
+	}
+	if val := os.Getenv(DATABASE_HOSTNAME); val != "" {
+		c.Hostname = val
+	}
+	if val := os.Getenv(DATABASE_PORT); val != "" {
+		port, err := strconv.Atoi(val)
+		if err != nil {
+			return c, err
+		}
+		c.Port = port
+	}
+	if val := os.Getenv(DATABASE_USER); val != "" {
+		c.Username = val
+	}
+	if val := os.Getenv(DATABASE_PASSWORD); val != "" {
+		c.Password = val
+	}
+	return c, nil
+}

statediff/indexer/database/sql/postgres/database.go

@@ -0,0 +1,126 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres
+
+import (
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared/schema"
+)
+
+var _ sql.Database = &DB{}
+
+const (
+	createNodeStm = `INSERT INTO nodes (genesis_block, network_id, node_id, client_name, chain_id) VALUES ($1, $2, $3, $4, $5)
+					 ON CONFLICT (node_id) DO NOTHING`
+)
+
+// NewPostgresDB returns a postgres.DB using the provided driver
+func NewPostgresDB(driver sql.Driver, upsert bool) *DB {
+	return &DB{upsert, driver}
+}
+
+// DB implements sql.Database using a configured driver and Postgres statement syntax
+type DB struct {
+	upsert bool
+	sql.Driver
+}
+
+// InsertHeaderStm satisfies the sql.Statements interface
+// Stm == Statement
+func (db *DB) InsertHeaderStm() string {
+	return schema.TableHeader.ToInsertStatement(db.upsert)
+}
+
+// InsertUncleStm satisfies the sql.Statements interface
+func (db *DB) InsertUncleStm() string {
+	return schema.TableUncle.ToInsertStatement(db.upsert)
+}
+
+// InsertTxStm satisfies the sql.Statements interface
+func (db *DB) InsertTxStm() string {
+	return schema.TableTransaction.ToInsertStatement(db.upsert)
+}
+
+// InsertRctStm satisfies the sql.Statements interface
+func (db *DB) InsertRctStm() string {
+	return schema.TableReceipt.ToInsertStatement(db.upsert)
+}
+
+// InsertLogStm satisfies the sql.Statements interface
+func (db *DB) InsertLogStm() string {
+	return schema.TableLog.ToInsertStatement(db.upsert)
+}
+
+// InsertStateStm satisfies the sql.Statements interface
+func (db *DB) InsertStateStm() string {
+	return schema.TableStateNode.ToInsertStatement(db.upsert)
+}
+
+// InsertStorageStm satisfies the sql.Statements interface
+func (db *DB) InsertStorageStm() string {
+	return schema.TableStorageNode.ToInsertStatement(db.upsert)
+}
+
+// InsertIPLDStm satisfies the sql.Statements interface
+func (db *DB) InsertIPLDStm() string {
+	return schema.TableIPLDBlock.ToInsertStatement(db.upsert)
+}
+
+// InsertIPLDsStm satisfies the sql.Statements interface
+func (db *DB) InsertIPLDsStm() string {
+	return `INSERT INTO ipld.blocks (block_number, key, data) VALUES (unnest($1::BIGINT[]), unnest($2::TEXT[]), unnest($3::BYTEA[])) ON CONFLICT DO NOTHING`
+}
+
+func (db *DB) LogTableName() []string {
+	return []string{"eth", "log_cids"}
+}
+
+func (db *DB) LogColumnNames() []string {
+	return []string{"block_number", "header_id", "cid", "rct_id", "address", "index", "topic0", "topic1", "topic2", "topic3"}
+}
+
+func (db *DB) RctTableName() []string {
+	return []string{"eth", "receipt_cids"}
+}
+
+func (db *DB) RctColumnNames() []string {
+	return []string{"block_number", "header_id", "tx_id", "cid", "contract", "post_state", "post_status"}
+}
+
+func (db *DB) StateTableName() []string {
+	return []string{"eth", "state_cids"}
+}
+
+func (db *DB) StateColumnNames() []string {
+	return []string{"block_number", "header_id", "state_leaf_key", "cid", "diff", "balance", "nonce", "code_hash", "storage_root", "removed"}
+}
+
+func (db *DB) StorageTableName() []string {
+	return []string{"eth", "storage_cids"}
+}
+
+func (db *DB) StorageColumnNames() []string {
+	return []string{"block_number", "header_id", "state_leaf_key", "storage_leaf_key", "cid", "diff", "val", "removed"}
+}
+
+func (db *DB) TxTableName() []string {
+	return []string{"eth", "transaction_cids"}
+}
+
+func (db *DB) TxColumnNames() []string {
+	return []string{"block_number", "header_id", "tx_hash", "cid", "dst", "src", "index", "tx_type", "value"}
+}

statediff/indexer/database/sql/postgres/errors.go

@@ -0,0 +1,38 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres
+
+import (
+	"fmt"
+)
+
+const (
+	DbConnectionFailedMsg = "db connection failed"
+	SettingNodeFailedMsg  = "unable to set db node"
+)
+
+func ErrDBConnectionFailed(connectErr error) error {
+	return formatError(DbConnectionFailedMsg, connectErr)
+}
+
+func ErrUnableToSetNode(setErr error) error {
+	return formatError(SettingNodeFailedMsg, setErr)
+}
+
+func formatError(msg string, err error) error {
+	return fmt.Errorf("%s: %w", msg, err)
+}

statediff/indexer/database/sql/postgres/log_adapter.go

@@ -0,0 +1,61 @@
+// Copyright © 2023 Cerc
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres
+
+import (
+	"context"
+
+	"github.com/ethereum/go-ethereum/log"
+	"github.com/jackc/pgx/v4"
+)
+
+type LogAdapter struct {
+	l log.Logger
+}
+
+func NewLogAdapter(l log.Logger) *LogAdapter {
+	return &LogAdapter{l: l}
+}
+
+func (l *LogAdapter) Log(ctx context.Context, level pgx.LogLevel, msg string, data map[string]interface{}) {
+	var logger log.Logger
+	if data != nil {
+		var args = make([]interface{}, 0)
+		for key, value := range data {
+			if value != nil {
+				args = append(args, key, value)
+			}
+		}
+		logger = l.l.New(args...)
+	} else {
+		logger = l.l
+	}
+
+	switch level {
+	case pgx.LogLevelTrace:
+		logger.Trace(msg)
+	case pgx.LogLevelDebug:
+		logger.Debug(msg)
+	case pgx.LogLevelInfo:
+		logger.Info(msg)
+	case pgx.LogLevelWarn:
+		logger.Warn(msg)
+	case pgx.LogLevelError:
+		logger.Error(msg)
+	default:
+		logger.New("INVALID_PGX_LOG_LEVEL", level).Error(msg)
+	}
+}

statediff/indexer/database/sql/postgres/pgx.go

@@ -0,0 +1,256 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres
+
+import (
+	"context"
+	"time"
+
+	"github.com/ethereum/go-ethereum/log"
+
+	"github.com/georgysavva/scany/pgxscan"
+	"github.com/jackc/pgconn"
+	"github.com/jackc/pgx/v4"
+	"github.com/jackc/pgx/v4/pgxpool"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/node"
+)
+
+// PGXDriver driver, implements sql.Driver
+type PGXDriver struct {
+	ctx      context.Context
+	pool     *pgxpool.Pool
+	nodeInfo node.Info
+	nodeID   string
+	config   Config
+}
+
+// ConnectPGX initializes and returns a PGX connection pool
+func ConnectPGX(ctx context.Context, config Config) (*pgxpool.Pool, error) {
+	pgConf, err := MakeConfig(config)
+	if err != nil {
+		return nil, err
+	}
+	return pgxpool.ConnectConfig(ctx, pgConf)
+}
+
+// NewPGXDriver returns a new pgx driver
+// it initializes the connection pool and creates the node info table
+func NewPGXDriver(ctx context.Context, config Config, node node.Info) (*PGXDriver, error) {
+	dbPool, err := ConnectPGX(ctx, config)
+	if err != nil {
+		return nil, ErrDBConnectionFailed(err)
+	}
+	pg := &PGXDriver{ctx: ctx, pool: dbPool, nodeInfo: node, config: config}
+	nodeErr := pg.createNode()
+	if nodeErr != nil {
+		return &PGXDriver{}, ErrUnableToSetNode(nodeErr)
+	}
+	return pg, nil
+}
+
+// MakeConfig creates a pgxpool.Config from the provided Config
+func MakeConfig(config Config) (*pgxpool.Config, error) {
+	conf, err := pgxpool.ParseConfig("")
+	if err != nil {
+		return nil, err
+	}
+
+	//conf.ConnConfig.BuildStatementCache = nil
+	conf.ConnConfig.Config.Host = config.Hostname
+	conf.ConnConfig.Config.Port = uint16(config.Port)
+	conf.ConnConfig.Config.Database = config.DatabaseName
+	conf.ConnConfig.Config.User = config.Username
+	conf.ConnConfig.Config.Password = config.Password
+
+	if config.ConnTimeout != 0 {
+		conf.ConnConfig.Config.ConnectTimeout = config.ConnTimeout
+	}
+	if config.MaxConns != 0 {
+		conf.MaxConns = int32(config.MaxConns)
+	}
+	if config.MinConns != 0 {
+		conf.MinConns = int32(config.MinConns)
+	}
+	if config.MaxConnLifetime != 0 {
+		conf.MaxConnLifetime = config.MaxConnLifetime
+	}
+	if config.MaxConnIdleTime != 0 {
+		conf.MaxConnIdleTime = config.MaxConnIdleTime
+	}
+
+	if config.LogStatements {
+		conf.ConnConfig.Logger = NewLogAdapter(log.New())
+	}
+
+	return conf, nil
+}
+
+func (pgx *PGXDriver) createNode() error {
+	_, err := pgx.pool.Exec(
+		pgx.ctx,
+		createNodeStm,
+		pgx.nodeInfo.GenesisBlock, pgx.nodeInfo.NetworkID,
+		pgx.nodeInfo.ID, pgx.nodeInfo.ClientName,
+		pgx.nodeInfo.ChainID)
+	if err != nil {
+		return ErrUnableToSetNode(err)
+	}
+	pgx.nodeID = pgx.nodeInfo.ID
+	return nil
+}
+
+// QueryRow satisfies sql.Database
+func (pgx *PGXDriver) QueryRow(ctx context.Context, sql string, args ...interface{}) sql.ScannableRow {
+	return pgx.pool.QueryRow(ctx, sql, args...)
+}
+
+// Exec satisfies sql.Database
+func (pgx *PGXDriver) Exec(ctx context.Context, sql string, args ...interface{}) (sql.Result, error) {
+	res, err := pgx.pool.Exec(ctx, sql, args...)
+	return resultWrapper{ct: res}, err
+}
+
+// Select satisfies sql.Database
+func (pgx *PGXDriver) Select(ctx context.Context, dest interface{}, query string, args ...interface{}) error {
+	return pgxscan.Select(ctx, pgx.pool, dest, query, args...)
+}
+
+// Get satisfies sql.Database
+func (pgx *PGXDriver) Get(ctx context.Context, dest interface{}, query string, args ...interface{}) error {
+	return pgxscan.Get(ctx, pgx.pool, dest, query, args...)
+}
+
+// Begin satisfies sql.Database
+func (pgx *PGXDriver) Begin(ctx context.Context) (sql.Tx, error) {
+	tx, err := pgx.pool.Begin(ctx)
+	if err != nil {
+		return nil, err
+	}
+	return pgxTxWrapper{tx: tx}, nil
+}
+
+func (pgx *PGXDriver) Stats() metrics.DbStats {
+	stats := pgx.pool.Stat()
+	return pgxStatsWrapper{stats: stats}
+}
+
+// NodeID satisfies sql.Database
+func (pgx *PGXDriver) NodeID() string {
+	return pgx.nodeID
+}
+
+// Close satisfies sql.Database/io.Closer
+func (pgx *PGXDriver) Close() error {
+	pgx.pool.Close()
+	return nil
+}
+
+// Context satisfies sql.Database
+func (pgx *PGXDriver) Context() context.Context {
+	return pgx.ctx
+}
+
+// HasCopy satisfies sql.Database
+func (pgx *PGXDriver) UseCopyFrom() bool {
+	return pgx.config.CopyFrom
+}
+
+type resultWrapper struct {
+	ct pgconn.CommandTag
+}
+
+// RowsAffected satisfies sql.Result
+func (r resultWrapper) RowsAffected() (int64, error) {
+	return r.ct.RowsAffected(), nil
+}
+
+type pgxStatsWrapper struct {
+	stats *pgxpool.Stat
+}
+
+// MaxOpen satisfies metrics.DbStats
+func (s pgxStatsWrapper) MaxOpen() int64 {
+	return int64(s.stats.MaxConns())
+}
+
+// Open satisfies metrics.DbStats
+func (s pgxStatsWrapper) Open() int64 {
+	return int64(s.stats.TotalConns())
+}
+
+// InUse satisfies metrics.DbStats
+func (s pgxStatsWrapper) InUse() int64 {
+	return int64(s.stats.AcquiredConns())
+}
+
+// Idle satisfies metrics.DbStats
+func (s pgxStatsWrapper) Idle() int64 {
+	return int64(s.stats.IdleConns())
+}
+
+// WaitCount satisfies metrics.DbStats
+func (s pgxStatsWrapper) WaitCount() int64 {
+	return s.stats.EmptyAcquireCount()
+}
+
+// WaitDuration satisfies metrics.DbStats
+func (s pgxStatsWrapper) WaitDuration() time.Duration {
+	return s.stats.AcquireDuration()
+}
+
+// MaxIdleClosed satisfies metrics.DbStats
+func (s pgxStatsWrapper) MaxIdleClosed() int64 {
+	// this stat isn't supported by pgxpool, but we don't want to panic
+	return 0
+}
+
+// MaxLifetimeClosed satisfies metrics.DbStats
+func (s pgxStatsWrapper) MaxLifetimeClosed() int64 {
+	return s.stats.CanceledAcquireCount()
+}
+
+type pgxTxWrapper struct {
+	tx pgx.Tx
+}
+
+// QueryRow satisfies sql.Tx
+func (t pgxTxWrapper) QueryRow(ctx context.Context, sql string, args ...interface{}) sql.ScannableRow {
+	return t.tx.QueryRow(ctx, sql, args...)
+}
+
+// Exec satisfies sql.Tx
+func (t pgxTxWrapper) Exec(ctx context.Context, sql string, args ...interface{}) (sql.Result, error) {
+	res, err := t.tx.Exec(ctx, sql, args...)
+	return resultWrapper{ct: res}, err
+}
+
+// Commit satisfies sql.Tx
+func (t pgxTxWrapper) Commit(ctx context.Context) error {
+	return t.tx.Commit(ctx)
+}
+
+// Rollback satisfies sql.Tx
+func (t pgxTxWrapper) Rollback(ctx context.Context) error {
+	return t.tx.Rollback(ctx)
+}
+
+func (t pgxTxWrapper) CopyFrom(ctx context.Context, tableName []string, columnNames []string, rows [][]interface{}) (int64, error) {
+	return t.tx.CopyFrom(ctx, tableName, columnNames, pgx.CopyFromRows(rows))
+}

statediff/indexer/database/sql/postgres/pgx_test.go

@@ -0,0 +1,121 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres_test
+
+import (
+	"context"
+	"fmt"
+	"math/big"
+	"strings"
+	"testing"
+
+	"github.com/jackc/pgx/v4/pgxpool"
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/node"
+)
+
+var (
+	pgConfig, _ = postgres.MakeConfig(postgres.DefaultConfig)
+	ctx         = context.Background()
+)
+
+func expectContainsSubstring(t *testing.T, full string, sub string) {
+	if !strings.Contains(full, sub) {
+		t.Fatalf("Expected \"%v\" to contain substring \"%v\"\n", full, sub)
+	}
+}
+
+func TestPostgresPGX(t *testing.T) {
+	t.Run("connects to the sql", func(t *testing.T) {
+		dbPool, err := pgxpool.ConnectConfig(context.Background(), pgConfig)
+		if err != nil {
+			t.Fatalf("failed to connect to db with connection string: %s err: %v", pgConfig.ConnString(), err)
+		}
+		if dbPool == nil {
+			t.Fatal("DB pool is nil")
+		}
+		dbPool.Close()
+	})
+
+	t.Run("serializes big.Int to db", func(t *testing.T) {
+		// postgres driver doesn't support go big.Int type
+		// various casts in golang uint64, int64, overflow for
+		// transaction value (in wei) even though
+		// postgres numeric can handle an arbitrary
+		// sized int, so use string representation of big.Int
+		// and cast on insert
+
+		dbPool, err := pgxpool.ConnectConfig(context.Background(), pgConfig)
+		if err != nil {
+			t.Fatalf("failed to connect to db with connection string: %s err: %v", pgConfig.ConnString(), err)
+		}
+		defer dbPool.Close()
+
+		bi := new(big.Int)
+		bi.SetString("34940183920000000000", 10)
+		require.Equal(t, "34940183920000000000", bi.String())
+
+		defer dbPool.Exec(ctx, `DROP TABLE IF EXISTS example`)
+		_, err = dbPool.Exec(ctx, "CREATE TABLE example ( id INTEGER, data NUMERIC )")
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		sqlStatement := `
+			INSERT INTO example (id, data)
+			VALUES (1, cast($1 AS NUMERIC))`
+		_, err = dbPool.Exec(ctx, sqlStatement, bi.String())
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		var data string
+		err = dbPool.QueryRow(ctx, `SELECT cast(data AS TEXT) FROM example WHERE id = 1`).Scan(&data)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		require.Equal(t, data, bi.String())
+		actual := new(big.Int)
+		actual.SetString(data, 10)
+		require.Equal(t, bi, actual)
+	})
+
+	t.Run("throws error when can't connect to the database", func(t *testing.T) {
+		goodInfo := node.Info{GenesisBlock: "GENESIS", NetworkID: "1", ID: "x123", ClientName: "geth"}
+		_, err := postgres.NewPGXDriver(ctx, postgres.Config{}, goodInfo)
+		if err == nil {
+			t.Fatal("Expected an error")
+		}
+
+		expectContainsSubstring(t, err.Error(), postgres.DbConnectionFailedMsg)
+	})
+
+	t.Run("throws error when can't create node", func(t *testing.T) {
+		badHash := fmt.Sprintf("x %s", strings.Repeat("1", 100))
+		badInfo := node.Info{GenesisBlock: badHash, NetworkID: "1", ID: "x123", ClientName: "geth"}
+
+		_, err := postgres.NewPGXDriver(ctx, postgres.DefaultConfig, badInfo)
+		if err == nil {
+			t.Fatal("Expected an error")
+		}
+
+		expectContainsSubstring(t, err.Error(), postgres.SettingNodeFailedMsg)
+	})
+}

statediff/indexer/database/sql/postgres/postgres_suite_test.go

@@ -0,0 +1,33 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres_test
+
+import (
+	"fmt"
+	"os"
+
+	"github.com/ethereum/go-ethereum/log"
+)
+
+func init() {
+	if os.Getenv("MODE") != "statediff" {
+		fmt.Println("Skipping statediff test")
+		os.Exit(0)
+	}
+
+	log.Root().SetHandler(log.DiscardHandler())
+}

statediff/indexer/database/sql/postgres/sqlx.go

@@ -0,0 +1,210 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres
+
+import (
+	"context"
+	coresql "database/sql"
+	"errors"
+	"time"
+
+	"github.com/jmoiron/sqlx"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/node"
+)
+
+// SQLXDriver driver, implements sql.Driver
+type SQLXDriver struct {
+	ctx      context.Context
+	db       *sqlx.DB
+	nodeInfo node.Info
+	nodeID   string
+}
+
+// ConnectSQLX initializes and returns a SQLX connection pool for postgres
+func ConnectSQLX(ctx context.Context, config Config) (*sqlx.DB, error) {
+	db, err := sqlx.ConnectContext(ctx, "postgres", config.DbConnectionString())
+	if err != nil {
+		return nil, ErrDBConnectionFailed(err)
+	}
+	if config.MaxConns > 0 {
+		db.SetMaxOpenConns(config.MaxConns)
+	}
+	if config.MaxConnLifetime > 0 {
+		db.SetConnMaxLifetime(config.MaxConnLifetime)
+	}
+	db.SetMaxIdleConns(config.MaxIdle)
+	return db, nil
+}
+
+// NewSQLXDriver returns a new sqlx driver for Postgres
+// it initializes the connection pool and creates the node info table
+func NewSQLXDriver(ctx context.Context, config Config, node node.Info) (*SQLXDriver, error) {
+	db, err := ConnectSQLX(ctx, config)
+	if err != nil {
+		return nil, err
+	}
+	driver := &SQLXDriver{ctx: ctx, db: db, nodeInfo: node}
+	if err := driver.createNode(); err != nil {
+		return nil, err
+	}
+	return driver, nil
+}
+
+func (driver *SQLXDriver) createNode() error {
+	_, err := driver.db.Exec(
+		createNodeStm,
+		driver.nodeInfo.GenesisBlock,
+		driver.nodeInfo.NetworkID,
+		driver.nodeInfo.ID,
+		driver.nodeInfo.ClientName,
+		driver.nodeInfo.ChainID)
+	if err != nil {
+		return ErrUnableToSetNode(err)
+	}
+	driver.nodeID = driver.nodeInfo.ID
+	return nil
+}
+
+// QueryRow satisfies sql.Database
+func (driver *SQLXDriver) QueryRow(_ context.Context, sql string, args ...interface{}) sql.ScannableRow {
+	return driver.db.QueryRowx(sql, args...)
+}
+
+// Exec satisfies sql.Database
+func (driver *SQLXDriver) Exec(_ context.Context, sql string, args ...interface{}) (sql.Result, error) {
+	return driver.db.Exec(sql, args...)
+}
+
+// Select satisfies sql.Database
+func (driver *SQLXDriver) Select(_ context.Context, dest interface{}, query string, args ...interface{}) error {
+	return driver.db.Select(dest, query, args...)
+}
+
+// Get satisfies sql.Database
+func (driver *SQLXDriver) Get(_ context.Context, dest interface{}, query string, args ...interface{}) error {
+	return driver.db.Get(dest, query, args...)
+}
+
+// Begin satisfies sql.Database
+func (driver *SQLXDriver) Begin(_ context.Context) (sql.Tx, error) {
+	tx, err := driver.db.Beginx()
+	if err != nil {
+		return nil, err
+	}
+	return sqlxTxWrapper{tx: tx}, nil
+}
+
+func (driver *SQLXDriver) Stats() metrics.DbStats {
+	stats := driver.db.Stats()
+	return sqlxStatsWrapper{stats: stats}
+}
+
+// NodeID satisfies sql.Database
+func (driver *SQLXDriver) NodeID() string {
+	return driver.nodeID
+}
+
+// Close satisfies sql.Database/io.Closer
+func (driver *SQLXDriver) Close() error {
+	return driver.db.Close()
+}
+
+// Context satisfies sql.Database
+func (driver *SQLXDriver) Context() context.Context {
+	return driver.ctx
+}
+
+// HasCopy satisfies sql.Database
+func (driver *SQLXDriver) UseCopyFrom() bool {
+	// sqlx does not currently support COPY.
+	return false
+}
+
+type sqlxStatsWrapper struct {
+	stats coresql.DBStats
+}
+
+// MaxOpen satisfies metrics.DbStats
+func (s sqlxStatsWrapper) MaxOpen() int64 {
+	return int64(s.stats.MaxOpenConnections)
+}
+
+// Open satisfies metrics.DbStats
+func (s sqlxStatsWrapper) Open() int64 {
+	return int64(s.stats.OpenConnections)
+}
+
+// InUse satisfies metrics.DbStats
+func (s sqlxStatsWrapper) InUse() int64 {
+	return int64(s.stats.InUse)
+}
+
+// Idle satisfies metrics.DbStats
+func (s sqlxStatsWrapper) Idle() int64 {
+	return int64(s.stats.Idle)
+}
+
+// WaitCount satisfies metrics.DbStats
+func (s sqlxStatsWrapper) WaitCount() int64 {
+	return s.stats.WaitCount
+}
+
+// WaitDuration satisfies metrics.DbStats
+func (s sqlxStatsWrapper) WaitDuration() time.Duration {
+	return s.stats.WaitDuration
+}
+
+// MaxIdleClosed satisfies metrics.DbStats
+func (s sqlxStatsWrapper) MaxIdleClosed() int64 {
+	return s.stats.MaxIdleClosed
+}
+
+// MaxLifetimeClosed satisfies metrics.DbStats
+func (s sqlxStatsWrapper) MaxLifetimeClosed() int64 {
+	return s.stats.MaxLifetimeClosed
+}
+
+type sqlxTxWrapper struct {
+	tx *sqlx.Tx
+}
+
+// QueryRow satisfies sql.Tx
+func (t sqlxTxWrapper) QueryRow(ctx context.Context, sql string, args ...interface{}) sql.ScannableRow {
+	return t.tx.QueryRowx(sql, args...)
+}
+
+// Exec satisfies sql.Tx
+func (t sqlxTxWrapper) Exec(ctx context.Context, sql string, args ...interface{}) (sql.Result, error) {
+	return t.tx.Exec(sql, args...)
+}
+
+// Commit satisfies sql.Tx
+func (t sqlxTxWrapper) Commit(ctx context.Context) error {
+	return t.tx.Commit()
+}
+
+// Rollback satisfies sql.Tx
+func (t sqlxTxWrapper) Rollback(ctx context.Context) error {
+	return t.tx.Rollback()
+}
+
+func (t sqlxTxWrapper) CopyFrom(ctx context.Context, tableName []string, columnNames []string, rows [][]interface{}) (int64, error) {
+	return 0, errors.New("Unsupported Operation")
+}

statediff/indexer/database/sql/postgres/sqlx_test.go

@@ -0,0 +1,119 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres_test
+
+import (
+	"fmt"
+	"math/big"
+	"strings"
+	"testing"
+
+	"github.com/jmoiron/sqlx"
+	_ "github.com/lib/pq"
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/node"
+)
+
+func TestPostgresSQLX(t *testing.T) {
+	var sqlxdb *sqlx.DB
+
+	t.Run("connects to the database", func(t *testing.T) {
+		var err error
+		connStr := postgres.DefaultConfig.DbConnectionString()
+
+		sqlxdb, err = sqlx.Connect("postgres", connStr)
+		if err != nil {
+			t.Fatalf("failed to connect to db with connection string: %s err: %v", connStr, err)
+		}
+		if sqlxdb == nil {
+			t.Fatal("DB is nil")
+		}
+		err = sqlxdb.Close()
+		if err != nil {
+			t.Fatal(err)
+		}
+	})
+
+	t.Run("serializes big.Int to db", func(t *testing.T) {
+		// postgres driver doesn't support go big.Int type
+		// various casts in golang uint64, int64, overflow for
+		// transaction value (in wei) even though
+		// postgres numeric can handle an arbitrary
+		// sized int, so use string representation of big.Int
+		// and cast on insert
+
+		connStr := postgres.DefaultConfig.DbConnectionString()
+		db, err := sqlx.Connect("postgres", connStr)
+		if err != nil {
+			t.Fatal(err)
+		}
+		defer db.Close()
+
+		bi := new(big.Int)
+		bi.SetString("34940183920000000000", 10)
+		require.Equal(t, "34940183920000000000", bi.String())
+
+		defer db.Exec(`DROP TABLE IF EXISTS example`)
+		_, err = db.Exec("CREATE TABLE example ( id INTEGER, data NUMERIC )")
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		sqlStatement := `
+			INSERT INTO example (id, data)
+			VALUES (1, cast($1 AS NUMERIC))`
+		_, err = db.Exec(sqlStatement, bi.String())
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		var data string
+		err = db.QueryRow(`SELECT data FROM example WHERE id = 1`).Scan(&data)
+		if err != nil {
+			t.Fatal(err)
+		}
+
+		require.Equal(t, data, bi.String())
+		actual := new(big.Int)
+		actual.SetString(data, 10)
+		require.Equal(t, bi, actual)
+	})
+
+	t.Run("throws error when can't connect to the database", func(t *testing.T) {
+		goodInfo := node.Info{GenesisBlock: "GENESIS", NetworkID: "1", ID: "x123", ClientName: "geth"}
+		_, err := postgres.NewSQLXDriver(ctx, postgres.Config{}, goodInfo)
+		if err == nil {
+			t.Fatal("Expected an error")
+		}
+
+		expectContainsSubstring(t, err.Error(), postgres.DbConnectionFailedMsg)
+	})
+
+	t.Run("throws error when can't create node", func(t *testing.T) {
+		badHash := fmt.Sprintf("x %s", strings.Repeat("1", 100))
+		badInfo := node.Info{GenesisBlock: badHash, NetworkID: "1", ID: "x123", ClientName: "geth"}
+
+		_, err := postgres.NewSQLXDriver(ctx, postgres.DefaultConfig, badInfo)
+		if err == nil {
+			t.Fatal("Expected an error")
+		}
+
+		expectContainsSubstring(t, err.Error(), postgres.SettingNodeFailedMsg)
+	})
+}

statediff/indexer/database/sql/postgres/test_helpers.go

@@ -0,0 +1,44 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package postgres
+
+import (
+	"context"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/node"
+)
+
+// SetupSQLXDB is used to setup a sqlx db for tests
+func SetupSQLXDB() (sql.Database, error) {
+	conf := DefaultConfig
+	conf.MaxIdle = 0
+	driver, err := NewSQLXDriver(context.Background(), conf, node.Info{})
+	if err != nil {
+		return nil, err
+	}
+	return NewPostgresDB(driver, false), nil
+}
+
+// SetupPGXDB is used to setup a pgx db for tests
+func SetupPGXDB(config Config) (sql.Database, error) {
+	driver, err := NewPGXDriver(context.Background(), config, node.Info{})
+	if err != nil {
+		return nil, err
+	}
+	return NewPostgresDB(driver, false), nil
+}

statediff/indexer/database/sql/sqlx_indexer_legacy_test.go

@@ -0,0 +1,52 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package sql_test
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+)
+
+func setupLegacySQLXIndexer(t *testing.T) {
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+	ind, err = sql.NewStateDiffIndexer(context.Background(), test.LegacyConfig, db)
+	require.NoError(t, err)
+}
+
+func setupLegacySQLX(t *testing.T) {
+	setupLegacySQLXIndexer(t)
+	test.SetupLegacyTestData(t, ind)
+}
+
+func TestLegacySQLXIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs", func(t *testing.T) {
+		setupLegacySQLX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestLegacyIndexer(t, db)
+	})
+}

statediff/indexer/database/sql/sqlx_indexer_test.go

@@ -0,0 +1,227 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package sql_test
+
+import (
+	"context"
+	"math/big"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql"
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
+	"github.com/ethereum/go-ethereum/statediff/indexer/mocks"
+	"github.com/ethereum/go-ethereum/statediff/indexer/test"
+)
+
+func setupSQLXIndexer(t *testing.T) {
+	db, err = postgres.SetupSQLXDB()
+	if err != nil {
+		t.Fatal(err)
+	}
+	ind, err = sql.NewStateDiffIndexer(context.Background(), mocks.TestConfig, db)
+	require.NoError(t, err)
+}
+
+func setupSQLX(t *testing.T) {
+	setupSQLXIndexer(t)
+	test.SetupTestData(t, ind)
+}
+
+func setupSQLXNonCanonical(t *testing.T) {
+	setupSQLXIndexer(t)
+	test.SetupTestDataNonCanonical(t, ind)
+}
+
+// Test indexer for a canonical block
+func TestSQLXIndexer(t *testing.T) {
+	t.Run("Publish and index header IPLDs in a single tx", func(t *testing.T) {
+		setupSQLX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexHeaderIPLDs(t, db)
+	})
+
+	t.Run("Publish and index transaction IPLDs in a single tx", func(t *testing.T) {
+		setupSQLX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexTransactionIPLDs(t, db)
+	})
+
+	t.Run("Publish and index log IPLDs for multiple receipt of a specific block", func(t *testing.T) {
+		setupSQLX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexLogIPLDs(t, db)
+	})
+
+	t.Run("Publish and index receipt IPLDs in a single tx", func(t *testing.T) {
+		setupSQLX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexReceiptIPLDs(t, db)
+	})
+
+	t.Run("Publish and index state IPLDs in a single tx", func(t *testing.T) {
+		setupSQLX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexStateIPLDs(t, db)
+	})
+
+	t.Run("Publish and index storage IPLDs in a single tx", func(t *testing.T) {
+		setupSQLX(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexStorageIPLDs(t, db)
+	})
+}
+
+// Test indexer for a canonical + a non-canonical block at London height + a non-canonical block at London height + 1
+func TestSQLXIndexerNonCanonical(t *testing.T) {
+	t.Run("Publish and index header", func(t *testing.T) {
+		setupSQLXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexHeaderNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index transactions", func(t *testing.T) {
+		setupSQLXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexTransactionsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index receipts", func(t *testing.T) {
+		setupSQLXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexReceiptsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index logs", func(t *testing.T) {
+		setupSQLXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexLogsNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index state nodes", func(t *testing.T) {
+		setupSQLXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexStateNonCanonical(t, db)
+	})
+
+	t.Run("Publish and index storage nodes", func(t *testing.T) {
+		setupSQLXNonCanonical(t)
+		defer tearDown(t)
+		defer checkTxClosure(t, 0, 0, 0)
+
+		test.TestPublishAndIndexStorageNonCanonical(t, db)
+	})
+}
+
+func TestSQLXWatchAddressMethods(t *testing.T) {
+	setupSQLXIndexer(t)
+	defer tearDown(t)
+	defer checkTxClosure(t, 0, 0, 0)
+
+	t.Run("Load watched addresses (empty table)", func(t *testing.T) {
+		test.TestLoadEmptyWatchedAddresses(t, ind)
+	})
+
+	t.Run("Insert watched addresses", func(t *testing.T) {
+		args := mocks.GetInsertWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt1)))
+		require.NoError(t, err)
+
+		test.TestInsertWatchedAddresses(t, db)
+	})
+
+	t.Run("Insert watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetInsertAlreadyWatchedAddressesArgs()
+		err = ind.InsertWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		test.TestInsertAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses", func(t *testing.T) {
+		args := mocks.GetRemoveWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		test.TestRemoveWatchedAddresses(t, db)
+	})
+
+	t.Run("Remove watched addresses (some non-watched)", func(t *testing.T) {
+		args := mocks.GetRemoveNonWatchedAddressesArgs()
+		err = ind.RemoveWatchedAddresses(args)
+		require.NoError(t, err)
+
+		test.TestRemoveNonWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses", func(t *testing.T) {
+		args := mocks.GetSetWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt2)))
+		require.NoError(t, err)
+
+		test.TestSetWatchedAddresses(t, db)
+	})
+
+	t.Run("Set watched addresses (some already watched)", func(t *testing.T) {
+		args := mocks.GetSetAlreadyWatchedAddressesArgs()
+		err = ind.SetWatchedAddresses(args, big.NewInt(int64(mocks.WatchedAt3)))
+		require.NoError(t, err)
+
+		test.TestSetAlreadyWatchedAddresses(t, db)
+	})
+
+	t.Run("Load watched addresses", func(t *testing.T) {
+		test.TestLoadWatchedAddresses(t, ind)
+	})
+
+	t.Run("Clear watched addresses", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		test.TestClearWatchedAddresses(t, db)
+	})
+
+	t.Run("Clear watched addresses (empty table)", func(t *testing.T) {
+		err = ind.ClearWatchedAddresses()
+		require.NoError(t, err)
+
+		test.TestClearEmptyWatchedAddresses(t, db)
+	})
+}

statediff/indexer/database/sql/writer.go

@@ -0,0 +1,345 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package sql
+
+import (
+	"fmt"
+	"strconv"
+
+	"github.com/jackc/pgtype"
+	shopspring "github.com/jackc/pgtype/ext/shopspring-numeric"
+	"github.com/lib/pq"
+	"github.com/shopspring/decimal"
+
+	"github.com/ethereum/go-ethereum/statediff/indexer/database/metrics"
+	"github.com/ethereum/go-ethereum/statediff/indexer/models"
+)
+
+// Writer handles processing and writing of indexed IPLD objects to Postgres
+type Writer struct {
+	db Database
+}
+
+// NewWriter creates a new pointer to a Writer
+func NewWriter(db Database) *Writer {
+	return &Writer{
+		db: db,
+	}
+}
+
+// Close satisfies io.Closer
+func (w *Writer) Close() error {
+	return w.db.Close()
+}
+
+/*
+INSERT INTO eth.header_cids (block_number, block_hash, parent_hash, cid, td, node_ids, reward, state_root, tx_root, receipt_root, uncles_hash, bloom, timestamp, coinbase)
+VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11, $12, $13, $14)
+ON CONFLICT (block_hash, block_number) DO NOTHING
+*/
+func (w *Writer) upsertHeaderCID(tx Tx, header models.HeaderModel) error {
+	nodeIDs := pq.StringArray([]string{w.db.NodeID()})
+	_, err := tx.Exec(w.db.Context(), w.db.InsertHeaderStm(),
+		header.BlockNumber,
+		header.BlockHash,
+		header.ParentHash,
+		header.CID,
+		header.TotalDifficulty,
+		nodeIDs,
+		header.Reward,
+		header.StateRoot,
+		header.TxRoot,
+		header.RctRoot,
+		header.UnclesHash,
+		header.Bloom,
+		header.Timestamp,
+		header.Coinbase)
+	if err != nil {
+		return insertError{"eth.header_cids", err, w.db.InsertHeaderStm(), header}
+	}
+	metrics.IndexerMetrics.BlocksCounter.Inc(1)
+	return nil
+}
+
+/*
+INSERT INTO eth.uncle_cids (block_number, block_hash, header_id, parent_hash, cid, reward, index) VALUES ($1, $2, $3, $4, $5, $6, $7)
+ON CONFLICT (block_hash, block_number) DO NOTHING
+*/
+func (w *Writer) upsertUncleCID(tx Tx, uncle models.UncleModel) error {
+	_, err := tx.Exec(w.db.Context(), w.db.InsertUncleStm(),
+		uncle.BlockNumber,
+		uncle.BlockHash,
+		uncle.HeaderID,
+		uncle.ParentHash,
+		uncle.CID,
+		uncle.Reward,
+		uncle.Index)
+	if err != nil {
+		return insertError{"eth.uncle_cids", err, w.db.InsertUncleStm(), uncle}
+	}
+	return nil
+}
+
+/*
+INSERT INTO eth.transaction_cids (block_number, header_id, tx_hash, cid, dst, src, index, tx_type, value) VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9)
+ON CONFLICT (tx_hash, header_id, block_number) DO NOTHING
+*/
+func (w *Writer) upsertTransactionCID(tx Tx, transaction models.TxModel) error {
+	val := transaction.Value
+	if val == "" {
+		val = "0"
+	}
+	if w.useCopyForTx(tx) {
+		blockNum, err := strconv.ParseInt(transaction.BlockNumber, 10, 64)
+		if err != nil {
+			return insertError{"eth.transaction_cids", err, "COPY", transaction}
+		}
+
+		value, err := toNumeric(val)
+		if err != nil {
+			return insertError{"eth.transaction_cids", err, "COPY", transaction}
+		}
+
+		_, err = tx.CopyFrom(w.db.Context(), w.db.TxTableName(), w.db.TxColumnNames(),
+			toRows(toRow(blockNum, transaction.HeaderID, transaction.TxHash, transaction.CID, transaction.Dst,
+				transaction.Src, transaction.Index, int(transaction.Type), value)))
+		if err != nil {
+			return insertError{"eth.transaction_cids", err, "COPY", transaction}
+		}
+	} else {
+		_, err := tx.Exec(w.db.Context(), w.db.InsertTxStm(),
+			transaction.BlockNumber,
+			transaction.HeaderID,
+			transaction.TxHash,
+			transaction.CID,
+			transaction.Dst,
+			transaction.Src,
+			transaction.Index,
+			transaction.Type,
+			transaction.Value)
+		if err != nil {
+			return insertError{"eth.transaction_cids", err, w.db.InsertTxStm(), transaction}
+		}
+	}
+	metrics.IndexerMetrics.TransactionsCounter.Inc(1)
+	return nil
+}
+
+/*
+INSERT INTO eth.receipt_cids (block_number, header_id, tx_id, cid, contract, post_state, post_status) VALUES ($1, $2, $3, $4, $5, $6, $7, $8)
+ON CONFLICT (tx_id, header_id, block_number) DO NOTHING
+*/
+func (w *Writer) upsertReceiptCID(tx Tx, rct *models.ReceiptModel) error {
+	if w.useCopyForTx(tx) {
+		blockNum, err := strconv.ParseUint(rct.BlockNumber, 10, 64)
+		if err != nil {
+			return insertError{"eth.receipt_cids", err, "COPY", rct}
+		}
+
+		_, err = tx.CopyFrom(w.db.Context(), w.db.RctTableName(), w.db.RctColumnNames(),
+			toRows(toRow(blockNum, rct.HeaderID, rct.TxID, rct.CID, rct.Contract,
+				rct.PostState, int(rct.PostStatus))))
+		if err != nil {
+			return insertError{"eth.receipt_cids", err, "COPY", rct}
+		}
+	} else {
+		_, err := tx.Exec(w.db.Context(), w.db.InsertRctStm(),
+			rct.BlockNumber,
+			rct.HeaderID,
+			rct.TxID,
+			rct.CID,
+			rct.Contract,
+			rct.PostState,
+			rct.PostStatus)
+		if err != nil {
+			return insertError{"eth.receipt_cids", err, w.db.InsertRctStm(), *rct}
+		}
+	}
+	metrics.IndexerMetrics.ReceiptsCounter.Inc(1)
+	return nil
+}
+
+/*
+INSERT INTO eth.log_cids (block_number, header_id, cid, rct_id, address, index, topic0, topic1, topic2, topic3) VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)
+ON CONFLICT (rct_id, index, header_id, block_number) DO NOTHING
+*/
+func (w *Writer) upsertLogCID(tx Tx, logs []*models.LogsModel) error {
+	if w.useCopyForTx(tx) {
+		var rows [][]interface{}
+		for _, log := range logs {
+			blockNum, err := strconv.ParseUint(log.BlockNumber, 10, 64)
+			if err != nil {
+				return insertError{"eth.log_cids", err, "COPY", log}
+			}
+
+			rows = append(rows, toRow(blockNum, log.HeaderID, log.CID, log.ReceiptID,
+				log.Address, log.Index, log.Topic0, log.Topic1, log.Topic2, log.Topic3))
+		}
+		if nil != rows && len(rows) >= 0 {
+			_, err := tx.CopyFrom(w.db.Context(), w.db.LogTableName(), w.db.LogColumnNames(), rows)
+			if err != nil {
+				return insertError{"eth.log_cids", err, "COPY", rows}
+			}
+			metrics.IndexerMetrics.LogsCounter.Inc(int64(len(rows)))
+		}
+	} else {
+		for _, log := range logs {
+			_, err := tx.Exec(w.db.Context(), w.db.InsertLogStm(),
+				log.BlockNumber,
+				log.HeaderID,
+				log.CID,
+				log.ReceiptID,
+				log.Address,
+				log.Index,
+				log.Topic0,
+				log.Topic1,
+				log.Topic2,
+				log.Topic3)
+			if err != nil {
+				return insertError{"eth.log_cids", err, w.db.InsertLogStm(), *log}
+			}
+			metrics.IndexerMetrics.LogsCounter.Inc(1)
+		}
+	}
+	return nil
+}
+
+/*
+INSERT INTO eth.state_cids (block_number, header_id, state_leaf_key, cid, removed, diff, balance, nonce, code_hash, storage_root) VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10)
+ON CONFLICT (header_id, state_leaf_key, block_number) DO NOTHING
+*/
+func (w *Writer) upsertStateCID(tx Tx, stateNode models.StateNodeModel) error {
+	bal := stateNode.Balance
+	if stateNode.Removed {
+		bal = "0"
+	}
+
+	if w.useCopyForTx(tx) {
+		blockNum, err := strconv.ParseUint(stateNode.BlockNumber, 10, 64)
+		if err != nil {
+			return insertError{"eth.state_cids", err, "COPY", stateNode}
+		}
+
+		balance, err := toNumeric(bal)
+		if err != nil {
+			return insertError{"eth.state_cids", err, "COPY", stateNode}
+		}
+
+		_, err = tx.CopyFrom(w.db.Context(), w.db.StateTableName(), w.db.StateColumnNames(),
+			toRows(toRow(blockNum, stateNode.HeaderID, stateNode.StateKey, stateNode.CID,
+				true, balance, stateNode.Nonce, stateNode.CodeHash, stateNode.StorageRoot, stateNode.Removed)))
+		if err != nil {
+			return insertError{"eth.state_cids", err, "COPY", stateNode}
+		}
+	} else {
+		_, err := tx.Exec(w.db.Context(), w.db.InsertStateStm(),
+			stateNode.BlockNumber,
+			stateNode.HeaderID,
+			stateNode.StateKey,
+			stateNode.CID,
+			true,
+			bal,
+			stateNode.Nonce,
+			stateNode.CodeHash,
+			stateNode.StorageRoot,
+			stateNode.Removed,
+		)
+		if err != nil {
+			return insertError{"eth.state_cids", err, w.db.InsertStateStm(), stateNode}
+		}
+	}
+	return nil
+}
+
+/*
+INSERT INTO eth.storage_cids (block_number, header_id, state_leaf_key, storage_leaf_key, cid, removed, diff, val) VALUES ($1, $2, $3, $4, $5, $6, $7, $8)
+ON CONFLICT (header_id, state_leaf_key, storage_leaf_key, block_number) DO NOTHING
+*/
+func (w *Writer) upsertStorageCID(tx Tx, storageCID models.StorageNodeModel) error {
+	if w.useCopyForTx(tx) {
+		blockNum, err := strconv.ParseUint(storageCID.BlockNumber, 10, 64)
+		if err != nil {
+			return insertError{"eth.storage_cids", err, "COPY", storageCID}
+		}
+
+		_, err = tx.CopyFrom(w.db.Context(), w.db.StorageTableName(), w.db.StorageColumnNames(),
+			toRows(toRow(blockNum, storageCID.HeaderID, storageCID.StateKey, storageCID.StorageKey, storageCID.CID,
+				true, storageCID.Value, storageCID.Removed)))
+		if err != nil {
+			return insertError{"eth.storage_cids", err, "COPY", storageCID}
+		}
+	} else {
+		_, err := tx.Exec(w.db.Context(), w.db.InsertStorageStm(),
+			storageCID.BlockNumber,
+			storageCID.HeaderID,
+			storageCID.StateKey,
+			storageCID.StorageKey,
+			storageCID.CID,
+			true,
+			storageCID.Value,
+			storageCID.Removed,
+		)
+		if err != nil {
+			return insertError{"eth.storage_cids", err, w.db.InsertStorageStm(), storageCID}
+		}
+	}
+	return nil
+}
+
+func (w *Writer) useCopyForTx(tx Tx) bool {
+	// Using COPY instead of INSERT only makes much sense if also using a DelayedTx, so that operations
+	// can be collected over time and then all submitted within in a single TX.
+	if _, ok := tx.(*DelayedTx); ok {
+		return w.db.UseCopyFrom()
+	}
+	return false
+}
+
+// combine args into a row
+func toRow(args ...interface{}) []interface{} {
+	var row []interface{}
+	row = append(row, args...)
+	return row
+}
+
+func toNumeric(value string) (*shopspring.Numeric, error) {
+	decimalValue, err := decimal.NewFromString(value)
+	if nil != err {
+		return nil, err
+	}
+
+	return &shopspring.Numeric{Decimal: decimalValue, Status: pgtype.Present}, nil
+}
+
+// combine row (or rows) into a slice of rows for CopyFrom
+func toRows(rows ...[]interface{}) [][]interface{} {
+	return rows
+}
+
+type insertError struct {
+	table     string
+	err       error
+	stmt      string
+	arguments interface{}
+}
+
+var _ error = insertError{}
+
+func (dbe insertError) Error() string {
+	return fmt.Sprintf("error inserting %s entry: %v\r\nstatement: %s\r\narguments: %+v",
+		dbe.table, dbe.err, dbe.stmt, dbe.arguments)
+}

statediff/indexer/interfaces/interfaces.go

@@ -0,0 +1,55 @@
+// VulcanizeDB
+// Copyright © 2021 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package interfaces
+
+import (
+	"io"
+	"math/big"
+	"time"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/statediff/indexer/shared"
+	sdtypes "github.com/ethereum/go-ethereum/statediff/types"
+)
+
+// StateDiffIndexer interface required to index statediff data
+type StateDiffIndexer interface {
+	PushBlock(block *types.Block, receipts types.Receipts, totalDifficulty *big.Int) (Batch, error)
+	PushStateNode(tx Batch, stateNode sdtypes.StateLeafNode, headerID string) error
+	PushIPLD(tx Batch, ipld sdtypes.IPLD) error
+	ReportDBMetrics(delay time.Duration, quit <-chan bool)
+
+	// Methods used by WatchAddress API/functionality
+	LoadWatchedAddresses() ([]common.Address, error)
+	InsertWatchedAddresses(addresses []sdtypes.WatchAddressArg, currentBlock *big.Int) error
+	RemoveWatchedAddresses(addresses []sdtypes.WatchAddressArg) error
+	SetWatchedAddresses(args []sdtypes.WatchAddressArg, currentBlockNumber *big.Int) error
+	ClearWatchedAddresses() error
+
+	io.Closer
+}
+
+// Batch required for indexing data atomically
+type Batch interface {
+	Submit(err error) error
+}
+
+// Config used to configure different underlying implementations
+type Config interface {
+	Type() shared.DBType
+}

statediff/indexer/ipld/eth_header.go

@@ -0,0 +1,60 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package ipld
+
+import (
+	"github.com/ipfs/go-cid"
+	mh "github.com/multiformats/go-multihash"
+
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/rlp"
+)
+
+// EthHeader (eth-block, codec 0x90), represents an ethereum block header
+type EthHeader struct {
+	cid     cid.Cid
+	rawdata []byte
+}
+
+// Static (compile time) check that EthHeader satisfies the node.Node interface.
+var _ IPLD = (*EthHeader)(nil)
+
+// NewEthHeader converts a *types.Header into an EthHeader IPLD node
+func NewEthHeader(header *types.Header) (*EthHeader, error) {
+	headerRLP, err := rlp.EncodeToBytes(header)
+	if err != nil {
+		return nil, err
+	}
+	c, err := RawdataToCid(MEthHeader, headerRLP, mh.KECCAK_256)
+	if err != nil {
+		return nil, err
+	}
+	return &EthHeader{
+		cid:     c,
+		rawdata: headerRLP,
+	}, nil
+}
+
+// RawData returns the binary of the RLP encode of the block header.
+func (b *EthHeader) RawData() []byte {
+	return b.rawdata
+}
+
+// Cid returns the cid of the block header.
+func (b *EthHeader) Cid() cid.Cid {
+	return b.cid
+}

statediff/indexer/ipld/eth_log.go

@@ -0,0 +1,44 @@
+package ipld
+
+import (
+	"github.com/ipfs/go-cid"
+	mh "github.com/multiformats/go-multihash"
+
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/rlp"
+)
+
+// EthLog (eth-log, codec 0x9a), represents an ethereum block header
+type EthLog struct {
+	rawData []byte
+	cid     cid.Cid
+}
+
+// Static (compile time) check that EthLog satisfies the node.Node interface.
+var _ IPLD = (*EthLog)(nil)
+
+// NewLog create a new EthLog IPLD node
+func NewLog(log *types.Log) (*EthLog, error) {
+	logRaw, err := rlp.EncodeToBytes(log)
+	if err != nil {
+		return nil, err
+	}
+	c, err := RawdataToCid(MEthLog, logRaw, mh.KECCAK_256)
+	if err != nil {
+		return nil, err
+	}
+	return &EthLog{
+		cid:     c,
+		rawData: logRaw,
+	}, nil
+}
+
+// RawData returns the binary of the RLP encode of the log.
+func (l *EthLog) RawData() []byte {
+	return l.rawData
+}
+
+// Cid returns the cid of the receipt log.
+func (l *EthLog) Cid() cid.Cid {
+	return l.cid
+}

statediff/indexer/ipld/eth_parser.go

@@ -0,0 +1,94 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package ipld
+
+import (
+	"github.com/ethereum/go-ethereum/core/types"
+)
+
+// FromBlockAndReceipts takes a block and processes it
+// to return it a set of IPLD nodes for further processing.
+func FromBlockAndReceipts(block *types.Block, receipts []*types.Receipt) (*EthHeader, []*EthTx, []*EthReceipt, [][]*EthLog, error) {
+	// Process the header
+	headerNode, err := NewEthHeader(block.Header())
+	if err != nil {
+		return nil, nil, nil, nil, err
+	}
+
+	// Process the txs
+	txNodes, err := processTransactions(block.Transactions())
+	if err != nil {
+		return nil, nil, nil, nil, err
+	}
+
+	// Process the receipts and logs
+	rctNodes, logNodes, err := processReceiptsAndLogs(receipts)
+
+	return headerNode, txNodes, rctNodes, logNodes, err
+}
+
+// processTransactions will take the found transactions in a parsed block body
+// to return IPLD node slices for eth-tx
+func processTransactions(txs []*types.Transaction) ([]*EthTx, error) {
+	var ethTxNodes []*EthTx
+	for _, tx := range txs {
+		ethTx, err := NewEthTx(tx)
+		if err != nil {
+			return nil, err
+		}
+		ethTxNodes = append(ethTxNodes, ethTx)
+	}
+
+	return ethTxNodes, nil
+}
+
+// processReceiptsAndLogs will take in receipts
+// to return IPLD node slices for eth-rct and eth-log
+func processReceiptsAndLogs(rcts []*types.Receipt) ([]*EthReceipt, [][]*EthLog, error) {
+	// Pre allocating memory.
+	ethRctNodes := make([]*EthReceipt, len(rcts))
+	ethLogNodes := make([][]*EthLog, len(rcts))
+
+	for idx, rct := range rcts {
+		logNodes, err := processLogs(rct.Logs)
+		if err != nil {
+			return nil, nil, err
+		}
+
+		ethRct, err := NewReceipt(rct)
+		if err != nil {
+			return nil, nil, err
+		}
+
+		ethRctNodes[idx] = ethRct
+		ethLogNodes[idx] = logNodes
+	}
+
+	return ethRctNodes, ethLogNodes, nil
+}
+
+func processLogs(logs []*types.Log) ([]*EthLog, error) {
+	logNodes := make([]*EthLog, len(logs))
+	for idx, log := range logs {
+		logNode, err := NewLog(log)
+		if err != nil {
+			return nil, err
+		}
+		logNodes[idx] = logNode
+	}
+	return logNodes, nil
+}

statediff/indexer/ipld/eth_parser_test.go

@@ -0,0 +1,126 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package ipld
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/ethereum/go-ethereum/common"
+	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/rlp"
+)
+
+type kind string
+
+const (
+	legacy  kind = "legacy"
+	eip1559 kind = "eip2930"
+)
+
+var blockFileNames = []string{
+	"eth-block-12252078",
+	"eth-block-12365585",
+	"eth-block-12365586",
+}
+
+var receiptsFileNames = []string{
+	"eth-receipts-12252078",
+	"eth-receipts-12365585",
+	"eth-receipts-12365586",
+}
+
+var kinds = []kind{
+	eip1559,
+	eip1559,
+	legacy,
+}
+
+type testCase struct {
+	kind     kind
+	block    *types.Block
+	receipts types.Receipts
+}
+
+func loadBlockData(t *testing.T) []testCase {
+	fileDir := "./eip2930_test_data"
+	testCases := make([]testCase, len(blockFileNames))
+	for i, blockFileName := range blockFileNames {
+		blockRLP, err := os.ReadFile(filepath.Join(fileDir, blockFileName))
+		if err != nil {
+			t.Fatalf("failed to load blockRLP from file, err %v", err)
+		}
+		block := new(types.Block)
+		if err := rlp.DecodeBytes(blockRLP, block); err != nil {
+			t.Fatalf("failed to decode blockRLP, err %v", err)
+		}
+		receiptsFileName := receiptsFileNames[i]
+		receiptsRLP, err := os.ReadFile(filepath.Join(fileDir, receiptsFileName))
+		if err != nil {
+			t.Fatalf("failed to load receiptsRLP from file, err %s", err)
+		}
+		receipts := make(types.Receipts, 0)
+		if err := rlp.DecodeBytes(receiptsRLP, &receipts); err != nil {
+			t.Fatalf("failed to decode receiptsRLP, err %s", err)
+		}
+		testCases[i] = testCase{
+			block:    block,
+			receipts: receipts,
+			kind:     kinds[i],
+		}
+	}
+	return testCases
+}
+
+func TestFromBlockAndReceipts(t *testing.T) {
+	testCases := loadBlockData(t)
+	for _, tc := range testCases {
+		_, _, _, _, err := FromBlockAndReceipts(tc.block, tc.receipts)
+		if err != nil {
+			t.Fatalf("error generating IPLDs from block and receipts, err %v, kind %s, block hash %s", err, tc.kind, tc.block.Hash())
+		}
+	}
+}
+
+func TestProcessLogs(t *testing.T) {
+	logs := []*types.Log{mockLog1, mockLog2}
+	nodes, err := processLogs(logs)
+	require.NoError(t, err)
+	require.GreaterOrEqual(t, len(nodes), len(logs))
+}
+
+var (
+	address        = common.HexToAddress("0xaE9BEa628c4Ce503DcFD7E305CaB4e29E7476592")
+	anotherAddress = common.HexToAddress("0xaE9BEa628c4Ce503DcFD7E305CaB4e29E7476593")
+	mockTopic11    = common.HexToHash("0x04")
+	mockTopic12    = common.HexToHash("0x06")
+	mockTopic21    = common.HexToHash("0x05")
+	mockTopic22    = common.HexToHash("0x07")
+	mockLog1       = &types.Log{
+		Address: address,
+		Topics:  []common.Hash{mockTopic11, mockTopic12},
+		Data:    []byte{},
+	}
+	mockLog2 = &types.Log{
+		Address: anotherAddress,
+		Topics:  []common.Hash{mockTopic21, mockTopic22},
+		Data:    []byte{},
+	}
+)

statediff/indexer/ipld/eth_receipt.go

@@ -0,0 +1,58 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package ipld
+
+import (
+	"github.com/ipfs/go-cid"
+	mh "github.com/multiformats/go-multihash"
+
+	"github.com/ethereum/go-ethereum/core/types"
+)
+
+type EthReceipt struct {
+	rawdata []byte
+	cid     cid.Cid
+}
+
+// Static (compile time) check that EthReceipt satisfies the node.Node interface.
+var _ IPLD = (*EthReceipt)(nil)
+
+// NewReceipt converts a types.ReceiptForStorage to an EthReceipt IPLD node
+func NewReceipt(receipt *types.Receipt) (*EthReceipt, error) {
+	rctRaw, err := receipt.MarshalBinary()
+	if err != nil {
+		return nil, err
+	}
+	c, err := RawdataToCid(MEthTxReceipt, rctRaw, mh.KECCAK_256)
+	if err != nil {
+		return nil, err
+	}
+	return &EthReceipt{
+		cid:     c,
+		rawdata: rctRaw,
+	}, nil
+}
+
+// RawData returns the binary of the RLP encode of the receipt.
+func (r *EthReceipt) RawData() []byte {
+	return r.rawdata
+}
+
+// Cid returns the cid of the receipt.
+func (r *EthReceipt) Cid() cid.Cid {
+	return r.cid
+}

statediff/indexer/ipld/eth_tx.go

@@ -0,0 +1,59 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package ipld
+
+import (
+	"github.com/ipfs/go-cid"
+	mh "github.com/multiformats/go-multihash"
+
+	"github.com/ethereum/go-ethereum/core/types"
+)
+
+// EthTx (eth-tx codec 0x93) represents an ethereum transaction
+type EthTx struct {
+	cid     cid.Cid
+	rawdata []byte
+}
+
+// Static (compile time) check that EthTx satisfies the node.Node interface.
+var _ IPLD = (*EthTx)(nil)
+
+// NewEthTx converts a *types.Transaction to an EthTx IPLD node
+func NewEthTx(tx *types.Transaction) (*EthTx, error) {
+	txRaw, err := tx.MarshalBinary()
+	if err != nil {
+		return nil, err
+	}
+	c, err := RawdataToCid(MEthTx, txRaw, mh.KECCAK_256)
+	if err != nil {
+		return nil, err
+	}
+	return &EthTx{
+		cid:     c,
+		rawdata: txRaw,
+	}, nil
+}
+
+// RawData returns the binary of the RLP encode of the transaction.
+func (t *EthTx) RawData() []byte {
+	return t.rawdata
+}
+
+// Cid returns the cid of the transaction.
+func (t *EthTx) Cid() cid.Cid {
+	return t.cid
+}

statediff/indexer/ipld/interface.go

@@ -0,0 +1,8 @@
+package ipld
+
+import "github.com/ipfs/go-cid"
+
+type IPLD interface {
+	Cid() cid.Cid
+	RawData() []byte
+}

statediff/indexer/ipld/shared.go

@@ -0,0 +1,66 @@
+// VulcanizeDB
+// Copyright © 2019 Vulcanize
+
+// This program is free software: you can redistribute it and/or modify
+// it under the terms of the GNU Affero General Public License as published by
+// the Free Software Foundation, either version 3 of the License, or
+// (at your option) any later version.
+
+// This program is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+// GNU Affero General Public License for more details.
+
+// You should have received a copy of the GNU Affero General Public License
+// along with this program.  If not, see <http://www.gnu.org/licenses/>.
+
+package ipld
+
+import (
+	"github.com/ipfs/go-cid"
+	mh "github.com/multiformats/go-multihash"
+)
+
+// IPLD Codecs for Ethereum
+// See the authoritative document:
+// https://github.com/multiformats/multicodec/blob/master/table.csv
+const (
+	RawBinary           = 0x55
+	MEthHeader          = 0x90
+	MEthHeaderList      = 0x91
+	MEthTxTrie          = 0x92
+	MEthTx              = 0x93
+	MEthTxReceiptTrie   = 0x94
+	MEthTxReceipt       = 0x95
+	MEthStateTrie       = 0x96
+	MEthAccountSnapshot = 0x97
+	MEthStorageTrie     = 0x98
+	MEthLogTrie         = 0x99
+	MEthLog             = 0x9a
+)
+
+// RawdataToCid takes the desired codec and a slice of bytes
+// and returns the proper cid of the object.
+func RawdataToCid(codec uint64, rawdata []byte, multiHash uint64) (cid.Cid, error) {
+	c, err := cid.Prefix{
+		Codec:    codec,
+		Version:  1,
+		MhType:   multiHash,
+		MhLength: -1,
+	}.Sum(rawdata)
+	if err != nil {
+		return cid.Cid{}, err
+	}
+	return c, nil
+}
+
+// Keccak256ToCid takes a keccak256 hash and returns its cid based on
+// the codec given.
+func Keccak256ToCid(codec uint64, h []byte) cid.Cid {
+	buf, err := mh.Encode(h, mh.KECCAK_256)
+	if err != nil {
+		panic(err)
+	}
+
+	return cid.NewCidV1(codec, buf)
+}