updated dependencies for statediffing geth 1.10.23 (#21)

* updated dependencies for statediffing geth 1.10.23

* another ref to GenesisBlockForTesting

.github/workflows/issues-notion-sync.yml

@@ -1,29 +0,0 @@
-name: Notion Sync
-
-on:
-  workflow_dispatch:
-  issues:
-    types:
-      [
-        opened,
-        edited,
-        labeled,
-        unlabeled,
-        assigned,
-        unassigned,
-        milestoned,
-        demilestoned,
-        reopened,
-        closed,
-      ]
-
-jobs:
-  notion_job:
-    runs-on: ubuntu-latest
-    name: Add GitHub Issues to Notion
-    steps:
-      - name: Add GitHub Issues to Notion
-        uses: vulcanize/notion-github-action@v1.2.4-issueid
-        with:
-          notion-token: ${{ secrets.NOTION_TOKEN }}
-          notion-db: ${{ secrets.NOTION_DATABASE }}

.github/workflows/tests.yml

@@ -3,8 +3,9 @@ on:
   workflow_call:
 
 env:
-  STACK_ORCHESTRATOR_REF: "main"
+  STACK_ORCHESTRATOR_REF: "f2fd766f5400fcb9eb47b50675d2e3b1f2753702"
-  GO_ETHEREUM_REF: "v1.10.18-statediff-v3"
+  GO_ETHEREUM_REF: "v1.10.19-statediff-4.1.0-alpha" # Use the tag, we are going to download the bin not build it.
+  IPLD_ETH_DB_REF: "b59505eab252670c622b42ce60621e9747fb64f9"
 
 jobs:
   integrationtest:
@@ -16,43 +17,50 @@ jobs:
     steps:
       - name: Create GOPATH
         run: mkdir -p /tmp/go
+
       - uses: actions/setup-go@v3
         with:
-          go-version: ">=1.18.0"
+          go-version: "1.18.0"
           check-latest: true
+
       - uses: actions/checkout@v2
         with:
           path: "./ipld-eth-db-validator"
+
       - uses: actions/checkout@v2
         with:
           ref: ${{ env.STACK_ORCHESTRATOR_REF }}
           path: "./stack-orchestrator/"
           repository: vulcanize/stack-orchestrator
+
       - uses: actions/checkout@v2
         with:
-          ref: ${{ env.GO_ETHEREUM_REF }}
+          ref: ${{ env.IPLD_ETH_DB_REF }}
-          repository: vulcanize/go-ethereum
+          repository: vulcanize/ipld-eth-db
-          path: "./go-ethereum/"
+          path: "./ipld-eth-db/"
+
       - name: Create config file
         run: |
-          echo vulcanize_go_ethereum=$GITHUB_WORKSPACE/go-ethereum/ > ./config.sh
           echo vulcanize_test_contract=$GITHUB_WORKSPACE/ipld-eth-db-validator/test/contract >> ./config.sh
+          echo vulcanize_ipld_eth_db=$GITHUB_WORKSPACE/ipld-eth-db/ >> ./config.sh
+          echo genesis_file_path=start-up-files/go-ethereum/genesis.json >> ./config.sh
           echo db_write=$DB_WRITE >> ./config.sh
           cat ./config.sh
-      - name: Build geth
+
+      - name: Download Geth
         run: |
           cd $GITHUB_WORKSPACE/stack-orchestrator/helper-scripts
-          ./compile-geth.sh \
+          wget https://github.com/vulcanize/go-ethereum/releases/download/${{env.GO_ETHEREUM_REF}}/geth-linux-amd64
-          -p "$GITHUB_WORKSPACE/config.sh" \
+
-          -e docker
       - name: Run docker compose
         run: |
           docker-compose  \
-          -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/latest/docker-compose-db.yml" \
+          -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-db-sharding.yml" \
           -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-go-ethereum.yml" \
           -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/local/docker-compose-contract.yml" \
           --env-file "$GITHUB_WORKSPACE/config.sh" \
           up -d --build
+
       - name: Run integration test.
         run: |
           cd $GITHUB_WORKSPACE/ipld-eth-db-validator
@@ -60,31 +68,24 @@ jobs:
 
   unittest:
     name: Run unit tests
-    env:
-      GOPATH: /tmp/go
-      DB_WRITE: true
     runs-on: ubuntu-latest
     steps:
       - name: Create GOPATH
         run: mkdir -p /tmp/go
+
       - uses: actions/setup-go@v3
         with:
-          go-version: ">=1.18.0"
+          go-version: "1.18.0"
           check-latest: true
-      - uses: actions/checkout@v2
+
-        with:
+      - name: Checkout code
-          path: "./ipld-eth-db-validator"
+        uses: actions/checkout@v2
-      - uses: actions/checkout@v2
+
-        with:
+      - name: Spin up database
-          ref: ${{ env.STACK_ORCHESTRATOR_REF }}
-          path: "./stack-orchestrator/"
-          repository: vulcanize/stack-orchestrator
-      - name: Run docker compose
         run: |
-          docker-compose  \
+          docker-compose up -d
-          -f "$GITHUB_WORKSPACE/stack-orchestrator/docker/latest/docker-compose-db.yml" \
+
-          up -d --build
+      - name: Run unit tests
-      - name: Run unit test.
         run: |
-          cd $GITHUB_WORKSPACE/ipld-eth-db-validator
+          sleep 30
           PGPASSWORD=password DATABASE_USER=vdbm DATABASE_PORT=8077 DATABASE_PASSWORD=password DATABASE_HOSTNAME=127.0.0.1 DATABASE_NAME=vulcanize_testing make test

.gitignore

@@ -0,0 +1,3 @@
+ipld-eth-db-validator
+.vscode
+.idea

README.md

@@ -1,75 +1,124 @@
-- [Validator-README](#validator-readme)
+# ipld-eth-db-validator
-- [Overview](#overview)
-- [Intention for the Validator](#intention-for-the-validator)
-  - [Edge Cases](#edge-cases)
-- [Instructions for Testing](#instructions-for-testing)
-- [Code Overview](#code-overview)
-- [Known Bugs](#known-bugs)
-- [Tests on 03/03/22](#tests-on-03-03-22)
-  - [Set Up](#set-up)
-  - [Testing Failures](#testing-failures)
 
-<small><i><a href='http://ecotrust-canada.github.io/markdown-toc/'>Table of contents generated with markdown-toc</a></i></small>
+> `ipld-eth-db-validator` performs validation checks on indexed Ethereum IPLD objects in a Postgres database:
+> * Attempt to apply transactions in each block and validate resultant block hash
+> * Check referential integrity between IPLD blocks and index tables
 
-# Overview
+## Setup
 
-This repository contains the validator. The purpose of the validator is to ensure that the data in the Core Postgres database match the data on the blockchain.
+Build the binary:
 
-# Intention for the Validator
+```bash
+make build
+```
 
-The perfect scenario for the validator is as follows:
+## Configuration
 
-1. The validator will have the capacity to perform historical checks for the Core Postgres database. Users can contain these historical checks to specified configurations (block range).
+An example config file:
-2. The validator will validate a certain number of trailing blocks, `t`, trailing the head, `n`. Therefore the validator will constantly perform real-time validation starting at `n` and ending at `n - t`.
-3. The validator validates the IPLD blocks in the Core Database; it will update the core database to indicate that the validator validated it.
 
-## Edge Cases
+```toml
+[database]
+  # db credentials
+  name     = "vulcanize_public" # DATABASE_NAME
+  hostname = "localhost"        # DATABASE_HOSTNAME
+  port     = 5432               # DATABASE_PORT
+  user     = "vdbm"             # DATABASE_USER
+  password = "..."              # DATABASE_PASSWORD
 
-We must consider the following edge cases for the validator.
+[validate]
+  # block height to initiate database validation at
+  blockHeight = 1      # VALIDATE_BLOCK_HEIGHT  (default: 1)
+  # number of blocks to trail behind the head
+  trail  = 16         # VALIDATE_TRAIL  (default: 16)
+  # sleep interval after validator has caught up to (head-trail) height (in sec)
+  sleepInterval = 10  # VALIDATE_SLEEP_INTERVAL (default: 10)
 
-- There are three different data types that the validator must account for.
+  # whether to perform a statediffing call on a missing block
+  stateDiffMissingBlock = true # (default: false)
+  # statediffing call timeout period (in sec)
+  stateDiffTimeout = 240 # (default: 240)
 
-# Instructions for Testing
+[ethereum]
+  # node info
+  # path to json chain config (optional)
+  chainConfig = ""            # ETH_CHAIN_CONFIG
+  # eth chain id for config (overridden by chainConfig)
+  chainID = "1"               # ETH_CHAIN_ID (default: 1)
+  # http RPC endpoint URL for a statediffing node
+  httpPath = "localhost:8545" # ETH_HTTP_PATH
 
-Follow steps in [test/README.md](./test/README.md)
+[prom]
+  # prometheus metrics
+  metrics = true        # PROM_METRICS    (default: false)
+  http = true           # PROM_HTTP       (default: false)
+  httpAddr = "0.0.0.0"  # PROM_HTTP_ADDR  (default: 127.0.0.1)
+  httpPort = "9001"     # PROM_HTTP_PORT  (default: 9001)
+  dbStats = true        # PROM_DB_STATS   (default: false)
 
-# Code Overview
+[log]
+  # log level (trace, debug, info, warn, error, fatal, panic)
+  level = "info"  # LOG_LEVEL (default: info)
+  # file path for logging, leave unset to log to stdout
+  file  = ""      # LOG_FILE_PATH
+```
 
-This section will provide some insight into specific files and their purpose.
 
-- `validator_test/chain_maker.go` - This file contains the code for creating a “test” blockchain.
+* The validation process trails behind the latest block number in the database by config parameter `validate.trail`.
-- `validator_test/validator_test.go` - This file contains testing to validate the validator. It leverages `chain_maker.go` to create a blockchain to validate.
-- `pkg/validator/validator.go` - This file contains most of the core logic for the validator.
 
-# Known Bugs
+* If the validator has caught up to (head-trail) height, it waits for a configured time interval (`validate.sleepInterval`) before again querying the database.
 
-1. The validator is improperly handling missing headers from the database.
+* If the validator encounters a missing block (gap) in the database, it makes a `writeStateDiffAt` call to the configured statediffing endpoint (`ethereum.httpPath`) if `validate.stateDiffMissingBlock` is set to `true`. Here it is assumed that the statediffing node pointed to is writing out to the database.
-   1. Scenario
-      1. The IPLD blocks from the mock blockchain are inserted into the Postgres Data.
-      2. The validator runs, and all tests pass.
-      3. Users manually remove the last few rows from the database.
-      4. The validator runs, and all tests pass - This behavior is neither expected nor wanted.
 
-# Tests on 03/03/22
+### Local Setup
 
-The tests highlighted below were conducted to validate the initial behavior of the validator.
+* Create a chain config file `chain.json` according to chain config in genesis json file used by local geth.
 
-## Set Up
+  Example:
 
-Below are the steps utilized to set up the test environment.
+  ```json
+  {
+    "chainId": 41337,
+    "homesteadBlock": 0,
+    "eip150Block": 0,
+    "eip150Hash": "0x0000000000000000000000000000000000000000000000000000000000000000",
+    "eip155Block": 0,
+    "eip158Block": 0,
+    "byzantiumBlock": 0,
+    "constantinopleBlock": 0,
+    "petersburgBlock": 0,
+    "istanbulBlock": 0,
+    "clique": {
+      "period": 5,
+      "epoch": 30000
+    }
+  }
+  ```
 
-1. Run the `scripts/run_integration_test.sh` script.
+  Provide the path to the above file in the config.
-   1. First comment outline 130 to 133 from `validator_test/validator_test.go`
-2. Once the code has completed running, comment out lines 55 to 126, 38 to 40, and 42 to 44.
-   1. Make the following change `db, err = setupDB() --> db, _ = setupDB()`
-3. Run the following command: `ginkgo -r validator_test/ -v`
-   1. All tests should pass
 
-## Testing Failures
+## Usage
 
-Once we had populated the database, we tested for failures.
+* Create / update the config file (refer to example config above).
 
-1. Removing a Transaction from `transaction_cids` - If we removed a transaction from the database and ran the test, the test would fail. **This is the expected behavior.**
+* Run validator:
-2. Removing Headers from `eth.header_cids`
+
-   1. If we removed a header block sandwiched between two header blocks, the test would fail (For example, we removed the entry for block 4, and the block range is 1-10). **This is the expected behavior.**
+  ```bash
-   2. If we removed the tail block(s) from the table, the test would pass (For example, we remove the entry for blocks 8, 9, 10, and the block range is 1-10). **This is _not_ the expected behavior.**
+  ./ipld-eth-db-validator stateValidator --config=<config path>
+  ```
+
+  Example:
+
+  ```bash
+  ./ipld-eth-db-validator stateValidator --config=environments/example.toml
+  ```
+
+## Monitoring
+
+* Enable metrics using config parameters `prom.metrics` and `prom.http`.
+* `ipld-eth-db-validator` exposes following prometheus metrics at `/metrics` endpoint:
+  * `last_validated_block`: Last validated block number.
+  * DB stats if `prom.dbStats` set to `true`.
+
+## Tests
+
+* Follow [Test Instructions](./test/README.md) to run unit and integration tests locally.

cmd/env.go

@@ -0,0 +1,84 @@
+// 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 cmd
+
+import (
+	"github.com/spf13/viper"
+)
+
+const (
+	LOG_LEVEL     = "LOG_LEVEL"
+	LOG_FILE_PATH = "LOG_FILE_PATH"
+
+	PROM_METRICS   = "PROM_METRICS"
+	PROM_HTTP      = "PROM_HTTP"
+	PROM_HTTP_ADDR = "PROM_HTTP_ADDR"
+	PROM_HTTP_PORT = "PROM_HTTP_PORT"
+	PROM_DB_STATS  = "PROM_DB_STATS"
+
+	DATABASE_NAME     = "DATABASE_NAME"
+	DATABASE_HOSTNAME = "DATABASE_HOSTNAME"
+	DATABASE_PORT     = "DATABASE_PORT"
+	DATABASE_USER     = "DATABASE_USER"
+	DATABASE_PASSWORD = "DATABASE_PASSWORD"
+
+	DATABASE_MAX_IDLE_CONNECTIONS = "DATABASE_MAX_IDLE_CONNECTIONS"
+	DATABASE_MAX_OPEN_CONNECTIONS = "DATABASE_MAX_OPEN_CONNECTIONS"
+	DATABASE_MAX_CONN_LIFETIME    = "DATABASE_MAX_CONN_LIFETIME"
+
+	ETH_CHAIN_CONFIG = "ETH_CHAIN_CONFIG"
+	ETH_CHAIN_ID     = "ETH_CHAIN_ID"
+	ETH_HTTP_PATH    = "ETH_HTTP_PATH"
+
+	VALIDATE_BLOCK_HEIGHT            = "VALIDATE_BLOCK_HEIGHT"
+	VALIDATE_TRAIL                   = "VALIDATE_TRAIL"
+	VALIDATE_SLEEP_INTERVAL          = "VALIDATE_SLEEP_INTERVAL"
+	VALIDATE_STATEDIFF_MISSING_BLOCK = "VALIDATE_STATEDIFF_MISSING_BLOCK"
+	VALIDATE_STATEDIFF_TIMEOUT       = "VALIDATE_STATEDIFF_TIMEOUT"
+)
+
+// Bind env vars
+func init() {
+	viper.BindEnv("log.level", LOG_LEVEL)
+	viper.BindEnv("log.file", LOG_FILE_PATH)
+
+	viper.BindEnv("prom.metrics", PROM_METRICS)
+	viper.BindEnv("prom.http", PROM_HTTP)
+	viper.BindEnv("prom.httpAddr", PROM_HTTP_ADDR)
+	viper.BindEnv("prom.httpPort", PROM_HTTP_PORT)
+	viper.BindEnv("prom.dbStats", PROM_DB_STATS)
+
+	viper.BindEnv("database.name", DATABASE_NAME)
+	viper.BindEnv("database.hostname", DATABASE_HOSTNAME)
+	viper.BindEnv("database.port", DATABASE_PORT)
+	viper.BindEnv("database.user", DATABASE_USER)
+	viper.BindEnv("database.password", DATABASE_PASSWORD)
+
+	viper.BindEnv("database.maxIdle", DATABASE_MAX_IDLE_CONNECTIONS)
+	viper.BindEnv("database.maxOpen", DATABASE_MAX_OPEN_CONNECTIONS)
+	viper.BindEnv("database.maxLifetime", DATABASE_MAX_CONN_LIFETIME)
+
+	viper.BindEnv("ethereum.chainConfig", ETH_CHAIN_CONFIG)
+	viper.BindEnv("ethereum.chainID", ETH_CHAIN_ID)
+	viper.BindEnv("ethereum.httpPath", ETH_HTTP_PATH)
+
+	viper.BindEnv("validate.blockHeight", VALIDATE_BLOCK_HEIGHT)
+	viper.BindEnv("validate.trail", VALIDATE_TRAIL)
+	viper.BindEnv("validate.sleepInterval", VALIDATE_SLEEP_INTERVAL)
+	viper.BindEnv("validate.stateDiffMissingBlock", VALIDATE_STATEDIFF_MISSING_BLOCK)
+	viper.BindEnv("validate.stateDiffTimeout", VALIDATE_STATEDIFF_TIMEOUT)
+}

cmd/root.go

@@ -1,12 +1,31 @@
+// 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 cmd
 
 import (
+	"fmt"
 	"os"
 	"strings"
 
 	log "github.com/sirupsen/logrus"
 	"github.com/spf13/cobra"
 	"github.com/spf13/viper"
+
+	"github.com/vulcanize/ipld-eth-db-validator/pkg/prom"
 )
 
 var (
@@ -31,7 +50,7 @@ func Execute() {
 }
 
 func initFunc(cmd *cobra.Command, args []string) {
-	logfile := viper.GetString("logfile")
+	logfile := viper.GetString("log.file")
 	if logfile != "" {
 		file, err := os.OpenFile(logfile,
 			os.O_CREATE|os.O_WRONLY|os.O_APPEND, 0666)
@@ -49,6 +68,21 @@ func initFunc(cmd *cobra.Command, args []string) {
 	if err := logLevel(); err != nil {
 		log.Fatal("Could not set log level: ", err)
 	}
+
+	if viper.GetBool("prom.metrics") {
+		log.Info("initializing prometheus metrics")
+		prom.Init()
+	}
+
+	if viper.GetBool("prom.http") {
+		addr := fmt.Sprintf(
+			"%s:%s",
+			viper.GetString("prom.httpAddr"),
+			viper.GetString("prom.httpPort"),
+		)
+		log.Info("starting prometheus server")
+		prom.Serve(addr)
+	}
 }
 
 func init() {
@@ -57,21 +91,33 @@ func init() {
 	viper.AutomaticEnv()
 
 	rootCmd.PersistentFlags().StringVar(&cfgFile, "config", "", "config file location")
-	rootCmd.PersistentFlags().String("logfile", "", "file path for logging")
 	rootCmd.PersistentFlags().String("database-name", "vulcanize_public", "database name")
 	rootCmd.PersistentFlags().Int("database-port", 5432, "database port")
 	rootCmd.PersistentFlags().String("database-hostname", "localhost", "database hostname")
 	rootCmd.PersistentFlags().String("database-user", "", "database user")
 	rootCmd.PersistentFlags().String("database-password", "", "database password")
+	rootCmd.PersistentFlags().String("log-file", "", "file path for logging")
 	rootCmd.PersistentFlags().String("log-level", log.InfoLevel.String(), "Log level (trace, debug, info, warn, error, fatal, panic")
 
-	_ = viper.BindPFlag("logfile", rootCmd.PersistentFlags().Lookup("logfile"))
+	rootCmd.PersistentFlags().Bool("prom-metrics", false, "enable prometheus metrics")
+	rootCmd.PersistentFlags().Bool("prom-http", false, "enable prometheus http service")
+	rootCmd.PersistentFlags().String("prom-httpAddr", "127.0.0.1", "prometheus http host")
+	rootCmd.PersistentFlags().String("prom-httpPort", "9001", "prometheus http port")
+	rootCmd.PersistentFlags().Bool("prom-dbStats", false, "enables prometheus db stats")
+
 	_ = viper.BindPFlag("database.name", rootCmd.PersistentFlags().Lookup("database-name"))
 	_ = viper.BindPFlag("database.port", rootCmd.PersistentFlags().Lookup("database-port"))
 	_ = viper.BindPFlag("database.hostname", rootCmd.PersistentFlags().Lookup("database-hostname"))
 	_ = viper.BindPFlag("database.user", rootCmd.PersistentFlags().Lookup("database-user"))
 	_ = viper.BindPFlag("database.password", rootCmd.PersistentFlags().Lookup("database-password"))
+	_ = viper.BindPFlag("log.file", rootCmd.PersistentFlags().Lookup("log-file"))
 	_ = viper.BindPFlag("log.level", rootCmd.PersistentFlags().Lookup("log-level"))
+
+	_ = viper.BindPFlag("prom.metrics", rootCmd.PersistentFlags().Lookup("prom-metrics"))
+	_ = viper.BindPFlag("prom.http", rootCmd.PersistentFlags().Lookup("prom-http"))
+	_ = viper.BindPFlag("prom.httpAddr", rootCmd.PersistentFlags().Lookup("prom-httpAddr"))
+	_ = viper.BindPFlag("prom.httpPort", rootCmd.PersistentFlags().Lookup("prom-httpPort"))
+	_ = viper.BindPFlag("prom.dbStats", rootCmd.PersistentFlags().Lookup("prom-dbStats"))
 }
 
 func logLevel() error {

cmd/state_validator.go

@@ -1,3 +1,19 @@
+// 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 cmd
 
 import (
@@ -52,14 +68,22 @@ func init() {
 	stateValidatorCmd.PersistentFlags().String("block-height", "1", "block height to initiate state validation")
 	stateValidatorCmd.PersistentFlags().String("trail", "16", "trail of block height to validate")
 	stateValidatorCmd.PersistentFlags().String("sleep-interval", "10", "sleep interval in seconds after validator has caught up to (head-trail) height")
+	stateValidatorCmd.PersistentFlags().Bool("statediff-missing-block", false, "whether to perform a statediffing call on a missing block")
+	stateValidatorCmd.PersistentFlags().Uint("statediff-timeout", 240, "statediffing call timeout period (in sec)")
 
-	stateValidatorCmd.PersistentFlags().String("chain-config", "", "path to chain config")
+	stateValidatorCmd.PersistentFlags().String("eth-chain-config", "", "path to json chain config")
+	stateValidatorCmd.PersistentFlags().String("eth-chain-id", "1", "eth chain id")
+	stateValidatorCmd.PersistentFlags().String("eth-http-path", "", "http url for a statediffing node")
 
-	_ = viper.BindPFlag("validate.block-height", stateValidatorCmd.PersistentFlags().Lookup("block-height"))
+	_ = viper.BindPFlag("validate.blockHeight", stateValidatorCmd.PersistentFlags().Lookup("block-height"))
 	_ = viper.BindPFlag("validate.trail", stateValidatorCmd.PersistentFlags().Lookup("trail"))
 	_ = viper.BindPFlag("validate.sleepInterval", stateValidatorCmd.PersistentFlags().Lookup("sleep-interval"))
+	_ = viper.BindPFlag("validate.stateDiffMissingBlock", stateValidatorCmd.PersistentFlags().Lookup("statediff-missing-block"))
+	_ = viper.BindPFlag("validate.stateDiffTimeout", stateValidatorCmd.PersistentFlags().Lookup("statediff-timeout"))
 
-	_ = viper.BindPFlag("ethereum.chainConfig", stateValidatorCmd.PersistentFlags().Lookup("chain-config"))
+	_ = viper.BindPFlag("ethereum.chainConfig", stateValidatorCmd.PersistentFlags().Lookup("eth-chain-config"))
+	_ = viper.BindPFlag("ethereum.chainID", stateValidatorCmd.PersistentFlags().Lookup("eth-chain-id"))
+	_ = viper.BindPFlag("ethereum.httpPath", stateValidatorCmd.PersistentFlags().Lookup("eth-http-path"))
 }
 
 func initConfig() {

docker-compose.yml

@@ -1,18 +1,30 @@
 version: '3.2'
 
 services:
+  migrations:
+    restart: on-failure
+    depends_on:
+      - ipld-eth-db
+    image: vulcanize/ipld-eth-db:v4.2.0-alpha
+    environment:
+      DATABASE_USER: "vdbm"
+      DATABASE_NAME: "vulcanize_testing"
+      DATABASE_PASSWORD: "password"
+      DATABASE_HOSTNAME: "ipld-eth-db"
+      DATABASE_PORT: 5432
+
   ipld-eth-db:
+    image: timescale/timescaledb:latest-pg14
     restart: always
-    image: vulcanize/ipld-eth-db:v3.2.0
+    command: ["postgres", "-c", "log_statement=all"]
     environment:
       POSTGRES_USER: "vdbm"
       POSTGRES_DB: "vulcanize_testing"
       POSTGRES_PASSWORD: "password"
-    volumes:
-      - vdb_db_eth_validator:/var/lib/postgresql/data
     ports:
       - "127.0.0.1:8077:5432"
-    command: ["postgres", "-c", "log_statement=all"]
+    volumes:
+      - vdb_db_eth_validator:/var/lib/postgresql/data
 
 volumes:
   vdb_db_eth_validator:

environments/example.toml

@@ -6,9 +6,24 @@
     user     = "vdbm"
 
 [validate]
-    block-height = 1
+    blockHeight = 1
     trail  = 16
     sleepInterval = 10
+    stateDiffMissingBlock = true
+    stateDiffTimeout = 240
 
 [ethereum]
-    chainConfig = "./chain.json"
+    chainConfig = ""
+    chainID = "1"
+    httpPath = "localhost:8545"
+
+[prom]
+    metrics = true
+    http = true
+    httpAddr = "localhost"
+    httpPort = "9001"
+    dbStats = true
+
+[log]
+    file = ""
+    level = "info"

go.mod

@@ -3,57 +3,68 @@ module github.com/vulcanize/ipld-eth-db-validator
 go 1.18
 
 require (
-	github.com/ethereum/go-ethereum v1.10.18
+	github.com/ethereum/go-ethereum v1.10.23
 	github.com/jmoiron/sqlx v1.3.5
 	github.com/onsi/ginkgo v1.16.5
 	github.com/onsi/gomega v1.19.0
+	github.com/prometheus/client_golang v1.12.1
 	github.com/sirupsen/logrus v1.8.1
 	github.com/spf13/cobra v1.4.0
 	github.com/spf13/viper v1.11.0
-	github.com/vulcanize/ipfs-ethdb/v3 v3.0.3
+	github.com/vulcanize/ipfs-ethdb/v4 v4.0.7-alpha
-	github.com/vulcanize/ipld-eth-server/v3 v3.2.1
+	github.com/vulcanize/ipld-eth-server/v4 v4.1.7-alpha
 )
 
 require (
 	bazil.org/fuse v0.0.0-20200117225306-7b5117fecadc // indirect
-	github.com/StackExchange/wmi v0.0.0-20180116203802-5d049714c4a6 // indirect
 	github.com/Stebalien/go-bitfield v0.0.1 // indirect
 	github.com/VictoriaMetrics/fastcache v1.6.0 // indirect
-	github.com/benbjohnson/clock v1.1.0 // indirect
+	github.com/alecthomas/units v0.0.0-20210927113745-59d0afb8317a // indirect
+	github.com/benbjohnson/clock v1.3.0 // indirect
 	github.com/beorn7/perks v1.0.1 // indirect
 	github.com/blang/semver/v4 v4.0.0 // indirect
 	github.com/btcsuite/btcd v0.22.1 // indirect
 	github.com/btcsuite/btcd/btcec/v2 v2.2.0 // indirect
+	github.com/btcsuite/btcd/chaincfg/chainhash v1.0.1 // indirect
 	github.com/cenkalti/backoff v2.2.1+incompatible // indirect
-	github.com/cenkalti/backoff/v4 v4.1.1 // indirect
+	github.com/cenkalti/backoff/v4 v4.1.3 // indirect
 	github.com/cespare/xxhash/v2 v2.1.2 // indirect
 	github.com/cheekybits/genny v1.0.0 // indirect
+	github.com/containerd/cgroups v1.0.3 // indirect
+	github.com/coreos/go-systemd/v22 v22.3.2 // indirect
+	github.com/cpuguy83/go-md2man/v2 v2.0.2 // indirect
 	github.com/crackcomm/go-gitignore v0.0.0-20170627025303-887ab5e44cc3 // indirect
 	github.com/cskr/pubsub v1.0.2 // indirect
 	github.com/davecgh/go-spew v1.1.1 // indirect
 	github.com/davidlazar/go-crypto v0.0.0-20200604182044-b73af7476f6c // indirect
 	github.com/deckarep/golang-set v1.8.0 // indirect
 	github.com/decred/dcrd/dcrec/secp256k1/v4 v4.0.1 // indirect
+	github.com/docker/go-units v0.4.0 // indirect
+	github.com/dustin/go-humanize v1.0.0 // indirect
 	github.com/edsrzf/mmap-go v1.0.0 // indirect
+	github.com/elastic/gosigar v0.14.2 // indirect
 	github.com/facebookgo/atomicfile v0.0.0-20151019160806-2de1f203e7d5 // indirect
 	github.com/fjl/memsize v0.0.0-20190710130421-bcb5799ab5e5 // indirect
 	github.com/flynn/noise v1.0.0 // indirect
 	github.com/francoispqt/gojay v1.2.13 // indirect
-	github.com/fsnotify/fsnotify v1.5.1 // indirect
+	github.com/fsnotify/fsnotify v1.5.4 // indirect
 	github.com/gballet/go-libpcsclite v0.0.0-20190607065134-2772fd86a8ff // indirect
 	github.com/georgysavva/scany v0.2.9 // indirect
-	github.com/go-ole/go-ole v1.2.1 // indirect
+	github.com/go-logr/logr v1.2.3 // indirect
+	github.com/go-logr/stdr v1.2.2 // indirect
+	github.com/go-ole/go-ole v1.2.6 // indirect
 	github.com/go-stack/stack v1.8.0 // indirect
 	github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0 // indirect
+	github.com/godbus/dbus/v5 v5.1.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/golang-jwt/jwt/v4 v4.3.0 // indirect
 	github.com/golang/protobuf v1.5.2 // indirect
 	github.com/golang/snappy v0.0.4 // indirect
 	github.com/google/gopacket v1.1.19 // indirect
 	github.com/google/uuid v1.3.0 // indirect
-	github.com/gorilla/websocket v1.4.2 // indirect
+	github.com/gorilla/websocket v1.5.0 // indirect
 	github.com/hannahhoward/go-pubsub v0.0.0-20200423002714-8d62886cc36e // indirect
-	github.com/hashicorp/errwrap v1.0.0 // indirect
+	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/hashicorp/go-bexpr v0.1.10 // indirect
 	github.com/hashicorp/go-multierror v1.1.1 // indirect
 	github.com/hashicorp/golang-lru v0.5.5-0.20210104140557-80c98217689d // indirect
@@ -63,115 +74,100 @@ require (
 	github.com/huin/goupnp v1.0.3 // indirect
 	github.com/inconshreveable/mousetrap v1.0.0 // indirect
 	github.com/ipfs/bbloom v0.0.4 // indirect
-	github.com/ipfs/go-bitswap v0.4.0 // indirect
+	github.com/ipfs/go-bitfield v1.0.0 // indirect
+	github.com/ipfs/go-bitswap v0.8.0 // indirect
 	github.com/ipfs/go-block-format v0.0.3 // indirect
-	github.com/ipfs/go-blockservice v0.1.7 // indirect
+	github.com/ipfs/go-blockservice v0.4.0 // indirect
-	github.com/ipfs/go-cid v0.0.7 // indirect
+	github.com/ipfs/go-cid v0.2.0 // indirect
-	github.com/ipfs/go-cidutil v0.0.2 // indirect
+	github.com/ipfs/go-cidutil v0.1.0 // indirect
-	github.com/ipfs/go-datastore v0.4.6 // indirect
+	github.com/ipfs/go-datastore v0.5.1 // indirect
-	github.com/ipfs/go-ds-measure v0.1.0 // indirect
+	github.com/ipfs/go-delegated-routing v0.3.0 // indirect
-	github.com/ipfs/go-fetcher v1.5.0 // indirect
+	github.com/ipfs/go-ds-measure v0.2.0 // indirect
-	github.com/ipfs/go-filestore v1.0.0 // indirect
+	github.com/ipfs/go-fetcher v1.6.1 // indirect
+	github.com/ipfs/go-filestore v1.2.0 // indirect
 	github.com/ipfs/go-fs-lock v0.0.7 // indirect
-	github.com/ipfs/go-graphsync v0.8.0 // indirect
+	github.com/ipfs/go-graphsync v0.13.1 // indirect
-	github.com/ipfs/go-ipfs v0.10.0 // indirect
+	github.com/ipfs/go-ipfs-blockstore v1.2.0 // indirect
-	github.com/ipfs/go-ipfs-blockstore v1.0.1 // indirect
 	github.com/ipfs/go-ipfs-chunker v0.0.5 // indirect
-	github.com/ipfs/go-ipfs-config v0.16.0 // indirect
 	github.com/ipfs/go-ipfs-delay v0.0.1 // indirect
-	github.com/ipfs/go-ipfs-ds-help v1.0.0 // indirect
+	github.com/ipfs/go-ipfs-ds-help v1.1.0 // indirect
-	github.com/ipfs/go-ipfs-exchange-interface v0.0.1 // indirect
+	github.com/ipfs/go-ipfs-exchange-interface v0.2.0 // indirect
-	github.com/ipfs/go-ipfs-exchange-offline v0.0.1 // indirect
+	github.com/ipfs/go-ipfs-exchange-offline v0.3.0 // indirect
-	github.com/ipfs/go-ipfs-files v0.0.8 // indirect
+	github.com/ipfs/go-ipfs-files v0.1.1 // indirect
 	github.com/ipfs/go-ipfs-keystore v0.0.2 // indirect
-	github.com/ipfs/go-ipfs-pinner v0.1.2 // indirect
+	github.com/ipfs/go-ipfs-pinner v0.2.1 // indirect
 	github.com/ipfs/go-ipfs-posinfo v0.0.1 // indirect
 	github.com/ipfs/go-ipfs-pq v0.0.2 // indirect
-	github.com/ipfs/go-ipfs-provider v0.6.1 // indirect
+	github.com/ipfs/go-ipfs-provider v0.7.1 // indirect
-	github.com/ipfs/go-ipfs-routing v0.1.0 // indirect
+	github.com/ipfs/go-ipfs-routing v0.2.1 // indirect
 	github.com/ipfs/go-ipfs-util v0.0.2 // indirect
 	github.com/ipfs/go-ipld-cbor v0.0.5 // indirect
-	github.com/ipfs/go-ipld-format v0.2.0 // indirect
+	github.com/ipfs/go-ipld-format v0.4.0 // indirect
-	github.com/ipfs/go-ipld-legacy v0.1.0 // indirect
+	github.com/ipfs/go-ipld-legacy v0.1.1 // indirect
 	github.com/ipfs/go-ipns v0.1.2 // indirect
 	github.com/ipfs/go-log v1.0.5 // indirect
-	github.com/ipfs/go-log/v2 v2.3.0 // indirect
+	github.com/ipfs/go-log/v2 v2.5.1 // indirect
-	github.com/ipfs/go-merkledag v0.4.0 // indirect
+	github.com/ipfs/go-merkledag v0.6.0 // indirect
 	github.com/ipfs/go-metrics-interface v0.0.1 // indirect
-	github.com/ipfs/go-mfs v0.1.2 // indirect
+	github.com/ipfs/go-mfs v0.2.1 // indirect
-	github.com/ipfs/go-namesys v0.3.1 // indirect
+	github.com/ipfs/go-namesys v0.5.0 // indirect
-	github.com/ipfs/go-path v0.1.2 // indirect
+	github.com/ipfs/go-path v0.3.0 // indirect
-	github.com/ipfs/go-peertaskqueue v0.4.0 // indirect
+	github.com/ipfs/go-peertaskqueue v0.7.1 // indirect
-	github.com/ipfs/go-unixfs v0.2.5 // indirect
+	github.com/ipfs/go-unixfs v0.4.0 // indirect
-	github.com/ipfs/go-unixfsnode v1.1.3 // indirect
+	github.com/ipfs/go-unixfsnode v1.4.0 // indirect
 	github.com/ipfs/go-verifcid v0.0.1 // indirect
-	github.com/ipfs/interface-go-ipfs-core v0.5.1 // indirect
+	github.com/ipfs/interface-go-ipfs-core v0.7.0 // indirect
-	github.com/ipld/go-codec-dagpb v1.3.0 // indirect
+	github.com/ipfs/kubo v0.14.0 // indirect
-	github.com/ipld/go-ipld-prime v0.12.2 // indirect
+	github.com/ipld/edelweiss v0.1.4 // indirect
+	github.com/ipld/go-codec-dagpb v1.4.0 // indirect
+	github.com/ipld/go-ipld-prime v0.17.0 // indirect
 	github.com/jackc/chunkreader/v2 v2.0.1 // indirect
-	github.com/jackc/pgconn v1.10.0 // indirect
+	github.com/jackc/pgconn v1.12.1 // 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/pgproto3/v2 v2.3.0 // indirect
 	github.com/jackc/pgservicefile v0.0.0-20200714003250-2b9c44734f2b // indirect
-	github.com/jackc/pgtype v1.8.1 // indirect
+	github.com/jackc/pgtype v1.11.0 // indirect
-	github.com/jackc/pgx/v4 v4.13.0 // indirect
+	github.com/jackc/pgx/v4 v4.16.1 // indirect
-	github.com/jackc/puddle v1.1.3 // indirect
+	github.com/jackc/puddle v1.2.1 // indirect
 	github.com/jackpal/go-nat-pmp v1.0.2 // indirect
 	github.com/jbenet/go-temp-err-catcher v0.1.0 // indirect
 	github.com/jbenet/goprocess v0.1.4 // indirect
-	github.com/klauspost/compress v1.11.7 // indirect
+	github.com/jinzhu/inflection v1.0.0 // indirect
-	github.com/klauspost/cpuid/v2 v2.0.9 // indirect
+	github.com/jinzhu/now v1.1.4 // indirect
+	github.com/klauspost/compress v1.15.1 // indirect
+	github.com/klauspost/cpuid/v2 v2.0.12 // indirect
 	github.com/koron/go-ssdp v0.0.2 // indirect
-	github.com/lib/pq v1.10.5 // indirect
+	github.com/lib/pq v1.10.6 // indirect
-	github.com/libp2p/go-addr-util v0.1.0 // indirect
 	github.com/libp2p/go-buffer-pool v0.0.2 // indirect
 	github.com/libp2p/go-cidranger v1.1.0 // indirect
-	github.com/libp2p/go-conn-security-multistream v0.2.1 // indirect
+	github.com/libp2p/go-doh-resolver v0.4.0 // indirect
-	github.com/libp2p/go-doh-resolver v0.3.1 // indirect
 	github.com/libp2p/go-eventbus v0.2.1 // indirect
 	github.com/libp2p/go-flow-metrics v0.0.3 // indirect
-	github.com/libp2p/go-libp2p v0.15.0 // indirect
+	github.com/libp2p/go-libp2p v0.20.3 // indirect
-	github.com/libp2p/go-libp2p-asn-util v0.0.0-20200825225859-85005c6cf052 // indirect
+	github.com/libp2p/go-libp2p-asn-util v0.2.0 // indirect
-	github.com/libp2p/go-libp2p-autonat v0.4.2 // indirect
+	github.com/libp2p/go-libp2p-core v0.16.1 // indirect
-	github.com/libp2p/go-libp2p-blankhost v0.2.0 // indirect
+	github.com/libp2p/go-libp2p-discovery v0.7.0 // indirect
-	github.com/libp2p/go-libp2p-circuit v0.4.0 // indirect
+	github.com/libp2p/go-libp2p-kad-dht v0.16.0 // indirect
-	github.com/libp2p/go-libp2p-connmgr v0.2.4 // indirect
-	github.com/libp2p/go-libp2p-core v0.9.0 // indirect
-	github.com/libp2p/go-libp2p-discovery v0.5.1 // indirect
-	github.com/libp2p/go-libp2p-kad-dht v0.13.1 // indirect
 	github.com/libp2p/go-libp2p-kbucket v0.4.7 // indirect
 	github.com/libp2p/go-libp2p-loggables v0.1.0 // indirect
-	github.com/libp2p/go-libp2p-mplex v0.4.1 // indirect
+	github.com/libp2p/go-libp2p-peerstore v0.6.0 // indirect
-	github.com/libp2p/go-libp2p-nat v0.0.6 // indirect
+	github.com/libp2p/go-libp2p-pubsub v0.6.1 // indirect
-	github.com/libp2p/go-libp2p-noise v0.2.2 // indirect
+	github.com/libp2p/go-libp2p-pubsub-router v0.5.0 // indirect
-	github.com/libp2p/go-libp2p-peerstore v0.2.8 // indirect
-	github.com/libp2p/go-libp2p-pnet v0.2.0 // indirect
-	github.com/libp2p/go-libp2p-pubsub v0.5.4 // indirect
-	github.com/libp2p/go-libp2p-pubsub-router v0.4.0 // indirect
-	github.com/libp2p/go-libp2p-quic-transport v0.12.0 // indirect
 	github.com/libp2p/go-libp2p-record v0.1.3 // indirect
+	github.com/libp2p/go-libp2p-resource-manager v0.3.0 // indirect
 	github.com/libp2p/go-libp2p-routing-helpers v0.2.3 // indirect
-	github.com/libp2p/go-libp2p-swarm v0.5.3 // indirect
+	github.com/libp2p/go-libp2p-swarm v0.11.0 // indirect
-	github.com/libp2p/go-libp2p-tls v0.2.0 // indirect
+	github.com/libp2p/go-libp2p-xor v0.1.0 // indirect
-	github.com/libp2p/go-libp2p-transport-upgrader v0.4.6 // indirect
+	github.com/libp2p/go-mplex v0.7.0 // indirect
-	github.com/libp2p/go-libp2p-xor v0.0.0-20210714161855-5c005aca55db // indirect
+	github.com/libp2p/go-msgio v0.2.0 // indirect
-	github.com/libp2p/go-libp2p-yamux v0.5.4 // indirect
+	github.com/libp2p/go-nat v0.1.0 // indirect
-	github.com/libp2p/go-maddr-filter v0.1.0 // indirect
+	github.com/libp2p/go-netroute v0.2.0 // indirect
-	github.com/libp2p/go-mplex v0.3.0 // indirect
-	github.com/libp2p/go-msgio v0.0.6 // indirect
-	github.com/libp2p/go-nat v0.0.5 // indirect
-	github.com/libp2p/go-netroute v0.1.6 // indirect
 	github.com/libp2p/go-openssl v0.0.7 // indirect
-	github.com/libp2p/go-reuseport v0.0.2 // indirect
+	github.com/libp2p/go-reuseport v0.2.0 // indirect
-	github.com/libp2p/go-reuseport-transport v0.0.5 // indirect
+	github.com/libp2p/go-yamux/v3 v3.1.2 // indirect
-	github.com/libp2p/go-sockaddr v0.1.1 // indirect
+	github.com/libp2p/zeroconf/v2 v2.1.1 // indirect
-	github.com/libp2p/go-stream-muxer-multistream v0.3.0 // indirect
+	github.com/lucas-clemente/quic-go v0.27.1 // indirect
-	github.com/libp2p/go-tcp-transport v0.2.8 // indirect
-	github.com/libp2p/go-ws-transport v0.5.0 // indirect
-	github.com/libp2p/go-yamux/v2 v2.2.0 // indirect
-	github.com/libp2p/zeroconf/v2 v2.0.0 // indirect
-	github.com/lucas-clemente/quic-go v0.26.0 // indirect
 	github.com/magiconair/properties v1.8.6 // indirect
 	github.com/mailgun/groupcache/v2 v2.3.0 // indirect
 	github.com/marten-seemann/qtls-go1-16 v0.1.5 // indirect
@@ -182,43 +178,46 @@ require (
 	github.com/mattn/go-isatty v0.0.14 // indirect
 	github.com/mattn/go-runewidth v0.0.9 // indirect
 	github.com/matttproud/golang_protobuf_extensions v1.0.1 // indirect
-	github.com/miekg/dns v1.1.43 // indirect
+	github.com/miekg/dns v1.1.48 // indirect
 	github.com/mikioh/tcpinfo v0.0.0-20190314235526-30a79bb1804b // indirect
 	github.com/mikioh/tcpopt v0.0.0-20190314235656-172688c1accc // indirect
-	github.com/minio/blake2b-simd v0.0.0-20160723061019-3f5f724cb5b1 // indirect
 	github.com/minio/sha256-simd v1.0.0 // indirect
 	github.com/mitchellh/go-homedir v1.1.0 // indirect
 	github.com/mitchellh/mapstructure v1.4.3 // indirect
 	github.com/mitchellh/pointerstructure v1.2.0 // indirect
 	github.com/mr-tron/base58 v1.2.0 // indirect
-	github.com/multiformats/go-base32 v0.0.3 // indirect
+	github.com/multiformats/go-base32 v0.0.4 // indirect
 	github.com/multiformats/go-base36 v0.1.0 // indirect
-	github.com/multiformats/go-multiaddr v0.4.0 // indirect
+	github.com/multiformats/go-multiaddr v0.5.0 // indirect
 	github.com/multiformats/go-multiaddr-dns v0.3.1 // indirect
 	github.com/multiformats/go-multiaddr-fmt v0.1.0 // indirect
-	github.com/multiformats/go-multibase v0.0.3 // indirect
+	github.com/multiformats/go-multibase v0.1.0 // indirect
-	github.com/multiformats/go-multicodec v0.3.0 // indirect
+	github.com/multiformats/go-multicodec v0.5.0 // indirect
-	github.com/multiformats/go-multihash v0.1.0 // indirect
+	github.com/multiformats/go-multihash v0.2.0 // indirect
-	github.com/multiformats/go-multistream v0.2.2 // indirect
+	github.com/multiformats/go-multistream v0.3.3 // indirect
 	github.com/multiformats/go-varint v0.0.6 // indirect
 	github.com/nxadm/tail v1.4.8 // indirect
 	github.com/olekukonko/tablewriter v0.0.5 // indirect
+	github.com/opencontainers/runtime-spec v1.0.2 // indirect
 	github.com/opentracing/opentracing-go v1.2.0 // indirect
+	github.com/pbnjay/memory v0.0.0-20210728143218-7b4eea64cf58 // indirect
 	github.com/pelletier/go-toml v1.9.4 // indirect
 	github.com/pelletier/go-toml/v2 v2.0.0-beta.8 // indirect
 	github.com/pganalyze/pg_query_go/v2 v2.1.0 // indirect
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/pmezard/go-difflib v1.0.0 // indirect
 	github.com/polydawn/refmt v0.0.0-20201211092308-30ac6d18308e // indirect
-	github.com/prometheus/client_golang v1.11.0 // indirect
 	github.com/prometheus/client_model v0.2.0 // indirect
-	github.com/prometheus/common v0.30.0 // indirect
+	github.com/prometheus/common v0.33.0 // indirect
 	github.com/prometheus/procfs v0.7.3 // indirect
-	github.com/prometheus/tsdb v0.7.1 // indirect
+	github.com/prometheus/tsdb v0.10.0 // indirect
+	github.com/raulk/clock v1.1.0 // indirect
+	github.com/raulk/go-watchdog v1.2.0 // indirect
 	github.com/rjeczalik/notify v0.9.1 // indirect
 	github.com/rs/cors v1.7.0 // indirect
+	github.com/russross/blackfriday/v2 v2.1.0 // indirect
 	github.com/segmentio/fasthash v1.0.3 // indirect
-	github.com/shirou/gopsutil v3.21.5+incompatible // indirect
+	github.com/shirou/gopsutil v3.21.11+incompatible // indirect
 	github.com/spacemonkeygo/spacelog v0.0.0-20180420211403-2296661a0572 // indirect
 	github.com/spaolacci/murmur3 v1.1.0 // indirect
 	github.com/spf13/afero v1.8.2 // indirect
@@ -227,48 +226,55 @@ require (
 	github.com/spf13/pflag v1.0.5 // indirect
 	github.com/status-im/keycard-go v0.0.0-20190316090335-8537d3370df4 // indirect
 	github.com/stretchr/objx v0.2.0 // indirect
-	github.com/stretchr/testify v1.7.1 // indirect
+	github.com/stretchr/testify v1.7.2 // indirect
 	github.com/subosito/gotenv v1.2.0 // indirect
-	github.com/syndtr/goleveldb v1.0.1-0.20210819022825-2ae1ddf74ef7 // indirect
+	github.com/syndtr/goleveldb v1.0.1-0.20220614013038-64ee5596c38a // indirect
 	github.com/thoas/go-funk v0.9.2 // indirect
+	github.com/tidwall/gjson v1.14.0 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.0 // indirect
 	github.com/tklauser/go-sysconf v0.3.6 // indirect
 	github.com/tklauser/numcpus v0.2.2 // indirect
 	github.com/tyler-smith/go-bip39 v1.0.1-0.20181017060643-dbb3b84ba2ef // indirect
-	github.com/vulcanize/eth-ipfs-state-validator/v3 v3.0.2 // indirect
+	github.com/urfave/cli/v2 v2.10.2 // indirect
+	github.com/vulcanize/eth-ipfs-state-validator/v4 v4.0.7-alpha // indirect
+	github.com/vulcanize/go-eth-state-node-iterator v1.1.4 // indirect
+	github.com/wI2L/jsondiff v0.2.0 // indirect
 	github.com/whyrusleeping/base32 v0.0.0-20170828182744-c30ac30633cc // indirect
 	github.com/whyrusleeping/cbor-gen v0.0.0-20210219115102-f37d292932f2 // indirect
 	github.com/whyrusleeping/chunker v0.0.0-20181014151217-fe64bd25879f // indirect
 	github.com/whyrusleeping/go-keyspace v0.0.0-20160322163242-5b898ac5add1 // indirect
-	github.com/whyrusleeping/mdns v0.0.0-20190826153040-b9b60ed33aa9 // indirect
 	github.com/whyrusleeping/multiaddr-filter v0.0.0-20160516205228-e903e4adabd7 // indirect
 	github.com/whyrusleeping/timecache v0.0.0-20160911033111-cfcb2f1abfee // indirect
+	github.com/xrash/smetrics v0.0.0-20201216005158-039620a65673 // indirect
+	github.com/yusufpapurcu/wmi v1.2.2 // indirect
 	go.opencensus.io v0.23.0 // indirect
-	go.opentelemetry.io/otel v0.20.0 // indirect
+	go.opentelemetry.io/otel v1.7.0 // indirect
-	go.opentelemetry.io/otel/metric v0.20.0 // indirect
+	go.opentelemetry.io/otel/trace v1.7.0 // indirect
-	go.opentelemetry.io/otel/trace v0.20.0 // indirect
 	go.uber.org/atomic v1.9.0 // indirect
-	go.uber.org/dig v1.10.0 // indirect
+	go.uber.org/dig v1.14.0 // indirect
-	go.uber.org/fx v1.13.1 // indirect
+	go.uber.org/fx v1.16.0 // indirect
-	go.uber.org/multierr v1.7.0 // indirect
+	go.uber.org/multierr v1.8.0 // indirect
-	go.uber.org/zap v1.19.0 // indirect
+	go.uber.org/zap v1.21.0 // indirect
 	go4.org v0.0.0-20200411211856-f5505b9728dd // indirect
-	golang.org/x/crypto v0.0.0-20220411220226-7b82a4e95df4 // indirect
+	golang.org/x/crypto v0.0.0-20220829220503-c86fa9a7ed90 // indirect
-	golang.org/x/mod v0.6.0-dev.0.20211013180041-c96bc1413d57 // indirect
+	golang.org/x/mod v0.6.0-dev.0.20220106191415-9b9b3d81d5e3 // indirect
-	golang.org/x/net v0.0.0-20220412020605-290c469a71a5 // indirect
+	golang.org/x/net v0.0.0-20220607020251-c690dde0001d // indirect
 	golang.org/x/sync v0.0.0-20210220032951-036812b2e83c // indirect
-	golang.org/x/sys v0.0.0-20220412211240-33da011f77ad // indirect
+	golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a // indirect
 	golang.org/x/text v0.3.7 // indirect
 	golang.org/x/time v0.0.0-20210220033141-f8bda1e9f3ba // indirect
-	golang.org/x/tools v0.1.8 // indirect
+	golang.org/x/tools v0.1.10 // indirect
-	golang.org/x/xerrors v0.0.0-20220411194840-2f41105eb62f // indirect
+	golang.org/x/xerrors v0.0.0-20220517211312-f3a8303e98df // indirect
 	google.golang.org/protobuf v1.28.0 // indirect
 	gopkg.in/ini.v1 v1.66.4 // indirect
 	gopkg.in/natefinch/npipe.v2 v2.0.0-20160621034901-c1b8fa8bdcce // indirect
 	gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7 // indirect
-	gopkg.in/urfave/cli.v1 v1.20.0 // indirect
 	gopkg.in/yaml.v2 v2.4.0 // indirect
-	gopkg.in/yaml.v3 v3.0.0-20210107192922-496545a6307b // indirect
+	gopkg.in/yaml.v3 v3.0.1 // indirect
-	lukechampine.com/blake3 v1.1.6 // indirect
+	gorm.io/driver/postgres v1.3.7 // indirect
+	gorm.io/gorm v1.23.5 // indirect
+	lukechampine.com/blake3 v1.1.7 // indirect
 )
 
-replace github.com/ethereum/go-ethereum v1.10.18 => github.com/vulcanize/go-ethereum v1.10.18-statediff-3.2.2
+replace github.com/ethereum/go-ethereum v1.10.23 => github.com/vulcanize/go-ethereum v1.10.23-statediff-4.2.0-alpha

main.go

@@ -1,3 +1,19 @@
+// 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 main
 
 import "github.com/vulcanize/ipld-eth-db-validator/cmd"

pkg/prom/db_stats_collector.go

@@ -0,0 +1,157 @@
+// 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 prom
+
+import (
+	"database/sql"
+
+	"github.com/prometheus/client_golang/prometheus"
+)
+
+// DBStatsGetter is an interface that gets sql.DBStats.
+type DBStatsGetter interface {
+	Stats() sql.DBStats
+}
+
+// DBStatsCollector implements the prometheus.Collector interface.
+type DBStatsCollector struct {
+	sg DBStatsGetter
+
+	// descriptions of exported metrics
+	maxOpenDesc           *prometheus.Desc
+	openDesc              *prometheus.Desc
+	inUseDesc             *prometheus.Desc
+	idleDesc              *prometheus.Desc
+	waitedForDesc         *prometheus.Desc
+	blockedSecondsDesc    *prometheus.Desc
+	closedMaxIdleDesc     *prometheus.Desc
+	closedMaxLifetimeDesc *prometheus.Desc
+}
+
+// NewDBStatsCollector creates a new DBStatsCollector.
+func NewDBStatsCollector(dbName string, sg DBStatsGetter) *DBStatsCollector {
+	labels := prometheus.Labels{"db_name": dbName}
+	return &DBStatsCollector{
+		sg: sg,
+		maxOpenDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "max_open"),
+			"Maximum number of open connections to the database.",
+			nil,
+			labels,
+		),
+		openDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "open"),
+			"The number of established connections both in use and idle.",
+			nil,
+			labels,
+		),
+		inUseDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "in_use"),
+			"The number of connections currently in use.",
+			nil,
+			labels,
+		),
+		idleDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "idle"),
+			"The number of idle connections.",
+			nil,
+			labels,
+		),
+		waitedForDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "waited_for"),
+			"The total number of connections waited for.",
+			nil,
+			labels,
+		),
+		blockedSecondsDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "blocked_seconds"),
+			"The total time blocked waiting for a new connection.",
+			nil,
+			labels,
+		),
+		closedMaxIdleDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "closed_max_idle"),
+			"The total number of connections closed due to SetMaxIdleConns.",
+			nil,
+			labels,
+		),
+		closedMaxLifetimeDesc: prometheus.NewDesc(
+			prometheus.BuildFQName(namespace, connSubsystem, "closed_max_lifetime"),
+			"The total number of connections closed due to SetConnMaxLifetime.",
+			nil,
+			labels,
+		),
+	}
+}
+
+// Describe implements the prometheus.Collector interface.
+func (c DBStatsCollector) Describe(ch chan<- *prometheus.Desc) {
+	ch <- c.maxOpenDesc
+	ch <- c.openDesc
+	ch <- c.inUseDesc
+	ch <- c.idleDesc
+	ch <- c.waitedForDesc
+	ch <- c.blockedSecondsDesc
+	ch <- c.closedMaxIdleDesc
+	ch <- c.closedMaxLifetimeDesc
+}
+
+// Collect implements the prometheus.Collector interface.
+func (c DBStatsCollector) Collect(ch chan<- prometheus.Metric) {
+	stats := c.sg.Stats()
+
+	ch <- prometheus.MustNewConstMetric(
+		c.maxOpenDesc,
+		prometheus.GaugeValue,
+		float64(stats.MaxOpenConnections),
+	)
+	ch <- prometheus.MustNewConstMetric(
+		c.openDesc,
+		prometheus.GaugeValue,
+		float64(stats.OpenConnections),
+	)
+	ch <- prometheus.MustNewConstMetric(
+		c.inUseDesc,
+		prometheus.GaugeValue,
+		float64(stats.InUse),
+	)
+	ch <- prometheus.MustNewConstMetric(
+		c.idleDesc,
+		prometheus.GaugeValue,
+		float64(stats.Idle),
+	)
+	ch <- prometheus.MustNewConstMetric(
+		c.waitedForDesc,
+		prometheus.CounterValue,
+		float64(stats.WaitCount),
+	)
+	ch <- prometheus.MustNewConstMetric(
+		c.blockedSecondsDesc,
+		prometheus.CounterValue,
+		stats.WaitDuration.Seconds(),
+	)
+	ch <- prometheus.MustNewConstMetric(
+		c.closedMaxIdleDesc,
+		prometheus.CounterValue,
+		float64(stats.MaxIdleClosed),
+	)
+	ch <- prometheus.MustNewConstMetric(
+		c.closedMaxLifetimeDesc,
+		prometheus.CounterValue,
+		float64(stats.MaxLifetimeClosed),
+	)
+}

pkg/prom/prom.go

@@ -0,0 +1,59 @@
+// 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 prom
+
+import (
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promauto"
+)
+
+const (
+	namespace = "ipld_eth_state_snapshot"
+
+	connSubsystem  = "connections"
+	statsSubsystem = "stats"
+)
+
+var (
+	metrics            bool
+	lastValidatedBlock prometheus.Gauge
+)
+
+func Init() {
+	metrics = true
+
+	lastValidatedBlock = promauto.NewGauge(prometheus.GaugeOpts{
+		Namespace: namespace,
+		Subsystem: statsSubsystem,
+		Name:      "last_validated_block",
+		Help:      "Last validated block number",
+	})
+}
+
+// RegisterDBCollector create metric collector for given connection
+func RegisterDBCollector(name string, db DBStatsGetter) {
+	if metrics {
+		prometheus.Register(NewDBStatsCollector(name, db))
+	}
+}
+
+// SetLastValidatedBlock sets the last validated block number
+func SetLastValidatedBlock(blockNumber float64) {
+	if metrics {
+		lastValidatedBlock.Set(blockNumber)
+	}
+}

pkg/prom/serve.go

@@ -0,0 +1,47 @@
+// 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 prom
+
+import (
+	"errors"
+	"net/http"
+
+	"github.com/prometheus/client_golang/prometheus/promhttp"
+	"github.com/sirupsen/logrus"
+)
+
+var errPromHTTP = errors.New("can't start http server for prometheus")
+
+// Serve start listening http
+func Serve(addr string) *http.Server {
+	mux := http.NewServeMux()
+	mux.Handle("/metrics", promhttp.Handler())
+	srv := http.Server{
+		Addr:    addr,
+		Handler: mux,
+	}
+	go func() {
+		if err := srv.ListenAndServe(); err != nil {
+			logrus.
+				WithError(err).
+				WithField("module", "prom").
+				WithField("addr", addr).
+				Fatal(errPromHTTP)
+		}
+	}()
+	return &srv
+}

pkg/validator/config.go

@@ -1,3 +1,19 @@
+// 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 validator
 
 import (
@@ -6,22 +22,14 @@ import (
 	"time"
 
 	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/rpc"
 	"github.com/ethereum/go-ethereum/statediff"
 	"github.com/ethereum/go-ethereum/statediff/indexer/database/sql/postgres"
 	"github.com/jmoiron/sqlx"
 	"github.com/spf13/viper"
-	"github.com/vulcanize/ipld-eth-server/v3/pkg/shared"
+	"github.com/vulcanize/ipld-eth-server/v4/pkg/shared"
-)
 
-var (
+	"github.com/vulcanize/ipld-eth-db-validator/pkg/prom"
-	DATABASE_NAME                 = "DATABASE_NAME"
-	DATABASE_HOSTNAME             = "DATABASE_HOSTNAME"
-	DATABASE_PORT                 = "DATABASE_PORT"
-	DATABASE_USER                 = "DATABASE_USER"
-	DATABASE_PASSWORD             = "DATABASE_PASSWORD"
-	DATABASE_MAX_IDLE_CONNECTIONS = "DATABASE_MAX_IDLE_CONNECTIONS"
-	DATABASE_MAX_OPEN_CONNECTIONS = "DATABASE_MAX_OPEN_CONNECTIONS"
-	DATABASE_MAX_CONN_LIFETIME    = "DATABASE_MAX_CONN_LIFETIME"
 )
 
 var IntegrationTestChainConfig = &params.ChainConfig{
@@ -61,7 +69,10 @@ type Config struct {
 	dbConfig postgres.Config
 	DB       *sqlx.DB
 
-	ChainCfg *params.ChainConfig
+	ChainCfg              *params.ChainConfig
+	Client                *rpc.Client
+	StateDiffMissingBlock bool
+	StateDiffTimeout      uint
 
 	BlockNum, Trail uint64
 	SleepInterval   uint
@@ -74,16 +85,12 @@ func NewConfig() (*Config, error) {
 		return nil, err
 	}
 
-	cfg.BlockNum = viper.GetUint64("validate.block-height")
+	err = cfg.setupEth()
-	if cfg.BlockNum < 1 {
+	if err != nil {
-		return nil, fmt.Errorf("block height cannot be less the 1")
+		return nil, err
 	}
 
-	cfg.Trail = viper.GetUint64("validate.trail")
+	err = cfg.setupValidator()
-	cfg.SleepInterval = viper.GetUint("validate.sleepInterval")
-
-	chainConfigPath := viper.GetString("ethereum.chainConfig")
-	cfg.ChainCfg, err = statediff.LoadConfig(chainConfigPath)
 	if err != nil {
 		return nil, err
 	}
@@ -92,15 +99,6 @@ func NewConfig() (*Config, error) {
 }
 
 func (c *Config) setupDB() error {
-	_ = viper.BindEnv("database.name", DATABASE_NAME)
-	_ = viper.BindEnv("database.hostname", DATABASE_HOSTNAME)
-	_ = viper.BindEnv("database.port", DATABASE_PORT)
-	_ = viper.BindEnv("database.user", DATABASE_USER)
-	_ = viper.BindEnv("database.password", DATABASE_PASSWORD)
-	_ = viper.BindEnv("database.maxIdle", DATABASE_MAX_IDLE_CONNECTIONS)
-	_ = viper.BindEnv("database.maxOpen", DATABASE_MAX_OPEN_CONNECTIONS)
-	_ = viper.BindEnv("database.maxLifetime", DATABASE_MAX_CONN_LIFETIME)
-
 	// DB Config
 	c.dbConfig.DatabaseName = viper.GetString("database.name")
 	c.dbConfig.Hostname = viper.GetString("database.hostname")
@@ -117,7 +115,53 @@ func (c *Config) setupDB() error {
 	if err != nil {
 		return fmt.Errorf("failed to create config: %w", err)
 	}
-
 	c.DB = db
+
+	// Enable DB stats
+	if viper.GetBool("prom.dbStats") {
+		prom.RegisterDBCollector(c.dbConfig.DatabaseName, c.DB)
+	}
+
 	return nil
 }
+
+func (c *Config) setupEth() error {
+	var err error
+	chainConfigPath := viper.GetString("ethereum.chainConfig")
+	if chainConfigPath != "" {
+		c.ChainCfg, err = statediff.LoadConfig(chainConfigPath)
+	} else {
+		// read chainID if chain config path not provided
+		chainID := viper.GetUint64("ethereum.chainID")
+		c.ChainCfg, err = statediff.ChainConfig(chainID)
+	}
+	if err != nil {
+		return err
+	}
+
+	// setup a statediffing client
+	ethHTTP := viper.GetString("ethereum.httpPath")
+	if ethHTTP != "" {
+		ethHTTPEndpoint := fmt.Sprintf("http://%s", ethHTTP)
+		c.Client, err = rpc.Dial(ethHTTPEndpoint)
+	}
+
+	return err
+}
+
+func (c *Config) setupValidator() error {
+	var err error
+	c.BlockNum = viper.GetUint64("validate.blockHeight")
+	if c.BlockNum < 1 {
+		return fmt.Errorf("block height cannot be less the 1")
+	}
+
+	c.Trail = viper.GetUint64("validate.trail")
+	c.SleepInterval = viper.GetUint("validate.sleepInterval")
+	c.StateDiffMissingBlock = viper.GetBool("validate.stateDiffMissingBlock")
+	if c.StateDiffMissingBlock {
+		c.StateDiffTimeout = viper.GetUint("validate.stateDiffTimeout")
+	}
+
+	return err
+}

pkg/validator/database.go

@@ -1,3 +1,19 @@
+// 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 validator
 
 import (

pkg/validator/ref_integrity.go

@@ -0,0 +1,239 @@
+// 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 validator
+
+import (
+	"fmt"
+
+	"github.com/jmoiron/sqlx"
+)
+
+// ValidateReferentialIntegrity validates referential integrity at the given height
+func ValidateReferentialIntegrity(db *sqlx.DB, blockNumber uint64) error {
+	err := ValidateHeaderCIDsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateUncleCIDsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateTransactionCIDsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateReceiptCIDsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateStateCIDsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateStorageCIDsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateStateAccountsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateAccessListElementsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	err = ValidateLogCIDsRef(db, blockNumber)
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateHeaderCIDsRef does a reference integrity check on references in eth.header_cids table
+func ValidateHeaderCIDsRef(db *sqlx.DB, blockNumber uint64) error {
+	err := ValidateIPFSBlocks(db, blockNumber, "eth.header_cids", "mh_key")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateUncleCIDsRef does a reference integrity check on references in eth.uncle_cids table
+func ValidateUncleCIDsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, UncleCIDsRefHeaderCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.header_cids")
+	}
+
+	err = ValidateIPFSBlocks(db, blockNumber, "eth.uncle_cids", "mh_key")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateTransactionCIDsRef does a reference integrity check on references in eth.header_cids table
+func ValidateTransactionCIDsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, TransactionCIDsRefHeaderCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.header_cids")
+	}
+
+	err = ValidateIPFSBlocks(db, blockNumber, "eth.transaction_cids", "mh_key")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateReceiptCIDsRef does a reference integrity check on references in eth.receipt_cids table
+func ValidateReceiptCIDsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, ReceiptCIDsRefTransactionCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.transaction_cids")
+	}
+
+	err = ValidateIPFSBlocks(db, blockNumber, "eth.receipt_cids", "leaf_mh_key")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateStateCIDsRef does a reference integrity check on references in eth.state_cids table
+func ValidateStateCIDsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, StateCIDsRefHeaderCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.header_cids")
+	}
+
+	err = ValidateIPFSBlocks(db, blockNumber, "eth.state_cids", "mh_key")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateStorageCIDsRef does a reference integrity check on references in eth.storage_cids table
+func ValidateStorageCIDsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, StorageCIDsRefStateCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.state_cids")
+	}
+
+	err = ValidateIPFSBlocks(db, blockNumber, "eth.storage_cids", "mh_key")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateStateAccountsRef does a reference integrity check on references in eth.state_accounts table
+func ValidateStateAccountsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, StateAccountsRefStateCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.state_cids")
+	}
+
+	return nil
+}
+
+// ValidateAccessListElementsRef does a reference integrity check on references in eth.access_list_elements table
+func ValidateAccessListElementsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, AccessListElementsRefTransactionCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.transaction_cids")
+	}
+
+	return nil
+}
+
+// ValidateLogCIDsRef does a reference integrity check on references in eth.log_cids table
+func ValidateLogCIDsRef(db *sqlx.DB, blockNumber uint64) error {
+	var exists bool
+	err := db.Get(&exists, LogCIDsRefReceiptCIDs, blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "eth.receipt_cids")
+	}
+
+	err = ValidateIPFSBlocks(db, blockNumber, "eth.log_cids", "leaf_mh_key")
+	if err != nil {
+		return err
+	}
+
+	return nil
+}
+
+// ValidateIPFSBlocks does a reference integrity check between the given CID table and IPFS blocks table on MHKey and block number
+func ValidateIPFSBlocks(db *sqlx.DB, blockNumber uint64, CIDTable string, mhKeyField string) error {
+	var exists bool
+	err := db.Get(&exists, fmt.Sprintf(CIDsRefIPLDBlocks, CIDTable, mhKeyField), blockNumber)
+	if err != nil {
+		return err
+	}
+	if exists {
+		return fmt.Errorf(ReferentialIntegrityErr, blockNumber, "public.blocks")
+	}
+
+	return nil
+}

pkg/validator/ref_integrity_queries.go

@@ -0,0 +1,137 @@
+// 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 validator
+
+// Queries to validate referential integrity in the indexed data:
+// At the given block number,
+// In each table, for each (would be) foreign key reference, perform left join with the referenced table on the foreign key fields.
+// Select rows where there are no matching rows in the referenced table.
+// If any such rows exist, there are missing entries in the referenced table.
+
+const (
+	CIDsRefIPLDBlocks = `SELECT EXISTS (
+						SELECT *
+						FROM %[1]s
+						LEFT JOIN public.blocks ON (
+							%[1]s.%[2]s = blocks.key
+							AND %[1]s.block_number = blocks.block_number
+						)
+						WHERE
+							%[1]s.block_number = $1
+							AND blocks.key IS NULL
+					)`
+
+	UncleCIDsRefHeaderCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.uncle_cids
+						LEFT JOIN eth.header_cids ON (
+							uncle_cids.header_id = header_cids.block_hash
+							AND uncle_cids.block_number = header_cids.block_number
+						)
+						WHERE
+							uncle_cids.block_number = $1
+							AND header_cids.block_hash IS NULL
+					)`
+
+	TransactionCIDsRefHeaderCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.transaction_cids
+						LEFT JOIN eth.header_cids ON (
+							transaction_cids.header_id = header_cids.block_hash
+							AND transaction_cids.block_number = header_cids.block_number
+						)
+						WHERE
+							transaction_cids.block_number = $1
+							AND header_cids.block_hash IS NULL
+					)`
+
+	ReceiptCIDsRefTransactionCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.receipt_cids
+						LEFT JOIN eth.transaction_cids ON (
+							receipt_cids.tx_id = transaction_cids.tx_hash
+							AND receipt_cids.header_id = transaction_cids.header_id
+							AND receipt_cids.block_number = transaction_cids.block_number
+						)
+						WHERE
+							receipt_cids.block_number = $1
+							AND transaction_cids.tx_hash IS NULL
+					)`
+
+	StateCIDsRefHeaderCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.state_cids
+						LEFT JOIN eth.header_cids ON (
+							state_cids.header_id = header_cids.block_hash
+							AND state_cids.block_number = header_cids.block_number
+						)
+						WHERE
+							state_cids.block_number = $1
+							AND header_cids.block_hash IS NULL
+					)`
+
+	StorageCIDsRefStateCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.storage_cids
+						LEFT JOIN eth.state_cids ON (
+							storage_cids.state_path = state_cids.state_path
+							AND storage_cids.header_id = state_cids.header_id
+							AND storage_cids.block_number = state_cids.block_number
+						)
+						WHERE
+							storage_cids.block_number = $1
+							AND state_cids.state_path IS NULL
+					)`
+
+	StateAccountsRefStateCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.state_accounts
+						LEFT JOIN eth.state_cids ON (
+							state_accounts.state_path = state_cids.state_path
+							AND state_accounts.header_id = state_cids.header_id
+							AND state_accounts.block_number = state_cids.block_number
+						)
+						WHERE
+							state_accounts.block_number = $1
+							AND state_cids.state_path IS NULL
+					)`
+
+	AccessListElementsRefTransactionCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.access_list_elements
+						LEFT JOIN eth.transaction_cids ON (
+							access_list_elements.tx_id = transaction_cids.tx_hash
+							AND access_list_elements.block_number = transaction_cids.block_number
+						)
+						WHERE
+							access_list_elements.block_number = $1
+							AND transaction_cids.tx_hash IS NULL
+					)`
+
+	LogCIDsRefReceiptCIDs = `SELECT EXISTS (
+						SELECT *
+						FROM eth.log_cids
+						LEFT JOIN eth.receipt_cids ON (
+							log_cids.rct_id = receipt_cids.tx_id
+							AND log_cids.header_id = receipt_cids.header_id
+							AND log_cids.block_number = receipt_cids.block_number
+						)
+						WHERE
+							log_cids.block_number = $1
+							AND receipt_cids.tx_id IS NULL
+					)`
+)

pkg/validator/validator.go

@@ -1,7 +1,24 @@
+// 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 validator
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"math/big"
@@ -18,38 +35,51 @@ import (
 	"github.com/ethereum/go-ethereum/core/vm"
 	"github.com/ethereum/go-ethereum/params"
 	"github.com/ethereum/go-ethereum/rpc"
+	"github.com/ethereum/go-ethereum/statediff"
 	"github.com/jmoiron/sqlx"
 	log "github.com/sirupsen/logrus"
-	ipfsethdb "github.com/vulcanize/ipfs-ethdb/v3/postgres"
+
-	ipldEth "github.com/vulcanize/ipld-eth-server/v3/pkg/eth"
+	ipfsethdb "github.com/vulcanize/ipfs-ethdb/v4/postgres"
-	ethServerShared "github.com/vulcanize/ipld-eth-server/v3/pkg/shared"
+	ipldEth "github.com/vulcanize/ipld-eth-server/v4/pkg/eth"
+	ethServerShared "github.com/vulcanize/ipld-eth-server/v4/pkg/shared"
+
+	"github.com/vulcanize/ipld-eth-db-validator/pkg/prom"
 )
 
 var (
 	big8  = big.NewInt(8)
 	big32 = big.NewInt(32)
+
+	ReferentialIntegrityErr = "referential integrity check failed at block %d, entry for %s not found"
+	EntryNotFoundErr        = "entry for %s not found"
 )
 
 type service struct {
 	db              *sqlx.DB
 	blockNum, trail uint64
 	sleepInterval   uint
-	logger          *log.Logger
 	chainCfg        *params.ChainConfig
-	quitChan        chan bool
+
-	progressChan    chan uint64
+	stateDiffMissingBlock bool
+	stateDiffTimeout      uint
+	ethClient             *rpc.Client
+
+	quitChan     chan bool
+	progressChan chan uint64
 }
 
 func NewService(cfg *Config, progressChan chan uint64) *service {
 	return &service{
-		db:            cfg.DB,
+		db:                    cfg.DB,
-		blockNum:      cfg.BlockNum,
+		blockNum:              cfg.BlockNum,
-		trail:         cfg.Trail,
+		trail:                 cfg.Trail,
-		sleepInterval: cfg.SleepInterval,
+		sleepInterval:         cfg.SleepInterval,
-		logger:        log.New(),
+		chainCfg:              cfg.ChainCfg,
-		chainCfg:      cfg.ChainCfg,
+		stateDiffMissingBlock: cfg.StateDiffMissingBlock,
-		quitChan:      make(chan bool),
+		stateDiffTimeout:      cfg.StateDiffTimeout,
-		progressChan:  progressChan,
+		ethClient:             cfg.Client,
+		quitChan:              make(chan bool),
+		progressChan:          progressChan,
 	}
 }
 
@@ -88,7 +118,7 @@ func (s *service) Start(ctx context.Context, wg *sync.WaitGroup) {
 
 	api, err := EthAPI(ctx, s.db, s.chainCfg)
 	if err != nil {
-		s.logger.Fatal(err)
+		log.Fatal(err)
 		return
 	}
 
@@ -97,7 +127,7 @@ func (s *service) Start(ctx context.Context, wg *sync.WaitGroup) {
 	for {
 		select {
 		case <-s.quitChan:
-			s.logger.Infof("last validated block %v", idxBlockNum-1)
+			log.Infof("last validated block %v", idxBlockNum-1)
 			if s.progressChan != nil {
 				close(s.progressChan)
 			}
@@ -105,17 +135,19 @@ func (s *service) Start(ctx context.Context, wg *sync.WaitGroup) {
 		default:
 			idxBlockNum, err = s.Validate(ctx, api, idxBlockNum)
 			if err != nil {
-				s.logger.Infof("last validated block %v", idxBlockNum-1)
+				log.Infof("last validated block %v", idxBlockNum-1)
-				s.logger.Fatal(err)
+				log.Fatal(err)
 				return
 			}
+
+			prom.SetLastValidatedBlock(float64(idxBlockNum))
 		}
 	}
 }
 
 // Stop is used to gracefully stop the service
 func (s *service) Stop() {
-	s.logger.Info("stopping ipld-eth-db-validator process")
+	log.Info("stopping ipld-eth-db-validator process")
 	close(s.quitChan)
 }
 
@@ -127,13 +159,33 @@ func (s *service) Validate(ctx context.Context, api *ipldEth.PublicEthAPI, idxBl
 
 	// Check if it block at height idxBlockNum can be validated
 	if idxBlockNum <= headBlockNum-s.trail {
-		err = ValidateBlock(ctx, api, idxBlockNum)
+		blockToBeValidated, err := api.B.BlockByNumber(ctx, rpc.BlockNumber(idxBlockNum))
 		if err != nil {
-			s.logger.Errorf("failed to verify state root at block %d", idxBlockNum)
+			log.Errorf("failed to fetch block at height %d", idxBlockNum)
 			return idxBlockNum, err
 		}
 
-		s.logger.Infof("state root verified for block %d", idxBlockNum)
+		// Make a writeStateDiffAt call if block not found in the db
+		if blockToBeValidated == nil {
+			err = s.writeStateDiffAt(idxBlockNum)
+			return idxBlockNum, err
+		}
+
+		err = ValidateBlock(blockToBeValidated, api.B, idxBlockNum)
+		if err != nil {
+			log.Errorf("failed to verify state root at block %d", idxBlockNum)
+			return idxBlockNum, err
+		}
+
+		log.Infof("state root verified for block %d", idxBlockNum)
+
+		err = ValidateReferentialIntegrity(s.db, idxBlockNum)
+		if err != nil {
+			log.Errorf("failed to verify referential integrity at block %d", idxBlockNum)
+			return idxBlockNum, err
+		}
+		log.Infof("referential integrity verified for block %d", idxBlockNum)
+
 		if s.progressChan != nil {
 			s.progressChan <- idxBlockNum
 		}
@@ -147,14 +199,37 @@ func (s *service) Validate(ctx context.Context, api *ipldEth.PublicEthAPI, idxBl
 	return idxBlockNum, nil
 }
 
-// ValidateBlock validates block at the given height
+// writeStateDiffAt calls out to a statediffing geth client to fill in a gap in the index
-func ValidateBlock(ctx context.Context, api *ipldEth.PublicEthAPI, blockNumber uint64) error {
+func (s *service) writeStateDiffAt(height uint64) error {
-	blockToBeValidated, err := api.B.BlockByNumber(ctx, rpc.BlockNumber(blockNumber))
+	if !s.stateDiffMissingBlock {
-	if err != nil {
+		return nil
+	}
+
+	var data json.RawMessage
+	params := statediff.Params{
+		IntermediateStateNodes:   true,
+		IntermediateStorageNodes: true,
+		IncludeBlock:             true,
+		IncludeReceipts:          true,
+		IncludeTD:                true,
+		IncludeCode:              true,
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Duration(s.stateDiffTimeout*uint(time.Second)))
+	defer cancel()
+
+	log.Warnf("making writeStateDiffAt call at height %d", height)
+	if err := s.ethClient.CallContext(ctx, &data, "statediff_writeStateDiffAt", height, params); err != nil {
+		log.Errorf("writeStateDiffAt %d faild with err %s", height, err.Error())
 		return err
 	}
 
-	stateDB, err := applyTransaction(blockToBeValidated, api.B)
+	return nil
+}
+
+// ValidateBlock validates block at the given height
+func ValidateBlock(blockToBeValidated *types.Block, b *ipldEth.Backend, blockNumber uint64) error {
+	stateDB, err := applyTransaction(blockToBeValidated, b)
 	if err != nil {
 		return err
 	}

scripts/run_integration_test.sh

@@ -1,3 +1,5 @@
+#!/bin/bash
+
 set -e
 set -o xtrace
 

scripts/run_unit_test.sh

@@ -1,9 +1,17 @@
+#!/bin/bash
+
+set -e
+
 # Clear up existing docker images and volume.
 docker-compose down --remove-orphans --volumes
 
-docker-compose -f docker-compose.yml up -d ipld-eth-db
+# Spin up TimescaleDB
-sleep 10
+docker-compose -f docker-compose.yml up -d migrations ipld-eth-db
+sleep 45
 
+# Run unit tests
+go clean -testcache
 PGPASSWORD=password DATABASE_USER=vdbm DATABASE_PORT=8077 DATABASE_PASSWORD=password DATABASE_HOSTNAME=127.0.0.1 DATABASE_NAME=vulcanize_testing make test
 
+# Clean up
 docker-compose down --remove-orphans --volumes

test/README.md

@@ -1,23 +1,30 @@
-# Test Insructions
+# Test Instructions
 
 ## Setup
 
 - For running integration tests:
 
-  - Clone [stack-orchestrator](https://github.com/vulcanize/stack-orchestrator) and [go-ethereum](https://github.com/vulcanize/go-ethereum) repositories.
+  - Clone [stack-orchestrator](https://github.com/vulcanize/stack-orchestrator), [go-ethereum](https://github.com/vulcanize/go-ethereum) and [ipld-eth-db](https://github.com/vulcanize/ipld-eth-db) repositories.
 
-  - Checkout [v3 release](https://github.com/vulcanize/go-ethereum/releases/tag/v1.10.18-statediff-3.2.2) in go-ethereum repo.
+  - Checkout [v4 release](https://github.com/vulcanize/ipld-eth-db/releases/tag/v4.2.1-alpha) in ipld-eth-db repo.
+
+    ```bash
+    # In ipld-eth-db repo.
+    git checkout v4.2.1-alpha
+    ```
+
+  - Checkout [v4 release](https://github.com/vulcanize/go-ethereum/releases/tag/v1.10.21-statediff-4.1.2-alpha) in go-ethereum repo.
 
     ```bash
     # In go-ethereum repo.
-    git checkout v1.10.18-statediff-3.2.2
+    git checkout v1.10.21-statediff-4.1.2-alpha
     ```
 
   - Checkout working commit in stack-orchestrator repo.
 
     ```bash
     # In stack-orchestrator repo.
-    git checkout main
+    git checkout f2fd766f5400fcb9eb47b50675d2e3b1f2753702
     ```
 
 ## Run
@@ -48,12 +55,16 @@
       ```bash
       #!/bin/bash
 
+      # Path to ipld-eth-server repo.
+      vulcanize_ipld_eth_db=~/ipld-eth-db/
+
       # Path to go-ethereum repo.
       vulcanize_go_ethereum=~/go-ethereum
 
       # Path to contract folder.
       vulcanize_test_contract=~/ipld-eth-db-validator/test/contract
 
+      genesis_file_path='start-up-files/go-ethereum/genesis.json'
       db_write=true
       ```
 
@@ -65,7 +76,7 @@
 
       ./wrapper.sh \
       -e docker \
-      -d ../docker/latest/docker-compose-db.yml \
+      -d ../docker/local/docker-compose-db-sharding.yml \
       -d ../docker/local/docker-compose-go-ethereum.yml \
       -d ../docker/local/docker-compose-contract.yml \
       -v remove \

test/helper.go

@@ -5,7 +5,7 @@ import (
 	"fmt"
 	"net/http"
 
-	ethServerIntegration "github.com/vulcanize/ipld-eth-server/v3/test"
+	ethServerIntegration "github.com/vulcanize/ipld-eth-server/v4/test"
 )
 
 type PutResult struct {

test/integration_test.go

@@ -11,8 +11,8 @@ import (
 	"github.com/vulcanize/ipld-eth-db-validator/pkg/validator"
 	integration "github.com/vulcanize/ipld-eth-db-validator/test"
 
-	"github.com/vulcanize/ipld-eth-server/v3/pkg/shared"
+	"github.com/vulcanize/ipld-eth-server/v4/pkg/shared"
-	ethServerIntegration "github.com/vulcanize/ipld-eth-server/v3/test"
+	ethServerIntegration "github.com/vulcanize/ipld-eth-server/v4/test"
 )
 
 const (

validator_test/chain_maker.go

@@ -2,6 +2,7 @@ package validator_test
 
 import (
 	"crypto/ecdsa"
+	"github.com/ethereum/go-ethereum/statediff/test_helpers"
 	"math/big"
 
 	"github.com/ethereum/go-ethereum/common"
@@ -23,7 +24,7 @@ var (
 	TestBankKey, _  = crypto.HexToECDSA("b71c71a67e1177ad4e901695e1b4b9ee17ae16c6668d313eac2f96dbcda3f291")
 	TestBankAddress = crypto.PubkeyToAddress(TestBankKey.PublicKey) //0x71562b71999873DB5b286dF957af199Ec94617F7
 	TestBankFunds   = big.NewInt(100000000)
-	Genesis         = core.GenesisBlockForTesting(Testdb, TestBankAddress, TestBankFunds)
+	Genesis         = test_helpers.GenesisBlockForTesting(Testdb, TestBankAddress, TestBankFunds)
 
 	Account1Key, _       = crypto.HexToECDSA("8a1f9a8f95be41cd7ccb6168179afb4504aefe388d1e14474d32c45c72ce7b7a")
 	Account2Key, _       = crypto.HexToECDSA("49a7b37aa6f6645917e7b807e9d1c00d4fa71f18343b0d4122a4d2df64dd6fee")

validator_test/ref_integrity_test.go

@@ -0,0 +1,334 @@
+package validator_test
+
+import (
+	"context"
+	"fmt"
+
+	"github.com/ethereum/go-ethereum/params"
+	"github.com/ethereum/go-ethereum/statediff/indexer/interfaces"
+	"github.com/ethereum/go-ethereum/statediff/indexer/mocks"
+	"github.com/jmoiron/sqlx"
+	. "github.com/onsi/ginkgo"
+	. "github.com/onsi/gomega"
+
+	"github.com/vulcanize/ipld-eth-db-validator/pkg/validator"
+	"github.com/vulcanize/ipld-eth-server/v4/pkg/eth/test_helpers"
+	"github.com/vulcanize/ipld-eth-server/v4/pkg/shared"
+)
+
+var _ = Describe("RefIntegrity", func() {
+	var (
+		ctx = context.Background()
+
+		db          *sqlx.DB
+		diffIndexer interfaces.StateDiffIndexer
+	)
+
+	BeforeEach(func() {
+		db = shared.SetupDB()
+		diffIndexer = shared.SetupTestStateDiffIndexer(ctx, params.TestChainConfig, test_helpers.Genesis.Hash())
+	})
+
+	AfterEach(func() {
+		shared.TearDownDB(db)
+	})
+
+	Describe("ValidateHeaderCIDsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of header_cids table", func() {
+			err := validator.ValidateHeaderCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding header IPFS block entry not found", func() {
+			err := deleteEntriesFrom(db, "public.blocks")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateHeaderCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "public.blocks"))
+		})
+	})
+
+	Describe("ValidateUncleCIDsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of uncle_cids table", func() {
+			err := validator.ValidateUncleCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding header_cid entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.header_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateUncleCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.header_cids"))
+		})
+
+		It("Throws an error if corresponding uncle IPFS block entry not found", func() {
+			err := deleteEntriesFrom(db, "public.blocks")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateUncleCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "public.blocks"))
+		})
+	})
+
+	Describe("ValidateTransactionCIDsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of transaction_cids table", func() {
+			err := validator.ValidateTransactionCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding header_cid entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.header_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateTransactionCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.header_cids"))
+		})
+
+		It("Throws an error if corresponding transaction IPFS block entry not found", func() {
+			err := deleteEntriesFrom(db, "public.blocks")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateTransactionCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "public.blocks"))
+		})
+	})
+
+	Describe("ValidateReceiptCIDsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of receipt_cids table", func() {
+			err := validator.ValidateReceiptCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding transaction_cids entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.transaction_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateReceiptCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.transaction_cids"))
+		})
+
+		It("Throws an error if corresponding receipt IPFS block entry not found", func() {
+			err := deleteEntriesFrom(db, "public.blocks")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateReceiptCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "public.blocks"))
+		})
+	})
+
+	Describe("ValidateStateCIDsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			for _, node := range test_helpers.MockStateNodes {
+				err = diffIndexer.PushStateNode(tx, node, test_helpers.MockBlock.Hash().String())
+				Expect(err).ToNot(HaveOccurred())
+			}
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of state_cids table", func() {
+			err := validator.ValidateStateCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding header_cids entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.header_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateStateCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.header_cids"))
+		})
+
+		It("Throws an error if corresponding state IPFS block entry not found", func() {
+			err := deleteEntriesFrom(db, "public.blocks")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateStateCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "public.blocks"))
+		})
+	})
+
+	Describe("ValidateStorageCIDsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			for _, node := range test_helpers.MockStateNodes {
+				err = diffIndexer.PushStateNode(tx, node, test_helpers.MockBlock.Hash().String())
+				Expect(err).ToNot(HaveOccurred())
+			}
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of storage_cids table", func() {
+			err := validator.ValidateStorageCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding state_cids entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.state_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateStorageCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.state_cids"))
+		})
+
+		It("Throws an error if corresponding storage IPFS block entry not found", func() {
+			err := deleteEntriesFrom(db, "public.blocks")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateStorageCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "public.blocks"))
+		})
+	})
+
+	Describe("ValidateStateAccountsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			for _, node := range test_helpers.MockStateNodes {
+				err = diffIndexer.PushStateNode(tx, node, test_helpers.MockBlock.Hash().String())
+				Expect(err).ToNot(HaveOccurred())
+			}
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of state_accounts table", func() {
+			err := validator.ValidateStateAccountsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding state_cids entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.state_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateStateAccountsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.state_cids"))
+		})
+	})
+
+	Describe("ValidateAccessListElementsRef", func() {
+		BeforeEach(func() {
+			indexAndPublisher := shared.SetupTestStateDiffIndexer(ctx, mocks.TestConfig, test_helpers.Genesis.Hash())
+
+			tx, err := indexAndPublisher.PushBlock(mocks.MockBlock, mocks.MockReceipts, mocks.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of access_list_elements table", func() {
+			err := validator.ValidateAccessListElementsRef(db, mocks.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding transaction_cids entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.transaction_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateAccessListElementsRef(db, mocks.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.transaction_cids"))
+		})
+	})
+
+	Describe("ValidateLogCIDsRef", func() {
+		BeforeEach(func() {
+			tx, err := diffIndexer.PushBlock(test_helpers.MockBlock, test_helpers.MockReceipts, test_helpers.MockBlock.Difficulty())
+			Expect(err).ToNot(HaveOccurred())
+
+			for _, node := range test_helpers.MockStateNodes {
+				err = diffIndexer.PushStateNode(tx, node, test_helpers.MockBlock.Hash().String())
+				Expect(err).ToNot(HaveOccurred())
+			}
+
+			err = tx.Submit(err)
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Validates referential integrity of log_cids table", func() {
+			err := validator.ValidateLogCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).ToNot(HaveOccurred())
+		})
+
+		It("Throws an error if corresponding receipt_cids entry not found", func() {
+			err := deleteEntriesFrom(db, "eth.receipt_cids")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateLogCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "eth.receipt_cids"))
+		})
+
+		It("Throws an error if corresponding log IPFS block entry not found", func() {
+			err := deleteEntriesFrom(db, "public.blocks")
+			Expect(err).ToNot(HaveOccurred())
+
+			err = validator.ValidateLogCIDsRef(db, test_helpers.MockBlock.NumberU64())
+			Expect(err).To(HaveOccurred())
+			Expect(err.Error()).To(ContainSubstring(validator.EntryNotFoundErr, "public.blocks"))
+		})
+	})
+
+})
+
+func deleteEntriesFrom(db *sqlx.DB, tableName string) error {
+	pgStr := "DELETE FROM %s"
+	_, err := db.Exec(fmt.Sprintf(pgStr, tableName))
+	return err
+}

validator_test/validator_suite_test.go

@@ -1,4 +1,4 @@
-package validator_test_test
+package validator_test
 
 import (
 	"io/ioutil"

validator_test/validator_test.go

@@ -7,13 +7,14 @@ import (
 	"github.com/ethereum/go-ethereum/common"
 	"github.com/ethereum/go-ethereum/core"
 	"github.com/ethereum/go-ethereum/core/types"
+	"github.com/ethereum/go-ethereum/rpc"
 	"github.com/ethereum/go-ethereum/statediff"
 	sdtypes "github.com/ethereum/go-ethereum/statediff/types"
 	"github.com/jmoiron/sqlx"
 	. "github.com/onsi/ginkgo"
 	. "github.com/onsi/gomega"
-	"github.com/vulcanize/ipld-eth-server/v3/pkg/eth/test_helpers"
+	"github.com/vulcanize/ipld-eth-server/v4/pkg/eth/test_helpers"
-	"github.com/vulcanize/ipld-eth-server/v3/pkg/shared"
+	"github.com/vulcanize/ipld-eth-server/v4/pkg/shared"
 
 	"github.com/vulcanize/ipld-eth-db-validator/pkg/validator"
 	"github.com/vulcanize/ipld-eth-db-validator/validator_test"
@@ -118,7 +119,14 @@ var _ = Describe("eth state reading tests", func() {
 			Expect(err).ToNot(HaveOccurred())
 
 			for i := uint64(blockHeight); i <= chainLength-trail; i++ {
-				err = validator.ValidateBlock(context.Background(), api, i)
+				blockToBeValidated, err := api.B.BlockByNumber(context.Background(), rpc.BlockNumber(i))
+				Expect(err).ToNot(HaveOccurred())
+				Expect(blockToBeValidated).ToNot(BeNil())
+
+				err = validator.ValidateBlock(blockToBeValidated, api.B, i)
+				Expect(err).ToNot(HaveOccurred())
+
+				err = validator.ValidateReferentialIntegrity(db, i)
 				Expect(err).ToNot(HaveOccurred())
 			}
 		})