Compare commits

..
19 Commits
Author SHA1 Message Date
dboreham 46cd8b1834 Merge pull request #103 from cerc-io/dboreham/prerun-workers
use workers in prerun mode
2022-09-22 07:37:38 -06:00
dboreham c0cd87ba6a Make doc consistent 2022-09-22 07:26:32 -06:00
prathamesh0 2db235f244 Add helper scripts for processing and importing statediffed data (#105)
* Add helper scripts for processing and importing statediffed data

* Add instructions to use the helper scripts

* Update scripts to use arrays

* Update README with bad row output example

* Remove delimiter option from xargs command
2022-09-22 13:52:47 +05:30
dboreham a827c4a36b Merge branch 'v4' into dboreham/prerun-workers 2022-09-21 14:04:46 -06:00
dboreham 14b9c169bc Add viper boiler plate 2022-09-21 14:00:45 -06:00
dboreham a2772762e1 Make pprof configurable, remove todos 2022-09-21 13:33:15 -06:00
dboreham b1440d9673 Fix off by one error 2022-09-21 13:06:41 -06:00
Michael Shaw 67d8bced4f one more reference changed to git.vdb.to 2022-09-21 13:27:05 -04:00
Michael Shaw 12f4810ced missed Makefile update for cerc-io 2022-09-21 11:55:17 -04:00
Michael Shaw 7a8d38c955 indentation problem in yml 2022-09-21 11:24:43 -04:00
Michael Shaw d09cd0afe6 update tagging and push to git.vdb.to registry 2022-09-21 11:13:23 -04:00
Michael bcca82eaa3 Cerc refactor (#104)
* cerc refactor waiting on unpublished dependencies

* updated go.mod for published dependencies in cerc-io refactoring
2022-09-20 14:00:10 -04:00
Michael dad77b561d Merge pull request #102 from vulcanize/rebase-1.10.23-wip
update for geth 1.10.23
2022-09-02 16:16:34 -04:00
Michael Shaw c939822a95 update for geth 1.10.23 2022-09-02 15:56:56 -04:00
dboreham 6d103cb1f1 Add some logging 2022-09-02 10:51:13 -06:00
dboreham 99f84b6fe6 Comment 2022-09-01 23:43:38 -06:00
dboreham 5b7f5feb1b Enable pprof 2022-09-01 23:42:55 -06:00
dboreham 7f8885f044 Add comment 2022-08-31 07:54:16 -06:00
dboreham d235f3b84c Initial version of parallel workers for prerun-only mode 2022-08-30 22:31:54 -06:00
23 changed files with 480 additions and 148 deletions
+33 -29
View File
@@ -32,38 +32,42 @@ jobs:
needs: run-tests
steps:
- uses: actions/checkout@v2
- name: Get the version
id: vars
run: echo ::set-output name=sha::$(echo ${GITHUB_SHA:0:7})
- name: Run docker build
run: make docker-build
- name: Tag docker image
run: docker tag vulcanize/eth-statediff-service docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
- name: Docker Login
run: echo ${{ secrets.GITHUB_TOKEN }} | docker login https://docker.pkg.github.com -u vulcanize --password-stdin
- name: Docker Push
run: docker push docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
push_to_registries:
name: Push Docker image to Docker Hub
runs-on: ubuntu-latest
if: |
always() &&
(needs.build.result == 'success') &&
github.event_name == 'release'
needs: build
steps:
- name: Get the version
id: vars
run: |
echo ::set-output name=sha::$(echo ${GITHUB_SHA:0:7})
echo ::set-output name=tag::$(echo ${GITHUB_REF#refs/tags/})
- name: Docker Login to Github Registry
run: echo ${{ secrets.GITHUB_TOKEN }} | docker login https://docker.pkg.github.com -u vulcanize --password-stdin
- name: Docker Pull
run: docker pull docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
- name: Docker Login to Docker Registry
run: echo ${{ secrets.VULCANIZEJENKINS_PAT }} | docker login -u vulcanizejenkins --password-stdin
- name: Run docker build
run: make docker-build
- name: Tag docker image
run: docker tag docker.pkg.github.com/vulcanize/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}} vulcanize/eth-statediff-service:${{steps.vars.outputs.tag}}
- name: Docker Push to Docker Hub
run: docker push vulcanize/eth-statediff-service:${{steps.vars.outputs.tag}}
run: docker tag cerc-io/eth-statediff-service git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
- name: Tag docker image TAG
run: docker tag git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}} git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.tag}}
- name: Docker Login
run: echo ${{ secrets.GITEA_TOKEN }} | docker login https://git.vdb.to -u cerccicd --password-stdin
- name: Docker Push
run: docker push git.vdb.to/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
# push_to_registries:
# name: Push Docker image to Docker Hub
# runs-on: ubuntu-latest
# if: |
# always() &&
# (needs.build.result == 'success') &&
# github.event_name == 'release'
# needs: build
# steps:
# - name: Get the version
# id: vars
# run: |
# echo ::set-output name=sha::$(echo ${GITHUB_SHA:0:7})
# echo ::set-output name=tag::$(echo ${GITHUB_REF#refs/tags/})
# - name: Docker Login to Github Registry
# run: echo ${{ secrets.GITHUB_TOKEN }} | docker login https://docker.pkg.github.com -u vulcanize --password-stdin
# - name: Docker Pull
# run: docker pull docker.pkg.github.com/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}}
# - name: Docker Login to Docker Registry
# run: echo ${{ secrets.VULCANIZEJENKINS_PAT }} | docker login -u vulcanizejenkins --password-stdin
# - name: Tag docker image
# run: docker tag docker.pkg.github.com/cerc-io/eth-statediff-service/eth-statediff-service:${{steps.vars.outputs.sha}} cerc-io/eth-statediff-service:${{steps.vars.outputs.tag}}
# - name: Docker Push to Docker Hub
# run: docker push cerc-io/eth-statediff-service:${{steps.vars.outputs.tag}}
+7 -7
View File
@@ -5,10 +5,10 @@ RUN apk --update --no-cache add make git g++ linux-headers
RUN apk add busybox-extras
# Get and build ipfs-blockchain-watcher
ADD . /go/src/github.com/vulcanize/eth-statediff-service
#RUN git clone https://github.com/vulcanize/eth-statediff-service.git /go/src/github.com/vulcanize/eth-statediff-service
ADD . /go/src/github.com/cerc-io/eth-statediff-service
#RUN git clone https://github.com/cerc-io/eth-statediff-service.git /go/src/github.com/vulcanize/eth-statediff-service
WORKDIR /go/src/github.com/vulcanize/eth-statediff-service
WORKDIR /go/src/github.com/cerc-io/eth-statediff-service
RUN GO111MODULE=on GCO_ENABLED=0 GOOS=linux go build -a -installsuffix cgo -ldflags '-extldflags "-static"' -o eth-statediff-service .
# app container
@@ -27,12 +27,12 @@ USER $USER
# chown first so dir is writable
# note: using $USER is merged, but not in the stable release yet
COPY --chown=5000:5000 --from=builder /go/src/github.com/vulcanize/eth-statediff-service/$CONFIG_FILE config.toml
COPY --chown=5000:5000 --from=builder /go/src/github.com/vulcanize/eth-statediff-service/startup_script.sh .
COPY --chown=5000:5000 --from=builder /go/src/github.com/vulcanize/eth-statediff-service/environments environments
COPY --chown=5000:5000 --from=builder /go/src/github.com/cerc-io/eth-statediff-service/$CONFIG_FILE config.toml
COPY --chown=5000:5000 --from=builder /go/src/github.com/cerc-io/eth-statediff-service/startup_script.sh .
COPY --chown=5000:5000 --from=builder /go/src/github.com/cerc-io/eth-statediff-service/environments environments
# keep binaries immutable
COPY --from=builder /go/src/github.com/vulcanize/eth-statediff-service/eth-statediff-service eth-statediff-service
COPY --from=builder /go/src/github.com/cerc-io/eth-statediff-service/eth-statediff-service eth-statediff-service
EXPOSE $EXPOSE_PORT
+2 -2
View File
@@ -1,10 +1,10 @@
## Build docker image
.PHONY: docker-build
docker-build:
docker build -t vulcanize/eth-statediff-service .
docker build -t cerc-io/eth-statediff-service .
.PHONY: test
test: | $(GOOSE)
test:
go test -p 1 ./pkg/... -v
build:
+39 -67
View File
@@ -8,7 +8,7 @@ Purpose:
Stand up a statediffing service directly on top of a go-ethereum LevelDB instance.
This service can serve historical state data over the same rpc interface as
[statediffing geth](https://github.com/vulcanize/go-ethereum) without needing to run a full node.
[statediffing geth](https://github.com/cerc-io/go-ethereum) without needing to run a full node.
## Setup
@@ -47,7 +47,8 @@ An example config file:
trieWorkers = 4 # STATEDIFF_TRIE_WORKERS
[prerun]
only = false # PRERUN_ONLY
only = false # PRERUN_ONLY
parallel = true # PRERUN_PARALLEL
# to perform prerun in a specific range (optional)
start = 0 # PRERUN_RANGE_START
@@ -122,6 +123,9 @@ An example config file:
# path to custom chain config file (optional)
# keep chainID same as that in chain config file
chainConfig = "./chain.json" # ETH_CHAIN_CONFIG
[debug]
pprof = false # DEBUG_PPROF
```
### Local Setup
@@ -216,6 +220,8 @@ An example config file:
* When `eth-statediff-service` is run in file mode (`database.type`) the output is in form of a SQL file or multiple CSV files.
### SQL
* Assuming the output files are located in host's `./output_dir` directory.
* Create a directory to store post-processed output:
@@ -224,7 +230,11 @@ An example config file:
mkdir -p output_dir/processed_output
```
### SQL
* (Optional) Get row counts in the output:
```bash
wc -l output_dir/statediff.sql > output_stats.txt
```
* De-duplicate data:
@@ -242,86 +252,48 @@ An example config file:
### CSV
* De-duplicate data and copy to post-processed output directory:
* Create an env file with the required variables. Refer [.sample.env](./scripts/.sample.env).
* (Optional) Get row counts in the output:
```bash
# public.blocks
sort -u output_dir/public.blocks.csv -o output_dir/processed_output/deduped-public.blocks.csv
# eth.header_cids
sort -u output_dir/eth.header_cids.csv -o output_dir/processed_output/deduped-eth.header_cids.csv
# eth.uncle_cids
sort -u output_dir/eth.uncle_cids.csv -o output_dir/processed_output/deduped-eth.uncle_cids.csv
# eth.transaction_cids
sort -u output_dir/eth.transaction_cids.csv -o output_dir/processed_output/deduped-eth.transaction_cids.csv
# eth.access_list_elements
sort -u output_dir/eth.access_list_elements.csv -o output_dir/processed_output/deduped-eth.access_list_elements.csv
# eth.receipt_cids
sort -u output_dir/eth.receipt_cids.csv -o output_dir/processed_output/deduped-eth.receipt_cids.csv
# eth.log_cids
sort -u output_dir/eth.log_cids.csv -o output_dir/processed_output/deduped-eth.log_cids.csv
# eth.state_cids
sort -u output_dir/eth.state_cids.csv -o output_dir/processed_output/deduped-eth.state_cids.csv
# eth.storage_cids
sort -u output_dir/eth.storage_cids.csv -o output_dir/processed_output/deduped-eth.storage_cids.csv
# eth.state_accounts
sort -u output_dir/eth.state_accounts.csv -o output_dir/processed_output/deduped-eth.state_accounts.csv
# public.nodes
cp output_dir/public.nodes.csv output_dir/processed_output/public.nodes.csv
./scripts/count-lines.sh <ENV_FILE_PATH>
```
* Copy over the post-processed output files to the DB server (say in `/output_dir`).
* Start `psql` to run the import commands:
* De-duplicate data:
```bash
psql -U <DATABASE_USER> -h <DATABASE_HOSTNAME> -p <DATABASE_PORT> <DATABASE_NAME>
./scripts/dedup.sh <ENV_FILE_PATH>
```
* Run the following to import data:
* Perform column checks:
```bash
# public.nodes
COPY public.nodes FROM '/output_dir/processed_output/public.nodes.csv' CSV;
./scripts/check-columns.sh <ENV_FILE_PATH>
```
# public.nodes
COPY public.blocks FROM '/output_dir/processed_output/deduped-public.blocks.csv' CSV;
Check the output logs for any rows detected with unexpected number of columns.
# eth.header_cids
COPY eth.header_cids FROM '/output_dir/processed_output/deduped-eth.header_cids.csv' CSV;
Example:
# eth.uncle_cids
COPY eth.uncle_cids FROM '/output_dir/processed_output/deduped-eth.uncle_cids.csv' CSV;
```bash
# log
eth.header_cids
Start: Wednesday 21 September 2022 06:00:38 PM IST
Time taken: 00:00:05
End: Wednesday 21 September 2022 06:00:43 PM IST
Total bad rows: 1 ./check-columns/eth.header_cids.txt
# eth.transaction_cids
COPY eth.transaction_cids FROM '/output_dir/processed_output/deduped-eth.transaction_cids.csv' CSV FORCE NOT NULL dst;
# bad row output
# line number, num. of columns, data
23 17 22,xxxxxx,0x07f5ea5c94aa8dea60b28f6b6315d92f2b6d78ca4b74ea409adeb191b5a114f2,0x5918487321aa57dd0c50977856c6231e7c4ee79e95b694c7c8830227d77a1ecc,bagiacgzaa726uxeuvkg6uyfsr5vwgfozf4vw26gkjn2ouqe232yzdnnbctza,45,geth,0,0xad8fa8df61b98dbda7acd6ca76d5ce4cbba663d5f608cc940957adcdb94cee8d,0xc621412320a20b4aaff5363bdf063b9d13e394ef82e55689ab703aae5db08e26,0x71ec1c7d81269ce115be81c81f13e1cc2601c292a7f20440a77257ecfdc69940,0x1dcc4de8dec75d7aab85b567b6ccd41ad312451b948a7413f0a142fd40d49347,\x2000000000000000000000000000000000000000000000000000020000000000000000000000000000000000000000000000000000000000000000000,1658408419,/blocks/DMQAP5PKLSKKVDPKMCZI623DCXMS6K3NPDFEW5HKICNN5MMRWWQRJ4Q,1,0x0000000000000000000000000000000000000000
```
# eth.access_list_elements
COPY eth.access_list_elements FROM '/output_dir/processed_output/deduped-eth.access_list_elements.csv' CSV;
* Import data using `timescaledb-parallel-copy`:
(requires [`timescaledb-parallel-copy`](https://github.com/timescale/timescaledb-parallel-copy) installation; readily comes with TimescaleDB docker image)
# eth.receipt_cids
COPY eth.receipt_cids FROM '/output_dir/processed_output/deduped-eth.receipt_cids.csv' CSV FORCE NOT NULL post_state, contract, contract_hash;
# eth.log_cids
COPY eth.log_cids FROM '/output_dir/processed_output/deduped-eth.log_cids.csv' CSV FORCE NOT NULL topic0, topic1, topic2, topic3;
# eth.state_cids
COPY eth.state_cids FROM '/output_dir/processed_output/deduped-eth.state_cids.csv' CSV FORCE NOT NULL state_leaf_key;
# eth.storage_cids
COPY eth.storage_cids FROM '/output_dir/processed_output/deduped-eth.storage_cids.csv' CSV FORCE NOT NULL storage_leaf_key;
# eth.state_accounts
COPY eth.state_accounts FROM '/output_dir/processed_output/deduped-eth.state_accounts.csv' CSV;
```bash
./scripts/timescaledb-import.sh <ENV_FILE_PATH>
```
* NOTE: `COPY` command on CSVs inserts empty strings as `NULL` in the DB. Passing `FORCE_NOT_NULL <COLUMN_NAME>` forces it to insert empty strings instead. This is required to maintain compatibility of the imported statediff data with the data generated in `postgres` mode. Reference: https://www.postgresql.org/docs/14/sql-copy.html
+6
View File
@@ -50,6 +50,7 @@ const (
PROM_DB_STATS = "PROM_DB_STATS"
PRERUN_ONLY = "PRERUN_ONLY"
PRERUN_PARALLEL = "PRERUN_PARALLEL"
PRERUN_RANGE_START = "PRERUN_RANGE_START"
PRERUN_RANGE_STOP = "PRERUN_RANGE_STOP"
PRERUN_INTERMEDIATE_STATE_NODES = "PRERUN_INTERMEDIATE_STATE_NODES"
@@ -81,6 +82,8 @@ const (
DATABASE_MAX_CONN_LIFETIME = "DATABASE_MAX_CONN_LIFETIME"
DATABASE_CONN_TIMEOUT = "DATABSE_CONN_TIMEOUT"
DATABASE_MAX_CONN_IDLE_TIME = "DATABASE_MAX_CONN_IDLE_TIME"
DEBUG_PPROF = "DEBUG_PPROF"
)
// Bind env vars for eth node and DB configuration
@@ -135,6 +138,7 @@ func init() {
viper.BindEnv("statediff.prerun", STATEDIFF_PRERUN)
viper.BindEnv("prerun.only", PRERUN_ONLY)
viper.BindEnv("prerun.parallel", PRERUN_PARALLEL)
viper.BindEnv("prerun.start", PRERUN_RANGE_START)
viper.BindEnv("prerun.stop", PRERUN_RANGE_STOP)
viper.BindEnv("prerun.params.intermediateStateNodes", PRERUN_INTERMEDIATE_STATE_NODES)
@@ -146,4 +150,6 @@ func init() {
viper.BindEnv("log.level", LOG_LEVEL)
viper.BindEnv("log.file", LOG_FILE_PATH)
viper.BindEnv("debug.pprof", DEBUG_PPROF)
}
+4 -1
View File
@@ -34,7 +34,7 @@ import (
"github.com/spf13/cobra"
"github.com/spf13/viper"
"github.com/vulcanize/eth-statediff-service/pkg/prom"
"github.com/cerc-io/eth-statediff-service/pkg/prom"
)
var (
@@ -221,6 +221,7 @@ func init() {
viper.BindPFlag("prom.metrics", rootCmd.PersistentFlags().Lookup("prom-metrics"))
viper.BindPFlag("prerun.only", rootCmd.PersistentFlags().Lookup("prerun-only"))
viper.BindPFlag("prerun.parallel", rootCmd.PersistentFlags().Lookup("prerun-parallel"))
viper.BindPFlag("prerun.start", rootCmd.PersistentFlags().Lookup("prerun-start"))
viper.BindPFlag("prerun.stop", rootCmd.PersistentFlags().Lookup("prerun-stop"))
viper.BindPFlag("prerun.params.intermediateStateNodes", rootCmd.PersistentFlags().Lookup("prerun-intermediate-state-nodes"))
@@ -230,6 +231,8 @@ func init() {
viper.BindPFlag("prerun.params.includeTD", rootCmd.PersistentFlags().Lookup("prerun-include-td"))
viper.BindPFlag("prerun.params.includeCode", rootCmd.PersistentFlags().Lookup("prerun-include-code"))
viper.BindPFlag("debug.pprof", rootCmd.PersistentFlags().Lookup("debug-pprof"))
rand.Seed(time.Now().UnixNano())
}
+27 -3
View File
@@ -16,8 +16,11 @@
package cmd
import (
"net/http"
_ "net/http/pprof"
"os"
"os/signal"
"runtime"
"sync"
"github.com/ethereum/go-ethereum/rpc"
@@ -25,8 +28,8 @@ import (
"github.com/spf13/cobra"
"github.com/spf13/viper"
sd "github.com/vulcanize/eth-statediff-service/pkg"
srpc "github.com/vulcanize/eth-statediff-service/pkg/rpc"
sd "github.com/cerc-io/eth-statediff-service/pkg"
srpc "github.com/cerc-io/eth-statediff-service/pkg/rpc"
)
// serveCmd represents the serve command
@@ -47,17 +50,38 @@ func init() {
rootCmd.AddCommand(serveCmd)
}
func maxParallelism() int {
maxProcs := runtime.GOMAXPROCS(0)
numCPU := runtime.NumCPU()
if maxProcs < numCPU {
return maxProcs
}
return numCPU
}
func serve() {
logWithCommand.Info("Running eth-statediff-service serve command")
logWithCommand.Infof("Parallelism: %d", maxParallelism())
statediffService, err := createStateDiffService()
if err != nil {
logWithCommand.Fatal(err)
}
// Enable the pprof agent if configured
if viper.GetBool("debug.pprof") {
// See: https://www.farsightsecurity.com/blog/txt-record/go-remote-profiling-20161028/
// For security reasons: do not use the default http multiplexor elsewhere in this process.
go func() {
logWithCommand.Info("Starting pprof listener on port 6060")
logWithCommand.Fatal(http.ListenAndServe("localhost:6060", nil))
}()
}
// short circuit if we only want to perform prerun
if viper.GetBool("prerun.only") {
if err := statediffService.Run(nil); err != nil {
parallel := viper.GetBool("prerun.parallel")
if err := statediffService.Run(nil, parallel); err != nil {
logWithCommand.Fatal("unable to perform prerun: %v", err)
}
return
+2 -2
View File
@@ -11,8 +11,8 @@ import (
"github.com/ethereum/go-ethereum/trie"
"github.com/spf13/viper"
sd "github.com/vulcanize/eth-statediff-service/pkg"
"github.com/vulcanize/eth-statediff-service/pkg/prom"
sd "github.com/cerc-io/eth-statediff-service/pkg"
"github.com/cerc-io/eth-statediff-service/pkg/prom"
)
type blockRange [2]uint64
+1 -1
View File
@@ -20,7 +20,7 @@ import (
log "github.com/sirupsen/logrus"
"github.com/spf13/cobra"
v "github.com/vulcanize/eth-statediff-service/version"
v "github.com/cerc-io/eth-statediff-service/version"
)
// versionCmd represents the version command
+9 -9
View File
@@ -1,16 +1,16 @@
module github.com/vulcanize/eth-statediff-service
module github.com/cerc-io/eth-statediff-service
go 1.18
require (
github.com/ethereum/go-ethereum v1.10.21
github.com/cerc-io/go-eth-state-node-iterator v1.1.7
github.com/ethereum/go-ethereum v1.10.23
github.com/jmoiron/sqlx v1.2.0 // indirect
github.com/prometheus/client_golang v1.4.0
github.com/sirupsen/logrus v1.7.0
github.com/sirupsen/logrus v1.9.0
github.com/spf13/cobra v1.3.0
github.com/spf13/viper v1.10.1
github.com/vulcanize/go-eth-state-node-iterator v1.1.4
github.com/vulcanize/leveldb-ethdb-rpc v0.1.6
github.com/vulcanize/leveldb-ethdb-rpc v0.1.7
)
require (
@@ -70,7 +70,7 @@ require (
github.com/jackpal/go-nat-pmp v1.0.2 // indirect
github.com/jbenet/goprocess v0.1.4 // indirect
github.com/klauspost/cpuid/v2 v2.0.9 // indirect
github.com/lib/pq v1.10.2 // indirect
github.com/lib/pq v1.10.6 // indirect
github.com/magiconair/properties v1.8.5 // indirect
github.com/mattn/go-colorable v0.1.12 // indirect
github.com/mattn/go-isatty v0.0.14 // indirect
@@ -121,10 +121,10 @@ require (
go.uber.org/atomic v1.7.0 // indirect
go.uber.org/multierr v1.6.0 // indirect
go.uber.org/zap v1.17.0 // indirect
golang.org/x/crypto v0.0.0-20220525230936-793ad666bf5e // indirect
golang.org/x/crypto v0.0.0-20220829220503-c86fa9a7ed90 // 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 v0.0.0-20220520151302-bc2c85ada10a // indirect
golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8 // indirect
golang.org/x/text v0.3.7 // indirect
golang.org/x/time v0.0.0-20210220033141-f8bda1e9f3ba // indirect
google.golang.org/protobuf v1.27.1 // indirect
@@ -135,4 +135,4 @@ require (
lukechampine.com/blake3 v1.1.6 // indirect
)
replace github.com/ethereum/go-ethereum v1.10.21 => github.com/vulcanize/go-ethereum v1.10.21-statediff-4.1.2-alpha
replace github.com/ethereum/go-ethereum v1.10.23 => github.com/cerc-io/go-ethereum v1.10.23-statediff-4.2.0-alpha
+15 -14
View File
@@ -86,6 +86,10 @@ github.com/btcsuite/btcd/chaincfg/chainhash v1.0.1 h1:q0rUy8C/TYNBQS1+CGKw68tLOF
github.com/c-bata/go-prompt v0.2.2/go.mod h1:VzqtzE2ksDBcdln8G7mk2RX9QyGjH+OVqOCSiVIqS34=
github.com/census-instrumentation/opencensus-proto v0.2.1/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
github.com/census-instrumentation/opencensus-proto v0.3.0/go.mod h1:f6KPmirojxKA12rnyqOA5BBL4O983OfeGPqjHWSTneU=
github.com/cerc-io/go-eth-state-node-iterator v1.1.7 h1:i4zCKkfowJ4aUVpqVyMpOZIbD5WVm/iijhMAPgcLJ44=
github.com/cerc-io/go-eth-state-node-iterator v1.1.7/go.mod h1:BBh4BetpBoHUbAiKAdatR3ij7IzDlgN9nPzZ7snn/lo=
github.com/cerc-io/go-ethereum v1.10.23-statediff-4.2.0-alpha h1:Na4mum/Qkw1mRHnq/TIRPIF5exZAEBznVs3G3/YSENo=
github.com/cerc-io/go-ethereum v1.10.23-statediff-4.2.0-alpha/go.mod h1:lKBVBWksSwBDR/5D9CAxaGQzDPIS3ueWb6idy7X1Shg=
github.com/cespare/cp v0.1.0 h1:SE+dxFebS7Iik5LK0tsi1k9ZCxEaFX4AjQmoyA+1dJk=
github.com/cespare/xxhash v1.1.0/go.mod h1:XrSqR1VqqWfGrhpAt58auRo0WTKS1nRRg3ghfAqPWnc=
github.com/cespare/xxhash/v2 v2.1.1/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
@@ -190,8 +194,8 @@ github.com/go-ole/go-ole v1.2.6/go.mod h1:pprOEPIfldk/42T2oK7lQ4v4JSDwmV0As9GaiU
github.com/go-openapi/jsonpointer v0.19.5/go.mod h1:Pl9vOtqEWErmShwVjC8pYs9cog34VGT37dQOVbmoatg=
github.com/go-openapi/swag v0.19.5/go.mod h1:POnQmlKehdgb5mhVOsnJFsivZCEZ/vjK9gh66Z9tfKk=
github.com/go-sql-driver/mysql v1.4.0/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
github.com/go-sql-driver/mysql v1.4.1 h1:g24URVg0OFbNUTx9qqY1IRZ9D9z3iPyi5zKhQZpNwpA=
github.com/go-sql-driver/mysql v1.4.1/go.mod h1:zAC/RDZ24gD3HViQzih4MyKcchzm+sOG5ZlKdlhCg5w=
github.com/go-sql-driver/mysql v1.6.0 h1:BCTh4TKNUYmOmMUcQ3IipzF5prigylS7XXjEkfCHuOE=
github.com/go-stack/stack v1.8.0 h1:5SgMzNM5HxrEjV0ww2lTmX6E2Izsfxas4+YHWRs3Lsk=
github.com/go-stack/stack v1.8.0/go.mod h1:v0f6uXyyMGvRgIKkXu+yp6POWl0qKG85gN/melR3HDY=
github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0/go.mod h1:fyg7847qk6SyHyPtNmDHnmrv/HOrqktSC+C9fM+CJOE=
@@ -519,8 +523,9 @@ github.com/lib/pq v1.1.1/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
github.com/lib/pq v1.2.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
github.com/lib/pq v1.3.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
github.com/lib/pq v1.4.0/go.mod h1:5WUZQaWbwv1U+lTReE5YruASi9Al49XbQIvNi/34Woo=
github.com/lib/pq v1.10.2 h1:AqzbZs4ZoCBp+GtejcpCpcxM3zlSMx29dXbUSeVtJb8=
github.com/lib/pq v1.10.2/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
github.com/lib/pq v1.10.6 h1:jbk+ZieJ0D7EVGJYpL9QTz7/YW6UHbmdnZWYyK5cdBs=
github.com/lib/pq v1.10.6/go.mod h1:AlVN5x4E4T544tWzH6hKfbfQvm3HdbOxrmggDNAPY9o=
github.com/lyft/protoc-gen-star v0.5.3/go.mod h1:V0xaHgaf5oCCqmcxYcWiDfTiKsZsRc87/1qhoTACD8w=
github.com/magiconair/properties v1.8.5 h1:b6kJs+EmPFMYGkow9GiUyCyOvIwYetYJ3fSaWak/Gls=
github.com/magiconair/properties v1.8.5/go.mod h1:y3VJvCyxH9uVvJTWEGAELF3aiYNyPKd5NZ3oSwXrF60=
@@ -695,8 +700,8 @@ github.com/shopspring/decimal v1.2.0/go.mod h1:DKyhrW/HYNuLGql+MJL6WCR6knT2jwCFR
github.com/sirupsen/logrus v1.2.0/go.mod h1:LxeOpSwHxABJmUn/MG1IvRgCAasNZTLOkJPxbbu5VWo=
github.com/sirupsen/logrus v1.4.1/go.mod h1:ni0Sbl8bgC9z8RoU9G6nDWqqs/fq4eDPysMBDgk/93Q=
github.com/sirupsen/logrus v1.4.2/go.mod h1:tLMulIdttU9McNUspp0xgXVQah82FyeX6MwdIuYE2rE=
github.com/sirupsen/logrus v1.7.0 h1:ShrD1U9pZB12TX0cVy0DtePoCH97K8EtX+mg7ZARUtM=
github.com/sirupsen/logrus v1.7.0/go.mod h1:yWOB1SBYBC5VeMP7gHvWumXLIWorT60ONWic61uBYv0=
github.com/sirupsen/logrus v1.9.0 h1:trlNQbNUG3OdDrDil03MCb1H2o9nJ1x4/5LYw7byDE0=
github.com/sirupsen/logrus v1.9.0/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
github.com/smartystreets/assertions v0.0.0-20180927180507-b2de0cb4f26d/go.mod h1:OnSkiWE9lh6wB0YB77sQom3nweQdgAjqCqsofrRNTgc=
github.com/smartystreets/goconvey v1.6.4/go.mod h1:syvi0/a8iFYH4r/RixwvyeAJjdLS9QV7WQ/tjFTllLA=
github.com/spaolacci/murmur3 v0.0.0-20180118202830-f09979ecbc72/go.mod h1:JwIasOWyU6f++ZhiEuf87xNszmSA2myDM2Kzu9HwQUA=
@@ -753,12 +758,8 @@ github.com/urfave/cli/v2 v2.10.2/go.mod h1:f8iq5LtQ/bLxafbdBSLPPNsgaW0l/2fYYEHhA
github.com/valyala/bytebufferpool v1.0.0/go.mod h1:6bBcMArwyJ5K/AmCkWv1jt77kVWyCJ6HpOuEn7z0Csc=
github.com/valyala/fasttemplate v1.0.1/go.mod h1:UQGH1tvbgY+Nz5t2n7tXsz52dQxojPUpymEIMZ47gx8=
github.com/valyala/fasttemplate v1.2.1/go.mod h1:KHLXt3tVN2HBp8eijSv/kGJopbvo7S+qRAEEKiv+SiQ=
github.com/vulcanize/go-eth-state-node-iterator v1.1.4 h1:2jIbgZ/yxrNZt5zmsXtvUPSxT0sP5k1PR5/O1GN/Ma0=
github.com/vulcanize/go-eth-state-node-iterator v1.1.4/go.mod h1:kFzlSi7rUB9mJWZf08xIEiiGuXnnUEn48It+WMHzxPc=
github.com/vulcanize/go-ethereum v1.10.21-statediff-4.1.2-alpha h1:ct+8FGuQnHA6SOGOQoAMINWdeexuSF40+IjF48J094A=
github.com/vulcanize/go-ethereum v1.10.21-statediff-4.1.2-alpha/go.mod h1:dNJkmCSbaasX0zfQM6pm1g3rWlW3EGhLOEZMScyrRAs=
github.com/vulcanize/leveldb-ethdb-rpc v0.1.6 h1:vkiplC4B8v5f0jTABLBFDn4HueYzbhYIBhjHuDFnPpU=
github.com/vulcanize/leveldb-ethdb-rpc v0.1.6/go.mod h1:VRNHF03FBH+6Gg+nn4JfXZ6R1+K/+/Yf/Eeodsyv7KE=
github.com/vulcanize/leveldb-ethdb-rpc v0.1.7 h1:iyaaNRNK2S6QNUwKlAzUbJFHEKyD7z9T74uCAgTHBI0=
github.com/vulcanize/leveldb-ethdb-rpc v0.1.7/go.mod h1:gqXQ5dpFcb517/NYzIezqZIDOgLMBHYzP+A0Orqdblg=
github.com/whyrusleeping/go-logging v0.0.0-20170515211332-0457bb6b88fc/go.mod h1:bopw91TMyo8J3tvftk8xmU2kPmlrt4nScJQZU2hE5EM=
github.com/willf/bitset v1.1.3/go.mod h1:RjeCKbqT1RxIR/KWY6phxZiaY1IyutSBfGjNPySAYV4=
github.com/xlab/treeprint v0.0.0-20180616005107-d6fb6747feb6/go.mod h1:ce1O1j6UtZfjr22oyGxGLbauSBp2YVXpARAosm7dHBg=
@@ -824,8 +825,8 @@ golang.org/x/crypto v0.0.0-20210220033148-5ea612d1eb83/go.mod h1:jdWPYTVW3xRLrWP
golang.org/x/crypto v0.0.0-20210616213533-5ff15b29337e/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.0.0-20210711020723-a769d52b0f97/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.0.0-20210817164053-32db794688a5/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
golang.org/x/crypto v0.0.0-20220525230936-793ad666bf5e h1:T8NU3HyQ8ClP4SEE+KbFlg6n0NhuTsN4MyznaarGsZM=
golang.org/x/crypto v0.0.0-20220525230936-793ad666bf5e/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
golang.org/x/crypto v0.0.0-20220829220503-c86fa9a7ed90 h1:Y/gsMcFOcR+6S6f3YeMKl5g+dZMEWqcz5Czj/GWYbkM=
golang.org/x/crypto v0.0.0-20220829220503-c86fa9a7ed90/go.mod h1:IxCIyHEi3zRg3s0A5j5BB6A9Jmi73HwBIUl50j+osU4=
golang.org/x/exp v0.0.0-20180321215751-8460e604b9de/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20180807140117-3d87b88a115f/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA=
@@ -1027,8 +1028,9 @@ golang.org/x/sys v0.0.0-20211124211545-fe61309f8881/go.mod h1:oPkhp1MJrh7nUepCBc
golang.org/x/sys v0.0.0-20211205182925-97ca703d548d/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20211216021012-1d35b9e2eb4e/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220412211240-33da011f77ad/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a h1:dGzPydgVsqGcTRVwiLJ1jVbufYwmzD3LfVPLKsKg+0k=
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8 h1:0A+M6Uqn+Eje4kHMK80dtF3JCXC4ykBgQG4Fe06QRhQ=
golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/term v0.0.0-20201117132131-f5c789dd3221/go.mod h1:Nr5EML6q2oocZ2LXRh80K7BxOlk5/8JxuGnuhpl+muw=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
@@ -1166,7 +1168,6 @@ google.golang.org/appengine v1.5.0/go.mod h1:xpcJRLb0r/rnEns0DIKYYv+WjYCduHsrkT7
google.golang.org/appengine v1.6.1/go.mod h1:i06prIuMbXzDqacNJfV5OdTW448YApPu5ww/cMBSeb0=
google.golang.org/appengine v1.6.5/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
google.golang.org/appengine v1.6.6/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
google.golang.org/appengine v1.6.7 h1:FZR1q0exgwxzPzp/aF+VccGrSfxfPpkBqjIIEq3ru6c=
google.golang.org/appengine v1.6.7/go.mod h1:8WjMMxjGQR8xUklV/ARdw2HLXBOI7O7uCIDZVag1xfc=
google.golang.org/genproto v0.0.0-20180817151627-c66870c02cf8/go.mod h1:JiN7NxoALGmiZfu7CAH4rXhgtRTLTxftemlI0sWmxmc=
google.golang.org/genproto v0.0.0-20190307195333-5fe7a883aa19/go.mod h1:VzzqZJRnGkLBvHegQrXjBqPurQTc5/KpmUdxsrq26oE=
+1 -1
View File
@@ -15,7 +15,7 @@
package main
import "github.com/vulcanize/eth-statediff-service/cmd"
import "github.com/cerc-io/eth-statediff-service/cmd"
func main() {
cmd.Execute()
+1 -1
View File
@@ -29,7 +29,7 @@ import (
sdtypes "github.com/ethereum/go-ethereum/statediff/types"
"github.com/sirupsen/logrus"
iter "github.com/vulcanize/go-eth-state-node-iterator"
iter "github.com/cerc-io/go-eth-state-node-iterator"
)
type builder struct {
+1 -1
View File
@@ -30,7 +30,7 @@ import (
"github.com/ethereum/go-ethereum/statediff/test_helpers"
sdtypes "github.com/ethereum/go-ethereum/statediff/types"
pkg "github.com/vulcanize/eth-statediff-service/pkg"
pkg "github.com/cerc-io/eth-statediff-service/pkg"
)
var (
+1 -1
View File
@@ -24,7 +24,7 @@ import (
"github.com/ethereum/go-ethereum/rpc"
log "github.com/sirupsen/logrus"
"github.com/vulcanize/eth-statediff-service/pkg/prom"
"github.com/cerc-io/eth-statediff-service/pkg/prom"
)
// StartHTTPEndpoint starts the HTTP RPC endpoint, configured with cors/vhosts/modules.
+1 -1
View File
@@ -26,7 +26,7 @@ import (
"github.com/ethereum/go-ethereum/rpc"
log "github.com/sirupsen/logrus"
"github.com/vulcanize/eth-statediff-service/pkg/prom"
"github.com/cerc-io/eth-statediff-service/pkg/prom"
)
var (
+45 -8
View File
@@ -33,7 +33,7 @@ import (
sdtypes "github.com/ethereum/go-ethereum/statediff/types"
"github.com/sirupsen/logrus"
"github.com/vulcanize/eth-statediff-service/pkg/prom"
"github.com/cerc-io/eth-statediff-service/pkg/prom"
)
const defaultQueueSize = 1024
@@ -48,7 +48,7 @@ type StateDiffService interface {
// Loop is the main event loop for processing state diffs
Loop(wg *sync.WaitGroup) error
// Run is a one-off command to run on a predefined set of ranges
Run(ranges []RangeRequest) error
Run(ranges []RangeRequest, parallel bool) error
// StateDiffAt method to get state diff object at specific block
StateDiffAt(blockNumber uint64, params sd.Params) (*sd.Payload, error)
// StateDiffFor method to get state diff object at specific block
@@ -118,18 +118,55 @@ func (sds *Service) APIs() []rpc.API {
}
// Run does a one-off processing run on the provided RangeRequests + any pre-runs, exiting afterwards
func (sds *Service) Run(rngs []RangeRequest) error {
func (sds *Service) Run(rngs []RangeRequest, parallel bool) error {
for _, preRun := range sds.preruns {
logrus.Infof("processing prerun range (%d, %d)", preRun.Start, preRun.Stop)
for i := preRun.Start; i <= preRun.Stop; i++ {
if err := sds.WriteStateDiffAt(i, preRun.Params); err != nil {
return fmt.Errorf("error writing statediff at height %d in range (%d, %d) : %v", i, preRun.Start, preRun.Stop, err)
if parallel {
// Chunk overall range into N subranges for workers
chunkSize := (preRun.Stop - preRun.Start) / uint64(sds.workers)
logrus.Infof("parallel processing prerun range (%d, %d) (%d blocks) divided into %d sized chunks with %d workers", preRun.Start, preRun.Stop,
preRun.Stop-preRun.Start+1, chunkSize, sds.workers)
// Sanity floor the chunk size
if chunkSize < 100 {
chunkSize = 100
logrus.Infof("Computed range chunk size for each worker is too small, defaulting to 100")
}
wg := new(sync.WaitGroup)
for i := 0; i < int(sds.workers); i++ {
blockRange := RangeRequest{
Start: preRun.Start + uint64(i)*chunkSize,
Stop: preRun.Start + uint64(i)*chunkSize + chunkSize - 1,
Params: preRun.Params,
}
// TODO(hack) this fixes quantization
if blockRange.Stop < preRun.Stop && preRun.Stop-blockRange.Stop < chunkSize {
blockRange.Stop = preRun.Stop
}
wg.Add(1)
go func(id int) {
defer wg.Done()
logrus.Infof("prerun worker %d processing range (%d, %d)", id, blockRange.Start, blockRange.Stop)
for j := blockRange.Start; j <= blockRange.Stop; j++ {
if err := sds.WriteStateDiffAt(j, blockRange.Params); err != nil {
logrus.Errorf("error writing statediff at height %d in range (%d, %d) : %v", i, blockRange.Start, blockRange.Stop, err)
}
}
logrus.Infof("prerun worker %d finished processing range (%d, %d)", id, blockRange.Start, blockRange.Stop)
}(i)
}
wg.Wait()
} else {
logrus.Infof("sequential processing prerun range (%d, %d)", preRun.Start, preRun.Stop)
for i := preRun.Start; i <= preRun.Stop; i++ {
if err := sds.WriteStateDiffAt(i, preRun.Params); err != nil {
return fmt.Errorf("error writing statediff at height %d in range (%d, %d) : %v", i, preRun.Start, preRun.Stop, err)
}
}
}
}
sds.preruns = nil
// At present this code is never called so we have not written the parallel version:
for _, rng := range rngs {
logrus.Infof("processing prerun range (%d, %d)", rng.Start, rng.Stop)
logrus.Infof("processing requested range (%d, %d)", rng.Start, rng.Stop)
for i := rng.Start; i <= rng.Stop; i++ {
if err := sds.WriteStateDiffAt(i, rng.Params); err != nil {
return fmt.Errorf("error writing statediff at height %d in range (%d, %d) : %v", i, rng.Start, rng.Stop, err)
+28
View File
@@ -0,0 +1,28 @@
# Used by the script to count rows (count-lines.sh)
COUNT_LINES_LOG=./count-lines.log
COUNT_LINES_INPUT_DIR=~/eth-statediff-service/output_dir
COUNT_LINES_OUTPUT_FILE=./output-stats.txt
# Used by the script to dedup output files (dedup.sh)
DEDUP_LOG=./dedup.log
DEDUP_INPUT_DIR=~/eth-statediff-service/output_dir
DEDUP_OUTPUT_DIR=~/eth-statediff-service/dedup_dir
DEDUP_SORT_DIR=./.sort
# Used by the script to perform column checks (check-columns.sh)
CHECK_COLUMNS_LOG=./check-columns.log
CHECK_COLUMNS_INPUT_DIR=~/eth-statediff-service/output_dir
CHECK_COLUMNS_INPUT_DEDUP_DIR=~/eth-statediff-service/dedup_dir
CHECK_COLUMNS_OUTPUT_DIR=./check-columns
# Used by the script to import data (timescaledb-import.sh)
IMPORT_LOG=./tsdb-import.log
IMPORT_INPUT_DIR=~/eth-statediff-service/output_dir
IMPORT_INPUT_DEDUP_DIR=~/eth-statediff-service/dedup_dir
TIMESCALEDB_WORKERS=8
DATABASE_USER=vdbm
DATABASE_HOSTNAME=localhost
DATABASE_PORT=8077
DATABASE_NAME=vulcanize_testing
DATABASE_PASSWORD=password
+58
View File
@@ -0,0 +1,58 @@
#!/bin/bash
# Requires:
# CHECK_COLUMNS_LOG
# CHECK_COLUMNS_INPUT_DIR
# CHECK_COLUMNS_INPUT_DEDUP_DIR
# CHECK_COLUMNS_OUTPUT_DIR
# env file arg
ENV=$1
echo "Using env file: ${ENV}"
# read env file
export $(grep -v '^#' ${ENV} | xargs)
# redirect stdout/stderr to a file
exec >"${CHECK_COLUMNS_LOG}" 2>&1
# create output dir if not exists
mkdir -p "${CHECK_COLUMNS_OUTPUT_DIR}"
start_timestamp=$(date +%s)
declare -A expected_columns
expected_columns=(
["public.nodes"]="5"
["public.blocks"]="3"
# ["eth.access_list_elements"]="?" # skipping as values include ','
["eth.log_cids"]="12"
["eth.state_accounts"]="7"
["eth.storage_cids"]="9"
["eth.uncle_cids"]="7"
["eth.header_cids"]="16"
["eth.receipt_cids"]="10"
["eth.state_cids"]="8"
["eth.transaction_cids"]="11"
)
for table_name in "${!expected_columns[@]}";
do
if [ "${table_name}" = "public.blocks" ];
then
command="$(dirname "$0")/find-bad-rows.sh -i ${CHECK_COLUMNS_INPUT_DEDUP_DIR}/deduped-${table_name}.csv -c ${expected_columns[${table_name}]} -d true -o ${CHECK_COLUMNS_OUTPUT_DIR}/${table_name}.txt"
else
command="$(dirname "$0")/find-bad-rows.sh -i ${CHECK_COLUMNS_INPUT_DIR}/${table_name}.csv -c ${expected_columns[${table_name}]} -d true -o ${CHECK_COLUMNS_OUTPUT_DIR}/${table_name}.txt"
fi
echo "${table_name}"
echo Start: "$(date)"
eval "${command}"
echo End: "$(date)"
echo Total bad rows: $(wc -l ${CHECK_COLUMNS_OUTPUT_DIR}/${table_name}.txt)
echo
done
difference=$(($(date +%s)-start_timestamp))
echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)
echo
+46
View File
@@ -0,0 +1,46 @@
#!/bin/bash
# Requires:
# COUNT_LINES_LOG
# COUNT_LINES_INPUT_DIR
# COUNT_LINES_OUTPUT_FILE
# env file arg
ENV=$1
echo "Using env file: ${ENV}"
# read env file
export $(grep -v '^#' ${ENV} | xargs)
# redirect stdout/stderr to a file
exec >"${COUNT_LINES_LOG}" 2>&1
start_timestamp=$(date +%s)
table_names=(
"public.nodes"
"public.blocks"
"eth.access_list_elements"
"eth.log_cids"
"eth.state_accounts"
"eth.storage_cids"
"eth.uncle_cids"
"eth.header_cids"
"eth.receipt_cids"
"eth.state_cids"
"eth.transaction_cids"
)
echo "Row counts:" > "${COUNT_LINES_OUTPUT_FILE}"
for table_name in "${table_names[@]}";
do
echo "${table_name}";
echo Start: "$(date)"
wc -l "${COUNT_LINES_INPUT_DIR}"/"${table_name}.csv" >> "${COUNT_LINES_OUTPUT_FILE}"
echo End: "$(date)"
echo
done
difference=$(($(date +%s)-start_timestamp))
echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)
+35
View File
@@ -0,0 +1,35 @@
#!/bin/bash
# Requires:
# DEDUP_LOG
# DEDUP_INPUT_DIR
# DEDUP_OUTPUT_DIR
# DEDUP_SORT_DIR
# env file arg
ENV=$1
echo "Using env file: ${ENV}"
# read env file
export $(grep -v '^#' ${ENV} | xargs)
# redirect stdout/stderr to a file
exec >"${DEDUP_LOG}" 2>&1
# create output dir if not exists
mkdir -p "${DEDUP_OUTPUT_DIR}"
start_timestamp=$(date +%s)
echo "public.blocks"
echo Start: "$(date)"
sort -T "${DEDUP_SORT_DIR}" -u "${DEDUP_INPUT_DIR}"/public.blocks.csv -o "${DEDUP_OUTPUT_DIR}"/deduped-public.blocks.csv
echo End: "$(date)"
echo Total deduped rows: $(wc -l ${DEDUP_OUTPUT_DIR}/deduped-public.blocks.csv)
echo
difference=$(($(date +%s)-start_timestamp))
echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)
# NOTE: This script currently only dedups public.blocks output file.
# If the output contains blocks that were statediffed more than once, output files for other tables will have to be deduped as well.
+43
View File
@@ -0,0 +1,43 @@
#!/bin/bash
# flags
# -i <input-file>: Input data file path
# -c <expected-columns>: Expected number of columns in each row of the input file
# -o [output-file]: Output destination file path (default: STDOUT)
# -d [include-data]: Whether to include the data row in output (true | false) (default: false)
# eg: ./scripts/find-bad-rows.sh -i eth.state_cids.csv -c 8 -o res.txt -d true
# output: 1 9 1500000,xxxxxxxx,0x83952d392f9b0059eea94b10d1a095eefb1943ea91595a16c6698757127d4e1c,,
# baglacgzasvqcntdahkxhufdnkm7a22s2eetj6mx6nzkarwxtkvy4x3bubdgq,\x0f,0,f,/blocks/,
# DMQJKYBGZRQDVLT2CRWVGPQNNJNCCJU7GL7G4VAI3LZVK4OL5Q2ARTI
while getopts i:c:o:d: OPTION
do
case "${OPTION}" in
i) inputFile=${OPTARG};;
c) expectedColumns=${OPTARG};;
o) outputFile=${OPTARG};;
d) data=${OPTARG};;
esac
done
timestamp=$(date +%s)
# if data requested, dump row number, number of columns and the row
if [ "${data}" = true ] ; then
if [ -z "${outputFile}" ]; then
awk -F"," "NF!=${expectedColumns} {print NR, NF, \$0}" < ${inputFile}
else
awk -F"," "NF!=${expectedColumns} {print NR, NF, \$0}" < ${inputFile} > ${outputFile}
fi
# else, dump only row number, number of columns
else
if [ -z "${outputFile}" ]; then
awk -F"," "NF!=${expectedColumns} {print NR, NF}" < ${inputFile}
else
awk -F"," "NF!=${expectedColumns} {print NR, NF}" < ${inputFile} > ${outputFile}
fi
fi
difference=$(($(date +%s)-timestamp))
echo Time taken: $(date -d@${difference} -u +%H:%M:%S)
+75
View File
@@ -0,0 +1,75 @@
#!/bin/bash
# Requires:
# IMPORT_LOG
# IMPORT_INPUT_DIR
# IMPORT_INPUT_DEDUP_DIR
# TIMESCALEDB_WORKERS
# DATABASE_USER
# DATABASE_HOSTNAME
# DATABASE_PORT
# DATABASE_NAME
# DATABASE_PASSWORD
DEFAULT_TIMESCALEDB_WORKERS=8
# env file arg
ENV=$1
echo "Using env file: ${ENV}"
# read env file
export $(grep -v '^#' ${ENV} | xargs)
if [ "$TIMESCALEDB_WORKERS" = "" ]; then
TIMESCALEDB_WORKERS=$DEFAULT_TIMESCALEDB_WORKERS
fi
# redirect stdout/stderr to a file
exec >"${IMPORT_LOG}" 2>&1
start_timestamp=$(date +%s)
declare -a tables
# schema-table-copyOptions
tables=(
"public-nodes"
"public-blocks"
"eth-access_list_elements"
"eth-log_cids-FORCE NOT NULL topic0, topic1, topic2, topic3 CSV"
"eth-state_accounts"
"eth-storage_cids-FORCE NOT NULL storage_leaf_key CSV"
"eth-uncle_cids"
"eth-header_cids"
"eth-receipt_cids-FORCE NOT NULL post_state, contract, contract_hash CSV"
"eth-state_cids-FORCE NOT NULL state_leaf_key CSV"
"eth-transaction_cids-FORCE NOT NULL dst CSV"
)
for elem in "${tables[@]}";
do
IFS='-' read -a arr <<< "${elem}"
if [ "${arr[0]}.${arr[1]}" = "public.blocks" ];
then
copy_command="timescaledb-parallel-copy --connection \"host=${DATABASE_HOSTNAME} port=${DATABASE_PORT} user=${DATABASE_USER} password=${DATABASE_PASSWORD} sslmode=disable\" --db-name ${DATABASE_NAME} --schema ${arr[0]} --table ${arr[1]} --file ${IMPORT_INPUT_DEDUP_DIR}/deduped-${arr[0]}.${arr[1]}.csv --workers ${TIMESCALEDB_WORKERS} --reporting-period 300s"
else
copy_command="timescaledb-parallel-copy --connection \"host=${DATABASE_HOSTNAME} port=${DATABASE_PORT} user=${DATABASE_USER} password=${DATABASE_PASSWORD} sslmode=disable\" --db-name ${DATABASE_NAME} --schema ${arr[0]} --table ${arr[1]} --file ${IMPORT_INPUT_DIR}/${arr[0]}.${arr[1]}.csv --workers ${TIMESCALEDB_WORKERS} --reporting-period 300s"
fi
if [ "${arr[2]}" != "" ];
then
copy_with_options="${copy_command} --copy-options \"${arr[2]}\""
else
copy_with_options=${copy_command}
fi
echo "${arr[0]}.${arr[1]}"
echo Start: "$(date)"
eval "${copy_with_options}"
echo End: "$(date)"
echo
done
difference=$(($(date +%s)-start_timestamp))
echo Time taken: $((difference/86400)):$(date -d@${difference} -u +%H:%M:%S)
echo