2023-11-01 03:32:09 +00:00
|
|
|
# Nimbus
|
2024-02-01 14:11:41 +00:00
|
|
|
# Copyright (c) 2020-2024 Status Research & Development GmbH
|
2023-11-01 03:32:09 +00:00
|
|
|
# Licensed under either of
|
|
|
|
|
# * Apache License, version 2.0, ([LICENSE-APACHE](LICENSE-APACHE) or
|
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0)
|
|
|
|
|
# * MIT license ([LICENSE-MIT](LICENSE-MIT) or
|
|
|
|
|
# http://opensource.org/licenses/MIT)
|
|
|
|
|
# at your option. This file may not be copied, modified, or distributed except
|
|
|
|
|
# according to those terms.
|
|
|
|
|
|
2019-01-06 15:21:34 +00:00
|
|
|
# use this module to quickly populate db with data from geth/parity
|
|
|
|
|
|
|
|
|
|
import
|
2024-02-01 14:11:41 +00:00
|
|
|
std/os,
|
2023-08-04 11:10:09 +00:00
|
|
|
chronicles,
|
2022-12-02 04:39:12 +00:00
|
|
|
../nimbus/errors,
|
|
|
|
|
../nimbus/core/chain,
|
2023-08-04 11:10:09 +00:00
|
|
|
../nimbus/common,
|
2024-06-05 15:08:29 +00:00
|
|
|
../nimbus/db/opts,
|
2023-08-04 11:10:09 +00:00
|
|
|
../nimbus/db/[core_db/persistent, storage_types],
|
|
|
|
|
configuration # must be late (compilation annoyance)
|
2019-01-06 15:21:34 +00:00
|
|
|
|
2021-09-14 09:49:31 +00:00
|
|
|
when defined(graphql):
|
|
|
|
|
import graphql_downloader
|
|
|
|
|
else:
|
|
|
|
|
import downloader
|
|
|
|
|
|
2023-08-04 11:10:09 +00:00
|
|
|
# `lmdb` is not used, anymore
|
|
|
|
|
#
|
|
|
|
|
# const
|
|
|
|
|
# manualCommit = nimbus_db_backend == "lmdb"
|
|
|
|
|
#
|
|
|
|
|
# template persistToDb(db: ChainDB, body: untyped) =
|
|
|
|
|
# when manualCommit:
|
|
|
|
|
# if not db.txBegin(): doAssert(false)
|
|
|
|
|
# body
|
|
|
|
|
# when manualCommit:
|
|
|
|
|
# if not db.txCommit(): doAssert(false)
|
|
|
|
|
|
|
|
|
|
template persistToDb(db: CoreDbRef, body: untyped) =
|
|
|
|
|
block: body
|
2024-02-01 14:11:41 +00:00
|
|
|
|
2024-06-05 20:52:04 +00:00
|
|
|
proc contains(kvt: CoreDxKvtRef; key: openArray[byte]): bool =
|
|
|
|
|
kvt.hasKey(key).expect "valid bool"
|
|
|
|
|
|
2020-07-21 06:15:06 +00:00
|
|
|
proc main() {.used.} =
|
2019-01-06 15:21:34 +00:00
|
|
|
# 97 block with uncles
|
|
|
|
|
# 46147 block with first transaction
|
|
|
|
|
# 46400 block with transaction
|
|
|
|
|
# 46402 block with first contract: failed
|
|
|
|
|
# 47205 block with first success contract
|
|
|
|
|
# 48712 block with 5 transactions
|
|
|
|
|
# 48915 block with contract
|
|
|
|
|
# 49018 first problematic block
|
|
|
|
|
# 49439 first block with contract call
|
|
|
|
|
# 52029 first block with receipts logs
|
|
|
|
|
# 66407 failed transaction
|
|
|
|
|
|
2020-06-19 10:52:19 +00:00
|
|
|
let conf = configuration.getConfiguration()
|
2023-08-04 11:10:09 +00:00
|
|
|
let com = CommonRef.new(
|
2024-06-05 15:08:29 +00:00
|
|
|
newCoreDbRef(DefaultDbPersistent, conf.dataDir, DbOptions.init()),
|
2024-05-20 10:17:51 +00:00
|
|
|
conf.netId, networkParams(conf.netId))
|
2019-01-06 15:21:34 +00:00
|
|
|
|
|
|
|
|
# move head to block number ...
|
2024-06-14 07:31:08 +00:00
|
|
|
if conf.head != 0'u64:
|
2024-02-01 14:11:41 +00:00
|
|
|
var parentBlock = requestBlock(conf.head, { DownloadAndValidate })
|
2022-12-02 04:39:12 +00:00
|
|
|
discard com.db.setHead(parentBlock.header)
|
2019-01-06 15:21:34 +00:00
|
|
|
|
2024-06-05 20:52:04 +00:00
|
|
|
let kvt = com.db.newKvt()
|
|
|
|
|
if canonicalHeadHashKey().toOpenArray notin kvt:
|
2023-08-04 11:10:09 +00:00
|
|
|
persistToDb(com.db):
|
2022-12-02 04:39:12 +00:00
|
|
|
com.initializeEmptyDb()
|
2024-06-05 20:52:04 +00:00
|
|
|
doAssert(canonicalHeadHashKey().toOpenArray in kvt)
|
2019-01-06 15:21:34 +00:00
|
|
|
|
2022-12-02 04:39:12 +00:00
|
|
|
var head = com.db.getCanonicalHead()
|
2024-06-14 07:31:08 +00:00
|
|
|
var blockNumber = head.number + 1
|
2022-12-02 04:39:12 +00:00
|
|
|
var chain = newChain(com)
|
2019-01-06 15:21:34 +00:00
|
|
|
|
2019-01-08 11:29:56 +00:00
|
|
|
let numBlocksToCommit = conf.numCommits
|
2019-01-06 15:21:34 +00:00
|
|
|
|
Consolidate block type for block processing (#2325)
This PR consolidates the split header-body sequences into a single EthBlock
sequence and cleans up the fallout from that which significantly reduces
block processing overhead during import thanks to less garbage collection
and fewer copies of things all around.
Notably, since the number of headers must always match the number of bodies,
we also get rid of a pointless degree of freedom that in the future could
introduce unnecessary bugs.
* only read header and body from era file
* avoid several unnecessary copies along the block processing way
* simplify signatures, cleaning up unused arguemnts and returns
* use `stew/assign2` in a few strategic places where the generated
nim assignent is slow and add a few `move` to work around poor
analysis in nim 1.6 (will need to be revisited for 2.0)
```
stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv
bps_x bps_y tps_x tps_y bpsd tpsd timed
block_number
(498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92%
(713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21%
(928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28%
(1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50%
(1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80%
(1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91%
(1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91%
(2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61%
(2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80%
blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s
bpsd (mean): 19.55%
tpsd (mean): 19.55%
Time (total): -29m13s, -15.14%
```
2024-06-09 14:32:20 +00:00
|
|
|
var blocks = newSeqOfCap[EthBlock](numBlocksToCommit)
|
2024-06-14 07:31:08 +00:00
|
|
|
var one = 1'u64
|
2019-01-06 15:21:34 +00:00
|
|
|
|
|
|
|
|
var numBlocks = 0
|
2019-01-08 11:29:56 +00:00
|
|
|
var counter = 0
|
2024-02-01 14:11:41 +00:00
|
|
|
var retryCount = 0
|
2019-01-08 11:29:56 +00:00
|
|
|
|
2019-07-07 10:12:01 +00:00
|
|
|
while true:
|
2024-02-01 14:11:41 +00:00
|
|
|
var thisBlock: Block
|
|
|
|
|
try:
|
|
|
|
|
thisBlock = requestBlock(blockNumber, { DownloadAndValidate })
|
|
|
|
|
except CatchableError as e:
|
|
|
|
|
if retryCount < 3:
|
|
|
|
|
warn "Unable to get block data via JSON-RPC API", error = e.msg
|
|
|
|
|
inc retryCount
|
|
|
|
|
sleep(1000)
|
|
|
|
|
continue
|
|
|
|
|
else:
|
|
|
|
|
raise e
|
2019-01-06 15:21:34 +00:00
|
|
|
|
Consolidate block type for block processing (#2325)
This PR consolidates the split header-body sequences into a single EthBlock
sequence and cleans up the fallout from that which significantly reduces
block processing overhead during import thanks to less garbage collection
and fewer copies of things all around.
Notably, since the number of headers must always match the number of bodies,
we also get rid of a pointless degree of freedom that in the future could
introduce unnecessary bugs.
* only read header and body from era file
* avoid several unnecessary copies along the block processing way
* simplify signatures, cleaning up unused arguemnts and returns
* use `stew/assign2` in a few strategic places where the generated
nim assignent is slow and add a few `move` to work around poor
analysis in nim 1.6 (will need to be revisited for 2.0)
```
stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv
bps_x bps_y tps_x tps_y bpsd tpsd timed
block_number
(498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92%
(713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21%
(928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28%
(1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50%
(1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80%
(1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91%
(1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91%
(2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61%
(2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80%
blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s
bpsd (mean): 19.55%
tpsd (mean): 19.55%
Time (total): -29m13s, -15.14%
```
2024-06-09 14:32:20 +00:00
|
|
|
blocks.add EthBlock.init(thisBlock.header, thisBlock.body)
|
2019-03-11 13:21:09 +00:00
|
|
|
info "REQUEST HEADER", blockNumber=blockNumber, txs=thisBlock.body.transactions.len
|
2019-07-07 10:12:01 +00:00
|
|
|
|
2019-01-06 15:21:34 +00:00
|
|
|
inc numBlocks
|
|
|
|
|
blockNumber += one
|
|
|
|
|
|
|
|
|
|
if numBlocks == numBlocksToCommit:
|
2023-08-04 11:10:09 +00:00
|
|
|
persistToDb(com.db):
|
Consolidate block type for block processing (#2325)
This PR consolidates the split header-body sequences into a single EthBlock
sequence and cleans up the fallout from that which significantly reduces
block processing overhead during import thanks to less garbage collection
and fewer copies of things all around.
Notably, since the number of headers must always match the number of bodies,
we also get rid of a pointless degree of freedom that in the future could
introduce unnecessary bugs.
* only read header and body from era file
* avoid several unnecessary copies along the block processing way
* simplify signatures, cleaning up unused arguemnts and returns
* use `stew/assign2` in a few strategic places where the generated
nim assignent is slow and add a few `move` to work around poor
analysis in nim 1.6 (will need to be revisited for 2.0)
```
stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv
bps_x bps_y tps_x tps_y bpsd tpsd timed
block_number
(498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92%
(713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21%
(928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28%
(1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50%
(1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80%
(1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91%
(1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91%
(2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61%
(2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80%
blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s
bpsd (mean): 19.55%
tpsd (mean): 19.55%
Time (total): -29m13s, -15.14%
```
2024-06-09 14:32:20 +00:00
|
|
|
let res = chain.persistBlocks(blocks)
|
2024-05-31 07:13:56 +00:00
|
|
|
res.isOkOr:
|
|
|
|
|
raise newException(ValidationError, "Error when validating blocks: " & res.error)
|
2019-01-06 15:21:34 +00:00
|
|
|
numBlocks = 0
|
Consolidate block type for block processing (#2325)
This PR consolidates the split header-body sequences into a single EthBlock
sequence and cleans up the fallout from that which significantly reduces
block processing overhead during import thanks to less garbage collection
and fewer copies of things all around.
Notably, since the number of headers must always match the number of bodies,
we also get rid of a pointless degree of freedom that in the future could
introduce unnecessary bugs.
* only read header and body from era file
* avoid several unnecessary copies along the block processing way
* simplify signatures, cleaning up unused arguemnts and returns
* use `stew/assign2` in a few strategic places where the generated
nim assignent is slow and add a few `move` to work around poor
analysis in nim 1.6 (will need to be revisited for 2.0)
```
stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv
bps_x bps_y tps_x tps_y bpsd tpsd timed
block_number
(498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92%
(713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21%
(928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28%
(1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50%
(1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80%
(1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91%
(1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91%
(2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61%
(2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80%
blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s
bpsd (mean): 19.55%
tpsd (mean): 19.55%
Time (total): -29m13s, -15.14%
```
2024-06-09 14:32:20 +00:00
|
|
|
blocks.setLen(0)
|
2019-01-06 15:21:34 +00:00
|
|
|
|
2019-01-08 11:29:56 +00:00
|
|
|
inc counter
|
|
|
|
|
if conf.maxBlocks != 0 and counter >= conf.maxBlocks:
|
|
|
|
|
break
|
|
|
|
|
|
2019-01-06 15:21:34 +00:00
|
|
|
if numBlocks > 0:
|
2023-08-04 11:10:09 +00:00
|
|
|
persistToDb(com.db):
|
Consolidate block type for block processing (#2325)
This PR consolidates the split header-body sequences into a single EthBlock
sequence and cleans up the fallout from that which significantly reduces
block processing overhead during import thanks to less garbage collection
and fewer copies of things all around.
Notably, since the number of headers must always match the number of bodies,
we also get rid of a pointless degree of freedom that in the future could
introduce unnecessary bugs.
* only read header and body from era file
* avoid several unnecessary copies along the block processing way
* simplify signatures, cleaning up unused arguemnts and returns
* use `stew/assign2` in a few strategic places where the generated
nim assignent is slow and add a few `move` to work around poor
analysis in nim 1.6 (will need to be revisited for 2.0)
```
stats-20240607_2223-a814aa0b.csv vs stats-20240608_0714-21c1d0a9.csv
bps_x bps_y tps_x tps_y bpsd tpsd timed
block_number
(498305, 713245] 1,540.52 1,809.73 2,361.58 2775.340189 17.63% 17.63% -14.92%
(713245, 928185] 730.36 865.26 1,715.90 2028.973852 18.01% 18.01% -15.21%
(928185, 1143126] 663.03 789.10 2,529.26 3032.490771 19.79% 19.79% -16.28%
(1143126, 1358066] 393.46 508.05 2,152.50 2777.578119 29.13% 29.13% -22.50%
(1358066, 1573007] 370.88 440.72 2,351.31 2791.896052 18.81% 18.81% -15.80%
(1573007, 1787947] 283.65 335.11 2,068.93 2441.373402 17.60% 17.60% -14.91%
(1787947, 2002888] 287.29 342.11 2,078.39 2474.179448 18.99% 18.99% -15.91%
(2002888, 2217828] 293.38 343.16 2,208.83 2584.77457 17.16% 17.16% -14.61%
(2217828, 2432769] 140.09 167.86 1,081.87 1296.336926 18.82% 18.82% -15.80%
blocks: 1934464, baseline: 3h13m1s, contender: 2h43m47s
bpsd (mean): 19.55%
tpsd (mean): 19.55%
Time (total): -29m13s, -15.14%
```
2024-06-09 14:32:20 +00:00
|
|
|
let res = chain.persistBlocks(blocks)
|
2024-05-31 07:13:56 +00:00
|
|
|
res.isOkOr:
|
|
|
|
|
raise newException(ValidationError, "Error when validating blocks: " & res.error)
|
2019-01-06 15:21:34 +00:00
|
|
|
|
2019-01-08 11:29:56 +00:00
|
|
|
when isMainModule:
|
|
|
|
|
var message: string
|
|
|
|
|
|
|
|
|
|
## Processing command line arguments
|
2020-06-19 10:52:19 +00:00
|
|
|
if configuration.processArguments(message) != Success:
|
2024-02-01 14:11:41 +00:00
|
|
|
if len(message) > 0:
|
|
|
|
|
echo message
|
|
|
|
|
echo "Usage: persist --datadir=<DATA_DIR> --maxblocks=<MAX_BLOCKS> --head=<HEAD> --numcommits=<NUM_COMMITS> --netid=<NETWORK_ID>"
|
2019-01-08 11:29:56 +00:00
|
|
|
quit(QuitFailure)
|
|
|
|
|
else:
|
|
|
|
|
if len(message) > 0:
|
|
|
|
|
echo message
|
|
|
|
|
quit(QuitSuccess)
|
|
|
|
|
|
2019-01-09 12:10:58 +00:00
|
|
|
try:
|
|
|
|
|
main()
|
2023-08-04 11:10:09 +00:00
|
|
|
except CatchableError:
|
2019-01-09 12:10:58 +00:00
|
|
|
echo getCurrentExceptionMsg()
|
