nimbus-eth1/tests/replay/undump_blocks_gz.nim

167 lines
5.2 KiB
Nim
Raw Normal View History

# Nimbus
# Copyright (c) 2021-2024 Status Research & Development GmbH
# 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.
import
std/[os, sequtils, strformat, strutils],
eth/[common, rlp],
nimcrypto/utils,
../../nimbus/db/core_db,
"."/[gunzip, undump_helpers]
# ------------------------------------------------------------------------------
# Private helpers
# ------------------------------------------------------------------------------
template say(args: varargs[untyped]) =
# echo args
discard
# ------------------------------------------------------------------------------
# Public capture
# ------------------------------------------------------------------------------
proc dumpBlocksBegin*(headers: openArray[Header]): string =
& "transaction #{headers[0].number} {headers.len}"
proc dumpBlocksList*(header: Header; body: BlockBody): string =
& "block {rlp.encode(header).toHex} {rlp.encode(body).toHex}"
proc dumpBlocksEnd*: string =
"commit"
proc dumpBlocksEndNl*: string =
dumpBlocksEnd() & "\n\n"
proc dumpBlocksListNl*(header: Header; body: BlockBody): string =
dumpBlocksList(header, body) & "\n"
proc dumpBlocksBeginNl*(db: CoreDbRef;
headers: openArray[Header]): string =
if headers[0].number == 1'u64:
let
h0 = db.getBlockHeader(0'u64)
b0 = db.getBlockBody(h0.blockHash)
result = "" &
dumpBlocksBegin(@[h0]) & "\n" &
dumpBlocksListNl(h0,b0) &
dumpBlocksEndNl()
result &= dumpBlocksBegin(headers) & "\n"
proc dumpBlocksNl*(db: CoreDbRef; headers: openArray[Header];
bodies: openArray[BlockBody]): string =
## Add this below the line `transaction.commit()` in the function
## `p2p/chain/persist_blocks.persistBlocksImpl()`:
## ::
## dumpStream.write c.db.dumpGroupNl(headers,bodies)
## dumpStream.flushFile
##
## where `dumpStream` is some stream (think of `stdout`) of type `File`
## that could be initialised with
## ::
## var dumpStream: File
## if dumpStream.isNil:
## doAssert dumpStream.open("./dump-stream.out", fmWrite)
##
db.dumpBlocksBeginNl(headers) &
toSeq(countup(0, headers.len-1))
.mapIt(dumpBlocksListNl(headers[it], bodies[it]))
.join &
dumpBlocksEndNl()
# ------------------------------------------------------------------------------
# Public undump
# ------------------------------------------------------------------------------
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
iterator undumpBlocksGz*(gzFile: string): seq[EthBlock] =
var
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
blockQ: seq[EthBlock]
current = 0u
start = 0u
top = 0u
waitFor = "transaction"
if not gzFile.fileExists:
raiseAssert &"No such file: \"{gzFile}\""
for lno,line in gzFile.gunzipLines:
if line.len == 0 or line[0] == '#':
continue
var flds = line.split
if 0 < flds.len and (waitFor == "" or waitFor == flds[0]):
case flds[0]
of "transaction":
let flds1Len = flds[1].len
if flds.len == 3 and
0 < flds1Len and flds[1][0] == '#' and
0 < flds[2].len:
start = flds[1][1 ..< flds1Len].parseUInt
top = start + flds[2].parseUInt
current = start
waitFor = ""
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
blockQ.reset
continue
else:
echo &"*** Ignoring line({lno}): {line}."
waitFor = "transaction"
of "block":
if flds.len == 3 and
0 < flds[1].len and
0 < flds[2].len and
start <= current and current < top:
var
rlpHeader = flds[1].rlpFromHex
rlpBody = flds[2].rlpFromHex
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
blockQ.add EthBlock.init(
rlpHeader.read(Header), rlpBody.read(BlockBody))
current.inc
continue
else:
echo &"*** Ignoring line({lno}): {line}."
waitFor = "transaction"
of "commit":
if current == top:
say &"*** commit({lno}) #{start}..{top-1}"
else:
echo &"*** commit({lno}) error, current({current}) should be {top}"
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
yield blockQ
waitFor = "transaction"
continue
echo &"*** Ignoring line({lno}): {line}."
waitFor = "transaction"
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
iterator undumpBlocksGz*(gzs: seq[string]): seq[EthBlock] =
## Variant of `undumpBlocks()`
for f in gzs:
for w in f.undumpBlocksGz:
yield w
iterator undumpBlocksGz*(
gzFile: string; # Data dump file
least: uint64; # First block to extract
stopAfter = high(uint64); # Last block to extract
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
): seq[EthBlock] =
## Variant of `undumpBlocks()`
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
for seqBlock in gzFile.undumpBlocksGz:
let b = startAt(seqBlock, least)
if b.len == 0:
continue
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 w = stopAfter(b, stopAfter)
if w.len == 0:
break
yield w
# ------------------------------------------------------------------------------
# End
# ------------------------------------------------------------------------------