2024-05-20 13:59:18 +00:00
|
|
|
# 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.
|
|
|
|
|
2024-05-26 06:24:13 +00:00
|
|
|
import results, eth/common, ../../nimbus/db/era1_db
|
2024-05-22 13:41:14 +00:00
|
|
|
|
2024-05-26 06:24:13 +00:00
|
|
|
var noisy* = false
|
2024-05-20 13:59:18 +00:00
|
|
|
|
|
|
|
# ------------------------------------------------------------------------------
|
|
|
|
# Public undump
|
|
|
|
# ------------------------------------------------------------------------------
|
|
|
|
|
2024-05-22 13:41:14 +00:00
|
|
|
iterator undumpBlocksEra1*(
|
2024-05-26 06:24:13 +00:00
|
|
|
dir: string,
|
|
|
|
least = low(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] =
|
2024-05-26 06:24:13 +00:00
|
|
|
let db = Era1DbRef.init(dir, "mainnet").expect("Era files present")
|
|
|
|
defer:
|
|
|
|
db.dispose()
|
|
|
|
|
|
|
|
# TODO it would be a lot more natural for this iterator to return 1 block at
|
|
|
|
# a time and let the consumer do the chunking
|
|
|
|
const blocksPerYield = 192
|
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 tmp = newSeqOfCap[EthBlock](blocksPerYield)
|
2024-05-26 06:24:13 +00:00
|
|
|
|
|
|
|
for i in 0 ..< stopAfter:
|
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 bck = db.getEthBlock(least + i).valueOr:
|
2024-05-26 06:24:13 +00:00
|
|
|
doAssert i > 0, "expected at least one block"
|
|
|
|
break
|
2024-05-22 13:41:14 +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
|
|
|
tmp.add move(bck)
|
2024-05-22 13:41:14 +00:00
|
|
|
|
2024-05-26 06:24:13 +00:00
|
|
|
# Genesis block requires a chunk of its own, for compatibility with current
|
|
|
|
# test setup (a bit weird, that...)
|
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
|
|
|
if tmp.len mod blocksPerYield == 0 or tmp[0].header.blockNumber == 0:
|
2024-05-26 06:24:13 +00:00
|
|
|
yield tmp
|
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
|
|
|
tmp.setLen(0)
|
2024-05-22 13:41:14 +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
|
|
|
if tmp.len > 0:
|
2024-05-26 06:24:13 +00:00
|
|
|
yield tmp
|
2024-05-22 13:41:14 +00:00
|
|
|
|
2024-05-20 13:59:18 +00:00
|
|
|
# ------------------------------------------------------------------------------
|
|
|
|
# End
|
|
|
|
# ------------------------------------------------------------------------------
|