nimbus-eth1/tests/test_tracer_json.nim

178 lines
6.2 KiB
Nim
Raw Normal View History

2018-12-12 22:18:46 +07:00
# Nimbus
# Copyright (c) 2018-2025 Status Research & Development GmbH
2018-12-12 22:18:46 +07:00
# 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.
2018-12-12 22:18:46 +07:00
import
std/[json, os, tables, strutils],
stew/byteutils,
chronicles,
2022-12-02 11:39:12 +07:00
unittest2,
results,
2022-12-02 11:39:12 +07:00
./test_helpers,
../execution_chain/db/aristo,
../execution_chain/db/aristo/[aristo_desc, aristo_part],
../execution_chain/db/aristo/aristo_part/part_debug,
../execution_chain/db/kvt/kvt_utils,
../execution_chain/[tracer, evm/types],
../execution_chain/common/common
2018-12-12 22:18:46 +07:00
proc setErrorLevel {.used.} =
when defined(chronicles_runtime_filtering) and loggingEnabled:
setLogLevel(LogLevel.ERROR)
proc preLoadAristoDb(cdb: CoreDbRef; jKvp: JsonNode; num: BlockNumber) =
## Hack for `Aristo` pre-lading using the `snap` protocol proof-loader
const
info = "preLoadAristoDb"
var
proof: seq[seq[byte]] # for pre-loading MPT
predRoot: Hash32 # from predecessor header
txRoot: Hash32 # header with block number `num`
rcptRoot: Hash32 # ditto
aristo: fork support via layers/txframes (#2960) * aristo: fork support via layers/txframes This change reorganises how the database is accessed: instead holding a "current frame" in the database object, a dag of frames is created based on the "base frame" held in `AristoDbRef` and all database access happens through this frame, which can be thought of as a consistent point-in-time snapshot of the database based on a particular fork of the chain. In the code, "frame", "transaction" and "layer" is used to denote more or less the same thing: a dag of stacked changes backed by the on-disk database. Although this is not a requirement, in practice each frame holds the change set of a single block - as such, the frame and its ancestors leading up to the on-disk state represents the state of the database after that block has been applied. "committing" means merging the changes to its parent frame so that the difference between them is lost and only the cumulative changes remain - this facility enables frames to be combined arbitrarily wherever they are in the dag. In particular, it becomes possible to consolidate a set of changes near the base of the dag and commit those to disk without having to re-do the in-memory frames built on top of them - this is useful for "flattening" a set of changes during a base update and sending those to storage without having to perform a block replay on top. Looking at abstractions, a side effect of this change is that the KVT and Aristo are brought closer together by considering them to be part of the "same" atomic transaction set - the way the code gets organised, applying a block and saving it to the kvt happens in the same "logical" frame - therefore, discarding the frame discards both the aristo and kvt changes at the same time - likewise, they are persisted to disk together - this makes reasoning about the database somewhat easier but has the downside of increased memory usage, something that perhaps will need addressing in the future. Because the code reasons more strictly about frames and the state of the persisted database, it also makes it more visible where ForkedChain should be used and where it is still missing - in particular, frames represent a single branch of history while forkedchain manages multiple parallel forks - user-facing services such as the RPC should use the latter, ie until it has been finalized, a getBlock request should consider all forks and not just the blocks in the canonical head branch. Another advantage of this approach is that `AristoDbRef` conceptually becomes more simple - removing its tracking of the "current" transaction stack simplifies reasoning about what can go wrong since this state now has to be passed around in the form of `AristoTxRef` - as such, many of the tests and facilities in the code that were dealing with "stack inconsistency" are now structurally prevented from happening. The test suite will need significant refactoring after this change. Once this change has been merged, there are several follow-ups to do: * there's no mechanism for keeping frames up to date as they get committed or rolled back - TODO * naming is confused - many names for the same thing for legacy reason * forkedchain support is still missing in lots of code * clean up redundant logic based on previous designs - in particular the debug and introspection code no longer makes sense * the way change sets are stored will probably need revisiting - because it's a stack of changes where each frame must be interrogated to find an on-disk value, with a base distance of 128 we'll at minimum have to perform 128 frame lookups for *every* database interaction - regardless, the "dag-like" nature will stay * dispose and commit are poorly defined and perhaps redundant - in theory, one could simply let the GC collect abandoned frames etc, though it's likely an explicit mechanism will remain useful, so they stay for now More about the changes: * `AristoDbRef` gains a `txRef` field (todo: rename) that "more or less" corresponds to the old `balancer` field * `AristoDbRef.stack` is gone - instead, there's a chain of `AristoTxRef` objects that hold their respective "layer" which has the actual changes * No more reasoning about "top" and "stack" - instead, each `AristoTxRef` can be a "head" that "more or less" corresponds to the old single-history `top` notion and its stack * `level` still represents "distance to base" - it's computed from the parent chain instead of being stored * one has to be careful not to use frames where forkedchain was intended - layers are only for a single branch of history! * fix layer vtop after rollback * engine fix * Fix test_txpool * Fix test_rpc * Fix copyright year * fix simulator * Fix copyright year * Fix copyright year * Fix tracer * Fix infinite recursion bug * Remove aristo and kvt empty files * Fic copyright year * Fix fc chain_kvt * ForkedChain refactoring * Fix merge master conflict * Fix copyright year * Reparent txFrame * Fix test * Fix txFrame reparent again * Cleanup and fix test * UpdateBase bugfix and fix test * Fixe newPayload bug discovered by hive * Fix engine api fcu * Clean up call template, chain_kvt, andn txguid * Fix copyright year * work around base block loading issue * Add test * Fix updateHead bug * Fix updateBase bug * Change func commitBase to proc commitBase * Touch up and fix debug mode crash --------- Co-authored-by: jangko <jangko128@gmail.com>
2025-02-06 08:04:50 +01:00
# let
# adb = cdb.ctx.mpt # `Aristo` db
# kdb = cdb.ctx.kvt # `Kvt` db
# ps = PartStateRef.init cdb.baseTxFrame # Partial DB descriptor
# # Fill KVT and collect `proof` data
# for (k,v) in jKvp.pairs:
# let
# key = hexToSeqByte(k)
# val = hexToSeqByte(v.getStr())
# if key.len == 32:
# doAssert key == val.keccak256.data
# if val != @[0x80u8]: # Exclude empty item
# proof.add val
# else:
# if key[0] == 0:
# try:
# # Pull our particular header fields (if possible)
# let header = rlp.decode(val, Header)
# if header.number == num:
# txRoot = header.txRoot
# rcptRoot = header.receiptsRoot
# elif header.number == num-1:
# predRoot = header.stateRoot
# except RlpError:
# discard
# check kdb.put(key, val).isOk
# # Set up production MPT
# ps.partPut(proof, AutomaticPayload).isOkOr:
# raiseAssert info & ": partPut => " & $error
# TODO code needs updating after removal of generic payloads
# # Handle transaction sub-tree
# if txRoot.isValid:
# var txs: seq[Transaction]
# for (key,pyl) in adb.rightPairs LeafTie(root: ps.partGetSubTree txRoot):
# let
# inx = key.path.to(UInt256).truncate(uint)
# tx = rlp.decode(pyl.rawBlob, Transaction)
# #
# # FIXME: Is this might be a bug in the test data?
# #
# # The single item test key is always `128`. For non-single test
# # lists, the keys are `1`,`2`, ..,`N`, `128` (some single digit
# # number `N`.)
# #
# # Unless the `128` item value is put at the start of the argument
# # list `txs[]` for `persistTransactions()`, the `tracer` module
# # will throw an exception at
# # `doAssert(transactions.calcTxRoot == header.txRoot)` in the
# # function `traceTransactionImpl()`.
# #
# if (inx and 0x80) != 0:
# txs = @[tx] & txs
# else:
# txs.add tx
# cdb.persistTransactions(num, txRoot, txs)
# # Handle receipts sub-tree
# if rcptRoot.isValid:
# var rcpts: seq[Receipt]
# for (key,pyl) in adb.rightPairs LeafTie(root: ps.partGetSubTree rcptRoot):
# let
# inx = key.path.to(UInt256).truncate(uint)
# rcpt = rlp.decode(pyl.rawBlob, Receipt)
# # FIXME: See comment at `txRoot` section.
# if (inx and 0x80) != 0:
# rcpts = @[rcpt] & rcpts
# else:
# rcpts.add rcpt
# cdb.persistReceipts(rcptRoot, rcpts)
Store keys together with node data (#2849) Currently, computed hash keys are stored in a separate column family with respect to the MPT data they're generated from - this has several disadvantages: * A lot of space is wasted because the lookup key (`RootedVertexID`) is repeated in both tables - this is 30% of the `AriKey` content! * rocksdb must maintain in-memory bloom filters and LRU caches for said keys, doubling its "minimal efficient cache size" * An extra disk traversal must be made to check for existence of cached hash key * Doubles the amount of files on disk due to each column family being its own set of files Here, the two CFs are joined such that both key and data is stored in `AriVtx`. This means: * we save ~30% disk space on repeated lookup keys * we save ~2gb of memory overhead that can be used to cache data instead of indices * we can skip storing hash keys for MPT leaf nodes - these are trivial to compute and waste a lot of space - previously they had to present in the `AriKey` CF to avoid having to look in two tables on the happy path. * There is a small increase in write amplification because when a hash value is updated for a branch node, we must write both key and branch data - previously we would write only the key * There's a small shift in CPU usage - instead of performing lookups in the database, hashes for leaf nodes are (re)-computed on the fly * We can return to slightly smaller on-disk SST files since there's fewer of them, which should reduce disk traffic a bit Internally, there are also other advantages: * when clearing keys, we no longer have to store a zero hash in memory - instead, we deduce staleness of the cached key from the presence of an updated VertexRef - this saves ~1gb of mem overhead during import * hash key cache becomes dedicated to branch keys since leaf keys are no longer stored in memory, reducing churn * key computation is a lot faster thanks to the skipped second disk traversal - a key computation for mainnet can be completed in 11 hours instead of ~2 days (!) thanks to better cache usage and less read amplification - with additional improvements to the on-disk format, we can probably get rid of the initial full traversal method of seeding the key cache on first start after import All in all, this PR reduces the size of a mainnet database from 160gb to 110gb and the peak memory footprint during import by ~1-2gb.
2024-11-20 09:56:27 +01:00
# # Save keys to database
# for (rvid,key) in ps.vkPairs:
# adb.layersPutKey(rvid, key)
aristo: fork support via layers/txframes (#2960) * aristo: fork support via layers/txframes This change reorganises how the database is accessed: instead holding a "current frame" in the database object, a dag of frames is created based on the "base frame" held in `AristoDbRef` and all database access happens through this frame, which can be thought of as a consistent point-in-time snapshot of the database based on a particular fork of the chain. In the code, "frame", "transaction" and "layer" is used to denote more or less the same thing: a dag of stacked changes backed by the on-disk database. Although this is not a requirement, in practice each frame holds the change set of a single block - as such, the frame and its ancestors leading up to the on-disk state represents the state of the database after that block has been applied. "committing" means merging the changes to its parent frame so that the difference between them is lost and only the cumulative changes remain - this facility enables frames to be combined arbitrarily wherever they are in the dag. In particular, it becomes possible to consolidate a set of changes near the base of the dag and commit those to disk without having to re-do the in-memory frames built on top of them - this is useful for "flattening" a set of changes during a base update and sending those to storage without having to perform a block replay on top. Looking at abstractions, a side effect of this change is that the KVT and Aristo are brought closer together by considering them to be part of the "same" atomic transaction set - the way the code gets organised, applying a block and saving it to the kvt happens in the same "logical" frame - therefore, discarding the frame discards both the aristo and kvt changes at the same time - likewise, they are persisted to disk together - this makes reasoning about the database somewhat easier but has the downside of increased memory usage, something that perhaps will need addressing in the future. Because the code reasons more strictly about frames and the state of the persisted database, it also makes it more visible where ForkedChain should be used and where it is still missing - in particular, frames represent a single branch of history while forkedchain manages multiple parallel forks - user-facing services such as the RPC should use the latter, ie until it has been finalized, a getBlock request should consider all forks and not just the blocks in the canonical head branch. Another advantage of this approach is that `AristoDbRef` conceptually becomes more simple - removing its tracking of the "current" transaction stack simplifies reasoning about what can go wrong since this state now has to be passed around in the form of `AristoTxRef` - as such, many of the tests and facilities in the code that were dealing with "stack inconsistency" are now structurally prevented from happening. The test suite will need significant refactoring after this change. Once this change has been merged, there are several follow-ups to do: * there's no mechanism for keeping frames up to date as they get committed or rolled back - TODO * naming is confused - many names for the same thing for legacy reason * forkedchain support is still missing in lots of code * clean up redundant logic based on previous designs - in particular the debug and introspection code no longer makes sense * the way change sets are stored will probably need revisiting - because it's a stack of changes where each frame must be interrogated to find an on-disk value, with a base distance of 128 we'll at minimum have to perform 128 frame lookups for *every* database interaction - regardless, the "dag-like" nature will stay * dispose and commit are poorly defined and perhaps redundant - in theory, one could simply let the GC collect abandoned frames etc, though it's likely an explicit mechanism will remain useful, so they stay for now More about the changes: * `AristoDbRef` gains a `txRef` field (todo: rename) that "more or less" corresponds to the old `balancer` field * `AristoDbRef.stack` is gone - instead, there's a chain of `AristoTxRef` objects that hold their respective "layer" which has the actual changes * No more reasoning about "top" and "stack" - instead, each `AristoTxRef` can be a "head" that "more or less" corresponds to the old single-history `top` notion and its stack * `level` still represents "distance to base" - it's computed from the parent chain instead of being stored * one has to be careful not to use frames where forkedchain was intended - layers are only for a single branch of history! * fix layer vtop after rollback * engine fix * Fix test_txpool * Fix test_rpc * Fix copyright year * fix simulator * Fix copyright year * Fix copyright year * Fix tracer * Fix infinite recursion bug * Remove aristo and kvt empty files * Fic copyright year * Fix fc chain_kvt * ForkedChain refactoring * Fix merge master conflict * Fix copyright year * Reparent txFrame * Fix test * Fix txFrame reparent again * Cleanup and fix test * UpdateBase bugfix and fix test * Fixe newPayload bug discovered by hive * Fix engine api fcu * Clean up call template, chain_kvt, andn txguid * Fix copyright year * work around base block loading issue * Add test * Fix updateHead bug * Fix updateBase bug * Change func commitBase to proc commitBase * Touch up and fix debug mode crash --------- Co-authored-by: jangko <jangko128@gmail.com>
2025-02-06 08:04:50 +01:00
# ps.check().isOkOr:
# raiseAssert info & ": check => " & $error
#echo ">>> preLoadAristoDb (9)",
# "\n ps\n ", ps.pp(byKeyOk=false,byVidOk=false),
# ""
# -----------
#if true: quit()
2018-12-12 22:18:46 +07:00
# use tracerTestGen.nim to generate additional test data
proc testFixtureImpl(node: JsonNode, testStatusIMPL: var TestStatus, memoryDB: CoreDbRef) {.deprecated: "needs fixing for non-generic payloads".} =
block:
return
setErrorLevel()
2018-12-12 22:18:46 +07:00
var
blockNumberHex = node["blockNumber"].getStr()
blockNumber = parseHexInt(blockNumberHex).uint64
com = CommonRef.new(memoryDB, nil, chainConfigForNetwork(MainNet))
2018-12-12 22:18:46 +07:00
state = node["state"]
2018-12-25 17:31:51 +07:00
receipts = node["receipts"]
2018-12-12 22:18:46 +07:00
# disable POS/post Merge feature
com.setTTD Opt.none(DifficultyInt)
# Import raw data into database
# Some hack for `Aristo` using the `snap` protocol proof-loader
memoryDB.preLoadAristoDb(state, blockNumber)
2018-12-12 22:18:46 +07:00
aristo: fork support via layers/txframes (#2960) * aristo: fork support via layers/txframes This change reorganises how the database is accessed: instead holding a "current frame" in the database object, a dag of frames is created based on the "base frame" held in `AristoDbRef` and all database access happens through this frame, which can be thought of as a consistent point-in-time snapshot of the database based on a particular fork of the chain. In the code, "frame", "transaction" and "layer" is used to denote more or less the same thing: a dag of stacked changes backed by the on-disk database. Although this is not a requirement, in practice each frame holds the change set of a single block - as such, the frame and its ancestors leading up to the on-disk state represents the state of the database after that block has been applied. "committing" means merging the changes to its parent frame so that the difference between them is lost and only the cumulative changes remain - this facility enables frames to be combined arbitrarily wherever they are in the dag. In particular, it becomes possible to consolidate a set of changes near the base of the dag and commit those to disk without having to re-do the in-memory frames built on top of them - this is useful for "flattening" a set of changes during a base update and sending those to storage without having to perform a block replay on top. Looking at abstractions, a side effect of this change is that the KVT and Aristo are brought closer together by considering them to be part of the "same" atomic transaction set - the way the code gets organised, applying a block and saving it to the kvt happens in the same "logical" frame - therefore, discarding the frame discards both the aristo and kvt changes at the same time - likewise, they are persisted to disk together - this makes reasoning about the database somewhat easier but has the downside of increased memory usage, something that perhaps will need addressing in the future. Because the code reasons more strictly about frames and the state of the persisted database, it also makes it more visible where ForkedChain should be used and where it is still missing - in particular, frames represent a single branch of history while forkedchain manages multiple parallel forks - user-facing services such as the RPC should use the latter, ie until it has been finalized, a getBlock request should consider all forks and not just the blocks in the canonical head branch. Another advantage of this approach is that `AristoDbRef` conceptually becomes more simple - removing its tracking of the "current" transaction stack simplifies reasoning about what can go wrong since this state now has to be passed around in the form of `AristoTxRef` - as such, many of the tests and facilities in the code that were dealing with "stack inconsistency" are now structurally prevented from happening. The test suite will need significant refactoring after this change. Once this change has been merged, there are several follow-ups to do: * there's no mechanism for keeping frames up to date as they get committed or rolled back - TODO * naming is confused - many names for the same thing for legacy reason * forkedchain support is still missing in lots of code * clean up redundant logic based on previous designs - in particular the debug and introspection code no longer makes sense * the way change sets are stored will probably need revisiting - because it's a stack of changes where each frame must be interrogated to find an on-disk value, with a base distance of 128 we'll at minimum have to perform 128 frame lookups for *every* database interaction - regardless, the "dag-like" nature will stay * dispose and commit are poorly defined and perhaps redundant - in theory, one could simply let the GC collect abandoned frames etc, though it's likely an explicit mechanism will remain useful, so they stay for now More about the changes: * `AristoDbRef` gains a `txRef` field (todo: rename) that "more or less" corresponds to the old `balancer` field * `AristoDbRef.stack` is gone - instead, there's a chain of `AristoTxRef` objects that hold their respective "layer" which has the actual changes * No more reasoning about "top" and "stack" - instead, each `AristoTxRef` can be a "head" that "more or less" corresponds to the old single-history `top` notion and its stack * `level` still represents "distance to base" - it's computed from the parent chain instead of being stored * one has to be careful not to use frames where forkedchain was intended - layers are only for a single branch of history! * fix layer vtop after rollback * engine fix * Fix test_txpool * Fix test_rpc * Fix copyright year * fix simulator * Fix copyright year * Fix copyright year * Fix tracer * Fix infinite recursion bug * Remove aristo and kvt empty files * Fic copyright year * Fix fc chain_kvt * ForkedChain refactoring * Fix merge master conflict * Fix copyright year * Reparent txFrame * Fix test * Fix txFrame reparent again * Cleanup and fix test * UpdateBase bugfix and fix test * Fixe newPayload bug discovered by hive * Fix engine api fcu * Clean up call template, chain_kvt, andn txguid * Fix copyright year * work around base block loading issue * Add test * Fix updateHead bug * Fix updateBase bug * Change func commitBase to proc commitBase * Touch up and fix debug mode crash --------- Co-authored-by: jangko <jangko128@gmail.com>
2025-02-06 08:04:50 +01:00
var blk = com.db.baseTxFrame().getEthBlock(blockNumber).expect("eth block exists")
2018-12-12 22:18:46 +07:00
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 16:32:20 +02:00
let txTraces = traceTransactions(com, blk.header, blk.transactions)
let stateDump = dumpBlockState(com, blk)
let blockTrace = traceBlock(com, blk, {DisableState})
2018-12-12 22:18:46 +07:00
# Fix hex representation
for inx in 0 ..< node["txTraces"].len:
for key in ["beforeRoot", "afterRoot"]:
# Here, `node["txTraces"]` stores a string while `txTraces` uses a
# `Hash32` which might expand to a didfferent upper/lower case.
var strHash = txTraces[inx]["stateDiff"][key].getStr.toUpperAscii
if strHash.len < 64:
strHash = '0'.repeat(64 - strHash.len) & strHash
txTraces[inx]["stateDiff"][key] = %(strHash)
2018-12-25 17:31:51 +07:00
check node["txTraces"] == txTraces
2018-12-12 22:18:46 +07:00
check node["stateDump"] == stateDump
check node["blockTrace"] == blockTrace
2018-12-25 17:31:51 +07:00
for i in 0 ..< receipts.len:
let receipt = receipts[i]
let stateDiff = txTraces[i]["stateDiff"]
check receipt["root"].getStr().toLowerAscii() == stateDiff["afterRoot"].getStr().toLowerAscii()
proc testFixtureAristo(node: JsonNode, testStatusIMPL: var TestStatus) =
node.testFixtureImpl(testStatusIMPL, newCoreDbRef AristoDbMemory)
proc tracerJsonMain*() =
suite "tracer json tests for Aristo DB":
jsonTest("TracerTests", testFixtureAristo)
when isMainModule:
tracerJsonMain()