mirror of
https://github.com/status-im/nimbus-eth1.git
synced 2025-01-14 14:24:32 +00:00
f034af422a
Each branch node may have up to 16 sub-items - currently, these are given VertexID based when they are first needed leading to a mostly-random order of vertexid for each subitem. Here, we pre-allocate all 16 vertex ids such that when a branch subitem is filled, it already has a vertexid waiting for it. This brings several important benefits: * subitems are sorted and "close" in their id sequencing - this means that when rocksdb stores them, they are likely to end up in the same data block thus improving read efficiency * because the ids are consequtive, we can store just the starting id and a bitmap representing which subitems are in use - this reduces disk space usage for branches allowing more of them fit into a single disk read, further improving disk read and caching performance - disk usage at block 18M is down from 84 to 78gb! * the in-memory footprint of VertexRef reduced allowing more instances to fit into caches and less memory to be used overall. Because of the increased locality of reference, it turns out that we no longer need to iterate over the entire database to efficiently generate the hash key database because the normal computation is now faster - this significantly benefits "live" chain processing as well where each dirtied key must be accompanied by a read of all branch subitems next to it - most of the performance benefit in this branch comes from this locality-of-reference improvement. On a sample resync, there's already ~20% improvement with later blocks seeing increasing benefit (because the trie is deeper in later blocks leading to more benefit from branch read perf improvements) ``` blocks: 18729664, baseline: 190h43m49s, contender: 153h59m0s Time (total): -36h44m48s, -19.27% ``` Note: clients need to be resynced as the PR changes the on-disk format R.I.P. little bloom filter - your life in the repo was short but valuable
90 lines
2.9 KiB
Nim
90 lines
2.9 KiB
Nim
# nimbus-eth1
|
|
# Copyright (c) 2023-2024 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.
|
|
|
|
## Aristo DB -- Handy Helpers
|
|
## ==========================
|
|
##
|
|
{.push raises: [].}
|
|
|
|
import
|
|
eth/common,
|
|
results,
|
|
"."/[aristo_desc, aristo_compute]
|
|
|
|
# ------------------------------------------------------------------------------
|
|
# Public functions, converters
|
|
# ------------------------------------------------------------------------------
|
|
|
|
proc toNode*(
|
|
vtx: VertexRef; # Vertex to convert
|
|
root: VertexID; # Sub-tree root the `vtx` belongs to
|
|
db: AristoDbRef; # Database
|
|
): Result[NodeRef,seq[VertexID]] =
|
|
## Convert argument the vertex `vtx` to a node type. Missing Merkle hash
|
|
## keys are searched for on the argument database `db`.
|
|
##
|
|
## On error, at least the vertex ID of the first missing Merkle hash key is
|
|
## returned. If the argument `stopEarly` is set `false`, all missing Merkle
|
|
## hash keys are returned.
|
|
##
|
|
## In the argument `beKeyOk` is set `false`, keys for node links are accepted
|
|
## only from the cache layer. This does not affect a link key for a payload
|
|
## storage root.
|
|
##
|
|
|
|
case vtx.vType:
|
|
of Leaf:
|
|
let node = NodeRef(vtx: vtx.dup())
|
|
# Need to resolve storage root for account leaf
|
|
if vtx.lData.pType == AccountData:
|
|
let stoID = vtx.lData.stoID
|
|
if stoID.isValid:
|
|
let key = db.computeKey((stoID.vid, stoID.vid)).valueOr:
|
|
return err(@[stoID.vid])
|
|
|
|
node.key[0] = key
|
|
return ok node
|
|
|
|
of Branch:
|
|
let node = NodeRef(vtx: vtx.dup())
|
|
for n, subvid in vtx.pairs():
|
|
let key = db.computeKey((root, subvid)).valueOr:
|
|
return err(@[subvid])
|
|
node.key[n] = key
|
|
return ok node
|
|
|
|
iterator subVids*(vtx: VertexRef): VertexID =
|
|
## Returns the list of all sub-vertex IDs for the argument `vtx`.
|
|
case vtx.vType:
|
|
of Leaf:
|
|
if vtx.lData.pType == AccountData:
|
|
let stoID = vtx.lData.stoID
|
|
if stoID.isValid:
|
|
yield stoID.vid
|
|
of Branch:
|
|
for _, subvid in vtx.pairs():
|
|
yield subvid
|
|
|
|
iterator subVidKeys*(node: NodeRef): (VertexID,HashKey) =
|
|
## Simolar to `subVids()` but for nodes
|
|
case node.vtx.vType:
|
|
of Leaf:
|
|
if node.vtx.lData.pType == AccountData:
|
|
let stoID = node.vtx.lData.stoID
|
|
if stoID.isValid:
|
|
yield (stoID.vid, node.key[0])
|
|
of Branch:
|
|
for n, subvid in node.vtx.pairs():
|
|
yield (subvid,node.key[n])
|
|
|
|
# ------------------------------------------------------------------------------
|
|
# End
|
|
# ------------------------------------------------------------------------------
|