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
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.
* batch database key writes during `computeKey` calls
* log progress when there are many keys to update
* avoid evicting the vertex cache when traversing the trie for key
computation purposes
* avoid storing trivial leaf hashes that directly can be loaded from the
vertex
* avoid costly hike memory allocations for operations that don't need to
re-traverse it
* avoid unnecessary state checks (which might trigger unwanted state
root computations)
* disable optimize-for-hits due to the MPT no longer being complete at
all times
* Cleanup unneeded stateless and block witness code. Keeping MultiKeys which is used in the eth_getProofsByBlockNumber RPC endpoint which is needed for the Fluffy state network bridge.
* Rename generateWitness flag to collectWitnessData to better describe what the flag does. We only collect the keys of the touched accounts and storage slots but no block witness generation is supported for now.
* Move remaining stateless code into nimbus directory.
* Add vmstate parameter to ChainRef to fix test.
* Exclude *.in from check copyright year
---------
Co-authored-by: jangko <jangko128@gmail.com>
This PR extends the `nimbus import` command to also allow reading from
era files - this command allows creating or topping up an existing
database with data coming from era files instead of network sync.
* add `--era1-dir` and `--max-blocks` options to command line
* make `persistBlocks` report basic stats like transactions and gas
* improve error reporting in several API
* allow importing multiple RLP files in one go
* clean up logging options to match nimbus-eth2
* make sure database is closed properly on shutdown
- The fluffy test vector repo got forked (well, copied rather) to
become the official one under ethereum github org, so we change
to that repo now and archive ours.
- Our repo also stored accumulator / historical_roots, replace
that with a new repo which is only for network configs.
- Several changes needed to be made due to test vectors that got
updated + some of them got changed to / are yaml format instead of
json.
* dist: precompiled binaries and Docker images
The builds are reproducible, the binaries are portable and statically link librocksdb.
This took some patching. Upstream PR: https://github.com/facebook/rocksdb/pull/9752
32-bit ARM is missing as a target because two different GCC versions
fail with an ICE when trying to cross-compile RocksDB. Using Clang
instead is too much trouble for a platform that nobody should be using
anyway.
(Clang doesn't come with its own target headers and libraries, can't be
easily convinced to use the ones from GCC, so it needs an fs image from
a 32-bit ARM distro - at which point I stopped caring).
* CI: disable reproducibility test
Siddarth Kumar
Jacek Sieka
tersec
web3-developer
Jordan Hrycaj
Kim De Mey
jangko
Ștefan Talpalaru