accounts-db: Benchmark cache evictions #4045
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
from
100c57d to
8206e16
Compare
alessandrod
reviewed
Dec 11, 2024
alessandrod
reviewed
Dec 11, 2024
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
2 times, most recently
from
2766162 to
42ca375
Compare
brooksprumo
reviewed
Dec 11, 2024
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
8 times, most recently
from
e50fa20 to
ba708a3
Compare
brooksprumo
reviewed
Dec 13, 2024
alessandrod
reviewed
Dec 14, 2024
alessandrod
reviewed
Dec 14, 2024
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
3 times, most recently
from
2bf4cd2 to
f3b9d49
Compare
Here we go with the results. 🙂 |
|
Profiles show that each thread spends 68-77% of time on futex, here is the example of a profile (which was run only against the
|
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
from
f3b9d49 to
42761bd
Compare
brooksprumo
reviewed
Dec 18, 2024
alessandrod
reviewed
Dec 18, 2024
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
from
42761bd to
8caedac
Compare
|
Latest benchmarks: |
|
Profile of the 64-thread case didn't change much, all write threads still spend around 80% of time on futex
|
brooksprumo
reviewed
Dec 19, 2024
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
2 times, most recently
from
681bae7 to
e1e4ede
Compare
brooksprumo
reviewed
Dec 19, 2024
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
from
e1e4ede to
4419c1d
Compare
brooksprumo
previously approved these changes
Dec 20, 2024
The already existing `concurrent_{read,scan}_write` benchmarks are not
sufficient for benchmarking the eviction and evaluating what kind of
eviction policy performs the best, because they don't fill up the cache,
so eviction never happens. The number of readers in that benchmark is
low (5) and there are no writer threads causing more contention. The
cache is RW-locked, so bencharking only concurrent reads doesn't push
it to the limits.
Add new benchmarks which are made with measuring contention in mind:
- `read_only_accounts_cache` - benchmarks read-only cache loads and
stores without causing eviction.
- `read_only_accounts_cache_lo_hi` - benchmarks read-only cache eviction
with low and high thresholds. After each eviction, enough stores need
to be made to reach the difference between the low and high threshold,
triggering another eviction. Aims to simulate contention in a manner
close to what occurs on validators.
- `read_only_accounts_cache_hi` - benchmarks read-only cache eviction
without differentiating between low and high thresholds. Each store
triggers another eviction immediately. Measures the absolutely
worst-case scenario, which may not reflect actual conditions in
validators.
vadorovsky
force-pushed
the
benchmark-cache-evictions
branch
from
4419c1d to
506b666
Compare
alessandrod
approved these changes
Dec 21, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
The already existing
concurrent_{read,scan}_writebenchmarks are not sufficient for benchmarking the eviction and evaluating what kind of eviction policy performs the best, because they don't fill up the cache, so eviction never happens. The number of readers in that benchmark is low (5) and there are no writer threads causing more contention. The cache is RW-locked, so bencharking only concurrent reads doesn't push it to the limits.Add new benchmarks which are made with measuring contention in mind:
read_only_accounts_cache- benchmarks read-only cache loads and stores without causing eviction.read_only_accounts_cache_lo_hi- benchmarks read-only cache eviction with low and high thresholds. After each eviction, enough stores need to be made to reach the difference between the low and high threshold, triggering another eviction. Aims to simulate contention in a manner close to what occurs on validators.read_only_accounts_cache_hi- benchmarks read-only cache eviction without differentiating between low and high thresholds. Each store triggers another eviction immediately. Measures the absolutely worst-case scenario, which may not reflect actual conditions in validators.