refactor: meta: Use released databend-meta optimization tags#19861
Merged
Conversation
Update Databend's external meta dependencies from local path patches to the released databend-meta v260512.1.0 and databend-meta-client v260205.9.0 tags. The server-side databend-meta tag includes the raft-log 0.4.2 WAL flush optimizations: bounded group-commit waiting, configurable flush batch size, vectored batch writes, and flush latency percentile stats. It also keeps the meta-side runtime and raft-log metrics needed to inspect the effect of the batching change. Refresh Cargo.lock so the workspace resolves the tagged packages from databendlabs/databend-meta and picks up Openraft 0.10.0-alpha.20 through those dependencies. Include the 2026-05-14 benchmark report comparing the patched build with ups/main. The report records the current binary version, dependency versions, workload parameters, throughput, latency, raft-log batch stats, and the observed throughput improvement. Performance summary from the 2-node upsert_kv benchmark: 4 clients improved from 176.8 to 199.0 qps (+12.6%), 64 clients improved from 2751.6 to 3109.5 qps (+13.0%), and 256 clients improved from 11794.4 to 12974.7 qps (+10.0%). Average client latency dropped by about 10% to 12%; the 64-client run still has mixed tail latency, with p99 changing from 35ms to 40ms and more slow RPC/IO outliers, so repeated runs are needed before treating that tail result as stable.
Contributor
🤖 CI Job Analysis
📊 Summary
❌ NO RETRY NEEDEDAll failures appear to be code/test issues requiring manual fixes. 🔍 Job Details
🤖 AboutAutomated analysis using job annotations to distinguish infrastructure issues (auto-retried) from code/test issues (manual fixes needed). |
xp-trumpet
approved these changes
May 14, 2026
Collaborator
xp-trumpet
left a comment
There was a problem hiding this comment.
@xp-trumpet reviewed 5 files and all commit messages.
Reviewable status:complete! all files reviewed, all discussions resolved (waiting on drmingdrmer).
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
I hereby agree to the terms of the CLA available at: https://docs.databend.com/dev/policies/cla/
Summary
perf: meta: Use released databend-meta optimization tags
Update Databend's external meta dependencies from local path patches to
the released databend-meta v260512.1.0 and databend-meta-client
v260205.9.0 tags.
The server-side databend-meta tag includes the raft-log 0.4.2 WAL flush
optimizations: bounded group-commit waiting, configurable flush batch
size, vectored batch writes, and flush latency percentile stats. It also
keeps the meta-side runtime and raft-log metrics needed to inspect the
effect of the batching change.
Refresh Cargo.lock so the workspace resolves the tagged packages from
databendlabs/databend-meta and picks up Openraft 0.10.0-alpha.20 through
those dependencies.
Include the 2026-05-14 benchmark report comparing the patched build with
ups/main. The report records the current binary version, dependency
versions, workload parameters, throughput, latency, raft-log batch
stats, and the observed throughput improvement.
Performance summary from the 2-node upsert_kv benchmark: 4 clients
improved from 176.8 to 199.0 qps (+12.6%), 64 clients improved from
2751.6 to 3109.5 qps (+13.0%), and 256 clients improved from 11794.4 to
12974.7 qps (+10.0%). Average client latency dropped by about 10% to
12%; the 64-client run still has mixed tail latency, with p99 changing
from 35ms to 40ms and more slow RPC/IO outliers, so repeated runs are
needed before treating that tail result as stable.
chore(meta): extend metabench metrics
chore(benchmark): improve meta cluster bench script
Tests
Type of change
Related Issues
This change is