Add fluss-microbench module with YAML-driven perf framework and JMH benchmarks#3082
Open
platinumhamburg wants to merge 1 commit intoapache:mainfrom
Open
Add fluss-microbench module with YAML-driven perf framework and JMH benchmarks#3082platinumhamburg wants to merge 1 commit intoapache:mainfrom
platinumhamburg wants to merge 1 commit intoapache:mainfrom
Conversation
…enchmarks Unified benchmarking module combining YAML-driven performance testing (write/lookup/scan/mixed workloads with resource sampling and reporting) and JMH micro-benchmarks (Arrow channel, log scanner). Key features: - MICROBENCH_ROOT-based output layout (.microbench/runs/datasets/baselines) - Auto-managed latest/previous symlinks per scenario for iterative comparison - --diff-previous and --diff-baseline flags for regression detection - Forked server log capture (logs/server-0.log) and run.log tee - 5 built-in presets: log-append, kv-upsert-get, kv-agg-mixed/listagg/rbm32 - Contributor guide at website/community/dev/benchmarking.md CLI design: workload parameters (records, threads, warmup, duration) are YAML-only and cannot be overridden via CLI, ensuring every benchmark report is statistically reliable. Warmup semantics are per-phase global (divided by threads internally). Validator enforces warmup < records/2, effective records per thread >= 10,000, and unique phase names per scenario. Phase names support type-prefix convention (e.g. write-bulk, write-sustained) resolved via longest-prefix matching to PhaseType. Preset tuning: thread counts capped at 8/4, warmup 500K global for JIT C2 coverage, duration-based write phases (5m) for stable measurement windows, scan warmup for cold-start elimination.
platinumhamburg
force-pushed
the
feature/fluss-perf
branch
from
7aab658 to
4daa284
Compare
platinumhamburg
changed the title
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
1 participant
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.
Unified benchmarking module combining YAML-driven performance testing (write/lookup/scan/mixed workloads with resource sampling and reporting) and JMH micro-benchmarks (Arrow channel, log scanner).
Key features:
CLI design: workload parameters (records, threads, warmup, duration) are YAML-only and cannot be overridden via CLI, ensuring every benchmark report is statistically reliable. Warmup semantics are per-phase global (divided by threads internally). Validator enforces warmup < records/2, effective records per thread >= 10,000, and unique phase names per scenario.
Phase names support type-prefix convention (e.g. write-bulk, write-sustained) resolved via longest-prefix matching to PhaseType. Preset tuning: thread counts capped at 8/4, warmup 500K global for JIT C2 coverage, duration-based write phases (5m) for stable measurement windows, scan warmup for cold-start elimination.
Purpose
Linked issue: close #3080
Brief change log
Tests
API and Format
Documentation