github-actions[bot] commented on PR #7231: URL: https://github.com/apache/texera/pull/7231#issuecomment-5150346518
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 1 better · 🔴 2 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `18ebb0d` benchmarked on **this same runner**, so the delta is largely free of cross-runner hardware noise. The "7d avg" column still reflects the gh-pages dashboard. Treat <±5% as noise unless repeated. [Dashboard](https://apache.github.io/texera/dev/bench/) · [Run](https://github.com/apache/texera/actions/runs/30689037071) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 423 | 0.258 | 21,860/31,653/31,653 us | 🟢 -8.1% / 🔴 +95.4% | | ⚪ | bs=100 sw=10 sl=64 | 834 | 0.509 | 118,950/154,968/154,968 us | ⚪ within ±5% / 🔴 +39.9% | | 🔴 | bs=1000 sw=10 sl=64 | 913 | 0.557 | 1,092,733/1,221,304/1,221,304 us | 🔴 +7.9% / 🔴 +14.9% | <details><summary>Baseline details</summary> Latest main `18ebb0d` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 423 tuples/sec | 432 tuples/sec | 765.25 tuples/sec | -2.1% | -44.7% | | bs=10 sw=10 sl=64 | MB/s | 0.258 MB/s | 0.264 MB/s | 0.467 MB/s | -2.3% | -44.8% | | bs=10 sw=10 sl=64 | p50 | 21,860 us | 23,784 us | 12,703 us | -8.1% | +72.1% | | bs=10 sw=10 sl=64 | p95 | 31,653 us | 31,664 us | 16,199 us | -0.0% | +95.4% | | bs=10 sw=10 sl=64 | p99 | 31,653 us | 31,664 us | 19,557 us | -0.0% | +61.8% | | bs=100 sw=10 sl=64 | throughput | 834 tuples/sec | 832 tuples/sec | 965.22 tuples/sec | +0.2% | -13.6% | | bs=100 sw=10 sl=64 | MB/s | 0.509 MB/s | 0.508 MB/s | 0.589 MB/s | +0.2% | -13.6% | | bs=100 sw=10 sl=64 | p50 | 118,950 us | 117,869 us | 103,830 us | +0.9% | +14.6% | | bs=100 sw=10 sl=64 | p95 | 154,968 us | 149,871 us | 110,778 us | +3.4% | +39.9% | | bs=100 sw=10 sl=64 | p99 | 154,968 us | 149,871 us | 118,713 us | +3.4% | +30.5% | | bs=1000 sw=10 sl=64 | throughput | 913 tuples/sec | 924 tuples/sec | 992.33 tuples/sec | -1.2% | -8.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.557 MB/s | 0.564 MB/s | 0.606 MB/s | -1.2% | -8.0% | | bs=1000 sw=10 sl=64 | p50 | 1,092,733 us | 1,083,634 us | 1,016,959 us | +0.8% | +7.5% | | bs=1000 sw=10 sl=64 | p95 | 1,221,304 us | 1,131,759 us | 1,062,501 us | +7.9% | +14.9% | | bs=1000 sw=10 sl=64 | p99 | 1,221,304 us | 1,131,759 us | 1,082,611 us | +7.9% | +12.8% | </details> <details><summary>Raw CSV</summary> ```csv config_idx,batch_size,schema_width,string_len,num_batches,total_ms,total_tuples,total_bytes,tuples_per_sec,mb_per_sec,lat_p50_us,lat_p95_us,lat_p99_us 0,10,10,64,20,472.93,200,128000,423,0.258,21860.15,31652.66,31652.66 1,100,10,64,20,2399.20,2000,1280000,834,0.509,118950.13,154968.42,154968.42 2,1000,10,64,20,21914.24,20000,12800000,913,0.557,1092733.32,1221303.55,1221303.55 ``` </details> -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
