github-actions[bot] commented on PR #7570: URL: https://github.com/apache/texera/pull/7570#issuecomment-5258725716
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 2 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `e878df3` 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/31534691840) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 438 | 0.268 | 22,492/28,726/28,726 us | 🟢 -10.1% / 🔴 +79.6% | | 🟢 | bs=100 sw=10 sl=64 | 951 | 0.58 | 104,631/123,723/123,723 us | 🟢 -15.5% / 🔴 +14.5% | | ⚪ | bs=1000 sw=10 sl=64 | 1,121 | 0.684 | 897,078/950,156/950,156 us | ⚪ within ±5% / 🟢 -11.1% | <details><summary>Baseline details</summary> Latest main `e878df3` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 438 tuples/sec | 467 tuples/sec | 784.3 tuples/sec | -6.2% | -44.2% | | bs=10 sw=10 sl=64 | MB/s | 0.268 MB/s | 0.285 MB/s | 0.479 MB/s | -6.0% | -44.0% | | bs=10 sw=10 sl=64 | p50 | 22,492 us | 21,607 us | 12,590 us | +4.1% | +78.6% | | bs=10 sw=10 sl=64 | p95 | 28,726 us | 31,963 us | 15,991 us | -10.1% | +79.6% | | bs=10 sw=10 sl=64 | p99 | 28,726 us | 31,963 us | 18,694 us | -10.1% | +53.7% | | bs=100 sw=10 sl=64 | throughput | 951 tuples/sec | 942 tuples/sec | 1,002 tuples/sec | +1.0% | -5.1% | | bs=100 sw=10 sl=64 | MB/s | 0.58 MB/s | 0.575 MB/s | 0.612 MB/s | +0.9% | -5.2% | | bs=100 sw=10 sl=64 | p50 | 104,631 us | 104,679 us | 101,285 us | -0.0% | +3.3% | | bs=100 sw=10 sl=64 | p95 | 123,723 us | 146,370 us | 108,068 us | -15.5% | +14.5% | | bs=100 sw=10 sl=64 | p99 | 123,723 us | 146,370 us | 118,235 us | -15.5% | +4.6% | | bs=1000 sw=10 sl=64 | throughput | 1,121 tuples/sec | 1,119 tuples/sec | 1,030 tuples/sec | +0.2% | +8.8% | | bs=1000 sw=10 sl=64 | MB/s | 0.684 MB/s | 0.683 MB/s | 0.629 MB/s | +0.1% | +8.8% | | bs=1000 sw=10 sl=64 | p50 | 897,078 us | 899,712 us | 991,882 us | -0.3% | -9.6% | | bs=1000 sw=10 sl=64 | p95 | 950,156 us | 940,496 us | 1,038,496 us | +1.0% | -8.5% | | bs=1000 sw=10 sl=64 | p99 | 950,156 us | 940,496 us | 1,068,265 us | +1.0% | -11.1% | </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 0,10,10,64,20,456.29,200,128000,438,0.268,22491.61,28725.82,28725.82 1,100,10,64,20,2103.58,2000,1280000,951,0.580,104631.10,123722.59,123722.59 2,1000,10,64,20,17841.11,20000,12800000,1121,0.684,897077.67,950156.44,950156.44 ``` </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]
