github-actions[bot] commented on PR #7932: URL: https://github.com/apache/texera/pull/7932#issuecomment-5399982213
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 5 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `6b8027e` 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/32765482469) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 586 | 0.357 | 16,301/24,717/24,717 us | 🔴 +16.3% / 🔴 +75.7% | | 🟢 | bs=100 sw=10 sl=64 | 1,297 | 0.792 | 75,078/92,339/92,339 us | 🟢 -5.2% / 🟢 -16.5% | | 🟢 | bs=1000 sw=10 sl=64 | 1,551 | 0.947 | 650,418/699,415/699,415 us | 🟢 -5.2% / 🟢 +34.3% | <details><summary>Baseline details</summary> Latest main `6b8027e` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 586 tuples/sec | 642 tuples/sec | 863.81 tuples/sec | -8.7% | -32.2% | | bs=10 sw=10 sl=64 | MB/s | 0.357 MB/s | 0.392 MB/s | 0.527 MB/s | -8.9% | -32.3% | | bs=10 sw=10 sl=64 | p50 | 16,301 us | 14,919 us | 11,488 us | +9.3% | +41.9% | | bs=10 sw=10 sl=64 | p95 | 24,717 us | 21,247 us | 14,067 us | +16.3% | +75.7% | | bs=10 sw=10 sl=64 | p99 | 24,717 us | 21,247 us | 17,591 us | +16.3% | +40.5% | | bs=100 sw=10 sl=64 | throughput | 1,297 tuples/sec | 1,327 tuples/sec | 1,127 tuples/sec | -2.3% | +15.1% | | bs=100 sw=10 sl=64 | MB/s | 0.792 MB/s | 0.81 MB/s | 0.688 MB/s | -2.2% | +15.1% | | bs=100 sw=10 sl=64 | p50 | 75,078 us | 74,014 us | 89,893 us | +1.4% | -16.5% | | bs=100 sw=10 sl=64 | p95 | 92,339 us | 97,374 us | 96,506 us | -5.2% | -4.3% | | bs=100 sw=10 sl=64 | p99 | 92,339 us | 97,374 us | 104,915 us | -5.2% | -12.0% | | bs=1000 sw=10 sl=64 | throughput | 1,551 tuples/sec | 1,517 tuples/sec | 1,156 tuples/sec | +2.2% | +34.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.947 MB/s | 0.926 MB/s | 0.705 MB/s | +2.3% | +34.3% | | bs=1000 sw=10 sl=64 | p50 | 650,418 us | 662,275 us | 886,448 us | -1.8% | -26.6% | | bs=1000 sw=10 sl=64 | p95 | 699,415 us | 737,537 us | 930,093 us | -5.2% | -24.8% | | bs=1000 sw=10 sl=64 | p99 | 699,415 us | 737,537 us | 963,104 us | -5.2% | -27.4% | </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 0,10,10,64,20,341.47,200,128000,586,0.357,16301.18,24717.43,24717.43 1,100,10,64,20,1541.60,2000,1280000,1297,0.792,75077.86,92338.54,92338.54 2,1000,10,64,20,12891.61,20000,12800000,1551,0.947,650418.38,699414.54,699414.54 ``` </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]
