github-actions[bot] commented on PR #8794: URL: https://github.com/apache/texera/pull/8794#issuecomment-5920157888
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 5 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `98d3d4b` 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/36777747274) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 510 | 0.311 | 19,206/23,368/23,368 us | 🟢 -19.4% / 🔴 +54.8% | | 🟢 | bs=100 sw=10 sl=64 | 1,192 | 0.727 | 83,976/102,781/102,781 us | 🟢 -20.7% / 🟢 -15.3% | | 🔴 | bs=1000 sw=10 sl=64 | 1,406 | 0.858 | 712,477/777,434/777,434 us | 🔴 +8.6% / 🟢 +29.3% | <details><summary>Baseline details</summary> Latest main `98d3d4b` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 510 tuples/sec | 547 tuples/sec | 818.62 tuples/sec | -6.8% | -37.7% | | bs=10 sw=10 sl=64 | MB/s | 0.311 MB/s | 0.334 MB/s | 0.5 MB/s | -6.9% | -37.8% | | bs=10 sw=10 sl=64 | p50 | 19,206 us | 17,754 us | 12,404 us | +8.2% | +54.8% | | bs=10 sw=10 sl=64 | p95 | 23,368 us | 29,004 us | 15,787 us | -19.4% | +48.0% | | bs=10 sw=10 sl=64 | p99 | 23,368 us | 29,004 us | 18,928 us | -19.4% | +23.5% | | bs=100 sw=10 sl=64 | throughput | 1,192 tuples/sec | 1,145 tuples/sec | 1,058 tuples/sec | +4.1% | +12.6% | | bs=100 sw=10 sl=64 | MB/s | 0.727 MB/s | 0.699 MB/s | 0.646 MB/s | +4.0% | +12.6% | | bs=100 sw=10 sl=64 | p50 | 83,976 us | 81,707 us | 99,149 us | +2.8% | -15.3% | | bs=100 sw=10 sl=64 | p95 | 102,781 us | 129,653 us | 106,165 us | -20.7% | -3.2% | | bs=100 sw=10 sl=64 | p99 | 102,781 us | 129,653 us | 114,997 us | -20.7% | -10.6% | | bs=1000 sw=10 sl=64 | throughput | 1,406 tuples/sec | 1,437 tuples/sec | 1,088 tuples/sec | -2.2% | +29.3% | | bs=1000 sw=10 sl=64 | MB/s | 0.858 MB/s | 0.877 MB/s | 0.664 MB/s | -2.2% | +29.2% | | bs=1000 sw=10 sl=64 | p50 | 712,477 us | 700,818 us | 971,066 us | +1.7% | -26.6% | | bs=1000 sw=10 sl=64 | p95 | 777,434 us | 715,767 us | 1,011,680 us | +8.6% | -23.2% | | bs=1000 sw=10 sl=64 | p99 | 777,434 us | 715,767 us | 1,037,719 us | +8.6% | -25.1% | </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 0,10,10,64,20,392.29,200,128000,510,0.311,19206.16,23367.83,23367.83 1,100,10,64,20,1678.09,2000,1280000,1192,0.727,83976.41,102780.80,102780.80 2,1000,10,64,20,14227.13,20000,12800000,1406,0.858,712476.60,777434.35,777434.35 ``` </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]
