github-actions[bot] commented on PR #6226: URL: https://github.com/apache/texera/pull/6226#issuecomment-4904397814
<!-- texera-benchmarks-comment --> ## ✅ No material benchmark regressions detected 🟢 5 better · 🔴 0 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `40526b8` 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/28869163475) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 648 | 0.395 | 14,230/23,661/23,661 us | 🟢 -33.6% / 🔴 +53.9% | | ⚪ | bs=100 sw=10 sl=64 | 1,592 | 0.972 | 61,334/77,250/77,250 us | ⚪ within ±5% / 🟢 +60.2% | | ⚪ | bs=1000 sw=10 sl=64 | 1,907 | 1.164 | 524,614/542,663/542,663 us | ⚪ within ±5% / 🟢 +85.7% | <details><summary>Baseline details</summary> Latest main `40526b8` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 648 tuples/sec | 610 tuples/sec | 776.68 tuples/sec | +6.2% | -16.6% | | bs=10 sw=10 sl=64 | MB/s | 0.395 MB/s | 0.372 MB/s | 0.474 MB/s | +6.2% | -16.7% | | bs=10 sw=10 sl=64 | p50 | 14,230 us | 15,004 us | 12,599 us | -5.2% | +12.9% | | bs=10 sw=10 sl=64 | p95 | 23,661 us | 35,642 us | 15,370 us | -33.6% | +53.9% | | bs=10 sw=10 sl=64 | p99 | 23,661 us | 35,642 us | 18,723 us | -33.6% | +26.4% | | bs=100 sw=10 sl=64 | throughput | 1,592 tuples/sec | 1,655 tuples/sec | 994.07 tuples/sec | -3.8% | +60.1% | | bs=100 sw=10 sl=64 | MB/s | 0.972 MB/s | 1.01 MB/s | 0.607 MB/s | -3.8% | +60.2% | | bs=100 sw=10 sl=64 | p50 | 61,334 us | 58,898 us | 100,754 us | +4.1% | -39.1% | | bs=100 sw=10 sl=64 | p95 | 77,250 us | 79,367 us | 106,898 us | -2.7% | -27.7% | | bs=100 sw=10 sl=64 | p99 | 77,250 us | 79,367 us | 113,210 us | -2.7% | -31.8% | | bs=1000 sw=10 sl=64 | throughput | 1,907 tuples/sec | 1,941 tuples/sec | 1,027 tuples/sec | -1.8% | +85.7% | | bs=1000 sw=10 sl=64 | MB/s | 1.164 MB/s | 1.184 MB/s | 0.627 MB/s | -1.7% | +85.7% | | bs=1000 sw=10 sl=64 | p50 | 524,614 us | 514,273 us | 979,814 us | +2.0% | -46.5% | | bs=1000 sw=10 sl=64 | p95 | 542,663 us | 537,427 us | 1,019,689 us | +1.0% | -46.8% | | bs=1000 sw=10 sl=64 | p99 | 542,663 us | 537,427 us | 1,049,906 us | +1.0% | -48.3% | </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 0,10,10,64,20,308.72,200,128000,648,0.395,14229.74,23661.45,23661.45 1,100,10,64,20,1256.10,2000,1280000,1592,0.972,61333.78,77249.92,77249.92 2,1000,10,64,20,10489.38,20000,12800000,1907,1.164,524614.24,542663.13,542663.13 ``` </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]
