github-actions[bot] commented on PR #8969: URL: https://github.com/apache/texera/pull/8969#issuecomment-6138405763
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 7 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `6a29c59` 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/38346537962) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 495 | 0.302 | 19,581/24,795/24,795 us | 🔴 +20.5% / 🔴 +58.2% | | 🔴 | bs=100 sw=10 sl=64 | 1,171 | 0.715 | 83,483/103,590/103,590 us | 🔴 +10.1% / 🟢 -15.5% | | ⚪ | bs=1000 sw=10 sl=64 | 1,395 | 0.852 | 718,769/797,246/797,246 us | ⚪ within ±5% / 🟢 +31.8% | <details><summary>Baseline details</summary> Latest main `6a29c59` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 495 tuples/sec | 569 tuples/sec | 790.31 tuples/sec | -13.0% | -37.4% | | bs=10 sw=10 sl=64 | MB/s | 0.302 MB/s | 0.347 MB/s | 0.482 MB/s | -13.0% | -37.4% | | bs=10 sw=10 sl=64 | p50 | 19,581 us | 16,249 us | 12,375 us | +20.5% | +58.2% | | bs=10 sw=10 sl=64 | p95 | 24,795 us | 28,620 us | 15,719 us | -13.4% | +57.7% | | bs=10 sw=10 sl=64 | p99 | 24,795 us | 28,620 us | 19,058 us | -13.4% | +30.1% | | bs=100 sw=10 sl=64 | throughput | 1,171 tuples/sec | 1,244 tuples/sec | 1,025 tuples/sec | -5.9% | +14.3% | | bs=100 sw=10 sl=64 | MB/s | 0.715 MB/s | 0.76 MB/s | 0.626 MB/s | -5.9% | +14.3% | | bs=100 sw=10 sl=64 | p50 | 83,483 us | 80,670 us | 98,759 us | +3.5% | -15.5% | | bs=100 sw=10 sl=64 | p95 | 103,590 us | 94,108 us | 105,327 us | +10.1% | -1.6% | | bs=100 sw=10 sl=64 | p99 | 103,590 us | 94,108 us | 120,491 us | +10.1% | -14.0% | | bs=1000 sw=10 sl=64 | throughput | 1,395 tuples/sec | 1,422 tuples/sec | 1,059 tuples/sec | -1.9% | +31.7% | | bs=1000 sw=10 sl=64 | MB/s | 0.852 MB/s | 0.868 MB/s | 0.646 MB/s | -1.8% | +31.8% | | bs=1000 sw=10 sl=64 | p50 | 718,769 us | 702,840 us | 965,886 us | +2.3% | -25.6% | | bs=1000 sw=10 sl=64 | p95 | 797,246 us | 815,154 us | 1,007,533 us | -2.2% | -20.9% | | bs=1000 sw=10 sl=64 | p99 | 797,246 us | 815,154 us | 1,031,622 us | -2.2% | -22.7% | </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 0,10,10,64,20,404.14,200,128000,495,0.302,19581.33,24795.29,24795.29 1,100,10,64,20,1708.25,2000,1280000,1171,0.715,83483.00,103589.83,103589.83 2,1000,10,64,20,14333.54,20000,12800000,1395,0.852,718768.62,797245.89,797245.89 ``` </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]
