github-actions[bot] commented on PR #6897: URL: https://github.com/apache/texera/pull/6897#issuecomment-5080503862
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 6 better · 🔴 4 worse · ⚪ 5 noise (<±5%) · 0 without baseline > Compared against main `57d4dba` 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/30174004149) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 644 | 0.393 | 15,660/18,388/18,388 us | 🟢 -20.4% / 🔴 +22.2% | | 🔴 | bs=100 sw=10 sl=64 | 1,315 | 0.803 | 75,582/99,481/99,481 us | 🟢 -14.9% / 🟢 +35.7% | | 🟢 | bs=1000 sw=10 sl=64 | 1,599 | 0.976 | 624,123/659,629/659,629 us | 🟢 -5.8% / 🟢 +59.3% | <details><summary>Baseline details</summary> Latest main `57d4dba` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 644 tuples/sec | 683 tuples/sec | 754.55 tuples/sec | -5.7% | -14.7% | | bs=10 sw=10 sl=64 | MB/s | 0.393 MB/s | 0.417 MB/s | 0.461 MB/s | -5.8% | -14.7% | | bs=10 sw=10 sl=64 | p50 | 15,660 us | 14,754 us | 12,816 us | +6.1% | +22.2% | | bs=10 sw=10 sl=64 | p95 | 18,388 us | 23,087 us | 16,594 us | -20.4% | +10.8% | | bs=10 sw=10 sl=64 | p99 | 18,388 us | 23,087 us | 19,806 us | -20.4% | -7.2% | | bs=100 sw=10 sl=64 | throughput | 1,315 tuples/sec | 1,366 tuples/sec | 969.38 tuples/sec | -3.7% | +35.7% | | bs=100 sw=10 sl=64 | MB/s | 0.803 MB/s | 0.834 MB/s | 0.592 MB/s | -3.7% | +35.7% | | bs=100 sw=10 sl=64 | p50 | 75,582 us | 68,800 us | 103,584 us | +9.9% | -27.0% | | bs=100 sw=10 sl=64 | p95 | 99,481 us | 116,853 us | 109,097 us | -14.9% | -8.8% | | bs=100 sw=10 sl=64 | p99 | 99,481 us | 116,853 us | 117,304 us | -14.9% | -15.2% | | bs=1000 sw=10 sl=64 | throughput | 1,599 tuples/sec | 1,613 tuples/sec | 1,004 tuples/sec | -0.9% | +59.3% | | bs=1000 sw=10 sl=64 | MB/s | 0.976 MB/s | 0.985 MB/s | 0.613 MB/s | -0.9% | +59.3% | | bs=1000 sw=10 sl=64 | p50 | 624,123 us | 614,996 us | 1,002,357 us | +1.5% | -37.7% | | bs=1000 sw=10 sl=64 | p95 | 659,629 us | 699,890 us | 1,046,463 us | -5.8% | -37.0% | | bs=1000 sw=10 sl=64 | p99 | 659,629 us | 699,890 us | 1,073,661 us | -5.8% | -38.6% | </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 0,10,10,64,20,310.69,200,128000,644,0.393,15660.20,18388.07,18388.07 1,100,10,64,20,1520.35,2000,1280000,1315,0.803,75581.87,99481.33,99481.33 2,1000,10,64,20,12506.48,20000,12800000,1599,0.976,624122.59,659629.12,659629.12 ``` </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]
