github-actions[bot] commented on PR #8815: URL: https://github.com/apache/texera/pull/8815#issuecomment-5945982382
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 5 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `566efb8` 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/36967278991) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 372 | 0.227 | 26,306/35,687/35,687 us | 🔴 +5.9% / 🔴 +132.9% | | 🟢 | bs=100 sw=10 sl=64 | 780 | 0.476 | 125,677/166,388/166,388 us | 🟢 -6.4% / 🔴 +59.1% | | 🔴 | bs=1000 sw=10 sl=64 | 898 | 0.548 | 1,107,255/1,272,950/1,272,950 us | 🔴 +10.8% / 🔴 +27.1% | <details><summary>Baseline details</summary> Latest main `566efb8` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 372 tuples/sec | 393 tuples/sec | 829.66 tuples/sec | -5.3% | -55.2% | | bs=10 sw=10 sl=64 | MB/s | 0.227 MB/s | 0.24 MB/s | 0.506 MB/s | -5.4% | -55.2% | | bs=10 sw=10 sl=64 | p50 | 26,306 us | 24,852 us | 12,230 us | +5.9% | +115.1% | | bs=10 sw=10 sl=64 | p95 | 35,687 us | 37,703 us | 15,320 us | -5.3% | +132.9% | | bs=10 sw=10 sl=64 | p99 | 35,687 us | 37,703 us | 18,789 us | -5.3% | +89.9% | | bs=100 sw=10 sl=64 | throughput | 780 tuples/sec | 788 tuples/sec | 1,070 tuples/sec | -1.0% | -27.1% | | bs=100 sw=10 sl=64 | MB/s | 0.476 MB/s | 0.481 MB/s | 0.653 MB/s | -1.0% | -27.1% | | bs=100 sw=10 sl=64 | p50 | 125,677 us | 119,757 us | 97,964 us | +4.9% | +28.3% | | bs=100 sw=10 sl=64 | p95 | 166,388 us | 177,840 us | 104,605 us | -6.4% | +59.1% | | bs=100 sw=10 sl=64 | p99 | 166,388 us | 177,840 us | 113,908 us | -6.4% | +46.1% | | bs=1000 sw=10 sl=64 | throughput | 898 tuples/sec | 915 tuples/sec | 1,096 tuples/sec | -1.9% | -18.1% | | bs=1000 sw=10 sl=64 | MB/s | 0.548 MB/s | 0.559 MB/s | 0.669 MB/s | -2.0% | -18.1% | | bs=1000 sw=10 sl=64 | p50 | 1,107,255 us | 1,092,078 us | 963,379 us | +1.4% | +14.9% | | bs=1000 sw=10 sl=64 | p95 | 1,272,950 us | 1,149,195 us | 1,001,808 us | +10.8% | +27.1% | | bs=1000 sw=10 sl=64 | p99 | 1,272,950 us | 1,149,195 us | 1,029,482 us | +10.8% | +23.6% | </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 0,10,10,64,20,537.90,200,128000,372,0.227,26306.36,35686.72,35686.72 1,100,10,64,20,2565.03,2000,1280000,780,0.476,125676.59,166387.72,166387.72 2,1000,10,64,20,22275.49,20000,12800000,898,0.548,1107254.60,1272950.45,1272950.45 ``` </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]
