github-actions[bot] commented on PR #7441: URL: https://github.com/apache/texera/pull/7441#issuecomment-5230998198
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 10 worse · ⚪ 5 noise (<±5%) · 0 without baseline > Compared against main `fb1a5c4` 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/31307820907) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 371 | 0.226 | 26,088/36,002/36,002 us | 🔴 -9.6% / 🔴 +123.4% | | 🔴 | bs=100 sw=10 sl=64 | 766 | 0.467 | 127,082/156,554/156,554 us | 🔴 +16.4% / 🔴 +40.8% | | 🔴 | bs=1000 sw=10 sl=64 | 886 | 0.541 | 1,115,404/1,469,758/1,469,758 us | 🔴 +28.1% / 🔴 +38.3% | <details><summary>Baseline details</summary> Latest main `fb1a5c4` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 371 tuples/sec | 409 tuples/sec | 752.25 tuples/sec | -9.3% | -50.7% | | bs=10 sw=10 sl=64 | MB/s | 0.226 MB/s | 0.25 MB/s | 0.459 MB/s | -9.6% | -50.8% | | bs=10 sw=10 sl=64 | p50 | 26,088 us | 24,164 us | 13,006 us | +8.0% | +100.6% | | bs=10 sw=10 sl=64 | p95 | 36,002 us | 34,726 us | 16,117 us | +3.7% | +123.4% | | bs=10 sw=10 sl=64 | p99 | 36,002 us | 34,726 us | 19,286 us | +3.7% | +86.7% | | bs=100 sw=10 sl=64 | throughput | 766 tuples/sec | 819 tuples/sec | 953.66 tuples/sec | -6.5% | -19.7% | | bs=100 sw=10 sl=64 | MB/s | 0.467 MB/s | 0.5 MB/s | 0.582 MB/s | -6.6% | -19.8% | | bs=100 sw=10 sl=64 | p50 | 127,082 us | 120,097 us | 105,130 us | +5.8% | +20.9% | | bs=100 sw=10 sl=64 | p95 | 156,554 us | 134,496 us | 111,226 us | +16.4% | +40.8% | | bs=100 sw=10 sl=64 | p99 | 156,554 us | 134,496 us | 121,065 us | +16.4% | +29.3% | | bs=1000 sw=10 sl=64 | throughput | 886 tuples/sec | 905 tuples/sec | 984.25 tuples/sec | -2.1% | -10.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.541 MB/s | 0.553 MB/s | 0.601 MB/s | -2.2% | -9.9% | | bs=1000 sw=10 sl=64 | p50 | 1,115,404 us | 1,106,398 us | 1,024,295 us | +0.8% | +8.9% | | bs=1000 sw=10 sl=64 | p95 | 1,469,758 us | 1,146,930 us | 1,062,710 us | +28.1% | +38.3% | | bs=1000 sw=10 sl=64 | p99 | 1,469,758 us | 1,146,930 us | 1,095,400 us | +28.1% | +34.2% | </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 0,10,10,64,20,539.37,200,128000,371,0.226,26087.85,36002.31,36002.31 1,100,10,64,20,2612.65,2000,1280000,766,0.467,127081.80,156553.73,156553.73 2,1000,10,64,20,22567.33,20000,12800000,886,0.541,1115403.63,1469757.72,1469757.72 ``` </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]
