github-actions[bot] commented on PR #8481: URL: https://github.com/apache/texera/pull/8481#issuecomment-5611907136
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 3 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `ec3a9dd` 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/34422088850) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 561 | 0.342 | 17,880/21,187/21,187 us | 🟢 -20.3% / 🔴 +38.1% | | 🟢 | bs=100 sw=10 sl=64 | 1,208 | 0.737 | 82,169/113,216/113,216 us | 🟢 -6.8% / 🟢 +23.0% | | ⚪ | bs=1000 sw=10 sl=64 | 1,381 | 0.843 | 723,610/777,698/777,698 us | ⚪ within ±5% / 🟢 +36.8% | <details><summary>Baseline details</summary> Latest main `ec3a9dd` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 561 tuples/sec | 604 tuples/sec | 754.83 tuples/sec | -7.1% | -25.7% | | bs=10 sw=10 sl=64 | MB/s | 0.342 MB/s | 0.369 MB/s | 0.461 MB/s | -7.3% | -25.8% | | bs=10 sw=10 sl=64 | p50 | 17,880 us | 16,306 us | 12,950 us | +9.7% | +38.1% | | bs=10 sw=10 sl=64 | p95 | 21,187 us | 26,569 us | 16,243 us | -20.3% | +30.4% | | bs=10 sw=10 sl=64 | p99 | 21,187 us | 26,569 us | 19,574 us | -20.3% | +8.2% | | bs=100 sw=10 sl=64 | throughput | 1,208 tuples/sec | 1,198 tuples/sec | 982.46 tuples/sec | +0.8% | +23.0% | | bs=100 sw=10 sl=64 | MB/s | 0.737 MB/s | 0.731 MB/s | 0.6 MB/s | +0.8% | +22.9% | | bs=100 sw=10 sl=64 | p50 | 82,169 us | 80,739 us | 101,575 us | +1.8% | -19.1% | | bs=100 sw=10 sl=64 | p95 | 113,216 us | 121,511 us | 108,655 us | -6.8% | +4.2% | | bs=100 sw=10 sl=64 | p99 | 113,216 us | 121,511 us | 121,794 us | -6.8% | -7.0% | | bs=1000 sw=10 sl=64 | throughput | 1,381 tuples/sec | 1,418 tuples/sec | 1,010 tuples/sec | -2.6% | +36.8% | | bs=1000 sw=10 sl=64 | MB/s | 0.843 MB/s | 0.866 MB/s | 0.616 MB/s | -2.7% | +36.8% | | bs=1000 sw=10 sl=64 | p50 | 723,610 us | 703,885 us | 998,032 us | +2.8% | -27.5% | | bs=1000 sw=10 sl=64 | p95 | 777,698 us | 774,429 us | 1,039,429 us | +0.4% | -25.2% | | bs=1000 sw=10 sl=64 | p99 | 777,698 us | 774,429 us | 1,068,120 us | +0.4% | -27.2% | </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 0,10,10,64,20,356.63,200,128000,561,0.342,17879.90,21187.16,21187.16 1,100,10,64,20,1655.55,2000,1280000,1208,0.737,82169.38,113216.14,113216.14 2,1000,10,64,20,14487.11,20000,12800000,1381,0.843,723610.04,777697.61,777697.61 ``` </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]
