github-actions[bot] commented on PR #5844: URL: https://github.com/apache/texera/pull/5844#issuecomment-4760929536
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 6 better · 🔴 1 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `6d31f46` 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/27893678207) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 429 | 0.262 | 23,105/30,769/30,769 us | 🟢 -9.6% / 🟢 -12.0% | | 🟢 | bs=100 sw=10 sl=64 | 960 | 0.586 | 105,525/119,751/119,751 us | 🟢 -26.9% / 🟢 -14.3% | | ⚪ | bs=1000 sw=10 sl=64 | 1,095 | 0.668 | 917,244/959,074/959,074 us | ⚪ within ±5% / 🟢 -6.3% | <details><summary>Baseline details</summary> Latest main `6d31f46` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 429 tuples/sec | 438 tuples/sec | 410.82 tuples/sec | -2.1% | +4.4% | | bs=10 sw=10 sl=64 | MB/s | 0.262 MB/s | 0.267 MB/s | 0.251 MB/s | -1.9% | +4.5% | | bs=10 sw=10 sl=64 | p50 | 23,105 us | 21,800 us | 23,785 us | +6.0% | -2.9% | | bs=10 sw=10 sl=64 | p95 | 30,769 us | 34,023 us | 34,980 us | -9.6% | -12.0% | | bs=10 sw=10 sl=64 | p99 | 30,769 us | 34,023 us | 34,980 us | -9.6% | -12.0% | | bs=100 sw=10 sl=64 | throughput | 960 tuples/sec | 884 tuples/sec | 891.94 tuples/sec | +8.6% | +7.6% | | bs=100 sw=10 sl=64 | MB/s | 0.586 MB/s | 0.54 MB/s | 0.544 MB/s | +8.5% | +7.6% | | bs=100 sw=10 sl=64 | p50 | 105,525 us | 108,113 us | 112,277 us | -2.4% | -6.0% | | bs=100 sw=10 sl=64 | p95 | 119,751 us | 163,887 us | 139,802 us | -26.9% | -14.3% | | bs=100 sw=10 sl=64 | p99 | 119,751 us | 163,887 us | 139,802 us | -26.9% | -14.3% | | bs=1000 sw=10 sl=64 | throughput | 1,095 tuples/sec | 1,128 tuples/sec | 1,041 tuples/sec | -2.9% | +5.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.668 MB/s | 0.689 MB/s | 0.635 MB/s | -3.0% | +5.1% | | bs=1000 sw=10 sl=64 | p50 | 917,244 us | 880,629 us | 972,714 us | +4.2% | -5.7% | | bs=1000 sw=10 sl=64 | p95 | 959,074 us | 954,899 us | 1,023,057 us | +0.4% | -6.3% | | bs=1000 sw=10 sl=64 | p99 | 959,074 us | 954,899 us | 1,023,057 us | +0.4% | -6.3% | </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 0,10,10,64,20,466.74,200,128000,429,0.262,23104.79,30768.86,30768.86 1,100,10,64,20,2083.31,2000,1280000,960,0.586,105525.44,119751.39,119751.39 2,1000,10,64,20,18267.28,20000,12800000,1095,0.668,917243.88,959074.08,959074.08 ``` </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]
