github-actions[bot] commented on PR #7577: URL: https://github.com/apache/texera/pull/7577#issuecomment-5259299053
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 4 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `e878df3` 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/31539651554) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 426 | 0.26 | 22,022/30,665/30,665 us | 🟢 -9.9% / 🔴 +91.8% | | 🔴 | bs=100 sw=10 sl=64 | 910 | 0.556 | 106,504/147,079/147,079 us | 🔴 +16.9% / 🔴 +36.1% | | 🔴 | bs=1000 sw=10 sl=64 | 1,078 | 0.658 | 922,596/1,024,055/1,024,055 us | 🔴 +6.4% / 🟢 -7.0% | <details><summary>Baseline details</summary> Latest main `e878df3` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 426 tuples/sec | 445 tuples/sec | 784.3 tuples/sec | -4.3% | -45.7% | | bs=10 sw=10 sl=64 | MB/s | 0.26 MB/s | 0.271 MB/s | 0.479 MB/s | -4.1% | -45.7% | | bs=10 sw=10 sl=64 | p50 | 22,022 us | 22,060 us | 12,590 us | -0.2% | +74.9% | | bs=10 sw=10 sl=64 | p95 | 30,665 us | 34,028 us | 15,991 us | -9.9% | +91.8% | | bs=10 sw=10 sl=64 | p99 | 30,665 us | 34,028 us | 18,694 us | -9.9% | +64.0% | | bs=100 sw=10 sl=64 | throughput | 910 tuples/sec | 954 tuples/sec | 1,002 tuples/sec | -4.6% | -9.2% | | bs=100 sw=10 sl=64 | MB/s | 0.556 MB/s | 0.582 MB/s | 0.612 MB/s | -4.5% | -9.1% | | bs=100 sw=10 sl=64 | p50 | 106,504 us | 102,405 us | 101,285 us | +4.0% | +5.2% | | bs=100 sw=10 sl=64 | p95 | 147,079 us | 125,840 us | 108,068 us | +16.9% | +36.1% | | bs=100 sw=10 sl=64 | p99 | 147,079 us | 125,840 us | 118,235 us | +16.9% | +24.4% | | bs=1000 sw=10 sl=64 | throughput | 1,078 tuples/sec | 1,091 tuples/sec | 1,030 tuples/sec | -1.2% | +4.7% | | bs=1000 sw=10 sl=64 | MB/s | 0.658 MB/s | 0.666 MB/s | 0.629 MB/s | -1.2% | +4.7% | | bs=1000 sw=10 sl=64 | p50 | 922,596 us | 916,616 us | 991,882 us | +0.7% | -7.0% | | bs=1000 sw=10 sl=64 | p95 | 1,024,055 us | 962,907 us | 1,038,496 us | +6.4% | -1.4% | | bs=1000 sw=10 sl=64 | p99 | 1,024,055 us | 962,907 us | 1,068,265 us | +6.4% | -4.1% | </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 0,10,10,64,20,470.03,200,128000,426,0.260,22021.69,30664.64,30664.64 1,100,10,64,20,2196.68,2000,1280000,910,0.556,106503.94,147079.27,147079.27 2,1000,10,64,20,18546.60,20000,12800000,1078,0.658,922595.51,1024054.70,1024054.70 ``` </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]
