github-actions[bot] commented on PR #7243: URL: https://github.com/apache/texera/pull/7243#issuecomment-5152659705
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 6 worse · ⚪ 7 noise (<±5%) · 0 without baseline > Compared against main `33cc5d1` 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/30711197153) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 648 | 0.396 | 15,487/18,990/18,990 us | 🟢 -15.8% / 🔴 +24.2% | | 🔴 | bs=100 sw=10 sl=64 | 1,192 | 0.728 | 82,819/107,204/107,204 us | 🔴 +21.6% / 🟢 +19.6% | | 🔴 | bs=1000 sw=10 sl=64 | 1,509 | 0.921 | 665,845/730,229/730,229 us | 🔴 +6.2% / 🟢 +47.4% | <details><summary>Baseline details</summary> Latest main `33cc5d1` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 648 tuples/sec | 627 tuples/sec | 782.98 tuples/sec | +3.3% | -17.2% | | bs=10 sw=10 sl=64 | MB/s | 0.396 MB/s | 0.383 MB/s | 0.478 MB/s | +3.4% | -17.1% | | bs=10 sw=10 sl=64 | p50 | 15,487 us | 15,900 us | 12,467 us | -2.6% | +24.2% | | bs=10 sw=10 sl=64 | p95 | 18,990 us | 22,553 us | 15,695 us | -15.8% | +21.0% | | bs=10 sw=10 sl=64 | p99 | 18,990 us | 22,553 us | 18,950 us | -15.8% | +0.2% | | bs=100 sw=10 sl=64 | throughput | 1,192 tuples/sec | 1,384 tuples/sec | 996.92 tuples/sec | -13.9% | +19.6% | | bs=100 sw=10 sl=64 | MB/s | 0.728 MB/s | 0.844 MB/s | 0.608 MB/s | -13.7% | +19.6% | | bs=100 sw=10 sl=64 | p50 | 82,819 us | 71,384 us | 100,899 us | +16.0% | -17.9% | | bs=100 sw=10 sl=64 | p95 | 107,204 us | 88,139 us | 107,385 us | +21.6% | -0.2% | | bs=100 sw=10 sl=64 | p99 | 107,204 us | 88,139 us | 115,226 us | +21.6% | -7.0% | | bs=1000 sw=10 sl=64 | throughput | 1,509 tuples/sec | 1,588 tuples/sec | 1,024 tuples/sec | -5.0% | +47.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.921 MB/s | 0.969 MB/s | 0.625 MB/s | -5.0% | +47.4% | | bs=1000 sw=10 sl=64 | p50 | 665,845 us | 627,160 us | 989,300 us | +6.2% | -32.7% | | bs=1000 sw=10 sl=64 | p95 | 730,229 us | 697,069 us | 1,031,689 us | +4.8% | -29.2% | | bs=1000 sw=10 sl=64 | p99 | 730,229 us | 697,069 us | 1,058,394 us | +4.8% | -31.0% | </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 0,10,10,64,20,308.57,200,128000,648,0.396,15487.04,18989.69,18989.69 1,100,10,64,20,1677.48,2000,1280000,1192,0.728,82819.19,107204.45,107204.45 2,1000,10,64,20,13250.38,20000,12800000,1509,0.921,665844.80,730229.45,730229.45 ``` </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]
