github-actions[bot] commented on PR #7156: URL: https://github.com/apache/texera/pull/7156#issuecomment-5139219703
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `45b7b20` 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/30603627885) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 494 | 0.301 | 19,815/27,874/27,874 us | 🔴 -5.0% / 🔴 +76.6% | | 🔴 | bs=100 sw=10 sl=64 | 1,007 | 0.615 | 97,177/142,829/142,829 us | 🔴 +15.0% / 🔴 +29.5% | | 🟢 | bs=1000 sw=10 sl=64 | 1,216 | 0.742 | 824,387/849,250/849,250 us | 🟢 -6.9% / 🟢 +21.4% | <details><summary>Baseline details</summary> Latest main `45b7b20` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 494 tuples/sec | 520 tuples/sec | 771.62 tuples/sec | -5.0% | -36.0% | | bs=10 sw=10 sl=64 | MB/s | 0.301 MB/s | 0.317 MB/s | 0.471 MB/s | -5.0% | -36.1% | | bs=10 sw=10 sl=64 | p50 | 19,815 us | 18,887 us | 12,626 us | +4.9% | +56.9% | | bs=10 sw=10 sl=64 | p95 | 27,874 us | 27,371 us | 15,786 us | +1.8% | +76.6% | | bs=10 sw=10 sl=64 | p99 | 27,874 us | 27,371 us | 19,344 us | +1.8% | +44.1% | | bs=100 sw=10 sl=64 | throughput | 1,007 tuples/sec | 1,034 tuples/sec | 971.56 tuples/sec | -2.6% | +3.6% | | bs=100 sw=10 sl=64 | MB/s | 0.615 MB/s | 0.631 MB/s | 0.593 MB/s | -2.5% | +3.7% | | bs=100 sw=10 sl=64 | p50 | 97,177 us | 93,493 us | 103,463 us | +3.9% | -6.1% | | bs=100 sw=10 sl=64 | p95 | 142,829 us | 124,197 us | 110,296 us | +15.0% | +29.5% | | bs=100 sw=10 sl=64 | p99 | 142,829 us | 124,197 us | 118,690 us | +15.0% | +20.3% | | bs=1000 sw=10 sl=64 | throughput | 1,216 tuples/sec | 1,203 tuples/sec | 1,001 tuples/sec | +1.1% | +21.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.742 MB/s | 0.735 MB/s | 0.611 MB/s | +1.0% | +21.4% | | bs=1000 sw=10 sl=64 | p50 | 824,387 us | 826,186 us | 1,008,988 us | -0.2% | -18.3% | | bs=1000 sw=10 sl=64 | p95 | 849,250 us | 911,779 us | 1,055,260 us | -6.9% | -19.5% | | bs=1000 sw=10 sl=64 | p99 | 849,250 us | 911,779 us | 1,074,689 us | -6.9% | -21.0% | </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 0,10,10,64,20,404.98,200,128000,494,0.301,19814.56,27874.35,27874.35 1,100,10,64,20,1985.27,2000,1280000,1007,0.615,97177.37,142829.28,142829.28 2,1000,10,64,20,16443.42,20000,12800000,1216,0.742,824386.58,849250.27,849250.27 ``` </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]
