github-actions[bot] commented on PR #8260: URL: https://github.com/apache/texera/pull/8260#issuecomment-5474306011
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 5 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `50321e4` 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/33361689849) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 636 | 0.388 | 16,262/18,676/18,676 us | 🔴 +13.0% / 🔴 +37.4% | | 🔴 | bs=100 sw=10 sl=64 | 1,356 | 0.828 | 70,907/90,200/90,200 us | 🔴 +10.5% / 🟢 +25.1% | | ⚪ | bs=1000 sw=10 sl=64 | 1,581 | 0.965 | 629,507/673,422/673,422 us | ⚪ within ±5% / 🟢 +41.2% | <details><summary>Baseline details</summary> Latest main `50321e4` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 636 tuples/sec | 699 tuples/sec | 844.57 tuples/sec | -9.0% | -24.7% | | bs=10 sw=10 sl=64 | MB/s | 0.388 MB/s | 0.427 MB/s | 0.515 MB/s | -9.1% | -24.7% | | bs=10 sw=10 sl=64 | p50 | 16,262 us | 14,393 us | 11,837 us | +13.0% | +37.4% | | bs=10 sw=10 sl=64 | p95 | 18,676 us | 18,224 us | 14,788 us | +2.5% | +26.3% | | bs=10 sw=10 sl=64 | p99 | 18,676 us | 18,224 us | 17,651 us | +2.5% | +5.8% | | bs=100 sw=10 sl=64 | throughput | 1,356 tuples/sec | 1,404 tuples/sec | 1,084 tuples/sec | -3.4% | +25.1% | | bs=100 sw=10 sl=64 | MB/s | 0.828 MB/s | 0.857 MB/s | 0.662 MB/s | -3.4% | +25.1% | | bs=100 sw=10 sl=64 | p50 | 70,907 us | 70,445 us | 94,505 us | +0.7% | -25.0% | | bs=100 sw=10 sl=64 | p95 | 90,200 us | 81,621 us | 100,941 us | +10.5% | -10.6% | | bs=100 sw=10 sl=64 | p99 | 90,200 us | 81,621 us | 108,642 us | +10.5% | -17.0% | | bs=1000 sw=10 sl=64 | throughput | 1,581 tuples/sec | 1,612 tuples/sec | 1,119 tuples/sec | -1.9% | +41.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.965 MB/s | 0.984 MB/s | 0.683 MB/s | -1.9% | +41.2% | | bs=1000 sw=10 sl=64 | p50 | 629,507 us | 620,699 us | 924,404 us | +1.4% | -31.9% | | bs=1000 sw=10 sl=64 | p95 | 673,422 us | 662,595 us | 967,785 us | +1.6% | -30.4% | | bs=1000 sw=10 sl=64 | p99 | 673,422 us | 662,595 us | 995,630 us | +1.6% | -32.4% | </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 0,10,10,64,20,314.54,200,128000,636,0.388,16262.05,18676.43,18676.43 1,100,10,64,20,1474.65,2000,1280000,1356,0.828,70906.94,90200.35,90200.35 2,1000,10,64,20,12650.75,20000,12800000,1581,0.965,629507.35,673421.71,673421.71 ``` </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]
