github-actions[bot] commented on PR #6414: URL: https://github.com/apache/texera/pull/6414#issuecomment-4969710096
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 7 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `0485d02` 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/29336024393) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 383 | 0.234 | 25,866/33,510/33,510 us | 🔴 +9.8% / 🔴 +131.3% | | 🔴 | bs=100 sw=10 sl=64 | 787 | 0.48 | 124,902/148,630/148,630 us | 🔴 +13.1% / 🔴 +47.9% | | 🔴 | bs=1000 sw=10 sl=64 | 903 | 0.551 | 1,104,973/1,218,550/1,218,550 us | 🔴 +6.9% / 🔴 +26.0% | <details><summary>Baseline details</summary> Latest main `0485d02` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 383 tuples/sec | 400 tuples/sec | 830.77 tuples/sec | -4.3% | -53.9% | | bs=10 sw=10 sl=64 | MB/s | 0.234 MB/s | 0.244 MB/s | 0.507 MB/s | -4.1% | -53.9% | | bs=10 sw=10 sl=64 | p50 | 25,866 us | 23,552 us | 11,905 us | +9.8% | +117.3% | | bs=10 sw=10 sl=64 | p95 | 33,510 us | 36,655 us | 14,486 us | -8.6% | +131.3% | | bs=10 sw=10 sl=64 | p99 | 33,510 us | 36,655 us | 19,430 us | -8.6% | +72.5% | | bs=100 sw=10 sl=64 | throughput | 787 tuples/sec | 833 tuples/sec | 1,082 tuples/sec | -5.5% | -27.3% | | bs=100 sw=10 sl=64 | MB/s | 0.48 MB/s | 0.509 MB/s | 0.66 MB/s | -5.7% | -27.3% | | bs=100 sw=10 sl=64 | p50 | 124,902 us | 120,818 us | 93,412 us | +3.4% | +33.7% | | bs=100 sw=10 sl=64 | p95 | 148,630 us | 131,415 us | 100,489 us | +13.1% | +47.9% | | bs=100 sw=10 sl=64 | p99 | 148,630 us | 131,415 us | 111,365 us | +13.1% | +33.5% | | bs=1000 sw=10 sl=64 | throughput | 903 tuples/sec | 920 tuples/sec | 1,104 tuples/sec | -1.8% | -18.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.551 MB/s | 0.561 MB/s | 0.674 MB/s | -1.8% | -18.2% | | bs=1000 sw=10 sl=64 | p50 | 1,104,973 us | 1,082,804 us | 925,459 us | +2.0% | +19.4% | | bs=1000 sw=10 sl=64 | p95 | 1,218,550 us | 1,140,253 us | 967,138 us | +6.9% | +26.0% | | bs=1000 sw=10 sl=64 | p99 | 1,218,550 us | 1,140,253 us | 997,758 us | +6.9% | +22.1% | </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 0,10,10,64,20,521.71,200,128000,383,0.234,25866.48,33509.74,33509.74 1,100,10,64,20,2542.88,2000,1280000,787,0.480,124902.34,148629.71,148629.71 2,1000,10,64,20,22140.47,20000,12800000,903,0.551,1104973.28,1218550.40,1218550.40 ``` </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]
