github-actions[bot] commented on PR #7659: URL: https://github.com/apache/texera/pull/7659#issuecomment-5290027397
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 6 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `4013ca7` 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/31774353133) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 384 | 0.234 | 24,607/34,307/34,307 us | 🔴 -7.9% / 🔴 +109.9% | | 🔴 | bs=100 sw=10 sl=64 | 759 | 0.463 | 126,000/183,264/183,264 us | 🔴 +28.0% / 🔴 +70.3% | | ⚪ | bs=1000 sw=10 sl=64 | 884 | 0.54 | 1,129,073/1,177,653/1,177,653 us | ⚪ within ±5% / 🔴 -14.2% | <details><summary>Baseline details</summary> Latest main `4013ca7` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 384 tuples/sec | 417 tuples/sec | 774.89 tuples/sec | -7.9% | -50.4% | | bs=10 sw=10 sl=64 | MB/s | 0.234 MB/s | 0.254 MB/s | 0.473 MB/s | -7.9% | -50.5% | | bs=10 sw=10 sl=64 | p50 | 24,607 us | 23,798 us | 12,738 us | +3.4% | +93.2% | | bs=10 sw=10 sl=64 | p95 | 34,307 us | 35,879 us | 16,348 us | -4.4% | +109.9% | | bs=10 sw=10 sl=64 | p99 | 34,307 us | 35,879 us | 18,848 us | -4.4% | +82.0% | | bs=100 sw=10 sl=64 | throughput | 759 tuples/sec | 805 tuples/sec | 1,005 tuples/sec | -5.7% | -24.5% | | bs=100 sw=10 sl=64 | MB/s | 0.463 MB/s | 0.492 MB/s | 0.613 MB/s | -5.9% | -24.5% | | bs=100 sw=10 sl=64 | p50 | 126,000 us | 120,286 us | 100,970 us | +4.8% | +24.8% | | bs=100 sw=10 sl=64 | p95 | 183,264 us | 143,136 us | 107,605 us | +28.0% | +70.3% | | bs=100 sw=10 sl=64 | p99 | 183,264 us | 143,136 us | 116,429 us | +28.0% | +57.4% | | bs=1000 sw=10 sl=64 | throughput | 884 tuples/sec | 900 tuples/sec | 1,030 tuples/sec | -1.8% | -14.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.54 MB/s | 0.549 MB/s | 0.629 MB/s | -1.6% | -14.1% | | bs=1000 sw=10 sl=64 | p50 | 1,129,073 us | 1,106,750 us | 991,433 us | +2.0% | +13.9% | | bs=1000 sw=10 sl=64 | p95 | 1,177,653 us | 1,218,730 us | 1,036,668 us | -3.4% | +13.6% | | bs=1000 sw=10 sl=64 | p99 | 1,177,653 us | 1,218,730 us | 1,070,470 us | -3.4% | +10.0% | </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 0,10,10,64,20,521.09,200,128000,384,0.234,24607.44,34306.50,34306.50 1,100,10,64,20,2634.00,2000,1280000,759,0.463,126000.49,183264.17,183264.17 2,1000,10,64,20,22616.13,20000,12800000,884,0.540,1129072.56,1177653.04,1177653.04 ``` </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]
