github-actions[bot] commented on PR #6974: URL: https://github.com/apache/texera/pull/6974#issuecomment-5109263064
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `5040cad` 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/30391525454) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 406 | 0.248 | 24,817/35,409/35,409 us | 🔴 +16.5% / 🔴 +124.1% | | 🟢 | bs=100 sw=10 sl=64 | 948 | 0.579 | 105,264/127,203/127,203 us | 🟢 -6.6% / 🔴 +18.5% | | ⚪ | bs=1000 sw=10 sl=64 | 1,101 | 0.672 | 915,320/947,297/947,297 us | ⚪ within ±5% / 🟢 -10.2% | <details><summary>Baseline details</summary> Latest main `5040cad` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 406 tuples/sec | 450 tuples/sec | 787.55 tuples/sec | -9.8% | -48.4% | | bs=10 sw=10 sl=64 | MB/s | 0.248 MB/s | 0.275 MB/s | 0.481 MB/s | -9.8% | -48.4% | | bs=10 sw=10 sl=64 | p50 | 24,817 us | 22,877 us | 12,255 us | +8.5% | +102.5% | | bs=10 sw=10 sl=64 | p95 | 35,409 us | 30,403 us | 15,802 us | +16.5% | +124.1% | | bs=10 sw=10 sl=64 | p99 | 35,409 us | 30,403 us | 19,008 us | +16.5% | +86.3% | | bs=100 sw=10 sl=64 | throughput | 948 tuples/sec | 965 tuples/sec | 997.81 tuples/sec | -1.8% | -5.0% | | bs=100 sw=10 sl=64 | MB/s | 0.579 MB/s | 0.589 MB/s | 0.609 MB/s | -1.7% | -4.9% | | bs=100 sw=10 sl=64 | p50 | 105,264 us | 101,191 us | 100,690 us | +4.0% | +4.5% | | bs=100 sw=10 sl=64 | p95 | 127,203 us | 136,173 us | 107,316 us | -6.6% | +18.5% | | bs=100 sw=10 sl=64 | p99 | 127,203 us | 136,173 us | 113,823 us | -6.6% | +11.8% | | bs=1000 sw=10 sl=64 | throughput | 1,101 tuples/sec | 1,107 tuples/sec | 1,030 tuples/sec | -0.5% | +6.9% | | bs=1000 sw=10 sl=64 | MB/s | 0.672 MB/s | 0.676 MB/s | 0.629 MB/s | -0.6% | +6.9% | | bs=1000 sw=10 sl=64 | p50 | 915,320 us | 900,157 us | 981,213 us | +1.7% | -6.7% | | bs=1000 sw=10 sl=64 | p95 | 947,297 us | 952,787 us | 1,027,605 us | -0.6% | -7.8% | | bs=1000 sw=10 sl=64 | p99 | 947,297 us | 952,787 us | 1,055,466 us | -0.6% | -10.2% | </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 0,10,10,64,20,492.90,200,128000,406,0.248,24817.13,35409.10,35409.10 1,100,10,64,20,2109.48,2000,1280000,948,0.579,105263.98,127203.41,127203.41 2,1000,10,64,20,18158.07,20000,12800000,1101,0.672,915320.02,947296.66,947296.66 ``` </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]
