github-actions[bot] commented on PR #6158: URL: https://github.com/apache/texera/pull/6158#issuecomment-4885514887
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 1 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `5acb734` 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/28735872322) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 433 | 0.264 | 22,845/33,076/33,076 us | 🔴 +16.3% / 🔴 +118.4% | | 🟢 | bs=100 sw=10 sl=64 | 932 | 0.569 | 103,121/153,204/153,204 us | 🟢 -11.4% / 🔴 +41.9% | | ⚪ | bs=1000 sw=10 sl=64 | 1,117 | 0.682 | 895,109/919,757/919,757 us | ⚪ within ±5% / 🟢 -13.2% | <details><summary>Baseline details</summary> Latest main `5acb734` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 433 tuples/sec | 453 tuples/sec | 776.36 tuples/sec | -4.4% | -44.2% | | bs=10 sw=10 sl=64 | MB/s | 0.264 MB/s | 0.276 MB/s | 0.474 MB/s | -4.3% | -44.3% | | bs=10 sw=10 sl=64 | p50 | 22,845 us | 19,647 us | 12,636 us | +16.3% | +80.8% | | bs=10 sw=10 sl=64 | p95 | 33,076 us | 32,811 us | 15,143 us | +0.8% | +118.4% | | bs=10 sw=10 sl=64 | p99 | 33,076 us | 32,811 us | 18,954 us | +0.8% | +74.5% | | bs=100 sw=10 sl=64 | throughput | 932 tuples/sec | 943 tuples/sec | 985.33 tuples/sec | -1.2% | -5.4% | | bs=100 sw=10 sl=64 | MB/s | 0.569 MB/s | 0.576 MB/s | 0.601 MB/s | -1.2% | -5.4% | | bs=100 sw=10 sl=64 | p50 | 103,121 us | 101,023 us | 101,671 us | +2.1% | +1.4% | | bs=100 sw=10 sl=64 | p95 | 153,204 us | 172,961 us | 107,939 us | -11.4% | +41.9% | | bs=100 sw=10 sl=64 | p99 | 153,204 us | 172,961 us | 113,798 us | -11.4% | +34.6% | | bs=1000 sw=10 sl=64 | throughput | 1,117 tuples/sec | 1,103 tuples/sec | 1,016 tuples/sec | +1.3% | +9.9% | | bs=1000 sw=10 sl=64 | MB/s | 0.682 MB/s | 0.673 MB/s | 0.62 MB/s | +1.3% | +9.9% | | bs=1000 sw=10 sl=64 | p50 | 895,109 us | 904,735 us | 989,693 us | -1.1% | -9.6% | | bs=1000 sw=10 sl=64 | p95 | 919,757 us | 936,769 us | 1,028,327 us | -1.8% | -10.6% | | bs=1000 sw=10 sl=64 | p99 | 919,757 us | 936,769 us | 1,059,969 us | -1.8% | -13.2% | </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 0,10,10,64,20,461.73,200,128000,433,0.264,22844.76,33076.27,33076.27 1,100,10,64,20,2146.68,2000,1280000,932,0.569,103121.24,153203.63,153203.63 2,1000,10,64,20,17903.93,20000,12800000,1117,0.682,895109.07,919757.20,919757.20 ``` </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]
