github-actions[bot] commented on PR #8200: URL: https://github.com/apache/texera/pull/8200#issuecomment-5472897686
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 5 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `70c2114` 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/33350067544) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 510 | 0.311 | 17,410/30,653/30,653 us | 🔴 +20.1% / 🔴 +107.3% | | 🟢 | bs=100 sw=10 sl=64 | 1,196 | 0.73 | 82,949/120,359/120,359 us | 🟢 -9.6% / 🔴 +19.2% | | 🟢 | bs=1000 sw=10 sl=64 | 1,423 | 0.869 | 703,351/772,537/772,537 us | 🟢 -5.9% / 🟢 +27.2% | <details><summary>Baseline details</summary> Latest main `70c2114` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 510 tuples/sec | 573 tuples/sec | 844.57 tuples/sec | -11.0% | -39.6% | | bs=10 sw=10 sl=64 | MB/s | 0.311 MB/s | 0.35 MB/s | 0.515 MB/s | -11.1% | -39.7% | | bs=10 sw=10 sl=64 | p50 | 17,410 us | 16,526 us | 11,837 us | +5.4% | +47.1% | | bs=10 sw=10 sl=64 | p95 | 30,653 us | 25,529 us | 14,788 us | +20.1% | +107.3% | | bs=10 sw=10 sl=64 | p99 | 30,653 us | 25,529 us | 17,651 us | +20.1% | +73.7% | | bs=100 sw=10 sl=64 | throughput | 1,196 tuples/sec | 1,151 tuples/sec | 1,084 tuples/sec | +3.9% | +10.3% | | bs=100 sw=10 sl=64 | MB/s | 0.73 MB/s | 0.702 MB/s | 0.662 MB/s | +4.0% | +10.3% | | bs=100 sw=10 sl=64 | p50 | 82,949 us | 85,645 us | 94,505 us | -3.1% | -12.2% | | bs=100 sw=10 sl=64 | p95 | 120,359 us | 133,126 us | 100,941 us | -9.6% | +19.2% | | bs=100 sw=10 sl=64 | p99 | 120,359 us | 133,126 us | 108,642 us | -9.6% | +10.8% | | bs=1000 sw=10 sl=64 | throughput | 1,423 tuples/sec | 1,417 tuples/sec | 1,119 tuples/sec | +0.4% | +27.1% | | bs=1000 sw=10 sl=64 | MB/s | 0.869 MB/s | 0.865 MB/s | 0.683 MB/s | +0.5% | +27.2% | | bs=1000 sw=10 sl=64 | p50 | 703,351 us | 703,226 us | 924,404 us | +0.0% | -23.9% | | bs=1000 sw=10 sl=64 | p95 | 772,537 us | 820,846 us | 967,785 us | -5.9% | -20.2% | | bs=1000 sw=10 sl=64 | p99 | 772,537 us | 820,846 us | 995,630 us | -5.9% | -22.4% | </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 0,10,10,64,20,392.37,200,128000,510,0.311,17410.22,30653.12,30653.12 1,100,10,64,20,1672.31,2000,1280000,1196,0.730,82949.34,120359.46,120359.46 2,1000,10,64,20,14053.16,20000,12800000,1423,0.869,703350.51,772537.21,772537.21 ``` </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]
