github-actions[bot] commented on PR #8535: URL: https://github.com/apache/texera/pull/8535#issuecomment-5655757530
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `7190a81` 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/34779276266) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 745 | 0.455 | 12,886/17,532/17,532 us | 🔴 +18.0% / 🔴 +19.3% | | 🔴 | bs=100 sw=10 sl=64 | 1,756 | 1.072 | 55,041/89,035/89,035 us | 🔴 +39.3% / 🟢 +60.4% | | ⚪ | bs=1000 sw=10 sl=64 | 2,078 | 1.268 | 479,514/537,470/537,470 us | ⚪ within ±5% / 🟢 +84.5% | <details><summary>Baseline details</summary> Latest main `7190a81` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 745 tuples/sec | 836 tuples/sec | 838.23 tuples/sec | -10.9% | -11.1% | | bs=10 sw=10 sl=64 | MB/s | 0.455 MB/s | 0.51 MB/s | 0.512 MB/s | -10.8% | -11.1% | | bs=10 sw=10 sl=64 | p50 | 12,886 us | 10,920 us | 11,878 us | +18.0% | +8.5% | | bs=10 sw=10 sl=64 | p95 | 17,532 us | 19,281 us | 14,690 us | -9.1% | +19.3% | | bs=10 sw=10 sl=64 | p99 | 17,532 us | 19,281 us | 18,483 us | -9.1% | -5.1% | | bs=100 sw=10 sl=64 | throughput | 1,756 tuples/sec | 1,837 tuples/sec | 1,095 tuples/sec | -4.4% | +60.4% | | bs=100 sw=10 sl=64 | MB/s | 1.072 MB/s | 1.121 MB/s | 0.668 MB/s | -4.4% | +60.4% | | bs=100 sw=10 sl=64 | p50 | 55,041 us | 53,163 us | 92,901 us | +3.5% | -40.8% | | bs=100 sw=10 sl=64 | p95 | 89,035 us | 63,928 us | 99,480 us | +39.3% | -10.5% | | bs=100 sw=10 sl=64 | p99 | 89,035 us | 63,928 us | 112,580 us | +39.3% | -20.9% | | bs=1000 sw=10 sl=64 | throughput | 2,078 tuples/sec | 2,105 tuples/sec | 1,126 tuples/sec | -1.3% | +84.5% | | bs=1000 sw=10 sl=64 | MB/s | 1.268 MB/s | 1.285 MB/s | 0.687 MB/s | -1.3% | +84.4% | | bs=1000 sw=10 sl=64 | p50 | 479,514 us | 475,025 us | 912,010 us | +0.9% | -47.4% | | bs=1000 sw=10 sl=64 | p95 | 537,470 us | 533,424 us | 950,922 us | +0.8% | -43.5% | | bs=1000 sw=10 sl=64 | p99 | 537,470 us | 533,424 us | 983,333 us | +0.8% | -45.3% | </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 0,10,10,64,20,268.52,200,128000,745,0.455,12886.37,17532.23,17532.23 1,100,10,64,20,1139.08,2000,1280000,1756,1.072,55040.96,89035.02,89035.02 2,1000,10,64,20,9625.61,20000,12800000,2078,1.268,479513.75,537470.37,537470.37 ``` </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]
