github-actions[bot] commented on PR #7740: URL: https://github.com/apache/texera/pull/7740#issuecomment-5320505528
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 4 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `e80add4` 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/32071101941) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 431 | 0.263 | 21,922/31,545/31,545 us | 🔴 +11.9% / 🔴 +97.3% | | 🔴 | bs=100 sw=10 sl=64 | 916 | 0.559 | 109,837/123,012/123,012 us | 🔴 +6.7% / 🔴 +14.6% | | ⚪ | bs=1000 sw=10 sl=64 | 1,105 | 0.674 | 907,614/973,620/973,620 us | ⚪ within ±5% / 🟢 -7.3% | <details><summary>Baseline details</summary> Latest main `e80add4` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 431 tuples/sec | 486 tuples/sec | 779.07 tuples/sec | -11.3% | -44.7% | | bs=10 sw=10 sl=64 | MB/s | 0.263 MB/s | 0.296 MB/s | 0.476 MB/s | -11.1% | -44.7% | | bs=10 sw=10 sl=64 | p50 | 21,922 us | 19,584 us | 12,818 us | +11.9% | +71.0% | | bs=10 sw=10 sl=64 | p95 | 31,545 us | 31,380 us | 15,986 us | +0.5% | +97.3% | | bs=10 sw=10 sl=64 | p99 | 31,545 us | 31,380 us | 19,339 us | +0.5% | +63.1% | | bs=100 sw=10 sl=64 | throughput | 916 tuples/sec | 961 tuples/sec | 1,011 tuples/sec | -4.7% | -9.4% | | bs=100 sw=10 sl=64 | MB/s | 0.559 MB/s | 0.586 MB/s | 0.617 MB/s | -4.6% | -9.4% | | bs=100 sw=10 sl=64 | p50 | 109,837 us | 102,979 us | 100,965 us | +6.7% | +8.8% | | bs=100 sw=10 sl=64 | p95 | 123,012 us | 130,750 us | 107,295 us | -5.9% | +14.6% | | bs=100 sw=10 sl=64 | p99 | 123,012 us | 130,750 us | 115,531 us | -5.9% | +6.5% | | bs=1000 sw=10 sl=64 | throughput | 1,105 tuples/sec | 1,081 tuples/sec | 1,049 tuples/sec | +2.2% | +5.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.674 MB/s | 0.66 MB/s | 0.64 MB/s | +2.1% | +5.3% | | bs=1000 sw=10 sl=64 | p50 | 907,614 us | 921,255 us | 978,248 us | -1.5% | -7.2% | | bs=1000 sw=10 sl=64 | p95 | 973,620 us | 972,955 us | 1,021,881 us | +0.1% | -4.7% | | bs=1000 sw=10 sl=64 | p99 | 973,620 us | 972,955 us | 1,050,075 us | +0.1% | -7.3% | </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 0,10,10,64,20,464.37,200,128000,431,0.263,21922.24,31544.62,31544.62 1,100,10,64,20,2184.34,2000,1280000,916,0.559,109836.92,123012.09,123012.09 2,1000,10,64,20,18098.36,20000,12800000,1105,0.674,907613.77,973620.00,973620.00 ``` </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]
