github-actions[bot] commented on PR #7233: URL: https://github.com/apache/texera/pull/7233#issuecomment-5150409591
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 3 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `e970abb` 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/30689620064) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 649 | 0.396 | 15,011/21,145/21,145 us | 🔴 +10.2% / 🔴 +30.5% | | ⚪ | bs=100 sw=10 sl=64 | 1,352 | 0.825 | 73,074/94,236/94,236 us | ⚪ within ±5% / 🟢 +40.1% | | ⚪ | bs=1000 sw=10 sl=64 | 1,512 | 0.923 | 653,259/756,462/756,462 us | ⚪ within ±5% / 🟢 +52.4% | <details><summary>Baseline details</summary> Latest main `e970abb` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 649 tuples/sec | 704 tuples/sec | 765.25 tuples/sec | -7.8% | -15.2% | | bs=10 sw=10 sl=64 | MB/s | 0.396 MB/s | 0.43 MB/s | 0.467 MB/s | -7.9% | -15.2% | | bs=10 sw=10 sl=64 | p50 | 15,011 us | 13,618 us | 12,703 us | +10.2% | +18.2% | | bs=10 sw=10 sl=64 | p95 | 21,145 us | 21,648 us | 16,199 us | -2.3% | +30.5% | | bs=10 sw=10 sl=64 | p99 | 21,145 us | 21,648 us | 19,557 us | -2.3% | +8.1% | | bs=100 sw=10 sl=64 | throughput | 1,352 tuples/sec | 1,340 tuples/sec | 965.22 tuples/sec | +0.9% | +40.1% | | bs=100 sw=10 sl=64 | MB/s | 0.825 MB/s | 0.818 MB/s | 0.589 MB/s | +0.9% | +40.0% | | bs=100 sw=10 sl=64 | p50 | 73,074 us | 73,240 us | 103,830 us | -0.2% | -29.6% | | bs=100 sw=10 sl=64 | p95 | 94,236 us | 94,609 us | 110,778 us | -0.4% | -14.9% | | bs=100 sw=10 sl=64 | p99 | 94,236 us | 94,609 us | 118,713 us | -0.4% | -20.6% | | bs=1000 sw=10 sl=64 | throughput | 1,512 tuples/sec | 1,534 tuples/sec | 992.33 tuples/sec | -1.4% | +52.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.923 MB/s | 0.936 MB/s | 0.606 MB/s | -1.4% | +52.4% | | bs=1000 sw=10 sl=64 | p50 | 653,259 us | 642,822 us | 1,016,959 us | +1.6% | -35.8% | | bs=1000 sw=10 sl=64 | p95 | 756,462 us | 770,478 us | 1,062,501 us | -1.8% | -28.8% | | bs=1000 sw=10 sl=64 | p99 | 756,462 us | 770,478 us | 1,082,611 us | -1.8% | -30.1% | </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 0,10,10,64,20,308.40,200,128000,649,0.396,15010.88,21144.58,21144.58 1,100,10,64,20,1479.78,2000,1280000,1352,0.825,73073.77,94235.90,94235.90 2,1000,10,64,20,13225.90,20000,12800000,1512,0.923,653259.10,756462.38,756462.38 ``` </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]
