github-actions[bot] commented on PR #8435: URL: https://github.com/apache/texera/pull/8435#issuecomment-5548781408
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 9 worse · ⚪ 4 noise (<±5%) · 0 without baseline > Compared against main `dcb25ef` 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/33939228704) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 519 | 0.317 | 18,069/25,847/25,847 us | 🔴 +10.2% / 🔴 +58.3% | | 🔴 | bs=100 sw=10 sl=64 | 1,171 | 0.715 | 82,337/123,910/123,910 us | 🔴 +41.2% / 🟢 +21.0% | | 🔴 | bs=1000 sw=10 sl=64 | 1,380 | 0.843 | 722,582/864,840/864,840 us | 🔴 +17.6% / 🟢 +38.4% | <details><summary>Baseline details</summary> Latest main `dcb25ef` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 519 tuples/sec | 558 tuples/sec | 749.39 tuples/sec | -7.0% | -30.7% | | bs=10 sw=10 sl=64 | MB/s | 0.317 MB/s | 0.341 MB/s | 0.457 MB/s | -7.0% | -30.7% | | bs=10 sw=10 sl=64 | p50 | 18,069 us | 16,404 us | 13,045 us | +10.2% | +38.5% | | bs=10 sw=10 sl=64 | p95 | 25,847 us | 28,050 us | 16,328 us | -7.9% | +58.3% | | bs=10 sw=10 sl=64 | p99 | 25,847 us | 28,050 us | 19,518 us | -7.9% | +32.4% | | bs=100 sw=10 sl=64 | throughput | 1,171 tuples/sec | 1,245 tuples/sec | 968.07 tuples/sec | -5.9% | +21.0% | | bs=100 sw=10 sl=64 | MB/s | 0.715 MB/s | 0.76 MB/s | 0.591 MB/s | -5.9% | +21.0% | | bs=100 sw=10 sl=64 | p50 | 82,337 us | 80,746 us | 103,330 us | +2.0% | -20.3% | | bs=100 sw=10 sl=64 | p95 | 123,910 us | 87,736 us | 110,305 us | +41.2% | +12.3% | | bs=100 sw=10 sl=64 | p99 | 123,910 us | 87,736 us | 121,264 us | +41.2% | +2.2% | | bs=1000 sw=10 sl=64 | throughput | 1,380 tuples/sec | 1,440 tuples/sec | 998 tuples/sec | -4.2% | +38.3% | | bs=1000 sw=10 sl=64 | MB/s | 0.843 MB/s | 0.879 MB/s | 0.609 MB/s | -4.1% | +38.4% | | bs=1000 sw=10 sl=64 | p50 | 722,582 us | 694,704 us | 1,009,354 us | +4.0% | -28.4% | | bs=1000 sw=10 sl=64 | p95 | 864,840 us | 735,443 us | 1,052,748 us | +17.6% | -17.8% | | bs=1000 sw=10 sl=64 | p99 | 864,840 us | 735,443 us | 1,081,982 us | +17.6% | -20.1% | </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 0,10,10,64,20,385.23,200,128000,519,0.317,18068.73,25846.69,25846.69 1,100,10,64,20,1708.37,2000,1280000,1171,0.715,82336.58,123909.53,123909.53 2,1000,10,64,20,14488.82,20000,12800000,1380,0.843,722581.86,864839.99,864839.99 ``` </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]
