github-actions[bot] commented on PR #7223: URL: https://github.com/apache/texera/pull/7223#issuecomment-5150199245
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 3 better · 🔴 7 worse · ⚪ 5 noise (<±5%) · 0 without baseline > Compared against main `050c226` 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/30687715438) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 395 | 0.241 | 24,406/31,375/31,375 us | 🟢 -13.8% / 🔴 +93.7% | | 🔴 | bs=100 sw=10 sl=64 | 781 | 0.477 | 126,193/154,129/154,129 us | 🔴 +20.0% / 🔴 +39.1% | | 🔴 | bs=1000 sw=10 sl=64 | 899 | 0.549 | 1,104,523/1,240,339/1,240,339 us | 🔴 +8.9% / 🔴 +16.7% | <details><summary>Baseline details</summary> Latest main `050c226` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 395 tuples/sec | 382 tuples/sec | 765.25 tuples/sec | +3.4% | -48.4% | | bs=10 sw=10 sl=64 | MB/s | 0.241 MB/s | 0.233 MB/s | 0.467 MB/s | +3.4% | -48.4% | | bs=10 sw=10 sl=64 | p50 | 24,406 us | 25,778 us | 12,703 us | -5.3% | +92.1% | | bs=10 sw=10 sl=64 | p95 | 31,375 us | 36,414 us | 16,199 us | -13.8% | +93.7% | | bs=10 sw=10 sl=64 | p99 | 31,375 us | 36,414 us | 19,557 us | -13.8% | +60.4% | | bs=100 sw=10 sl=64 | throughput | 781 tuples/sec | 831 tuples/sec | 965.22 tuples/sec | -6.0% | -19.1% | | bs=100 sw=10 sl=64 | MB/s | 0.477 MB/s | 0.507 MB/s | 0.589 MB/s | -5.9% | -19.0% | | bs=100 sw=10 sl=64 | p50 | 126,193 us | 120,002 us | 103,830 us | +5.2% | +21.5% | | bs=100 sw=10 sl=64 | p95 | 154,129 us | 128,436 us | 110,778 us | +20.0% | +39.1% | | bs=100 sw=10 sl=64 | p99 | 154,129 us | 128,436 us | 118,713 us | +20.0% | +29.8% | | bs=1000 sw=10 sl=64 | throughput | 899 tuples/sec | 915 tuples/sec | 992.33 tuples/sec | -1.7% | -9.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.549 MB/s | 0.558 MB/s | 0.606 MB/s | -1.6% | -9.4% | | bs=1000 sw=10 sl=64 | p50 | 1,104,523 us | 1,090,186 us | 1,016,959 us | +1.3% | +8.6% | | bs=1000 sw=10 sl=64 | p95 | 1,240,339 us | 1,138,838 us | 1,062,501 us | +8.9% | +16.7% | | bs=1000 sw=10 sl=64 | p99 | 1,240,339 us | 1,138,838 us | 1,082,611 us | +8.9% | +14.6% | </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 0,10,10,64,20,505.91,200,128000,395,0.241,24406.02,31374.64,31374.64 1,100,10,64,20,2560.74,2000,1280000,781,0.477,126193.41,154128.50,154128.50 2,1000,10,64,20,22240.96,20000,12800000,899,0.549,1104522.74,1240339.11,1240339.11 ``` </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]
