github-actions[bot] commented on PR #7855: URL: https://github.com/apache/texera/pull/7855#issuecomment-5383355232
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `ce0510d` 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/32607506863) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 531 | 0.324 | 19,025/25,110/25,110 us | 🔴 +19.0% / 🔴 +74.6% | | ⚪ | bs=100 sw=10 sl=64 | 1,201 | 0.733 | 82,969/107,331/107,331 us | ⚪ within ±5% / 🟢 -10.9% | | ⚪ | bs=1000 sw=10 sl=64 | 1,401 | 0.855 | 710,089/777,039/777,039 us | ⚪ within ±5% / 🟢 +25.2% | <details><summary>Baseline details</summary> Latest main `ce0510d` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 531 tuples/sec | 592 tuples/sec | 833.79 tuples/sec | -10.3% | -36.3% | | bs=10 sw=10 sl=64 | MB/s | 0.324 MB/s | 0.361 MB/s | 0.509 MB/s | -10.2% | -36.3% | | bs=10 sw=10 sl=64 | p50 | 19,025 us | 15,993 us | 11,864 us | +19.0% | +60.4% | | bs=10 sw=10 sl=64 | p95 | 25,110 us | 29,221 us | 14,381 us | -14.1% | +74.6% | | bs=10 sw=10 sl=64 | p99 | 25,110 us | 29,221 us | 18,035 us | -14.1% | +39.2% | | bs=100 sw=10 sl=64 | throughput | 1,201 tuples/sec | 1,220 tuples/sec | 1,083 tuples/sec | -1.6% | +10.8% | | bs=100 sw=10 sl=64 | MB/s | 0.733 MB/s | 0.745 MB/s | 0.661 MB/s | -1.6% | +10.8% | | bs=100 sw=10 sl=64 | p50 | 82,969 us | 79,999 us | 93,077 us | +3.7% | -10.9% | | bs=100 sw=10 sl=64 | p95 | 107,331 us | 103,764 us | 99,553 us | +3.4% | +7.8% | | bs=100 sw=10 sl=64 | p99 | 107,331 us | 103,764 us | 108,604 us | +3.4% | -1.2% | | bs=1000 sw=10 sl=64 | throughput | 1,401 tuples/sec | 1,415 tuples/sec | 1,119 tuples/sec | -1.0% | +25.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.855 MB/s | 0.863 MB/s | 0.683 MB/s | -0.9% | +25.2% | | bs=1000 sw=10 sl=64 | p50 | 710,089 us | 701,997 us | 909,247 us | +1.2% | -21.9% | | bs=1000 sw=10 sl=64 | p95 | 777,039 us | 747,073 us | 952,561 us | +4.0% | -18.4% | | bs=1000 sw=10 sl=64 | p99 | 777,039 us | 747,073 us | 985,186 us | +4.0% | -21.1% | </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 0,10,10,64,20,376.78,200,128000,531,0.324,19024.73,25109.76,25109.76 1,100,10,64,20,1665.78,2000,1280000,1201,0.733,82969.27,107331.42,107331.42 2,1000,10,64,20,14276.25,20000,12800000,1401,0.855,710088.71,777038.87,777038.87 ``` </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]
