github-actions[bot] commented on PR #7624: URL: https://github.com/apache/texera/pull/7624#issuecomment-5276288578
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `310ab88` 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/31669615483) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 436 | 0.266 | 22,162/28,905/28,905 us | 🔴 +8.8% / 🔴 +77.2% | | 🔴 | bs=100 sw=10 sl=64 | 891 | 0.544 | 109,553/152,198/152,198 us | 🔴 +12.8% / 🔴 +40.7% | | 🔴 | bs=1000 sw=10 sl=64 | 1,098 | 0.67 | 911,194/1,003,346/1,003,346 us | 🔴 +5.2% / 🟢 -8.5% | <details><summary>Baseline details</summary> Latest main `310ab88` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 436 tuples/sec | 453 tuples/sec | 775.33 tuples/sec | -3.8% | -43.8% | | bs=10 sw=10 sl=64 | MB/s | 0.266 MB/s | 0.276 MB/s | 0.473 MB/s | -3.6% | -43.8% | | bs=10 sw=10 sl=64 | p50 | 22,162 us | 20,377 us | 12,743 us | +8.8% | +73.9% | | bs=10 sw=10 sl=64 | p95 | 28,905 us | 31,124 us | 16,310 us | -7.1% | +77.2% | | bs=10 sw=10 sl=64 | p99 | 28,905 us | 31,124 us | 18,926 us | -7.1% | +52.7% | | bs=100 sw=10 sl=64 | throughput | 891 tuples/sec | 921 tuples/sec | 1,001 tuples/sec | -3.3% | -11.0% | | bs=100 sw=10 sl=64 | MB/s | 0.544 MB/s | 0.562 MB/s | 0.611 MB/s | -3.2% | -10.9% | | bs=100 sw=10 sl=64 | p50 | 109,553 us | 107,259 us | 101,399 us | +2.1% | +8.0% | | bs=100 sw=10 sl=64 | p95 | 152,198 us | 134,890 us | 108,206 us | +12.8% | +40.7% | | bs=100 sw=10 sl=64 | p99 | 152,198 us | 134,890 us | 118,195 us | +12.8% | +28.8% | | bs=1000 sw=10 sl=64 | throughput | 1,098 tuples/sec | 1,108 tuples/sec | 1,026 tuples/sec | -0.9% | +7.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.67 MB/s | 0.677 MB/s | 0.626 MB/s | -1.0% | +7.0% | | bs=1000 sw=10 sl=64 | p50 | 911,194 us | 899,001 us | 996,304 us | +1.4% | -8.5% | | bs=1000 sw=10 sl=64 | p95 | 1,003,346 us | 953,842 us | 1,042,531 us | +5.2% | -3.8% | | bs=1000 sw=10 sl=64 | p99 | 1,003,346 us | 953,842 us | 1,074,934 us | +5.2% | -6.7% | </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 0,10,10,64,20,458.34,200,128000,436,0.266,22162.09,28905.47,28905.47 1,100,10,64,20,2245.35,2000,1280000,891,0.544,109552.70,152198.16,152198.16 2,1000,10,64,20,18217.01,20000,12800000,1098,0.670,911194.07,1003345.94,1003345.94 ``` </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]
