github-actions[bot] commented on PR #8307: URL: https://github.com/apache/texera/pull/8307#issuecomment-5499041499
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 2 worse · ⚪ 11 noise (<±5%) · 0 without baseline > Compared against main `8aea604` 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/33546722597) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 393 | 0.24 | 24,730/30,180/30,180 us | 🟢 -13.7% / 🔴 +89.8% | | 🔴 | bs=100 sw=10 sl=64 | 791 | 0.483 | 120,363/183,518/183,518 us | 🔴 +27.8% / 🔴 +65.9% | | ⚪ | bs=1000 sw=10 sl=64 | 937 | 0.572 | 1,060,104/1,142,824/1,142,824 us | ⚪ within ±5% / 🔴 +8.4% | <details><summary>Baseline details</summary> Latest main `8aea604` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 393 tuples/sec | 410 tuples/sec | 750.65 tuples/sec | -4.1% | -47.6% | | bs=10 sw=10 sl=64 | MB/s | 0.24 MB/s | 0.25 MB/s | 0.458 MB/s | -4.0% | -47.6% | | bs=10 sw=10 sl=64 | p50 | 24,730 us | 24,219 us | 13,049 us | +2.1% | +89.5% | | bs=10 sw=10 sl=64 | p95 | 30,180 us | 34,984 us | 15,902 us | -13.7% | +89.8% | | bs=10 sw=10 sl=64 | p99 | 30,180 us | 34,984 us | 19,184 us | -13.7% | +57.3% | | bs=100 sw=10 sl=64 | throughput | 791 tuples/sec | 815 tuples/sec | 960.3 tuples/sec | -2.9% | -17.6% | | bs=100 sw=10 sl=64 | MB/s | 0.483 MB/s | 0.497 MB/s | 0.586 MB/s | -2.8% | -17.6% | | bs=100 sw=10 sl=64 | p50 | 120,363 us | 119,536 us | 104,199 us | +0.7% | +15.5% | | bs=100 sw=10 sl=64 | p95 | 183,518 us | 143,625 us | 110,645 us | +27.8% | +65.9% | | bs=100 sw=10 sl=64 | p99 | 183,518 us | 143,625 us | 120,888 us | +27.8% | +51.8% | | bs=1000 sw=10 sl=64 | throughput | 937 tuples/sec | 965 tuples/sec | 993.27 tuples/sec | -2.9% | -5.7% | | bs=1000 sw=10 sl=64 | MB/s | 0.572 MB/s | 0.589 MB/s | 0.606 MB/s | -2.9% | -5.6% | | bs=1000 sw=10 sl=64 | p50 | 1,060,104 us | 1,038,904 us | 1,012,191 us | +2.0% | +4.7% | | bs=1000 sw=10 sl=64 | p95 | 1,142,824 us | 1,098,292 us | 1,054,057 us | +4.1% | +8.4% | | bs=1000 sw=10 sl=64 | p99 | 1,142,824 us | 1,098,292 us | 1,081,313 us | +4.1% | +5.7% | </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 0,10,10,64,20,509.43,200,128000,393,0.240,24730.21,30180.15,30180.15 1,100,10,64,20,2528.12,2000,1280000,791,0.483,120363.40,183517.75,183517.75 2,1000,10,64,20,21337.55,20000,12800000,937,0.572,1060103.76,1142823.60,1142823.60 ``` </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]
