github-actions[bot] commented on PR #6824: URL: https://github.com/apache/texera/pull/6824#issuecomment-5055363553
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 3 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `0ba5d1a` 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/29985934775) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 337 | 0.206 | 29,319/39,257/39,257 us | 🔴 +13.7% / 🔴 +143.6% | | 🟢 | bs=100 sw=10 sl=64 | 703 | 0.429 | 140,226/169,830/169,830 us | 🟢 -20.0% / 🔴 +58.1% | | 🔴 | bs=1000 sw=10 sl=64 | 803 | 0.49 | 1,240,694/1,386,463/1,386,463 us | 🔴 +9.0% / 🔴 +34.6% | <details><summary>Baseline details</summary> Latest main `0ba5d1a` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 337 tuples/sec | 350 tuples/sec | 760.2 tuples/sec | -3.7% | -55.7% | | bs=10 sw=10 sl=64 | MB/s | 0.206 MB/s | 0.213 MB/s | 0.464 MB/s | -3.3% | -55.6% | | bs=10 sw=10 sl=64 | p50 | 29,319 us | 25,792 us | 12,781 us | +13.7% | +129.4% | | bs=10 sw=10 sl=64 | p95 | 39,257 us | 42,855 us | 16,118 us | -8.4% | +143.6% | | bs=10 sw=10 sl=64 | p99 | 39,257 us | 42,855 us | 19,074 us | -8.4% | +105.8% | | bs=100 sw=10 sl=64 | throughput | 703 tuples/sec | 689 tuples/sec | 988.68 tuples/sec | +2.0% | -28.9% | | bs=100 sw=10 sl=64 | MB/s | 0.429 MB/s | 0.42 MB/s | 0.603 MB/s | +2.1% | -28.9% | | bs=100 sw=10 sl=64 | p50 | 140,226 us | 133,821 us | 101,448 us | +4.8% | +38.2% | | bs=100 sw=10 sl=64 | p95 | 169,830 us | 212,240 us | 107,410 us | -20.0% | +58.1% | | bs=100 sw=10 sl=64 | p99 | 169,830 us | 212,240 us | 120,258 us | -20.0% | +41.2% | | bs=1000 sw=10 sl=64 | throughput | 803 tuples/sec | 823 tuples/sec | 1,023 tuples/sec | -2.4% | -21.5% | | bs=1000 sw=10 sl=64 | MB/s | 0.49 MB/s | 0.502 MB/s | 0.624 MB/s | -2.4% | -21.5% | | bs=1000 sw=10 sl=64 | p50 | 1,240,694 us | 1,209,779 us | 983,888 us | +2.6% | +26.1% | | bs=1000 sw=10 sl=64 | p95 | 1,386,463 us | 1,272,471 us | 1,030,100 us | +9.0% | +34.6% | | bs=1000 sw=10 sl=64 | p99 | 1,386,463 us | 1,272,471 us | 1,056,513 us | +9.0% | +31.2% | </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 0,10,10,64,20,593.53,200,128000,337,0.206,29319.37,39256.81,39256.81 1,100,10,64,20,2845.28,2000,1280000,703,0.429,140225.82,169830.29,169830.29 2,1000,10,64,20,24921.79,20000,12800000,803,0.490,1240694.27,1386462.80,1386462.80 ``` </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]
