github-actions[bot] commented on PR #8088: URL: https://github.com/apache/texera/pull/8088#issuecomment-5460041534
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `604f109` 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/33231123359) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 500 | 0.305 | 19,890/24,930/24,930 us | 🔴 -7.6% / 🔴 +78.2% | | 🔴 | bs=100 sw=10 sl=64 | 1,184 | 0.723 | 83,131/106,628/106,628 us | 🔴 +5.3% / 🔴 +12.2% | | ⚪ | bs=1000 sw=10 sl=64 | 1,409 | 0.86 | 700,781/843,274/843,274 us | ⚪ within ±5% / 🟢 -19.8% | <details><summary>Baseline details</summary> Latest main `604f109` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 500 tuples/sec | 541 tuples/sec | 894.27 tuples/sec | -7.6% | -44.1% | | bs=10 sw=10 sl=64 | MB/s | 0.305 MB/s | 0.33 MB/s | 0.546 MB/s | -7.6% | -44.1% | | bs=10 sw=10 sl=64 | p50 | 19,890 us | 18,718 us | 11,164 us | +6.3% | +78.2% | | bs=10 sw=10 sl=64 | p95 | 24,930 us | 26,538 us | 14,219 us | -6.1% | +75.3% | | bs=10 sw=10 sl=64 | p99 | 24,930 us | 26,538 us | 16,863 us | -6.1% | +47.8% | | bs=100 sw=10 sl=64 | throughput | 1,184 tuples/sec | 1,228 tuples/sec | 1,158 tuples/sec | -3.6% | +2.2% | | bs=100 sw=10 sl=64 | MB/s | 0.723 MB/s | 0.75 MB/s | 0.707 MB/s | -3.6% | +2.3% | | bs=100 sw=10 sl=64 | p50 | 83,131 us | 80,137 us | 88,711 us | +3.7% | -6.3% | | bs=100 sw=10 sl=64 | p95 | 106,628 us | 101,286 us | 95,062 us | +5.3% | +12.2% | | bs=100 sw=10 sl=64 | p99 | 106,628 us | 101,286 us | 102,275 us | +5.3% | +4.3% | | bs=1000 sw=10 sl=64 | throughput | 1,409 tuples/sec | 1,412 tuples/sec | 1,188 tuples/sec | -0.2% | +18.6% | | bs=1000 sw=10 sl=64 | MB/s | 0.86 MB/s | 0.862 MB/s | 0.725 MB/s | -0.2% | +18.6% | | bs=1000 sw=10 sl=64 | p50 | 700,781 us | 697,612 us | 874,204 us | +0.5% | -19.8% | | bs=1000 sw=10 sl=64 | p95 | 843,274 us | 816,977 us | 916,845 us | +3.2% | -8.0% | | bs=1000 sw=10 sl=64 | p99 | 843,274 us | 816,977 us | 947,186 us | +3.2% | -11.0% | </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 0,10,10,64,20,399.90,200,128000,500,0.305,19889.74,24929.86,24929.86 1,100,10,64,20,1689.54,2000,1280000,1184,0.723,83131.34,106627.58,106627.58 2,1000,10,64,20,14192.68,20000,12800000,1409,0.860,700781.42,843274.26,843274.26 ``` </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]
