github-actions[bot] commented on PR #8073: URL: https://github.com/apache/texera/pull/8073#issuecomment-5456867726
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 7 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `bdc6d2a` 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/33201531779) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 526 | 0.321 | 18,760/22,786/22,786 us | 🔴 +19.7% / 🔴 +68.0% | | 🔴 | bs=100 sw=10 sl=64 | 1,136 | 0.693 | 84,562/112,320/112,320 us | 🔴 +17.6% / 🔴 +18.2% | | ⚪ | bs=1000 sw=10 sl=64 | 1,342 | 0.819 | 744,037/788,116/788,116 us | ⚪ within ±5% / 🟢 -16.8% | <details><summary>Baseline details</summary> Latest main `bdc6d2a` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 526 tuples/sec | 568 tuples/sec | 894.27 tuples/sec | -7.4% | -41.2% | | bs=10 sw=10 sl=64 | MB/s | 0.321 MB/s | 0.347 MB/s | 0.546 MB/s | -7.5% | -41.2% | | bs=10 sw=10 sl=64 | p50 | 18,760 us | 15,667 us | 11,164 us | +19.7% | +68.0% | | bs=10 sw=10 sl=64 | p95 | 22,786 us | 28,065 us | 14,219 us | -18.8% | +60.2% | | bs=10 sw=10 sl=64 | p99 | 22,786 us | 28,065 us | 16,863 us | -18.8% | +35.1% | | bs=100 sw=10 sl=64 | throughput | 1,136 tuples/sec | 1,209 tuples/sec | 1,158 tuples/sec | -6.0% | -1.9% | | bs=100 sw=10 sl=64 | MB/s | 0.693 MB/s | 0.738 MB/s | 0.707 MB/s | -6.1% | -2.0% | | bs=100 sw=10 sl=64 | p50 | 84,562 us | 81,586 us | 88,711 us | +3.6% | -4.7% | | bs=100 sw=10 sl=64 | p95 | 112,320 us | 95,531 us | 95,062 us | +17.6% | +18.2% | | bs=100 sw=10 sl=64 | p99 | 112,320 us | 95,531 us | 102,275 us | +17.6% | +9.8% | | bs=1000 sw=10 sl=64 | throughput | 1,342 tuples/sec | 1,362 tuples/sec | 1,188 tuples/sec | -1.5% | +13.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.819 MB/s | 0.831 MB/s | 0.725 MB/s | -1.4% | +13.0% | | bs=1000 sw=10 sl=64 | p50 | 744,037 us | 733,377 us | 874,204 us | +1.5% | -14.9% | | bs=1000 sw=10 sl=64 | p95 | 788,116 us | 773,315 us | 916,845 us | +1.9% | -14.0% | | bs=1000 sw=10 sl=64 | p99 | 788,116 us | 773,315 us | 947,186 us | +1.9% | -16.8% | </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 0,10,10,64,20,380.15,200,128000,526,0.321,18759.97,22786.01,22786.01 1,100,10,64,20,1760.75,2000,1280000,1136,0.693,84562.42,112320.47,112320.47 2,1000,10,64,20,14908.60,20000,12800000,1342,0.819,744036.68,788115.67,788115.67 ``` </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]
