github-actions[bot] commented on PR #8142: URL: https://github.com/apache/texera/pull/8142#issuecomment-5471074869
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `98588bf` 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/33333506551) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 496 | 0.303 | 20,156/27,340/27,340 us | 🔴 +25.1% / 🔴 +84.9% | | ⚪ | bs=100 sw=10 sl=64 | 1,087 | 0.664 | 89,749/123,882/123,882 us | ⚪ within ±5% / 🔴 +22.7% | | 🟢 | bs=1000 sw=10 sl=64 | 1,236 | 0.754 | 811,290/869,187/869,187 us | 🟢 -6.8% / 🟢 -12.7% | <details><summary>Baseline details</summary> Latest main `98588bf` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 496 tuples/sec | 604 tuples/sec | 844.57 tuples/sec | -17.9% | -41.3% | | bs=10 sw=10 sl=64 | MB/s | 0.303 MB/s | 0.369 MB/s | 0.515 MB/s | -17.9% | -41.2% | | bs=10 sw=10 sl=64 | p50 | 20,156 us | 16,118 us | 11,837 us | +25.1% | +70.3% | | bs=10 sw=10 sl=64 | p95 | 27,340 us | 27,128 us | 14,788 us | +0.8% | +84.9% | | bs=10 sw=10 sl=64 | p99 | 27,340 us | 27,128 us | 17,651 us | +0.8% | +54.9% | | bs=100 sw=10 sl=64 | throughput | 1,087 tuples/sec | 1,101 tuples/sec | 1,084 tuples/sec | -1.3% | +0.3% | | bs=100 sw=10 sl=64 | MB/s | 0.664 MB/s | 0.672 MB/s | 0.662 MB/s | -1.2% | +0.4% | | bs=100 sw=10 sl=64 | p50 | 89,749 us | 86,176 us | 94,505 us | +4.1% | -5.0% | | bs=100 sw=10 sl=64 | p95 | 123,882 us | 124,273 us | 100,941 us | -0.3% | +22.7% | | bs=100 sw=10 sl=64 | p99 | 123,882 us | 124,273 us | 108,642 us | -0.3% | +14.0% | | bs=1000 sw=10 sl=64 | throughput | 1,236 tuples/sec | 1,229 tuples/sec | 1,119 tuples/sec | +0.6% | +10.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.754 MB/s | 0.75 MB/s | 0.683 MB/s | +0.5% | +10.4% | | bs=1000 sw=10 sl=64 | p50 | 811,290 us | 810,218 us | 924,404 us | +0.1% | -12.2% | | bs=1000 sw=10 sl=64 | p95 | 869,187 us | 933,016 us | 967,785 us | -6.8% | -10.2% | | bs=1000 sw=10 sl=64 | p99 | 869,187 us | 933,016 us | 995,630 us | -6.8% | -12.7% | </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 0,10,10,64,20,402.93,200,128000,496,0.303,20155.83,27340.29,27340.29 1,100,10,64,20,1839.15,2000,1280000,1087,0.664,89748.91,123882.04,123882.04 2,1000,10,64,20,16182.54,20000,12800000,1236,0.754,811289.62,869187.35,869187.35 ``` </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]
