github-actions[bot] commented on PR #7989: URL: https://github.com/apache/texera/pull/7989#issuecomment-5421298155
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 2 worse · ⚪ 11 noise (<±5%) · 0 without baseline > Compared against main `5de9bf9` 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/32936429618) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 789 | 0.482 | 11,952/16,170/16,170 us | 🟢 -12.5% / 🔴 +18.9% | | 🔴 | bs=100 sw=10 sl=64 | 1,856 | 1.133 | 52,494/66,482/66,482 us | 🔴 +10.9% / 🟢 +56.3% | | ⚪ | bs=1000 sw=10 sl=64 | 2,136 | 1.304 | 463,343/509,673/509,673 us | ⚪ within ±5% / 🟢 +74.9% | <details><summary>Baseline details</summary> Latest main `5de9bf9` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 789 tuples/sec | 792 tuples/sec | 908.02 tuples/sec | -0.4% | -13.1% | | bs=10 sw=10 sl=64 | MB/s | 0.482 MB/s | 0.483 MB/s | 0.554 MB/s | -0.2% | -13.0% | | bs=10 sw=10 sl=64 | p50 | 11,952 us | 12,494 us | 10,907 us | -4.3% | +9.6% | | bs=10 sw=10 sl=64 | p95 | 16,170 us | 18,488 us | 13,604 us | -12.5% | +18.9% | | bs=10 sw=10 sl=64 | p99 | 16,170 us | 18,488 us | 16,697 us | -12.5% | -3.2% | | bs=100 sw=10 sl=64 | throughput | 1,856 tuples/sec | 1,893 tuples/sec | 1,188 tuples/sec | -2.0% | +56.3% | | bs=100 sw=10 sl=64 | MB/s | 1.133 MB/s | 1.155 MB/s | 0.725 MB/s | -1.9% | +56.3% | | bs=100 sw=10 sl=64 | p50 | 52,494 us | 52,073 us | 85,003 us | +0.8% | -38.2% | | bs=100 sw=10 sl=64 | p95 | 66,482 us | 59,933 us | 91,599 us | +10.9% | -27.4% | | bs=100 sw=10 sl=64 | p99 | 66,482 us | 59,933 us | 99,202 us | +10.9% | -33.0% | | bs=1000 sw=10 sl=64 | throughput | 2,136 tuples/sec | 2,134 tuples/sec | 1,221 tuples/sec | +0.1% | +74.9% | | bs=1000 sw=10 sl=64 | MB/s | 1.304 MB/s | 1.302 MB/s | 0.745 MB/s | +0.2% | +74.9% | | bs=1000 sw=10 sl=64 | p50 | 463,343 us | 465,774 us | 837,593 us | -0.5% | -44.7% | | bs=1000 sw=10 sl=64 | p95 | 509,673 us | 507,942 us | 881,015 us | +0.3% | -42.1% | | bs=1000 sw=10 sl=64 | p99 | 509,673 us | 507,942 us | 915,550 us | +0.3% | -44.3% | </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 0,10,10,64,20,253.44,200,128000,789,0.482,11951.96,16170.36,16170.36 1,100,10,64,20,1077.44,2000,1280000,1856,1.133,52494.28,66481.98,66481.98 2,1000,10,64,20,9363.34,20000,12800000,2136,1.304,463343.07,509672.98,509672.98 ``` </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]
