github-actions[bot] commented on PR #6044: URL: https://github.com/apache/texera/pull/6044#issuecomment-4849424697
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `434bcae` 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/28487054582) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 450 | 0.275 | 20,918/28,406/28,406 us | 🔴 +13.8% / 🔴 +88.5% | | ⚪ | bs=100 sw=10 sl=64 | 934 | 0.57 | 104,465/126,662/126,662 us | ⚪ within ±5% / 🔴 +17.7% | | ⚪ | bs=1000 sw=10 sl=64 | 1,120 | 0.683 | 895,331/933,133/933,133 us | ⚪ within ±5% / 🟢 -11.8% | <details><summary>Baseline details</summary> Latest main `434bcae` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 450 tuples/sec | 475 tuples/sec | 777.62 tuples/sec | -5.3% | -42.1% | | bs=10 sw=10 sl=64 | MB/s | 0.275 MB/s | 0.29 MB/s | 0.475 MB/s | -5.2% | -42.1% | | bs=10 sw=10 sl=64 | p50 | 20,918 us | 18,386 us | 12,612 us | +13.8% | +65.9% | | bs=10 sw=10 sl=64 | p95 | 28,406 us | 29,979 us | 15,070 us | -5.2% | +88.5% | | bs=10 sw=10 sl=64 | p99 | 28,406 us | 29,979 us | 18,360 us | -5.2% | +54.7% | | bs=100 sw=10 sl=64 | throughput | 934 tuples/sec | 950 tuples/sec | 988.31 tuples/sec | -1.7% | -5.5% | | bs=100 sw=10 sl=64 | MB/s | 0.57 MB/s | 0.58 MB/s | 0.603 MB/s | -1.7% | -5.5% | | bs=100 sw=10 sl=64 | p50 | 104,465 us | 104,944 us | 101,066 us | -0.5% | +3.4% | | bs=100 sw=10 sl=64 | p95 | 126,662 us | 126,749 us | 107,594 us | -0.1% | +17.7% | | bs=100 sw=10 sl=64 | p99 | 126,662 us | 126,749 us | 115,830 us | -0.1% | +9.4% | | bs=1000 sw=10 sl=64 | throughput | 1,120 tuples/sec | 1,088 tuples/sec | 1,019 tuples/sec | +2.9% | +9.9% | | bs=1000 sw=10 sl=64 | MB/s | 0.683 MB/s | 0.664 MB/s | 0.622 MB/s | +2.9% | +9.8% | | bs=1000 sw=10 sl=64 | p50 | 895,331 us | 922,132 us | 986,982 us | -2.9% | -9.3% | | bs=1000 sw=10 sl=64 | p95 | 933,133 us | 942,911 us | 1,028,491 us | -1.0% | -9.3% | | bs=1000 sw=10 sl=64 | p99 | 933,133 us | 942,911 us | 1,058,493 us | -1.0% | -11.8% | </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 0,10,10,64,20,444.58,200,128000,450,0.275,20917.90,28406.23,28406.23 1,100,10,64,20,2140.74,2000,1280000,934,0.570,104464.52,126662.22,126662.22 2,1000,10,64,20,17861.05,20000,12800000,1120,0.683,895330.60,933132.58,933132.58 ``` </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]
