github-actions[bot] commented on PR #8872: URL: https://github.com/apache/texera/pull/8872#issuecomment-6009370025
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 7 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `1df2c56` 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/37413582429) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 385 | 0.235 | 25,246/31,939/31,939 us | 🔴 +11.2% / 🔴 +136.9% | | 🔴 | bs=100 sw=10 sl=64 | 783 | 0.478 | 123,889/175,454/175,454 us | 🔴 +17.9% / 🔴 +86.8% | | ⚪ | bs=1000 sw=10 sl=64 | 920 | 0.561 | 1,081,694/1,160,733/1,160,733 us | ⚪ within ±5% / 🔴 +28.3% | <details><summary>Baseline details</summary> Latest main `1df2c56` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 385 tuples/sec | 426 tuples/sec | 962.17 tuples/sec | -9.6% | -60.0% | | bs=10 sw=10 sl=64 | MB/s | 0.235 MB/s | 0.26 MB/s | 0.587 MB/s | -9.6% | -60.0% | | bs=10 sw=10 sl=64 | p50 | 25,246 us | 22,710 us | 11,046 us | +11.2% | +128.5% | | bs=10 sw=10 sl=64 | p95 | 31,939 us | 33,908 us | 13,484 us | -5.8% | +136.9% | | bs=10 sw=10 sl=64 | p99 | 31,939 us | 33,908 us | 16,626 us | -5.8% | +92.1% | | bs=100 sw=10 sl=64 | throughput | 783 tuples/sec | 829 tuples/sec | 1,234 tuples/sec | -5.5% | -36.6% | | bs=100 sw=10 sl=64 | MB/s | 0.478 MB/s | 0.506 MB/s | 0.753 MB/s | -5.5% | -36.5% | | bs=100 sw=10 sl=64 | p50 | 123,889 us | 119,071 us | 87,952 us | +4.0% | +40.9% | | bs=100 sw=10 sl=64 | p95 | 175,454 us | 148,863 us | 93,929 us | +17.9% | +86.8% | | bs=100 sw=10 sl=64 | p99 | 175,454 us | 148,863 us | 103,096 us | +17.9% | +70.2% | | bs=1000 sw=10 sl=64 | throughput | 920 tuples/sec | 920 tuples/sec | 1,272 tuples/sec | 0.0% | -27.7% | | bs=1000 sw=10 sl=64 | MB/s | 0.561 MB/s | 0.562 MB/s | 0.777 MB/s | -0.2% | -27.8% | | bs=1000 sw=10 sl=64 | p50 | 1,081,694 us | 1,089,207 us | 862,437 us | -0.7% | +25.4% | | bs=1000 sw=10 sl=64 | p95 | 1,160,733 us | 1,150,809 us | 904,996 us | +0.9% | +28.3% | | bs=1000 sw=10 sl=64 | p99 | 1,160,733 us | 1,150,809 us | 929,784 us | +0.9% | +24.8% | </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 0,10,10,64,20,519.46,200,128000,385,0.235,25245.50,31938.88,31938.88 1,100,10,64,20,2555.71,2000,1280000,783,0.478,123888.50,175453.62,175453.62 2,1000,10,64,20,21740.83,20000,12800000,920,0.561,1081694.37,1160732.62,1160732.62 ``` </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]
