github-actions[bot] commented on PR #6988: URL: https://github.com/apache/texera/pull/6988#issuecomment-5111935013
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 3 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `469e8f0` 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/30415461462) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 373 | 0.228 | 27,062/32,607/32,607 us | 🟢 -9.6% / 🔴 +120.8% | | 🔴 | bs=100 sw=10 sl=64 | 737 | 0.45 | 134,163/166,330/166,330 us | 🟢 -11.2% / 🔴 +55.0% | | 🔴 | bs=1000 sw=10 sl=64 | 835 | 0.51 | 1,194,228/1,312,017/1,312,017 us | 🔴 +7.6% / 🔴 +27.7% | <details><summary>Baseline details</summary> Latest main `469e8f0` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 373 tuples/sec | 381 tuples/sec | 787.55 tuples/sec | -2.1% | -52.6% | | bs=10 sw=10 sl=64 | MB/s | 0.228 MB/s | 0.233 MB/s | 0.481 MB/s | -2.1% | -52.6% | | bs=10 sw=10 sl=64 | p50 | 27,062 us | 26,307 us | 12,255 us | +2.9% | +120.8% | | bs=10 sw=10 sl=64 | p95 | 32,607 us | 36,084 us | 15,802 us | -9.6% | +106.3% | | bs=10 sw=10 sl=64 | p99 | 32,607 us | 36,084 us | 19,008 us | -9.6% | +71.5% | | bs=100 sw=10 sl=64 | throughput | 737 tuples/sec | 766 tuples/sec | 997.81 tuples/sec | -3.8% | -26.1% | | bs=100 sw=10 sl=64 | MB/s | 0.45 MB/s | 0.467 MB/s | 0.609 MB/s | -3.6% | -26.1% | | bs=100 sw=10 sl=64 | p50 | 134,163 us | 127,233 us | 100,690 us | +5.4% | +33.2% | | bs=100 sw=10 sl=64 | p95 | 166,330 us | 187,361 us | 107,316 us | -11.2% | +55.0% | | bs=100 sw=10 sl=64 | p99 | 166,330 us | 187,361 us | 113,823 us | -11.2% | +46.1% | | bs=1000 sw=10 sl=64 | throughput | 835 tuples/sec | 849 tuples/sec | 1,030 tuples/sec | -1.6% | -19.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.51 MB/s | 0.518 MB/s | 0.629 MB/s | -1.5% | -18.9% | | bs=1000 sw=10 sl=64 | p50 | 1,194,228 us | 1,172,941 us | 981,213 us | +1.8% | +21.7% | | bs=1000 sw=10 sl=64 | p95 | 1,312,017 us | 1,219,607 us | 1,027,605 us | +7.6% | +27.7% | | bs=1000 sw=10 sl=64 | p99 | 1,312,017 us | 1,219,607 us | 1,055,466 us | +7.6% | +24.3% | </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 0,10,10,64,20,536.14,200,128000,373,0.228,27061.92,32606.78,32606.78 1,100,10,64,20,2711.87,2000,1280000,737,0.450,134163.48,166330.36,166330.36 2,1000,10,64,20,23944.76,20000,12800000,835,0.510,1194228.21,1312016.54,1312016.54 ``` </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]
