github-actions[bot] commented on PR #8750: URL: https://github.com/apache/texera/pull/8750#issuecomment-5883176460
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 6 better · 🔴 3 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `acc6dd1` 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/36517795266) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 683 | 0.417 | 14,188/17,849/17,849 us | 🟢 -25.1% / 🔴 -15.4% | | 🔴 | bs=100 sw=10 sl=64 | 1,737 | 1.06 | 56,181/73,819/73,819 us | 🔴 +7.2% / 🟢 +67.2% | | 🟢 | bs=1000 sw=10 sl=64 | 2,015 | 1.23 | 489,572/567,639/567,639 us | 🟢 -6.0% / 🟢 +89.2% | <details><summary>Baseline details</summary> Latest main `acc6dd1` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 683 tuples/sec | 725 tuples/sec | 807.63 tuples/sec | -5.8% | -15.4% | | bs=10 sw=10 sl=64 | MB/s | 0.417 MB/s | 0.443 MB/s | 0.493 MB/s | -5.9% | -15.4% | | bs=10 sw=10 sl=64 | p50 | 14,188 us | 13,989 us | 12,578 us | +1.4% | +12.8% | | bs=10 sw=10 sl=64 | p95 | 17,849 us | 23,823 us | 16,088 us | -25.1% | +11.0% | | bs=10 sw=10 sl=64 | p99 | 17,849 us | 23,823 us | 19,009 us | -25.1% | -6.1% | | bs=100 sw=10 sl=64 | throughput | 1,737 tuples/sec | 1,784 tuples/sec | 1,039 tuples/sec | -2.6% | +67.2% | | bs=100 sw=10 sl=64 | MB/s | 1.06 MB/s | 1.089 MB/s | 0.634 MB/s | -2.7% | +67.1% | | bs=100 sw=10 sl=64 | p50 | 56,181 us | 52,387 us | 101,098 us | +7.2% | -44.4% | | bs=100 sw=10 sl=64 | p95 | 73,819 us | 78,405 us | 107,890 us | -5.8% | -31.6% | | bs=100 sw=10 sl=64 | p99 | 73,819 us | 78,405 us | 119,853 us | -5.8% | -38.4% | | bs=1000 sw=10 sl=64 | throughput | 2,015 tuples/sec | 1,996 tuples/sec | 1,065 tuples/sec | +1.0% | +89.2% | | bs=1000 sw=10 sl=64 | MB/s | 1.23 MB/s | 1.218 MB/s | 0.65 MB/s | +1.0% | +89.2% | | bs=1000 sw=10 sl=64 | p50 | 489,572 us | 487,542 us | 992,940 us | +0.4% | -50.7% | | bs=1000 sw=10 sl=64 | p95 | 567,639 us | 604,094 us | 1,035,756 us | -6.0% | -45.2% | | bs=1000 sw=10 sl=64 | p99 | 567,639 us | 604,094 us | 1,062,329 us | -6.0% | -46.6% | </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 0,10,10,64,20,292.66,200,128000,683,0.417,14187.93,17849.39,17849.39 1,100,10,64,20,1151.09,2000,1280000,1737,1.060,56180.58,73818.64,73818.64 2,1000,10,64,20,9925.72,20000,12800000,2015,1.230,489572.40,567638.71,567638.71 ``` </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]
