github-actions[bot] commented on PR #5737: URL: https://github.com/apache/texera/pull/5737#issuecomment-4724239310
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 7 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `cb30970` 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/27652779065) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 509 | 0.31 | 17,921/30,486/30,486 us | 🔴 +13.4% / 🟢 -24.7% | | 🔴 | bs=100 sw=10 sl=64 | 1,171 | 0.715 | 83,594/107,907/107,907 us | 🔴 +10.5% / 🟢 +31.3% | | ⚪ | bs=1000 sw=10 sl=64 | 1,433 | 0.874 | 699,567/755,678/755,678 us | ⚪ within ±5% / 🟢 +37.7% | <details><summary>Baseline details</summary> Latest main `cb30970` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 509 tuples/sec | 570 tuples/sec | 410.82 tuples/sec | -10.7% | +23.9% | | bs=10 sw=10 sl=64 | MB/s | 0.31 MB/s | 0.348 MB/s | 0.251 MB/s | -10.9% | +23.6% | | bs=10 sw=10 sl=64 | p50 | 17,921 us | 16,575 us | 23,785 us | +8.1% | -24.7% | | bs=10 sw=10 sl=64 | p95 | 30,486 us | 26,886 us | 34,980 us | +13.4% | -12.8% | | bs=10 sw=10 sl=64 | p99 | 30,486 us | 26,886 us | 34,980 us | +13.4% | -12.8% | | bs=100 sw=10 sl=64 | throughput | 1,171 tuples/sec | 1,216 tuples/sec | 891.94 tuples/sec | -3.7% | +31.3% | | bs=100 sw=10 sl=64 | MB/s | 0.715 MB/s | 0.742 MB/s | 0.544 MB/s | -3.6% | +31.3% | | bs=100 sw=10 sl=64 | p50 | 83,594 us | 80,984 us | 112,277 us | +3.2% | -25.5% | | bs=100 sw=10 sl=64 | p95 | 107,907 us | 97,662 us | 139,802 us | +10.5% | -22.8% | | bs=100 sw=10 sl=64 | p99 | 107,907 us | 97,662 us | 139,802 us | +10.5% | -22.8% | | bs=1000 sw=10 sl=64 | throughput | 1,433 tuples/sec | 1,409 tuples/sec | 1,041 tuples/sec | +1.7% | +37.7% | | bs=1000 sw=10 sl=64 | MB/s | 0.874 MB/s | 0.86 MB/s | 0.635 MB/s | +1.6% | +37.6% | | bs=1000 sw=10 sl=64 | p50 | 699,567 us | 715,064 us | 972,714 us | -2.2% | -28.1% | | bs=1000 sw=10 sl=64 | p95 | 755,678 us | 752,421 us | 1,023,057 us | +0.4% | -26.1% | | bs=1000 sw=10 sl=64 | p99 | 755,678 us | 752,421 us | 1,023,057 us | +0.4% | -26.1% | </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 0,10,10,64,20,393.17,200,128000,509,0.310,17921.15,30486.27,30486.27 1,100,10,64,20,1707.88,2000,1280000,1171,0.715,83594.13,107906.56,107906.56 2,1000,10,64,20,13960.41,20000,12800000,1433,0.874,699566.61,755677.85,755677.85 ``` </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]
