github-actions[bot] commented on PR #5722: URL: https://github.com/apache/texera/pull/5722#issuecomment-4704541344
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 1 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `83df2b5` 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/27523695206) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 450 | 0.275 | 21,828/28,385/28,385 us | 🟢 -12.2% / 🟢 -18.9% | | 🔴 | bs=100 sw=10 sl=64 | 933 | 0.569 | 106,843/129,770/129,770 us | 🔴 +6.3% / 🟢 -7.2% | | ⚪ | bs=1000 sw=10 sl=64 | 1,123 | 0.686 | 888,183/951,775/951,775 us | ⚪ within ±5% / 🟢 -8.7% | <details><summary>Baseline details</summary> Latest main `83df2b5` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 450 tuples/sec | 436 tuples/sec | 410.82 tuples/sec | +3.2% | +9.5% | | bs=10 sw=10 sl=64 | MB/s | 0.275 MB/s | 0.266 MB/s | 0.251 MB/s | +3.4% | +9.7% | | bs=10 sw=10 sl=64 | p50 | 21,828 us | 22,005 us | 23,785 us | -0.8% | -8.2% | | bs=10 sw=10 sl=64 | p95 | 28,385 us | 32,346 us | 34,980 us | -12.2% | -18.9% | | bs=10 sw=10 sl=64 | p99 | 28,385 us | 32,346 us | 34,980 us | -12.2% | -18.9% | | bs=100 sw=10 sl=64 | throughput | 933 tuples/sec | 967 tuples/sec | 891.94 tuples/sec | -3.5% | +4.6% | | bs=100 sw=10 sl=64 | MB/s | 0.569 MB/s | 0.59 MB/s | 0.544 MB/s | -3.6% | +4.5% | | bs=100 sw=10 sl=64 | p50 | 106,843 us | 100,469 us | 112,277 us | +6.3% | -4.8% | | bs=100 sw=10 sl=64 | p95 | 129,770 us | 127,531 us | 139,802 us | +1.8% | -7.2% | | bs=100 sw=10 sl=64 | p99 | 129,770 us | 127,531 us | 139,802 us | +1.8% | -7.2% | | bs=1000 sw=10 sl=64 | throughput | 1,123 tuples/sec | 1,122 tuples/sec | 1,041 tuples/sec | +0.1% | +7.9% | | bs=1000 sw=10 sl=64 | MB/s | 0.686 MB/s | 0.685 MB/s | 0.635 MB/s | +0.1% | +8.0% | | bs=1000 sw=10 sl=64 | p50 | 888,183 us | 893,407 us | 972,714 us | -0.6% | -8.7% | | bs=1000 sw=10 sl=64 | p95 | 951,775 us | 949,391 us | 1,023,057 us | +0.3% | -7.0% | | bs=1000 sw=10 sl=64 | p99 | 951,775 us | 949,391 us | 1,023,057 us | +0.3% | -7.0% | </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 0,10,10,64,20,443.98,200,128000,450,0.275,21828.47,28384.52,28384.52 1,100,10,64,20,2144.06,2000,1280000,933,0.569,106842.67,129769.55,129769.55 2,1000,10,64,20,17804.00,20000,12800000,1123,0.686,888183.15,951775.34,951775.34 ``` </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]
