github-actions[bot] commented on PR #6157: URL: https://github.com/apache/texera/pull/6157#issuecomment-4885515935
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `5acb734` 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/28735871602) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 399 | 0.243 | 24,323/32,394/32,394 us | 🔴 -9.7% / 🔴 +113.9% | | 🟢 | bs=100 sw=10 sl=64 | 830 | 0.507 | 119,678/132,950/132,950 us | 🟢 -14.5% / 🔴 +23.2% | | ⚪ | bs=1000 sw=10 sl=64 | 944 | 0.576 | 1,063,533/1,088,104/1,088,104 us | ⚪ within ±5% / 🔴 +7.5% | <details><summary>Baseline details</summary> Latest main `5acb734` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 399 tuples/sec | 440 tuples/sec | 776.36 tuples/sec | -9.3% | -48.6% | | bs=10 sw=10 sl=64 | MB/s | 0.243 MB/s | 0.269 MB/s | 0.474 MB/s | -9.7% | -48.7% | | bs=10 sw=10 sl=64 | p50 | 24,323 us | 22,403 us | 12,636 us | +8.6% | +92.5% | | bs=10 sw=10 sl=64 | p95 | 32,394 us | 33,116 us | 15,143 us | -2.2% | +113.9% | | bs=10 sw=10 sl=64 | p99 | 32,394 us | 33,116 us | 18,954 us | -2.2% | +70.9% | | bs=100 sw=10 sl=64 | throughput | 830 tuples/sec | 835 tuples/sec | 985.33 tuples/sec | -0.6% | -15.8% | | bs=100 sw=10 sl=64 | MB/s | 0.507 MB/s | 0.51 MB/s | 0.601 MB/s | -0.6% | -15.7% | | bs=100 sw=10 sl=64 | p50 | 119,678 us | 118,152 us | 101,671 us | +1.3% | +17.7% | | bs=100 sw=10 sl=64 | p95 | 132,950 us | 155,463 us | 107,939 us | -14.5% | +23.2% | | bs=100 sw=10 sl=64 | p99 | 132,950 us | 155,463 us | 113,798 us | -14.5% | +16.8% | | bs=1000 sw=10 sl=64 | throughput | 944 tuples/sec | 927 tuples/sec | 1,016 tuples/sec | +1.8% | -7.1% | | bs=1000 sw=10 sl=64 | MB/s | 0.576 MB/s | 0.566 MB/s | 0.62 MB/s | +1.8% | -7.2% | | bs=1000 sw=10 sl=64 | p50 | 1,063,533 us | 1,084,889 us | 989,693 us | -2.0% | +7.5% | | bs=1000 sw=10 sl=64 | p95 | 1,088,104 us | 1,107,084 us | 1,028,327 us | -1.7% | +5.8% | | bs=1000 sw=10 sl=64 | p99 | 1,088,104 us | 1,107,084 us | 1,059,969 us | -1.7% | +2.7% | </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 0,10,10,64,20,501.33,200,128000,399,0.243,24323.10,32393.78,32393.78 1,100,10,64,20,2409.69,2000,1280000,830,0.507,119677.67,132950.42,132950.42 2,1000,10,64,20,21184.90,20000,12800000,944,0.576,1063533.36,1088103.53,1088103.53 ``` </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]
