github-actions[bot] commented on PR #6199: URL: https://github.com/apache/texera/pull/6199#issuecomment-4887552291
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 5 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `aaed085` 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/28754356296) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 401 | 0.245 | 23,224/44,227/44,227 us | 🔴 +32.3% / 🔴 +190.7% | | ⚪ | bs=100 sw=10 sl=64 | 936 | 0.571 | 104,616/127,232/127,232 us | ⚪ within ±5% / 🔴 +17.9% | | ⚪ | bs=1000 sw=10 sl=64 | 1,085 | 0.662 | 916,222/958,659/958,659 us | ⚪ within ±5% / 🟢 -9.1% | <details><summary>Baseline details</summary> Latest main `aaed085` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 401 tuples/sec | 432 tuples/sec | 777.63 tuples/sec | -7.2% | -48.4% | | bs=10 sw=10 sl=64 | MB/s | 0.245 MB/s | 0.263 MB/s | 0.475 MB/s | -6.8% | -48.4% | | bs=10 sw=10 sl=64 | p50 | 23,224 us | 21,357 us | 12,603 us | +8.7% | +84.3% | | bs=10 sw=10 sl=64 | p95 | 44,227 us | 33,425 us | 15,215 us | +32.3% | +190.7% | | bs=10 sw=10 sl=64 | p99 | 44,227 us | 33,425 us | 18,617 us | +32.3% | +137.6% | | bs=100 sw=10 sl=64 | throughput | 936 tuples/sec | 933 tuples/sec | 987.11 tuples/sec | +0.3% | -5.2% | | bs=100 sw=10 sl=64 | MB/s | 0.571 MB/s | 0.57 MB/s | 0.602 MB/s | +0.2% | -5.2% | | bs=100 sw=10 sl=64 | p50 | 104,616 us | 105,096 us | 101,428 us | -0.5% | +3.1% | | bs=100 sw=10 sl=64 | p95 | 127,232 us | 126,562 us | 107,959 us | +0.5% | +17.9% | | bs=100 sw=10 sl=64 | p99 | 127,232 us | 126,562 us | 114,777 us | +0.5% | +10.9% | | bs=1000 sw=10 sl=64 | throughput | 1,085 tuples/sec | 1,097 tuples/sec | 1,021 tuples/sec | -1.1% | +6.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.662 MB/s | 0.67 MB/s | 0.623 MB/s | -1.2% | +6.2% | | bs=1000 sw=10 sl=64 | p50 | 916,222 us | 912,141 us | 986,363 us | +0.4% | -7.1% | | bs=1000 sw=10 sl=64 | p95 | 958,659 us | 973,588 us | 1,026,594 us | -1.5% | -6.6% | | bs=1000 sw=10 sl=64 | p99 | 958,659 us | 973,588 us | 1,054,559 us | -1.5% | -9.1% | </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 0,10,10,64,20,498.60,200,128000,401,0.245,23223.84,44227.12,44227.12 1,100,10,64,20,2137.31,2000,1280000,936,0.571,104616.38,127231.99,127231.99 2,1000,10,64,20,18432.51,20000,12800000,1085,0.662,916222.14,958658.69,958658.69 ``` </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]
