github-actions[bot] commented on PR #7586: URL: https://github.com/apache/texera/pull/7586#issuecomment-5262336961
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 4 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `408b33a` 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/31563553497) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 479 | 0.292 | 19,299/28,484/28,484 us | 🟢 -9.9% / 🔴 +78.1% | | 🔴 | bs=100 sw=10 sl=64 | 1,022 | 0.624 | 96,271/131,014/131,014 us | 🔴 +5.3% / 🔴 +21.2% | | ⚪ | bs=1000 sw=10 sl=64 | 1,205 | 0.735 | 831,385/880,627/880,627 us | ⚪ within ±5% / 🟢 -17.6% | <details><summary>Baseline details</summary> Latest main `408b33a` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 479 tuples/sec | 506 tuples/sec | 784.3 tuples/sec | -5.3% | -38.9% | | bs=10 sw=10 sl=64 | MB/s | 0.292 MB/s | 0.309 MB/s | 0.479 MB/s | -5.5% | -39.0% | | bs=10 sw=10 sl=64 | p50 | 19,299 us | 18,056 us | 12,590 us | +6.9% | +53.3% | | bs=10 sw=10 sl=64 | p95 | 28,484 us | 31,622 us | 15,991 us | -9.9% | +78.1% | | bs=10 sw=10 sl=64 | p99 | 28,484 us | 31,622 us | 18,694 us | -9.9% | +52.4% | | bs=100 sw=10 sl=64 | throughput | 1,022 tuples/sec | 1,037 tuples/sec | 1,002 tuples/sec | -1.4% | +2.0% | | bs=100 sw=10 sl=64 | MB/s | 0.624 MB/s | 0.633 MB/s | 0.612 MB/s | -1.4% | +2.0% | | bs=100 sw=10 sl=64 | p50 | 96,271 us | 91,391 us | 101,285 us | +5.3% | -4.9% | | bs=100 sw=10 sl=64 | p95 | 131,014 us | 128,548 us | 108,068 us | +1.9% | +21.2% | | bs=100 sw=10 sl=64 | p99 | 131,014 us | 128,548 us | 118,235 us | +1.9% | +10.8% | | bs=1000 sw=10 sl=64 | throughput | 1,205 tuples/sec | 1,207 tuples/sec | 1,030 tuples/sec | -0.2% | +17.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.735 MB/s | 0.737 MB/s | 0.629 MB/s | -0.3% | +16.9% | | bs=1000 sw=10 sl=64 | p50 | 831,385 us | 831,083 us | 991,882 us | +0.0% | -16.2% | | bs=1000 sw=10 sl=64 | p95 | 880,627 us | 881,519 us | 1,038,496 us | -0.1% | -15.2% | | bs=1000 sw=10 sl=64 | p99 | 880,627 us | 881,519 us | 1,068,265 us | -0.1% | -17.6% | </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 0,10,10,64,20,417.56,200,128000,479,0.292,19298.60,28484.42,28484.42 1,100,10,64,20,1957.27,2000,1280000,1022,0.624,96271.42,131014.24,131014.24 2,1000,10,64,20,16602.28,20000,12800000,1205,0.735,831385.20,880627.23,880627.23 ``` </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]
