github-actions[bot] commented on PR #8509: URL: https://github.com/apache/texera/pull/8509#issuecomment-5660815327
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 5 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `fd09f20` 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/34818618150) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 618 | 0.377 | 15,698/24,269/24,269 us | 🔴 +8.0% / 🔴 +65.2% | | 🔴 | bs=100 sw=10 sl=64 | 1,344 | 0.82 | 73,897/104,072/104,072 us | 🔴 +14.3% / 🟢 +22.7% | | ⚪ | bs=1000 sw=10 sl=64 | 1,516 | 0.925 | 655,784/726,392/726,392 us | ⚪ within ±5% / 🟢 +34.6% | <details><summary>Baseline details</summary> Latest main `fd09f20` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 618 tuples/sec | 667 tuples/sec | 838.23 tuples/sec | -7.3% | -26.3% | | bs=10 sw=10 sl=64 | MB/s | 0.377 MB/s | 0.407 MB/s | 0.512 MB/s | -7.4% | -26.3% | | bs=10 sw=10 sl=64 | p50 | 15,698 us | 14,533 us | 11,878 us | +8.0% | +32.2% | | bs=10 sw=10 sl=64 | p95 | 24,269 us | 25,493 us | 14,690 us | -4.8% | +65.2% | | bs=10 sw=10 sl=64 | p99 | 24,269 us | 25,493 us | 18,483 us | -4.8% | +31.3% | | bs=100 sw=10 sl=64 | throughput | 1,344 tuples/sec | 1,360 tuples/sec | 1,095 tuples/sec | -1.2% | +22.7% | | bs=100 sw=10 sl=64 | MB/s | 0.82 MB/s | 0.83 MB/s | 0.668 MB/s | -1.2% | +22.7% | | bs=100 sw=10 sl=64 | p50 | 73,897 us | 72,222 us | 92,901 us | +2.3% | -20.5% | | bs=100 sw=10 sl=64 | p95 | 104,072 us | 91,055 us | 99,480 us | +14.3% | +4.6% | | bs=100 sw=10 sl=64 | p99 | 104,072 us | 91,055 us | 112,580 us | +14.3% | -7.6% | | bs=1000 sw=10 sl=64 | throughput | 1,516 tuples/sec | 1,519 tuples/sec | 1,126 tuples/sec | -0.2% | +34.6% | | bs=1000 sw=10 sl=64 | MB/s | 0.925 MB/s | 0.927 MB/s | 0.687 MB/s | -0.2% | +34.6% | | bs=1000 sw=10 sl=64 | p50 | 655,784 us | 660,127 us | 912,010 us | -0.7% | -28.1% | | bs=1000 sw=10 sl=64 | p95 | 726,392 us | 695,996 us | 950,922 us | +4.4% | -23.6% | | bs=1000 sw=10 sl=64 | p99 | 726,392 us | 695,996 us | 983,333 us | +4.4% | -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 0,10,10,64,20,323.61,200,128000,618,0.377,15698.30,24269.12,24269.12 1,100,10,64,20,1487.96,2000,1280000,1344,0.820,73897.11,104071.90,104071.90 2,1000,10,64,20,13196.61,20000,12800000,1516,0.925,655783.60,726391.66,726391.66 ``` </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]
