github-actions[bot] commented on PR #6659: URL: https://github.com/apache/texera/pull/6659#issuecomment-5027538348
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `f14cd39` 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/29780595281) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 383 | 0.234 | 23,362/40,683/40,683 us | 🔴 +43.8% / 🔴 +160.2% | | 🟢 | bs=100 sw=10 sl=64 | 978 | 0.597 | 102,447/116,020/116,020 us | 🟢 -8.5% / 🔴 +9.5% | | ⚪ | bs=1000 sw=10 sl=64 | 1,101 | 0.672 | 909,178/956,762/956,762 us | ⚪ within ±5% / 🟢 -8.8% | <details><summary>Baseline details</summary> Latest main `f14cd39` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 383 tuples/sec | 472 tuples/sec | 767.23 tuples/sec | -18.9% | -50.1% | | bs=10 sw=10 sl=64 | MB/s | 0.234 MB/s | 0.288 MB/s | 0.468 MB/s | -18.7% | -50.0% | | bs=10 sw=10 sl=64 | p50 | 23,362 us | 21,940 us | 12,705 us | +6.5% | +83.9% | | bs=10 sw=10 sl=64 | p95 | 40,683 us | 28,298 us | 15,633 us | +43.8% | +160.2% | | bs=10 sw=10 sl=64 | p99 | 40,683 us | 28,298 us | 20,214 us | +43.8% | +101.3% | | bs=100 sw=10 sl=64 | throughput | 978 tuples/sec | 967 tuples/sec | 1,001 tuples/sec | +1.1% | -2.3% | | bs=100 sw=10 sl=64 | MB/s | 0.597 MB/s | 0.59 MB/s | 0.611 MB/s | +1.2% | -2.3% | | bs=100 sw=10 sl=64 | p50 | 102,447 us | 102,117 us | 99,949 us | +0.3% | +2.5% | | bs=100 sw=10 sl=64 | p95 | 116,020 us | 126,840 us | 105,996 us | -8.5% | +9.5% | | bs=100 sw=10 sl=64 | p99 | 116,020 us | 126,840 us | 117,999 us | -8.5% | -1.7% | | bs=1000 sw=10 sl=64 | throughput | 1,101 tuples/sec | 1,118 tuples/sec | 1,033 tuples/sec | -1.5% | +6.6% | | bs=1000 sw=10 sl=64 | MB/s | 0.672 MB/s | 0.682 MB/s | 0.631 MB/s | -1.5% | +6.6% | | bs=1000 sw=10 sl=64 | p50 | 909,178 us | 892,838 us | 974,571 us | +1.8% | -6.7% | | bs=1000 sw=10 sl=64 | p95 | 956,762 us | 968,743 us | 1,016,467 us | -1.2% | -5.9% | | bs=1000 sw=10 sl=64 | p99 | 956,762 us | 968,743 us | 1,048,798 us | -1.2% | -8.8% | </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 0,10,10,64,20,522.44,200,128000,383,0.234,23362.02,40682.61,40682.61 1,100,10,64,20,2045.23,2000,1280000,978,0.597,102447.28,116019.93,116019.93 2,1000,10,64,20,18167.77,20000,12800000,1101,0.672,909177.74,956761.97,956761.97 ``` </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]
