github-actions[bot] commented on PR #6009: URL: https://github.com/apache/texera/pull/6009#issuecomment-4828070125
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 4 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `e5b928f` 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/28341639148) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 392 | 0.239 | 25,158/35,519/35,519 us | 🔴 +19.1% / 🔴 +131.6% | | 🔴 | bs=100 sw=10 sl=64 | 829 | 0.506 | 120,685/135,069/135,069 us | 🔴 +5.1% / 🔴 +22.1% | | 🔴 | bs=1000 sw=10 sl=64 | 960 | 0.586 | 1,037,758/1,108,152/1,108,152 us | 🔴 +5.7% / ⚪ within ±5% | <details><summary>Baseline details</summary> Latest main `e5b928f` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 392 tuples/sec | 408 tuples/sec | 757.16 tuples/sec | -3.9% | -48.2% | | bs=10 sw=10 sl=64 | MB/s | 0.239 MB/s | 0.249 MB/s | 0.462 MB/s | -4.0% | -48.3% | | bs=10 sw=10 sl=64 | p50 | 25,158 us | 21,126 us | 12,971 us | +19.1% | +94.0% | | bs=10 sw=10 sl=64 | p95 | 35,519 us | 39,144 us | 15,333 us | -9.3% | +131.6% | | bs=10 sw=10 sl=64 | p99 | 35,519 us | 39,144 us | 18,732 us | -9.3% | +89.6% | | bs=100 sw=10 sl=64 | throughput | 829 tuples/sec | 860 tuples/sec | 957.66 tuples/sec | -3.6% | -13.4% | | bs=100 sw=10 sl=64 | MB/s | 0.506 MB/s | 0.525 MB/s | 0.585 MB/s | -3.6% | -13.4% | | bs=100 sw=10 sl=64 | p50 | 120,685 us | 114,837 us | 103,982 us | +5.1% | +16.1% | | bs=100 sw=10 sl=64 | p95 | 135,069 us | 134,460 us | 110,583 us | +0.5% | +22.1% | | bs=100 sw=10 sl=64 | p99 | 135,069 us | 134,460 us | 118,369 us | +0.5% | +14.1% | | bs=1000 sw=10 sl=64 | throughput | 960 tuples/sec | 974 tuples/sec | 979.6 tuples/sec | -1.4% | -2.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.586 MB/s | 0.595 MB/s | 0.598 MB/s | -1.5% | -2.0% | | bs=1000 sw=10 sl=64 | p50 | 1,037,758 us | 1,024,729 us | 1,024,553 us | +1.3% | +1.3% | | bs=1000 sw=10 sl=64 | p95 | 1,108,152 us | 1,047,991 us | 1,063,789 us | +5.7% | +4.2% | | bs=1000 sw=10 sl=64 | p99 | 1,108,152 us | 1,047,991 us | 1,096,239 us | +5.7% | +1.1% | </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 0,10,10,64,20,509.88,200,128000,392,0.239,25158.05,35519.00,35519.00 1,100,10,64,20,2413.02,2000,1280000,829,0.506,120684.75,135068.66,135068.66 2,1000,10,64,20,20834.66,20000,12800000,960,0.586,1037757.74,1108152.12,1108152.12 ``` </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]
