github-actions[bot] commented on PR #8597: URL: https://github.com/apache/texera/pull/8597#issuecomment-5735478893
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 3 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `5264df2` 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/35388586310) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 744 | 0.454 | 13,211/18,237/18,237 us | 🔴 +16.4% / 🔴 +18.0% | | ⚪ | bs=100 sw=10 sl=64 | 1,662 | 1.015 | 58,180/79,286/79,286 us | ⚪ within ±5% / 🟢 +62.0% | | ⚪ | bs=1000 sw=10 sl=64 | 1,982 | 1.21 | 501,694/571,795/571,795 us | ⚪ within ±5% / 🟢 +87.8% | <details><summary>Baseline details</summary> Latest main `5264df2` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 744 tuples/sec | 790 tuples/sec | 796.29 tuples/sec | -5.8% | -6.6% | | bs=10 sw=10 sl=64 | MB/s | 0.454 MB/s | 0.482 MB/s | 0.486 MB/s | -5.8% | -6.6% | | bs=10 sw=10 sl=64 | p50 | 13,211 us | 11,349 us | 12,549 us | +16.4% | +5.3% | | bs=10 sw=10 sl=64 | p95 | 18,237 us | 18,753 us | 15,458 us | -2.8% | +18.0% | | bs=10 sw=10 sl=64 | p99 | 18,237 us | 18,753 us | 19,275 us | -2.8% | -5.4% | | bs=100 sw=10 sl=64 | throughput | 1,662 tuples/sec | 1,675 tuples/sec | 1,027 tuples/sec | -0.8% | +61.9% | | bs=100 sw=10 sl=64 | MB/s | 1.015 MB/s | 1.022 MB/s | 0.627 MB/s | -0.7% | +62.0% | | bs=100 sw=10 sl=64 | p50 | 58,180 us | 57,379 us | 100,085 us | +1.4% | -41.9% | | bs=100 sw=10 sl=64 | p95 | 79,286 us | 82,646 us | 105,895 us | -4.1% | -25.1% | | bs=100 sw=10 sl=64 | p99 | 79,286 us | 82,646 us | 116,076 us | -4.1% | -31.7% | | bs=1000 sw=10 sl=64 | throughput | 1,982 tuples/sec | 2,003 tuples/sec | 1,055 tuples/sec | -1.0% | +87.8% | | bs=1000 sw=10 sl=64 | MB/s | 1.21 MB/s | 1.223 MB/s | 0.644 MB/s | -1.1% | +87.8% | | bs=1000 sw=10 sl=64 | p50 | 501,694 us | 497,346 us | 979,292 us | +0.9% | -48.8% | | bs=1000 sw=10 sl=64 | p95 | 571,795 us | 549,955 us | 1,018,835 us | +4.0% | -43.9% | | bs=1000 sw=10 sl=64 | p99 | 571,795 us | 549,955 us | 1,039,692 us | +4.0% | -45.0% | </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 0,10,10,64,20,268.64,200,128000,744,0.454,13210.97,18236.89,18236.89 1,100,10,64,20,1203.06,2000,1280000,1662,1.015,58180.37,79285.93,79285.93 2,1000,10,64,20,10091.28,20000,12800000,1982,1.210,501694.08,571794.86,571794.86 ``` </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]
