github-actions[bot] commented on PR #6238: URL: https://github.com/apache/texera/pull/6238#issuecomment-4909323300
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 10 worse · ⚪ 3 noise (<±5%) · 0 without baseline > Compared against main `7c135ee` 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/28900511168) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 393 | 0.24 | 24,401/36,378/36,378 us | 🔴 +25.5% / 🔴 +130.3% | | 🔴 | bs=100 sw=10 sl=64 | 914 | 0.558 | 107,675/151,453/151,453 us | 🔴 +26.6% / 🔴 +37.1% | | 🟢 | bs=1000 sw=10 sl=64 | 1,116 | 0.681 | 901,386/917,892/917,892 us | 🟢 -5.5% / 🟢 -15.6% | <details><summary>Baseline details</summary> Latest main `7c135ee` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 393 tuples/sec | 479 tuples/sec | 749.87 tuples/sec | -18.0% | -47.6% | | bs=10 sw=10 sl=64 | MB/s | 0.24 MB/s | 0.292 MB/s | 0.458 MB/s | -17.8% | -47.6% | | bs=10 sw=10 sl=64 | p50 | 24,401 us | 19,437 us | 13,071 us | +25.5% | +86.7% | | bs=10 sw=10 sl=64 | p95 | 36,378 us | 34,392 us | 15,795 us | +5.8% | +130.3% | | bs=10 sw=10 sl=64 | p99 | 36,378 us | 34,392 us | 19,469 us | +5.8% | +86.9% | | bs=100 sw=10 sl=64 | throughput | 914 tuples/sec | 983 tuples/sec | 960.12 tuples/sec | -7.0% | -4.8% | | bs=100 sw=10 sl=64 | MB/s | 0.558 MB/s | 0.6 MB/s | 0.586 MB/s | -7.0% | -4.8% | | bs=100 sw=10 sl=64 | p50 | 107,675 us | 102,422 us | 104,066 us | +5.1% | +3.5% | | bs=100 sw=10 sl=64 | p95 | 151,453 us | 119,671 us | 110,469 us | +26.6% | +37.1% | | bs=100 sw=10 sl=64 | p99 | 151,453 us | 119,671 us | 116,561 us | +26.6% | +29.9% | | bs=1000 sw=10 sl=64 | throughput | 1,116 tuples/sec | 1,094 tuples/sec | 985.46 tuples/sec | +2.0% | +13.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.681 MB/s | 0.668 MB/s | 0.601 MB/s | +1.9% | +13.2% | | bs=1000 sw=10 sl=64 | p50 | 901,386 us | 914,808 us | 1,019,691 us | -1.5% | -11.6% | | bs=1000 sw=10 sl=64 | p95 | 917,892 us | 971,038 us | 1,058,233 us | -5.5% | -13.3% | | bs=1000 sw=10 sl=64 | p99 | 917,892 us | 971,038 us | 1,088,106 us | -5.5% | -15.6% | </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 0,10,10,64,20,508.56,200,128000,393,0.240,24400.54,36378.43,36378.43 1,100,10,64,20,2187.60,2000,1280000,914,0.558,107674.64,151453.31,151453.31 2,1000,10,64,20,17915.21,20000,12800000,1116,0.681,901386.29,917891.67,917891.67 ``` </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]
