github-actions[bot] commented on PR #7165: URL: https://github.com/apache/texera/pull/7165#issuecomment-5143047444
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 7 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `45b7b20` 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/30631699599) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 409 | 0.25 | 24,864/32,283/32,283 us | 🔴 +23.4% / 🔴 +104.5% | | 🟢 | bs=100 sw=10 sl=64 | 946 | 0.577 | 105,222/124,057/124,057 us | 🟢 -18.9% / 🔴 +12.5% | | 🔴 | bs=1000 sw=10 sl=64 | 1,096 | 0.669 | 916,061/1,008,963/1,008,963 us | 🔴 +7.6% / 🟢 +9.5% | <details><summary>Baseline details</summary> Latest main `45b7b20` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 409 tuples/sec | 480 tuples/sec | 771.62 tuples/sec | -14.8% | -47.0% | | bs=10 sw=10 sl=64 | MB/s | 0.25 MB/s | 0.293 MB/s | 0.471 MB/s | -14.7% | -46.9% | | bs=10 sw=10 sl=64 | p50 | 24,864 us | 21,061 us | 12,626 us | +18.1% | +96.9% | | bs=10 sw=10 sl=64 | p95 | 32,283 us | 26,154 us | 15,786 us | +23.4% | +104.5% | | bs=10 sw=10 sl=64 | p99 | 32,283 us | 26,154 us | 19,344 us | +23.4% | +66.9% | | bs=100 sw=10 sl=64 | throughput | 946 tuples/sec | 906 tuples/sec | 971.56 tuples/sec | +4.4% | -2.6% | | bs=100 sw=10 sl=64 | MB/s | 0.577 MB/s | 0.553 MB/s | 0.593 MB/s | +4.3% | -2.7% | | bs=100 sw=10 sl=64 | p50 | 105,222 us | 105,279 us | 103,463 us | -0.1% | +1.7% | | bs=100 sw=10 sl=64 | p95 | 124,057 us | 152,970 us | 110,296 us | -18.9% | +12.5% | | bs=100 sw=10 sl=64 | p99 | 124,057 us | 152,970 us | 118,690 us | -18.9% | +4.5% | | bs=1000 sw=10 sl=64 | throughput | 1,096 tuples/sec | 1,120 tuples/sec | 1,001 tuples/sec | -2.1% | +9.5% | | bs=1000 sw=10 sl=64 | MB/s | 0.669 MB/s | 0.683 MB/s | 0.611 MB/s | -2.0% | +9.5% | | bs=1000 sw=10 sl=64 | p50 | 916,061 us | 894,712 us | 1,008,988 us | +2.4% | -9.2% | | bs=1000 sw=10 sl=64 | p95 | 1,008,963 us | 937,772 us | 1,055,260 us | +7.6% | -4.4% | | bs=1000 sw=10 sl=64 | p99 | 1,008,963 us | 937,772 us | 1,074,689 us | +7.6% | -6.1% | </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 0,10,10,64,20,488.63,200,128000,409,0.250,24863.79,32282.60,32282.60 1,100,10,64,20,2114.09,2000,1280000,946,0.577,105221.94,124056.55,124056.55 2,1000,10,64,20,18241.81,20000,12800000,1096,0.669,916060.89,1008963.33,1008963.33 ``` </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]
