github-actions[bot] commented on PR #8192: URL: https://github.com/apache/texera/pull/8192#issuecomment-5472772087
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 4 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `70c2114` 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/33348969802) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 432 | 0.264 | 22,538/31,959/31,959 us | 🔴 +12.0% / 🔴 +116.1% | | 🔴 | bs=100 sw=10 sl=64 | 907 | 0.554 | 107,263/167,990/167,990 us | 🔴 +38.8% / 🔴 +66.4% | | ⚪ | bs=1000 sw=10 sl=64 | 1,081 | 0.66 | 922,891/976,156/976,156 us | ⚪ within ±5% / ⚪ within ±5% | <details><summary>Baseline details</summary> Latest main `70c2114` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 432 tuples/sec | 453 tuples/sec | 844.57 tuples/sec | -4.6% | -48.8% | | bs=10 sw=10 sl=64 | MB/s | 0.264 MB/s | 0.277 MB/s | 0.515 MB/s | -4.7% | -48.8% | | bs=10 sw=10 sl=64 | p50 | 22,538 us | 20,123 us | 11,837 us | +12.0% | +90.4% | | bs=10 sw=10 sl=64 | p95 | 31,959 us | 33,910 us | 14,788 us | -5.8% | +116.1% | | bs=10 sw=10 sl=64 | p99 | 31,959 us | 33,910 us | 17,651 us | -5.8% | +81.1% | | bs=100 sw=10 sl=64 | throughput | 907 tuples/sec | 956 tuples/sec | 1,084 tuples/sec | -5.1% | -16.3% | | bs=100 sw=10 sl=64 | MB/s | 0.554 MB/s | 0.583 MB/s | 0.662 MB/s | -5.0% | -16.3% | | bs=100 sw=10 sl=64 | p50 | 107,263 us | 103,340 us | 94,505 us | +3.8% | +13.5% | | bs=100 sw=10 sl=64 | p95 | 167,990 us | 121,011 us | 100,941 us | +38.8% | +66.4% | | bs=100 sw=10 sl=64 | p99 | 167,990 us | 121,011 us | 108,642 us | +38.8% | +54.6% | | bs=1000 sw=10 sl=64 | throughput | 1,081 tuples/sec | 1,110 tuples/sec | 1,119 tuples/sec | -2.6% | -3.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.66 MB/s | 0.677 MB/s | 0.683 MB/s | -2.5% | -3.4% | | bs=1000 sw=10 sl=64 | p50 | 922,891 us | 897,605 us | 924,404 us | +2.8% | -0.2% | | bs=1000 sw=10 sl=64 | p95 | 976,156 us | 1,006,495 us | 967,785 us | -3.0% | +0.9% | | bs=1000 sw=10 sl=64 | p99 | 976,156 us | 1,006,495 us | 995,630 us | -3.0% | -2.0% | </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 0,10,10,64,20,463.04,200,128000,432,0.264,22537.73,31958.89,31958.89 1,100,10,64,20,2204.75,2000,1280000,907,0.554,107263.14,167989.89,167989.89 2,1000,10,64,20,18500.50,20000,12800000,1081,0.660,922890.77,976156.24,976156.24 ``` </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]
