github-actions[bot] commented on PR #6909: URL: https://github.com/apache/texera/pull/6909#issuecomment-5085313567
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 4 better · 🔴 2 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `f521750` 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/30219268879) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | ⚪ | bs=10 sw=10 sl=64 | 398 | 0.243 | 23,379/33,959/33,959 us | ⚪ within ±5% / 🔴 +107.4% | | 🟢 | bs=100 sw=10 sl=64 | 981 | 0.598 | 102,754/120,513/120,513 us | 🟢 -14.9% / 🔴 +10.3% | | 🔴 | bs=1000 sw=10 sl=64 | 1,086 | 0.663 | 920,371/1,030,863/1,030,863 us | 🔴 +8.8% / 🟢 +8.8% | <details><summary>Baseline details</summary> Latest main `f521750` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 398 tuples/sec | 403 tuples/sec | 759.72 tuples/sec | -1.2% | -47.6% | | bs=10 sw=10 sl=64 | MB/s | 0.243 MB/s | 0.246 MB/s | 0.464 MB/s | -1.2% | -47.6% | | bs=10 sw=10 sl=64 | p50 | 23,379 us | 23,972 us | 12,653 us | -2.5% | +84.8% | | bs=10 sw=10 sl=64 | p95 | 33,959 us | 33,922 us | 16,371 us | +0.1% | +107.4% | | bs=10 sw=10 sl=64 | p99 | 33,959 us | 33,922 us | 19,941 us | +0.1% | +70.3% | | bs=100 sw=10 sl=64 | throughput | 981 tuples/sec | 924 tuples/sec | 966.78 tuples/sec | +6.2% | +1.5% | | bs=100 sw=10 sl=64 | MB/s | 0.598 MB/s | 0.564 MB/s | 0.59 MB/s | +6.0% | +1.3% | | bs=100 sw=10 sl=64 | p50 | 102,754 us | 103,223 us | 103,654 us | -0.5% | -0.9% | | bs=100 sw=10 sl=64 | p95 | 120,513 us | 141,644 us | 109,308 us | -14.9% | +10.3% | | bs=100 sw=10 sl=64 | p99 | 120,513 us | 141,644 us | 116,369 us | -14.9% | +3.6% | | bs=1000 sw=10 sl=64 | throughput | 1,086 tuples/sec | 1,107 tuples/sec | 997.95 tuples/sec | -1.9% | +8.8% | | bs=1000 sw=10 sl=64 | MB/s | 0.663 MB/s | 0.675 MB/s | 0.609 MB/s | -1.8% | +8.8% | | bs=1000 sw=10 sl=64 | p50 | 920,371 us | 909,492 us | 1,007,348 us | +1.2% | -8.6% | | bs=1000 sw=10 sl=64 | p95 | 1,030,863 us | 947,793 us | 1,050,149 us | +8.8% | -1.8% | | bs=1000 sw=10 sl=64 | p99 | 1,030,863 us | 947,793 us | 1,079,497 us | +8.8% | -4.5% | </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 0,10,10,64,20,502.05,200,128000,398,0.243,23378.76,33958.50,33958.50 1,100,10,64,20,2039.67,2000,1280000,981,0.598,102753.62,120513.14,120513.14 2,1000,10,64,20,18422.29,20000,12800000,1086,0.663,920371.04,1030863.11,1030863.11 ``` </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]
