github-actions[bot] commented on PR #5946: URL: https://github.com/apache/texera/pull/5946#issuecomment-4796915779
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 2 worse · ⚪ 11 noise (<±5%) · 0 without baseline > Compared against main `43ca4b2` 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/28154080292) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 391 | 0.238 | 24,251/37,667/37,667 us | 🔴 +6.9% / 🔴 +151.8% | | 🟢 | bs=100 sw=10 sl=64 | 806 | 0.492 | 122,402/149,603/149,603 us | 🟢 -6.5% / 🔴 +49.3% | | ⚪ | bs=1000 sw=10 sl=64 | 918 | 0.561 | 1,090,203/1,115,842/1,115,842 us | ⚪ within ±5% / 🔴 +21.2% | <details><summary>Baseline details</summary> Latest main `43ca4b2` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 391 tuples/sec | 389 tuples/sec | 799.7 tuples/sec | +0.5% | -51.1% | | bs=10 sw=10 sl=64 | MB/s | 0.238 MB/s | 0.237 MB/s | 0.488 MB/s | +0.4% | -51.2% | | bs=10 sw=10 sl=64 | p50 | 24,251 us | 24,787 us | 12,125 us | -2.2% | +100.0% | | bs=10 sw=10 sl=64 | p95 | 37,667 us | 35,243 us | 14,959 us | +6.9% | +151.8% | | bs=10 sw=10 sl=64 | p99 | 37,667 us | 35,243 us | 18,503 us | +6.9% | +103.6% | | bs=100 sw=10 sl=64 | throughput | 806 tuples/sec | 790 tuples/sec | 1,069 tuples/sec | +2.0% | -24.6% | | bs=100 sw=10 sl=64 | MB/s | 0.492 MB/s | 0.482 MB/s | 0.652 MB/s | +2.1% | -24.6% | | bs=100 sw=10 sl=64 | p50 | 122,402 us | 121,955 us | 92,709 us | +0.4% | +32.0% | | bs=100 sw=10 sl=64 | p95 | 149,603 us | 159,987 us | 100,227 us | -6.5% | +49.3% | | bs=100 sw=10 sl=64 | p99 | 149,603 us | 159,987 us | 109,877 us | -6.5% | +36.2% | | bs=1000 sw=10 sl=64 | throughput | 918 tuples/sec | 912 tuples/sec | 1,114 tuples/sec | +0.7% | -17.6% | | bs=1000 sw=10 sl=64 | MB/s | 0.561 MB/s | 0.557 MB/s | 0.68 MB/s | +0.7% | -17.5% | | bs=1000 sw=10 sl=64 | p50 | 1,090,203 us | 1,097,482 us | 899,197 us | -0.7% | +21.2% | | bs=1000 sw=10 sl=64 | p95 | 1,115,842 us | 1,148,617 us | 945,162 us | -2.9% | +18.1% | | bs=1000 sw=10 sl=64 | p99 | 1,115,842 us | 1,148,617 us | 986,231 us | -2.9% | +13.1% | </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 0,10,10,64,20,511.84,200,128000,391,0.238,24250.70,37667.20,37667.20 1,100,10,64,20,2480.95,2000,1280000,806,0.492,122401.70,149603.32,149603.32 2,1000,10,64,20,21778.61,20000,12800000,918,0.561,1090202.69,1115841.83,1115841.83 ``` </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]
