github-actions[bot] commented on PR #8940: URL: https://github.com/apache/texera/pull/8940#issuecomment-6076059084
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 6 better · 🔴 2 worse · ⚪ 7 noise (<±5%) · 0 without baseline > Compared against main `be65bf8` 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/37895563183) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 528 | 0.322 | 17,958/23,092/23,092 us | 🟢 -41.4% / 🔴 +70.6% | | 🟢 | bs=100 sw=10 sl=64 | 1,050 | 0.641 | 92,795/121,571/121,571 us | 🟢 -20.9% / 🔴 +30.3% | | 🔴 | bs=1000 sw=10 sl=64 | 1,273 | 0.777 | 778,822/872,697/872,697 us | 🔴 +5.9% / 🟢 -8.8% | <details><summary>Baseline details</summary> Latest main `be65bf8` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 528 tuples/sec | 523 tuples/sec | 983 tuples/sec | +1.0% | -46.3% | | bs=10 sw=10 sl=64 | MB/s | 0.322 MB/s | 0.319 MB/s | 0.6 MB/s | +0.9% | -46.3% | | bs=10 sw=10 sl=64 | p50 | 17,958 us | 17,588 us | 10,903 us | +2.1% | +64.7% | | bs=10 sw=10 sl=64 | p95 | 23,092 us | 39,436 us | 13,539 us | -41.4% | +70.6% | | bs=10 sw=10 sl=64 | p99 | 23,092 us | 39,436 us | 16,174 us | -41.4% | +42.8% | | bs=100 sw=10 sl=64 | throughput | 1,050 tuples/sec | 995 tuples/sec | 1,259 tuples/sec | +5.5% | -16.6% | | bs=100 sw=10 sl=64 | MB/s | 0.641 MB/s | 0.607 MB/s | 0.769 MB/s | +5.6% | -16.6% | | bs=100 sw=10 sl=64 | p50 | 92,795 us | 94,536 us | 86,981 us | -1.8% | +6.7% | | bs=100 sw=10 sl=64 | p95 | 121,571 us | 153,727 us | 93,289 us | -20.9% | +30.3% | | bs=100 sw=10 sl=64 | p99 | 121,571 us | 153,727 us | 105,695 us | -20.9% | +15.0% | | bs=1000 sw=10 sl=64 | throughput | 1,273 tuples/sec | 1,283 tuples/sec | 1,300 tuples/sec | -0.8% | -2.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.777 MB/s | 0.783 MB/s | 0.793 MB/s | -0.8% | -2.0% | | bs=1000 sw=10 sl=64 | p50 | 778,822 us | 777,006 us | 854,105 us | +0.2% | -8.8% | | bs=1000 sw=10 sl=64 | p95 | 872,697 us | 824,119 us | 901,686 us | +5.9% | -3.2% | | bs=1000 sw=10 sl=64 | p99 | 872,697 us | 824,119 us | 924,532 us | +5.9% | -5.6% | </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 0,10,10,64,20,378.66,200,128000,528,0.322,17957.96,23091.98,23091.98 1,100,10,64,20,1904.02,2000,1280000,1050,0.641,92794.73,121571.28,121571.28 2,1000,10,64,20,15708.88,20000,12800000,1273,0.777,778822.01,872696.69,872696.69 ``` </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]
