github-actions[bot] commented on PR #6852: URL: https://github.com/apache/texera/pull/6852#issuecomment-5064839877
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 1 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `d2ab966` 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/30055702663) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 405 | 0.247 | 24,472/31,576/31,576 us | 🟢 -10.8% / 🔴 +97.2% | | ⚪ | bs=100 sw=10 sl=64 | 801 | 0.489 | 124,034/144,345/144,345 us | ⚪ within ±5% / 🔴 +35.7% | | ⚪ | bs=1000 sw=10 sl=64 | 919 | 0.561 | 1,085,757/1,118,700/1,118,700 us | ⚪ within ±5% / 🔴 +11.6% | <details><summary>Baseline details</summary> Latest main `d2ab966` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 405 tuples/sec | 424 tuples/sec | 767.66 tuples/sec | -4.5% | -47.2% | | bs=10 sw=10 sl=64 | MB/s | 0.247 MB/s | 0.259 MB/s | 0.469 MB/s | -4.6% | -47.3% | | bs=10 sw=10 sl=64 | p50 | 24,472 us | 22,793 us | 12,623 us | +7.4% | +93.9% | | bs=10 sw=10 sl=64 | p95 | 31,576 us | 35,402 us | 16,011 us | -10.8% | +97.2% | | bs=10 sw=10 sl=64 | p99 | 31,576 us | 35,402 us | 18,856 us | -10.8% | +67.5% | | bs=100 sw=10 sl=64 | throughput | 801 tuples/sec | 823 tuples/sec | 998.44 tuples/sec | -2.7% | -19.8% | | bs=100 sw=10 sl=64 | MB/s | 0.489 MB/s | 0.502 MB/s | 0.609 MB/s | -2.6% | -19.8% | | bs=100 sw=10 sl=64 | p50 | 124,034 us | 123,111 us | 100,463 us | +0.7% | +23.5% | | bs=100 sw=10 sl=64 | p95 | 144,345 us | 145,784 us | 106,400 us | -1.0% | +35.7% | | bs=100 sw=10 sl=64 | p99 | 144,345 us | 145,784 us | 117,712 us | -1.0% | +22.6% | | bs=1000 sw=10 sl=64 | throughput | 919 tuples/sec | 924 tuples/sec | 1,034 tuples/sec | -0.5% | -11.1% | | bs=1000 sw=10 sl=64 | MB/s | 0.561 MB/s | 0.564 MB/s | 0.631 MB/s | -0.5% | -11.1% | | bs=1000 sw=10 sl=64 | p50 | 1,085,757 us | 1,087,098 us | 973,294 us | -0.1% | +11.6% | | bs=1000 sw=10 sl=64 | p95 | 1,118,700 us | 1,126,941 us | 1,019,213 us | -0.7% | +9.8% | | bs=1000 sw=10 sl=64 | p99 | 1,118,700 us | 1,126,941 us | 1,049,896 us | -0.7% | +6.6% | </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 0,10,10,64,20,493.77,200,128000,405,0.247,24472.31,31576.05,31576.05 1,100,10,64,20,2498.20,2000,1280000,801,0.489,124033.50,144345.00,144345.00 2,1000,10,64,20,21767.22,20000,12800000,919,0.561,1085756.67,1118700.26,1118700.26 ``` </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]
