github-actions[bot] commented on PR #8480: URL: https://github.com/apache/texera/pull/8480#issuecomment-5611941232
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `ec3a9dd` 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/34422075407) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 415 | 0.253 | 23,678/32,520/32,520 us | 🔴 +19.5% / 🔴 +100.2% | | 🔴 | bs=100 sw=10 sl=64 | 907 | 0.554 | 108,505/148,575/148,575 us | 🔴 +12.4% / 🔴 +36.7% | | ⚪ | bs=1000 sw=10 sl=64 | 1,080 | 0.659 | 926,324/1,020,690/1,020,690 us | ⚪ within ±5% / 🟢 -7.2% | <details><summary>Baseline details</summary> Latest main `ec3a9dd` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 415 tuples/sec | 448 tuples/sec | 754.83 tuples/sec | -7.4% | -45.0% | | bs=10 sw=10 sl=64 | MB/s | 0.253 MB/s | 0.274 MB/s | 0.461 MB/s | -7.7% | -45.1% | | bs=10 sw=10 sl=64 | p50 | 23,678 us | 19,808 us | 12,950 us | +19.5% | +82.8% | | bs=10 sw=10 sl=64 | p95 | 32,520 us | 39,236 us | 16,243 us | -17.1% | +100.2% | | bs=10 sw=10 sl=64 | p99 | 32,520 us | 39,236 us | 19,574 us | -17.1% | +66.1% | | bs=100 sw=10 sl=64 | throughput | 907 tuples/sec | 947 tuples/sec | 982.46 tuples/sec | -4.2% | -7.7% | | bs=100 sw=10 sl=64 | MB/s | 0.554 MB/s | 0.578 MB/s | 0.6 MB/s | -4.2% | -7.6% | | bs=100 sw=10 sl=64 | p50 | 108,505 us | 104,769 us | 101,575 us | +3.6% | +6.8% | | bs=100 sw=10 sl=64 | p95 | 148,575 us | 132,201 us | 108,655 us | +12.4% | +36.7% | | bs=100 sw=10 sl=64 | p99 | 148,575 us | 132,201 us | 121,794 us | +12.4% | +22.0% | | bs=1000 sw=10 sl=64 | throughput | 1,080 tuples/sec | 1,078 tuples/sec | 1,010 tuples/sec | +0.2% | +7.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.659 MB/s | 0.658 MB/s | 0.616 MB/s | +0.2% | +6.9% | | bs=1000 sw=10 sl=64 | p50 | 926,324 us | 920,971 us | 998,032 us | +0.6% | -7.2% | | bs=1000 sw=10 sl=64 | p95 | 1,020,690 us | 1,027,027 us | 1,039,429 us | -0.6% | -1.8% | | bs=1000 sw=10 sl=64 | p99 | 1,020,690 us | 1,027,027 us | 1,068,120 us | -0.6% | -4.4% | </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 0,10,10,64,20,482.15,200,128000,415,0.253,23678.08,32520.35,32520.35 1,100,10,64,20,2204.20,2000,1280000,907,0.554,108504.78,148575.07,148575.07 2,1000,10,64,20,18510.74,20000,12800000,1080,0.659,926323.67,1020690.43,1020690.43 ``` </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]
