github-actions[bot] commented on PR #6049: URL: https://github.com/apache/texera/pull/6049#issuecomment-4860101050
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `a1a7eb0` 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/28547959511) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 382 | 0.233 | 26,293/33,560/33,560 us | 🔴 -7.5% / 🔴 +127.0% | | ⚪ | bs=100 sw=10 sl=64 | 836 | 0.51 | 117,163/141,794/141,794 us | ⚪ within ±5% / 🔴 +32.6% | | ⚪ | bs=1000 sw=10 sl=64 | 950 | 0.58 | 1,056,913/1,092,430/1,092,430 us | ⚪ within ±5% / 🔴 +7.4% | <details><summary>Baseline details</summary> Latest main `a1a7eb0` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 382 tuples/sec | 413 tuples/sec | 786.27 tuples/sec | -7.5% | -51.4% | | bs=10 sw=10 sl=64 | MB/s | 0.233 MB/s | 0.252 MB/s | 0.48 MB/s | -7.5% | -51.4% | | bs=10 sw=10 sl=64 | p50 | 26,293 us | 24,980 us | 12,495 us | +5.3% | +110.4% | | bs=10 sw=10 sl=64 | p95 | 33,560 us | 35,419 us | 14,784 us | -5.2% | +127.0% | | bs=10 sw=10 sl=64 | p99 | 33,560 us | 35,419 us | 18,468 us | -5.2% | +81.7% | | bs=100 sw=10 sl=64 | throughput | 836 tuples/sec | 819 tuples/sec | 991.49 tuples/sec | +2.1% | -15.7% | | bs=100 sw=10 sl=64 | MB/s | 0.51 MB/s | 0.5 MB/s | 0.605 MB/s | +2.0% | -15.7% | | bs=100 sw=10 sl=64 | p50 | 117,163 us | 118,828 us | 100,929 us | -1.4% | +16.1% | | bs=100 sw=10 sl=64 | p95 | 141,794 us | 144,593 us | 106,894 us | -1.9% | +32.6% | | bs=100 sw=10 sl=64 | p99 | 141,794 us | 144,593 us | 114,085 us | -1.9% | +24.3% | | bs=1000 sw=10 sl=64 | throughput | 950 tuples/sec | 941 tuples/sec | 1,023 tuples/sec | +1.0% | -7.1% | | bs=1000 sw=10 sl=64 | MB/s | 0.58 MB/s | 0.574 MB/s | 0.624 MB/s | +1.0% | -7.1% | | bs=1000 sw=10 sl=64 | p50 | 1,056,913 us | 1,059,164 us | 983,835 us | -0.2% | +7.4% | | bs=1000 sw=10 sl=64 | p95 | 1,092,430 us | 1,094,588 us | 1,023,777 us | -0.2% | +6.7% | | bs=1000 sw=10 sl=64 | p99 | 1,092,430 us | 1,094,588 us | 1,053,883 us | -0.2% | +3.7% | </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 0,10,10,64,20,523.48,200,128000,382,0.233,26292.81,33559.97,33559.97 1,100,10,64,20,2391.38,2000,1280000,836,0.510,117162.59,141793.86,141793.86 2,1000,10,64,20,21059.10,20000,12800000,950,0.580,1056912.55,1092430.40,1092430.40 ``` </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]
