github-actions[bot] commented on PR #7976: URL: https://github.com/apache/texera/pull/7976#issuecomment-5416168526
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 2 worse · ⚪ 11 noise (<±5%) · 0 without baseline > Compared against main `2c2c0e5` 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/32893532547) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 429 | 0.262 | 22,043/32,602/32,602 us | 🟢 -9.1% / 🔴 +139.7% | | 🔴 | bs=100 sw=10 sl=64 | 823 | 0.502 | 119,029/148,347/148,347 us | 🔴 +14.1% / 🔴 +62.0% | | ⚪ | bs=1000 sw=10 sl=64 | 919 | 0.561 | 1,087,059/1,174,069/1,174,069 us | ⚪ within ±5% / 🔴 +33.3% | <details><summary>Baseline details</summary> Latest main `2c2c0e5` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 429 tuples/sec | 430 tuples/sec | 908.02 tuples/sec | -0.2% | -52.8% | | bs=10 sw=10 sl=64 | MB/s | 0.262 MB/s | 0.263 MB/s | 0.554 MB/s | -0.4% | -52.7% | | bs=10 sw=10 sl=64 | p50 | 22,043 us | 22,399 us | 10,907 us | -1.6% | +102.1% | | bs=10 sw=10 sl=64 | p95 | 32,602 us | 35,850 us | 13,604 us | -9.1% | +139.7% | | bs=10 sw=10 sl=64 | p99 | 32,602 us | 35,850 us | 16,697 us | -9.1% | +95.3% | | bs=100 sw=10 sl=64 | throughput | 823 tuples/sec | 847 tuples/sec | 1,188 tuples/sec | -2.8% | -30.7% | | bs=100 sw=10 sl=64 | MB/s | 0.502 MB/s | 0.517 MB/s | 0.725 MB/s | -2.9% | -30.7% | | bs=100 sw=10 sl=64 | p50 | 119,029 us | 117,200 us | 85,003 us | +1.6% | +40.0% | | bs=100 sw=10 sl=64 | p95 | 148,347 us | 130,071 us | 91,599 us | +14.1% | +62.0% | | bs=100 sw=10 sl=64 | p99 | 148,347 us | 130,071 us | 99,202 us | +14.1% | +49.5% | | bs=1000 sw=10 sl=64 | throughput | 919 tuples/sec | 909 tuples/sec | 1,221 tuples/sec | +1.1% | -24.8% | | bs=1000 sw=10 sl=64 | MB/s | 0.561 MB/s | 0.555 MB/s | 0.745 MB/s | +1.1% | -24.7% | | bs=1000 sw=10 sl=64 | p50 | 1,087,059 us | 1,103,738 us | 837,593 us | -1.5% | +29.8% | | bs=1000 sw=10 sl=64 | p95 | 1,174,069 us | 1,160,079 us | 881,015 us | +1.2% | +33.3% | | bs=1000 sw=10 sl=64 | p99 | 1,174,069 us | 1,160,079 us | 915,550 us | +1.2% | +28.2% | </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 0,10,10,64,20,466.63,200,128000,429,0.262,22042.54,32602.04,32602.04 1,100,10,64,20,2430.95,2000,1280000,823,0.502,119028.51,148346.54,148346.54 2,1000,10,64,20,21773.46,20000,12800000,919,0.561,1087059.33,1174069.23,1174069.23 ``` </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]
