github-actions[bot] commented on PR #8483: URL: https://github.com/apache/texera/pull/8483#issuecomment-5613526540
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 7 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `ded7ba1` 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/34438425500) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 640 | 0.39 | 15,210/22,749/22,749 us | 🔴 +16.0% / 🔴 +40.1% | | 🔴 | bs=100 sw=10 sl=64 | 1,301 | 0.794 | 73,832/110,776/110,776 us | 🔴 +10.7% / 🟢 +32.4% | | ⚪ | bs=1000 sw=10 sl=64 | 1,519 | 0.927 | 658,956/697,936/697,936 us | ⚪ within ±5% / 🟢 +50.4% | <details><summary>Baseline details</summary> Latest main `ded7ba1` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 640 tuples/sec | 740 tuples/sec | 754.83 tuples/sec | -13.5% | -15.2% | | bs=10 sw=10 sl=64 | MB/s | 0.39 MB/s | 0.452 MB/s | 0.461 MB/s | -13.7% | -15.3% | | bs=10 sw=10 sl=64 | p50 | 15,210 us | 13,116 us | 12,950 us | +16.0% | +17.5% | | bs=10 sw=10 sl=64 | p95 | 22,749 us | 20,022 us | 16,243 us | +13.6% | +40.1% | | bs=10 sw=10 sl=64 | p99 | 22,749 us | 20,022 us | 19,574 us | +13.6% | +16.2% | | bs=100 sw=10 sl=64 | throughput | 1,301 tuples/sec | 1,299 tuples/sec | 982.46 tuples/sec | +0.2% | +32.4% | | bs=100 sw=10 sl=64 | MB/s | 0.794 MB/s | 0.793 MB/s | 0.6 MB/s | +0.1% | +32.4% | | bs=100 sw=10 sl=64 | p50 | 73,832 us | 76,517 us | 101,575 us | -3.5% | -27.3% | | bs=100 sw=10 sl=64 | p95 | 110,776 us | 100,086 us | 108,655 us | +10.7% | +2.0% | | bs=100 sw=10 sl=64 | p99 | 110,776 us | 100,086 us | 121,794 us | +10.7% | -9.0% | | bs=1000 sw=10 sl=64 | throughput | 1,519 tuples/sec | 1,514 tuples/sec | 1,010 tuples/sec | +0.3% | +50.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.927 MB/s | 0.924 MB/s | 0.616 MB/s | +0.3% | +50.4% | | bs=1000 sw=10 sl=64 | p50 | 658,956 us | 655,367 us | 998,032 us | +0.5% | -34.0% | | bs=1000 sw=10 sl=64 | p95 | 697,936 us | 715,441 us | 1,039,429 us | -2.4% | -32.9% | | bs=1000 sw=10 sl=64 | p99 | 697,936 us | 715,441 us | 1,068,120 us | -2.4% | -34.7% | </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 0,10,10,64,20,312.74,200,128000,640,0.390,15209.79,22748.88,22748.88 1,100,10,64,20,1536.85,2000,1280000,1301,0.794,73831.64,110776.04,110776.04 2,1000,10,64,20,13163.32,20000,12800000,1519,0.927,658956.42,697936.46,697936.46 ``` </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]
