github-actions[bot] commented on PR #7664: URL: https://github.com/apache/texera/pull/7664#issuecomment-5297022597
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 1 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `3cb3479` 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/31830310073) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 485 | 0.296 | 20,205/27,850/27,850 us | 🟢 -14.0% / 🔴 +70.4% | | ⚪ | bs=100 sw=10 sl=64 | 1,009 | 0.616 | 96,051/123,200/123,200 us | ⚪ within ±5% / 🔴 +15.7% | | ⚪ | bs=1000 sw=10 sl=64 | 1,199 | 0.732 | 833,232/890,224/890,224 us | ⚪ within ±5% / 🟢 -15.5% | <details><summary>Baseline details</summary> Latest main `3cb3479` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 485 tuples/sec | 500 tuples/sec | 779.28 tuples/sec | -3.0% | -37.8% | | bs=10 sw=10 sl=64 | MB/s | 0.296 MB/s | 0.305 MB/s | 0.476 MB/s | -3.0% | -37.8% | | bs=10 sw=10 sl=64 | p50 | 20,205 us | 17,880 us | 12,712 us | +13.0% | +58.9% | | bs=10 sw=10 sl=64 | p95 | 27,850 us | 32,372 us | 16,345 us | -14.0% | +70.4% | | bs=10 sw=10 sl=64 | p99 | 27,850 us | 32,372 us | 19,050 us | -14.0% | +46.2% | | bs=100 sw=10 sl=64 | throughput | 1,009 tuples/sec | 1,054 tuples/sec | 1,017 tuples/sec | -4.3% | -0.8% | | bs=100 sw=10 sl=64 | MB/s | 0.616 MB/s | 0.643 MB/s | 0.621 MB/s | -4.2% | -0.8% | | bs=100 sw=10 sl=64 | p50 | 96,051 us | 93,009 us | 100,048 us | +3.3% | -4.0% | | bs=100 sw=10 sl=64 | p95 | 123,200 us | 122,094 us | 106,477 us | +0.9% | +15.7% | | bs=100 sw=10 sl=64 | p99 | 123,200 us | 122,094 us | 114,739 us | +0.9% | +7.4% | | bs=1000 sw=10 sl=64 | throughput | 1,199 tuples/sec | 1,204 tuples/sec | 1,048 tuples/sec | -0.4% | +14.5% | | bs=1000 sw=10 sl=64 | MB/s | 0.732 MB/s | 0.735 MB/s | 0.639 MB/s | -0.4% | +14.5% | | bs=1000 sw=10 sl=64 | p50 | 833,232 us | 830,224 us | 976,350 us | +0.4% | -14.7% | | bs=1000 sw=10 sl=64 | p95 | 890,224 us | 880,839 us | 1,022,084 us | +1.1% | -12.9% | | bs=1000 sw=10 sl=64 | p99 | 890,224 us | 880,839 us | 1,053,520 us | +1.1% | -15.5% | </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 0,10,10,64,20,412.56,200,128000,485,0.296,20205.05,27849.77,27849.77 1,100,10,64,20,1981.65,2000,1280000,1009,0.616,96051.05,123199.84,123199.84 2,1000,10,64,20,16680.40,20000,12800000,1199,0.732,833231.79,890223.99,890223.99 ``` </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]
