github-actions[bot] commented on PR #8786: URL: https://github.com/apache/texera/pull/8786#issuecomment-5920164436
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `98d3d4b` 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/36777618409) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 318 | 0.194 | 31,117/39,897/39,897 us | 🔴 +21.6% / 🔴 +152.7% | | 🟢 | bs=100 sw=10 sl=64 | 758 | 0.463 | 128,746/154,582/154,582 us | 🟢 -5.6% / 🔴 +45.6% | | ⚪ | bs=1000 sw=10 sl=64 | 857 | 0.523 | 1,165,038/1,237,413/1,237,413 us | ⚪ within ±5% / 🔴 +22.3% | <details><summary>Baseline details</summary> Latest main `98d3d4b` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 318 tuples/sec | 375 tuples/sec | 818.62 tuples/sec | -15.2% | -61.2% | | bs=10 sw=10 sl=64 | MB/s | 0.194 MB/s | 0.229 MB/s | 0.5 MB/s | -15.3% | -61.2% | | bs=10 sw=10 sl=64 | p50 | 31,117 us | 25,599 us | 12,404 us | +21.6% | +150.9% | | bs=10 sw=10 sl=64 | p95 | 39,897 us | 41,224 us | 15,787 us | -3.2% | +152.7% | | bs=10 sw=10 sl=64 | p99 | 39,897 us | 41,224 us | 18,928 us | -3.2% | +110.8% | | bs=100 sw=10 sl=64 | throughput | 758 tuples/sec | 745 tuples/sec | 1,058 tuples/sec | +1.7% | -28.4% | | bs=100 sw=10 sl=64 | MB/s | 0.463 MB/s | 0.454 MB/s | 0.646 MB/s | +2.0% | -28.3% | | bs=100 sw=10 sl=64 | p50 | 128,746 us | 129,059 us | 99,149 us | -0.2% | +29.9% | | bs=100 sw=10 sl=64 | p95 | 154,582 us | 163,715 us | 106,165 us | -5.6% | +45.6% | | bs=100 sw=10 sl=64 | p99 | 154,582 us | 163,715 us | 114,997 us | -5.6% | +34.4% | | bs=1000 sw=10 sl=64 | throughput | 857 tuples/sec | 875 tuples/sec | 1,088 tuples/sec | -2.1% | -21.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.523 MB/s | 0.534 MB/s | 0.664 MB/s | -2.1% | -21.2% | | bs=1000 sw=10 sl=64 | p50 | 1,165,038 us | 1,143,369 us | 971,066 us | +1.9% | +20.0% | | bs=1000 sw=10 sl=64 | p95 | 1,237,413 us | 1,200,662 us | 1,011,680 us | +3.1% | +22.3% | | bs=1000 sw=10 sl=64 | p99 | 1,237,413 us | 1,200,662 us | 1,037,719 us | +3.1% | +19.2% | </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 0,10,10,64,20,628.63,200,128000,318,0.194,31116.63,39897.48,39897.48 1,100,10,64,20,2638.30,2000,1280000,758,0.463,128746.05,154581.50,154581.50 2,1000,10,64,20,23341.54,20000,12800000,857,0.523,1165038.26,1237413.28,1237413.28 ``` </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]
