github-actions[bot] commented on PR #8867: URL: https://github.com/apache/texera/pull/8867#issuecomment-6006068466
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 1 worse · ⚪ 12 noise (<±5%) · 0 without baseline > Compared against main `33b47a8` 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/37391744745) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 657 | 0.401 | 14,524/18,886/18,886 us | 🟢 -16.5% / 🔴 +40.1% | | ⚪ | bs=100 sw=10 sl=64 | 1,506 | 0.919 | 62,784/96,001/96,001 us | ⚪ within ±5% / 🟢 -28.6% | | ⚪ | bs=1000 sw=10 sl=64 | 1,866 | 1.139 | 534,837/596,146/596,146 us | ⚪ within ±5% / 🟢 +46.7% | <details><summary>Baseline details</summary> Latest main `33b47a8` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 657 tuples/sec | 654 tuples/sec | 962.17 tuples/sec | +0.5% | -31.7% | | bs=10 sw=10 sl=64 | MB/s | 0.401 MB/s | 0.399 MB/s | 0.587 MB/s | +0.5% | -31.7% | | bs=10 sw=10 sl=64 | p50 | 14,524 us | 13,564 us | 11,046 us | +7.1% | +31.5% | | bs=10 sw=10 sl=64 | p95 | 18,886 us | 22,605 us | 13,484 us | -16.5% | +40.1% | | bs=10 sw=10 sl=64 | p99 | 18,886 us | 22,605 us | 16,626 us | -16.5% | +13.6% | | bs=100 sw=10 sl=64 | throughput | 1,506 tuples/sec | 1,530 tuples/sec | 1,234 tuples/sec | -1.6% | +22.0% | | bs=100 sw=10 sl=64 | MB/s | 0.919 MB/s | 0.934 MB/s | 0.753 MB/s | -1.6% | +22.0% | | bs=100 sw=10 sl=64 | p50 | 62,784 us | 60,649 us | 87,952 us | +3.5% | -28.6% | | bs=100 sw=10 sl=64 | p95 | 96,001 us | 99,521 us | 93,929 us | -3.5% | +2.2% | | bs=100 sw=10 sl=64 | p99 | 96,001 us | 99,521 us | 103,096 us | -3.5% | -6.9% | | bs=1000 sw=10 sl=64 | throughput | 1,866 tuples/sec | 1,901 tuples/sec | 1,272 tuples/sec | -1.8% | +46.7% | | bs=1000 sw=10 sl=64 | MB/s | 1.139 MB/s | 1.161 MB/s | 0.777 MB/s | -1.9% | +46.7% | | bs=1000 sw=10 sl=64 | p50 | 534,837 us | 521,383 us | 862,437 us | +2.6% | -38.0% | | bs=1000 sw=10 sl=64 | p95 | 596,146 us | 622,995 us | 904,996 us | -4.3% | -34.1% | | bs=1000 sw=10 sl=64 | p99 | 596,146 us | 622,995 us | 929,784 us | -4.3% | -35.9% | </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 0,10,10,64,20,304.45,200,128000,657,0.401,14523.56,18885.71,18885.71 1,100,10,64,20,1327.79,2000,1280000,1506,0.919,62783.97,96001.07,96001.07 2,1000,10,64,20,10720.41,20000,12800000,1866,1.139,534837.37,596145.58,596145.58 ``` </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]
