github-actions[bot] commented on PR #6473: URL: https://github.com/apache/texera/pull/6473#issuecomment-4996058860
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 7 better · 🔴 3 worse · ⚪ 5 noise (<±5%) · 0 without baseline > Compared against main `c7473a1` 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/29529973227) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 548 | 0.334 | 17,324/25,014/25,014 us | 🔴 +8.0% / 🔴 +78.2% | | 🟢 | bs=100 sw=10 sl=64 | 1,223 | 0.746 | 81,113/103,901/103,901 us | 🟢 -16.2% / 🟢 -11.3% | | ⚪ | bs=1000 sw=10 sl=64 | 1,434 | 0.875 | 710,283/735,185/735,185 us | ⚪ within ±5% / 🟢 +27.2% | <details><summary>Baseline details</summary> Latest main `c7473a1` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 548 tuples/sec | 579 tuples/sec | 845.85 tuples/sec | -5.4% | -35.2% | | bs=10 sw=10 sl=64 | MB/s | 0.334 MB/s | 0.353 MB/s | 0.516 MB/s | -5.4% | -35.3% | | bs=10 sw=10 sl=64 | p50 | 17,324 us | 16,034 us | 11,663 us | +8.0% | +48.5% | | bs=10 sw=10 sl=64 | p95 | 25,014 us | 26,485 us | 14,037 us | -5.6% | +78.2% | | bs=10 sw=10 sl=64 | p99 | 25,014 us | 26,485 us | 18,666 us | -5.6% | +34.0% | | bs=100 sw=10 sl=64 | throughput | 1,223 tuples/sec | 1,149 tuples/sec | 1,102 tuples/sec | +6.4% | +11.0% | | bs=100 sw=10 sl=64 | MB/s | 0.746 MB/s | 0.701 MB/s | 0.673 MB/s | +6.4% | +10.9% | | bs=100 sw=10 sl=64 | p50 | 81,113 us | 85,459 us | 91,441 us | -5.1% | -11.3% | | bs=100 sw=10 sl=64 | p95 | 103,901 us | 123,978 us | 97,817 us | -16.2% | +6.2% | | bs=100 sw=10 sl=64 | p99 | 103,901 us | 123,978 us | 108,384 us | -16.2% | -4.1% | | bs=1000 sw=10 sl=64 | throughput | 1,434 tuples/sec | 1,401 tuples/sec | 1,128 tuples/sec | +2.4% | +27.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.875 MB/s | 0.855 MB/s | 0.688 MB/s | +2.3% | +27.1% | | bs=1000 sw=10 sl=64 | p50 | 710,283 us | 711,522 us | 901,939 us | -0.2% | -21.2% | | bs=1000 sw=10 sl=64 | p95 | 735,185 us | 751,753 us | 940,934 us | -2.2% | -21.9% | | bs=1000 sw=10 sl=64 | p99 | 735,185 us | 751,753 us | 977,688 us | -2.2% | -24.8% | </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 0,10,10,64,20,365.25,200,128000,548,0.334,17324.46,25014.13,25014.13 1,100,10,64,20,1635.45,2000,1280000,1223,0.746,81112.58,103900.98,103900.98 2,1000,10,64,20,13947.79,20000,12800000,1434,0.875,710283.38,735185.05,735185.05 ``` </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]
