github-actions[bot] commented on PR #8877: URL: https://github.com/apache/texera/pull/8877#issuecomment-6012173866
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 5 better · 🔴 7 worse · ⚪ 3 noise (<±5%) · 0 without baseline > Compared against main `b43d465` 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/37433907747) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🟢 | bs=10 sw=10 sl=64 | 475 | 0.29 | 19,483/27,765/27,765 us | 🟢 -18.4% / 🔴 +105.9% | | 🔴 | bs=100 sw=10 sl=64 | 949 | 0.579 | 104,732/160,020/160,020 us | 🔴 +21.4% / 🔴 +70.4% | | 🔴 | bs=1000 sw=10 sl=64 | 1,134 | 0.692 | 876,289/1,001,636/1,001,636 us | 🔴 +7.6% / 🔴 -10.9% | <details><summary>Baseline details</summary> Latest main `b43d465` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 475 tuples/sec | 441 tuples/sec | 962.17 tuples/sec | +7.7% | -50.6% | | bs=10 sw=10 sl=64 | MB/s | 0.29 MB/s | 0.269 MB/s | 0.587 MB/s | +7.8% | -50.6% | | bs=10 sw=10 sl=64 | p50 | 19,483 us | 23,865 us | 11,046 us | -18.4% | +76.4% | | bs=10 sw=10 sl=64 | p95 | 27,765 us | 30,887 us | 13,484 us | -10.1% | +105.9% | | bs=10 sw=10 sl=64 | p99 | 27,765 us | 30,887 us | 16,626 us | -10.1% | +67.0% | | bs=100 sw=10 sl=64 | throughput | 949 tuples/sec | 1,015 tuples/sec | 1,234 tuples/sec | -6.5% | -23.1% | | bs=100 sw=10 sl=64 | MB/s | 0.579 MB/s | 0.619 MB/s | 0.753 MB/s | -6.5% | -23.1% | | bs=100 sw=10 sl=64 | p50 | 104,732 us | 95,321 us | 87,952 us | +9.9% | +19.1% | | bs=100 sw=10 sl=64 | p95 | 160,020 us | 131,824 us | 93,929 us | +21.4% | +70.4% | | bs=100 sw=10 sl=64 | p99 | 160,020 us | 131,824 us | 103,096 us | +21.4% | +55.2% | | bs=1000 sw=10 sl=64 | throughput | 1,134 tuples/sec | 1,147 tuples/sec | 1,272 tuples/sec | -1.1% | -10.9% | | bs=1000 sw=10 sl=64 | MB/s | 0.692 MB/s | 0.7 MB/s | 0.777 MB/s | -1.1% | -10.9% | | bs=1000 sw=10 sl=64 | p50 | 876,289 us | 867,904 us | 862,437 us | +1.0% | +1.6% | | bs=1000 sw=10 sl=64 | p95 | 1,001,636 us | 931,289 us | 904,996 us | +7.6% | +10.7% | | bs=1000 sw=10 sl=64 | p99 | 1,001,636 us | 931,289 us | 929,784 us | +7.6% | +7.7% | </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 0,10,10,64,20,420.79,200,128000,475,0.290,19483.23,27764.66,27764.66 1,100,10,64,20,2108.50,2000,1280000,949,0.579,104731.90,160020.13,160020.13 2,1000,10,64,20,17635.91,20000,12800000,1134,0.692,876289.06,1001635.93,1001635.93 ``` </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]
