github-actions[bot] commented on PR #7318: URL: https://github.com/apache/texera/pull/7318#issuecomment-5186172015
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `25e40ec` 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/30963565917) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 405 | 0.247 | 22,679/32,158/32,158 us | 🔴 -16.6% / 🔴 +107.0% | | 🟢 | bs=100 sw=10 sl=64 | 926 | 0.565 | 107,861/133,768/133,768 us | 🟢 -20.7% / 🔴 +22.6% | | 🔴 | bs=1000 sw=10 sl=64 | 1,069 | 0.653 | 926,313/1,054,643/1,054,643 us | 🔴 +9.8% / 🟢 -7.6% | <details><summary>Baseline details</summary> Latest main `25e40ec` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 405 tuples/sec | 485 tuples/sec | 767.32 tuples/sec | -16.5% | -47.2% | | bs=10 sw=10 sl=64 | MB/s | 0.247 MB/s | 0.296 MB/s | 0.468 MB/s | -16.6% | -47.3% | | bs=10 sw=10 sl=64 | p50 | 22,679 us | 20,422 us | 12,772 us | +11.1% | +77.6% | | bs=10 sw=10 sl=64 | p95 | 32,158 us | 31,009 us | 15,538 us | +3.7% | +107.0% | | bs=10 sw=10 sl=64 | p99 | 32,158 us | 31,009 us | 18,948 us | +3.7% | +69.7% | | bs=100 sw=10 sl=64 | throughput | 926 tuples/sec | 943 tuples/sec | 972.51 tuples/sec | -1.8% | -4.8% | | bs=100 sw=10 sl=64 | MB/s | 0.565 MB/s | 0.576 MB/s | 0.594 MB/s | -1.9% | -4.8% | | bs=100 sw=10 sl=64 | p50 | 107,861 us | 102,766 us | 103,020 us | +5.0% | +4.7% | | bs=100 sw=10 sl=64 | p95 | 133,768 us | 168,760 us | 109,070 us | -20.7% | +22.6% | | bs=100 sw=10 sl=64 | p99 | 133,768 us | 168,760 us | 118,964 us | -20.7% | +12.4% | | bs=1000 sw=10 sl=64 | throughput | 1,069 tuples/sec | 1,103 tuples/sec | 1,005 tuples/sec | -3.1% | +6.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.653 MB/s | 0.673 MB/s | 0.613 MB/s | -3.0% | +6.5% | | bs=1000 sw=10 sl=64 | p50 | 926,313 us | 909,776 us | 1,002,400 us | +1.8% | -7.6% | | bs=1000 sw=10 sl=64 | p95 | 1,054,643 us | 960,561 us | 1,039,228 us | +9.8% | +1.5% | | bs=1000 sw=10 sl=64 | p99 | 1,054,643 us | 960,561 us | 1,069,081 us | +9.8% | -1.4% | </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 0,10,10,64,20,493.26,200,128000,405,0.247,22679.23,32157.85,32157.85 1,100,10,64,20,2160.18,2000,1280000,926,0.565,107860.72,133767.97,133767.97 2,1000,10,64,20,18700.61,20000,12800000,1069,0.653,926312.85,1054642.60,1054642.60 ``` </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]
