github-actions[bot] commented on PR #6123: URL: https://github.com/apache/texera/pull/6123#issuecomment-4884251071
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `6de8a48` 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/28724129109) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 368 | 0.224 | 26,041/38,465/38,465 us | 🔴 +12.2% / 🔴 +154.0% | | ⚪ | bs=100 sw=10 sl=64 | 789 | 0.481 | 128,112/143,903/143,903 us | ⚪ within ±5% / 🔴 +33.3% | | ⚪ | bs=1000 sw=10 sl=64 | 902 | 0.551 | 1,103,668/1,146,532/1,146,532 us | ⚪ within ±5% / 🔴 +11.5% | <details><summary>Baseline details</summary> Latest main `6de8a48` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 368 tuples/sec | 392 tuples/sec | 776.36 tuples/sec | -6.1% | -52.6% | | bs=10 sw=10 sl=64 | MB/s | 0.224 MB/s | 0.239 MB/s | 0.474 MB/s | -6.3% | -52.7% | | bs=10 sw=10 sl=64 | p50 | 26,041 us | 23,218 us | 12,636 us | +12.2% | +106.1% | | bs=10 sw=10 sl=64 | p95 | 38,465 us | 40,750 us | 15,143 us | -5.6% | +154.0% | | bs=10 sw=10 sl=64 | p99 | 38,465 us | 40,750 us | 18,954 us | -5.6% | +102.9% | | bs=100 sw=10 sl=64 | throughput | 789 tuples/sec | 809 tuples/sec | 985.33 tuples/sec | -2.5% | -19.9% | | bs=100 sw=10 sl=64 | MB/s | 0.481 MB/s | 0.494 MB/s | 0.601 MB/s | -2.6% | -20.0% | | bs=100 sw=10 sl=64 | p50 | 128,112 us | 123,142 us | 101,671 us | +4.0% | +26.0% | | bs=100 sw=10 sl=64 | p95 | 143,903 us | 140,743 us | 107,939 us | +2.2% | +33.3% | | bs=100 sw=10 sl=64 | p99 | 143,903 us | 140,743 us | 113,798 us | +2.2% | +26.5% | | bs=1000 sw=10 sl=64 | throughput | 902 tuples/sec | 913 tuples/sec | 1,016 tuples/sec | -1.2% | -11.3% | | bs=1000 sw=10 sl=64 | MB/s | 0.551 MB/s | 0.557 MB/s | 0.62 MB/s | -1.1% | -11.2% | | bs=1000 sw=10 sl=64 | p50 | 1,103,668 us | 1,098,730 us | 989,693 us | +0.4% | +11.5% | | bs=1000 sw=10 sl=64 | p95 | 1,146,532 us | 1,125,489 us | 1,028,327 us | +1.9% | +11.5% | | bs=1000 sw=10 sl=64 | p99 | 1,146,532 us | 1,125,489 us | 1,059,969 us | +1.9% | +8.2% | </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 0,10,10,64,20,543.92,200,128000,368,0.224,26040.86,38464.75,38464.75 1,100,10,64,20,2535.95,2000,1280000,789,0.481,128111.99,143902.86,143902.86 2,1000,10,64,20,22172.85,20000,12800000,902,0.551,1103667.50,1146532.06,1146532.06 ``` </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]
