github-actions[bot] commented on PR #6165: URL: https://github.com/apache/texera/pull/6165#issuecomment-4885709399
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 5 better · 🔴 5 worse · ⚪ 5 noise (<±5%) · 0 without baseline > Compared against main `6fdfe19` 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/28737881929) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 384 | 0.234 | 22,558/48,737/48,737 us | 🔴 +48.2% / 🔴 +221.8% | | 🟢 | bs=100 sw=10 sl=64 | 940 | 0.574 | 106,329/128,121/128,121 us | 🟢 -20.9% / 🔴 +18.7% | | ⚪ | bs=1000 sw=10 sl=64 | 1,092 | 0.667 | 918,770/975,036/975,036 us | ⚪ within ±5% / 🟢 -8.0% | <details><summary>Baseline details</summary> Latest main `6fdfe19` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 384 tuples/sec | 462 tuples/sec | 776.36 tuples/sec | -16.9% | -50.5% | | bs=10 sw=10 sl=64 | MB/s | 0.234 MB/s | 0.282 MB/s | 0.474 MB/s | -17.0% | -50.6% | | bs=10 sw=10 sl=64 | p50 | 22,558 us | 19,154 us | 12,636 us | +17.8% | +78.5% | | bs=10 sw=10 sl=64 | p95 | 48,737 us | 32,886 us | 15,143 us | +48.2% | +221.8% | | bs=10 sw=10 sl=64 | p99 | 48,737 us | 32,886 us | 18,954 us | +48.2% | +157.1% | | bs=100 sw=10 sl=64 | throughput | 940 tuples/sec | 884 tuples/sec | 985.33 tuples/sec | +6.3% | -4.6% | | bs=100 sw=10 sl=64 | MB/s | 0.574 MB/s | 0.539 MB/s | 0.601 MB/s | +6.5% | -4.6% | | bs=100 sw=10 sl=64 | p50 | 106,329 us | 112,863 us | 101,671 us | -5.8% | +4.6% | | bs=100 sw=10 sl=64 | p95 | 128,121 us | 161,943 us | 107,939 us | -20.9% | +18.7% | | bs=100 sw=10 sl=64 | p99 | 128,121 us | 161,943 us | 113,798 us | -20.9% | +12.6% | | bs=1000 sw=10 sl=64 | throughput | 1,092 tuples/sec | 1,092 tuples/sec | 1,016 tuples/sec | 0.0% | +7.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.667 MB/s | 0.666 MB/s | 0.62 MB/s | +0.2% | +7.5% | | bs=1000 sw=10 sl=64 | p50 | 918,770 us | 924,763 us | 989,693 us | -0.6% | -7.2% | | bs=1000 sw=10 sl=64 | p95 | 975,036 us | 952,495 us | 1,028,327 us | +2.4% | -5.2% | | bs=1000 sw=10 sl=64 | p99 | 975,036 us | 952,495 us | 1,059,969 us | +2.4% | -8.0% | </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 0,10,10,64,20,520.88,200,128000,384,0.234,22557.92,48736.61,48736.61 1,100,10,64,20,2126.79,2000,1280000,940,0.574,106329.31,128121.43,128121.43 2,1000,10,64,20,18310.43,20000,12800000,1092,0.667,918770.22,975036.46,975036.46 ``` </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]
