github-actions[bot] commented on PR #6833: URL: https://github.com/apache/texera/pull/6833#issuecomment-5057359291
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `0ba5d1a` 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/29998491963) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 434 | 0.265 | 22,816/28,699/28,699 us | 🟢 -17.9% / 🔴 +78.5% | | 🔴 | bs=100 sw=10 sl=64 | 924 | 0.564 | 105,233/156,049/156,049 us | 🔴 +19.2% / 🔴 +45.3% | | ⚪ | bs=1000 sw=10 sl=64 | 1,101 | 0.672 | 914,839/958,871/958,871 us | ⚪ within ±5% / 🟢 -9.2% | <details><summary>Baseline details</summary> Latest main `0ba5d1a` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 434 tuples/sec | 418 tuples/sec | 760.2 tuples/sec | +3.8% | -42.9% | | bs=10 sw=10 sl=64 | MB/s | 0.265 MB/s | 0.255 MB/s | 0.464 MB/s | +3.9% | -42.9% | | bs=10 sw=10 sl=64 | p50 | 22,816 us | 20,344 us | 12,781 us | +12.2% | +78.5% | | bs=10 sw=10 sl=64 | p95 | 28,699 us | 34,938 us | 16,118 us | -17.9% | +78.1% | | bs=10 sw=10 sl=64 | p99 | 28,699 us | 34,938 us | 19,074 us | -17.9% | +50.5% | | bs=100 sw=10 sl=64 | throughput | 924 tuples/sec | 963 tuples/sec | 988.68 tuples/sec | -4.0% | -6.5% | | bs=100 sw=10 sl=64 | MB/s | 0.564 MB/s | 0.588 MB/s | 0.603 MB/s | -4.1% | -6.5% | | bs=100 sw=10 sl=64 | p50 | 105,233 us | 102,314 us | 101,448 us | +2.9% | +3.7% | | bs=100 sw=10 sl=64 | p95 | 156,049 us | 130,861 us | 107,410 us | +19.2% | +45.3% | | bs=100 sw=10 sl=64 | p99 | 156,049 us | 130,861 us | 120,258 us | +19.2% | +29.8% | | bs=1000 sw=10 sl=64 | throughput | 1,101 tuples/sec | 1,082 tuples/sec | 1,023 tuples/sec | +1.8% | +7.6% | | bs=1000 sw=10 sl=64 | MB/s | 0.672 MB/s | 0.66 MB/s | 0.624 MB/s | +1.8% | +7.6% | | bs=1000 sw=10 sl=64 | p50 | 914,839 us | 926,537 us | 983,888 us | -1.3% | -7.0% | | bs=1000 sw=10 sl=64 | p95 | 958,871 us | 978,638 us | 1,030,100 us | -2.0% | -6.9% | | bs=1000 sw=10 sl=64 | p99 | 958,871 us | 978,638 us | 1,056,513 us | -2.0% | -9.2% | </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 0,10,10,64,20,460.91,200,128000,434,0.265,22816.13,28698.68,28698.68 1,100,10,64,20,2163.64,2000,1280000,924,0.564,105232.52,156049.35,156049.35 2,1000,10,64,20,18168.18,20000,12800000,1101,0.672,914839.37,958870.50,958870.50 ``` </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]
