github-actions[bot] commented on PR #6806: URL: https://github.com/apache/texera/pull/6806#issuecomment-5052269978
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 12 worse · ⚪ 3 noise (<±5%) · 0 without baseline > Compared against main `fa075d1` 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/29962721131) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 461 | 0.281 | 21,818/34,072/34,072 us | 🔴 +18.2% / 🔴 +111.4% | | 🔴 | bs=100 sw=10 sl=64 | 934 | 0.57 | 102,136/167,289/167,289 us | 🔴 +34.8% / 🔴 +55.7% | | 🔴 | bs=1000 sw=10 sl=64 | 1,127 | 0.688 | 886,593/940,042/940,042 us | 🔴 +5.8% / 🟢 -11.0% | <details><summary>Baseline details</summary> Latest main `fa075d1` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 461 tuples/sec | 496 tuples/sec | 760.2 tuples/sec | -7.1% | -39.4% | | bs=10 sw=10 sl=64 | MB/s | 0.281 MB/s | 0.303 MB/s | 0.464 MB/s | -7.3% | -39.4% | | bs=10 sw=10 sl=64 | p50 | 21,818 us | 18,461 us | 12,781 us | +18.2% | +70.7% | | bs=10 sw=10 sl=64 | p95 | 34,072 us | 31,464 us | 16,118 us | +8.3% | +111.4% | | bs=10 sw=10 sl=64 | p99 | 34,072 us | 31,464 us | 19,074 us | +8.3% | +78.6% | | bs=100 sw=10 sl=64 | throughput | 934 tuples/sec | 1,013 tuples/sec | 988.68 tuples/sec | -7.8% | -5.5% | | bs=100 sw=10 sl=64 | MB/s | 0.57 MB/s | 0.619 MB/s | 0.603 MB/s | -7.9% | -5.5% | | bs=100 sw=10 sl=64 | p50 | 102,136 us | 96,866 us | 101,448 us | +5.4% | +0.7% | | bs=100 sw=10 sl=64 | p95 | 167,289 us | 124,086 us | 107,410 us | +34.8% | +55.7% | | bs=100 sw=10 sl=64 | p99 | 167,289 us | 124,086 us | 120,258 us | +34.8% | +39.1% | | bs=1000 sw=10 sl=64 | throughput | 1,127 tuples/sec | 1,140 tuples/sec | 1,023 tuples/sec | -1.1% | +10.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.688 MB/s | 0.696 MB/s | 0.624 MB/s | -1.1% | +10.2% | | bs=1000 sw=10 sl=64 | p50 | 886,593 us | 878,938 us | 983,888 us | +0.9% | -9.9% | | bs=1000 sw=10 sl=64 | p95 | 940,042 us | 888,791 us | 1,030,100 us | +5.8% | -8.7% | | bs=1000 sw=10 sl=64 | p99 | 940,042 us | 888,791 us | 1,056,513 us | +5.8% | -11.0% | </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 0,10,10,64,20,433.99,200,128000,461,0.281,21818.40,34071.93,34071.93 1,100,10,64,20,2141.00,2000,1280000,934,0.570,102135.63,167289.27,167289.27 2,1000,10,64,20,17739.90,20000,12800000,1127,0.688,886593.46,940042.07,940042.07 ``` </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]
