github-actions[bot] commented on PR #7760: URL: https://github.com/apache/texera/pull/7760#issuecomment-5334350597
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 7 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `fb9f4e2` 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/32187996506) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 460 | 0.281 | 20,781/33,153/33,153 us | 🔴 +16.1% / 🔴 +104.4% | | 🔴 | bs=100 sw=10 sl=64 | 958 | 0.585 | 98,248/138,209/138,209 us | 🔴 +6.3% / 🔴 +24.5% | | ⚪ | bs=1000 sw=10 sl=64 | 1,146 | 0.699 | 865,582/935,141/935,141 us | ⚪ within ±5% / 🟢 +15.2% | <details><summary>Baseline details</summary> Latest main `fb9f4e2` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 460 tuples/sec | 511 tuples/sec | 743.3 tuples/sec | -10.0% | -38.1% | | bs=10 sw=10 sl=64 | MB/s | 0.281 MB/s | 0.312 MB/s | 0.454 MB/s | -9.9% | -38.1% | | bs=10 sw=10 sl=64 | p50 | 20,781 us | 17,896 us | 13,204 us | +16.1% | +57.4% | | bs=10 sw=10 sl=64 | p95 | 33,153 us | 31,327 us | 16,220 us | +5.8% | +104.4% | | bs=10 sw=10 sl=64 | p99 | 33,153 us | 31,327 us | 19,867 us | +5.8% | +66.9% | | bs=100 sw=10 sl=64 | throughput | 958 tuples/sec | 987 tuples/sec | 959.52 tuples/sec | -2.9% | -0.2% | | bs=100 sw=10 sl=64 | MB/s | 0.585 MB/s | 0.602 MB/s | 0.586 MB/s | -2.8% | -0.1% | | bs=100 sw=10 sl=64 | p50 | 98,248 us | 98,270 us | 103,974 us | -0.0% | -5.5% | | bs=100 sw=10 sl=64 | p95 | 138,209 us | 130,069 us | 111,036 us | +6.3% | +24.5% | | bs=100 sw=10 sl=64 | p99 | 138,209 us | 130,069 us | 118,982 us | +6.3% | +16.2% | | bs=1000 sw=10 sl=64 | throughput | 1,146 tuples/sec | 1,144 tuples/sec | 994.68 tuples/sec | +0.2% | +15.2% | | bs=1000 sw=10 sl=64 | MB/s | 0.699 MB/s | 0.698 MB/s | 0.607 MB/s | +0.1% | +15.1% | | bs=1000 sw=10 sl=64 | p50 | 865,582 us | 873,487 us | 1,011,206 us | -0.9% | -14.4% | | bs=1000 sw=10 sl=64 | p95 | 935,141 us | 911,435 us | 1,055,603 us | +2.6% | -11.4% | | bs=1000 sw=10 sl=64 | p99 | 935,141 us | 911,435 us | 1,084,808 us | +2.6% | -13.8% | </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 0,10,10,64,20,434.89,200,128000,460,0.281,20781.37,33153.48,33153.48 1,100,10,64,20,2088.23,2000,1280000,958,0.585,98247.99,138208.58,138208.58 2,1000,10,64,20,17459.41,20000,12800000,1146,0.699,865582.34,935141.41,935141.41 ``` </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]
