github-actions[bot] commented on PR #8323: URL: https://github.com/apache/texera/pull/8323#issuecomment-5502043503
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 0 better · 🔴 9 worse · ⚪ 6 noise (<±5%) · 0 without baseline > Compared against main `fc7cfcd` 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/33571333692) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 381 | 0.232 | 24,750/36,040/36,040 us | 🔴 -10.1% / 🔴 +126.6% | | 🔴 | bs=100 sw=10 sl=64 | 787 | 0.48 | 124,577/173,603/173,603 us | 🔴 +29.4% / 🔴 +56.9% | | 🔴 | bs=1000 sw=10 sl=64 | 909 | 0.555 | 1,098,389/1,230,019/1,230,019 us | 🔴 +5.1% / 🔴 +16.7% | <details><summary>Baseline details</summary> Latest main `fc7cfcd` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 381 tuples/sec | 422 tuples/sec | 750.65 tuples/sec | -9.7% | -49.2% | | bs=10 sw=10 sl=64 | MB/s | 0.232 MB/s | 0.258 MB/s | 0.458 MB/s | -10.1% | -49.4% | | bs=10 sw=10 sl=64 | p50 | 24,750 us | 22,506 us | 13,049 us | +10.0% | +89.7% | | bs=10 sw=10 sl=64 | p95 | 36,040 us | 33,728 us | 15,902 us | +6.9% | +126.6% | | bs=10 sw=10 sl=64 | p99 | 36,040 us | 33,728 us | 19,184 us | +6.9% | +87.9% | | bs=100 sw=10 sl=64 | throughput | 787 tuples/sec | 824 tuples/sec | 960.3 tuples/sec | -4.5% | -18.0% | | bs=100 sw=10 sl=64 | MB/s | 0.48 MB/s | 0.503 MB/s | 0.586 MB/s | -4.6% | -18.1% | | bs=100 sw=10 sl=64 | p50 | 124,577 us | 120,084 us | 104,199 us | +3.7% | +19.6% | | bs=100 sw=10 sl=64 | p95 | 173,603 us | 134,143 us | 110,645 us | +29.4% | +56.9% | | bs=100 sw=10 sl=64 | p99 | 173,603 us | 134,143 us | 120,888 us | +29.4% | +43.6% | | bs=1000 sw=10 sl=64 | throughput | 909 tuples/sec | 914 tuples/sec | 993.27 tuples/sec | -0.5% | -8.5% | | bs=1000 sw=10 sl=64 | MB/s | 0.555 MB/s | 0.558 MB/s | 0.606 MB/s | -0.5% | -8.5% | | bs=1000 sw=10 sl=64 | p50 | 1,098,389 us | 1,084,889 us | 1,012,191 us | +1.2% | +8.5% | | bs=1000 sw=10 sl=64 | p95 | 1,230,019 us | 1,170,708 us | 1,054,057 us | +5.1% | +16.7% | | bs=1000 sw=10 sl=64 | p99 | 1,230,019 us | 1,170,708 us | 1,081,313 us | +5.1% | +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 0,10,10,64,20,525.39,200,128000,381,0.232,24749.66,36039.95,36039.95 1,100,10,64,20,2540.61,2000,1280000,787,0.480,124577.28,173603.00,173603.00 2,1000,10,64,20,21992.09,20000,12800000,909,0.555,1098388.82,1230018.86,1230018.86 ``` </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]
