github-actions[bot] commented on PR #8644: URL: https://github.com/apache/texera/pull/8644#issuecomment-5787215263
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `54fba31` 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/35804596752) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 488 | 0.298 | 19,352/30,807/30,807 us | 🔴 +25.5% / 🔴 +98.1% | | 🟢 | bs=100 sw=10 sl=64 | 1,173 | 0.716 | 85,112/104,155/104,155 us | 🟢 -14.3% / 🟢 +19.3% | | ⚪ | bs=1000 sw=10 sl=64 | 1,400 | 0.854 | 717,932/770,725/770,725 us | ⚪ within ±5% / 🟢 +38.3% | <details><summary>Baseline details</summary> Latest main `54fba31` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 488 tuples/sec | 584 tuples/sec | 771.42 tuples/sec | -16.4% | -36.7% | | bs=10 sw=10 sl=64 | MB/s | 0.298 MB/s | 0.356 MB/s | 0.471 MB/s | -16.3% | -36.7% | | bs=10 sw=10 sl=64 | p50 | 19,352 us | 15,414 us | 12,757 us | +25.5% | +51.7% | | bs=10 sw=10 sl=64 | p95 | 30,807 us | 25,470 us | 15,551 us | +21.0% | +98.1% | | bs=10 sw=10 sl=64 | p99 | 30,807 us | 25,470 us | 19,296 us | +21.0% | +59.7% | | bs=100 sw=10 sl=64 | throughput | 1,173 tuples/sec | 1,155 tuples/sec | 983.07 tuples/sec | +1.6% | +19.3% | | bs=100 sw=10 sl=64 | MB/s | 0.716 MB/s | 0.705 MB/s | 0.6 MB/s | +1.6% | +19.3% | | bs=100 sw=10 sl=64 | p50 | 85,112 us | 81,207 us | 102,799 us | +4.8% | -17.2% | | bs=100 sw=10 sl=64 | p95 | 104,155 us | 121,580 us | 109,018 us | -14.3% | -4.5% | | bs=100 sw=10 sl=64 | p99 | 104,155 us | 121,580 us | 121,110 us | -14.3% | -14.0% | | bs=1000 sw=10 sl=64 | throughput | 1,400 tuples/sec | 1,429 tuples/sec | 1,012 tuples/sec | -2.0% | +38.3% | | bs=1000 sw=10 sl=64 | MB/s | 0.854 MB/s | 0.872 MB/s | 0.618 MB/s | -2.1% | +38.2% | | bs=1000 sw=10 sl=64 | p50 | 717,932 us | 699,517 us | 1,006,484 us | +2.6% | -28.7% | | bs=1000 sw=10 sl=64 | p95 | 770,725 us | 806,024 us | 1,046,167 us | -4.4% | -26.3% | | bs=1000 sw=10 sl=64 | p99 | 770,725 us | 806,024 us | 1,074,106 us | -4.4% | -28.2% | </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 0,10,10,64,20,409.43,200,128000,488,0.298,19351.66,30806.60,30806.60 1,100,10,64,20,1704.48,2000,1280000,1173,0.716,85111.88,104154.95,104154.95 2,1000,10,64,20,14288.10,20000,12800000,1400,0.854,717932.42,770725.13,770725.13 ``` </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]
