github-actions[bot] commented on PR #8518: URL: https://github.com/apache/texera/pull/8518#issuecomment-5639874671
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 4 worse · ⚪ 9 noise (<±5%) · 0 without baseline > Compared against main `069cd20` 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/34640726502) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 556 | 0.339 | 17,541/21,234/21,234 us | 🟢 -15.7% / 🔴 +41.0% | | 🔴 | bs=100 sw=10 sl=64 | 1,209 | 0.738 | 83,787/95,190/95,190 us | 🔴 +7.4% / 🟢 -19.2% | | 🔴 | bs=1000 sw=10 sl=64 | 1,397 | 0.852 | 710,895/831,925/831,925 us | 🔴 +7.2% / 🟢 +31.0% | <details><summary>Baseline details</summary> Latest main `069cd20` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 556 tuples/sec | 577 tuples/sec | 794.98 tuples/sec | -3.6% | -30.1% | | bs=10 sw=10 sl=64 | MB/s | 0.339 MB/s | 0.352 MB/s | 0.485 MB/s | -3.7% | -30.1% | | bs=10 sw=10 sl=64 | p50 | 17,541 us | 15,245 us | 12,443 us | +15.1% | +41.0% | | bs=10 sw=10 sl=64 | p95 | 21,234 us | 25,192 us | 15,648 us | -15.7% | +35.7% | | bs=10 sw=10 sl=64 | p99 | 21,234 us | 25,192 us | 19,794 us | -15.7% | +7.3% | | bs=100 sw=10 sl=64 | throughput | 1,209 tuples/sec | 1,271 tuples/sec | 1,034 tuples/sec | -4.9% | +16.9% | | bs=100 sw=10 sl=64 | MB/s | 0.738 MB/s | 0.776 MB/s | 0.631 MB/s | -4.9% | +16.9% | | bs=100 sw=10 sl=64 | p50 | 83,787 us | 77,993 us | 97,860 us | +7.4% | -14.4% | | bs=100 sw=10 sl=64 | p95 | 95,190 us | 92,068 us | 104,570 us | +3.4% | -9.0% | | bs=100 sw=10 sl=64 | p99 | 95,190 us | 92,068 us | 117,811 us | +3.4% | -19.2% | | bs=1000 sw=10 sl=64 | throughput | 1,397 tuples/sec | 1,427 tuples/sec | 1,066 tuples/sec | -2.1% | +31.0% | | bs=1000 sw=10 sl=64 | MB/s | 0.852 MB/s | 0.871 MB/s | 0.651 MB/s | -2.2% | +30.9% | | bs=1000 sw=10 sl=64 | p50 | 710,895 us | 702,884 us | 958,266 us | +1.1% | -25.8% | | bs=1000 sw=10 sl=64 | p95 | 831,925 us | 775,850 us | 998,734 us | +7.2% | -16.7% | | bs=1000 sw=10 sl=64 | p99 | 831,925 us | 775,850 us | 1,032,953 us | +7.2% | -19.5% | </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 0,10,10,64,20,359.92,200,128000,556,0.339,17541.27,21233.84,21233.84 1,100,10,64,20,1654.79,2000,1280000,1209,0.738,83786.99,95189.55,95189.55 2,1000,10,64,20,14321.32,20000,12800000,1397,0.852,710895.03,831924.51,831924.51 ``` </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]
