github-actions[bot] commented on PR #7298: URL: https://github.com/apache/texera/pull/7298#issuecomment-5172661738
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 5 worse · ⚪ 8 noise (<±5%) · 0 without baseline > Compared against main `7f6402d` 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/30860555135) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 376 | 0.23 | 25,593/34,880/34,880 us | 🔴 +5.7% / 🔴 +127.4% | | 🔴 | bs=100 sw=10 sl=64 | 919 | 0.561 | 107,740/129,750/129,750 us | 🟢 -9.4% / 🔴 +23.3% | | 🔴 | bs=1000 sw=10 sl=64 | 1,096 | 0.669 | 901,388/1,051,080/1,051,080 us | 🔴 +5.8% / 🟢 -6.5% | <details><summary>Baseline details</summary> Latest main `7f6402d` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 376 tuples/sec | 397 tuples/sec | 791.9 tuples/sec | -5.3% | -52.5% | | bs=10 sw=10 sl=64 | MB/s | 0.23 MB/s | 0.242 MB/s | 0.483 MB/s | -5.0% | -52.4% | | bs=10 sw=10 sl=64 | p50 | 25,593 us | 24,203 us | 12,391 us | +5.7% | +106.5% | | bs=10 sw=10 sl=64 | p95 | 34,880 us | 35,872 us | 15,336 us | -2.8% | +127.4% | | bs=10 sw=10 sl=64 | p99 | 34,880 us | 35,872 us | 18,924 us | -2.8% | +84.3% | | bs=100 sw=10 sl=64 | throughput | 919 tuples/sec | 967 tuples/sec | 1,018 tuples/sec | -5.0% | -9.8% | | bs=100 sw=10 sl=64 | MB/s | 0.561 MB/s | 0.59 MB/s | 0.622 MB/s | -4.9% | -9.7% | | bs=100 sw=10 sl=64 | p50 | 107,740 us | 99,009 us | 98,925 us | +8.8% | +8.9% | | bs=100 sw=10 sl=64 | p95 | 129,750 us | 143,147 us | 105,265 us | -9.4% | +23.3% | | bs=100 sw=10 sl=64 | p99 | 129,750 us | 143,147 us | 112,729 us | -9.4% | +15.1% | | bs=1000 sw=10 sl=64 | throughput | 1,096 tuples/sec | 1,083 tuples/sec | 1,051 tuples/sec | +1.2% | +4.3% | | bs=1000 sw=10 sl=64 | MB/s | 0.669 MB/s | 0.661 MB/s | 0.641 MB/s | +1.2% | +4.3% | | bs=1000 sw=10 sl=64 | p50 | 901,388 us | 929,207 us | 964,104 us | -3.0% | -6.5% | | bs=1000 sw=10 sl=64 | p95 | 1,051,080 us | 993,661 us | 1,002,343 us | +5.8% | +4.9% | | bs=1000 sw=10 sl=64 | p99 | 1,051,080 us | 993,661 us | 1,030,483 us | +5.8% | +2.0% | </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 0,10,10,64,20,531.65,200,128000,376,0.230,25593.25,34879.83,34879.83 1,100,10,64,20,2175.14,2000,1280000,919,0.561,107740.25,129749.81,129749.81 2,1000,10,64,20,18249.02,20000,12800000,1096,0.669,901388.33,1051079.74,1051079.74 ``` </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]
