perf: bypass async I/O pipeline for in-memory buffer reads #6813
+79
−5
CodSpeed HQ / CodSpeed Performance Analysis
succeeded
Mar 9, 2026 in 0s
Performance Gate Passed
⚡ 5 improved benchmarks
✅ 995 untouched benchmarks
⏩ 1466 skipped benchmarks1
Performance Changes
| Mode | Benchmark | BASE |
HEAD |
Efficiency | |
|---|---|---|---|---|---|
| ⚡ | Simulation | patched_take_200k_dispersed |
5.6 ms | 4.7 ms | +19.88% |
| ⚡ | Simulation | patched_take_10k_contiguous_patches |
2.3 ms | 2.1 ms | +10.81% |
| ⚡ | Simulation | patched_take_200k_first_chunk_only |
5.4 ms | 4.8 ms | +11.99% |
| ⚡ | Simulation | take_200k_first_chunk_only |
4.2 ms | 3.3 ms | +26.44% |
| ⚡ | Simulation | take_200k_dispersed |
4.5 ms | 3.6 ms | +24.36% |
Comparing ad/bypass-async-pipeline (34edfad) with develop (4d124b0)
Footnotes
-
1466 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩
Loading