| commit | 1e2100c2d11b938cc9472ddcd5ae888d84ca8212 | [log] [tgz] |
|---|---|---|
| author | Ryan Savitski <rsavitski@google.com> | Tue Feb 14 19:22:59 2023 +0000 |
| committer | Ryan Savitski <rsavitski@google.com> | Tue Feb 14 19:22:59 2023 +0000 |
| tree | e8b29be0688d51fdafafa58c37e05b2c17f6927c | |
| parent | 3b5b77c0db72fc5544996fc1c801391d97178c29 [diff] |
ftrace: fully respect max_pages in CpuReader::ReadCycle If max_pages is not a multiple of parsing_buf_size_pages (=32), then we might over-read since we step by that amount. That in turn violates an expectation that pages_read <= max_pages in ftrace_controller. This isn't a problem in practice since we don't normally hit these max_pages limits. And even if we do, the outcome is that the ftrace read tick reads fewer pages out of the kernel buffer than it otherwise would, but the next tick onwards is good again. Change-Id: I4cc6e38afeeaa59b624c8414528a1c6525da06b5
Perfetto is a production-grade open-source stack for performance instrumentation and trace analysis. It offers services and libraries and for recording system-level and app-level traces, native + java heap profiling, a library for analyzing traces using SQL and a web-based UI to visualize and explore multi-GB traces.
See https://perfetto.dev/docs or the /docs/ directory for documentation.