| commit | c6c7e84ae44dbe8b8887a9f5e0e0e65ee66922fb | [log] [tgz] |
|---|---|---|
| author | Ryan Savitski <rsavitski@google.com> | Wed Mar 10 14:26:59 2021 +0000 |
| committer | Ryan Savitski <rsavitski@google.com> | Wed Mar 10 14:26:59 2021 +0000 |
| tree | d1f863ed3eacbab4ea3850a19dc52085869b9f6e | |
| parent | 12c6f30478ea0884851ed7a859a2a4a1ba2dfe5e [diff] |
trace_processor: perf sample counter tracking and distinguishing between multiple data sources
Primary additions:
* perf_session_id, which distinguishes individual profiling data sources.
* perf_counter_track, which both names the timebase for a
per-{cpu, perf_session_id} sampling stream, and tracks the sampled
counts themselves (now inserted into |counter| table).
The is_timebase column is added prematurely, but should become relevant
once we start supporting multi-counter sampling.
See go/perf-counters-tp for overall plan.
Will send a difftest in a separate patch once we agree that this
implementation makes sense.
Bug: 180437026
Change-Id: Ie23024ea4c6a9bdc1eb3c5abdb098705f3a21d58Perfetto 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.