commit | 2fc5db22f222dceb674baefb85bb4915dfecd5c1 | [log] [tgz] |
---|---|---|
author | Lalit Maganti <lalitm@google.com> | Thu Aug 13 15:02:47 2020 +0100 |
committer | Lalit Maganti <lalitm@google.com> | Thu Aug 13 15:02:47 2020 +0100 |
tree | fc4b9dffe52ad24037a0c0281ea0bd88634d0e19 | |
parent | 3902cda1ade25bc906ad5b3738e4878b2edd9813 [diff] |
[RELAND] tp: move thread state implementation to trace processor Thread state is pretty complicated to calculate and has a lot of edge cases and subtlety that's hard to capture in SQL. The other problem is that we also want to have thread state available for metrics (currently some metrics have recreated a cut down version of this class). For this reason, move the thread state computation as a dynamic table in C++ which allows sharing it with other places. It also has the advantage of making startup of the UI much faster as it doesn't need to compute the thread state table. This is a reland of aosp/1360559 Bug: 163812686 Change-Id: I48ed30e9b9696890fb8d389b0014d65e609feb3d
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.