commit | 07d02b088a65ea8d267f92052d9b598a92e2ab77 | [log] [tgz] |
---|---|---|
author | Omar Elmekkawy <mekk@google.com> | Tue Dec 14 20:36:36 2021 +0000 |
committer | Omar Elmekkawy <mekk@google.com> | Wed Dec 15 16:28:16 2021 +0000 |
tree | 4fa94a9095440a1c210ce7ca5f3ebd5a5a4ff439 | |
parent | 22467673a50f5599e7d8b1f49982faf7c1bc30d9 [diff] |
Improve CPU time accuracy by using thread_slice. Previously we were performing multiple joins with the counter table, afterwards we get the data pre-joined by trace processor. This improves speed as well as accuracy since we know which slice generated which CPU timestamp. Bug: 209995826 Change-Id: I4cd60421ccc351f1babe2d8a16164ba333312b0e Testing: tools/diff_test_trace_processor.py out/android/trace_processor_shell [==========] 287 tests ran. (535925 ms total) [ PASSED ] 287 tests
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.