commit | 3fd9ccf6653591a7d8e1a8e3cd0a1cba39471c3a | [log] [tgz] |
---|---|---|
author | Ryan Savitski <rsavitski@google.com> | Sat May 01 16:10:53 2021 +0100 |
committer | Ryan Savitski <rsavitski@google.com> | Sat May 01 15:12:02 2021 +0000 |
tree | 6e5ac0037ef239b5e012a10c0248b5e5c4f5d822 | |
parent | 9f85729fdbafefa1e1caec3775c648a5f6a25c7d [diff] |
profilers: always log cross-process read errors Failures here are pretty much always indicative of something going very wrong (either state corruption or mismatch of expectations). The logging might get extremely spammy in the worst case, but I'd argue that we want a very prominent signal if the reads do go wrong. Otherwise we might miss issues like b/185312982 for a long time. Bug: 185312982 Change-Id: Id57968158eb7100f71737540f4e23052dd4db17e
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.