Move record parsing away from tokenization.

Do minimal parsing at tokenization time and put all records into the
sorter. In particular mmap2 records need to be time ordered so that
stacks are correctly resolved if mappings are deleted and recreated over
time (e.g. jitted code)

Also adds missing tokenization code for Features.

Bug: b/334978369

Change-Id: I4e496cdb6d42e76a54470fb76e8b8a69ee72dccc
24 files changed
tree: 240695e03986a82a311f3b4ccb18d07bd6fb5559
  1. .github/
  2. bazel/
  3. build_overrides/
  4. buildtools/
  5. debian/
  6. docs/
  7. examples/
  8. gn/
  9. include/
  10. infra/
  11. protos/
  12. python/
  13. src/
  14. test/
  15. third_party/
  16. tools/
  17. ui/
  18. .clang-format
  19. .clang-tidy
  20. .git-blame-ignore-revs
  21. .gitattributes
  22. .gitignore
  23. .gn
  24. .style.yapf
  25. Android.bp
  26. Android.bp.extras
  27. BUILD
  28. BUILD.extras
  29. BUILD.gn
  30. CHANGELOG
  31. codereview.settings
  32. DIR_METADATA
  33. heapprofd.rc
  34. LICENSE
  35. meson.build
  36. METADATA
  37. MODULE_LICENSE_APACHE2
  38. OWNERS
  39. perfetto.rc
  40. PerfettoIntegrationTests.xml
  41. persistent_cfg.pbtxt
  42. PRESUBMIT.py
  43. README.chromium
  44. README.md
  45. TEST_MAPPING
  46. traced_perf.rc
  47. WATCHLISTS
  48. WORKSPACE
README.md

Perfetto - System profiling, app tracing and trace analysis

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.