Skip to content
GitLab
Projects Groups Snippets
  • /
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in / Register
  • D dynamorio
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 1,467
    • Issues 1,467
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 44
    • Merge requests 44
  • CI/CD
    • CI/CD
    • Pipelines
    • Jobs
    • Schedules
  • Deployments
    • Deployments
    • Environments
    • Releases
  • Packages and registries
    • Packages and registries
    • Package Registry
    • Infrastructure Registry
  • Monitor
    • Monitor
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • CI/CD
    • Repository
  • Wiki
    • Wiki
  • Snippets
    • Snippets
  • Activity
  • Graph
  • Create a new issue
  • Jobs
  • Commits
  • Issue Boards
Collapse sidebar
  • DynamoRIO
  • dynamorio
  • Issues
  • #4187
Closed
Open
Issue created Mar 17, 2020 by Derek Bruening@derekbrueningContributor

improve drsym_unix_lookup_symbol linear walk performance

On a large app, drcachesim's -record_heap can take a long time (1.5 minutes!) to query just the handful of heap functions it's looking for. (We recently added operator new and that rose to 2:40).

It looks like drsyms does a linear walk for symbol lookup! We should have it build a hashtable or sthg, or if we're worried about space take in a list of things to look for (or trace_func.cpp should change to enumerate w/ its own callback to do a single walk).

Even for addr lookup, for ELF it looks linear. MachO and PECOFF have a binary search.

Or, add a flag --dynsym_only where func_trace never calls into drsyms, as a drcachesim-focused fix.

Assignee
Assign to
Time tracking