Skip to content

GitLab

  • Menu
Projects Groups Snippets
    • Loading...
  • Help
    • Help
    • Support
    • Community forum
    • Submit feedback
    • Contribute to GitLab
  • Sign in
  • C codes
  • Project information
    • Project information
    • Activity
    • Labels
    • Members
  • Repository
    • Repository
    • Files
    • Commits
    • Branches
    • Tags
    • Contributors
    • Graph
    • Compare
  • Issues 38
    • Issues 38
    • List
    • Boards
    • Service Desk
    • Milestones
  • Merge requests 8
    • Merge requests 8
  • Deployments
    • Deployments
    • Releases
  • Monitor
    • Monitor
    • Incidents
  • Analytics
    • Analytics
    • Value stream
    • Repository
  • Wiki
    • Wiki
  • Activity
  • Graph
  • Create a new issue
  • Commits
  • Issue Boards
Collapse sidebar
  • codes
  • codes
  • Issues
  • #50

Closed
Open
Created Jan 14, 2016 by Jonathan Jenkins@jenkinsContributor

model-net seemingly causing non-trivial performance overheads

We've heard about this a few times now (Ning with the fattree, Misbah with the dragonfly model / MPI replay program, and potentially Misbah/Caitlin with "awesim" runs) - something is causing performance regressions (resulting in less ROSS efficiency) when using model-net vs direct ROSS in optimistic mode.

It's unclear why this is happening for the time being. model-net imposes two extra events (sched-new, sched-next) per model_net_event call, the first of which is a remote from the client (the original "packet event" that the client used to directly send is now a self-event). I would imagine there to be some degree of overhead for this, but nothing that would significantly affect the rollback rate / ROSS efficiency...

We should keep this in the back of our minds while we are working on other things.

Assignee
Assign to
Time tracking