Userfaultfd

From CRIU
Revision as of 15:56, 26 February 2015 by Xemul (talk | contribs)
Jump to navigation Jump to search

Collected on this page is the design notes about supporting userfaultfd in CRIU


Concepts

  • Tasks after restore should have lazy VMAs being backed by userfaultfd, the fd itself should be sent before resume to CRIU daemon and closed
  • Only MAP_PRIVATE | MAP_ANONYMOUS will be supported in the 1st version due to kernel constraints
  • On source side the page server should be taught to use page-read to send pages out on the destination one
  • Protocol should include out-of-order pages and background pages pushing (sending them before demand from the process)
  • The now dump-only --page-server option should be used for restore action to tell that the memory will be sucked in through page server