Bug 734829

Summary: memcg: prevent livelocking the system on a memcg in trouble
Product: Red Hat Enterprise Linux 6 Reporter: Johannes Weiner <jweiner>
Component: kernelAssignee: Johannes Weiner <jweiner>
Status: CLOSED NOTABUG QA Contact: Red Hat Kernel QE team <kernel-qe>
Severity: medium Docs Contact:
Priority: unspecified    
Version: 6.3CC: lwang
Target Milestone: rc   
Target Release: ---   
Hardware: All   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: 2013-05-13 19:19:36 UTC Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:
Embargoed:
Bug Depends On:    
Bug Blocks: 767187    

Description Johannes Weiner 2011-08-31 14:51:41 UTC 
A memory cgroup in trouble (oom-killer disabled, forkbomb) can potentially livelock tasks outside the group that share the same data (shared libraries e.g.).

When COW-breaking a page, the copy is allocated and charged while the original page is locked.  If the charging requires reclaim or oom-killing, other tasks are tripped up when trying to access and lock the same COW page, causing indefinite stalls.
Comment 2 RHEL Program Management 2012-05-03 05:29:15 UTC 
Since RHEL 6.3 External Beta has begun, and this bug remains
unresolved, it has been rejected as it is not proposed as
exception or blocker.

Red Hat invites you to ask your support representative to
propose this request, if appropriate and relevant, in the
next release of Red Hat Enterprise Linux.