Bug 1339710

Summary:	initalization of 'recursive' tls variable in libunwind stack capturer occasionally triggers deadlock in ceph
Product:	Red Hat Enterprise Linux 7	Reporter:	Ken Dreyer (Red Hat) <kdreyer>
Component:	gperftools	Assignee:	Paolo Bonzini <pbonzini>
Status:	CLOSED ERRATA	QA Contact:	Robin Hack <rhack>
Severity:	unspecified	Docs Contact:
Priority:	unspecified
Version:	7.3	CC:	chayang, dahorak, databases-maint, juzhang, knoel, lmiksik, pbonzini, rhack, sjust
Target Milestone:	rc
Target Release:	---
Hardware:	Unspecified
OS:	Unspecified
Whiteboard:
Fixed In Version:	gperftools-2.4-8.el7	Doc Type:	If docs needed, set a value
Doc Text:		Story Points:	---
Clone Of:		Environment:
Last Closed:	2016-11-04 07:35:19 UTC	Type:	Bug
Regression:	---	Mount Type:	---
Documentation:	---	CRM:
Verified Versions:		Category:	---
oVirt Team:	---	RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---	Target Upstream Version:
Embargoed:

Description Ken Dreyer (Red Hat) 2016-05-25 16:37:42 UTC

Description of problem:
ceph occasionally deadlocks due to the way tcmalloc initializes the "recursive" tls variable.

Version-Release number of selected component (if applicable):
gperftools-libs-2.4-7.el7.x86_64


How reproducible:
intermittent

Steps to Reproduce:
We don't have a completely reliable reproducer, but this is tracked upstream in Ceph at http://tracker.ceph.com/issues/13522 , and we've identified what looks to be the same issue downsteam in the Red Hat Ceph Storage product in bz 1334636.

Additional info:
The gperftools upstream project merged https://github.com/gperftools/gperftools/issues/786 to fix this issue. Would you please ship that patch in RHEL 7's gperftools as well?

Comment 2 Samuel Just 2016-06-13 17:31:58 UTC

Causes trouble in automated 2.0 testing as well.  It would be good to get a patched version...

Comment 3 Miroslav Rezanina 2016-06-22 14:08:49 UTC

Fix included in gperftools-2.4-8.el7

Comment 8 errata-xmlrpc 2016-11-04 07:35:19 UTC

Since the problem described in this bug report should be
resolved in a recent advisory, it has been closed with a
resolution of ERRATA.

For information on the advisory, and where to find the updated
files, follow the link below.

If the solution does not work for you, open a new bug report.

https://rhn.redhat.com/errata/RHBA-2016-2489.html