Bug 1394007 – filestore: can get stuck in an unbounded loop during scrub

Bugzilla will be upgraded to version 5.0. The upgrade date is tentatively scheduled for 2 December 2018, pending final testing and feedback.

Bug 1394007 - filestore: can get stuck in an unbounded loop during scrub

Summary:	filestore: can get stuck in an unbounded loop during scrub

Status:	CLOSED ERRATA

Aliases:	None

Product:	Red Hat Ceph Storage
Classification:	Red Hat
Component:	RADOS (Show other bugs)
Sub Component:
Version:	2.0
Hardware:	x86_64 Linux

Priority	high Severity high
Target Milestone:	rc
Target Release:	2.1
Assigned To:	Samuel Just
QA Contact:	ceph-qe-bugs
Docs Contact:

URL:
Whiteboard:
Keywords:

Depends On:
Blocks:
	Show dependency tree / graph

Reported:	2016-11-10 14:55 EST by Ken Dreyer (Red Hat)
Modified:	2017-07-30 11:19 EDT (History)
CC List:	9 users (show)

See Also:
Fixed In Version:	RHEL: ceph-10.2.3-14.el7cp Ubuntu: ceph_10.2.3-15redhat1
Doc Type:	Bug Fix
Doc Text:	Due to a bug in the underlying source code, OSD nodes sometimes looped through the entire placement group, not only the requested segment, during the scrubbing process. Consequently, in some cases, the OSD nodes reached the 'suicide timeout' and terminated. This bug has been fixed, and OSD nodes no longer terminate due to the described problem.
Story Points:	---
Clone Of:
Environment:
Last Closed:	2016-12-15 11:49:16 EST
Type:	Bug
Regression:	---
Mount Type:	---
Documentation:	---
CRM:
Verified Versions:
Category:	---
oVirt Team:	---
RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---

Attachments	(Terms of Use)
Add an attachment (proposed patch, testcase, etc.)

External Trackers
Tracker	ID	Priority	Status	Summary	Last Updated
Red Hat Knowledge Base (Solution)	2800491	None	None	None	2016-12-08 16:12 EST
Ceph Project Bug Tracker	17859	None	None	None	2016-11-10 14:55 EST
Red Hat Product Errata	RHSA-2016:2954	normal	SHIPPED_LIVE	Moderate: Red Hat Ceph Storage 2.1 security and bug fix update	2017-03-21 22:06:31 EDT
Red Hat Product Errata	RHSA-2016:2956	normal	SHIPPED_LIVE	Moderate: Red Hat Ceph Storage 2.1 security and bug fix update	2016-12-15 18:02:58 EST

Groups: None (edit)

Description Ken Dreyer (Red Hat) 2016-11-10 14:55:27 EST

Description of problem:
Filestore collections with a certain layout can lead to slow scrubs or OSD suicides

Version-Release number of selected component (if applicable):
ceph v10.2.3

How reproducible:
unknown

Actual results:
slow scrubs or OSD suicides

Expected results:
scrubs finish in normal time, OSDs do not suicide

Comment 27 errata-xmlrpc 2016-12-15 11:49:16 EST

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/RHSA-2016-2954.html

Note You need to log in before you can comment on or make changes to this bug.