Bug 1195378

Summary:	Perf: DHT errors filling logs when perf tests are run.
Product:	[Red Hat Storage] Red Hat Gluster Storage	Reporter:	Ben Turner <bturner>
Component:	core	Assignee:	Raghavendra G <rgowdapp>
Status:	CLOSED ERRATA	QA Contact:	Ben Turner <bturner>
Severity:	high	Docs Contact:
Priority:	high
Version:	rhgs-3.0	CC:	annair, asrivast, nbalacha, rcyriac, rhs-bugs, storage-qa-internal, vagarwal
Target Milestone:	---	Keywords:	Regression, ZStream
Target Release:	RHGS 3.0.4
Hardware:	x86_64
OS:	Linux
Whiteboard:
Fixed In Version:	glusterfs-3.6.0.50-1	Doc Type:	Bug Fix
Doc Text:		Story Points:	---
Clone Of:
Clones:	1195668 (view as bug list)		Environment:
Last Closed:	2015-03-26 06:36:27 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:
Bug Depends On:
Bug Blocks:	1182947, 1195668

Description Ben Turner 2015-02-23 17:05:02 UTC

Description of problem:

During performance testing I see the following messages spamming the client logs:

[2015-02-23 05:06:06.355467] W [dict.c:329:dict_set] (-->/usr/lib64/glusterfs/3.6.0.46/xlator/cluster/distribute.so(dht_selfheal_layout_lock_cbk+0x10) [0x7fc76447b110] (-->/usr/lib64/glusterfs/3.6.0.46/xlator/cluster/distribute.so(dht_refresh_layout+0x30e) [0x7fc76447b08e] (-->/usr/lib64/libglusterfs.so.0(dict_set_uint32+0x3b) [0x7fc76ef32ceb]))) 0-dict: !this || !value for key=trusted.glusterfs.dht
[2015-02-23 05:06:06.355478] W [MSGID: 109003] [dht-selfheal.c:270:dht_refresh_layout] 0-testvol-dht: /file_dstdir/192.168.52.107/thrd_07/d_008/d_009: Failed to set dictionary value:key = trusted.glusterfs.dht
[2015-02-23 05:06:06.356455] I [dict.c:371:dict_get] (-->/usr/lib64/glusterfs/3.6.0.46/xlator/cluster/distribute.so(dht_inodelk_done+0x4e) [0x7fc7644702ce] (-->/usr/lib64/glusterfs/3.6.0.46/xlator/cluster/distribute.so(dht_selfheal_layout_lock_cbk+0x10) [0x7fc76447b110] (-->/usr/lib64/glusterfs/3.6.0.46/xlator/cluster/distribute.so(dht_refresh_layout+0xb3) [0x7fc76447ae33]))) 0-dict: !this || key=trusted.glusterfs.dht

Version-Release number of selected component (if applicable):

glusterfs-3.6.0.46-1.el6.x86_64

How reproducible:

Every run.

Steps to Reproduce:
1.  Run gluster benchmark kit on 2x1 volume.
2.  Check logs

Actual results:

The mount logs are spammed with the above messages, also note that performance is poor.

Expected results:

Normal operation / performance.

Additional info:

Comment 1 Raghavendra G 2015-03-05 09:16:20 UTC

https://code.engineering.redhat.com/gerrit/43335

Comment 2 Ben Turner 2015-03-11 14:30:00 UTC

Verified on glusterfs-3.6.0.50-1.

Comment 4 errata-xmlrpc 2015-03-26 06:36:27 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-2015-0682.html