Bug 1546620

Summary:	DHT calls dht_lookup_everywhere for 1xn volumes
Product:	[Community] GlusterFS	Reporter:	Nithya Balachandran <nbalacha>
Component:	distribute	Assignee:	Nithya Balachandran <nbalacha>
Status:	CLOSED CURRENTRELEASE	QA Contact:
Severity:	unspecified	Docs Contact:
Priority:	unspecified
Version:	mainline	CC:	bugs, rhinduja, rhs-bugs, storage-qa-internal, tdesala
Target Milestone:	---
Target Release:	---
Hardware:	Unspecified
OS:	Unspecified
Whiteboard:
Fixed In Version:	glusterfs-v4.1.0	Doc Type:	If docs needed, set a value
Doc Text:		Story Points:	---
Clone Of:	1545570
Clones:	1548270 1548271 (view as bug list)		Environment:
Last Closed:	2018-06-20 18:00:23 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:	1545570, 1548270, 1548271

Description Nithya Balachandran 2018-02-19 04:11:40 UTC

+++ This bug was initially created as a clone of Bug #1545570 +++

Description of problem:

DHT lookup does not handle lookups on 1xn volumes optimally. It calls a dht_lookup_everywhere even though it has already checked the only subvol leading to repeated, redundant lookups for entries.

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


How reproducible:
Consistently

Steps to Reproduce:
1. Create a 1x3 volume and set client-log-level to DEBUG
2. Fuse mount the volume and create some files (touch file-{1..10})
3. Check the mnt log for dht messages

Actual results:
[2018-02-15 09:53:04.799711] D [MSGID: 0] [dht-common.c:2761:dht_lookup] 0-gitmo-dht: Calling fresh lookup for /file-10 on gitmo-replicate-0
[2018-02-15 09:53:04.800179] D [MSGID: 0] [dht-common.c:2344:dht_lookup_cbk] 0-gitmo-dht: fresh_lookup returned for /file-10 with op_ret -1 [No such file or directory]
[2018-02-15 09:53:04.800188] D [MSGID: 0] [dht-common.c:2357:dht_lookup_cbk] 0-gitmo-dht: Entry /file-10 missing on subvol gitmo-replicate-0
[2018-02-15 09:53:04.800196] D [MSGID: 0] [dht-common.c:2128:dht_lookup_everywhere] 0-gitmo-dht: winding lookup call to 1 subvols
[2018-02-15 09:53:04.800670] D [MSGID: 0] [dht-common.c:1930:dht_lookup_everywhere_cbk] 0-gitmo-dht: returned with op_ret -1 and op_errno 2 (/file-10) from subvol gitmo-replicate-0
[2018-02-15 09:53:04.800679] D [MSGID: 0] [dht-common.c:1594:dht_lookup_everywhere_done] 0-gitmo-dht: STATUS: hashed_subvol gitmo-replicate-0 cached_subvol null
[2018-02-15 09:53:04.800684] D [MSGID: 0] [dht-common.c:1655:dht_lookup_everywhere_done] 0-gitmo-dht: There was no cached file and  unlink on hashed is not skipped /file-10
[2018-02-15 09:53:04.800691] D [MSGID: 0] [dht-common.c:1658:dht_lookup_everywhere_done] 0-stack-trace: stack-address: 0x7f03e4000d50, gitmo-dht returned -1 error: No such file or directory [No such file or directory]


Expected results:

DHT need not call dht_lookup_everywhere for 1xn volumes

Additional info:

--- Additional comment from Red Hat Bugzilla Rules Engine on 2018-02-15 04:58:27 EST ---

This bug is automatically being proposed for the release of Red Hat Gluster Storage 3 under active development and open for bug fixes, by setting the release flag 'rhgs‑3.4.0' to '?'. 

If this bug should be proposed for a different release, please manually change the proposed release flag.

--- Additional comment from Red Hat Bugzilla Rules Engine on 2018-02-15 07:26:53 EST ---

This bug is automatically being provided 'pm_ack+' for the release flag 'rhgs‑3.4.0', having been appropriately marked for the release, and having been provided ACK from Development and QE

--- Additional comment from Red Hat Bugzilla Rules Engine on 2018-02-16 07:26:30 EST ---

Since this bug has has been approved for the RHGS 3.4.0 release of Red Hat Gluster Storage 3, through release flag 'rhgs-3.4.0+', and through the Internal Whiteboard entry of '3.4.0', the Target Release is being automatically set to 'RHGS 3.4.0'

Comment 1 Worker Ant 2018-02-19 04:24:37 UTC

REVIEW: https://review.gluster.org/19581 (cluster/dht: Handle single dht child in dht_lookup) posted (#1) for review on master by N Balachandran

Comment 2 Worker Ant 2018-02-22 10:51:59 UTC

COMMIT: https://review.gluster.org/19581 committed in master by "Raghavendra G" <rgowdapp> with a commit message- cluster/dht: Handle single dht child in dht_lookup

This patch limits itself to only handling the case
where no file (data or linkto) exists on the subvol.

Additional cases to be handled:
1. A linkto file was found on the only child subvol. This currently
calls dht_lookup_everywhere which eventually deletes it. It can be
deleted directly as it will not be pointing to a valid subvol.
2. Directory lookups - locking might be unnecessary in some cases.

Change-Id: I940ba34531f2aaee1d36fd9ca45ecfd46be662a4
BUG: 1546620
Signed-off-by: N Balachandran <nbalacha>

Comment 3 Shyamsundar 2018-06-20 18:00:23 UTC

This bug is getting closed because a release has been made available that should address the reported issue. In case the problem is still not fixed with glusterfs-v4.1.0, please open a new bug report.

glusterfs-v4.1.0 has been announced on the Gluster mailinglists [1], packages for several distributions should become available in the near future. Keep an eye on the Gluster Users mailinglist [2] and the update infrastructure for your distribution.

[1] http://lists.gluster.org/pipermail/announce/2018-June/000102.html
[2] https://www.gluster.org/pipermail/gluster-users/