Bug 1583462 – Sharding sends all application sent fsyncs to the main shard file

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

Bug 1583462 - Sharding sends all application sent fsyncs to the main shard file [NEEDINFO]

Summary:	Sharding sends all application sent fsyncs to the main shard file

Status:	CLOSED ERRATA

Aliases:	None

Product:	Red Hat Gluster Storage
Classification:	Red Hat
Component:	sharding (Show other bugs)
Sub Component:
Version:	3.3
Hardware:	x86_64 Linux

Priority	medium Severity high
Target Milestone:	---
Target Release:	RHGS 3.3.1 Async
Assigned To:	Krutika Dhananjay
QA Contact:	SATHEESARAN
Docs Contact:

URL:
Whiteboard:
Keywords:	ZStream

Depends On:	1468483 1493085
Blocks:	1523608 1585104
	Show dependency tree / graph

Reported:	2018-05-29 00:55 EDT by Sunil Kumar Acharya
Modified:	2018-07-19 02:09 EDT (History)
CC List:	13 users (show)

See Also:
Fixed In Version:	glusterfs-3.8.4-54.12
Doc Type:	Bug Fix
Doc Text:	Previously, when an application sent fsync on a sharded file, the shards associated with the file were not being synced to disk. Hence, potentially causing data loss in case of a plain distribute shard volume. This update fixes the shard translator by syncing all the modified shards to disk whenever the application sends an fsync.
Story Points:	---
Clone Of:	1493085
Clones:	1585104 (view as bug list)
Environment:
Last Closed:	2018-07-19 02:00:07 EDT
Type:	Bug
Regression:	---
Mount Type:	---
Documentation:	---
CRM:
Verified Versions:
Category:	---
oVirt Team:	---
RHEL 7.3 requirements from Atomic Host:
Cloudforms Team:	---

Flags:	nchilaka: needinfo? (sasundar)

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

External Trackers
Tracker	ID	Priority	Status	Summary	Last Updated
Red Hat Product Errata	RHBA-2018:2222	None	None	None	2018-07-19 02:01 EDT

Groups: None (edit)

Comment 4 Atin Mukherjee 2018-06-25 08:54:31 EDT

Krutika - Can you please provide doc text for this bug?

Comment 5 SATHEESARAN 2018-07-05 09:18:10 EDT

Tested with glusterfs-3.8.4-54.13.el7rhgs with the following steps:

1. Created few VMs with their images on the distribute volume
2. Started all the VMs and installed OS on them.
3. Triggered lot of fsyncs inside the VM
4. Ran I/O inside them for few hours

There were no issues seen.

Comment 7 Nithya Balachandran 2018-07-17 02:07:04 EDT

Not the requestee but the doc text seems a little too technical. I do not understand the impact of not having this fix in the code to the end user.
Were distribute volumes supported in earlier releases? If not, perhaps the doc text is not required at all.

Comment 13 errata-xmlrpc 2018-07-19 02:00:07 EDT

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://access.redhat.com/errata/RHBA-2018:2222

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