Bug 765052 (GLUSTER-3320)

Summary: Improve handling of concurrent operations in glusterd.
Product: [Community] GlusterFS Reporter: krishnan parthasarathi <kparthas>
Component: glusterdAssignee: krishnan parthasarathi <kparthas>
Status: CLOSED CURRENTRELEASE QA Contact:
Severity: medium Docs Contact:
Priority: medium    
Version: mainlineCC: fharshav, gluster-bugs, glusterfs, nsathyan, rabhat
Target Milestone: ---   
Target Release: ---   
Hardware: x86_64   
OS: Linux   
Whiteboard:
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: --- Mount Type: ---
Documentation: --- CRM:
Verified Versions: glusterfs-3.3.0qa10 Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:

Description krishnan parthasarathi 2011-08-03 07:35:03 EDT
This bug tracks the following changes,

- removal of glusterd's local cli lock and use the cluster wide lock to serialize
  concurrent cli requests to the same glusterd.

- improve glusterd's internal cluster-wide locking mechanism when multiple clients request operations via multiple glusterds.
Comment 1 Harshavardhana 2011-08-15 12:06:48 EDT
*** Bug 2193 has been marked as a duplicate of this bug. ***
Comment 2 Anand Avati 2011-09-04 23:58:49 EDT
CHANGE: http://review.gluster.com/123 (This change contains,) merged in master by Vijay Bellur (vijay@gluster.com)
Comment 3 Raghavendra Bhat 2011-09-23 02:59:08 EDT
Its fixed now. Checked with glusterfs-3.3.0qa10. Now parallel cli operations will make only one of them succeed, and glusterd wont crash.