Bug 763983 (GLUSTER-2251)

Summary: NFS server hangs on 40 dds running in parallel
Product: [Community] GlusterFS Reporter: Prasanth <prasanth>
Component: nfsAssignee: Shehjar Tikoo <shehjart>
Severity: medium Docs Contact:
Priority: medium    
Version: pre-2.0CC: gluster-bugs
Target Milestone: ---   
Target Release: ---   
Hardware: All   
OS: Linux   
Fixed In Version: Doc Type: Bug Fix
Doc Text:
Story Points: ---
Clone Of: Environment:
Last Closed: Type: ---
Regression: RTP Mount Type: nfs
Documentation: --- CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: ---

Description Shehjar Tikoo 2010-12-27 22:43:06 EST
Please use accurate wording when filing a bug. NFS wasnt crashing anywhere in the tests that we conducted. The whole machine was freezing...two very different situations.
Comment 1 Prasanth 2010-12-28 01:33:58 EST

This bug is opened based on the ticket: http://support.gluster.com/rt/Ticket/Display.html?id=2504

The Gluster native NFS crashes when mounted locally over localhost and handling many parallel writes. 40 parallel "dd if=/dev/zero of=/nfsmount/inX.dat bs=1M" are started and the dd processes quickly hangs together with the NFS mount.

I could reproduce this issue inhouse while doing 40+ parallel dd's. The server itself get hanged while doing parallel writes in the mount point. Unable to run any commands after that and a reboot is required to bring the server back online.

Comment 2 Shehjar Tikoo 2011-01-27 00:31:42 EST
More information available at 2251.

*** This bug has been marked as a duplicate of bug 2320 ***