Red Hat Bugzilla – Bug 1282771
IO hangs after detach tier commit of nfs mount
Last modified: 2018-02-06 12:52:18 EST
Description of problem:
Created a 8+4 disperse volume and attached a 2x2 hot tier. While IO is running, detached hot tier and committed, IO hangs on the client. This is on NFS mount.
Version-Release number of selected component (if applicable):
[root@vertigo glusterfs]# gluster --version
glusterfs 3.7.5 built on Nov 10 2015 00:13:38
Repository revision: git://git.gluster.com/glusterfs.git
Copyright (c) 2006-2011 Gluster Inc. <http://www.gluster.com>
GlusterFS comes with ABSOLUTELY NO WARRANTY.
You may redistribute copies of GlusterFS under the terms of the GNU General Public License.
Steps to Reproduce:
1. create a 8+4 ec volume and attach a 2x2 dist-rep hot tier
2. NFS mount on the client. untar kernel tarball and while it is in progress detach tier and commit.
3. Check the IO from client
IO should continue to run.
sosreports will be copied to rhsqe.
It seems to be rpc throttle issue. I see so many outstanding requests during attach/detach-tier operations. Once the throttle limit is set to zero, I do not see any hangs.
Request QE to try re-runnig the tests after disabling throttling and confirm if the issue still persist. Thanks!
Thank you for your bug report.
We are not further root causing this bug, as a result this bug is being closed as WONTFIX. Please reopen if the problem continues to be observed after upgrading
to a latest version.