Bug 764671 (GLUSTER-2939)

Summary: crash in io-cache
Product: [Community] GlusterFS Reporter: Raghavendra G <raghavendra>
Component: io-cacheAssignee: Raghavendra G <raghavendra>
Status: CLOSED WORKSFORME QA Contact:
Severity: high Docs Contact:
Priority: medium    
Version: mainlineCC: anush, gluster-bugs, vijay
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: RTNR Mount Type: fuse
Documentation: DNR CRM:
Verified Versions: Category: ---
oVirt Team: --- RHEL 7.3 requirements from Atomic Host:
Cloudforms Team: --- Target Upstream Version:

Description Raghavendra G 2011-05-24 18:49:50 UTC
reported by
"Cal Leeming [Simplicity Media Ltd]"<cal.leeming.uk> on gluster-users.

<bug report>

Every now and then I keep getting the following error:

mkdir: cannot create directory `/home/simplicitymedialtd/ds': Transport endpoint is not connected
mkdir: cannot create directory `/home/simplicitymedialtd/ds': Transport endpoint is not connected

To make this error go away, I have to unmount and mount the directory. Seems to be related to a crash (see below log)...

Any idea why this keeps happening?

Cal


PS: log file shows a crash this:

pending frames:

patchset: v3.1.4
signal received: 11
time of crash: 2011-05-20 12:14:13
configuration details:
argp 1
backtrace 1
dlfcn 1
fdatasync 1
libpthread 1
llistxattr 1
setfsid 1
spinlock 1
epoll.h 1
xattr.h 1
st_atim.tv_nsec 1
package-string: glusterfs 3.1.4
/lib/libc.so.6[0x7ff4c459af60]
/lib/libpthread.so.0(pthread_spin_lock+0x0)[0x7ff4c48c7630]
/usr/lib/libglusterfs.so.0(iobref_size+0x17)[0x7ff4c5142977]
/usr/lib/glusterfs/3.1.4/xlator/performance/io-cache.so(ioc_page_destroy+0x26)[0x7ff4c274b9e6]
/usr/lib/glusterfs/3.1.4/xlator/performance/io-cache.so(__ioc_inode_flush+0x2e)[0x7ff4c2748a2e]
/usr/lib/glusterfs/3.1.4/xlator/performance/io-cache.so(ioc_inode_flush+0x51)[0x7ff4c2748f51]
/usr/lib/glusterfs/3.1.4/xlator/performance/io-cache.so(ioc_inode_destroy+0xf5)[0x7ff4c274d495]
/usr/lib/glusterfs/3.1.4/xlator/performance/io-cache.so(ioc_forget+0x2f)[0x7ff4c27489ef]
/usr/lib/libglusterfs.so.0[0x7ff4c51316d9]
/usr/lib/libglusterfs.so.0(inode_unref+0x3c)[0x7ff4c51318ec]
/usr/lib/glusterfs/3.1.4/xlator/mount/fuse.so[0x7ff4c36761c5]
/usr/lib/glusterfs/3.1.4/xlator/mount/fuse.so[0x7ff4c367a679]
/lib/libpthread.so.0[0x7ff4c48c2fc7]
/lib/libc.so.6(clone+0x6d)[0x7ff4c463864d]
---------
</bug report>

Comment 1 Anand Avati 2011-07-29 05:31:26 UTC
CHANGE: http://review.gluster.com/25 (Change-Id: Idbec92e3ffb838a0ac866fb42ceb6ee26a0b8a87) merged in release-3.1 by Anand Avati (avati)

Comment 2 Anand Avati 2011-07-29 05:33:36 UTC
CHANGE: http://review.gluster.com/24 (Change-Id: I77e94166d4ad7a9ac87127de840add7278992bf3) merged in release-3.2 by Anand Avati (avati)

Comment 3 Anand Avati 2011-07-29 05:33:45 UTC
CHANGE: http://review.gluster.com/21 (Change-Id: Ifc435c2e289b2a8ceeed2a091e555953af179936) merged in master by Anand Avati (avati)

Comment 4 Anush Shetty 2011-08-21 07:23:56 UTC
There are no testcases to reproduce this bug. So closing this bug after discussing with the developer

Comment 5 Anush Shetty 2011-08-22 06:09:38 UTC
Moving this to "workforme" state