Bug 762741 (GLUSTER-1009) - cd into the mount point hangs with error-gen
Summary: cd into the mount point hangs with error-gen
Keywords:
Status: CLOSED WORKSFORME
Alias: GLUSTER-1009
Product: GlusterFS
Classification: Community
Component: replicate
Version: 3.0.4
Hardware: All
OS: Linux
low
medium
Target Milestone: ---
Assignee: shishir gowda
QA Contact:
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2010-06-18 11:33 UTC by Anush Shetty
Modified: 2015-12-01 16:45 UTC (History)
4 users (show)

Fixed In Version:
Doc Type: Bug Fix
Doc Text:
Clone Of:
Environment:
Last Closed:
Regression: ---
Mount Type: ---
Documentation: ---
CRM:
Verified Versions:


Attachments (Terms of Use)
Client process state dump (169.91 KB, application/octet-stream)
2010-06-18 08:34 UTC, Anush Shetty
no flags Details

Description Anush Shetty 2010-06-18 08:34:49 UTC
Created attachment 233 [details]
XF86Config

Comment 1 Anush Shetty 2010-06-18 11:33:11 UTC
While running dbench on 1 screen, and cd-ing into the mount point hangs

It was a 4 subvolume dist-replicate with all the 4 subvolumes being error-gen subvolumes

Client log:

[2010-06-18 16:56:58] T [fuse-bridge.c:2528:fuse_xattr_cbk] glusterfs-fuse: 4387: GETXATTR() /touch123/clients/client4/filler.000 => 0
[2010-06-18 16:56:58] T [fuse-bridge.c:2528:fuse_xattr_cbk] glusterfs-fuse: 4389: GETXATTR() /touch123/clients/client3/filler.000 => 0
[2010-06-18 16:56:58] T [fuse-bridge.c:1964:fuse_write] glusterfs-fuse: 4390: WRITE (0x23452d0, size=65536, offset=0)
[2010-06-18 16:56:58] T [fuse-bridge.c:1964:fuse_write] glusterfs-fuse: 4391: WRITE (0x22fab60, size=65536, offset=0)
[2010-06-18 16:56:58] T [fuse-bridge.c:1912:fuse_writev_cbk] glusterfs-fuse: 4378: WRITE => 1/1,65534/0
[2010-06-18 16:56:58] T [client-protocol.c:1583:client_writev] client1: (4065206): failed to get fd ctx. EBADFD
[2010-06-18 16:56:58] E [error-gen.c:1125:error_gen_writev] eg2: unwind(-1, Is a directory)
[2010-06-18 16:56:58] W [fuse-bridge.c:1919:fuse_writev_cbk] glusterfs-fuse: 4390: WRITE => -1 (Is a directory)
[2010-06-18 16:56:58] T [client-protocol.c:1583:client_writev] client1: (4065178): failed to get fd ctx. EBADFD
[2010-06-18 16:56:58] T [fuse-bridge.c:2062:fuse_release] glusterfs-fuse: 4392: RELEASE 0x23452d0 (FLUSH implied)
[2010-06-18 16:56:58] T [fuse-bridge.c:2062:fuse_release] glusterfs-fuse: 4393: RELEASE 0x232ec10 (FLUSH implied)
[2010-06-18 16:56:58] T [fuse-bridge.c:1912:fuse_writev_cbk] glusterfs-fuse: 4384: WRITE => 1/1,65534/0
[2010-06-18 16:56:58] T [client-protocol.c:1921:client_fxattrop] client2: (4065196): failed to get fd ctx. returning EBADFD
[2010-06-18 16:56:58] T [fuse-bridge.c:1912:fuse_writev_cbk] glusterfs-fuse: 4391: WRITE => 65536/65536,0/655360
[2010-06-18 16:56:58] T [fuse-bridge.c:1664:fuse_create_cbk] glusterfs-fuse: 4385: CREATE() /touch123/clients/client8/filler.000 => 0x2331790 (ino=4065240)
[2010-06-18 16:56:58] T [client-protocol.c:1710:client_flush] client1: (4065190): failed to get fd ctx. EBADFD
[2010-06-18 16:56:58] T [fuse-bridge.c:1152:fuse_err_cbk] glusterfs-fuse: 4393: FLUSH() ERR => 0
[2010-06-18 16:56:58] T [fuse-bridge.c:2062:fuse_release] glusterfs-fuse: 4394: RELEASE 0x2330f40 (FLUSH implied)
[2010-06-18 16:56:58] T [fuse-bridge.c:1912:fuse_writev_cbk] glusterfs-fuse: 4388: WRITE => 1/1,65534/0
[2010-06-18 16:56:58] T [fuse-bridge.c:1152:fuse_err_cbk] glusterfs-fuse: 4394: FLUSH() ERR => 0
[2010-06-18 16:56:58] T [fuse-bridge.c:2062:fuse_release] glusterfs-fuse: 4395: RELEASE 0x2331790 (FLUSH implied)
[2010-06-18 16:56:58] E [error-gen.c:1161:error_gen_flush] eg1: unwind(-1, No such file or directory)
[2010-06-18 16:56:58] T [fuse-bridge.c:1152:fuse_err_cbk] glusterfs-fuse: 4395: FLUSH() ERR => 0
[2010-06-18 16:56:58] T [fuse-bridge.c:2062:fuse_release] glusterfs-fuse: 4396: RELEASE 0x22fab60 (FLUSH implied)

Comment 2 shishir gowda 2010-11-16 07:18:43 UTC
While running dbench in a loop, with bricks having error-gen trans, cd'ing into mnt point multiple time works for me in 3.1.1.qa7.


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