Bug #1341
closedCeph mount hangs when OSD and Ceph Client on the same node
0%
Description
Hi guys.
When I tried to run 2 OSD nodes (1-6 OSD, 7-12 OSD) on node1 and node2, (MDS/MON on node3), and run the Ceph client on node2. (i.e., same node as OSD)
I can mount, but as soon as I tried to copy some files, the mount hangs and the system basically halts, and I have to hard shutdown.
It seems that I could never get to work the Client and the OSD on the same node (since version 0.20 I think), is this normal?
I have attached the ceph-error, but let me know if more information is needed.
Thanks
ceph version 0.31 (commit:9019c6ce64053ad515a493e912e2e63ba9b8e278)
Linux ss2 2.6.39.3-37-default #1 SMP Sat Jul 9 09:18:50 UTC 2011 (84b09a0) x86_64 x86_64 x86_64 GNU/Linux
Files
Updated by Greg Farnum almost 13 years ago
- Status changed from New to Won't Fix
Unless you're using btrfs or a very new kernel and glibc (which support the new syncfs syscall), this is never going to work. The Ceph daemons need to call the sync system call, which can do all kinds of badness when that in turn calls a sync on a ceph mount.
Updated by Greg Farnum almost 7 years ago
- Project changed from Ceph to CephFS
- Category deleted (
26)