Hello Jason,
yesterday i started rbd-nbd in forground mode to see if there are any additional informations.
root@int-nfs-001:/etc/ceph# rbd-nbd map rbd_hdd/int-nfs-001_srv-ceph -d --id nfs
2019-09-11 13:07:41.444534 7ffff7fe1040 0 ceph version 12.2.12 (1436006594665279fe734b4c15d7e08c13ebd777) luminous (stable), process rbd-nbd, pid 14735
2019-09-11 13:07:41.444555 7ffff7fe1040 0 pidfile_write: ignore empty --pid-file
/dev/nbd0
---------
2019-09-11 21:31:03.126223 7fffc3fff700 -1 rbd-nbd: failed to read nbd request header: (33) Numerical argument out of domain
Whats that, have we seen that before? ("Numerical argument out of domain")
Am 10.09.19 um 16:10 schrieb Jason Dillaman:
> [Tue Sep 10 14:46:51 2019] ? __schedule+0x2c5/0x850
> [Tue Sep 10 14:46:51 2019] kthread+0x121/0x140
> [Tue Sep 10 14:46:51 2019] ? xfs_trans_ail_cursor_first+0x90/0x90 [xfs]
> [Tue Sep 10 14:46:51 2019] ? kthread+0x121/0x140
> [Tue Sep 10 14:46:51 2019] ? xfs_trans_ail_cursor_first+0x90/0x90 [xfs]
> [Tue Sep 10 14:46:51 2019] ? kthread_park+0x90/0x90
> [Tue Sep 10 14:46:51 2019] ret_from_fork+0x35/0x40
> Perhaps try it w/ ext4 instead of XFS?
I can try that, but i am skeptical, i am note sure that we are searching on the right place...
Why?
- we run hundreds of heavy use rbd-nbd instances in our xen dom-0 systems for 1.5 years now
- we never experienced problems like that in xen dom0 systems
- as described these instances run 12.2.5 ceph components with kernel 4.4.0+10
- the domU (virtual machines) are interacting heavily with that dom0 are using various filesystems
-> probably the architecture of the blktap components leads to different io scenario : https://wiki.xenproject.org/wiki/Blktap
Nevertheless i will try EXT4 on another system.....
Regards
Marc
_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
