[gpfsug-discuss] gpfs client cluster, lost quorum, ccr issues
Renata Maria Dart
renata at slac.stanford.edu
Wed Jun 27 20:30:33 BST 2018
Hi, any gpfs commands fail with:
root at ocio-gpu01 ~]# mmlsmgr
get file failed: Not enough CCR quorum nodes available (err 809)
gpfsClusterInit: Unexpected error from ccr fget mmsdrfs. Return code: 158
mmlsmgr: Command failed. Examine previous error messages to determine cause.
The two "working" nodes are arbitrating. Also, they are using ccr,
so doesn't that mean the primary/secondary setup for a client cluster
doesn't apply?
Renata
On Wed, 27 Jun 2018, Iban Cabrillo wrote:
>Hi, Have you check if there is any manager node available?
>#mmlsmgr
>
>If not could you try to asig a new cluster/gpfs_fs manager.
>
>Mmchmgr gpfs_fs. Manager_node
>Mmchmgr. -c. Cluster_manager_node
>
>Cheers.
>
>
More information about the gpfsug-discuss
mailing list