[ceph-users] Re: rbd: map failed: rbd: sysfs write failed -- (108) Cannot send after transport endpoint shutdown

On Thu, Jul 1, 2021 at 10:36 AM Oliver Dzombic <info@layer7.net> wrote:

Hi,

mapping of rbd volumes fails clusterwide.

Hi Oliver, Clusterwide -- meaning on more than one client node?

The volumes that are mapped, are ok, but new volumes wont map.

Receiving errors liks:

(108) Cannot send after transport endpoint shutdown

or executing:

#rbd -p CEPH map vm-120-disk-0

will show:

rbd: sysfs write failed In some cases useful info is found in syslog - try "dmesg | tail". rbd: map failed: (108) Cannot send after transport endpoint shutdown

Did you look in dmesg as the error suggests? Please attach the entire dmesg -- it seems doubtful that the existing mappings are OK because it appears that the client instance got blocklisted. Thanks, Ilya