What do you mean 'it is not really down"? Does the process run? If yes, then had the process been bound to its port (netstat check) ? If yes, then my next guess is a firewall issue that prevents monitors for reaching each other. If no, then check the logs for the cause. One possible case is that you run out of file descriptors. On 27 October 2016 at 04:56, Rui Xie <jerry.xr86@xxxxxxxxx> wrote: > Hi: > Sometimes when i use ceph -s to query cluster status, it shows > all mons down (Hammer), but in fact monitor is not really down. from > the code it seems ceph -s not wait elect finish, so maybe quorum is > empty at that time? > -- > To unsubscribe from this list: send the line "unsubscribe ceph-devel" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe ceph-devel" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
