Hi, We are planing to test and use ceph object storage(no RBD/no cephFS), but before that we have some questions: 1. How much time it will take to be ready for processing client request if we restart the the whole cluster(MON+OSDs). In this case how cluster map will create(OSD dependency). 2. If we have 3 MON and and 1 MON is down then can we read/write object? if no then what will be the solution? 3. Is there a way like haystack... where we can append into same file 4. Inside osd/current directory we are creating a no. of directory for storing object. There is some restriction(ex. - ext3) - we cannot create more than ~33000 no. of directories. Are we handling those conditions? 5. what will happen if one osd down(Primary) and up after 2 hrs? And within this 2 hrs, we assuming that lot of read/write operation also going on.
Thanks, Upendra Yadav
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
