Yes, operations within the OSD are ordered on a per-PG basis, a read will be blocked until the writes are applied.
From: ceph-users [mailto:ceph-users-boun...@lists.ceph.com] On Behalf Of Sam Huracan Sent: Tuesday, January 26, 2016 2:26 PM To: Loris Cuoghi Cc: ceph-users@lists.ceph.com Subject: Re: [ceph-users] Ceph Write process Thanks Loris, So after client receiving ACK, if client makes a read request to this object immediately , does it have to wait for object written to file store, or read directly from journal? 2016-01-25 17:12 GMT+07:00 Loris Cuoghi <l...@stella-telecom.fr<mailto:l...@stella-telecom.fr>>: Le 25/01/2016 11:04, Sam Huracan a écrit : > Hi Cephers, > > When an Ceph write made, does it write to all File Stores of Primary OSD > and Secondary OSD before sending ACK to client, or it writes to journal > of OSD and sending ACK without writing to File Store? > > I think it would write to journal of all OSD, so using SSD journal will > increase write IOPS. Hi That's it, writes are acknowledged as soon as they're written to each OSD's journal. Loris _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com<mailto:ceph-users@lists.ceph.com> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
