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:[email protected]] On Behalf Of Sam Huracan Sent: Tuesday, January 26, 2016 2:26 PM To: Loris Cuoghi Cc: [email protected] 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 <[email protected]<mailto:[email protected]>>: 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 [email protected]<mailto:[email protected]> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
