On Fri, Oct 25, 2013 at 9:14 AM, Brad Childs <bdc at redhat.com> wrote: > If the replica took n+1 day to complete, > Gluster's replication is synchronous. So writes are done in parallel. If a server was down and we self-heal it later, we sync both data and mtime. > then returning the highest value would show that the file was modified a > full day after the user considered it modified. Shouldn't it be the lesser > value (if both replicas are consistant)? > > In support of James statement from a user perspective, I may want to know > the last time I wrote some data to a file-- timestamp is metadata for the > user. Showing the date gluster completed replicating the file to another > node is confusing. > > As I described above, that is not the case. Delayed replication (healing) happens for both data and mtime. Avati > > -bc > > > ------------------------------ > > *From: *"Anand Avati" <avati at gluster.org> > *To: *"James" <purpleidea at gmail.com> > *Cc: *"gluster-users" <gluster-users at gluster.org> > *Sent: *Thursday, October 24, 2013 7:12:56 PM > *Subject: *Re: metadata for stat : Should it be identical? > > > Gluster does have logic to always show mtime which is the highest in > value. It is probably a bug if you are witnessing different mtimes at > different times when no writes have happened in between. > > Avati > > > > On Thu, Oct 24, 2013 at 4:31 PM, James <purpleidea at gmail.com> wrote: > >> On Thu, 2013-10-24 at 13:00 -0700, Robert Hajime Lanning wrote: >> > >> > Design philosophy... >> > >> > There is no metadata server. When you look at timestamps in stat, >> > you >> > are seeing the real stat of the file. >> So this raises an interesting point... >> >> > >> > If you have "replica 2" then you have two files. The stat can come >> > from >> > either one. Mtime will be the modification time of the file >> If the replica N files all have slightly different mtimes (it seems they >> usually will because they weren't written at exactly the same time), >> then isn't this a point of inconsistency for a script running on a fuse >> mount which expects the same mtime on a file? >> >> Shouldn't gluster somehow coordinate to set all the files mtimes to be >> consistent to say the last mtime in the replica set? >> >> >> > referenced >> > by the time on the server (not the client.) >> > >> > One of the strengths of GlusterFS is that it does not have the >> > bottleneck/single point of failure of a single metadata server. >> >> >> _______________________________________________ >> Gluster-users mailing list >> Gluster-users at gluster.org >> http://supercolony.gluster.org/mailman/listinfo/gluster-users >> > > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://supercolony.gluster.org/mailman/listinfo/gluster-users > > > -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20131025/2ee2b240/attachment.html>
