[Gluster-devel] Server-side AFR + Failover and mixed server/client-side AFR
Krishna Srinivas
krishna at zresearch.com
Wed May 7 08:31:21 UTC 2008
On Tue, May 6, 2008 at 9:45 PM, Derek Price <derek at ximbiot.com> wrote:
> Krishna Srinivas wrote:
>
> >
> > > > Is this an issue in server-side-only AFR? I have two servers which
> are also
> > > > clients of themselves, and they both list their local subvolume first
> and
> > > > remote subvolume second. Is this a problem? What are the possible
> > > > consequences of this?
> > >
> > > It will be a problem. The "first" subvol is always the "lock" server.
> > > Consider a case where you are creating a file simultaneously
> > > on two clients, only one of them should succeed. If AFR's
> > > subvols order are not same, chances are that both client
> > > returns success for file creation with same name.
> > >
> >
> > Hence you have "option read-subvlume" to speeden the
> > read() calls so that it can be done from local subvol.
> >
>
> So, what happens if the "lock" server is the one that goes down? Will that
> render the whole AFR cluster inoperable, at least for writes?
>
If first server is down, the second one is tried and so on. The cluster remains
operable.
Krishna
> Why not arrange some sort of voting system for AFR locks, where no specific
> server, but rather half of the listed servers (maybe the first server listed
> gets an extra vote in the case of an even number of servers) have to agree
> to assign the lock (and increment the version # without receiving the data).
> Then writes could also be done locally and synchronized at leisure.
>
> Derek
> --
> Derek R. Price
> Solutions Architect
> Ximbiot, LLC <http://ximbiot.com>
> Get CVS and Subversion Support from Ximbiot!
>
> v: +1 248.835.1260
> f: +1 248.246.1176
>
More information about the Gluster-devel
mailing list