Albert, the scheduler starts using non local nodes only for newly created files. Files which are already created continue to stay on the local node and will not get moved out automatically. avati 2007/12/7, Albert Shih <Albert.Shih@xxxxxxxx>: > > Hi all (again) > > I've put into my gluster-client config > > volume node1 > type storage/posix > option directory /_glusterfs > end-volume > > volume node2 > type protocol/client > option transport-type tcp/client # for TCP/IP transport > option remote-host x.y.z.t > option transport-timeout 30 > option remote-subvolume brick > end-volume > > volume node3 > etc... > > volume unify > type cluster/unify > subvolumes node1....node18 > option scheduler nufa > option nufa.local-volume-name node1 > option nufa.limits.min-free-disk 5% > option namespace ns > end-volume > > In my head that's mean when the local disk of node1 is full at 95% > glusterfs must write on other node. > > But....it's not working. Event the only left 1% gluster always write on > local disk. He jump to another node when they left...nothing. > > Is my config/syntax wrong ? > > Any help > > Regards. > > -- > Albert SHIH > Observatoire de Paris Meudon > SIO batiment 15 > Heure local/Local time: > Ven 7 déc 2007 17:40:48 CET > > > _______________________________________________ > Gluster-devel mailing list > Gluster-devel@xxxxxxxxxx > http://lists.nongnu.org/mailman/listinfo/gluster-devel > -- It always takes longer than you expect, even when you take into account Hofstadter's Law. -- Hofstadter's Law
