Le 08/12/2007 à 00:15:26+0530, Anand Avati a écrit Hi > 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. Yes I known and I understand. But what I mean is WHEN le local disk is full at 99%, I start A NEW write...and gluster write on local disk until the disk is full at 100% and give me I «no left space» error. Regrads. > > 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 ? > > -- Albert SHIH Observatoire de Paris Meudon SIO batiment 15 Téléphone : 01 45 07 76 26 Heure local/Local time: Ven 7 déc 2007 21:52:39 CET
