Raghavendra G wrote: > Hi Kirby, > > As of now, dht does balancing of storage only during creation of files. > Files which are already created are not moved b/w nodes because of less free > storage. > > During creation dht tries to balance out the storage b/w its children. it > accepts an option min-free-disk which is nothing but the minimum percentage > of disk space on a node needed for dht to store the file on that node. If > the hashed node does not satisfy this criteria, dht stores the actual file > on any node which has minimum percentage of free disk configured and stores > the a pointer to this node in the hashed node. in reply to Raghavendra, above seems clear, but how does this apply to directory's ? lets say that the directory /customer1/personalfiles/ fills up a single brick and a new file is added called /customer1/personalfiles/onceanotherfile.pdf is it the same story for directory's as it is for files? thanks, Randall > > regards, > On Wed, Apr 15, 2009 at 6:27 AM, Kirby Zhou <kirbyzhou at sohu-rd.com> wrote: > >> If a file grows bigger and bigger, how can glusterfs move it between >> bricks? >> The original bricks are full of space, but newly added bricks are nearly >> empty, How can DHT translator deals that situation? >> >> Thanks >> >> >> >> >> >> _______________________________________________ >> Gluster-users mailing list >> Gluster-users at gluster.org >> http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users >> > > > > > ------------------------------------------------------------------------ > > _______________________________________________ > Gluster-users mailing list > Gluster-users at gluster.org > http://zresearch.com/cgi-bin/mailman/listinfo/gluster-users
