On Thu, Nov 24, 2016 at 03:58:01PM +0000, Ankireddypalle Reddy wrote: > Hi, > Gluster does not seem to be supporting hole punch support correctly. This might be a limiting factor for people switching from hardware based storage to glusterfs for archival/backup use cases. In these use cases hole punch support is one of the key deciding factors. I request gluster developers to expedite their efforts in this direction. Hi Ram, this is something we should be able to fix somehow. There is a similar bug reported for this already: fallocate + punch_hole used instead of fallocate + zero_range in glfs_discard() https://bugzilla.redhat.com/show_bug.cgi?id=1327857 From a cursory look, libgfapi supports punching holes through the glfs_discard() function. FUSE also has an implementation for fallocate(). How are you testing this, and what is the behaviour you see? Thanks, Niels
Attachment:
signature.asc
Description: PGP signature
_______________________________________________ Gluster-devel mailing list Gluster-devel@xxxxxxxxxxx http://www.gluster.org/mailman/listinfo/gluster-devel
