[Gluster-users] Gluster not recognizing available space

[Jeffrey Darcy]

> rebooting gluster-0-1 did not solve the problem.  The one
> change I did notice is that now the only place I can write
> is to one of the test directories I had previously created
> which had not appeared on gluster-0-1.  Now, trying to create
> a new directory elsewhere results in the "No space left on device"
> error.

It would be very interesting to look at the trusted.glusterfs.dht
xattrs on (the various copies of) that directory, especially as
compared to the same on some other directory where you *do* get
the ENOSPC error.  It does sound like we think that one brick is
full, even though there's no particular reason we should.  Maybe
misinterpreting some other error?  Using a different filesystem
"under" the one that's currently mounted there, and that one
really *is* full?  That could happen if glusterfsd is starting
before local filesystems are all mounted, for example.