On Thu, Oct 20, 2011 at 1:46 AM, David Howells <dhowells@xxxxxxxxxx> wrote: > Mark Moseley <moseleymark@xxxxxxxxx> wrote: > >> I left the existing cache in place. For a few hours, it was culling > > That will be whilst the inode cache was filling, I suspect. > >> Is there anything I can do to verify whether the objects are indeed >> pinned? This is a pretty busy box. The nfs inode cache is quite large >> (from slabtop): > > Hmmm... Can you get me a dump of /proc/fs/fscache/stats to look at? > > The "Objects:" and "Relinqs:" lines are the most interesting. On the first > line avl=N shows the number of objects that are in the "available" state - > ie. are live for caching. > > Also, can you do: > > df -i /path/to/cache/partition > > to get the number of inodes available and used. # df /var/cache/fscache/ Filesystem 1K-blocks Used Available Use% Mounted on /dev/sdb6 29338652 16148968 11699352 58% /var/cache/fscache # df -i /var/cache/fscache/ Filesystem Inodes IUsed IFree IUse% Mounted on /dev/sdb6 1864128 339163 1524965 19% /var/cache/fscache -- Linux-cachefs mailing list Linux-cachefs@xxxxxxxxxx https://www.redhat.com/mailman/listinfo/linux-cachefs
