On Mon, Sep 28, 2015 at 12:39 PM, John Spray <jspray@xxxxxxxxxx> wrote: > On Mon, Sep 28, 2015 at 11:08 AM, Burkhard Linke > <Burkhard.Linke@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx> wrote: >> Hi, >> >> I've created CephFS with a certain data pool some time ago (using firefly >> release). I've added addtional pools in the meantime and moved all data to >> them. But a large number of empty (or very small) objects are left in the >> pool according to 'ceph df': >> >> cephfs_test_data 7 918M 0 45424G 6751721 >> >> The number of objects change if new files are added to CephFS or deleted. >> >> Does the first data pool play a different role and is used to store >> additional information? How can I remove this pool? In the current >> configuration the pool is a burden both to recovery/backfilling (many >> objects) and to performance due to object creation/deletion. > > You can't remove it. The reason is an implementation quirk for > hardlinks: where inodes have layouts pointing to another data pool, > they also write backtraces to the default data pool (whichever was the > first is the default). It's so that when we resolve a hardlink, we > don't have to chase through all data pools looking for an inode, we > can just look it up in the default data pool. > > Clearly this isn't optimal, but that's how it works right now. For > each file you create, you'll get a few hundred bytes-ish written to an > xattr on an object in the default data pool. I've created a feature ticket with some thoughts about how we could improve this situation in the future: http://tracker.ceph.com/issues/13259 John _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |