On Wed, 18 May 2016 08:56:51 +0000 Van Leeuwen, Robert wrote: > >We've hit issues (twice now) that seem (have not > >figured out exactly how to confirm this yet) to be related to kernel > >dentry slab cache exhaustion - symptoms were a major slow down in > >performance and slow requests all over the place on writes, watching > >OSD iostat would show a single drive hitting 90+% util for ~15s with a > >bunch of small reads and no writes. > > Not specifically ceph related but I hit the same issue with Swift some > time ago. I created a blogpost then about the issue and how to > troubleshoot it (there are some useful xfs stats) > http://engineering.spilgames.com/openstack-swift-lots-small-files/ > > tldr: In the end we moved to nodes with smaller disks and more memory > Ayup, I keep telling people to watch their slab, enough RAM to keep all your important bits in memory can be a game changer. Christian -- Christian Balzer Network/Systems Engineer chibi@xxxxxxx Global OnLine Japan/Rakuten Communications http://www.gol.com/ _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |