On Mon, Apr 14, 2014 at 3:16 PM, Dan Van Der Ster <[email protected]> wrote: > > Hi, > > On 14 Apr 2014 at 00:43:01, Yan, Zheng > ([email protected](mailto:[email protected])) wrote: >> On Mon, Apr 14, 2014 at 2:54 AM, Qing Zheng wrote: >> > Hi - >> > >> > We are currently evaluating CephFS's metadata scalability >> > and performance. One important feature of CephFS is its support >> > for running multiple "active" mds instances and partitioning huge >> > directories into small shards. >> > >> > We use mdtest to simulate workloads where multiple parallel client >> > processes will keep inserting empty files into several large directories. >> > We found that CephFS is only able to run for the first 5-10 mins, >> > and then stop making progress -- the clients' "creat" call no longer >> > return. >> > >> > We were using Ceph 0.72 and Ubuntu 12.10 with kernel 3.6.6. >> > Our setup consisted of 8 osds, 3 mds, and 1 mon. All mds were active, >> > instead of >> > standby, and they were all configured to split directories once the >> > directory >> > size is greater than 2k. We kernel (not fuse) mounted CephFS on all 8 >> > osd nodes. >> >> 3.6 kernel is too old for cephfs. please use kernel compiled from >> testing branch https://github.com/ceph/ceph-client and the newest >> development version of Ceph. There are large number of fixes for >> directory fragment and multimds. > > Does the dev version of the MDS rely on any dev features in RADOS? ie. can we > use a dumpling or emperor cluster with dev MDS? >
dev version MDS rely on a new OSD operation. It can't work with old OSD. > And what is the status of fuse cephfs in the new dev version? Is that up to > date with the latest kernel client? > dev version ceph-fuse supports directory fragment and multimds, but still less stable than kclient Regards Yan, Zheng > Cheers, Dan > > -- Dan van der Ster || Data & Storage Services || CERN IT Department -- > >> >> >> Regards >> Yan, Zheng _______________________________________________ ceph-users mailing list [email protected] http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
