hi mark, what kind of caching is actually needed here? i assume a 2 replica pool for writes (don't want to loose the data will it has not been flushed back to the EC pools) and a 1 replica for reading (no additional write IOs and network traffic while reading, no data loss if the read cache pool fails). but probably the read-cache has to be the same as the write cache (eg when people want to modify a file). stijn On 07/08/2014 05:24 PM, Stijn De Weirdt wrote: > hi mark, > > thanks for clarifying it a bit. we'll certainly have a look at the > caching tier setup. > > > stijn > > On 07/08/2014 01:53 PM, Mark Nelson wrote: >> On 07/08/2014 04:28 AM, Stijn De Weirdt wrote: >>> hi all, >>> >>> one of the changes in the 0.82 release (accoridng to the notes) is: >>> >>> mon: prevent EC pools from being used with cephfs >>> >>> can someone clarify this a bit? cephfs with EC pools make no sense? now? >>> ever? or is it just not recommended (i'm also interested in the >>> technical reasons behind it) >> >> There are limitations regarding the operations that are supported by EC >> pools, so you can't directly use them for RBD/CephFS. Potentially you >> can put a replication based cache tier pool in front of an EC base pool >> which should work. I've tested this kind of setup with RBD and it >> appears to work fine. Currently the end result is pretty slow, but we >> may be able to improve it with time. >> >> An interesting use case to be sure. :) >> >> Mark >> >>> >>> many thanks >>> >>> stijn >>> _______________________________________________ >>> ceph-users mailing list >>> ceph-users at lists.ceph.com >>> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> >> _______________________________________________ >> ceph-users mailing list >> ceph-users at lists.ceph.com >> http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >> >> > _______________________________________________ > ceph-users mailing list > ceph-users at lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com > >
 |