> > On 10/20/2015 08:41 AM, Robert LeBlanc wrote: >> >> Given enough load, that fast Jornal will get filled and you will only be >> as fast as the back disk can flush (and at the same time service reads). >> That the the situation we are in right now. We are still seeing better >> performance than a raw spindle, but only 150 IOPs, not 15000 IOPS that >> the SSD can do. You are still ultimately bound by the back end disk. >> >> Robert LeBlanc >>
This is true. However I've seen this happening in "enterprise-grade" storage systems, where you have an amount of cache which is very quick to write. However when that finishes you can go to write through mode or even worse in to back-to-back mode (think sync write IO). However given the cluster size, the way ceph works, replication factors, etc, the volume you need to write at once can be very big, and easily grown with more OSDs/nodes. OTOH worst case you are exactly where you started: HDD performance. Also you can start doing "smart" stuff, like allowing small random IO into the journal, but coalescing into big writes to the back end filesystem. If there are any problems then you can just replay through the journal. _______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com