Journals that are too small can cause performance problems; it basically takes away the SSD journal speedup, and forces all writes to go at the speed of the HDD. Once you make the journal big enough to prevent that, there is no benefit to making it larger. There might be a slight performance penalty to making it too large. SSD wear leveling can take advantage of an under-provisioning. It should make things slightly faster when the SSD needs to execute wear leveling operations (ie, not often). Under provisioning also extends the life of the SSD. Putting numbers to those statements... I really couldn't say. On Wed, Oct 29, 2014 at 2:01 PM, Cristian Falcas <cristi.falcas@xxxxxxxxx> wrote: > Hello, > > Will there be any benefit in making the journal the size of an entire ssd disk? > > I was also thinking on increasing "journal max write entries" and > "journal queue max ops". > > But will it matter, or it will have the same effect as a 4gb journal > on the same ssd? > > Thank you, > Cristian Falcas > _______________________________________________ > ceph-users mailing list > ceph-users@xxxxxxxxxxxxxx > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com _______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
 |