Hello Mike, there is no problem adding 100 OSDs at the same time if your cluster is configured correctly. Just add the OSDs and let the cluster slowly (as fast as your hardware supports without service interruption) rebalance.
-- Martin Verges Managing director Mobile: +49 174 9335695 E-Mail: martin.ver...@croit.io Chat: https://t.me/MartinVerges croit GmbH, Freseniusstr. 31h, 81247 Munich CEO: Martin Verges - VAT-ID: DE310638492 Com. register: Amtsgericht Munich HRB 231263 Web: https://croit.io YouTube: https://goo.gl/PGE1Bx Am Do., 30. Mai 2019 um 02:00 Uhr schrieb Mike Cave <mc...@uvic.ca>: > Good afternoon, > > > > I’m about to expand my cluster from 380 to 480 OSDs (5 nodes with 20 disks > per node) and am trying to determine the best way to go about this task. > > > > I deployed the cluster with ceph ansible and everything worked well. So > I’d like to add the new nodes with ceph ansible as well. > > > > The issue I have is adding that many OSDs at once will likely cause a huge > issue with the cluster if they come in fully weighted. > > > > I was hoping to use ceph ansible and set the initial weight to zero and > then gently bring them up to the correct weight for each OSD. > > > > I will be doing this with a total of 380 OSDs over the next while. My plan > is to bring in groups of 6 nodes (I have six racks and the map is > rack-redundant) until I’m completed on the additions. > > > > In dev I tried bringing in a node while the cluster was in ‘no rebalance’ > mode and there was still significant movement with some stuck pgs and other > oddities until I reweighted and then unset ‘no rebalance’. > > > > I’d like a s little friction for the cluster as possible as it is in heavy > use right now. > > > > I’m running mimic (13.2.5) on CentOS. > > > > Any suggestions on best practices for this? > > > > Thank you for reading and any help you might be able provide. I’m happy to > provide any details you might want. > > > > Cheers, > > Mike > _______________________________________________ > ceph-users mailing list > ceph-users@lists.ceph.com > http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com >
_______________________________________________ ceph-users mailing list ceph-users@lists.ceph.com http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
