So gossip behaves reasonably well up into the ~1000 or so hosts per cluster.
Repairs can get hard to schedule with ~256 vnodes and large numbers of nodes. It's do-able, it just requires a bit of extra work. Personally, I wouldn't run over 60 hosts with 256 vnodes, but I know from JIRA that some people go quite a bit above that. Going from 100 -> 150 is probably not going to be a deal breaker. I expect you'll see quite a bit of compaction as you bootstrap/rebuild the new hosts, but that's probably true for you now. On Wed, Mar 13, 2019 at 5:27 PM Ahmed Eljami <ahmed.elj...@gmail.com> wrote: > Yes, 256 vnodes > > Le mer. 13 mars 2019 à 17:31, Jeff Jirsa <jji...@gmail.com> a écrit : > >> Do you use vnodes? How many vnodes per machine? >> >> -- >> Jeff Jirsa >> >> >> On Mar 13, 2019, at 3:58 PM, Ahmed Eljami <ahmed.elj...@gmail.com> wrote: >> >> Hi, >> >> We are planning to add a third datacenter to our cluster (already has 2 >> datacenter, every datcenter has 50 nodes, so 100 nodes in total). >> >> My fear is that an important number of nodes per cluster (> 100) could >> cause a lot of problems like gossip duration, maintenance (repair...)... >> >> I know that it depends on use cases, volume of data and many other >> thing, but I would like that you share your experiences with that. >> >> Thx >> >> >> >>