As to a few specifics surrounding what was mentioned above (I'm running Riak
on RHEL 6 on dedicated Rackspace gear):

- RAID 10 if you've got the money for the drives and can work within the
space constraints. Otherwise, RAID 5.
- deadline i/o scheduler
- vm.swappiness = 0
- pay careful attention to the memory tuning of leveldb caches (if you're
using level) based on your fault tolerance requirements, available ram,
number of nodes (check the docs, the recommended formula is in there)
- give a lot of thought to your ring size. Too large with too few physical
nodes and you'll run into performance issues, to small and you'll not be
able to expand. Again, read through all the docs.




--
View this message in context: 
http://riak-users.197444.n3.nabble.com/Riak-Production-cluster-tp4026318p4026344.html
Sent from the Riak Users mailing list archive at Nabble.com.

_______________________________________________
riak-users mailing list
[email protected]
http://lists.basho.com/mailman/listinfo/riak-users_lists.basho.com

Reply via email to