mirror of
https://github.com/ceph/ceph
synced 2024-12-23 20:03:56 +00:00
9c825ec2c4
When a cluster has few OSDs (less than 50) propose a preselection of values: as long as the number of placement groups is not too small nor too large, it won't make much of a difference anyway. Users of small clusters tend to blindly apply the (OSD*100)/(pool size) formula and worry about chosing a wrong value because they do not understand the tradeoffs. The preselection will hopefully save them from this uncertainty. Add an explanation of how placement groups relate to OSDs, CRUSH and pools to help understand the tradeoffs. Explain the tradeoffs (durability, distribution and resource usages) with examples. Signed-off-by: Loic Dachary <loic-201408@dachary.org> Reviewed-by: Gerben Meijer <infernix@gmail.com> Reviewed-by: Laurent Guerby <laurent@guerby.net> |
||
|---|---|---|
| .. | ||
| api | ||
| configuration | ||
| deployment | ||
| man | ||
| operations | ||
| troubleshooting | ||
| index.rst | ||