Re: [ceph-users] Ruleset vs replica count

On Thu, Aug 24, 2017 at 6:44 PM, David Turner wrote: >> min_size 1 > STOP THE MADNESS. Search the ML to realize why you should never user a > min_size of 1. This is a (completely understandable) misunderstanding. The "min_size" in a crush rule is a different thing to the

Re: [ceph-users] Ruleset vs replica count

:02 AM To: ceph-us...@ceph.com Subject: [ceph-users] Ruleset vs replica count Hi, In a Multi Datacenter Cluster I have the following rulesets: -- rule ams5_ssd { ruleset 1 type replicated min_size 1 max_size 10 step take ams5-ssd step

Re: [ceph-users] Ruleset vs replica count

] Ruleset vs replica count > min_size 1 STOP THE MADNESS. Search the ML to realize why you should never user a min_size of 1. I'm curious as well as to what this sort of configuration will do for how many copies are stored between DCs. On Thu, Aug 24, 2017 at 1:03 PM Sinan Polat

Re: [ceph-users] Ruleset vs replica count

> min_size 1 STOP THE MADNESS. Search the ML to realize why you should never user a min_size of 1. I'm curious as well as to what this sort of configuration will do for how many copies are stored between DCs. On Thu, Aug 24, 2017 at 1:03 PM Sinan Polat wrote: > Hi, > > > > In

[ceph-users] Ruleset vs replica count

Hi, In a Multi Datacenter Cluster I have the following rulesets: -- rule ams5_ssd { ruleset 1 type replicated min_size 1 max_size 10 step take ams5-ssd step chooseleaf firstn 2 type host step emit step