According to my tests there is difference in performance between usual named
buckets (test, test01, test02), uuid-named buckets (like
'7c9e4a81-df86-4c9d-a681-3a570de109db') or just date ('2016-09-20-16h').
Getting ~3x more upload performance (220 uploads\s vs 650 uploads\s) with
SSD-backed indexes or 'blind buckets' feature enabled.
> On Sep 21, 2016, at 1:28 PM, Félix Barbeira <fbarbe...@gmail.com> wrote:
> Regarding to Amazon S3 documentation, it is advised to insert a bit of random
> chars in the bucket name in order to gain performance. This is related to how
> Amazon store key names. It looks like they store an index of object key names
> in each region.
> My question is: is this also a good practice in a ceph cluster where all the
> nodes are in the same datacenter? It is relevant in ceph the name of the
> bucket to gain more performance? I think it's not, because all the data is
> spread in the placement groups all over the osd nodes, no matter what bucket
> name he got. Can anyone confirm this?
> Thanks in advance.
> Félix Barbeira.
> ceph-users mailing list
ceph-users mailing list