Will there be a well documented strategy / method for
changing block sizes
on existing clusters? Is there anything that could be done to optimize or
assist clusters in the cut over?
On Tue, Feb 16, 2021 at 3:41 AM Loïc Dachary <loic(a)dachary.org> wrote:
Hi Josh :-)
Thanks for the update: this is great news and I look forward to using this
once Pacific is released.
On 16/02/2021 00:43, Josh Durgin wrote:
We have developed a strategy in pacific - reducing the min_alloc_size
for HDD to
4KB by default.
Igor Fedotov did a lot of investigation and benchmarking, and came up
with some improvements to bluestore  to make this change have
little performance impact (it even increases performance in many cases).
On 2/14/21 9:21 AM, Loïc Dachary wrote:
> Reading Karan's blog post about benchmarking the insertion of billions
objects to Ceph via S3 / RGW from last year, it reads:
>> we decided to lower bluestore_min_alloc_size_hdd to 18KB and re-test.
represented in chart-5, the object creation rate found to be notably
reduced after lowering the bluestore_min_alloc_size_hdd parameter from 64KB
(default) to 18KB. As such, for objects larger than the
bluestore_min_alloc_size_hdd , the default values seems to be optimal,
smaller objects further require more investigation if you intended to
reduce bluestore_min_alloc_size_hdd parameter.
> There also is a mail thread dated 2018 on this topic as well, with the
conclusion although using RADOS directly and not RGW. I read the
RGW data layout page in the documentation and concluded that by default
every object inserted with S3 / RGW will indeed use at least 64kb. A pull
request from last year seems to confirm it and also suggests modifying
bluestore_min_alloc_size_hdd has adverse side effects.
> That being said, I'm curious to know if people developed strategies to
cope with this overhead. Someone mentioned packing objects together client
side to make them larger. But maybe there are simpler ways to do the same?
>  https://www.redhat.com/en/blog/scaling-ceph-billion-objects-and-beyond
Loïc Dachary, Artisan Logiciel Libre
ceph-users mailing list -- ceph-users(a)ceph.io
To unsubscribe send an email to ceph-users-leave(a)ceph.io