Thanks William ! I'm really interested in any contention issues between the
compute workload and the storage workload in converged nodes, and how folks
who are doing this are managing that.
On 3 September 2016 at 13:21, William Josefsson
wrote:
> Hi matt, the hardware depends on your workload re
Hi matt, the hardware depends on your workload requirements,
especially when we are talking latency. I do Dell PE R630s for
Controllers, and R730 for Compute/Ceph. The latter got 8x400G Intel
S3610+18xHitachi 1.8T SAS. Depending on the workload sensitivity if
you have DBs and long distance between
; alleviate some of the worst of the memory steal, but it's been one hack
> >> after another to keep it going. I hope to be able to re-architect our
> design
> >> at some point to de-converge Ceph from the compute nodes so that the two
> >> sides can evol
g. I hope to be able to re-architect our design
>> at some point to de-converge Ceph from the compute nodes so that the two
>> sides can evolve separately once more.
>>
>> From: matt.jar...@datacentred.co.uk
>> Subject: Re:[Openstack-operators] Converged infrastructure
>&g
evolve separately once more.
>
> From: matt.jar...@datacentred.co.uk
> Subject: Re:[Openstack-operators] Converged infrastructure
>
> Time once again to dredge this topic up and see what the wider operators
> community thinks this time :) There were a fair amount of summit submissions
> for Bar
n one hack after another to keep it
going. I hope to be able to re-architect our design at some point to
de-converge Ceph from the compute nodes so that the two sides can evolve
separately once more.
From: matt.jar...@datacentred.co.uk
Subject: Re:[Openstack-operators] Converged infrastructure
On Wed, Aug 31, 2016 at 01:01:56PM +0100, Matt Jarvis wrote:
: Like a lot of others we run Ceph, and we absolutely don't converge our
: storage and compute nodes for a variety of performance and management
: related reasons. In our experience, the hardware and tuning
: characteristics of b
