We easily see line rate sequential io of most disk.
I would say that 150GB/s with 40G networking and a minimum of 20 host is no
problem.
Tyler Bishop
Chief Technical Officer
513-299-7108 x10
[email protected]
If you are not the intended recipient of this transmission you are notified
that disclosing, copying, distributing or taking any action in reliance on the
contents of this information is strictly prohibited.
From: "Nick Fisk" <[email protected]>
To: "Gerald Spencer" <[email protected]>, [email protected]
Sent: Thursday, September 29, 2016 11:04:45 AM
Subject: Re: [ceph-users] Interested in Ceph, but have performance questions
Hi Gerald,
I would say it’s definitely possible. I would make sure you invest in the
networking to make sure you have enough bandwidth and choose disks based on
performance rather than capacity. Either lots of lower capacity disks or SSD’s
would be best. The biggest challenge may be around the client interface (ie
block,object,file) and if you can get it to create the parallelism required to
drive the underlying RADOS cluster.
With my 60 disk cluster I can max out a 10G Nic with both read and writes.
Ceph’s performance will increase with scale, so I don’t see why with 40G
networking those figures wouldn’t be achievable.
Nick
From: ceph-users [mailto:[email protected]] On Behalf Of Gerald
Spencer
Sent: 29 September 2016 15:38
To: [email protected]
Subject: [ceph-users] Interested in Ceph, but have performance questions
Greetings new world of Ceph,
Long story short, at work we perform high throughput volumetric imaging and
create a decent chunk of data per machine. We are about to bring the next
generation of our system online and the IO requirements will outpace our
current storage solution (jbod using zfs on Linux). We are currently searching
for a template-able scale out solution that we can add as we bring each new
system online starting in a few months. There are several quotes floating
around from all of the big players, but the buy in on hardware and software is
unsettling as they are a hefty chunk of change.
The current performance we are currently estimating is per machine:
- simultaneous 30Gbps read and 30Gbps write
- 180 TB capacity (roughly a two day buffer into a public cloud)
So our question is: are these types of performances possible using Ceph? I
haven't found any benchmarks of this nature beyond
https://www.mellanox.com/related-docs/whitepapers/WP_Deploying_Ceph_over_High_Performance_Networks.pdf
Which claims 150GB/s? I think perhaps they meant 150Gb/s (150 1Gbps clients).
Cheers,
Gerald Spencer
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
_______________________________________________
ceph-users mailing list
[email protected]
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
