Re: Cost- and Powerefficient OSD-Nodes

[Frank Brendel <frank.brendel@xxxxxxxxxxx>]

If you don't need LACP you could use round-robin bonding mode.
With 4x1Gbit NICs you can get a bandwidth of 4Gbit per TCP connection.

Either create trunks on stacked switches (e.g. Avaya) or use single switches (e.g. HP 1810-24) and a locally managed MAC address per node/bond.
The latter is somewhat sophisticated because you have to monitor the NICs. If the link or the NIC itself on one node goes down you have to remove the corresponding slaves on the other nodes.

To make it really cheap you could configure VLANs to get 4Gbit or more per connection with two switches, for testing of course ;-)

Am 28.04.2015 um 23:01 schrieb Patrick Hahn:

I haven't used them myself but switching silicon is getting pretty cheap nowadays: 

http://whiteboxswitch.com/products/edge-core-as5610-52x

There's similar products (basically the same Broadcom ASIC) from Quanta and I think Supermicro announced one recently as well.  

They're not as plug and play since they run linux but you have a lot more options for tweaking. 

Thanks,

Patrick

On Tue, Apr 28, 2015 at 4:35 PM, Dominik Hannen <hannen@xxxxxxxxx> wrote:

> FYI, most Juniper switches hash LAGs on IP+port, so you'd get somewhat
> better performance than you would with simple MAC or IP hashing.  10G is
> better if you can afford it, though.

interesting, I just read up about the topic, those Juniper-Switches seem to
be a nice pick then.

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

--

Patrick Hahn

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com

_______________________________________________
ceph-users mailing list
ceph-users@xxxxxxxxxxxxxx
http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com