[GE users] implementation opinion / suggestions

dougalb dougal.lists at gmail.com
Thu Jan 28 20:57:27 GMT 2010

    [ The following text is in the "utf-8" character set. ]
    [ Your display is set for the "ISO-8859-10" character set.  ]
    [ Some characters may be displayed incorrectly. ]

On Thu, Jan 28, 2010 at 7:38 PM, jesperkrogh <jesper at krogh.cc> wrote:
> craffi wrote:
>> I would never use classic spooling on a cluster this size if we did not
>> have the Isilon storage gear. Every NFS client uses a different IP
>> address to speak to the NFS server and the algorithm-based load
>> balancing is done via using arp calls to migrate the NFS IP endpoints
>> between Isilon storage nodes as needed. The end result is we can drive
>> 24 GigE ports at wire speed while servicing a single-namespace NFS
>> volume. Works great.
> 10GbitE can easily be served using a standard linux kernel and a 10GbitE
> NIC directly in the server. We use a  Sun X4600 but it is by no means
> overloaded filling the link. If needed I would just plug a second
> 10GbitE NIC into the server and put them in a bond. I dont doubt that
> the Isilon stuff is far better, but taken the price into the equation
> many of us "small" users can go that way.
> Then its basically up to whatever SAN / Diskarray you plug in.

I think the point is not the available bandwidth but the available
IOPS and disk throughput. Using 10GbitE will not help if you can only
push 100MB/sec from your disk(s).

> --
> Jesper
> ------------------------------------------------------
> http://gridengine.sunsource.net/ds/viewMessage.do?dsForumId=38&dsMessageId=241559
> To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].


To unsubscribe from this discussion, e-mail: [users-unsubscribe at gridengine.sunsource.net].

More information about the gridengine-users mailing list