examples of "high throughput" IdP instances

[David Langenberg]

I'd be curious to see how much a t1.micro did or would do in your
environment.  If it could perform well enough it may be worth maintaining
an AMI that small schools could leverage to get an IdP up and running
quickly and free (for the first year at least).

Dave


On Fri, Dec 27, 2013 at 9:35 AM, Nate Klingenstein <ndk at internet2.edu>wrote:

>  Just out of curiosity.  I didn't know whether there would be some OS
> overhead or some bottleneck that would make smaller instances run slower or
> faster, different ratios of CPU to RAM and throughput, etc. etc.  It was
> easy enough to drop one from the pool and see what happened(and how many
> requests got stranded).
>
>  The biggest problem with the stock AWS instances is they give you
> ridiculously little disk, and that's almost across the board.
>
>  On Dec 27, 2013, at 6:50 AM, Tom Scavo <trscavo at gmail.com>
>  wrote:
>
> Impressive. May I ask why there's a mixture of medium and large nodes?
>
>
>
> --
> To unsubscribe from this list send an email to
> users-unsubscribe at shibboleth.net
>



-- 
David Langenberg
Identity & Access Management
The University of Chicago
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://shibboleth.net/pipermail/users/attachments/20131227/125c3e55/attachment.html