On Mon, Aug 13, 2012 at 6:33 AM, Johan Euphrosine <[email protected]> wrote:
>
> Hi Jeff,
>
> Can you share your test methodology ?
>
> I would like to reproduce this testing on my side before escalating the
> results.
>
> In particular I'm wondering if are you calling ab on the backends directly,
> or on App Engine frontend that urlfetch to the backend in an handler?

I tried both.  Going ab -> frontend -> backend is _much_ slower than
going directly to a backend.

You can see the code for testing backends here:

https://github.com/stickfigure/wh-test

There is a bunch of extra code in there you should ignore.  The
important methods are:

/noop - returns static string from frontend
/bnoop - urlfetch from frontend to backend which returns static string
/backend/noop - directly to backend to return static string
/away - just does a urlfetch to a rackspacecloud vps instance

There's pretty much no code here.  Just handlers that do nothing.

Jeff

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To post to this group, send email to [email protected].
To unsubscribe from this group, send email to 
[email protected].
For more options, visit this group at 
http://groups.google.com/group/google-appengine?hl=en.

Reply via email to