On Mon, Aug 13, 2012 at 8:06 AM, Johan Euphrosine <[email protected]> wrote:
>
>> I tried both.  Going ab -> frontend -> backend is _much_ slower than
>> going directly to a backend.
>
> And the numbers you posted were for hitting directly the vps instance? or
> urlfetch from a frontend?

I'm not sure which exact numbers you are referring to.  The VPS tests
run 'ab' on the same VPS running the server.  The 'wh-test' noop tests
ran 'ab' across a 30Mbit link with fairly low latency to
ghs.google.com... basically the best connection I had available.

Given that these are high-concurrency tests, I wouldn't expect latency
to be a significant issue - there's a large pending backlog on the
server in each case.

Jeff
(sorry, I've been travelling in internet dark zones for the last several days)

-- 
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