This is mind boggling. 

There is a simple, brain-dead fix that does NOT require the (presumably 
complex) scheduling logic to change one bit. Simply NEVER expose a 
user-facing request to a loading request, if the developer configures it 
that way. Let the scheduler spin up and down instances however it sees fit, 
but don't let a new instance serve requests until it successfully completes 
initialization. 

This was beat to death months ago in a series of threads, but obviously 
resulted in no action.

On Tuesday, December 18, 2012 12:03:19 PM UTC-5, Cesium wrote:
>
> I changed my settings to have 3 resident instances.
>
> I still see long latency when the scheduler creates new instances, rather 
> than using the resident instances.
>
> The GAE scheduler behavior at low request rates is odd, and 
> counterintuitive.
>
> But we knew that didn't we?
> David
>
>

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To view this discussion on the web visit 
https://groups.google.com/d/msg/google-appengine/-/mibjVETUupIJ.
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