Your billing experience seems similar to mine (overly long thread link
below). I have not yet tried Joshua's setting for very low transaction/
sec apps, but there is a suggestion here that Auto/Auto slider
settings may be sub-optimtal for very low QPS apps. What I am really
starting to wonder about is the infrastructure costs this Scheduler
behavior might impose. Constantly starting/stopping instances, and --
most certainly -- starting a buffer instance when only one would ever
be needed (based on QPS history) -- well all those needless instance
startup cpu cycles aren't free. Maybe it is less cost, less resource
intensive than having an idle instance stay alive, I am sure we will
never know. -stevep

Link:
http://groups.google.com/group/google-appengine/browse_thread/thread/9c63e9b38c038a35/95c3c4106bd0b340?lnk=gst&q=stevep#95c3c4106bd0b340

On Jun 1, 5:39 am, Cesium <[email protected]> wrote:
> A few hours ago, one app started to settle down:
>
> > milliseconds per request:
>
> [image: Requests/Second (24 hrs)]
>
> But the app that makes the customers call my f%*#ing cell phone shows:
>
> milliseconds per request:
> [image: Requests/Second (24 hrs)]
>
> It appears both apps showed improvement about 5 hours ago. Yet this one
> still suffers.
>
> So, Google App Engine Team, whatcha' think?
>
> Did you put fresh gerbils in the UPS?
> Antivirals in the bio-neural gel packs?
>
> Could you do it for all my apps?
>
> Don't make me put on my Dire Straits album this early in the day!
> David

-- 
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