On Mon, Jul 14, 2014 at 7:23 AM, Alexander Botov <[email protected]>
 wrote:

> No, the others are not close to their memory limit. We have one resident
> instance running, it's not at all close to the memory limit
> I can't say for sure whether the latency periods are longer or not - gut
> feel is that they are, at least for a period of time
>


My suspicion is (and I have no way to verify this; you'd have to ask a
Googler to confirm) is that once a single instance exceeds its' instance
RAM limit, the scheduler shuts down, then reopens a new instance in a new
location within the physical infrastructure. To help reduce latency (here
comes the speculation), the scheduler then shuts down the other instances
and reopens them closer to the new location.

I wouldn't worry about it too much; I see this phenomenon happen
occasionally, as well as other strangeness with instance restarting. If you
look back in this forum's archives you'll see similar stories. Most likely
the scheduler has decided that you'll get better performance if it moves
you to a different location; if you're not seeing any major latency or RPC
issues, I'd ignore it for now and periodically monitor the issue.


-----------------
-Vinny P
Technology & Media Consultant
Chicago, IL

App Engine Code Samples: http://www.learntogoogleit.com

-- 
You received this message because you are subscribed to the Google Groups 
"Google App Engine" group.
To unsubscribe from this group and stop receiving emails from it, send an email 
to [email protected].
To post to this group, send email to [email protected].
Visit this group at http://groups.google.com/group/google-appengine.
For more options, visit https://groups.google.com/d/optout.

Reply via email to