Are you sure about this ? I have noticed that I did indeed get new additional instance, but are their automatic scaling algorithm so simple that uses only average latency time. Maybe this is truth for first 10 instances and then they add additional checking. Although they nowhere display average cpu_ms or api_cpu_ms per instance we can't be sure that they don't collect it and use it. Few bytes per instance and few mathematical operation. I would collect it.
With low latency they are able to easily scale applications on application servers, but with high cpu/api cpu ms they are not able to easily scale datastore or any other api service. So we can't say that 160 ms request with 17000 cpu ms is nice scalable request, but is 160 ms request with 1700 cpu ms ok or not. So is there some good max cpu/api cpu policy that they didn't explained ? Or they did with this yellow and red coloring schema around 700/1000 ms cpu usage. -- You received this message because you are subscribed to the Google Groups "Google App Engine" group. To post to this group, send email to google-appeng...@googlegroups.com. To unsubscribe from this group, send email to google-appengine+unsubscr...@googlegroups.com. For more options, visit this group at http://groups.google.com/group/google-appengine?hl=en.