The 15 minutes start-up fee seems odd with the current scheduler. A Java app with very low latency and high QPS would be billed a lot more than it should be. That is because for some unknown reason GAE kills an instance when it has reached exactly 9000 requests. I've tested this with several apps, the simplest had just one servlet doing nothing.
I have an app which can serve about 30 QPS per instance. That means the 9000 requests limit will be reached within 5 minutes. That instance will be billed for 15 minutes! That's 3x the price of the actual instance usage! I hope the 9000 requests limit will change before the new pricing takes place. If the 9000 requests limit stays, I must make sure none of my app instances will serve more than 10QPS (=15 minutes life time / instance). -- 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/-/6vl54r7F_2UJ. 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.
