The graph of instances is very confusing to me as neither line seems to correspond to the number of instances running, or running with > 0 qps, try playing with those instance "knobs" they can dramatically effect instance count, but for a high qps app like yours, I don't think you will see a dramatic change.
Are you running python? it sounds like your will benefit heavily from Python 2.7 with concurrent request handling per instance. If your requests spend the majority of their time waiting, should be no problem to do 4 up, which could really drop your instance costs. I'd then try and tackle your datastore reads. While I have no idea about your app, it seems a bit odd to me that you have more reads that writes, in my app I have a 5:1 write to read ratio as I cache just about everything I write. If you aren't confident you will soon read what you write, cache on read every time. Memcache is fast and free, something to think about. -- 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/-/ASjp-0R-u8wJ. 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.
