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.
