We are seeing this problem too, our regular instance are 6-10 and they were at 300-400
Our code is now disabled, it was using memcache, but we have no fix for it so far, no change in code or traffic. See this thread. http://groups.google.com/group/google-appengine/browse_thread/thread/29515fdc51f80b32# On Dec 8, 11:13 am, Rishi Arora <[email protected]> wrote: > I'm seeing this too, but for me this has turned out to be a good thing. I > have my Max-Idle-Instances fixed at one. But I thought my issue was more > because I lowered my Max-Pending-Latency from 5 seconds down to 1 second, > and then further down to 50ms. In terms of impact on resource-usage, I > have only seen my overall instance-hours used per-day go from ~27 (under > the free amount of 28), to about 30. To me, a cost increase of $0.16 is a > small price to pay for a really low max-pending-latency of 50ms. The user > experience has been a lot better since then. > > For your case, keep in mind that QPS is only averaged over the last minute > - so it may not be a good indication for overall load demanded of your > instances. I do feel that there was a change in GAE's instance scheduler, > but I would recommend tweaking the scheduler settings - more importantly, > you may need to lower your Max-Idle-Instances, so that an increase in > active-instance-count (in response to spike in incoming requests) doesn't > have a huge impact to your cost. Also, correspondingly, if you're reducing > max-idle-instances, you may also need to reduce your max-pending-latency so > that instances are spawned sooner to serve your incoming load. Do you have > a sense for how long your instance start up time is? > > > > > > > > On Thu, Dec 8, 2011 at 10:33 AM, Clément <[email protected]> wrote: > > I'm experiencing a very high and unusual instance count on one of my apps > > since this morning. > > > I have about 10 instances usually, but today it's stuck between 40 and 50. > > > There is no code change since yesterday, and the load is about the same as > > every day. > > > The average QPS is extremely low (below 0.1), and the latency is also > > quite low (below 500ms), so it doesn't make any sense. > > > I've almost exhausted my quota for today because of this issue. > > > Has something changed in the instance scheduler since yesteday ? > > > -- > > 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/-/DgFyJxrcopQJ. > > 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. -- 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.
