I can confirm that we are observing increased latency and bothersome startups of new instances. David
On Thursday, November 29, 2012 9:35:29 AM UTC-7, Nik Eleftheriou wrote: > Right about the time i noticed the scheduler had started cycling instances > every 3-4 minutes, I also noticed that our QPS has dropped to 30% of what it > used to be. > Instead of ~1 QPS average we now have 0.3 QPS average. > Seems to be the same for Master/Slave and HR datastore apps. > > Anybody else noticed similar? > > nik. > > On Wednesday, November 28, 2012 8:43:45 AM UTC, Francois Masurel wrote:We are > only using https with appspot domain for our Facebook fan page app. > > > But on the other side we are using a lot of custom domains, our app is some > kind of multi-host CMS. > > > I have read somewhere that custom domains are not performing as well as > appspot domains. > > > François > > > > > On Wednesday, November 28, 2012 2:15:48 AM UTC+1, Per wrote: > We had a very similar problem (see my other post). It's resolved since two > days or so, after some quite bumpy weeks. Latency is down, and "spikyness" of > the dashboard charts is down too, everything runs a lot smoother since > yesterday. > > Maybe we're just lucky, but maybe also something has actually been > reconfigured and we're just the first who moved to new smarter settings, and > you'll follow soon. > > Do you guys happen to use https by the way, and do you track latency > externally like with Pingdom or so? > > Cheers, > Per > > > > On Wednesday, November 28, 2012 1:32:25 AM UTC+1, Nik Eleftheriou wrote:I can > confirm that we are seeing same behaviour in our app. > we can usually serve everyone with 6 instances, but in the last 6 weeks > something has been changed and even though at any one time we have 6-7 > instances, we have 1000 warmups a day. > > so definitely something caused the scheduler to change behaviour as we only > had 10 warmups a day before Oct. > We've not made any code changes to our app in 5 months. > > nik. > > On Saturday, November 17, 2012 3:31:42 PM UTC, Francois Masurel wrote: > After checking my logs for warming requests I can see that new instances have > been started every 3 to 4 minutes for the last hours. > > > Is this normal behavior ? > > > > > On Saturday, November 17, 2012 4:21:28 PM UTC+1, Francois Masurel wrote:I've > notice lots of user facing loading requests since a few hours (days?). > > > Just check the screenshot below. Two new instances have been started to > serve only 13 (12 + 1) requests though another instance was already running > and available and obviously was not overloaded as it had only served 105 > requests during the last hour : > > > > My application instance settings are all set to automatic and pending latency > set to 10s : > > Did something change on GAE side recently ? > These user facing loading requests are really killing my business as my users > are getting really upset about it. > Thanx for your help. > François > App Id = vncts1 -- 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/-/1KTA3ZaDEJoJ. 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.
