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.

Reply via email to