Sigh,

Brandon wrote:

> The variance between my "identical" requests is less than 10%.  
>

Yea, me too. Except when it ain't.

I went class 4 ape$hit a couple of weeks ago, when I saw latencies for my 
app increase by 50x. That's 5000%.

Check out the last 30 days of operation (milliseconds per request):

 [image: Requests/Second (24 hrs)]

Note the correlation between the dates given by Nischal Shetty and the 
signal at -14d.

Takashi was kind enough to explain:

Besides that, please keep in mind that the performance of each loading 
> request(sure, actually every single request) may vary, because of 
> various reasons like actions of other customers in the same cluster, 
> the load on the system, or some kind of maintenance happening. App 
> Engine is a multi-tenant cloud platform. 
>

Huh. Interesting.  "App Engine is a multi-tenant cloud platform."

Get used to hearing that explanation for your observed QoS.
David


-- 
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/-/TuNfHBxaMfsJ.
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