Any news about this issue ?

Two different parallel requests with no other requests. No instance
server and first request has cold start (ms=2851 and
loading_request=1). Second request is waiting for first request to
finish (pending_ms = 2420). Average latency 1276 is ms!.

10-25 01:19AM 38.587 ms=2851 cpu_ms=3278 api_cpu_ms=31
cpm_usd=0.091116 loading_request=1
10-25 01:19AM 39.016 ms=2481 cpu_ms=144 api_cpu_ms=8 cpm_usd=0.004045
pending_ms=2420

QPS     Latency Memory
0.083   1276.5 ms       47.2 MBytes

--------------------------------

One instance server available and two same requests. Average latency
is now only 30 ms!

10-25 01:22AM 39.415 ms=44 cpu_ms=89 api_cpu_ms=31 cpm_usd=0.002551
10-25 01:22AM 39.416 ms=69 cpu_ms=47 api_cpu_ms=8 cpm_usd=0.001337
pending_ms=42

QPS     Latency Memory
0.050   30.0 ms 47.6 MBytes

--------------------------------

I don't ask you to reserve me few server instances whole time, but
don't count pending_ms in average latency. Am I wrong ? Is there
something that I am missing ?

It would be nice if you also don't count cold start time for average
latency, but I agree that it is hard to know if cold start is simply
result of poor programming or necessary GAE overhead.

-- 
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.

Reply via email to