SV: Re: Varnish stuck on stresstest/approved by real traffic

[Václav Bílek]

Mail for Exchange napsal(a):
> (sorry for bad quoting/name... Damned phone)
> 
> Yes. The value depends on the size of the average object, but often values all the way up to 150ms make sense, possibly even more.

will try ...

> If this was/is the issue for you, you should see a significantt improvement on performance when you are cpu-sarved
 on 8core server ve do not get ower 300% cpu usage

>, and on 2.0.4 and older you will often use noticeably fewer threads (threads should no longer grow considerably larger than actual concurrent requests, which is somewhat counter intuitive)

Vaclav


> 
> - Kristian
> 
> --- opprinnelig melding ---
> Fra: Václav Bílek <v.bilek at 1art.cz>
> Emne: Re: Varnish stuck on stresstest/approved by real traffic
> Dato: 5. november 2009
> Klokkeslett: 07:39:48
> 
> 
> 
> Kristian Lyngstol napsal(a):
>> (Excessive trimming ahead. Whoohoo)
>>
>> On Tue, Nov 03, 2009 at 11:51:22AM +0100, Václav Bílek wrote:
>>> When testing varnish throughput and scalability I have found strange
>>> varnish behavior.
>> What's the cpu load at that point?
> zero
> 
> 
>> Also: use sess_linger. No session_linger == kaboom when things get too
>> loaded. It's 50ms default in 2.0.5/trunk, but set to 0ms in 2.0.4 and
>> previous.
>>
> if I understand i should set higher value than 0, right?
> 
> 
>> The behaviour in trunk is slightly different/better, but it's still worth
>> using it in 2.0.4.
>>
>> - Kristian