Uoti Urpala wrote:
> 
> Does changing the order of the unlock_in() and unlock_out() statements
> at the end of conn_register() in conn.c help? It fixes at least one race
> condition in HTTP code.

no, this does at least not change behaviour for the HTTP/1.1 CPU
cycling problem we get on Linux that I described in my summary report.

My CPU usage here on the bearerbox raises to 99% and keep remaining.

We need some mutex and pthread experts! -- someone knowing where to
grap them?

Stipe

[EMAIL PROTECTED]
-------------------------------------------------------------------
Wapme Systems AG

M�nsterstr. 248
40470 D�sseldorf

Tel: +49-211-74845-0
Fax: +49-211-74845-299

E-Mail: [EMAIL PROTECTED]
Internet: http://www.wapme-systems.de
-------------------------------------------------------------------
wapme.net - wherever you are

Reply via email to