Skip site navigation (1)Skip section navigation (2)
Date:      Tue, 01 Dec 2009 18:35:44 -0700
From:      Brett Glass <brett@lariat.net>
To:        Julian Elischer <julian@elischer.org>
Cc:        net@freebsd.org
Subject:   Re: Question regarding netgraph and threading
Message-ID:  <200912020135.SAA17434@lariat.net>
In-Reply-To: <4B15AFE9.5070606@elischer.org>
References:  <200912011952.MAA12927@lariat.net> <4B1580E2.4080006@elischer.org> <200912012333.QAA16055@lariat.net> <4B15AFE9.5070606@elischer.org>

next in thread | previous in thread | raw e-mail | index | archive | help
At 05:08 PM 12/1/2009, Julian Elischer wrote:

>in the netgraph code I see:
>
>                /* Autoconfigure number of threads. */
>                 if (numthreads <= 0)
>                         numthreads = mp_ncpus;

Ah.... Found this in /sys/netgraph/ng_base.c. Yes, it does seem to 
have a pool of worker threads. This is good. It means that if 
there's a single thread or single CPU bottleneck for a busy PPTP 
server, it would not be the netgraph traffic but rather the one 
process handling the TCP control connections for the PPTP sessions. 
I'll give it a try and see if this causes any problems.

Still wondering about that boot time message, though.

--Brett




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200912020135.SAA17434>