Skip site navigation (1)Skip section navigation (2)
Date:      Fri, 05 May 1995 21:40:18 -0700
From:      David Greenman <davidg@Root.COM>
To:        Brian Tao <taob@gate.sinica.edu.tw>
Cc:        FREEBSD-QUESTIONS-L <freebsd-questions@FreeBSD.org>
Subject:   Re: Heavy HTTPD serving on 2.0-950412 
Message-ID:  <199505060440.VAA00157@corbin.Root.COM>
In-Reply-To: Your message of "Sat, 06 May 95 11:37:22 %2B0800." <Pine.BSI.3.91.950506112626.7636D-100000@aries.ibms.sinica.edu.tw> 

next in thread | previous in thread | raw e-mail | index | archive | help
>60 remote clients.  No problems with NMBCLUSTERS set to 1024.  Doing a
>'netstat -n | grep ^tcp' showed between 450 and 520 open connections,

   1024 probably isn't enough, then. I'd recommend increasing it to 1500. Note
that this will consume 6MB of memory.

>    Ummm... what should I be looking for, if I think I'm running out
>of mbufs?  Add up all the X's and see if they exceed NMBCLUSTERS?  How

   "netstat -m" and make sure that the "mbuf clusters in use" remains well
below NMBCLUSTERS. For instance:

17/44 mbuf clusters in use

   ...indicates that the kernel has allocated 44 mbuf clusters (escentially
the peak usage since the system has been up) and that it is currently using 17
of them. The '44' will increase up to a maximum of NMBCLUSTERS.

-DG



Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199505060440.VAA00157>