Date: Sun, 7 May 1995 16:06:45 +0800 (CST) From: Brian Tao <taob@gate.sinica.edu.tw> To: David Greenman <davidg@Root.COM> Cc: FREEBSD-QUESTIONS-L <freebsd-questions@FreeBSD.org> Subject: Re: Heavy HTTPD serving on 2.0-950412 Message-ID: <Pine.BSI.3.91.950506172920.8049B-100000@aries.ibms.sinica.edu.tw> In-Reply-To: <199505060440.VAA00157@corbin.Root.COM>
next in thread | previous in thread | raw e-mail | index | archive | help
On Fri, 5 May 1995, David Greenman wrote:
>
> 1024 probably isn't enough, then. I'd recommend increasing it to 1500. Note
> that this will consume 6MB of memory.
Yow, I'll keep that in mind. When I run a netstat -m, I get:
112 mbufs in use:
2 mbufs allocated to data
20 mbufs allocated to packet headers
79 mbufs allocated to protocol control blocks
11 mbufs allocated to socket names and addresses
1/644 mbuf clusters in use
1302 Kbytes allocated to network (1% in use)
0 requests for memory denied
0 requests for memory delayed
0 calls to protocol drain routines
i.e., 644 clusters were in use at any one time during the test (I
haven't rebooted since then). Is one mbuf needed per network connection,
in general? Netstat showed around 500 open tcp connections during the
test (most in TIME_WAIT, mind you).
--
Brian ("Though this be madness, yet there is method in't") Tao
taob@gate.sinica.edu.tw <-- work ........ play --> taob@io.org
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?Pine.BSI.3.91.950506172920.8049B-100000>