Skip site navigation (1)Skip section navigation (2)
Date:      Mon, 26 Apr 1999 16:01:47 -0400
From:      Dennis Rockwell <dennis@bbn.com>
To:        mwlucas@exceptionet.com
Cc:        jonny@jonny.eng.br, stable@FreeBSD.ORG
Subject:   Re: nmbclusters=4096 doesn't increase mbufs 
Message-ID:  <199904262001.QAA07107@po1.bbn.com>
In-Reply-To: Message from mwlucas@exceptionet.com  <199904261944.PAA24025@easeway.com> .

next in thread | previous in thread | raw e-mail | index | archive | help
On 26 Apr, mwlucas@exceptionet.com wrote:

> The machine in question frequently slows to a crawl.  The IPFilter people
> have specifically cited mbuf starvation as a classic cause of this
> symptom.

Run netstat -m when the system is crawling and see what you
get, especially the denied and delayed numbers.

> How can I determine how many mbufs a FreeBSD machine has at a given time?

That's what netstat -m tells you; how many mbufs and
clusters have been allocated, and how many of them are in
use (ie, not on the freelists).

> If 132 is the current high-water mark, and we actually have 4096
> available, I'll shut up and go away happy.

That is precisely the case on other related systems I've
dealt with; I cannot claim to be authoritative about this
particular version of FreeBSD, but the output of netstat -m
is similar enough that I would expect that the underlying
mechanisms are the same.

Dennis Rockwell                 dennis@bbn.com
GTE Internetworking
Powered by BBN                  +1-617-873-5745
Cambridge, MA                   +1-617-873-6091 (Fax)


To Unsubscribe: send mail to majordomo@FreeBSD.org
with "unsubscribe freebsd-stable" in the body of the message




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?199904262001.QAA07107>