Skip site navigation (1)Skip section navigation (2)
Date:      Wed, 26 Apr 2000 10:49:20 -0400 (EDT)
From:      Andrew Gallatin <gallatin@cs.duke.edu>
To:        Dennis <dennis@etinc.com>
Cc:        hackers@freebsd.org
Subject:   Re: Large mbufs?
Message-ID:  <14598.65443.725745.6119@grasshopper.cs.duke.edu>
In-Reply-To: <200004261359.JAA16855@etinc.com>
References:  <200004261359.JAA16855@etinc.com>

next in thread | previous in thread | raw e-mail | index | archive | help

Dennis writes:
 > Is there support for large mbufs in v4.0? (that is, allocations of any size?)
 > 

There are 2 ways to use large mbufs:

o options MCLSHIFT=XXXX in your kernel config file.  
Where XXX is 1 << XXX bytes.  Eg, MCLSHIFT=12 is 4K mbuf clusters,
MCLSHIFT=13 is 8k clusters, etc.  config will complain, but it will
work.

There are several drawbacks to this method.  The most glaring is that
you'll probably be wasting an awfully large amount of space.

o allocate & manage them yourself, using m_ext mbufs, within the
subsystem you feel needs them.  See the Tigon (sys/pci/if_ti.c)
driver's management of jumbo frame receive buffers for an example
of how this is done.

Hope this helps,

Drew

------------------------------------------------------------------------------
Andrew Gallatin, Sr Systems Programmer	http://www.cs.duke.edu/~gallatin
Duke University				Email: gallatin@cs.duke.edu
Department of Computer Science		Phone: (919) 660-6590



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




Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?14598.65443.725745.6119>