Date: Thu, 18 Jan 2007 08:58:16 -0500 From: Randall Stewart <rrs@cisco.com> To: Christian Brueffer <brueffer@FreeBSD.org> Cc: freebsd-net <freebsd-net@FreeBSD.org> Subject: Re: mbuf large clusters Message-ID: <45AF7CF8.6030102@cisco.com> In-Reply-To: <20070118135319.GB1874@haakonia.hitnet.RWTH-Aachen.DE> References: <45AF55DE.1070700@cisco.com> <45AF7962.7040407@cisco.com> <20070118135319.GB1874@haakonia.hitnet.RWTH-Aachen.DE>
next in thread | previous in thread | raw e-mail | index | archive | help
Christian Brueffer wrote:
>
> Not sure if I'm understanding you correctly, but kern.ipc.nmbclusters is
> a tunable not a sysctl, so it has to be set in /boot/loader.conf or at
> the loader prompt (see loader(8)).
>
Not in current from what I see (if
I understand this correctly of course):
-----------------------------------------------------
static int
sysctl_nmbclusters(SYSCTL_HANDLER_ARGS)
{
int error, newnmbclusters;
newnmbclusters = nmbclusters;
error = sysctl_handle_int(oidp, &newnmbclusters, sizeof(int), req);
if (error == 0 && req->newptr) {
if (newnmbclusters > nmbclusters) {
nmbclusters = newnmbclusters;
uma_zone_set_max(zone_clust, nmbclusters);
EVENTHANDLER_INVOKE(nmbclusters_change);
} else
error = EINVAL;
}
return (error);
}
SYSCTL_PROC(_kern_ipc, OID_AUTO, nmbclusters, CTLTYPE_INT|CTLFLAG_RW,
&nmbclusters, 0, sysctl_nmbclusters, "IU",
"Maximum number of mbuf clusters allowed");
-----------------------------------------------------
It looks to me like it lets you INCREASE the value from
the calculated system value.. but NOT shrink it :-0
R
--
Randall Stewart
NSSTG - Cisco Systems Inc.
803-345-0369 <or> 803-317-4952 (cell)
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?45AF7CF8.6030102>