Date: Fri, 4 Mar 2005 18:47:04 -0500 From: David Schultz <das@FreeBSD.ORG> To: Peter Jeremy <PeterJeremy@optushome.com.au> Cc: cvs-all@FreeBSD.ORG Subject: Re: cvs commit: src/sys/kern kern_sig.c Message-ID: <20050304234704.GA41005@VARK.MIT.EDU> In-Reply-To: <20050304231620.GA4394@cirb503493.alcatel.com.au> References: <4226446B.7020406@freebsd.org> <61ac46c154aa515a692308440dd1141d@FreeBSD.org> <422710DD.1070203@freebsd.org> <422719E0.10703@samsco.org> <42279B6D.1000005@freebsd.org> <20050304182629.GA39457@VARK.MIT.EDU> <4228AB27.3020204@samsco.org> <4228B504.7000302@elischer.org> <20050304212329.GA40395@VARK.MIT.EDU> <20050304231620.GA4394@cirb503493.alcatel.com.au>
index | next in thread | previous in thread | raw e-mail
On Sat, Mar 05, 2005, Peter Jeremy wrote: > On Fri, 2005-Mar-04 16:23:29 -0500, David Schultz wrote: > >On Fri, Mar 04, 2005, Julian Elischer wrote: > >> for a start I'd like to add a sysctl to turn off swapping out kernel > >> stacks.. > >> then if someone had a reproducible or atleast 'common" problem, > >> we could suggest turning it off to see > >> if it fixes the problem.. that would be a big smoking gun.. > > > >You mean like vm.swap_enabled? ;-) > > That turns off all swapping and isn't going to answer the question. > Julian's point does seem reasonable - there is a potential problem > relating to swapping kernel threads but there's no clear evidence > that it is or isn't a real problem. Adding a knob to easily control > the behaviour would be useful - we stand to get some real data and > can then better make a decision as to how to proceed. vm.swap_enabled *does* control kstack swapping only. What you're thinking of, namely, paging in general, is controlled by whether or not you have any swap devices configured.home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20050304234704.GA41005>