Date: Fri, 16 Dec 2011 23:16:24 +0100 From: Michel Talon <talon@lpthe.jussieu.fr> To: Doug Barton <dougb@FreeBSD.org> Cc: freebsd-stable@FreeBSD.org Subject: Re: switching schedulers (Re: SCHED_ULE should not be the default) Message-ID: <91A8A86F-4D83-4C6F-8E27-B74204C6ACF9@lpthe.jussieu.fr> In-Reply-To: <4EEBBD5E.50603@FreeBSD.org> References: <1350C7A0-BE58-4C34-804A-A6A3C1C61761@lpthe.jussieu.fr> <4EEBBD5E.50603@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
Le 16 déc. 2011 à 22:51, Doug Barton a écrit : > On 12/16/2011 13:40, Michel Talon wrote: >> Adrian Chadd said: >> >> >>> Hi all, >>> >>> Can someone load a kernel module dynamically at boot-time? >>> >>> Ie, instead of compiling it in, can 4bsd/ule be loaded as a KLD at >>> boot-time, so the user can just change by rebooting? >>> >>> That may be an acceptable solution for now. >> >> As Luigi explained, the problem is not to have code for both >> schedulers residing in the kernel, the problem is to migrate >> processes from one scheduler to the other. > > I think dynamically switching schedulers on a running system and loading > one or the other at boot time are different problems, are they not? > Of course, you are perfectly right., and i had misunderstood Adrian's post. But if the problem is only to change scheduler by rebooting, i think it is no more expensive to compile a kernel with the other scheduler. Or is it that people never compile kernels nowadays? The ability to switch scheduler on a running machine would certainly be a more desirable way to test the best adaptation of the system to the load. To come back to the problems in question about ULE i must say i don't see obvious malfunctions for my own use (i had some problems of this sort long ago, but they disappeared with more recent FreeBSD). > > Doug > > -- Michel Talon talon@lpthe.jussieu.fr
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?91A8A86F-4D83-4C6F-8E27-B74204C6ACF9>