Date: Mon, 24 Dec 2007 19:21:10 -1000 (HST) From: Jeff Roberson <jroberson@chesapeake.net> To: David Xu <davidxu@freebsd.org> Cc: Brian McGinty <brian.mcginty@gmail.com>, Robert Watson <rwatson@freebsd.org>, arch@freebsd.org Subject: Re: Linux compatible setaffinity. Message-ID: <20071224191954.Q73903@desktop> In-Reply-To: <47707EA2.8010002@freebsd.org> References: <20071219211025.T899@desktop> <476B1973.6070902@freebsd.org> <20071222183700.L5866@fledge.watson.org> <476F0EE5.1040404@freebsd.org> <601bffc40712241909t10e6f3k8e7940d387b6efc2@mail.gmail.com> <47707EA2.8010002@freebsd.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Tue, 25 Dec 2007, David Xu wrote: > Brian McGinty wrote: >> On Dec 23, 2007 5:44 PM, David Xu <davidxu@freebsd.org> wrote: >>> Robert Watson wrote: >>>> On Fri, 21 Dec 2007, David Xu wrote: >>>> >>>>> I don't say no to these interfaces, but there is a need to tell user >>>>> which cpus are sharing cache, or memory distance is closest enough, >>>>> and which cpus are servicing interrupts, e.g, network interrupt and >>>>> disks etc, etc, otherwise, blindly setting cpu affinity mask only can >>>>> shoot itself in the foot. >>>> While the Mac OS X API is pretty Mach-specific, it's worth taking a look >>>> at their recently-announced affinity API: >>>> >>>> http://developer.apple.com/releasenotes/Performance/RN-AffinityAPI/index.html >>>> >>>> >>>> Robert N M Watson >>>> Computer Laboratory >>>> University of Cambridge >>>> >>> >>> I like the interfaces, it is more flexible. >> >> I agree. May I as k what's being planned? It's Jeffs' call finally I think. >> >> Brian. > > I don't have plan. ;-) If I understand it correctly, it is a hint to > scheduler, it is better describing thread relationship, while Jeff's > interface is a hard cpu binding interface, it is still needed in some > circumstance. Yes, I don't think they're exclusive. However, the system scheduler makes some observations about what threads might be best placed near each other. I have plans to make ULE even smarter in this regard so that the application developers would almost never need to hint it. I think these kinds of hints are not often correct or very useful anyway. Thanks, Jeff > > Regards, > > _______________________________________________ > freebsd-arch@freebsd.org mailing list > http://lists.freebsd.org/mailman/listinfo/freebsd-arch > To unsubscribe, send any mail to "freebsd-arch-unsubscribe@freebsd.org" >
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20071224191954.Q73903>