Date: Tue, 2 Oct 2007 20:30:04 -0700 From: Alfred Perlstein <alfred@freebsd.org> To: Kip Macy <kip.macy@gmail.com> Cc: Daniel Eischen <deischen@freebsd.org>, hackers@freebsd.org Subject: Re: Critical Sections for userland. Message-ID: <20071003033004.GS31826@elvis.mu.org> In-Reply-To: <b1fa29170710022023j3550bdebld40e505997d7a84f@mail.gmail.com> References: <20071003015231.GJ31826@elvis.mu.org> <Pine.GSO.4.64.0710022244250.626@sea.ntplx.net> <20071003025418.GN31826@elvis.mu.org> <Pine.GSO.4.64.0710022257340.626@sea.ntplx.net> <20071003030943.GQ31826@elvis.mu.org> <Pine.GSO.4.64.0710022311450.626@sea.ntplx.net> <b1fa29170710022023j3550bdebld40e505997d7a84f@mail.gmail.com>
next in thread | previous in thread | raw e-mail | index | archive | help
* Kip Macy <kip.macy@gmail.com> [071002 20:24] wrote: > See /sys/priority.h realtime is right below ithreads in terms of > priority. One of the big motivations for gang scheduling and part of > the reason why SMP guests often perform poorly is that apps / VMs > don't scale well if they're descheduled from the cpu while holding a > lock. Yes, exactly the problem, it sucks when process A on CPU 1 runs out of quantum while holding a lock that a runner on CPU 2 wants. -- - Alfred Perlstein
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?20071003033004.GS31826>