Date: Wed, 22 Oct 2008 14:35:36 -0400 From: Jung-uk Kim <jkim@FreeBSD.org> To: "Attilio Rao" <attilio@freebsd.org> Cc: svn-src-head@freebsd.org, svn-src-all@freebsd.org, src-committers@freebsd.org Subject: Re: svn commit: r184108 - head/sys/i386/i386 Message-ID: <200810221435.42202.jkim@FreeBSD.org> In-Reply-To: <200810221429.51834.jkim@FreeBSD.org> References: <200810210431.m9L4V7Pb088978@svn.freebsd.org> <3bbf2fe10810220853r34256b59y1fe57f49eca2014@mail.gmail.com> <200810221429.51834.jkim@FreeBSD.org>
next in thread | previous in thread | raw e-mail | index | archive | help
On Wednesday 22 October 2008 02:29 pm, Jung-uk Kim wrote: > On Wednesday 22 October 2008 11:53 am, Attilio Rao wrote: > > 2008/10/21, Jung-uk Kim <jkim@freebsd.org>: > > > On Tuesday 21 October 2008 06:07 am, Attilio Rao wrote: > > > > Something we could do with this is adding a "quirk" table of > > > > TSC arch dependant known to be working (based on cpu_model > > > > and such) and use that table in order to replace tsc_smp. > > > > > > Please note the invariant_tsc and smp_tsc are different. If we > > > go with the route, we need two quirk tables. :-( > > > > It doesn't matter. > > I think it is silly we have different quirks flag states for TSC. > > We should just having a table assuming that the TSC is safe to > > use in SMP environments and gets rid of any other flag (in this > > case, for amd64 based machine, the logic could, for example, > > check if the CPU is P state invariant and assume it is safe, > > etc.) > > Yes, it does matter as TSC is not just for timecounter and it can > be used independently. For example, if a thread is bound to a CPU and the CPU has P-state invariant TSC, > it can provide the fastest AND safest timer. > Besides, the whole point was not to modify TSC freq. if it is > independent from CPU freq. > > Jung-uk Kim
Want to link to this message? Use this URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?200810221435.42202.jkim>