Re: axe CPU_UPGRADE_HW_CACHE from i386 specific code

2005-03-26 Thread M. Warner Losh
In message: <[EMAIL PROTECTED]> Mark Santcroos <[EMAIL PROTECTED]> writes: : It looks like CPU_UPGRADE_HW_CACHE is only used in PC98, so it can be : removed from all I386 specific code. : : Any objections to the following patch? This does appear to be a pc98 only item. A grep of the

Re[2]: relation between PQ_CACHESIZE and PQ_L2_SIZE

2005-03-26 Thread Igor Shmukler
> http://lists.freebsd.org/mailman/htdig/freebsd-hackers/2003-June/001655.html >But what puzzled me is : why not page size is a > factor when calculating the number of colors? Page coloring in freebsd was implemented by John Dyson. It is needed to better utilize the cache. Depending on cac

Re: relation between PQ_CACHESIZE and PQ_L2_SIZE

2005-03-26 Thread Bao Zhao
--- Bruce M Simpson <[EMAIL PROTECTED]> wrote: > On Sat, Mar 26, 2005 at 09:44:36AM -0800, Bao Zhao > wrote: > > some think it is 4-way set associative,but I think > it > > is the page's size-4KB. > > > > If I'm right, How BSD deals with 8KB page size? > > Please search this list's archives as t

Re: relation between PQ_CACHESIZE and PQ_L2_SIZE

2005-03-26 Thread Bruce M Simpson
On Sat, Mar 26, 2005 at 09:44:36AM -0800, Bao Zhao wrote: > some think it is 4-way set associative,but I think it > is the page's size-4KB. > > If I'm right, How BSD deals with 8KB page size? Please search this list's archives as there's a thread on this from a few years back (I was one of the pr

Re: contributing to fbsd

2005-03-26 Thread Brian Fundakowski Feldman
On Sat, Mar 26, 2005 at 04:32:56PM -0500, Mark W. Krentel wrote: > > The VM map algorithms are the same as ever, though. They use linear > > traversal along with a cached reference to the last lookup. There > > are certainly some workloads that should benefit from this, so it > > definitely could

Re: contributing to fbsd

2005-03-26 Thread Andriy Tkachuk
(exept patching [2005/01/26] threads/76690threads fork hang in child for (-lc_r & -lthr) in wich anyone doesn't interesting as it appeared )) PRs can get lost or misfiled... it's just human nature. threads PRs are broadcasted every moth AFAIN ) ___

Re: make_dev(9) man page: inconsistent with reality

2005-03-26 Thread Christian Brueffer
On Sat, Mar 26, 2005 at 06:21:21PM +0300, Dmitry Morozovsky wrote: > Dear colleagues, > > [EMAIL PROTECTED]:/FreeBSD/src.current> cvs -R stat share/man/man9/make_dev.9 > === > File: make_dev.9Status: Up-to-date > >Working

relation between PQ_CACHESIZE and PQ_L2_SIZE

2005-03-26 Thread Bao Zhao
hi,all in vm_page.h PQ_CACHESIZE/PQ_L2_SIZE is always equal to 4. what does "4 " mean? some think it is 4-way set associative,but I think it is the page's size-4KB. If I'm right, How BSD deals with 8KB page size? Best Regards Bao Zhao __ Do

Re[2]: contributing to fbsd

2005-03-26 Thread Andriy Tkachuk
> If you're interested, I can send you a copy of the code... It's a bare > implementation with some basic regression tests performed It doesn't > layer ontop of kmem_cache though... Yes, John. Send me please. Thank you, Andriy. ___ freebsd-hacker

relation between PQ_CACHESIZE and PQ_L2_SIZE

2005-03-26 Thread Bao Zhao
hi, all in vm_page.h PQ_CACHESIZE / PQ_L2_SIZE is always equal to 4. some think "4" represents a 4-way set associative, but I think "4" is the page size.Which is right? If I'm right, how bsd deal with 8KB page size? Best Regards Bao Zhao __

make_dev(9) man page: inconsistent with reality

2005-03-26 Thread Dmitry Morozovsky
Dear colleagues, [EMAIL PROTECTED]:/FreeBSD/src.current> cvs -R stat share/man/man9/make_dev.9 === File: make_dev.9Status: Up-to-date Working revision:1.15Mon Nov 10 10:22:33 2003 Repository revision: 1.15/h