Messages in this thread | | | Date | Thu, 2 Oct 2008 16:20:08 -0700 | From | "Yinghai Lu" <> | Subject | Re: [PATCH 2/2] x86: mtrr_cleanup try gran_size to less than 1M |
| |
On Thu, Oct 2, 2008 at 4:00 PM, J.A. Magallón <jamagallon@ono.com> wrote: > On Thu, 2 Oct 2008 15:52:11 -0700, "Yinghai Lu" <yinghai@kernel.org> wrote: > >> On Thu, Oct 2, 2008 at 3:33 PM, Yinghai Lu <yinghai@kernel.org> wrote: >> > On Thu, Oct 2, 2008 at 3:03 PM, J.A. Magallón <jamagallon@ono.com> wrote: >> >> On Mon, 29 Sep 2008 18:54:12 -0700, Yinghai Lu <yhlu.kernel@gmail.com> wrote: >> >> >> >>> >> >>> so start from 64k instead of 1M >> >>> >> >> >> >> Or there is something I don't catch about mtrrs, or it still does silly >> >> things. >> >> >> >> I have an ASUS PCDL, dual xeon, 2Gb of memory. Mtrrs after cleanup are: >> >> >> >> werewolf:/proc> cat mtrr >> >> reg00: base=0x00000000 ( 0MB), size=1024MB: write-back, count=1 >> >> reg01: base=0x40000000 (1024MB), size= 512MB: write-back, count=1 >> >> reg02: base=0x60000000 (1536MB), size= 256MB: write-back, count=1 >> >> reg03: base=0x70000000 (1792MB), size= 128MB: write-back, count=1 >> >> reg04: base=0x78000000 (1920MB), size= 64MB: write-back, count=1 >> >> reg05: base=0x7c000000 (1984MB), size= 64MB: write-back, count=1 >> >> reg06: base=0x7ff00000 (2047MB), size= 1MB: uncachable, count=1 >> >> >> >> So it adds a last WB zone, but substracts the last 1Mb. (Why do >> >> I have that stupid uncacheable mb ? probably a bios issue...) >> >> But those two 64 mb zones could be add to a 128Mb, that new one >> >> with previous to 256Mb and so on, giving something like: >> >> >> >> reg00: base=0x00000000 ( 0MB), size=2048MB: write-back, count=1 >> >> reg01: base=0x7ff00000 (2047MB), size= 1MB: uncachable, count=1 >> >> >> >> Is this incorrect ? >> >> >> > >> > can you boot with mtrr_cleanup_debug? >> > >> > also what is /proc/mtrr with disable_mtrr_cleanup? >> >> are you on latest tip/master? >> > > No, I use rc8-git3 with your patches (the small gran_size series and the > parameter rename, except the debug one) manually applied. >
ah.. please pick up all of them from tip/master...
x86: don't need to go to chunksize to 4G x86: mtrr_cleanup optimization, v2 x86: add mtrr_cleanup_debug command line x86: cleanup, remove extra ifdef x86: mtrr_cleanup hole size should be less than half of chunk_size, v2 x86: mtrr_cleanup safe to get more spare regs now x86: mtrr_cleanup prepare to make gran_size to less 1M x86: mtrr_cleanup try gran_size to less than 1M x86: change MTRR_SANITIZER to def_bool y
YH -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/
| |