Messages in this thread | | | Date | Fri, 02 May 2008 03:18:38 +0200 | From | Gabriel C <> | Subject | Re: [PATCH] x86: mtrr cleanup for converting continuous to discrete - auto detect |
| |
Yinghai Lu wrote: > On Thu, May 1, 2008 at 5:29 PM, Gabriel C <nix.or.die@googlemail.com> wrote: >> Yinghai Lu wrote: >> > On Thu, May 1, 2008 at 4:45 AM, Gabriel C <nix.or.die@googlemail.com> wrote: >> >> Yinghai Lu wrote: >> >> > loop mtrr chunk_size and gran_size from 1M to 2G to find out optimal value. >> >> > >> >> > so user don't need to add mtrr_chunk_size and mtrr_gran_size, >> >> > >> >> > if optimal value is not found, print out all list to help select less optimal >> >> > value. >> >> > >> >> > add mtrr_spare_reg_nr= so user could set 2 instead of 1, if the card need more entries. >> >> >> >> WOW :) >> >> >> >> With this patch all is working fine , no RAM is lost , X is fast , >> >> so far everything else seems to work fine. \o/ >> >> >> >> I will test on 32bit tomorrow and stress the box later on today to be sure everything works fine. >> >> >> >> There is my dmesg , meminfo , mtrr output with this patch on top x86-latest : >> >> >> >> http://frugalware.org/~crazy/mtrr_x86-latest/ >> > >> > while look at that you boot log, it seems there is one bug about hole >> > position. but I look that code, it should already be handled. >> > >> > Can you send out boot msg and /proc/mtrr when using >> > disable_mtrr_cleanup command line? >> >> Sure , there it is : >> >> http://frugalware.org/~crazy/mtrr_x86-latest/dmesg2 >> http://frugalware.org/~crazy/mtrr_x86-latest/proc_mtrr2 >> >> I'm still using this version of your patch , didn't got any time to update to v2. >> If you want me to try v2 tell me , I have some free time in about 30 minutes. >> > original > > reg00: base=0xd0000000 (3328MB), size= 256MB: uncachable, count=1 > reg01: base=0xe0000000 (3584MB), size= 512MB: uncachable, count=1 > reg02: base=0x00000000 ( 0MB), size=4096MB: write-back, count=1 > reg03: base=0x100000000 (4096MB), size= 512MB: write-back, count=1 > reg04: base=0x120000000 (4608MB), size= 128MB: write-back, count=1 > reg05: base=0x128000000 (4736MB), size= 64MB: write-back, count=1 > reg06: base=0xcf600000 (3318MB), size= 2MB: uncachable, count=1 > > after clean up > > reg00: base=0x00000000 ( 0MB), size=2048MB: write-back, count=1 > reg01: base=0x80000000 (2048MB), size=1024MB: write-back, count=1 > reg02: base=0xc0000000 (3072MB), size= 256MB: write-back, count=1 > reg03: base=0xcfe00000 (3326MB), size= 2MB: uncachable, count=1 > reg04: base=0x100000000 (4096MB), size= 512MB: write-back, count=1 > reg05: base=0x120000000 (4608MB), size= 256MB: write-back, count=1 > reg06: base=0x12c000000 (4800MB), size= 64MB: uncachable, count=1 > > so the hole base is not right, it should be at 3318MB instead of 3326MB. > please hold to test v3 ...
All is still fine here after an quick test ( BTW that version is really chatty :P )
http://frugalware.org/~crazy/mtrr_x86-latest/dmesg_v3
> > Thanks > > Yinghai Lu >
Gabriel
| |