![]() | |||||||||||
Messages in this thread |
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? Thanks Yinghai Lu | ||||||||||
| Last update: 2008-05-02 02:09 [from the cache] ©2003-2008 | |||||||||||