[lkml]   [1997]   [Jan]   [9]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
Messages in this thread
SubjectRe: Since no one else has stepped forward: 'ZeroD' patch

On 9 Jan 1997, Jes Degn Soerensen wrote:

> The idea of zerod may not be that good for cpus with relatively small
> caches and no cache write-through instructions such as the 68030 (the
> 68030 only has a 256 byte data cache and a 256 byte ins cache). On
> these cpus a clear-page() is enough to wipe out the entire data-cache
> ;( However for the 68040 and 68060, which got these nice move16
> instructions that bypasses the cache, zerod will be fine.

look into the current kernel code. Pages are zeroed quite often. In some
situations the kernel does almost nothing but zeroes pages.

Now 'zerod' does nothing but changes the order of things ... it zeroes
pages a bit earlier, nothing else.

It doesnt zero more pages, it doesnt do it in a more cache hostile way. It
does the very same thing, but a bit earlier. This way in certain
situations otherwise idle CPU time gets utilized.

-- mingo

 \ /
  Last update: 2005-03-22 13:38    [W:0.036 / U:2.452 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site