lkml.org 
[lkml]   [1997]   [Jan]   [8]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: Since no one else has stepped forward: 'ZeroD' patch

On Wed, 8 Jan 1997, Nigel Metheringham wrote:

> } Ingo Molnar <mingo@pc5829.hil.siemens.at> writes:
> }
> } > Here is a patch that implements 'ZeroD', a simple kernel thread that uses
> } > up CPU idle time to keep a pool of pre-zeroed pages around. Almost
> } > anything that doesnt burn 100% CPU time all the time should benefit from
> } > this.
> }
> } Hmm, did you check that this hasn't a bad effect on the cache memory when
> } a cpu intensive process has to sleep for short times?
> } A /proc/sys interface to tune it would be nice too.
>
> This would also presumably affect the heat production of the CPU -
> especially on hot Cyrixs!
>
> Does it spend all the idle time doing this, or just a part??

no, just part of it. There is a limited queue of prezeroed pages
currently. So the current typical way of operation is that some system
activity eats 1-2-3 zero pages, zerod wakes up whenever there is some idle
time left and zeroes some 1-2-3 new pages.

i dont even know if it makes sense at all :) This is an experimental patch
for an experimental kernel :))

for the cache subsystem thing: if you think about it, it generates
slightly >faster< general system operation, mainly because all the zeroing
done by the daemon (or lets it call a pinguin :) has to happen anyways.
And we should rather do it when the system is idle.

-- mingo


\
 
 \ /
  Last update: 2005-03-22 13:38    [W:0.083 / U:0.940 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site