Re: Some thoughts about cache and swap

[Bill Davidsen <davidsen@tmr.com>]

Christian Borntraeger wrote:
> John Bradford wrote:
> 
>>Quote from Rik van Riel <riel@redhat.com>:
>>
>>>I wonder if we should just bite the bullet and implement
>>>LIRS, ARC or CART for Linux.  These replacement algorithms
>>>should pretty much detect by themselves which pages are
>>>being used again (within a reasonable time) and which pages
>>>aren't.
>>
>>Is there really much performance to be gained from tuning the 'limited'
>>cache space, or will it just hurt as many or more systems than it helps?
> 
> 
> Thats a very good question. 
> Most of the time the current algorithm works quite well.
> On the other hand, I definitely know what people mean when they complain 
> about cachingand all this stuff. By just copying a big file that I dont use 
> afterwards or watching an video I have 2 wonderful scenarios.  The cache is 
> filled with useless information and big parts of KDE are neither in memory 
> nor in cache. Applications  could use madvice or other things to indicate 
> that they dont need this file a second time, but they usually dont. 
> 
> I think it might be interesting to have some kind of benchmark, similiar to 
> the interactive benchmark of Con that just triggers the workload so many 
> people are complaining. If I find the time, I will give it a try in the 
> next days.

You might find my response test program useful. My web server is in 
three pieces at the moment, but http://pages.prodigy.net/davidsen has a 
copy. You might want to do your own, but mine does show the results of 
i/o pushing out programs.

-- 
    -bill davidsen (davidsen@tmr.com)
"The secret to procrastination is to put things off until the
  last possible moment - but no longer"  -me