Adding RAM

[Wei-Yee Chan]

As I've mentioned, it's just a hypothesis.  I did not jump to that
conclusion, as U may be aware. 

You'll never know what went wrong unless U know all the facts.  Anything
that's based on your own assumptions is of little use in isolating the
problem. 

Hindsight is always twenty-twenty, but that doesn't quite come in handy
when your faced with an unusual problem.

Tony Arnold wrote:
> On Sat, 2006-10-14 at 06:46 +0800, Wei-Yee Chan wrote:
>   
>> http://www.pcguide.com/ref/mbsys/cache/char_Cacheability.htm
>>     
>
> An interesting description, but I don't think it helps much. If you add
> more memory without increasing the amount of cache AND you increase the
> load by running more processes, thus more randomly distributing the
> addresses accessed and thus reducing the probability of a cache hit,
> then yes I can see things might slow down.
>
> But we were talking about a single user system and I presumed the work
> being done by the computer was about the same before and after the
> increase in memory so I can't see how there can be any slow down as a
> result of the extra memory.
>
> This also assumes the cache is capable of caching up to 1GB of memory.
> If it is built to support only caching the first 512MB, then again there
> would be a slow down. The manufacturer's statements of maximum amount of
> memory supported by the system could be quite misleading this scenario.
>
> Hmm, maybe I'm almost convinced! But not quite yet!
>
> Regards,
> Tony.
>   

-------------- next part --------------
A non-text attachment was scrubbed...
Name: smime.p7s
Type: application/x-pkcs7-signature
Size: 1938 bytes
Desc: S/MIME Cryptographic Signature
URL: <https://lists.ubuntu.com/archives/ubuntu-users/attachments/20061014/fe82a50d/attachment.bin>