Re: Memory requirements, 3GB cache

From: Stephen R. van den Berg <srb@dont-contact.us>
Date: Fri, 26 Jul 1996 19:26:58 +0200

Duane Wessels wrote:
>Stephen van den Berg wrote:
>>What's the current design policy on squid? If such a scheme would be
>>made possible where most of the store management is off-loaded onto
>>disk (so that the natural disk cache of the OS takes care of caching),
>>would it be a requirement that the old way (most in memory) still works?
>>If yes, would we settle for compile-time switchable?
>>If given enough room for maneuvering, I might take a stab at
>>reducing the memory requirements.

>Send me code that works.

I've only been on the list for a few hours, but I think I already like you :-).

Ok, further exploring the boundaries: what's with the accelerator
functionality? Do many people use it? I would personally think that
with more and more web pages becoming generated-on-the-fly and servers getting
faster, the need for the accelerator functionality starts to diminish?

I'm not saying that the functionality has to go, just checking how far I can
warp the code without risking that the patches will not be accepted by
the current maintainer(s).

Other than this, I still have a few questions about the code (mostly
about the necessity of certain entries in the StoreEntry struct), where do
I ask them? Here? Or better directly to Duane?

-- 
Sincerely,                                                          srb@cuci.nl
           Stephen R. van den Berg (AKA BuGless).
"I have a *cunning* plan!"
Received on Fri Jul 26 1996 - 10:28:31 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:32:42 MST