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