Re: How cache into RAM memory rather than on disk?

From: Flavio Pescuma <edtfopa@dont-contact.us>
Date: Tue, 16 May 2000 16:44:58 +0200

Hi

I think you haven't yet answer his question,
How to make squid use the spare memory?

My guess is that if you create a ram disk make a fs on it and mount it
and then tell squid to use this cache drive as well then you will use
your spare memory and get the benefit from RAM speed compared to disk,
but of course this will only be for the objects stored on the RAM disk
which probably are a small percentage compared to the ones stored in
disk.

Regards,

Flavio

Henrik Nordstrom wrote:
>
> hillel@learn.co.za wrote:
>
> > Anyone know how to place the cache in RAM memory, rather than on the
> > harddrive.
> > When you view access.log, you get many TCP_HIT's and TCP_MEM_HIT's.
> > TCP_HIT's are when a valid copy of the requested object was in the cache.
> > and TCP_MEM_HIT's are when the requested object was in cache and memory,
> > thus avoiding disk access. How do you get squid to put the cached objects
> > in memory if there is space? This should speed up the cache considerably.
>
> Squid currently can't do that. It did once in a time (the Squid-1.1
> series) but was changed to the current behaviour because of other memory
> usage performance problems (it was a bit to keen on using memory).
>
> Squid will quite likely be changed to again cache TCP_HIT's in memory
> some time, but I cannot give you a date when this will happen. Hopefully
> sometime this year.
>
> --
> Henrik Nordstrom
> Squid hacker

-- 
WIRE - Web & Internet Resources at Ericsson
Flavio Pescuma           phone: +46 (0)8 7263359
L M Ericsson Data AB     fax:   +46 (0)8 7217207
125 82 Stockholm Sweden  http://eriweb.ericsson.se
Received on Tue May 16 2000 - 06:51:43 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:53:30 MST