Re: Cache in multiple disks

From: Bill Wichers <billw@dont-contact.us>
Date: Tue, 16 Sep 1997 23:34:35 -0400 (EDT)

On Tue, 16 Sep 1997, Fernando Schapachnik wrote:

> (Please reply to me and I'll sumarize, because I'm not in the list.)
>
> Hello:
> I'd like to know how to tell Squid to use X Mbs of space in, say,
> /usr/cache1, and Y Mbs in /usr/cache2 (another disk), where the available
> space in, for example, /usr/cache1 is bigger than X Mbs. In other words:
> I want Squid to use two disks, but I'd like to control how many Mbs in
> each. Do any of you know how to achieve this?

You can specify multiple cache_dirs. For example, if you have 4 GB of
cache space *total*, and have it on 2 1 GB disks and one 2 GB disk, you
would configure Squid as follows:

cache_swap 4096
cache_dir /cache0-1GB
cache_dir /cache1-1GB
cache_dir /cache2-2GB
cache_dir /cache2-2GB

Each cache_dir is the same size, so to split 4 GB onto three disks --
2 one GB disks and 1 two GB disk -- you have to put one cache_dir on each
1 GB disk and two cache_dirs on the 2 GB disk. You also must specify
cache_swap to the total cache size, which is 4 GB.

> I was also wondering how many connections does Squid open to
> fectch a page an its images. It first gets the html, then images one
> after the other, as oposed to the browser which opens many connections
> simultaneously, right?

It is my understanding that Squid establishes one connection per request,
thus if the browser opens 4 simultaneous connections for different objects
Squid will do the same. When I watch the cache_mgr filedescriptor list
this seems to be the case.

        -Bill
Received on Tue Sep 16 1997 - 20:37:07 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:37:06 MST