Justin Lintz wrote:
On Wed, Feb 10, 2010 at 4:23 PM, Amos Jeffries <squid3@xxxxxxxxxxxxx> wrote:
http_access allow localhost
http_access allow all
Why?
Sorry I should mention this is running in a reverse proxy setup
So what is the request/second load on Squid?
Is RAID involved?
The underlying disks are running in a RAID 1 configuration. Each
server is seeing around 170 rec/sec during peak traffic
Sigh. My advice on RAID is to avoid it like a plague.
There are people who do get good results, but they all seems to be able
to afford the most expensive hardware arrays as as well.
From RAID1, you can almost halve the disk IO load by removing it.
You only have 4GB of storage. Thats just a little bit above trivial for
Squid.
With 4GB of RAM cache and 4GB of disk cache, I'd raise the maximum object
size a bit. or at least remove the maximum in-memory object size. It's
forcibly pushing half the objects to disk, when there is just as much space
in RAM to hold them.
Amos
Would this only be the case for a forward proxy? I'd say probably
less than 1% of our objects are anywhere near the memory limit.
Thanks for the reply
Less than 1% of your objects are close to or over 4KB in size? Okay
then, you _really_ want to be using COSS.
All the UFS storage types use 4KB chunks to read/write from disk. COSS
reads/writes in MB chunks, but aggregates many small objects very
efficiently into that space at once.
Amos
--
Please be using
Current Stable Squid 2.7.STABLE7 or 3.0.STABLE23
Current Beta Squid 3.1.0.16
