[squid-users] Performance Troubleshooting

Greetings List,

I recently moved our squid installation from SuSE 8 to RHEL ES 3 and the performance has decreased significantly. I am looking here for pointers of what you think may be the difference. I attempted to keep the configuration largely the same, and the hardware is 100% the same (same system).

The performance with SuSE:

peak median response time = .250 s
peak requests per minute = 930

Now on RHEL ES 3:

peak median response time > .800 s
same numbers of requests per minute

We are using a ton of memory, but I think we are in good shape:

Page faults with physical i/o: 553
Number of HTTP requests received: 2975409

[me@proxy home]$ free -m
             total used free shared buffers cached
Mem: 3778 3709 69 0 415 2209
-/+ buffers/cache: 1084 2694
Swap: 8997 5 8992

I am not running named on this system, so I am wondering if this is an area for improvement. How do these DNS times look?:

DNS Lookups: 0.05313 0.06657

One thing that I know is different is the file system of the cache_dirs. They are now ext3 while before they were reiserfs, store io type is aufs.

I did not attempt to preserve the cache_dirs so the cache before was 2 x 45 GB while the cache now has grown to only 2 x 3,259 MB (online about 2 weeks now).

Does anyone have any suggestions for me?

Many thanks in advance,

Grant

This electronic message transmission is a PRIVATE communication which contains
information which may be confidential or privileged. The information is intended
to be for the use of the individual or entity named above. If you are not the
intended recipient, please be aware that any disclosure, copying, distribution
or use of the contents of this information is prohibited. Please notify the
sender of the delivery error by replying to this message, or notify us by
telephone (877-633-2436, ext. 0), and then delete it from your system.
Received on Tue Jul 13 2004 - 14:32:20 MDT