Re: Request Rates

From: Ross Wheeler <rossw@dont-contact.us>
Date: Sat, 14 Jun 1997 08:06:40 +1000 (EST)

> Cache Information from cachemgr.cgi (present, not from the mentioned test):
>
> dated Thu Jun 12 11:31:33 1997
>
> Resource usage for squid:
> CPU Time: 15480 seconds (7364 user 8116 sys)
> CPU Usage: 3%
> Maximum Resident Size: 0 KB
> Page faults with physical i/o: 572495
                                         ^^^^^^

Could somene please explain this for me?

When I ran my first squid, I had over 1000 users accessing it, and i/o
error count of zero (0) after several months. (that is, squid would run
for 3 weeks or so at a time, but even after several months I never had
any errors). My squid was the same, but the current one, and one other I
manage, both 1.1.9 on freebsd, have significant error counts.

It doesn't seem to cause any problems, nor does anything get reported
in the logs, but I'm curious. My first squid was 1.0.6 I think, running
on a slow 486DX4/75 with only 16Mb RAM, BSDI 2.0.1, and doing other things,
with only 100Mb on a SCSI disk set to cache buffers. (I was only trying
the concept).

The new squids, are on P166 or P200 with 64/128Mb RAM and multiple 4Gb
Barracuda drives with FreeBSD 2.2.1

RossW
Received on Fri Jun 13 1997 - 15:24:46 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:35:31 MST