[squid-users] Squid 2.4STABLE1 and RedHat 6.1

==
I apologize for the HTML in my previous post, I only have access to Hotmail
at this time and I forgot it formats email to HTML.
==

Hello,

Are there any known issues with Linux RedHat 6.1 and Squid 2.4STABLE1? I
have been running Squid 2.3STABLE1 through STABLE5 for many months without
problems, however whenever I try to implement 2.4STABLE1 to benefit from
AsyncIO or DISKD, as soon as the server has finished validating the store,
the load average jumps through the roof (20 or more!!!). When AsyncIO is
configured, within 30 seconds I get warning messages of IO overloading.
Please note that the above is observed even though I have not yet begun to
send requests to the cache!!!!! The machine basically comes to a crawl
almost instantaneously with no client requests. When using DISKD, load
average sky-rockets and tests of sending only a few client requests have
6000ms or more before a response is given with less than 60 reqs/min.

I am using the following configuration directives:

--enable-snmp --disable-poll --disable-ident-lookups --enable-delay-pools
--enable-underscores --enable-removal-policies=heap --enable-async-io=64
--enable-storeio=aufs

The machine specs are as follows:

PentiumIII 800Mhz
Linux 2.2.19 with 8192 fds available
glibc-2.1.3
egcs-2.91.66 19990314/Linux (egcs-1.1.2 release)
768 MB RAM
3 x 18G 10K RPM SCSI drives
aic7892: Ultra160 Wide Channel A, SCSI Id=7, 32/255 SCBs (this is the
adaptec driver)

I tried using --enable-poll and --disable-poll, and so far even on
2.3STABLE5 using --disable-poll seems to give a more responsive cache.

Any help would be appreciated, as I have been looking forward to using
AsyncIO for a while but have yet to be able to!

Thanks,

Ron

_________________________________________________________________
Get your FREE download of MSN Explorer at http://explorer.msn.com/intl.asp
Received on Wed Aug 22 2001 - 14:26:08 MDT