Re: [squid-users] 2.4STABLE1 and Linux RedHat 6.1

From: Marc Elsen <marc.elsen@dont-contact.us>
Date: Fri, 24 Aug 2001 10:06:17 +0200

>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 had similar problems when upgrading to 2.4S1 on RedHat 6.2,it turned
out that this was due to 2.4S1 deciding to trim the cachedirs somewhat.
Now the trick was to disable AsyncIO during this initial
2.4S1 'birth-phase' on my box. After Squid was happy with it's
intended actions on the cache dirs it ran and still runs very fine
for me.

Marc.
Received on Fri Aug 24 2001 - 02:06:50 MDT

This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:01:54 MST