[squid-users] errors-to-log ratio/thresholds for software abort and comm_accept

Hello,

Watching my logs these past two weeks since we rolled out our new 2.5STABLE2
squid on an upgraded 2.8 Sun Ultra 60, I've seen "a lot" of warning/error
type messages in the cache.log file. Researching these errors on this
mailing list, the answer has often been "if you aren't getting too many"
don't worry or "Sun's do that" (in the case of the s/w abort msg). So I am
just wondering how many is "too many" and if my daily error message totals,
relative to the daily size of the access.log file, are ok, average, or too
high/a sign of a problem. The example below covers one full day and are
representative of typical/average daily totals for the 2 errors and the
access.log on a normal day. Any guidelines as to what is too many for each
error are appreciated.

thanks,

Adam

          886 messages with 'Software caused connection abort'
          443 messages with 'comm_accept: FD *: (*) Software caused
connection abort'
1,503,788 access.log = Total number lines in the /logs/access.log file
Received on Thu Apr 24 2003 - 19:55:57 MDT