I see alot of these messages in my squid warning log...
Specifically, in filtering off the date, and sort+uniq+counting, I see:
var/log# grp "Median response" warn|cut -c36-90 |more|sort|uniq -c
107 WARNING: Median response time is 57448 milliseconds
1 WARNING: Median response time is 6996 milliseconds
1 WARNING: Median response time is 7384 milliseconds
---- This is out of 471 lines in this 'warn' log -- over 20% are warnings from squid that things are taking alot longer than I would think they should. Usually, it doesn't behave this way... Notable, I have my "dns" timeout set for 1 minute (so the above are all slightly under my dns lookup time. I also notice that the default timeout time waiting for a connection is about 1 minute. Could it really be that I have this many timeouts ... ? 1 minute seems like a pathological case -- not something I'd consider 'normal'... Ideas? Suggestions? Do other people get these types of warnings often? Thanks (My DSL is 3Mb/768) that times close to that rate when I time it...) -lindaReceived on Fri Oct 24 2008 - 18:52:35 MDT
This archive was generated by hypermail 2.2.0 : Sat Oct 25 2008 - 12:00:03 MDT