Justin Lintz wrote:
dont top list,
we have seveal heavy load squids, and we realized that sometimes inet surf is
slow, we've discovered that it is because IO (as you see in your top command
more than 1% of IO waiting), so we purge our cache to dont let it rise
cache_swap_high percentage very often
The iowait time is more than 1%, at times between 20-50%. We've tried
purging the cache a few times but that only appears to give temporary
relief to the issue. I was looking to tune our configuration more
before ruling out the need for more caching servers or looking into
faster disks for just the cache.
FWIW...
You mentioned at the outset that this was a virtualized installation. I
read a piece by Novell the other day that mentioned that IO was one of
the factors that made virtualization inadvisable under certain
conditions. As Squid is known to make heavy use of disk IO and you are
having iowait problems it make the virtualized installation suspect to
me (having read that piece). Perhaps others more knowledgeable can
comment otherwise but absent that I would at least explore that avenue
were it me.
--
Mike Rambo
NOTE: In order to control energy costs the light at the end
of the tunnel has been shut off until further notice...
