Well you should at least recompile for more than 1024 FDs. Try around
4096 FDs. Also, I personally wouldn't go for a 30GB cache with only 1GB
of RAM to play with. I'd probably go for about 8GB per 1GB of RAM, I
may be wrong. When I tried large caches, I started running into swap.
Then again, YMMV. I think it mostly depends on how many objects you
anticipate caching on disk and how many (and what size) hot objects you
are expecting. You shouldn't need to ever reboot your Squid server.
That should help some.
Peter Smith
Nikos Mouat wrote:
>Hello,
> We have a cache server which handles a fair amount of traffic. I think
>our stats are something like:
>
>Average HTTP hits 1048.0 req/min
>Average HTTP requests 2312.0 req/min
>Average Percentage 45.0 %
>
>
Received on Thu Jan 09 2003 - 14:55:21 MST
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 17:12:36 MST