page faults

Hi,
I'm using Linux 2.0.35 and squid 1.1.21, cache manager reports the ratio of number of tcp connection/page faults per physical io is around 0.5 and it's increasing by time. Due to the FAQ, this is a bad thing and an indicator of system doing a lot of swapping , however looking at the output of other system tools, like vmstat it indicates that the system is doing no swapping at all and looking at "free" output , it shows that swap space is free. How is that ? my first guess is that the Linux interpretation of the pagefaults parameter is different from other OS'es. Is that true ? I would like to know. Thanks
Received on Wed Oct 28 1998 - 10:00:03 MST