There is a bug here in that coordinator should not be opening itself a
cache_dir. It is obviously prevented from doing so on startup, but the
reconfigure code apparently is still trying to do so.
Please report the details to replicate this in our bugzilla at
bugs.squid-cach.org.
There is also a unrelated config problem... details below on that...
On Mon, Jan 7, 2013 at 11:51 PM, Tom Tom wrote:
> Hi
>
> I just added the following lines:
> workers 4
> cache_dir aufs /squid-cache0${process_number} 100000 64 512
> cache_dir aufs /squid-cache0${process_number} 100000 64 512
> cache_dir aufs /squid-cache0${process_number} 100000 64 512
> cache_dir aufs /squid-cache0${process_number} 100000 64 512
What this means is that there are 16 cache directories... each of 4
workers owns 4 caches which happen to be named identically.
You should have unique cache_dir paths on every cache_dir in the config
file. Use of ${process_number} ensures that each worker has a
non-colliding location with other workers. So you only need one of the
above cache_dir lines to make all workers use unique directory locations.
HTH
Amos
Received on Tue Jan 08 2013 - 11:28:35 MST
This archive was generated by hypermail 2.2.0 : Tue Jan 08 2013 - 12:00:03 MST