Hi Duane,
> http://squid.nlanr.net/Squid/1.1/1.1.8/fixes.patch
>
> Changes to this patch:
...
> - Removed storeCheckExpired() from storeGetSwapSpace() as
> likely cause of slowing down cache when exceeding the high
> water mark.
Indirectly. I'd recommend whomever is seeing the problem decrease the
configuration parameter for objects per bucket from the default of 50 to 10
i.e.
store_objects_per_bucket 10
What will be happening is this, storeGetSwapSpace() gets called when
the swap usage is above the high water mark. Since calculation of
reference age is now dynamic storeCheckExpired() will practically always
return expired.
storeCheckExpired() calls the dynamic calculation routine
storeExpiredReferenceAge(). storeExpiredReferenceAge() calculates
an age that varies over the range 60 seconds to 1 year over the
the cache utilisation interval swap_high to swap_low. As storeGetSwapSpace
only enters the LRU garbage collection mode when utilisation is over
swap_high, storeExpiredReferenceAge is going to return a reference age
of 60 seconds. This means that almost all objects in a bucket are going
to be removed, which is too aggressive. The rate your system can perform
unlinks will quickly become a bottle neck.
> - Deny access to dangerous TCP ports (7, 19).
Discard should also be excluded, it's just going to tie up a fd till
it times out (3 hours ?).
- Mark.
Received on Tue Jul 29 2003 - 13:15:40 MDT
This archive was generated by hypermail pre-2.1.9 : Tue Dec 09 2003 - 16:11:14 MST