[c-nsp] WCCPv2 Cisco 7600 + mask assignment problems

[Lincoln Dale (ltd)]

> >btw, if there are 6 caches here, looks like they're either dealing
with
> different traffic allocations - OR - they're not coping with
> >the load you're giving them & they've reduced the amount of traffic
being
> pushed at them; note that its 10.15% traffic allotment,
> >not 1/6th of 100%...
> 
> And yes we have deliberately unbalanced hashes currently as the caches
> have
> varying specs. We occasionally tweak the weighting to keep the
CPU/Disk
> loads even.

heh, ok.

just bear in mind that unless your cache vendor has other tricks for
recognizing bucket reallocations & where previous allocations are,
you're probably reducing your cache-hit-rate every time you rebalance
traffic, as you may be directing an existing bucket to a new cache
(where it'll be a cache-miss) when the _previous_ cache that bucket may
have gone to it could well have been a cache-hit.

once again - something some caching vendors (Cisco :) ) had thought of &
have mechanisms to deal with.



cheers,

lincoln.