On Sun, May 12, 2002 at 11:08:31AM +1000, Darren Reed wrote:

 > Looking at the code, it doesn't always perform the operation - it calls
 > m_get with M_DONTWAIT, which is what I was expecting to see.

Err, it does always perform the "slurp" operation, unlike m_pullup
which checks trailing-space in the first mbuf to determine if a new
mbuf should be allocated.

 > I imagine a new set of structures to describe these protocols that were
 > alignment agnostic would also be in order ?

Huh?  Protocols that are alignment-agnostic don't have to do anything,
now, or with my changes.

 > Hmmm, maybe there should be a single structure which holds all of the mbuf
 > statistic counters rather than having MPFail, MSFail, etc.  Then we could
 > make that available via sysctl too...maybe I should come back with a patch
 > for that ?

I was thinking of turning them into evcnt's.

-- 
        -- Jason R. Thorpe <thorpej@wasabisystems.com>