> > My machine way up above looks like it's starting again... If I
> > understand the math here...
> >
> > Name        Size Requests Fail Releases Pgreq Pgrel Npage Hiwat
> > Minpg Maxpg Idle
> > mbpl         256    44130    0    37383   464    41   423   423
> > 1   inf    1
> > mclpl       2048    10215    0     6484  2444   574  1870  1870
> > 4 32768    4
>
> Continuing to monitor the above webserver:
>
> mbpl         256   179782    0   169941   756    77   679   687
> 1   inf    0
> mclpl       2048    38721    0    30442  6381  2210  4171  4275     4
> 32768    8
>
> 9419 mbufs in use:
>          8515 mbufs allocated to data
>          903 mbufs allocated to packet headers
>          1 mbufs allocated to socket names and addresses
> 738 calls to protocol drain routines

Strangely, the machine above which I was having to reboot every  
couple of weeks for running out of mbuf clusters has been up for 45  
days with no changes to configuration and seemingly no change in  
traffic patterns....

mbpl         256  2515234    0  2460965  4656  1195  3461  3477      
1   inf    0
mclpl       2048   494591    0   443108 54531 28736 25795 25842     4  
32768    8

It's using quite a lot still but is hovering:

53709 mbufs in use:
         52586 mbufs allocated to data
         1122 mbufs allocated to packet headers
         1 mbufs allocated to socket names and addresses
10356 calls to protocol drain routines