K 10
svn:author
V 3
mav
K 8
svn:date
V 27
2008-12-14T20:15:30.992165Z
K 7
svn:log
V 205
To avoid one doubtless netgraph SMP scalability limitation point, switch
node queues processing from single swi:net thread to several specialized
threads.

Reviewed by:	julian
Tested with:	Netperf Cluster

END