Kenjiro Cho wrote: > > Lars Eggert wrote: > > Please let me give you a little more background information, so you know why > > I'm interested in this, and why I think for my scenario input queue control > > makes sense. The big picture is that I'm developing (host) OS extensions to > > allow background use of any idle resources in the system. One example is the > > CPU, for which POSIX idle-time scheduling (hard priorities, possibly > > infinite preemption) basically gets me most of the way there. > > OK, then I think it isn't too hard to use "struct ifaltq" for input > queues. > > The main problem of input queueing implementation is how to trigger > "dequeue" for low priority queues. (for output queues, tx complete > interrupts trigger dequeueing.) > With only 2 queues (foreground and background), your approach seems to > be straightforward. I have some patches that allow priq and fifoq to be applied to ipintrq (other queueing disciplines should be straightforward to add). If there is interest, I could clean them up and make them available somewhere. Maybe you'd also consider to commit them to the CVS tree; changes are contained through #ifdef ALTQ_INTRQ, so they can be selectively enabled. Lars -- Lars Eggert <larse@isi.edu> Information Sciences Institute http://www.isi.edu/larse/ University of Southern California
S/MIME Cryptographic Signature