Re: altq tbr_set

Dan Shechter wrote:
> I think I poted it on the wrong mailing list...

pf_ioctl() copies the value (set by pfctl(8)) when it enables altq.

> 2. Who sets tbr_timer, and who calls tbr_timeout (except for

tbr_timeout() is called by the kernel timer (from softclock()) to drain the queue in case there is no other packet event. tbr_timer shows whether the timer is armed or not, and is set only in tbr_set().

> 3. What happens when the cpu freq changes (transmeta...)?

It results in erroneous rate control.
So, machclk_usepcc should be set to 0 for such CPUs to not use the processor cycle counter.
(you can use the ALTQ_NOPCC option to force it. it is better to detect those CPUs automatically but I haven't figured out a good way to do that.)

however, if a box is actively sending packets, the CPU is probably running at the full speed.

Do you need help?

In addition to our free technical library, Pantek provides professional IT services to companies who utilize Open Source software: Learn more about Pantek's Technical Support offerings Place an order for 24/7/365 Technical Support here Learn more about Pantek, who we are, and what we do Chat with a Live Operator Related openbsd.org Links advocacy announce bugs ipv6 misc ports ports-changes security-announce smp source-changes tech Request more information about Pantek

-Kenjiro Received on Fri Sep 19 04:54:02 2003