iproute2/tc
osdl.net!shemminger 2c5474ada2 Use common code to print tcstats
(Logical change 1.78)
2004-08-31 17:54:25 +00:00
..
f_fw.c add action 2004-08-13 23:54:55 +00:00
f_route.c (Logical change 1.3) 2004-04-15 20:56:59 +00:00
f_rsvp.c (Logical change 1.3) 2004-04-15 20:56:59 +00:00
f_tcindex.c (Logical change 1.3) 2004-04-15 20:56:59 +00:00
f_u32.c Import patch jamal-p1 2004-08-23 20:20:41 +00:00
m_action.c new tc_stats handling, and const args to filter 2004-08-31 17:45:21 +00:00
m_estimator.c (Logical change 1.3) 2004-04-15 20:56:59 +00:00
m_gact.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
m_police.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
Makefile make clean remove .so 2004-08-30 22:37:50 +00:00
normal.c Change name of tablefactor. 2004-08-30 20:54:46 +00:00
pareto.c Change name of tablefactor. 2004-08-30 20:54:46 +00:00
paretonormal.c Change name of tablefactor. 2004-08-30 20:54:46 +00:00
q_atm.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_cbq.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_dsmark.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_fifo.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_gred.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_hfsc.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_htb.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_ingress.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_netem.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_prio.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_red.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_sfq.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
q_tbf.c no longer need xstats stub 2004-08-31 17:45:21 +00:00
README.last (Logical change 1.3) 2004-04-15 20:56:59 +00:00
tc_cbq.c (Logical change 1.3) 2004-04-15 20:56:59 +00:00
tc_cbq.h (Logical change 1.3) 2004-04-15 20:56:59 +00:00
tc_class.c Use common code to print tcstats 2004-08-31 17:54:25 +00:00
tc_common.h Auto merged 2004-08-23 20:21:21 +00:00
tc_core.c Adds mpu support to HTB (ATM) queueing discipline 2004-07-30 20:26:15 +00:00
tc_core.h (Logical change 1.3) 2004-04-15 20:56:59 +00:00
tc_estimator.c (Logical change 1.3) 2004-04-15 20:56:59 +00:00
tc_filter.c handle new tcstats 2004-08-31 17:45:21 +00:00
tc_qdisc.c Fix typo in requeues 2004-08-31 17:54:25 +00:00
tc_red.c (Logical change 1.3) 2004-04-15 20:56:59 +00:00
tc_red.h (Logical change 1.3) 2004-04-15 20:56:59 +00:00
tc_util.c make all filtering handles take const args. 2004-08-31 17:45:21 +00:00
tc_util.h make all filtering handles take const args. 2004-08-31 17:45:21 +00:00
tc.c id can be const char 2004-08-31 17:45:21 +00:00

Kernel code and interface.
--------------------------

* Compile time switches

There is only one, but very important, compile time switch.
It is not settable by "make config", but should be selected
manually and after a bit of thinking in <include/net/pkt_sched.h>

PSCHED_CLOCK_SOURCE can take three values:

	PSCHED_GETTIMEOFDAY
	PSCHED_JIFFIES
	PSCHED_CPU


 PSCHED_GETTIMEOFDAY

Default setting is the most conservative PSCHED_GETTIMEOFDAY.
It is very slow both because of weird slowness of do_gettimeofday()
and because it forces code to use unnatural "timeval" format,
where microseconds and seconds fields are separate.
Besides that, it will misbehave, when delays exceed 2 seconds
(f.e. very slow links or classes bounded to small slice of bandwidth)
To resume: as only you will get it working, select correct clock
source and forget about PSCHED_GETTIMEOFDAY forever.


 PSCHED_JIFFIES

Clock is derived from jiffies. On architectures with HZ=100
granularity of this clock is not enough to make reasonable
bindings to real time. However, taking into account Linux
architecture problems, which force us to use artificial
integrated clock in any case, this switch is not so bad
for schduling even on high speed networks, though policing
is not reliable.


 PSCHED_CPU

It is available only for alpha and pentiums with correct
CPU timestamp. It is the fastest way, use it when it is available,
but remember: not all pentiums have this facility, and
a lot of them have clock, broken by APM etc. etc.