svn commit: r197652 - stable/7/sys/kern
Zachary Loafman
zml at FreeBSD.org
Wed Sep 30 19:40:51 UTC 2009
Author: zml
Date: Wed Sep 30 19:40:51 2009
New Revision: 197652
URL: http://svn.freebsd.org/changeset/base/197652
Log:
sched_ule in stable/7 has a bug (introduced in r180607) where a thread
that is running often will appear to not be running much at all.
sched_ule has a much less accurate mechanism for determining how much
various threads are running. Every tick, hardclock_cpu() calls
sched_tick(), and the currently running thread gets it's ts_ticks
incremented. Whenever an event of interest happens to a thread, the
ts_ticks value may be decayed; it's supposed to be a rough running
average of the last 10 seconds. So there's a ts_ltick which is the last
tick we looked at decaying ts_ticks.
The increment in sched_tick() was slightly buggy on SMP, because a
thread could get incremented on two different CPUs in the rare case
where it was swapped from one which had run sched_tick() this tick to
one which hadn't. The fix that was used relied on ts_ltick and only
incremented ts_ticks if ts_ltick was not from the current tick.
This is buggy, because any time the thread began running on a CPU in the
current tick, we would have set ts_ltick to ticks, so if it was still
running at sched_tick() we wouldn't increment.
A system with a single process that hogs the CPU and is otherwise idle,
therefore, would look like all threads were at 0%. The threads not
running are really at 0%, and the hog is not getting its ts_ticks
incremented since it went through some other runq stats that set
ts_ltick. On a 2-way SMP the thread used to get shuffled regularly
between CPUs (I think fallout from this bug), so it would appear a
little over 50% busy.
The fix is to use a separate variable to record when the last
sched_tick() increment happened.
Submitted by: Matthew Fleming (matthew.fleming at isilon.com)
Reviewed by: zml, dfr
Approved by: dfr (mentor)
Modified:
stable/7/sys/kern/sched_ule.c
Modified: stable/7/sys/kern/sched_ule.c
==============================================================================
--- stable/7/sys/kern/sched_ule.c Wed Sep 30 19:19:53 2009 (r197651)
+++ stable/7/sys/kern/sched_ule.c Wed Sep 30 19:40:51 2009 (r197652)
@@ -101,6 +101,7 @@ struct td_sched {
u_int ts_runtime; /* Number of ticks we were running */
/* The following variables are only used for pctcpu calculation */
int ts_ltick; /* Last tick that we were running on */
+ int ts_incrtick; /* Last tick that we incremented on */
int ts_ftick; /* First tick that we were running on */
int ts_ticks; /* Tick count */
#ifdef SMP
@@ -2075,6 +2076,7 @@ sched_fork_thread(struct thread *td, str
*/
ts2->ts_ticks = ts->ts_ticks;
ts2->ts_ltick = ts->ts_ltick;
+ ts2->ts_incrtick = ts->ts_incrtick;
ts2->ts_ftick = ts->ts_ftick;
child->td_user_pri = td->td_user_pri;
child->td_base_user_pri = td->td_base_user_pri;
@@ -2266,10 +2268,11 @@ sched_tick(void)
* Ticks is updated asynchronously on a single cpu. Check here to
* avoid incrementing ts_ticks multiple times in a single tick.
*/
- if (ts->ts_ltick == ticks)
+ if (ts->ts_incrtick == ticks)
return;
/* Adjust ticks for pctcpu */
ts->ts_ticks += 1 << SCHED_TICK_SHIFT;
+ ts->ts_incrtick = ticks;
ts->ts_ltick = ticks;
/*
* Update if we've exceeded our desired tick threshhold by over one
More information about the svn-src-stable-7
mailing list