Commit 029632fbb7 ("sched: Make
separate sched*.c translation units") removed the include of
asm/mutex.h from sched.c.
This breaks the combination of:
CONFIG_MUTEX_SPIN_ON_OWNER=yes
CONFIG_HAVE_ARCH_MUTEX_CPU_RELAX=yes
like s390 without mutex debugging:
CC kernel/sched/core.o
kernel/sched/core.c: In function ‘mutex_spin_on_owner’:
kernel/sched/core.c:3287: error: implicit declaration of function ‘arch_mutex_cpu_relax’
Lets re-add the include to kernel/sched/core.c
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1326268696-30904-1-git-send-email-borntraeger@de.ibm.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
KOSAKI Motohiro noticed the following race:
> CPU0 CPU1
> --------------------------------------------------------
> deactivate_task()
> task->state = TASK_UNINTERRUPTIBLE;
> activate_task()
> rq->nr_uninterruptible--;
>
> schedule()
> deactivate_task()
> rq->nr_uninterruptible++;
>
Kosaki-San's scenario is possible when CPU0 runs
__sched_setscheduler() against CPU1's current @task.
__sched_setscheduler() does a dequeue/enqueue in order to move
the task to its new queue (position) to reflect the newly provided
scheduling parameters. However it should be completely invariant to
nr_uninterruptible accounting, sched_setscheduler() doesn't affect
readyness to run, merely policy on when to run.
So convert the inappropriate activate/deactivate_task usage to
enqueue/dequeue_task, which avoids the nr_uninterruptible accounting.
Also convert the two other sites: __migrate_task() and
normalize_task() that still use activate/deactivate_task. These sites
aren't really a problem since __migrate_task() will only be called on
non-running task (and therefore are immume to the described problem)
and normalize_task() isn't ever used on regular systems.
Also remove the comments from activate/deactivate_task since they're
misleading at best.
Reported-by: KOSAKI Motohiro <kosaki.motohiro@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1327486224.2614.45.camel@laptop
Signed-off-by: Ingo Molnar <mingo@elte.hu>
If CONFIG_SCHEDSTATS is defined, the kernel maintains
information about how long the task was sleeping or
in the case of iowait, blocking in the kernel before
getting woken up.
This will be useful for sleep time profiling.
Note: this information is only provided for sched_fair.
Other scheduling classes may choose to provide this in
the future.
Note: the delay includes the time spent on the runqueue
as well.
Signed-off-by: Arun Sharma <asharma@fb.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/1324512940-32060-2-git-send-email-asharma@fb.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Remove cfs bandwidth period check from tg_set_cfs_period.
Invalid bandwidth period's lower/upper limits are denoted
by min_cfs_quota_period/max_cfs_quota_period repsectively,
and are checked against valid period in tg_set_cfs_bandwidth().
As pjt pointed out, negative input will result in very large unsigned
numbers and will be caught by the max allowed period test.
Signed-off-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Acked-by: Paul Turner <pjt@google.com>
[ammended changelog to mention negative values]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111210135925.GA14593@linux.vnet.ibm.com
--
kernel/sched/core.c | 3 ---
1 file changed, 3 deletions(-)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Mike reported a 13% drop in netperf TCP_RR performance due to the
new remote wakeup code. Suresh too noticed some performance issues
with it.
Reducing the IPIs to only cross cache domains solves the observed
performance issues.
Reported-by: Suresh Siddha <suresh.b.siddha@intel.com>
Reported-by: Mike Galbraith <efault@gmx.de>
Acked-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Dave Kleikamp <dave.kleikamp@oracle.com>
Link: http://lkml.kernel.org/r/1323338531.17673.7.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that we initialize jump_labels before sched_init() we can use them
for the debug features without having to worry about a window where
they have the wrong setting.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-vpreo4hal9e0kzqmg5y0io2k@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that we're pointing cpuacct's root cgroup to cpustat and accounting
through task_group_account_field(), we should not access cpustat directly.
Since it is done anyway inside the acessor function, we end up accounting
it twice, which is wrong.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1322863119-14225-2-git-send-email-glommer@parallels.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Right now, after we collect tick statistics for user and system and store them
in a well known location, we keep the same statistics again for cpuacct.
Since cpuacct is hierarchical, the numbers for the root cgroup should be
absolutely equal to the system-wide numbers.
So it would be better to just use it: this patch changes cpuacct accounting
in a way that the cpustat statistics are kept in a struct kernel_cpustat percpu
array. In the root cgroup case, we just point it to the main array. The rest of
the hierarchy walk can be totally disabled later with a static branch - but I am
not doing it here.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Paul Tuner <pjt@google.com>
Link: http://lkml.kernel.org/r/1322498719-2255-4-git-send-email-glommer@parallels.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
We already have a pointer to the cgroup parent (whose data is more likely
to be in the cache than this, anyway), so there is no need to have this one
in cpuacct.
This patch makes the underlying cgroup be used instead.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Paul Tuner <pjt@google.com>
Cc: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1322498719-2255-3-git-send-email-glommer@parallels.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch changes fields in cpustat from a structure, to an
u64 array. Math gets easier, and the code is more flexible.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Paul Tuner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1322498719-2255-2-git-send-email-glommer@parallels.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Introduce nr_busy_cpus in the struct sched_group_power [Not in sched_group
because sched groups are duplicated for the SD_OVERLAP scheduler domain]
and for each cpu that enters and exits idle, this parameter will
be updated in each scheduler group of the scheduler domain that this cpu
belongs to.
To avoid the frequent update of this state as the cpu enters
and exits idle, the update of the stat during idle exit is
delayed to the first timer tick that happens after the cpu becomes busy.
This is done using NOHZ_IDLE flag in the struct rq's nohz_flags.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20111202010832.555984323@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Introduce nohz_flags in the struct rq, which will track these two flags
for now.
NOHZ_TICK_STOPPED keeps track of the tick stopped status that gets set when
the tick is stopped. It will be used to update the nohz idle load balancer data
structures during the first busy tick after the tick is restarted. At this
first busy tick after tickless idle, NOHZ_TICK_STOPPED flag will be reset.
This will minimize the nohz idle load balancer status updates that currently
happen for every tickless exit, making it more scalable when there
are many logical cpu's that enter and exit idle often.
NOHZ_BALANCE_KICK will track the need for nohz idle load balance
on this rq. This will replace the nohz_balance_kick in the rq, which was
not being updated atomically.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20111202010832.499438999@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For the SD_OVERLAP domain, sched_groups for each CPU's sched_domain are
privately allocated and not shared with any other cpu. So the
sched group allocation should come from the cpu's node for which
SD_OVERLAP sched domain is being setup.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111118230554.164910950@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This is another case where we are on our way to schedule(),
so can save a useless clock update and resulting microscopic
vruntime update.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1321971686.6855.18.camel@marge.simson.net
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There's too many sched*.[ch] files in kernel/, give them their own
directory.
(No code changed, other than Makefile glue added.)
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Since once needs to do something at conferences and fixing compile
warnings doesn't actually require much if any attention I decided
to break up the sched.c #include "*.c" fest.
This further modularizes the scheduler code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-x0fcd3mnp8f9c99grcpewmhi@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It improves perfomance, especially if autogroup is enabled.
The size of set_task_rq() was 0x180 and now it is 0xa0.
Signed-off-by: Andrew Vagin <avagin@openvz.org>
Acked-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1321020240-3874331-1-git-send-email-avagin@openvz.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Even though there are no siblings, the list should be
initialized to not contain bogus values.
Signed-off-by: Glauber Costa <glommer@parallels.com>
Acked-by: Paul Menage <paul@paulmenage.org>
Acked-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1320182360-20043-2-git-send-email-glommer@parallels.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that the linkage of jump-labels has been fixed they show a measurable
improvement in overhead for the enabled-but-unused case.
Workload is:
'taskset -c 0 perf stat --repeat 50 -e instructions,cycles,branches
bash -c "for ((i=0;i<5;i++)); do $(dirname $0)/pipe-test 20000; done"'
There's a speedup for all situations:
instructions cycles branches
-------------------------------------------------------------------------
Intel Westmere
base 806611770 745895590 146765378
+jumplabel 803090165 (-0.44%) 713381840 (-4.36%) 144561130
AMD Barcelona
base 824657415 740055589 148855354
+jumplabel 821056910 (-0.44%) 737558389 (-0.34%) 146635229
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111108042736.560831357@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In UP systems, the idle task is initialized using the init_task
structure from which the command name is taken (currently "swapper").
In SMP systems, one idle task per CPU is forked by the worker thread
from which the task structure is copied. The command name is, therefore,
"kworker/0:0" or "kworker/0:1", if not updated. Since such update was
lacking, all idle tasks in SMP systems were incorrectly named. This
longtime bug was not discovered immediately, because there is no /proc/0
entry - the bug only becomes apparent when tracing is enabled.
This patch sets the command name of the idle tasks in SMP systems to the
name that is used in the INIT_TASK structure suffixed by a slash and the
number of the CPU.
Signed-off-by: Carsten Emde <C.Emde@osadl.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111026211708.768925506@osadl.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The return-value convention for these functions varies depending on
whether they're interruptible or can timeout. It can be a little
confusing--document it.
Signed-off-by: J. Bruce Fields <bfields@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111006192246.GB28026@fieldses.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Avoid taking locks from debug prints, this avoids latencies on -rt,
and improves reliability of the debug code.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently every sched_class::set_cpus_allowed() implementation has to
copy the cpumask into task_struct::cpus_allowed, this is pointless,
put this copy in the generic code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-jhl5s9fckd9ptw1fzbqqlrd3@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This task is preparatory for the migrate_disable() implementation, but
stands on its own and provides a cleanup.
It currently only converts those sites required for task-placement.
Kosaki-san once mentioned replacing cpus_allowed with a proper
cpumask_t instead of the NR_CPUS sized array it currently is, that
would also require something like this.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Link: http://lkml.kernel.org/n/tip-e42skvaddos99psip0vce41o@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
rq's idle_at_tick is set to idle/busy during the timer tick
depending on the cpu was idle or not. This will be used later in the load
balance that will be done in the softirq context (which is a process
context in -RT kernels).
For nohz kernels, for the cpu doing nohz idle load balance on behalf of
all the idle cpu's, its rq->idle_at_tick might have a stale value (which is
recorded when it got the timer tick presumably when it is busy).
As the nohz idle load balancing is also being done at the same place
as the regular load balancing, nohz idle load balancing was bailing out
when it sees rq's idle_at_tick not set.
Thus leading to poor system utilization.
Rename rq's idle_at_tick to idle_balance and set it when someone requests
for nohz idle balance on an idle cpu.
Reported-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111003220934.892350549@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Current use of smp call function to kick the nohz idle balance can deadlock
in this scenario.
1. cpu-A did a generic_exec_single() to cpu-B and after queuing its call single
data (csd) to the call single queue, cpu-A took a timer interrupt. Actual IPI
to cpu-B to process the call single queue is not yet sent.
2. As part of the timer interrupt handler, cpu-A decided to kick cpu-B
for the idle load balancing (sets cpu-B's rq->nohz_balance_kick to 1)
and __smp_call_function_single() with nowait will queue the csd to the
cpu-B's queue. But the generic_exec_single() won't send an IPI to cpu-B
as the call single queue was not empty.
3. cpu-A is busy with lot of interrupts
4. Meanwhile cpu-B is entering and exiting idle and noticed that it has
it's rq->nohz_balance_kick set to '1'. So it will go ahead and do the
idle load balancer and clear its rq->nohz_balance_kick.
5. At this point, csd queued as part of the step-2 above is still locked
and waiting to be serviced on cpu-B.
6. cpu-A is still busy with interrupt load and now it got another timer
interrupt and as part of it decided to kick cpu-B for another idle load
balancing (as it finds cpu-B's rq->nohz_balance_kick cleared in step-4
above) and does __smp_call_function_single() with the same csd that is
still locked.
7. And we get a deadlock waiting for the csd_lock() in the
__smp_call_function_single().
Main issue here is that cpu-B can service the idle load balancer kick
request from cpu-A even with out receiving the IPI and this lead to
doing multiple __smp_call_function_single() on the same csd leading to
deadlock.
To kick a cpu, scheduler already has the reschedule vector reserved. Use
that mechanism (kick_process()) instead of using the generic smp call function
mechanism to kick off the nohz idle load balancing and avoid the deadlock.
[ This issue is present from 2.6.35+ kernels, but marking it -stable
only from v3.0+ as the proposed fix depends on the scheduler_ipi()
that is introduced recently. ]
Reported-by: Prarit Bhargava <prarit@redhat.com>
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: stable@kernel.org # v3.0+
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20111003220934.834943260@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
On -rt we observed hackbench waking all 400 tasks to a single cpu.
This is because of select_idle_sibling()'s interaction with the new
ipi based wakeup scheme.
The existing idle_cpu() test only checks to see if the current task on
that cpu is the idle task, it does not take already queued tasks into
account, nor does it take queued to be woken tasks into account.
If the remote wakeup IPIs come hard enough, there won't be time to
schedule away from the idle task, and would thus keep thinking the cpu
was in fact idle, regardless of the fact that there were already
several hundred tasks runnable.
We couldn't reproduce on mainline, but there's no reason it couldn't
happen.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-3o30p18b2paswpc9ohy2gltp@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use the generic llist primitives.
We had a private lockless list implementation in the scheduler in the wake-list
code, now that we have a generic llist implementation that provides all required
operations, switch to it.
This patch is not expected to change any behavior.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Huang Ying <ying.huang@intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: http://lkml.kernel.org/r/1315836353.26517.42.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
David reported:
Attached below is a watered-down version of rt/tst-cpuclock2.c from
GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or
similar.
Run it several times, and you will see cases where the main thread
will measure a process clock difference before and after the nanosleep
which is smaller than the cpu-burner thread's individual thread clock
difference. This doesn't make any sense since the cpu-burner thread
is part of the top-level process's thread group.
I've reproduced this on both x86-64 and sparc64 (using both 32-bit and
64-bit binaries).
For example:
[davem@boricha build-x86_64-linux]$ ./test
process: before(0.001221967) after(0.498624371) diff(497402404)
thread: before(0.000081692) after(0.498316431) diff(498234739)
self: before(0.001223521) after(0.001240219) diff(16698)
[davem@boricha build-x86_64-linux]$
The diff of 'process' should always be >= the diff of 'thread'.
I make sure to wrap the 'thread' clock measurements the most tightly
around the nanosleep() call, and that the 'process' clock measurements
are the outer-most ones.
---
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <fcntl.h>
#include <string.h>
#include <errno.h>
#include <pthread.h>
static pthread_barrier_t barrier;
static void *chew_cpu(void *arg)
{
pthread_barrier_wait(&barrier);
while (1)
__asm__ __volatile__("" : : : "memory");
return NULL;
}
int main(void)
{
clockid_t process_clock, my_thread_clock, th_clock;
struct timespec process_before, process_after;
struct timespec me_before, me_after;
struct timespec th_before, th_after;
struct timespec sleeptime;
unsigned long diff;
pthread_t th;
int err;
err = clock_getcpuclockid(0, &process_clock);
if (err)
return 1;
err = pthread_getcpuclockid(pthread_self(), &my_thread_clock);
if (err)
return 1;
pthread_barrier_init(&barrier, NULL, 2);
err = pthread_create(&th, NULL, chew_cpu, NULL);
if (err)
return 1;
err = pthread_getcpuclockid(th, &th_clock);
if (err)
return 1;
pthread_barrier_wait(&barrier);
err = clock_gettime(process_clock, &process_before);
if (err)
return 1;
err = clock_gettime(my_thread_clock, &me_before);
if (err)
return 1;
err = clock_gettime(th_clock, &th_before);
if (err)
return 1;
sleeptime.tv_sec = 0;
sleeptime.tv_nsec = 500000000;
nanosleep(&sleeptime, NULL);
err = clock_gettime(th_clock, &th_after);
if (err)
return 1;
err = clock_gettime(my_thread_clock, &me_after);
if (err)
return 1;
err = clock_gettime(process_clock, &process_after);
if (err)
return 1;
diff = process_after.tv_nsec - process_before.tv_nsec;
printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
process_before.tv_sec, process_before.tv_nsec,
process_after.tv_sec, process_after.tv_nsec, diff);
diff = th_after.tv_nsec - th_before.tv_nsec;
printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
th_before.tv_sec, th_before.tv_nsec,
th_after.tv_sec, th_after.tv_nsec, diff);
diff = me_after.tv_nsec - me_before.tv_nsec;
printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
me_before.tv_sec, me_before.tv_nsec,
me_after.tv_sec, me_after.tv_nsec, diff);
return 0;
}
This is due to us using p->se.sum_exec_runtime in
thread_group_cputime() where we iterate the thread group and sum all
data. This does not take time since the last schedule operation (tick
or otherwise) into account. We can cure this by using
task_sched_runtime() at the cost of having to take locks.
This also means we can (and must) do away with
thread_group_sched_runtime() since the modified thread_group_cputime()
is now more accurate and would deadlock when called from
thread_group_sched_runtime().
Aside of that it makes the function safe on 32 bit systems. The old
code added t->se.sum_exec_runtime unprotected. sum_exec_runtime is a
64bit value and could be changed on another cpu at the same time.
Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: stable@kernel.org
Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins
Tested-by: David Miller <davem@davemloft.net>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
RCU no longer uses this global variable, nor does anyone else. This
commit therefore removes this variable. This reduces memory footprint
and also removes some atomic instructions and memory barriers from
the dyntick-idle path.
Signed-off-by: Alex Shi <alex.shi@intel.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Long ago, using TREE_RCU with PREEMPT would result in "scheduling
while atomic" diagnostics if you blocked in an RCU read-side critical
section. However, PREEMPT now implies TREE_PREEMPT_RCU, which defeats
this diagnostic. This commit therefore adds a replacement diagnostic
based on PROVE_RCU.
Because rcu_lockdep_assert() and lockdep_rcu_dereference() are now being
used for things that have nothing to do with rcu_dereference(), rename
lockdep_rcu_dereference() to lockdep_rcu_suspicious() and add a third
argument that is a string indicating what is suspicious. This third
argument is passed in from a new third argument to rcu_lockdep_assert().
Update all calls to rcu_lockdep_assert() to add an informative third
argument.
Also, add a pair of rcu_lockdep_assert() calls from within
rcu_note_context_switch(), one complaining if a context switch occurs
in an RCU-bh read-side critical section and another complaining if a
context switch occurs in an RCU-sched read-side critical section.
These are present only if the PROVE_RCU kernel parameter is enabled.
Finally, fix some checkpatch whitespace complaints in lockdep.c.
Again, you must enable PROVE_RCU to see these new diagnostics. But you
are enabling PROVE_RCU to check out new RCU uses in any case, aren't you?
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Commit c259e01a1e ("sched: Separate the scheduler entry for
preemption") contained a boo-boo wrecking wchan output. It forgot to
put the new schedule() function in the __sched section and thereby
doesn't get properly ignored for things like wchan.
Tested-by: Simon Kirby <sim@hostway.ca>
Cc: stable@kernel.org # 2.6.39+
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110923000346.GA25425@hostway.ca
Signed-off-by: Ingo Molnar <mingo@elte.hu>
We want to override the default value of SD_NODES_PER_DOMAIN on ppc64,
so move it into linux/topology.h.
Signed-off-by: Anton Blanchard <anton@samba.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
David reported:
Attached below is a watered-down version of rt/tst-cpuclock2.c from
GLIBC. Just build it with "gcc -o test test.c -lpthread -lrt" or
similar.
Run it several times, and you will see cases where the main thread
will measure a process clock difference before and after the nanosleep
which is smaller than the cpu-burner thread's individual thread clock
difference. This doesn't make any sense since the cpu-burner thread
is part of the top-level process's thread group.
I've reproduced this on both x86-64 and sparc64 (using both 32-bit and
64-bit binaries).
For example:
[davem@boricha build-x86_64-linux]$ ./test
process: before(0.001221967) after(0.498624371) diff(497402404)
thread: before(0.000081692) after(0.498316431) diff(498234739)
self: before(0.001223521) after(0.001240219) diff(16698)
[davem@boricha build-x86_64-linux]$
The diff of 'process' should always be >= the diff of 'thread'.
I make sure to wrap the 'thread' clock measurements the most tightly
around the nanosleep() call, and that the 'process' clock measurements
are the outer-most ones.
---
#include <unistd.h>
#include <stdio.h>
#include <stdlib.h>
#include <time.h>
#include <fcntl.h>
#include <string.h>
#include <errno.h>
#include <pthread.h>
static pthread_barrier_t barrier;
static void *chew_cpu(void *arg)
{
pthread_barrier_wait(&barrier);
while (1)
__asm__ __volatile__("" : : : "memory");
return NULL;
}
int main(void)
{
clockid_t process_clock, my_thread_clock, th_clock;
struct timespec process_before, process_after;
struct timespec me_before, me_after;
struct timespec th_before, th_after;
struct timespec sleeptime;
unsigned long diff;
pthread_t th;
int err;
err = clock_getcpuclockid(0, &process_clock);
if (err)
return 1;
err = pthread_getcpuclockid(pthread_self(), &my_thread_clock);
if (err)
return 1;
pthread_barrier_init(&barrier, NULL, 2);
err = pthread_create(&th, NULL, chew_cpu, NULL);
if (err)
return 1;
err = pthread_getcpuclockid(th, &th_clock);
if (err)
return 1;
pthread_barrier_wait(&barrier);
err = clock_gettime(process_clock, &process_before);
if (err)
return 1;
err = clock_gettime(my_thread_clock, &me_before);
if (err)
return 1;
err = clock_gettime(th_clock, &th_before);
if (err)
return 1;
sleeptime.tv_sec = 0;
sleeptime.tv_nsec = 500000000;
nanosleep(&sleeptime, NULL);
err = clock_gettime(th_clock, &th_after);
if (err)
return 1;
err = clock_gettime(my_thread_clock, &me_after);
if (err)
return 1;
err = clock_gettime(process_clock, &process_after);
if (err)
return 1;
diff = process_after.tv_nsec - process_before.tv_nsec;
printf("process: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
process_before.tv_sec, process_before.tv_nsec,
process_after.tv_sec, process_after.tv_nsec, diff);
diff = th_after.tv_nsec - th_before.tv_nsec;
printf("thread: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
th_before.tv_sec, th_before.tv_nsec,
th_after.tv_sec, th_after.tv_nsec, diff);
diff = me_after.tv_nsec - me_before.tv_nsec;
printf("self: before(%lu.%.9lu) after(%lu.%.9lu) diff(%lu)\n",
me_before.tv_sec, me_before.tv_nsec,
me_after.tv_sec, me_after.tv_nsec, diff);
return 0;
}
This is due to us using p->se.sum_exec_runtime in
thread_group_cputime() where we iterate the thread group and sum all
data. This does not take time since the last schedule operation (tick
or otherwise) into account. We can cure this by using
task_sched_runtime() at the cost of having to take locks.
This also means we can (and must) do away with
thread_group_sched_runtime() since the modified thread_group_cputime()
is now more accurate and would deadlock when called from
thread_group_sched_runtime().
Reported-by: David Miller <davem@davemloft.net>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1314874459.7945.22.camel@twins
Cc: stable@kernel.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
The current cgroup context switch code was incorrect leading
to bogus counts. Furthermore, as soon as there was an active
cgroup event on a CPU, the context switch cost on that CPU
would increase by a significant amount as demonstrated by a
simple ping/pong example:
$ ./pong
Both processes pinned to CPU1, running for 10s
10684.51 ctxsw/s
Now start a cgroup perf stat:
$ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 100
$ ./pong
Both processes pinned to CPU1, running for 10s
6674.61 ctxsw/s
That's a 37% penalty.
Note that pong is not even in the monitored cgroup.
The results shown by perf stat are bogus:
$ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 100
Performance counter stats for 'sleep 100':
CPU1 <not counted> cycles test
CPU1 16,984,189,138 cycles # 0.000 GHz
The second 'cycles' event should report a count @ CPU clock
(here 2.4GHz) as it is counting across all cgroups.
The patch below fixes the bogus accounting and bypasses any
cgroup switches in case the outgoing and incoming tasks are
in the same cgroup.
With this patch the same test now yields:
$ ./pong
Both processes pinned to CPU1, running for 10s
10775.30 ctxsw/s
Start perf stat with cgroup:
$ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10
Run pong outside the cgroup:
$ /pong
Both processes pinned to CPU1, running for 10s
10687.80 ctxsw/s
The penalty is now less than 2%.
And the results for perf stat are correct:
$ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10
Performance counter stats for 'sleep 10':
CPU1 <not counted> cycles test # 0.000 GHz
CPU1 23,933,981,448 cycles # 0.000 GHz
Now perf stat reports the correct counts for
for the non cgroup event.
If we run pong inside the cgroup, then we also get the
correct counts:
$ perf stat -e cycles,cycles -A -a -G test -C 1 -- sleep 10
Performance counter stats for 'sleep 10':
CPU1 22,297,726,205 cycles test # 0.000 GHz
CPU1 23,933,981,448 cycles # 0.000 GHz
10.001457237 seconds time elapsed
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110825135803.GA4697@quad
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There is no real reason to run blk_schedule_flush_plug() with
interrupts and preemption disabled.
Move it into schedule() and call it when the task is going voluntarily
to sleep. There might be false positives when the task is woken
between that call and actually scheduling, but that's not really
different from being woken immediately after switching away.
This fixes a deadlock in the scheduler where the
blk_schedule_flush_plug() callchain enables interrupts and thereby
allows a wakeup to happen of the task that's going to sleep.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@kernel.org # 2.6.39+
Link: http://lkml.kernel.org/n/tip-dwfxtra7yg1b5r65m32ywtct@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Block-IO and workqueues call into notifier functions from the
scheduler core code with interrupts and preemption disabled. These
calls should be made before entering the scheduler core.
To simplify this, separate the scheduler core code into
__schedule(). __schedule() is directly called from the places which
set PREEMPT_ACTIVE and from schedule(). This allows us to add the work
checks into schedule(), so they are only called when a task voluntary
goes to sleep.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: stable@kernel.org # 2.6.39+
Link: http://lkml.kernel.org/r/20110622174918.813258321@linutronix.de
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When a local cfs_rq blocks we return the majority of its remaining quota to the
global bandwidth pool for use by other runqueues.
We do this only when the quota is current and there is more than
min_cfs_rq_quota [1ms by default] of runtime remaining on the rq.
In the case where there are throttled runqueues and we have sufficient
bandwidth to meter out a slice, a second timer is kicked off to handle this
delivery, unthrottling where appropriate.
Using a 'worst case' antagonist which executes on each cpu
for 1ms before moving onto the next on a fairly large machine:
no quota generations:
197.47 ms /cgroup/a/cpuacct.usage
199.46 ms /cgroup/a/cpuacct.usage
205.46 ms /cgroup/a/cpuacct.usage
198.46 ms /cgroup/a/cpuacct.usage
208.39 ms /cgroup/a/cpuacct.usage
Since we are allowed to use "stale" quota our usage is effectively bounded by
the rate of input into the global pool and performance is relatively stable.
with quota generations [1s increments]:
119.58 ms /cgroup/a/cpuacct.usage
119.65 ms /cgroup/a/cpuacct.usage
119.64 ms /cgroup/a/cpuacct.usage
119.63 ms /cgroup/a/cpuacct.usage
119.60 ms /cgroup/a/cpuacct.usage
The large deficit here is due to quota generations (/intentionally/) preventing
us from now using previously stranded slack quota. The cost is that this quota
becomes unavailable.
with quota generations and quota return:
200.09 ms /cgroup/a/cpuacct.usage
200.09 ms /cgroup/a/cpuacct.usage
198.09 ms /cgroup/a/cpuacct.usage
200.09 ms /cgroup/a/cpuacct.usage
200.06 ms /cgroup/a/cpuacct.usage
By returning unused quota we're able to both stably consume our desired quota
and prevent unintentional overages due to the abuse of slack quota from
previous quota periods (especially on a large machine).
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184758.306848658@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This change introduces statistics exports for the cpu sub-system, these are
added through the use of a stat file similar to that exported by other
subsystems.
The following exports are included:
nr_periods: number of periods in which execution occurred
nr_throttled: the number of periods above in which execution was throttle
throttled_time: cumulative wall-time that any cpus have been throttled for
this group
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Nikhil Rao <ncrao@google.com>
Signed-off-by: Bharata B Rao <bharata@linux.vnet.ibm.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184758.198901931@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Throttled tasks are invisisble to cpu-offline since they are not eligible for
selection by pick_next_task(). The regular 'escape' path for a thread that is
blocked at offline is via ttwu->select_task_rq, however this will not handle a
throttled group since there are no individual thread wakeups on an unthrottle.
Resolve this by unthrottling offline cpus so that threads can be migrated.
Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184757.989000590@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
From the perspective of load-balance and shares distribution, throttled
entities should be invisible.
However, both of these operations work on 'active' lists and are not
inherently aware of what group hierarchies may be present. In some cases this
may be side-stepped (e.g. we could sideload via tg_load_down in load balance)
while in others (e.g. update_shares()) it is more difficult to compute without
incurring some O(n^2) costs.
Instead, track hierarchicaal throttled state at time of transition. This
allows us to easily identify whether an entity belongs to a throttled hierarchy
and avoid incorrect interactions with it.
Also, when an entity leaves a throttled hierarchy we need to advance its
time averaging for shares averaging so that the elapsed throttled time is not
considered as part of the cfs_rq's operation.
We also use this information to prevent buddy interactions in the wakeup and
yield_to() paths.
Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184757.777916795@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
At the start of each period we refresh the global bandwidth pool. At this time
we must also unthrottle any cfs_rq entities who are now within bandwidth once
more (as quota permits).
Unthrottled entities have their corresponding cfs_rq->throttled flag cleared
and their entities re-enqueued.
Signed-off-by: Paul Turner <pjt@google.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184757.574628950@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Now that consumption is tracked (via update_curr()) we add support to throttle
group entities (and their corresponding cfs_rqs) in the case where this is no
run-time remaining.
Throttled entities are dequeued to prevent scheduling, additionally we mark
them as throttled (using cfs_rq->throttled) to prevent them from becoming
re-enqueued until they are unthrottled. A list of a task_group's throttled
entities are maintained on the cfs_bandwidth structure.
Note: While the machinery for throttling is added in this patch the act of
throttling an entity exceeding its bandwidth is deferred until later within
the series.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20110721184757.480608533@google.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Christian Borntraeger