Dhaval Giani reported this warning during cpu hotplug stress-tests:
| On running kernel compiles in parallel with cpu hotplug:
|
| WARNING: at arch/x86/kernel/smp.c:118
| native_smp_send_reschedule+0x21/0x36()
| Modules linked in:
| Pid: 27483, comm: cc1 Not tainted 2.6.26-rc7 #1
| [...]
| [<c0110355>] native_smp_send_reschedule+0x21/0x36
| [<c014fe8f>] force_quiescent_state+0x47/0x57
| [<c014fef0>] call_rcu+0x51/0x6d
| [<c01713b3>] __fput+0x130/0x158
| [<c0171231>] fput+0x17/0x19
| [<c016fd99>] filp_close+0x4d/0x57
| [<c016fdff>] sys_close+0x5c/0x97
IMHO the warning is a spurious one.
cpu_online_map is updated by the _cpu_down() using stop_machine_run().
Since force_quiescent_state is invoked from irqs disabled section,
stop_machine_run() won't be executing while a cpu is executing
force_quiescent_state(). Hence the cpu_online_map is stable while we're
in the irq disabled section.
However, a cpu might have been offlined _just_ before we disabled irqs
while entering force_quiescent_state(). And rcu subsystem might not yet
have handled the CPU_DEAD notification, leading to the offlined cpu's
bit being set in the rcp->cpumask.
Hence cpumask = (rcp->cpumask & cpu_online_map) to prevent sending
smp_reschedule() to an offlined CPU.
Here's the timeline:
CPU_A CPU_B
--------------------------------------------------------------
cpu_down(): .
. .
. .
stop_machine(): /* disables preemption, .
* and irqs */ .
. .
. .
take_cpu_down(); .
. .
. .
. .
cpu_disable(); /*this removes cpu .
*from cpu_online_map .
*/ .
. .
. .
restart_machine(); /* enables irqs */ .
------WINDOW DURING WHICH rcp->cpumask is stale ---------------
. call_rcu();
. /* disables irqs here */
. .force_quiescent_state();
.CPU_DEAD: .for_each_cpu(rcp->cpumask)
. . smp_send_reschedule();
. .
. . WARN_ON() for offlined CPU!
.
.
.
rcu_cpu_notify:
.
-------- WINDOW ENDS ------------------------------------------
rcu_offline_cpu() /* Which calls cpu_quiet()
* which removes
* cpu from rcp->cpumask.
*/
If a new batch was started just before calling stop_machine_run(), the
"tobe-offlined" cpu is still present in rcp-cpumask.
During a cpu-offline, from take_cpu_down(), we queue an rt-prio idle
task as the next task to be picked by the scheduler. We also call
cpu_disable() which will disable any further interrupts and remove the
cpu's bit from the cpu_online_map.
Once the stop_machine_run() successfully calls take_cpu_down(), it calls
schedule(). That's the last time a schedule is called on the offlined
cpu, and hence the last time when rdp->passed_quiesc will be set to 1
through rcu_qsctr_inc().
But the cpu_quiet() will be on this cpu will be called only when the
next RCU_SOFTIRQ occurs on this CPU. So at this time, the offlined CPU
is still set in rcp->cpumask.
Now coming back to the idle_task which truely offlines the CPU, it does
check for a pending RCU and raises the softirq, since it will find
rdp->passed_quiesc to be 0 in this case. However, since the cpu is
offline I am not sure if the softirq will trigger on the CPU.
Even if it doesn't the rcu_offline_cpu() will find that rcp->completed
is not the same as rcp->cur, which means that our cpu could be holding
up the grace period progression. Hence we call cpu_quiet() and move
ahead.
But because of the window explained in the timeline, we could still have
a call_rcu() before the RCU subsystem executes it's CPU_DEAD
notification, and we send smp_send_reschedule() to offlined cpu while
trying to force the quiescent states. The appended patch adds comments
and prevents checking for offlined cpu everytime.
cpu_online_map is updated by the _cpu_down() using stop_machine_run().
Since force_quiescent_state is invoked from irqs disabled section,
stop_machine_run() won't be executing while a cpu is executing
force_quiescent_state(). Hence the cpu_online_map is stable while we're
in the irq disabled section.
Reported-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Gautham R Shenoy <ego@in.ibm.com>
Acked-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: laijs@cn.fujitsu.com
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Rusty Russel <rusty@rustcorp.com.au>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch fixes the following warning:
kernel/sched.c:1667: warning: 'cfs_rq_set_shares' defined but not used
This seems the correct way to fix this; cfs_rq_set_shares() is only used
in a single place, which is also inside #ifdef CONFIG_FAIR_GROUP_SCHED.
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix:
kernel/sched.c: In function ‘sched_group_set_shares':
kernel/sched.c:8635: error: implicit declaration of function ‘cfs_rq_set_shares'
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'audit.b52' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/audit-current:
[PATCH] remove useless argument type in audit_filter_user()
[PATCH] audit: fix kernel-doc parameter notation
[PATCH] kernel/audit.c: nlh->nlmsg_type is gotten more than once
Vegard Nossum reported:
> WARNING: at kernel/lockdep.c:2738 check_flags+0x142/0x160()
which happens due to:
unsigned long long cpu_clock(int cpu)
{
unsigned long long clock;
unsigned long flags;
raw_local_irq_save(flags);
as lower level functions can take locks, we must not do that, use
proper lockdep-annotated irq save/restore.
Reported-by: Vegard Nossum <vegard.nossum@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
the CPU hotplug problems (crashes under high-volume unplug+replug
tests) seem to be related to migrate_dead_tasks().
Firstly I added traces to see all tasks being migrated with
migrate_live_tasks() and migrate_dead_tasks(). On my setup the problem
pops up (the one with "se == NULL" in the loop of
pick_next_task_fair()) shortly after the traces indicate that some has
been migrated with migrate_dead_tasks()). btw., I can reproduce it
much faster now with just a plain cpu down/up loop.
[disclaimer] Well, unless I'm really missing something important in
this late hour [/desclaimer] pick_next_task() is not something
appropriate for migrate_dead_tasks() :-)
the following change seems to eliminate the problem on my setup
(although, I kept it running only for a few minutes to get a few
messages indicating migrate_dead_tasks() does move tasks and the
system is still ok)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
On qemu, the backtrace would show up _after_ the "end of backtrace
testing" message.
This patch changes it to use completions instead, which will guarantee
that no such race exists.
Cc: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch adds saved stack-traces to the backtrace suite of self-tests.
Note that we don't depend on or unconditionally enable CONFIG_STACKTRACE
because not all architectures may have it (and we still want to enable the
other tests for those architectures).
Cc: Arjan van de Ven <arjan@infradead.org>
Signed-off-by: Vegard Nossum <vegard.nossum@gmail.com>
Cc: Arjan van de Ven <arjan@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Measurement shows that the difference between cgroup:/ and cgroup:/foo
wake_affine() results is that the latter succeeds significantly more.
Therefore bias the calculations towards failing the test.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Increase the accuracy of the effective_load values.
Not only consider the current increment (as per the attempted wakeup), but
also consider the delta between when we last adjusted the shares and the
current situation.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It was observed these mults can overflow.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
We found that the affine wakeup code needs rather accurate load figures
to be effective. The trouble is that updating the load figures is fairly
expensive with group scheduling. Therefore ratelimit the updating.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In case the domain is empty, pretend there is a single task on each cpu, so
that together with the boost logic we end up giving 1/n shares to each
cpu.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The bias given by source/target_load functions can be very large, disable
it by default to get faster convergence.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Priority looses much of its meaning in a hierarchical context. So don't
use it in balance decisions.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently task_h_load() computes the load of a task and uses that to either
subtract it from the total, or add to it.
However, removing or adding a task need not have any effect on the total load
at all. Imagine adding a task to a group that is local to one cpu - in that
case the total load of that cpu is unaffected.
So properly compute addition/removal:
s_i = S * rw_i / \Sum_j rw_j
s'_i = S * (rw_i + wl) / (\Sum_j rw_j + wg)
then s'_i - s_i gives the change in load.
Where s_i is the shares for cpu i, S the group weight, rw_i the runqueue weight
for that cpu, wl the weight we add (subtract) and wg the weight contribution to
the runqueue.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
doing the load balance will change cfs_rq->load.weight (that's the whole point)
but since that's part of the scale factor, we'll scale back with a different
amount.
Weight getting smaller would result in an inflated moved_load which causes
it to stop balancing too soon.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
find_busiest_group() has some assumptions about task weight being in the
NICE_0_LOAD range. Hierarchical task groups break this assumption - fix this
by replacing it with the average task weight, which will adapt the situation.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
With hierarchical grouping we can't just compare task weight to rq weight - we
need to scale the weight appropriately.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Remove the fall-back to SCHED_LOAD_SCALE by remembering the previous value of
cpu_avg_load_per_task() - this is useful because of the hierarchical group
model in which task weight can be much smaller.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Finding the least idle cpu is more accurate when done with updated shares.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Re-compute the shares on newidle - so we can make a decision based on
recent data.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
While thinking about the previous patch - I realized that using per domain
aggregate load values in load_balance_fair() is wrong. We should use the
load value for that CPU.
By not needing per domain hierarchical load values we don't need to store
per domain aggregate shares, which greatly simplifies all the math.
It basically falls apart in two separate computations:
- per domain update of the shares
- per CPU update of the hierarchical load
Also get rid of the move_group_shares() stuff - just re-compute the shares
again after a successful load balance.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
We only need to know the task_weight of the busiest rq - nothing to do
if there are no tasks there.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
We used to try and contain the loss of 'shares' by playing arithmetic
games. Replace that by noticing that at the top sched_domain we'll
always have the full weight in shares to distribute.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The idea was to balance groups until we've reached the global goal, however
Vatsa rightly pointed out that we might never reach that goal this way -
hence take out this logic.
[ the initial rationale for this 'feature' was to promote max concurrency
within a group - it does not however affect fairness ]
Reported-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It was observed that in __update_group_shares_cpu()
rq_weight > aggregate()->rq_weight
This is caused by forks/wakeups in between the initial aggregate pass and
locking of the RQs for load balance. To avoid this situation partially re-do
the aggregation once we have the RQs locked (which avoids new tasks from
appearing).
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Keeping the aggregate on the first cpu of the sched domain has two problems:
- it could collide between different sched domains on different cpus
- it could slow things down because of the remote accesses
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
show all the schedstats in /debug/sched_debug as well.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Uncouple buddy selection from wakeup granularity.
The initial idea was that buddies could run ahead as far as a normal task
can - do this by measuring a pair 'slice' just as we do for a normal task.
This means we can drop the wakeup_granularity back to 5ms.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
with sched_clock_cpu() being reasonably in sync between cpus (max 1 jiffy
difference) use this to provide cpu_clock().
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Ok, so why are we in this mess, it was:
1/w
but now we mixed that rw in the mix like:
rw/w
rw being \Sum w suggests: fiddling w, we should also fiddle rw, humm?
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
calc_delta_asym() is supposed to do the same as calc_delta_fair() except
linearly shrink the result for negative nice processes - this causes them
to have a smaller preemption threshold so that they are more easily preempted.
The problem is that for task groups se->load.weight is the per cpu share of
the actual task group weight; take that into account.
Also provide a debug switch to disable the asymmetry (which I still don't
like - but it does greatly benefit some workloads)
This would explain the interactivity issues reported against group scheduling.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
In file included from /mnt/build/linux-2.6/kernel/sched.c:1496:
/mnt/build/linux-2.6/kernel/sched_rt.c: In function '__enable_runtime':
/mnt/build/linux-2.6/kernel/sched_rt.c:339: warning: unused variable 'rd'
/mnt/build/linux-2.6/kernel/sched_rt.c: In function 'requeue_rt_entity':
/mnt/build/linux-2.6/kernel/sched_rt.c:692: warning: unused variable 'queue'
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Cc: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix:
kernel/smp.c: In function 'smp_call_function_mask':
kernel/smp.c:303: error: too many arguments to function 'smp_call_function_single'
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It's not even passed on to smp_call_function() anymore, since that
was removed. So kill it.
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
It's never used and the comments refer to nonatomic and retry
interchangably. So get rid of it.
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This adds kernel/smp.c which contains helpers for IPI function calls. In
addition to supporting the existing smp_call_function() in a more efficient
manner, it also adds a more scalable variant called smp_call_function_single()
for calling a given function on a single CPU only.
The core of this is based on the x86-64 patch from Nick Piggin, lots of
changes since then. "Alan D. Brunelle" <Alan.Brunelle@hp.com> has
contributed lots of fixes and suggestions as well. Also thanks to
Paul E. McKenney <paulmck@linux.vnet.ibm.com> for reviewing RCU usage
and getting rid of the data allocation fallback deadlock.
Acked-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
