Commit 367456c ("sched: Ditch per cgroup task lists for
load-balancing") completely wrecked load-balancing due to
a few silly mistakes.
Correct those and remove more pointless code.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-zk04ihygwxn7qqrlpaf73b0r@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This reverts commit 8f2f748b06.
It causes some odd regression that we have not figured out, and it's too
late in the -rc series to try to figure it out now.
As reported by Konstantin Khlebnikov, it causes consistent hangs on his
laptop (Thinkpad x220: 2x cores + HT). They can be avoided by adding
calls to "rebuild_sched_domains();" in cpuset_cpu_[in]active() for the
CPU_{ONLINE/DOWN_FAILED/DOWN_PREPARE}_FROZEN cases, but it's not at all
clear why, and it makes no sense.
Konstantin's config doesn't even have CONFIG_CPUSETS enabled, just to
make things even more interesting. So it's not the cpusets, it's just
the scheduling domains.
So until this is understood, revert.
Bisected-reported-and-tested-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pass nice as a value to proc_sched_autogroup_set_nice().
No side effect is expected, and the variable err will be overwritten with
the return value.
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/4F45FBB7.5090607@ct.jp.nec.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Per cgroup load-balance has numerous problems, chief amongst them that
there is no real sane order in them. So stop pretending it makes sense
and enqueue all tasks on a single list.
This also allows us to more easily fix the fwd progress issue
uncovered by the lock-break stuff. Rotate the list on failure to
migreate and limit the total iterations to nr_running (which with
releasing the lock isn't strictly accurate but close enough).
Also add a filter that skips very light tasks on the first attempt
around the list, this attempts to avoid shooting whole cgroups around
without affecting over balance.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: pjt@google.com
Link: http://lkml.kernel.org/n/tip-tx8yqydc7eimgq7i4rkc3a4g@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Passing large sets of similar arguments all around the load-balancer
gets tiresom when you want to modify something. Stick them all in a
helper structure and pass the structure around.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: pjt@google.com
Link: http://lkml.kernel.org/n/tip-5slqz0vhsdzewrfk9eza1aon@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When we are PI-blocked then we want to get things done ASAP.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-vw8et3445km5b8mpihf4trae@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Idle task boosting is a nono in general. There is one
exception, when PREEMPT_RT and NOHZ is active:
The idle task calls get_next_timer_interrupt() and holds
the timer wheel base->lock on the CPU and another CPU wants
to access the timer (probably to cancel it). We can safely
ignore the boosting request, as the idle CPU runs this code
with interrupts disabled and will complete the lock
protected section without being interrupted. So there is no
real need to boost.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-755rvsosz7sdzot12a3gbha6@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
For code which protects the waitqueue itself with another lock it
makes no sense to acquire the waitqueue lock for wakeup all. Provide
__wake_up_all_locked().
This is an optimization on the vanilla kernel (to be used by the
PCI code) and an important semantic distinction on -rt.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-ux6m4b8jonb9inx8xafh77ds@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Create a distinction between scheduler related preempt_enable_no_resched()
calls and the nearly one hundred other places in the kernel that do not
want to reschedule, for one reason or another.
This distinction matters for -rt, where the scheduler and the non-scheduler
preempt models (and checks) are different. For upstream it's purely
documentational.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-gs88fvx2mdv5psnzxnv575ke@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add helper to get rid of the ever repeating:
preempt_enable_no_resched();
schedule();
preempt_disable();
patterns.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-wxx7btox7coby6ifv5vzhzgp@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When a runqueue has rt_runtime_us = 0 then the only way it can
accumulate rt_time is via PI boosting. That causes the runqueue
to be throttled and replenishing does not change anything due to
rt_runtime_us = 0. So avoid that situation by clearing rt_time and
skip the throttling alltogether.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
[ Changelog ]
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-7x70cypsotjb4jvcor3edctk@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When a runqueue is throttled we cannot disable the period timer
because that timer is the only way to undo the throttling.
We got stale throttling entries when a rq was throttled and then the
global sysctl was disabled, which stopped the timer.
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
[ Added changelog ]
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/n/tip-nuj34q52p6ro7szapuz84i0v@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently, during CPU hotplug, the cpuset callbacks modify the cpusets
to reflect the state of the system, and this handling is asymmetric.
That is, upon CPU offline, that CPU is removed from all cpusets. However
when it comes back online, it is put back only to the root cpuset.
This gives rise to a significant problem during suspend/resume. During
suspend, we offline all non-boot cpus and during resume we online them back.
Which means, after a resume, all cpusets (except the root cpuset) will be
restricted to just one single CPU (the boot cpu). But the whole point of
suspend/resume is to restore the system to a state which is as close as
possible to how it was before suspend.
So to fix this, don't touch cpusets during suspend/resume. That is, modify
the cpuset-related CPU hotplug callback to just ignore CPU hotplug when it
is initiated as part of the suspend/resume sequence.
Reported-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com>
Signed-off-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: stable@vger.kernel.org
Link: http://lkml.kernel.org/r/4F460D7B.1020703@linux.vnet.ibm.com
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
So here's a boot tested patch on top of Jason's series that does
all the cleanups I talked about and turns jump labels into a
more intuitive to use facility. It should also address the
various misconceptions and confusions that surround jump labels.
Typical usage scenarios:
#include <linux/static_key.h>
struct static_key key = STATIC_KEY_INIT_TRUE;
if (static_key_false(&key))
do unlikely code
else
do likely code
Or:
if (static_key_true(&key))
do likely code
else
do unlikely code
The static key is modified via:
static_key_slow_inc(&key);
...
static_key_slow_dec(&key);
The 'slow' prefix makes it abundantly clear that this is an
expensive operation.
I've updated all in-kernel code to use this everywhere. Note
that I (intentionally) have not pushed through the rename
blindly through to the lowest levels: the actual jump-label
patching arch facility should be named like that, so we want to
decouple jump labels from the static-key facility a bit.
On non-jump-label enabled architectures static keys default to
likely()/unlikely() branches.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Acked-by: Jason Baron <jbaron@redhat.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: a.p.zijlstra@chello.nl
Cc: mathieu.desnoyers@efficios.com
Cc: davem@davemloft.net
Cc: ddaney.cavm@gmail.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20120222085809.GA26397@elte.hu
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Current the initial SCHED_RR timeslice of init_task is HZ, which means
1s, and is not same as the default SCHED_RR timeslice DEF_TIMESLICE.
Change that initial timeslice to the DEF_TIMESLICE.
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
[ s/DEF_TIMESLICE/RR_TIMESLICE/g ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/4F3C9995.3010800@ct.jp.nec.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
select_idle_sibling() is called from select_task_rq_fair(), which
already has the RCU read lock held.
Signed-off-by: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/20120217030409.11748.12491.stgit@abhimanyu
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Commit 1ac9bc69 ("sched/tracing: Add a new tracepoint for sleeptime")
added a new sched:sched_stat_sleeptime tracepoint.
It's broken: the first sample we get on a task might be bad because
of a stale sleep_start value that wasn't reset at the last task switch
because the tracepoint was not active.
It also breaks the existing schedstat samples due to the side
effects of:
- se->statistics.sleep_start = 0;
...
- se->statistics.block_start = 0;
Nor do I see means to fix it without adding overhead to the scheduler
fast path, which I'm not willing to for the sake of redundant
instrumentation.
Most importantly, sleep time information can already be constructed
by tracing context switches and wakeups, and taking the timestamp
difference between the schedule-out, the wakeup and the schedule-in.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Andrew Vagin <avagin@openvz.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/n/tip-pc4c9qhl8q6vg3bs4j6k0rbd@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The argument is not used at all, and it's not necessary, because
a specific callback handler of course knows which subsys it
belongs to.
Now only ->pupulate() takes this argument, because the handlers of
this callback always call cgroup_add_file()/cgroup_add_files().
So we reduce a few lines of code, though the shrinking of object size
is minimal.
16 files changed, 113 insertions(+), 162 deletions(-)
text data bss dec hex filename
5486240 656987 7039960 13183187 c928d3 vmlinux.o.orig
5486170 656987 7039960 13183117 c9288d vmlinux.o
Signed-off-by: Li Zefan <lizf@cn.fujitsu.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
This also fixes the following compilation warning on !SMP:
CC kernel/sched/fair.o
kernel/sched/fair.c:218:36: warning: 'max_load_balance_interval' defined but not used [-Wunused-variable]
Signed-off-by: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/4F2754A0.9090306@ct.jp.nec.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Currently we don't utilize the sched_switch field anymore.
But, simply removing sched_switch field from the middle of the
sched_stat output will break tools.
So, to stay compatible we hardcode it to zero and remove the
field from the scheduler data structures.
Update the schedstat documentation accordingly.
Signed-off-by: Rakib Mullick <rakib.mullick@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1327422836.27181.5.camel@localhost.localdomain
Signed-off-by: Ingo Molnar <mingo@elte.hu>
With a lot of small tasks, the softirq sched is nearly never called
when no_hz is enabled. In this case load_balance() is mainly called
with the newly_idle mode which doesn't update the cpu_power.
Add a next_update field which ensure a maximum update period when
there is short activity.
Having stale cpu_power information can skew the load-balancing
decisions, this is cured by the guaranteed update.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1323717668-2143-1-git-send-email-vincent.guittot@linaro.org
The block layer has some code trying to determine if two CPUs share a
cache, the scheduler has a similar function. Expose the function used
by the scheduler and make the block layer use it, thereby removing the
block layers usage of CONFIG_SCHED* and topology bits.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Jens Axboe <axboe@kernel.dk>
Link: http://lkml.kernel.org/r/1327579450.2446.95.camel@twins
This issue happens under the following conditions:
1. preemption is off
2. __ARCH_WANT_INTERRUPTS_ON_CTXSW is defined
3. RT scheduling class
4. SMP system
Sequence is as follows:
1.suppose current task is A. start schedule()
2.task A is enqueued pushable task at the entry of schedule()
__schedule
prev = rq->curr;
...
put_prev_task
put_prev_task_rt
enqueue_pushable_task
4.pick the task B as next task.
next = pick_next_task(rq);
3.rq->curr set to task B and context_switch is started.
rq->curr = next;
4.At the entry of context_swtich, release this cpu's rq->lock.
context_switch
prepare_task_switch
prepare_lock_switch
raw_spin_unlock_irq(&rq->lock);
5.Shortly after rq->lock is released, interrupt is occurred and start IRQ context
6.try_to_wake_up() which called by ISR acquires rq->lock
try_to_wake_up
ttwu_remote
rq = __task_rq_lock(p)
ttwu_do_wakeup(rq, p, wake_flags);
task_woken_rt
7.push_rt_task picks the task A which is enqueued before.
task_woken_rt
push_rt_tasks(rq)
next_task = pick_next_pushable_task(rq)
8.At find_lock_lowest_rq(), If double_lock_balance() returns 0,
lowest_rq can be the remote rq.
(But,If preemption is on, double_lock_balance always return 1 and it
does't happen.)
push_rt_task
find_lock_lowest_rq
if (double_lock_balance(rq, lowest_rq))..
9.find_lock_lowest_rq return the available rq. task A is migrated to
the remote cpu/rq.
push_rt_task
...
deactivate_task(rq, next_task, 0);
set_task_cpu(next_task, lowest_rq->cpu);
activate_task(lowest_rq, next_task, 0);
10. But, task A is on irq context at this cpu.
So, task A is scheduled by two cpus at the same time until restore from IRQ.
Task A's stack is corrupted.
To fix it, don't migrate an RT task if it's still running.
Signed-off-by: Chanho Min <chanho.min@lge.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: <stable@kernel.org>
Link: http://lkml.kernel.org/r/CAOAMb1BHA=5fm7KTewYyke6u-8DP0iUuJMpgQw54vNeXFsGpoQ@mail.gmail.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
With the recent nohz scheduler changes, rq's nohz flag
'NOHZ_TICK_STOPPED' and its associated state doesn't get cleared
immediately after the cpu exits idle. This gets cleared as part
of the next tick seen on that cpu.
For the cpu offline support, we need to clear this state
manually. Fix it by registering a cpu notifier, which clears the
nohz idle load balance state for this rq explicitly during the
CPU_DYING notification.
There won't be any nohz updates for that cpu, after the
CPU_DYING notification. But lets be extra paranoid and skip
updating the nohz state in the select_nohz_load_balancer() if
the cpu is not in active state anymore.
Reported-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Reviewed-and-tested-by: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Tested-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.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/1327026538.16150.40.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
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>
Fix new kernel-doc notation warnings:
Warning(include/linux/sched.h:2094): No description found for parameter 'p'
Warning(include/linux/sched.h:2094): Excess function parameter 'tsk' description in 'is_idle_task'
Warning(kernel/sched/cpupri.c:139): No description found for parameter 'newpri'
Warning(kernel/sched/cpupri.c:139): Excess function parameter 'pri' description in 'cpupri_set'
Warning(kernel/sched/cpupri.c:208): Excess function parameter 'bootmem' description in 'cpupri_init'
Signed-off-by: Randy Dunlap <rdunlap@xenotime.net>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'for-linus' of git://selinuxproject.org/~jmorris/linux-security:
capabilities: remove __cap_full_set definition
security: remove the security_netlink_recv hook as it is equivalent to capable()
ptrace: do not audit capability check when outputing /proc/pid/stat
capabilities: remove task_ns_* functions
capabitlies: ns_capable can use the cap helpers rather than lsm call
capabilities: style only - move capable below ns_capable
capabilites: introduce new has_ns_capabilities_noaudit
capabilities: call has_ns_capability from has_capability
capabilities: remove all _real_ interfaces
capabilities: introduce security_capable_noaudit
capabilities: reverse arguments to security_capable
capabilities: remove the task from capable LSM hook entirely
selinux: sparse fix: fix several warnings in the security server cod
selinux: sparse fix: fix warnings in netlink code
selinux: sparse fix: eliminate warnings for selinuxfs
selinux: sparse fix: declare selinux_disable() in security.h
selinux: sparse fix: move selinux_complete_init
selinux: sparse fix: make selinux_secmark_refcount static
SELinux: Fix RCU deref check warning in sel_netport_insert()
Manually fix up a semantic mis-merge wrt security_netlink_recv():
- the interface was removed in commit fd77846152 ("security: remove
the security_netlink_recv hook as it is equivalent to capable()")
- a new user of it appeared in commit a38f7907b9 ("crypto: Add
userspace configuration API")
causing no automatic merge conflict, but Eric Paris pointed out the
issue.
Eric and David reported dead machines and traced it to commit
a195f004 ("sched: Fix load-balance lock-breaking"), it turns out
there's still a scenario where we can end up re-trying forever.
Since there is no strict forward progress guarantee in the
load-balance iteration we can get stuck re-retrying the same
task-set over and over.
Creating a forward progress guarantee with the existing
structure is somewhat non-trivial, for now simply terminate the
retry loop after a few tries.
Reported-by: Eric Dumazet <eric.dumazet@gmail.com>
Tested-by: Eric Dumazet <eric.dumazet@gmail.com>
Reported-by: David Ahern <dsahern@gmail.com>
[ logic cleanup as suggested by Eric ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Link: http://lkml.kernel.org/r/1326297936.2442.157.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* 'for-3.3' of git://git.kernel.org/pub/scm/linux/kernel/git/tj/cgroup: (21 commits)
cgroup: fix to allow mounting a hierarchy by name
cgroup: move assignement out of condition in cgroup_attach_proc()
cgroup: Remove task_lock() from cgroup_post_fork()
cgroup: add sparse annotation to cgroup_iter_start() and cgroup_iter_end()
cgroup: mark cgroup_rmdir_waitq and cgroup_attach_proc() as static
cgroup: only need to check oldcgrp==newgrp once
cgroup: remove redundant get/put of task struct
cgroup: remove redundant get/put of old css_set from migrate
cgroup: Remove unnecessary task_lock before fetching css_set on migration
cgroup: Drop task_lock(parent) on cgroup_fork()
cgroups: remove redundant get/put of css_set from css_set_check_fetched()
resource cgroups: remove bogus cast
cgroup: kill subsys->can_attach_task(), pre_attach() and attach_task()
cgroup, cpuset: don't use ss->pre_attach()
cgroup: don't use subsys->can_attach_task() or ->attach_task()
cgroup: introduce cgroup_taskset and use it in subsys->can_attach(), cancel_attach() and attach()
cgroup: improve old cgroup handling in cgroup_attach_proc()
cgroup: always lock threadgroup during migration
threadgroup: extend threadgroup_lock() to cover exit and exec
threadgroup: rename signal->threadgroup_fork_lock to ->group_rwsem
...
Fix up conflict in kernel/cgroup.c due to commit e0197aae59: "cgroups:
fix a css_set not found bug in cgroup_attach_proc" that already
mentioned that the bug is fixed (differently) in Tejun's cgroup
patchset. This one, in other words.
* 'for-linus2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (165 commits)
reiserfs: Properly display mount options in /proc/mounts
vfs: prevent remount read-only if pending removes
vfs: count unlinked inodes
vfs: protect remounting superblock read-only
vfs: keep list of mounts for each superblock
vfs: switch ->show_options() to struct dentry *
vfs: switch ->show_path() to struct dentry *
vfs: switch ->show_devname() to struct dentry *
vfs: switch ->show_stats to struct dentry *
switch security_path_chmod() to struct path *
vfs: prefer ->dentry->d_sb to ->mnt->mnt_sb
vfs: trim includes a bit
switch mnt_namespace ->root to struct mount
vfs: take /proc/*/mounts and friends to fs/proc_namespace.c
vfs: opencode mntget() mnt_set_mountpoint()
vfs: spread struct mount - remaining argument of next_mnt()
vfs: move fsnotify junk to struct mount
vfs: move mnt_devname
vfs: move mnt_list to struct mount
vfs: switch pnode.h macros to struct mount *
...
* 'driver-core-next' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/driver-core: (73 commits)
arm: fix up some samsung merge sysdev conversion problems
firmware: Fix an oops on reading fw_priv->fw in sysfs loading file
Drivers:hv: Fix a bug in vmbus_driver_unregister()
driver core: remove __must_check from device_create_file
debugfs: add missing #ifdef HAS_IOMEM
arm: time.h: remove device.h #include
driver-core: remove sysdev.h usage.
clockevents: remove sysdev.h
arm: convert sysdev_class to a regular subsystem
arm: leds: convert sysdev_class to a regular subsystem
kobject: remove kset_find_obj_hinted()
m86k: gpio - convert sysdev_class to a regular subsystem
mips: txx9_sram - convert sysdev_class to a regular subsystem
mips: 7segled - convert sysdev_class to a regular subsystem
sh: dma - convert sysdev_class to a regular subsystem
sh: intc - convert sysdev_class to a regular subsystem
power: suspend - convert sysdev_class to a regular subsystem
power: qe_ic - convert sysdev_class to a regular subsystem
power: cmm - convert sysdev_class to a regular subsystem
s390: time - convert sysdev_class to a regular subsystem
...
Fix up conflicts with 'struct sysdev' removal from various platform
drivers that got changed:
- arch/arm/mach-exynos/cpu.c
- arch/arm/mach-exynos/irq-eint.c
- arch/arm/mach-s3c64xx/common.c
- arch/arm/mach-s3c64xx/cpu.c
- arch/arm/mach-s5p64x0/cpu.c
- arch/arm/mach-s5pv210/common.c
- arch/arm/plat-samsung/include/plat/cpu.h
- arch/powerpc/kernel/sysfs.c
and fix up cpu_is_hotpluggable() as per Greg in include/linux/cpu.h
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>
There is a small race between try_to_wake_up() and sched_move_task(),
which is trying to move the process being woken up.
try_to_wake_up() on CPU0 sched_move_task() on CPU1
--------------------------------+---------------------------------
raw_spin_lock_irqsave(p->pi_lock)
task_waking_fair()
->p.se.vruntime -= cfs_rq->min_vruntime
ttwu_queue()
->send reschedule IPI to CPU1
raw_spin_unlock_irqsave(p->pi_lock)
task_rq_lock()
-> tring to aquire both p->pi_lock and
rq->lock with IRQ disabled
task_move_group_fair()
-> p.se.vruntime
-= (old)cfs_rq->min_vruntime
+= (new)cfs_rq->min_vruntime
task_rq_unlock()
(via IPI)
sched_ttwu_pending()
raw_spin_lock(rq->lock)
ttwu_do_activate()
...
enqueue_entity()
child.se->vruntime += cfs_rq->min_vruntime
raw_spin_unlock(rq->lock)
As a result, vruntime of the process becomes far bigger than min_vruntime,
if (new)cfs_rq->min_vruntime >> (old)cfs_rq->min_vruntime.
This patch fixes this problem by just ignoring such process in
task_move_group_fair(), because the vruntime has already been normalized in
task_waking_fair().
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20111215143741.df82dd50.nishimura@mxp.nes.nec.co.jp
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There is a small race between do_fork() and sched_move_task(), which is
trying to move the child.
do_fork() sched_move_task()
--------------------------------+---------------------------------
copy_process()
sched_fork()
task_fork_fair()
-> vruntime of the child is initialized
based on that of the parent.
-> we can see the child in "tasks" file now.
task_rq_lock()
task_move_group_fair()
-> child.se.vruntime
-= (old)cfs_rq->min_vruntime
+= (new)cfs_rq->min_vruntime
task_rq_unlock()
wake_up_new_task()
...
enqueue_entity()
child.se.vruntime += cfs_rq->min_vruntime
As a result, vruntime of the child becomes far bigger than min_vruntime,
if (new)cfs_rq->min_vruntime >> (old)cfs_rq->min_vruntime.
This patch fixes this problem by just ignoring such process in
task_move_group_fair(), because the vruntime has already been normalized in
task_fork_fair().
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20111215143607.2ee12c5d.nishimura@mxp.nes.nec.co.jp
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There is a small race between task_fork_fair() and sched_move_task(),
which is trying to move the parent.
task_fork_fair() sched_move_task()
--------------------------------+---------------------------------
cfs_rq = task_cfs_rq(current)
-> cfs_rq is the "old" one.
curr = cfs_rq->curr
-> curr is set to the parent.
task_rq_lock()
dequeue_task()
->parent.se.vruntime -= (old)cfs_rq->min_vruntime
enqueue_task()
->parent.se.vruntime += (new)cfs_rq->min_vruntime
task_rq_unlock()
raw_spin_lock_irqsave(rq->lock)
se->vruntime = curr->vruntime
-> vruntime of the child is set to that of the parent
which has already been updated by sched_move_task().
se->vruntime -= (old)cfs_rq->min_vruntime.
raw_spin_unlock_irqrestore(rq->lock)
As a result, vruntime of the child becomes far bigger than expected,
if (new)cfs_rq->min_vruntime >> (old)cfs_rq->min_vruntime.
This patch fixes this problem by setting "cfs_rq" and "curr" after
holding the rq->lock.
Signed-off-by: Daisuke Nishimura <nishimura@mxp.nes.nec.co.jp>
Acked-by: Paul Turner <pjt@google.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Tejun Heo <tj@kernel.org>
Link: http://lkml.kernel.org/r/20111215143655.662676b0.nishimura@mxp.nes.nec.co.jp
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>
The current lock break relies on contention on the rq locks, something
which might never come because we've got IRQs disabled. Or will be
very likely because on anything with more than 2 cpus a synchronized
load-balance pass will very likely cause contention on the rq locks.
Also the sched_nr_migrate thing fails when it gets trapped the loops
of either the cgroup muck in load_balance_fair() or the move_tasks()
load condition.
Instead, use the new lb_flags field to propagate break/abort
conditions for all these loops and create a new loop outside the irq
disabled on the break being required.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-tsceb6w61q0gakmsccix6xxi@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Replace the all_pinned argument with a flags field so that we can add
some extra controls throughout that entire call chain.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-33kevm71m924ok1gpxd720v3@git.kernel.org
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>
Yong Zhang reported:
> [ INFO: suspicious RCU usage. ]
> kernel/sched/fair.c:5091 suspicious rcu_dereference_check() usage!
This is due to the sched_domain stuff being RCU protected and
commit 0b005cf5 ("sched, nohz: Implement sched group, domain
aware nohz idle load balancing") overlooking this fact.
The sd variable only lives inside the for_each_domain() block,
so we only need to wrap that.
Reported-by: Yong Zhang <yong.zhang0@gmail.com>
Tested-by: Yong Zhang <yong.zhang0@gmail.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Link: http://lkml.kernel.org/r/1323264728.32012.107.camel@twins
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Intention is to set the NOHZ_BALANCE_KICK flag for the 'ilb_cpu'. Not
for the 'cpu' which is the local cpu. Fix the typo.
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/1323199594.1984.18.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
cpu bit in the nohz.idle_cpu_mask are reset in the first busy tick after
exiting idle. So during nohz_idle_balance(), intention is to double
check if the cpu that is part of the idle_cpu_mask is indeed idle before
going ahead in performing idle balance for that cpu.
Fix the cpu typo in the idle_cpu() check during nohz_idle_balance().
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/1323199177.1984.12.camel@sbsiddha-desk.sc.intel.com
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>
nr_busy_cpus in the sched_group_power indicates whether the group
is semi idle or not. This helps remove the is_semi_idle_group() and simplify
the find_new_ilb() in the context of finding an optimal cpu that can do
idle load balancing.
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/20111202010832.656983582@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
When there are many logical cpu's that enter and exit idle often, members of
the global nohz data structure are getting modified very frequently causing
lot of cache-line contention.
Make the nohz idle load balancing more scalabale by using the sched domain
topology and 'nr_busy_cpu's in the struct sched_group_power.
Idle load balance is kicked on one of the idle cpu's when there is atleast
one idle cpu and:
- a busy rq having more than one task or
- a busy rq's scheduler group that share package resources (like HT/MC
siblings) and has more than one member in that group busy or
- for the SD_ASYM_PACKING domain, if the lower numbered cpu's in that
domain are idle compared to the busy ones.
This will help in kicking the idle load balancing request only when
there is a potential imbalance. And once it is mostly balanced, these kicks will
be minimized.
These changes helped improve the workload that is context switch intensive
between number of task pairs by 2x on a 8 socket NHM-EX based system.
Reported-by: Tim Chen <tim.c.chen@intel.com>
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/20111202010832.602203411@sbsiddha-desk.sc.intel.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>
The second call to sched_rt_period() is redundant, because the value of the
rt_runtime was already read and it was protected by the ->rt_runtime_lock.
Signed-off-by: Shan Hai <haishan.bai@gmail.com>
Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1322535836-13590-2-git-send-email-haishan.bai@gmail.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>
Instead of going through the scheduler domain hierarchy multiple times
(for giving priority to an idle core over an idle SMT sibling in a busy
core), start with the highest scheduler domain with the SD_SHARE_PKG_RESOURCES
flag and traverse the domain hierarchy down till we find an idle group.
This cleanup also addresses an issue reported by Mike where the recent
changes returned the busy thread even in the presence of an idle SMT
sibling in single socket platforms.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Tested-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1321556904.15339.25.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This tracepoint shows how long a task is sleeping in uninterruptible state.
E.g. it may show how long and where a mutex is waited for.
Signed-off-by: Andrew Vagin <avagin@openvz.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1322471015-107825-8-git-send-email-avagin@openvz.org
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>
