Changeset a43455a1d5 ("sched/numa: Ensure task_numa_migrate() checks
the preferred node") fixes an issue where workloads would never
converge on a fully loaded (or overloaded) system.
However, it introduces a regression on less than fully loaded systems,
where workloads converge on a few NUMA nodes, instead of properly
staying spread out across the whole system. This leads to a reduction
in available memory bandwidth, and usable CPU cache, with predictable
performance problems.
The root cause appears to be an interaction between the load balancer
and NUMA balancing, where the short term load represented by the load
balancer differs from the long term load the NUMA balancing code would
like to base its decisions on.
Simply reverting a43455a1d5 would re-introduce the non-convergence
of workloads on fully loaded systems, so that is not a good option. As
an aside, the check done before a43455a1d5 only applied to a task's
preferred node, not to other candidate nodes in the system, so the
converge-on-too-few-nodes problem still happens, just to a lesser
degree.
Instead, try to compensate for the impedance mismatch between the load
balancer and NUMA balancing by only ever considering a lesser loaded
node as a destination for NUMA balancing, regardless of whether the
task is trying to move to the preferred node, or to another node.
This patch also addresses the issue that a system with a single
runnable thread would never migrate that thread to near its memory,
introduced by 095bebf61a ("sched/numa: Do not move past the balance
point if unbalanced").
A test where the main thread creates a large memory area, and spawns a
worker thread to iterate over the memory (placed on another node by
select_task_rq_fair), after which the main thread goes to sleep and
waits for the worker thread to loop over all the memory now sees the
worker thread migrated to where the memory is, instead of having all
the memory migrated over like before.
Jirka has run a number of performance tests on several systems: single
instance SpecJBB 2005 performance is 7-15% higher on a 4 node system,
with higher gains on systems with more cores per socket.
Multi-instance SpecJBB 2005 (one per node), linpack, and stream see
little or no changes with the revert of 095bebf61a and this patch.
Reported-by: Artem Bityutski <dedekind1@gmail.com>
Reported-by: Jirka Hladky <jhladky@redhat.com>
Tested-by: Jirka Hladky <jhladky@redhat.com>
Tested-by: Artem Bityutskiy <dedekind1@gmail.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20150528095249.3083ade0@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit 095bebf61a ("sched/numa: Do not move past the balance point
if unbalanced") broke convergence of workloads with just one runnable
thread, by making it impossible for the one runnable thread on the
system to move from one NUMA node to another.
Instead, the thread would remain where it was, and pull all the memory
across to its location, which is much slower than just migrating the
thread to where the memory is.
The next patch has a better fix for the issue that 095bebf61a tried
to address.
Reported-by: Jirka Hladky <jhladky@redhat.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: dedekind1@gmail.com
Cc: mgorman@suse.de
Link: http://lkml.kernel.org/r/1432753468-7785-2-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The optimized task selection logic optimistically selects a new task
to run without first doing a full put_prev_task(). This is so that we
can avoid a put/set on the common ancestors of the old and new task.
Similarly, we should only call check_cfs_rq_runtime() to throttle
eligible groups if they're part of the common ancestry, otherwise it
is possible to end up with no eligible task in the simple task
selection.
Imagine:
/root
/prev /next
/A /B
If our optimistic selection ends up throttling /next, we goto simple
and our put_prev_task() ends up throttling /prev, after which we're
going to bug out in set_next_entity() because there aren't any tasks
left.
Avoid this scenario by only throttling common ancestors.
Reported-by: Mohammed Naser <mnaser@vexxhost.com>
Reported-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Ben Segall <bsegall@google.com>
[ munged Changelog ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: pjt@google.com
Fixes: 678d5718d8 ("sched/fair: Optimize cgroup pick_next_task_fair()")
Link: http://lkml.kernel.org/r/xm26wq1oswoq.fsf@sword-of-the-dawn.mtv.corp.google.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
It is possible for fbq_classify_rq() to indicate that a CPU has tasks that
should be moved to another NUMA node, but for migrate_improves_locality
and migrate_degrades_locality to not identify those tasks.
This patch always gives preference to preferred node evaluations, and
only checks the number of faults when evaluating moves between two
non-preferred nodes on a larger NUMA system.
On a two node system, the number of faults is never evaluated. Either
a task is about to be pulled off its preferred node, or migrated onto
it.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: mgorman@suse.de
Link: http://lkml.kernel.org/r/20150514225936.35b91717@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In the below two commits (see Fixes) we have periodic timers that can
stop themselves when they're no longer required, but need to be
(re)-started when their idle condition changes.
Further complications is that we want the timer handler to always do
the forward such that it will always correctly deal with the overruns,
and we do not want to race such that the handler has already decided
to stop, but the (external) restart sees the timer still active and we
end up with a 'lost' timer.
The problem with the current code is that the re-start can come before
the callback does the forward, at which point the forward from the
callback will WARN about forwarding an enqueued timer.
Now, conceptually its easy to detect if you're before or after the fwd
by comparing the expiration time against the current time. Of course,
that's expensive (and racy) because we don't have the current time.
Alternatively one could cache this state inside the timer, but then
everybody pays the overhead of maintaining this extra state, and that
is undesired.
The only other option that I could see is the external timer_active
variable, which I tried to kill before. I would love a nicer interface
for this seemingly simple 'problem' but alas.
Fixes: 272325c482 ("perf: Fix mux_interval hrtimer wreckage")
Fixes: 77a4d1a1b9 ("sched: Cleanup bandwidth timers")
Cc: pjt@google.com
Cc: tglx@linutronix.de
Cc: klamm@yandex-team.ru
Cc: mingo@kernel.org
Cc: bsegall@google.com
Cc: hpa@zytor.com
Cc: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20150514102311.GX21418@twins.programming.kicks-ass.net
static code checking was unhappy with:
./kernel/sched/fair.c:162 WARNING: return of wrong type
int != unsigned int
get_update_sysctl_factor() is declared to return int but is
currently returning an unsigned int. The first few preprocessed
lines are:
static int get_update_sysctl_factor(void)
{
unsigned int cpus = ({ int __min1 = (cpumask_weight(cpu_online_mask));
int __min2 = (8); __min1 < __min2 ? __min1: __min2; });
unsigned int factor;
The type used by min_t() should be 'unsigned int' and the return type
of get_update_sysctl_factor() should also be 'unsigned int' as its
call-site update_sysctl() is expecting 'unsigned int' and the values
utilizing:
'factor'
'sysctl_sched_min_granularity'
'sched_nr_latency'
'sysctl_sched_wakeup_granularity'
... are also all 'unsigned int', plus cpumask_weight() is also
returning 'unsigned int'.
So the natural type to use around here is 'unsigned int'.
( Patch was compile tested with x86_64_defconfig +
CONFIG_SCHED_DEBUG=y and the changed sections in
kernel/sched/fair.i were reviewed. )
Signed-off-by: Nicholas Mc Guire <hofrat@osadl.org>
[ Improved the changelog a bit. ]
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1431716742-11077-1-git-send-email-hofrat@osadl.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The p->mm->numa_scan_seq is accessed using READ_ONCE/WRITE_ONCE
and modified without exclusive access. It is not clear why it is
accessed this way. This patch provides some documentation on that.
Suggested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rik van Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Waiman Long <waiman.long@hp.com>
Link: http://lkml.kernel.org/r/1430440094.2475.61.camel@j-VirtualBox
Signed-off-by: Ingo Molnar <mingo@kernel.org>
ACCESS_ONCE doesn't work reliably on non-scalar types. This patch removes
the rest of the existing usages of ACCESS_ONCE() in the scheduler, and use
the new READ_ONCE() and WRITE_ONCE() APIs as appropriate.
Signed-off-by: Jason Low <jason.low2@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Waiman Long <Waiman.Long@hp.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Aswin Chandramouleeswaran <aswin@hp.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Scott J Norton <scott.norton@hp.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1430251224-5764-2-git-send-email-jason.low2@hp.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
I could not find the loadavg code.. turns out it was hidden in a file
called proc.c. It further got mingled up with the cruft per rq load
indexes (which we really want to get rid of).
Move the per rq load indexes into the fair.c load-balance code (that's
the only thing that uses them) and rename proc.c to loadavg.c so we
can find it again.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
[ Did minor cleanups to the code. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Roman reported a 3 cpu lockup scenario involving __start_cfs_bandwidth().
The more I look at that code the more I'm convinced its crack, that
entire __start_cfs_bandwidth() thing is brain melting, we don't need to
cancel a timer before starting it, *hrtimer_start*() will happily remove
the timer for you if its still enqueued.
Removing that, removes a big part of the problem, no more ugly cancel
loop to get stuck in.
So now, if I understand things right, the entire reason you have this
cfs_b->lock guarded ->timer_active nonsense is to make sure we don't
accidentally lose the timer.
It appears to me that it should be possible to guarantee that same by
unconditionally (re)starting the timer when !queued. Because regardless
what hrtimer::function will return, if we beat it to (re)enqueue the
timer, it doesn't matter.
Now, because hrtimers don't come with any serialization guarantees we
must ensure both handler and (re)start loop serialize their access to
the hrtimer to avoid both trying to forward the timer at the same
time.
Update the rt bandwidth timer to match.
This effectively reverts: 09dc4ab039 ("sched/fair: Fix
tg_set_cfs_bandwidth() deadlock on rq->lock").
Reported-by: Roman Gushchin <klamm@yandex-team.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Paul Turner <pjt@google.com>
Link: http://lkml.kernel.org/r/20150415095011.804589208@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
hrtimer_start() now enforces a timer interrupt when an already expired
timer is enqueued.
Get rid of the __hrtimer_start_range_ns() invocations and the loops
around it.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Cc: Viresh Kumar <viresh.kumar@linaro.org>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20150414203502.531131739@linutronix.de
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Pull scheduler changes from Ingo Molnar:
"Major changes:
- Reworked CPU capacity code, for better SMP load balancing on
systems with assymetric CPUs. (Vincent Guittot, Morten Rasmussen)
- Reworked RT task SMP balancing to be push based instead of pull
based, to reduce latencies on large CPU count systems. (Steven
Rostedt)
- SCHED_DEADLINE support updates and fixes. (Juri Lelli)
- SCHED_DEADLINE task migration support during CPU hotplug. (Wanpeng Li)
- x86 mwait-idle optimizations and fixes. (Mike Galbraith, Len Brown)
- sched/numa improvements. (Rik van Riel)
- various cleanups"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (28 commits)
sched/core: Drop debugging leftover trace_printk call
sched/deadline: Support DL task migration during CPU hotplug
sched/core: Check for available DL bandwidth in cpuset_cpu_inactive()
sched/deadline: Always enqueue on previous rq when dl_task_timer() fires
sched/core: Remove unused argument from init_[rt|dl]_rq()
sched/deadline: Fix rt runtime corruption when dl fails its global constraints
sched/deadline: Avoid a superfluous check
sched: Improve load balancing in the presence of idle CPUs
sched: Optimize freq invariant accounting
sched: Move CFS tasks to CPUs with higher capacity
sched: Add SD_PREFER_SIBLING for SMT level
sched: Remove unused struct sched_group_capacity::capacity_orig
sched: Replace capacity_factor by usage
sched: Calculate CPU's usage statistic and put it into struct sg_lb_stats::group_usage
sched: Add struct rq::cpu_capacity_orig
sched: Make scale_rt invariant with frequency
sched: Make sched entity usage tracking scale-invariant
sched: Remove frequency scaling from cpu_capacity
sched: Track group sched_entity usage contributions
sched: Add sched_avg::utilization_avg_contrib
...
Currently when a process accesses a hugetlb range protected with
PROTNONE, unexpected COWs are triggered, which finally puts the hugetlb
subsystem into a broken/uncontrollable state, where for example
h->resv_huge_pages is subtracted too much and wraps around to a very
large number, and the free hugepage pool is no longer maintainable.
This patch simply stops changing protection for vma(VM_HUGETLB) to fix
the problem. And this also allows us to avoid useless overhead of minor
faults.
Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Suggested-by: Mel Gorman <mgorman@suse.de>
Cc: Hugh Dickins <hughd@google.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: David Rientjes <rientjes@google.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a CPU is kicked to do nohz idle balancing, it wakes up to do load
balancing on itself, followed by load balancing on behalf of idle CPUs.
But it may end up with load after the load balancing attempt on itself.
This aborts nohz idle balancing. As a result several idle CPUs are left
without tasks till such a time that an ILB CPU finds it unfavorable to
pull tasks upon itself. This delays spreading of load across idle CPUs
and worse, clutters only a few CPUs with tasks.
The effect of the above problem was observed on an SMT8 POWER server
with 2 levels of numa domains. Busy loops equal to number of cores were
spawned. Since load balancing on fork/exec is discouraged across numa
domains, all busy loops would start on one of the numa domains. However
it was expected that eventually one busy loop would run per core across
all domains due to nohz idle load balancing. But it was observed that it
took as long as 10 seconds to spread the load across numa domains.
Further investigation showed that this was a consequence of the
following:
1. An ILB CPU was chosen from the first numa domain to trigger nohz idle
load balancing [Given the experiment, upto 6 CPUs per core could be
potentially idle in this domain.]
2. However the ILB CPU would call load_balance() on itself before
initiating nohz idle load balancing.
3. Given cores are SMT8, the ILB CPU had enough opportunities to pull
tasks from its sibling cores to even out load.
4. Now that the ILB CPU was no longer idle, it would abort nohz idle
load balancing
As a result the opportunities to spread load across numa domains were
lost until such a time that the cores within the first numa domain had
equal number of tasks among themselves. This is a pretty bad scenario,
since the cores within the first numa domain would have as many as 4
tasks each, while cores in the neighbouring numa domains would all
remain idle.
Fix this, by checking if a CPU was woken up to do nohz idle load
balancing, before it does load balancing upon itself. This way we allow
idle CPUs across the system to do load balancing which results in
quicker spread of load, instead of performing load balancing within the
local sched domain hierarchy of the ILB CPU alone under circumstances
such as above.
Signed-off-by: Preeti U Murthy <preeti@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Jason Low <jason.low2@hp.com>
Cc: benh@kernel.crashing.org
Cc: daniel.lezcano@linaro.org
Cc: efault@gmx.de
Cc: iamjoonsoo.kim@lge.com
Cc: morten.rasmussen@arm.com
Cc: pjt@google.com
Cc: riel@redhat.com
Cc: srikar@linux.vnet.ibm.com
Cc: svaidy@linux.vnet.ibm.com
Cc: tim.c.chen@linux.intel.com
Cc: vincent.guittot@linaro.org
Link: http://lkml.kernel.org/r/20150326130014.21532.17158.stgit@preeti.in.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently the freq invariant accounting (in
__update_entity_runnable_avg() and sched_rt_avg_update()) get the
scale factor from a weak function call, this means that even for archs
that default on their implementation the compiler cannot see into this
function and optimize the extra scaling math away.
This is sad, esp. since its a 64-bit multiplication which can be quite
costly on some platforms.
So replace the weak function with #ifdef and __always_inline goo. This
is not quite as nice from an arch support PoV but should at least
result in compile time errors if done wrong.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/20150323131905.GF23123@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When a CPU is used to handle a lot of IRQs or some RT tasks, the remaining
capacity for CFS tasks can be significantly reduced. Once we detect such
situation by comparing cpu_capacity_orig and cpu_capacity, we trig an idle
load balance to check if it's worth moving its tasks on an idle CPU.
It's worth trying to move the task before the CPU is fully utilized to
minimize the preemption by irq or RT tasks.
Once the idle load_balance has selected the busiest CPU, it will look for an
active load balance for only two cases:
- There is only 1 task on the busiest CPU.
- We haven't been able to move a task of the busiest rq.
A CPU with a reduced capacity is included in the 1st case, and it's worth to
actively migrate its task if the idle CPU has got more available capacity for
CFS tasks. This test has been added in need_active_balance.
As a sidenote, this will not generate more spurious ilb because we already
trig an ilb if there is more than 1 busy cpu. If this cpu is the only one that
has a task, we will trig the ilb once for migrating the task.
The nohz_kick_needed function has been cleaned up a bit while adding the new
test
env.src_cpu and env.src_rq must be set unconditionnally because they are used
in need_active_balance which is called even if busiest->nr_running equals 1
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-12-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The scheduler tries to compute how many tasks a group of CPUs can handle by
assuming that a task's load is SCHED_LOAD_SCALE and a CPU's capacity is
SCHED_CAPACITY_SCALE.
'struct sg_lb_stats:group_capacity_factor' divides the capacity of the group
by SCHED_LOAD_SCALE to estimate how many task can run in the group. Then, it
compares this value with the sum of nr_running to decide if the group is
overloaded or not.
But the 'group_capacity_factor' concept is hardly working for SMT systems, it
sometimes works for big cores but fails to do the right thing for little cores.
Below are two examples to illustrate the problem that this patch solves:
1- If the original capacity of a CPU is less than SCHED_CAPACITY_SCALE
(640 as an example), a group of 3 CPUS will have a max capacity_factor of 2
(div_round_closest(3x640/1024) = 2) which means that it will be seen as
overloaded even if we have only one task per CPU.
2 - If the original capacity of a CPU is greater than SCHED_CAPACITY_SCALE
(1512 as an example), a group of 4 CPUs will have a capacity_factor of 4
(at max and thanks to the fix [0] for SMT system that prevent the apparition
of ghost CPUs) but if one CPU is fully used by rt tasks (and its capacity is
reduced to nearly nothing), the capacity factor of the group will still be 4
(div_round_closest(3*1512/1024) = 5 which is cap to 4 with [0]).
So, this patch tries to solve this issue by removing capacity_factor and
replacing it with the 2 following metrics:
- The available CPU's capacity for CFS tasks which is already used by
load_balance().
- The usage of the CPU by the CFS tasks. For the latter, utilization_avg_contrib
has been re-introduced to compute the usage of a CPU by CFS tasks.
'group_capacity_factor' and 'group_has_free_capacity' has been removed and replaced
by 'group_no_capacity'. We compare the number of task with the number of CPUs and
we evaluate the level of utilization of the CPUs to define if a group is
overloaded or if a group has capacity to handle more tasks.
For SD_PREFER_SIBLING, a group is tagged overloaded if it has more than 1 task
so it will be selected in priority (among the overloaded groups). Since [1],
SD_PREFER_SIBLING is no more concerned by the computation of 'load_above_capacity'
because local is not overloaded.
[1] 9a5d9ba6a3 ("sched/fair: Allow calculate_imbalance() to move idle cpus")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1425052454-25797-9-git-send-email-vincent.guittot@linaro.org
[ Tidied up the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Monitor the usage level of each group of each sched_domain level. The usage is
the portion of cpu_capacity_orig that is currently used on a CPU or group of
CPUs. We use the utilization_load_avg to evaluate the usage level of each
group.
The utilization_load_avg only takes into account the running time of the CFS
tasks on a CPU with a maximum value of SCHED_LOAD_SCALE when the CPU is fully
utilized. Nevertheless, we must cap utilization_load_avg which can be
temporally greater than SCHED_LOAD_SCALE after the migration of a task on this
CPU and until the metrics are stabilized.
The utilization_load_avg is in the range [0..SCHED_LOAD_SCALE] to reflect the
running load on the CPU whereas the available capacity for the CFS task is in
the range [0..cpu_capacity_orig]. In order to test if a CPU is fully utilized
by CFS tasks, we have to scale the utilization in the cpu_capacity_orig range
of the CPU to get the usage of the latter. The usage can then be compared with
the available capacity (ie cpu_capacity) to deduct the usage level of a CPU.
The frequency scaling invariance of the usage is not taken into account in this
patch, it will be solved in another patch which will deal with frequency
scaling invariance on the utilization_load_avg.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425455327-13508-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This new field 'cpu_capacity_orig' reflects the original capacity of a CPU
before being altered by rt tasks and/or IRQ
The cpu_capacity_orig will be used:
- to detect when the capacity of a CPU has been noticeably reduced so we can
trig load balance to look for a CPU with better capacity. As an example, we
can detect when a CPU handles a significant amount of irq
(with CONFIG_IRQ_TIME_ACCOUNTING) but this CPU is seen as an idle CPU by
scheduler whereas CPUs, which are really idle, are available.
- evaluate the available capacity for CFS tasks
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-7-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The average running time of RT tasks is used to estimate the remaining compute
capacity for CFS tasks. This remaining capacity is the original capacity scaled
down by a factor (aka scale_rt_capacity). This estimation of available capacity
must also be invariant with frequency scaling.
A frequency scaling factor is applied on the running time of the RT tasks for
computing scale_rt_capacity.
In sched_rt_avg_update(), we now scale the RT execution time like below:
rq->rt_avg += rt_delta * arch_scale_freq_capacity() >> SCHED_CAPACITY_SHIFT
Then, scale_rt_capacity can be summarized by:
scale_rt_capacity = SCHED_CAPACITY_SCALE * available / total
with available = total - rq->rt_avg
This has been been optimized in current code by:
scale_rt_capacity = available / (total >> SCHED_CAPACITY_SHIFT)
But we can also developed the equation like below:
scale_rt_capacity = SCHED_CAPACITY_SCALE - ((rq->rt_avg << SCHED_CAPACITY_SHIFT) / total)
and we can optimize the equation by removing SCHED_CAPACITY_SHIFT shift in
the computation of rq->rt_avg and scale_rt_capacity().
so rq->rt_avg += rt_delta * arch_scale_freq_capacity()
and
scale_rt_capacity = SCHED_CAPACITY_SCALE - (rq->rt_avg / total)
arch_scale_frequency_capacity() will be called in the hot path of the scheduler
which implies to have a short and efficient function.
As an example, arch_scale_frequency_capacity() should return a cached value that
is updated periodically outside of the hot path.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Morten.Rasmussen@arm.com
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-6-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Apply frequency scale-invariance correction factor to usage tracking.
Each segment of the running_avg_sum geometric series is now scaled by the
current frequency so the utilization_avg_contrib of each entity will be
invariant with frequency scaling.
As a result, utilization_load_avg which is the sum of utilization_avg_contrib,
becomes invariant too. So the usage level that is returned by get_cpu_usage(),
stays relative to the max frequency as the cpu_capacity which is is compared against.
Then, we want the keep the load tracking values in a 32-bit type, which implies
that the max value of {runnable|running}_avg_sum must be lower than
2^32/88761=48388 (88761 is the max weigth of a task). As LOAD_AVG_MAX = 47742,
arch_scale_freq_capacity() must return a value less than
(48388/47742) << SCHED_CAPACITY_SHIFT = 1037 (SCHED_SCALE_CAPACITY = 1024).
So we define the range to [0..SCHED_SCALE_CAPACITY] in order to avoid overflow.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Paul Turner <pjt@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425455186-13451-1-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Add usage contribution tracking for group entities. Unlike
se->avg.load_avg_contrib, se->avg.utilization_avg_contrib for group
entities is the sum of se->avg.utilization_avg_contrib for all entities on the
group runqueue.
It is _not_ influenced in any way by the task group h_load. Hence it is
representing the actual cpu usage of the group, not its intended load
contribution which may differ significantly from the utilization on
lightly utilized systems.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Paul Turner <pjt@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-3-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Add new statistics which reflect the average time a task is running on the CPU
and the sum of these running time of the tasks on a runqueue. The latter is
named utilization_load_avg.
This patch is based on the usage metric that was proposed in the 1st
versions of the per-entity load tracking patchset by Paul Turner
<pjt@google.com> but that has be removed afterwards. This version differs from
the original one in the sense that it's not linked to task_group.
The rq's utilization_load_avg will be used to check if a rq is overloaded or
not instead of trying to compute how many tasks a group of CPUs can handle.
Rename runnable_avg_period into avg_period as it is now used with both
runnable_avg_sum and running_avg_sum.
Add some descriptions of the variables to explain their differences.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Morten Rasmussen <morten.rasmussen@arm.com>
Cc: Paul Turner <pjt@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Morten.Rasmussen@arm.com
Cc: Paul Turner <pjt@google.com>
Cc: dietmar.eggemann@arm.com
Cc: efault@gmx.de
Cc: kamalesh@linux.vnet.ibm.com
Cc: linaro-kernel@lists.linaro.org
Cc: nicolas.pitre@linaro.org
Cc: preeti@linux.vnet.ibm.com
Cc: riel@redhat.com
Link: http://lkml.kernel.org/r/1425052454-25797-2-git-send-email-vincent.guittot@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226
Across the board the 4.0-rc1 numbers are much slower, and the degradation
is far worse when using the large memory footprint configs. Perf points
straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config:
- 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys
- default_send_IPI_mask_sequence_phys
- 99.99% physflat_send_IPI_mask
- 99.37% native_send_call_func_ipi
smp_call_function_many
- native_flush_tlb_others
- 99.85% flush_tlb_page
ptep_clear_flush
try_to_unmap_one
rmap_walk
try_to_unmap
migrate_pages
migrate_misplaced_page
- handle_mm_fault
- 99.73% __do_page_fault
trace_do_page_fault
do_async_page_fault
+ async_page_fault
0.63% native_send_call_func_single_ipi
generic_exec_single
smp_call_function_single
This is showing excessive migration activity even though excessive
migrations are meant to get throttled. Normally, the scan rate is tuned
on a per-task basis depending on the locality of faults. However, if
migrations fail for any reason then the PTE scanner may scan faster if
the faults continue to be remote. This means there is higher system CPU
overhead and fault trapping at exactly the time we know that migrations
cannot happen. This patch tracks when migration failures occur and
slows the PTE scanner.
Signed-off-by: Mel Gorman <mgorman@suse.de>
Reported-by: Dave Chinner <david@fromorbit.com>
Tested-by: Dave Chinner <david@fromorbit.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Aneesh Kumar <aneesh.kumar@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Commit 81907478c4 ("sched/fair: Avoid using uninitialized variable
in preferred_group_nid()") unconditionally initializes max_group with
NODE_MASK_NONE, this means that when !max_faults (max_group didn't get
set), we'll now continue the iteration with an empty mask.
Which in turn makes the actual body of the loop go away, so we'll just
iterate until completion; short circuit this by breaking out of the
loop as soon as this would happen.
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20150209113727.GS5029@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
There is a subtle interaction between the logic introduced in commit
e63da03639 ("sched/numa: Allow task switch if load imbalance improves"),
the way the load balancer counts the load on each NUMA node, and the way
NUMA hinting faults are done.
Specifically, the load balancer only counts currently running tasks
in the load, while NUMA hinting faults may cause tasks to stop, if
the page is locked by another task.
This could cause all of the threads of a large single instance workload,
like SPECjbb2005, to migrate to the same NUMA node. This was possible
because occasionally they all fault on the same few pages, and only one
of the threads remains runnable. That thread can move to the process's
preferred NUMA node without making the imbalance worse, because nothing
else is running at that time.
The fix is to check the direction of the net moving of load, and to
refuse a NUMA move if it would cause the system to move past the point
of balance. In an unbalanced state, only moves that bring us closer
to the balance point are allowed.
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: mgorman@suse.de
Link: http://lkml.kernel.org/r/20150203165648.0e9ac692@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
At least some gcc versions - validly afaict - warn about potentially
using max_group uninitialized: There's no way the compiler can prove
that the body of the conditional where it and max_faults get set/
updated gets executed; in fact, without knowing all the details of
other scheduler code, I can't prove this either.
Generally the necessary change would appear to be to clear max_group
prior to entering the inner loop, and break out of the outer loop when
it ends up being all clear after the inner one. This, however, seems
inefficient, and afaict the same effect can be achieved by exiting the
outer loop when max_faults is still zero after the inner loop.
[ mingo: changed the solution to zero initialization: uninitialized_var()
needs to die, as it's an actively dangerous construct: if in the future
a known-proven-good piece of code is changed to have a true, buggy
uninitialized variable, the compiler warning is then supressed...
The better long term solution is to clean up the code flow, so that
even simple minded compilers (and humans!) are able to read it without
getting a headache. ]
Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/54C2139202000078000588F7@mail.emea.novell.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The original purpose of rq::skip_clock_update was to avoid 'costly' clock
updates for back to back wakeup-preempt pairs. The big problem with it
has always been that the rq variable is unaware of the context and
causes indiscrimiate clock skips.
Rework the entire thing and create a sense of context by only allowing
schedule() to skip clock updates. (XXX can we measure the cost of the
added store?)
By ensuring only schedule can ever skip an update, we guarantee we're
never more than 1 tick behind on the update.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: umgwanakikbuti@gmail.com
Link: http://lkml.kernel.org/r/20150105103554.432381549@infradead.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
rq->clock{,_task} are serialized by rq->lock, verify this.
One immediate fail is the usage in scale_rt_capability, so 'annotate'
that for now, there's more 'funny' there. Maybe change rq->lock into a
raw_seqlock_t?
(Only 32-bit is affected)
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20150105103554.361872747@infradead.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: umgwanakikbuti@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Child has the same decay_count as parent. If it's not zero,
we add it to parent's cfs_rq->removed_load:
wake_up_new_task()->set_task_cpu()->migrate_task_rq_fair().
Child's load is a just garbade after copying of parent,
it hasn't been on cfs_rq yet, and it must not be added to
cfs_rq::removed_load in migrate_task_rq_fair().
The patch moves sched_entity::avg::decay_count intialization
in sched_fork(). So, migrate_task_rq_fair() does not change
removed_load.
Signed-off-by: Kirill Tkhai <ktkhai@parallels.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418644618.6074.13.camel@tkhai
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In __synchronize_entity_decay(), if "decays" happens to be zero,
se->avg.decay_count will not be zeroed, holding the positive value
assigned when dequeued last time.
This is problematic in the following case:
If this runnable task is CFS-balanced to other CPUs soon afterwards,
migrate_task_rq_fair() will treat it as a blocked task due to its
non-zero decay_count, thereby adding its load to cfs_rq->removed_load
wrongly.
Thus, we must zero se->avg.decay_count in this case as well.
Signed-off-by: Xunlei Pang <pang.xunlei@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1418745509-2609-1-git-send-email-pang.xunlei@linaro.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In effective_load, we have (long w * unsigned long tg->shares) / long W,
when w is negative, it is cast to unsigned long and hence the product is
insanely large. Fix this by casting tg->shares to long.
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Yuyang Du <yuyang.du@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Dave Jones <davej@redhat.com>
Cc: Andrey Ryabinin <a.ryabinin@samsung.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141219002956.GA25405@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit caeb178c60 ("sched/fair: Make update_sd_pick_busiest() return
'true' on a busier sd") changes groups to be ranked in the order of
overloaded > imbalance > other, and busiest group is picked according
to this order.
sgs->group_capacity_factor is used to check if the group is overloaded.
When the child domain prefers tasks to go to siblings first, the
sgs->group_capacity_factor will be set lower than one in order to
move all the excess tasks away.
However, group overloaded status is not updated when
sgs->group_capacity_factor is set to lower than one, which leads to us
missing to find the busiest group.
This patch fixes it by updating group overloaded status when sg capacity
factor is set to one, in order to find the busiest group accurately.
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Kirill Tkhai <ktkhai@parallels.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415144690-25196-1-git-send-email-wanpeng.li@linux.intel.com
[ Fixed the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Move the p->nr_cpus_allowed check into kernel/sched/core.c: select_task_rq().
This change will make fair.c, rt.c, and deadline.c all start with the
same logic.
Suggested-and-Acked-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Wanpeng Li <wanpeng.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "pang.xunlei" <pang.xunlei@linaro.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1415150077-59053-1-git-send-email-wanpeng.li@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit d670ec1317 "posix-cpu-timers: Cure SMP wobbles" fixes one glibc
test case in cost of breaking another one. After that commit, calling
clock_nanosleep(TIMER_ABSTIME, X) and then clock_gettime(&Y) can result
of Y time being smaller than X time.
Reproducer/tester can be found further below, it can be compiled and ran by:
gcc -o tst-cpuclock2 tst-cpuclock2.c -pthread
while ./tst-cpuclock2 ; do : ; done
This reproducer, when running on a buggy kernel, will complain
about "clock_gettime difference too small".
Issue happens because on start in thread_group_cputimer() we initialize
sum_exec_runtime of cputimer with threads runtime not yet accounted and
then add the threads runtime to running cputimer again on scheduler
tick, making it's sum_exec_runtime bigger than actual threads runtime.
KOSAKI Motohiro posted a fix for this problem, but that patch was never
applied: https://lkml.org/lkml/2013/5/26/191 .
This patch takes different approach to cure the problem. It calls
update_curr() when cputimer starts, that assure we will have updated
stats of running threads and on the next schedule tick we will account
only the runtime that elapsed from cputimer start. That also assure we
have consistent state between cpu times of individual threads and cpu
time of the process consisted by those threads.
Full reproducer (tst-cpuclock2.c):
#define _GNU_SOURCE
#include <unistd.h>
#include <sys/syscall.h>
#include <stdio.h>
#include <time.h>
#include <pthread.h>
#include <stdint.h>
#include <inttypes.h>
/* Parameters for the Linux kernel ABI for CPU clocks. */
#define CPUCLOCK_SCHED 2
#define MAKE_PROCESS_CPUCLOCK(pid, clock) \
((~(clockid_t) (pid) << 3) | (clockid_t) (clock))
static pthread_barrier_t barrier;
/* Help advance the clock. */
static void *chew_cpu(void *arg)
{
pthread_barrier_wait(&barrier);
while (1) ;
return NULL;
}
/* Don't use the glibc wrapper. */
static int do_nanosleep(int flags, const struct timespec *req)
{
clockid_t clock_id = MAKE_PROCESS_CPUCLOCK(0, CPUCLOCK_SCHED);
return syscall(SYS_clock_nanosleep, clock_id, flags, req, NULL);
}
static int64_t tsdiff(const struct timespec *before, const struct timespec *after)
{
int64_t before_i = before->tv_sec * 1000000000ULL + before->tv_nsec;
int64_t after_i = after->tv_sec * 1000000000ULL + after->tv_nsec;
return after_i - before_i;
}
int main(void)
{
int result = 0;
pthread_t th;
pthread_barrier_init(&barrier, NULL, 2);
if (pthread_create(&th, NULL, chew_cpu, NULL) != 0) {
perror("pthread_create");
return 1;
}
pthread_barrier_wait(&barrier);
/* The test. */
struct timespec before, after, sleeptimeabs;
int64_t sleepdiff, diffabs;
const struct timespec sleeptime = {.tv_sec = 0,.tv_nsec = 100000000 };
/* The relative nanosleep. Not sure why this is needed, but its presence
seems to make it easier to reproduce the problem. */
if (do_nanosleep(0, &sleeptime) != 0) {
perror("clock_nanosleep");
return 1;
}
/* Get the current time. */
if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &before) < 0) {
perror("clock_gettime[2]");
return 1;
}
/* Compute the absolute sleep time based on the current time. */
uint64_t nsec = before.tv_nsec + sleeptime.tv_nsec;
sleeptimeabs.tv_sec = before.tv_sec + nsec / 1000000000;
sleeptimeabs.tv_nsec = nsec % 1000000000;
/* Sleep for the computed time. */
if (do_nanosleep(TIMER_ABSTIME, &sleeptimeabs) != 0) {
perror("absolute clock_nanosleep");
return 1;
}
/* Get the time after the sleep. */
if (clock_gettime(CLOCK_PROCESS_CPUTIME_ID, &after) < 0) {
perror("clock_gettime[3]");
return 1;
}
/* The time after sleep should always be equal to or after the absolute sleep
time passed to clock_nanosleep. */
sleepdiff = tsdiff(&sleeptimeabs, &after);
if (sleepdiff < 0) {
printf("absolute clock_nanosleep woke too early: %" PRId64 "\n", sleepdiff);
result = 1;
printf("Before %llu.%09llu\n", before.tv_sec, before.tv_nsec);
printf("After %llu.%09llu\n", after.tv_sec, after.tv_nsec);
printf("Sleep %llu.%09llu\n", sleeptimeabs.tv_sec, sleeptimeabs.tv_nsec);
}
/* The difference between the timestamps taken before and after the
clock_nanosleep call should be equal to or more than the duration of the
sleep. */
diffabs = tsdiff(&before, &after);
if (diffabs < sleeptime.tv_nsec) {
printf("clock_gettime difference too small: %" PRId64 "\n", diffabs);
result = 1;
}
pthread_cancel(th);
return result;
}
Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Rik van Riel <riel@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141112155843.GA24803@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Because the whole numa task selection stuff runs with preemption
enabled (its long and expensive) we can end up migrating and selecting
oneself as a swap target. This doesn't really work out well -- we end
up trying to acquire the same lock twice for the swap migrate -- so
avoid this.
Reported-and-Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141110100328.GF29390@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch simplifies task_struct by removing the four numa_* pointers
in the same array and replacing them with the array pointer. By doing this,
on x86_64, the size of task_struct is reduced by 3 ulong pointers (24 bytes on
x86_64).
A new parameter is added to the task_faults_idx function so that it can return
an index to the correct offset, corresponding with the old precalculated
pointers.
All of the code in sched/ that depended on task_faults_idx and numa_* was
changed in order to match the new logic.
Signed-off-by: Iulia Manda <iulia.manda21@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: dave@stgolabs.net
Cc: riel@redhat.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141031001331.GA30662@winterfell
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Idle cpu is idler than non-idle cpu, so we needn't search for least_loaded_cpu
after we have found an idle cpu.
Signed-off-by: Yao Dongdong <yaodongdong@huawei.com>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1414469286-6023-1-git-send-email-yaodongdong@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In pseudo-interleaved numa_groups, all tasks try to relocate to
the group's preferred_nid. When a group is spread across multiple
NUMA nodes, this can lead to tasks swapping their location with
other tasks inside the same group, instead of swapping location with
tasks from other NUMA groups. This can keep NUMA groups from converging.
Examining all nodes, when dealing with a task in a pseudo-interleaved
NUMA group, avoids this problem. Note that only CPUs in nodes that
improve the task or group score are examined, so the loop isn't too
bad.
Tested-by: Vinod Chegu <chegu_vinod@hp.com>
Signed-off-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: "Vinod Chegu" <chegu_vinod@hp.com>
Cc: mgorman@suse.de
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20141009172747.0d97c38c@annuminas.surriel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
On systems with complex NUMA topologies, the node scoring is adjusted
to allow workloads to converge on nodes that are near each other.
The way a task group's preferred nid is determined needs to be adjusted,
in order for the preferred_nid to be consistent with group_weight scoring.
This ensures that we actually try to converge workloads on adjacent nodes.
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413530994-9732-6-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
In order to do task placement on systems with complex NUMA topologies,
it is necessary to count the faults on nodes nearby the node that is
being examined for a potential move.
In case of a system with a backplane interconnect, we are dealing with
groups of NUMA nodes; each of the nodes within a group is the same number
of hops away from nodes in other groups in the system. Optimal placement
on this topology is achieved by counting all nearby nodes equally. When
comparing nodes A and B at distance N, nearby nodes are those at distances
smaller than N from nodes A or B.
Placement strategy on a system with a glueless mesh NUMA topology needs
to be different, because there are no natural groups of nodes determined
by the hardware. Instead, when dealing with two nodes A and B at distance
N, N >= 2, there will be intermediate nodes at distance < N from both nodes
A and B. Good placement can be achieved by right shifting the faults on
nearby nodes by the number of hops from the node being scored. In this
context, a nearby node is any node less than the maximum distance in the
system away from the node. Those nodes are skipped for efficiency reasons,
there is no real policy reason to do so.
Placement policy on directly connected NUMA systems is not affected.
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Link: http://lkml.kernel.org/r/1413530994-9732-5-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Preparatory patch for adding NUMA placement on systems with
complex NUMA topology. Also fix a potential divide by zero
in group_weight()
Signed-off-by: Rik van Riel <riel@redhat.com>
Tested-by: Chegu Vinod <chegu_vinod@hp.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: mgorman@suse.de
Cc: chegu_vinod@hp.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1413530994-9732-4-git-send-email-riel@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
