split out the affine-wakeup bits.
No code changed:
kernel/sched.o:
text data bss dec hex filename
42521 2858 232 45611 b22b sched.o.before
42521 2858 232 45611 b22b sched.o.after
md5:
9d76738f1272aa82f0b7affd2f51df6b sched.o.before.asm
09b31c44e9aff8666f72773dc433e2df sched.o.after.asm
(the md5's changed because stack slots changed and some registers
get scheduled by gcc in a different order - but otherwise the before
and after assembly is instruction for instruction equivalent.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use the existing calc_delta_mine() calculation for sched_slice(). This
saves a divide and simplifies the code because we share it with the
other /cfs_rq->load users.
It also improves code size:
text data bss dec hex filename
42659 2740 144 45543 b1e7 sched.o.before
42093 2740 144 44977 afb1 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Fair sleepers need to scale their latency target down by runqueue
weight. Otherwise busy systems will gain ever larger sleep bonus.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Currently we schedule to the leftmost task in the runqueue. When the
runtimes are very short because of some server/client ping-pong,
especially in over-saturated workloads, this will cycle through all
tasks trashing the cache.
Reduce cache trashing by keeping dependent tasks together by running
newly woken tasks first. However, by not running the leftmost task first
we could starve tasks because the wakee can gain unlimited runtime.
Therefore we only run the wakee if its within a small
(wakeup_granularity) window of the leftmost task. This preserves
fairness, but does alternate server/client task groups.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Current min_vruntime tracking is incorrect and will cause serious
problems when we don't run the leftmost task for some reason.
min_vruntime does two things; 1) it's used to determine a forward
direction when the u64 vruntime wraps, 2) it's used to track the
leftmost vruntime to position newly enqueued tasks from.
The current logic advances min_vruntime whenever the current task's
vruntime advance. Because the current task may pass the leftmost task
still waiting we're failing the second goal. This causes new tasks to be
placed too far ahead and thus penalizes their runtime.
Fix this by making min_vruntime the min_vruntime of the waiting tasks by
tracking it in enqueue/dequeue, and compare against current's vruntime
to obtain the absolute minimum when placing new tasks.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Kei Tokunaga reported an interactivity problem when moving tasks
between control groups.
Tasks would retain their old vruntime when moved between groups, this
can cause funny lags. Re-set the vruntime on group move to fit within
the new tree.
Reported-by: Kei Tokunaga <tokunaga.keiich@jp.fujitsu.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The following commits cause a number of regressions:
commit 58e2d4ca58
Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Date: Fri Jan 25 21:08:00 2008 +0100
sched: group scheduling, change how cpu load is calculated
commit 6b2d770026
Author: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Date: Fri Jan 25 21:08:00 2008 +0100
sched: group scheduler, fix fairness of cpu bandwidth allocation for task groups
Namely:
- very frequent wakeups on SMP, reported by PowerTop users.
- cacheline trashing on (large) SMP
- some latencies larger than 500ms
While there is a mergeable patch to fix the latter, the former issues
are not fixable in a manner suitable for .25 (we're at -rc3 now).
Hence we revert them and try again in v2.6.26.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
CC: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Tested-by: Alexey Zaytsev <alexey.zaytsev@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
pick_task_entity() duplicates existing code. This functionality can be
easily obtained using rb_last(). Avoid code duplication by using rb_last().
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Michel Dänzr has bisected an interactivity problem with
plus-reniced tasks back to this commit:
810e95ccd5 is first bad commit
commit 810e95ccd5
Author: Peter Zijlstra <a.p.zijlstra@chello.nl>
Date: Mon Oct 15 17:00:14 2007 +0200
sched: another wakeup_granularity fix
unit mis-match: wakeup_gran was used against a vruntime
fix this by assymetrically scaling the vtime of positive reniced
tasks.
Bisected-by: Michel Dänzer <michel@tungstengraphics.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The reason why we are getting better wakeup latencies for
!FAIR_USER_SCHED is because of this snippet of code in place_entity():
if (!initial) {
/* sleeps upto a single latency don't count. */
if (sched_feat(NEW_FAIR_SLEEPERS) && entity_is_task(se))
^^^^^^^^^^^^^^^^^^
vruntime -= sysctl_sched_latency;
/* ensure we never gain time by being placed backwards. */
vruntime = max_vruntime(se->vruntime, vruntime);
}
NEW_FAIR_SLEEPERS feature gives credit for sleeping only to tasks and
not group-level entities. With the patch attached, I could see that
wakeup latencies with FAIR_USER_SCHED are restored to the same level as
!FAIR_USER_SCHED.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Right now, the linux kernel (with scheduler statistics enabled) keeps track
of the maximum time a process is waiting to be scheduled. While the maximum
is a very useful metric, tracking average and total is equally useful
(at least for latencytop) to figure out the accumulated effect of scheduler
delays. The accumulated effect is important to judge the performance impact
of scheduler tuning/behavior.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
print_cfs_stats is callable from interrupt context (sysrq), hence it should
not take mutexes. Change it to use RCU since the task group data is RCU
freed anyway.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
LatencyTOP kernel infrastructure; it measures latencies in the
scheduler and tracks it system wide and per process.
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use HR-timers (when available) to deliver an accurate preemption tick.
The regular scheduler tick that runs at 1/HZ can be too coarse when nice
level are used. The fairness system will still keep the cpu utilisation 'fair'
by then delaying the task that got an excessive amount of CPU time but try to
minimize this by delivering preemption points spot-on.
The average frequency of this extra interrupt is sched_latency / nr_latency.
Which need not be higher than 1/HZ, its just that the distribution within the
sched_latency period is important.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Dmitry Adamushko found that the current implementation of the RT
balancing code left out changes to the sched_setscheduler and
rt_mutex_setprio.
This patch addresses this issue by adding methods to the schedule classes
to handle being switched out of (switched_from) and being switched into
(switched_to) a sched_class. Also a method for changing of priorities
is also added (prio_changed).
This patch also removes some duplicate logic between rt_mutex_setprio and
sched_setscheduler.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Yanmin Zhang noticed a nice optimization:
p = l * nr / nl, nl = l/g -> p = g * nr
which eliminates a do_div() from __sched_period().
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
No need to do a check for 'affine wakeup and passive balancing possibilities'
in select_task_rq_fair() when task_cpu(p) == this_cpu.
I guess, this part got missed upon introduction of per-sched_class
select_task_rq() in try_to_wake_up().
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The current wake-up code path tries to determine if it can optimize the
wake-up to "this_cpu" by computing load calculations. The problem is that
these calculations are only relevant to SCHED_OTHER tasks where load is king.
For RT tasks, priority is king. So the load calculation is completely wasted
bandwidth.
Therefore, we create a new sched_class interface to help with
pre-wakeup routing decisions and move the load calculation as a function
of CFS task's class.
Signed-off-by: Gregory Haskins <ghaskins@novell.com>
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The current load balancing scheme isn't good enough for precise
group fairness.
For example: on a 8-cpu system, I created 3 groups as under:
a = 8 tasks (cpu.shares = 1024)
b = 4 tasks (cpu.shares = 1024)
c = 3 tasks (cpu.shares = 1024)
a, b and c are task groups that have equal weight. We would expect each
of the groups to receive 33.33% of cpu bandwidth under a fair scheduler.
This is what I get with the latest scheduler git tree:
Signed-off-by: Ingo Molnar <mingo@elte.hu>
--------------------------------------------------------------------------------
Col1 | Col2 | Col3 | Col4
------|---------|-------|-------------------------------------------------------
a | 277.676 | 57.8% | 54.1% 54.1% 54.1% 54.2% 56.7% 62.2% 62.8% 64.5%
b | 116.108 | 24.2% | 47.4% 48.1% 48.7% 49.3%
c | 86.326 | 18.0% | 47.5% 47.9% 48.5%
--------------------------------------------------------------------------------
Explanation of o/p:
Col1 -> Group name
Col2 -> Cumulative execution time (in seconds) received by all tasks of that
group in a 60sec window across 8 cpus
Col3 -> CPU bandwidth received by the group in the 60sec window, expressed in
percentage. Col3 data is derived as:
Col3 = 100 * Col2 / (NR_CPUS * 60)
Col4 -> CPU bandwidth received by each individual task of the group.
Col4 = 100 * cpu_time_recd_by_task / 60
[I can share the test case that produces a similar o/p if reqd]
The deviation from desired group fairness is as below:
a = +24.47%
b = -9.13%
c = -15.33%
which is quite high.
After the patch below is applied, here are the results:
--------------------------------------------------------------------------------
Col1 | Col2 | Col3 | Col4
------|---------|-------|-------------------------------------------------------
a | 163.112 | 34.0% | 33.2% 33.4% 33.5% 33.5% 33.7% 34.4% 34.8% 35.3%
b | 156.220 | 32.5% | 63.3% 64.5% 66.1% 66.5%
c | 160.653 | 33.5% | 85.8% 90.6% 91.4%
--------------------------------------------------------------------------------
Deviation from desired group fairness is as below:
a = +0.67%
b = -0.83%
c = +0.17%
which is far better IMO. Most of other runs have yielded a deviation within
+-2% at the most, which is good.
Why do we see bad (group) fairness with current scheuler?
=========================================================
Currently cpu's weight is just the summation of individual task weights.
This can yield incorrect results. For ex: consider three groups as below
on a 2-cpu system:
CPU0 CPU1
---------------------------
A (10) B(5)
C(5)
---------------------------
Group A has 10 tasks, all on CPU0, Group B and C have 5 tasks each all
of which are on CPU1. Each task has the same weight (NICE_0_LOAD =
1024).
The current scheme would yield a cpu weight of 10240 (10*1024) for each cpu and
the load balancer will think both CPUs are perfectly balanced and won't
move around any tasks. This, however, would yield this bandwidth:
A = 50%
B = 25%
C = 25%
which is not the desired result.
What's changing in the patch?
=============================
- How cpu weights are calculated when CONFIF_FAIR_GROUP_SCHED is
defined (see below)
- API Change
- Two tunables introduced in sysfs (under SCHED_DEBUG) to
control the frequency at which the load balance monitor
thread runs.
The basic change made in this patch is how cpu weight (rq->load.weight) is
calculated. Its now calculated as the summation of group weights on a cpu,
rather than summation of task weights. Weight exerted by a group on a
cpu is dependent on the shares allocated to it and also the number of
tasks the group has on that cpu compared to the total number of
(runnable) tasks the group has in the system.
Let,
W(K,i) = Weight of group K on cpu i
T(K,i) = Task load present in group K's cfs_rq on cpu i
T(K) = Total task load of group K across various cpus
S(K) = Shares allocated to group K
NRCPUS = Number of online cpus in the scheduler domain to
which group K is assigned.
Then,
W(K,i) = S(K) * NRCPUS * T(K,i) / T(K)
A load balance monitor thread is created at bootup, which periodically
runs and adjusts group's weight on each cpu. To avoid its overhead, two
min/max tunables are introduced (under SCHED_DEBUG) to control the rate
at which it runs.
Fixes from: Peter Zijlstra <a.p.zijlstra@chello.nl>
- don't start the load_balance_monitor when there is only a single cpu.
- rename the kthread because its currently longer than TASK_COMM_LEN
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
This patch changes how the cpu load exerted by fair_sched_class tasks
is calculated. Load exerted by fair_sched_class tasks on a cpu is now
a summation of the group weights, rather than summation of task weights.
Weight exerted by a group on a cpu is dependent on the shares allocated
to it.
This version of patch has a minor impact on code size, but should have
no runtime/functional impact for !CONFIG_FAIR_GROUP_SCHED.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Minor bug fixes for the group scheduler:
- Use a mutex to serialize add/remove of task groups and also when
changing shares of a task group. Use the same mutex when printing
cfs_rq debugging stats for various task groups.
- Use list_for_each_entry_rcu in for_each_leaf_cfs_rq macro (when
walking task group list)
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
measurements by Yanmin Zhang have shown that SCHED_BATCH tasks benefit
if they run the same place_entity() logic as SCHED_OTHER tasks - so
uniformize behavior in this area.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
do more agressive yield for SCHED_BATCH tuned tasks: they are all
about throughput anyway. This allows a gentler migration path for
any apps that relied on stronger yield.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Commit cfb5285660 removed a useful feature for
us, which provided a cpu accounting resource controller. This feature would be
useful if someone wants to group tasks only for accounting purpose and doesnt
really want to exercise any control over their cpu consumption.
The patch below reintroduces the feature. It is based on Paul Menage's
original patch (Commit 62d0df6406), with
these differences:
- Removed load average information. I felt it needs more thought (esp
to deal with SMP and virtualized platforms) and can be added for
2.6.25 after more discussions.
- Convert group cpu usage to be nanosecond accurate (as rest of the cfs
stats are) and invoke cpuacct_charge() from the respective scheduler
classes
- Make accounting scalable on SMP systems by splitting the usage
counter to be per-cpu
- Move the code from kernel/cpu_acct.c to kernel/sched.c (since the
code is not big enough to warrant a new file and also this rightly
needs to live inside the scheduler. Also things like accessing
rq->lock while reading cpu usage becomes easier if the code lived in
kernel/sched.c)
The patch also modifies the cpu controller not to provide the same accounting
information.
Tested-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Tested the patches on top of 2.6.24-rc3. The patches work fine. Ran
some simple tests like cpuspin (spin on the cpu), ran several tasks in
the same group and timed them. Compared their time stamps with
cpuacct.usage.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Balbir Singh <balbir@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
increase the default minimum granularity some more - this gives us
more performance in aim7 benchmarks.
also correct some comments: we scale with ilog(ncpus) + 1.
Signed-off-by: Zou Nan hai <nanhai.zou@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Sukadev Bhattiprolu reported a kernel crash with control groups.
There are couple of problems discovered by Suka's test:
- The test requires the cgroup filesystem to be mounted with
atleast the cpu and ns options (i.e both namespace and cpu
controllers are active in the same hierarchy).
# mkdir /dev/cpuctl
# mount -t cgroup -ocpu,ns none cpuctl
(or simply)
# mount -t cgroup none cpuctl -> Will activate all controllers
in same hierarchy.
- The test invokes clone() with CLONE_NEWNS set. This causes a a new child
to be created, also a new group (do_fork->copy_namespaces->ns_cgroup_clone->
cgroup_clone) and the child is attached to the new group (cgroup_clone->
attach_task->sched_move_task). At this point in time, the child's scheduler
related fields are uninitialized (including its on_rq field, which it has
inherited from parent). As a result sched_move_task thinks its on
runqueue, when it isn't.
As a solution to this problem, I moved sched_fork() call, which
initializes scheduler related fields on a new task, before
copy_namespaces(). I am not sure though whether moving up will
cause other side-effects. Do you see any issue?
- The second problem exposed by this test is that task_new_fair()
assumes that parent and child will be part of the same group (which
needn't be as this test shows). As a result, cfs_rq->curr can be NULL
for the child.
The solution is to test for curr pointer being NULL in
task_new_fair().
With the patch below, I could run ns_exec() fine w/o a crash.
Reported-by: Sukadev Bhattiprolu <sukadev@us.ibm.com>
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
clean up the preemption check to not use unnecessary 64-bit
variables. This improves code size:
text data bss dec hex filename
44227 3326 36 47589 b9e5 sched.o.before
44201 3326 36 47563 b9cb sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
wakeup preemption fix: do not make it dependent on p->prio.
Preemption purely depends on ->vruntime.
This improves preemption in mixed-nice-level workloads.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove PREEMPT_RESTRICT. (this is a separate commit so that any
regression related to the removal itself is bisectable)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Yanmin Zhang reported an aim7 regression and bisected it down to:
| commit 38ad464d41
| Author: Ingo Molnar <mingo@elte.hu>
| Date: Mon Oct 15 17:00:02 2007 +0200
|
| sched: uniform tunings
|
| use the same defaults on both UP and SMP.
fix this by reintroducing similar SMP tunings again. This resolves
the regression.
(also update the comments to match the ilog2(nr_cpus) tuning effect)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
we lost the sched_min_granularity tunable to a clever optimization
that uses the sched_latency/min_granularity ratio - but the ratio
is quite unintuitive to users and can also crash the kernel if the
ratio is set to 0. So reintroduce the min_granularity tunable,
while keeping the ratio maintained internally.
no functionality changed.
[ mingo@elte.hu: some fixlets. ]
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Add a few comments to place_entity(). No code changed.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
vslice was missing a factor NICE_0_LOAD, as weight is in
weight*NICE_0_LOAD units.
the effect of this bug was larger initial slices and
thus latency-noisier forks.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix style of swap() macro in kernel/sched_fair.c.
( this macro should eventually move to a general header, as ext3 uses
a similar construct too. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
At the moment, a lot of load balancing code that is irrelevant to non
SMP systems gets included during non SMP builds.
This patch addresses this issue and reduces the binary size on non
SMP systems:
text data bss dec hex filename
10983 28 1192 12203 2fab sched.o.before
10739 28 1192 11959 2eb7 sched.o.after
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
At the moment, balance_tasks() provides low level functionality for both
move_tasks() and move_one_task() (indirectly) via the load_balance()
function (in the sched_class interface) which also provides dual
functionality. This dual functionality complicates the interfaces and
internal mechanisms and makes the run time overhead of operations that
are called with two run queue locks held.
This patch addresses this issue and reduces the overhead of these
operations.
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Child task may be added on a different cpu that the one on which parent
is running. In which case, task_new_fair() should check whether the new
born task's parent entity should be added as well on the cfs_rq.
Patch below fixes the problem in task_new_fair.
This could fix the put_prev_task_fair() crashes reported.
Reported-by: Kamalesh Babulal <kamalesh@linux.vnet.ibm.com>
Reported-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
reintroduce a simplified version of cache-hot/cold scheduling
affinity. This improves performance with certain SMP workloads,
such as sysbench.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
speed up context-switches a bit by not clearing p->exec_start.
(as a side-effect, this also makes p->exec_start a universal timestamp
available to cache-hot estimations.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Prevent wakeup over-scheduling. Once a task has been preempted by a
task of the same or lower priority, it becomes ineligible for repeated
preemption by same until it has been ticked, or slept. Instead, the
task is marked for preemption at the next tick. Tasks of higher
priority still preempt immediately.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Implement feature bit to disable forced preemption. This way
it can be checked whether a workload is overscheduling or not.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The following patch (sched: disable sleeper_fairness on SCHED_BATCH)
seems to break GROUP_SCHED. Although, it may be 'oops'-less due to the
possibility of 'p' being always a valid address.
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
disable sleeper fairness for batch tasks - they are about
batch processing after all.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
unit mis-match: wakeup_gran was used against a vruntime
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
noticed by Peter Zijlstra:
fix: move the CPU check into ->task_new_fair(), this way we
can call place_entity() and get child ->vruntime right at
initial wakeup time.
(without this there can be large latencies)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
The thing is that __pick_next_entity() must never be called when
first_fair(cfs_rq) == NULL. It wouldn't be a problem, should 'run_node'
be the very first field of 'struct sched_entity' (and it's the second).
The 'nr_running != 0' check is _not_ enough, due to the fact that
'current' is not within the tree. Generic paths are ok (e.g. schedule()
as put_prev_task() is called previously)... I'm more worried about e.g.
migration_call() -> CPU_DEAD_FROZEN -> migrate_dead_tasks()... if
'current' == rq->idle, no problems.. if it's one of the SCHED_NORMAL
tasks (or imagine, some other use-cases in the future -- i.e. we should
not make outer world dependent on internal details of sched_fair class)
-- it may be "Houston, we've got a problem" case.
it's +16 bytes to the ".text". Another variant is to make 'run_node' the
first data member of 'struct sched_entity' but an additional check (se !
= NULL) is still needed in pick_next_entity().
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Make vslice accurate wrt nice levels, and add some comments
while we're at it.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
mark scheduling classes as const. The speeds up the code
a bit and shrinks it:
text data bss dec hex filename
40027 4018 292 44337 ad31 sched.o.before
40190 3842 292 44324 ad24 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
There is a possibility that because of task of a group moving from one
cpu to another, it may gain more cpu time that desired. See
http://marc.info/?l=linux-kernel&m=119073197730334 for details.
This is an attempt to fix that problem. Basically it simulates dequeue
of higher level entities as if they are going to sleep. Similarly it
simulate wakeup of higher level entities as if they are waking up from
sleep.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
fix yield bugs due to the current-not-in-rbtree changes: the task is
not in the rbtree so rbtree-removal is a no-no.
[ From: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>: build fix. ]
also, nice code size reduction:
kernel/sched.o:
text data bss dec hex filename
38323 3506 24 41853 a37d sched.o.before
38236 3506 24 41766 a326 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
group scheduler wakeup latency fix: when checking for preemption
we must check cross-group too, not just intra-group.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Lee Schermerhorn noticed that set_leftmost() contains dead code,
remove this.
Reported-by: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
fix sign check error in place_entity() - we'd get excessive
latencies due to negatives being converted to large u64's.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
undo some of the recent changes that are not needed after all,
such as last_min_vruntime.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
entity_key() fix - we'd occasionally end up with a 0 vruntime
in the !initial case.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
debug feature: check how well we schedule within a reasonable
vruntime 'spread' range. (note that CPU overload can increase
the spread, so this is not a hard condition, but normal loads
should be within the spread.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
add vslice: the load-dependent "virtual slice" a task should
run ideally, so that the observed latency stays within the
sched_latency window.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
With the view of supporting user-id based fair scheduling (and not just
container-based fair scheduling), this patch renames several functions
and makes them independent of whether they are being used for container
or user-id based fair scheduling.
Also fix a problem reported by KAMEZAWA Hiroyuki (wrt allocating
less-sized array for tg->cfs_rq[] and tf->se[]).
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
- Print &rq->cfs statistics as well (useful for group scheduling)
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
- fix a minor bug in yield (seen for CONFIG_FAIR_GROUP_SCHED),
group scheduling would skew when yield was called.
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
the 'p' (task_struct) parameter in the sched_class :: yield_task() is
redundant as the caller is always the 'current'. Get rid of it.
text data bss dec hex filename
24341 2734 20 27095 69d7 sched.o.before
24330 2734 20 27084 69cc sched.o.after
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
due to the fact that we no longer keep the 'current' within the tree,
dequeue/enqueue_entity() is useless for the 'current' in
task_new_fair(). We are about to reschedule and
sched_class->put_prev_task() will put the 'current' back into the tree,
based on its new key.
text data bss dec hex filename
24388 2734 20 27142 6a06 sched.o.before
24341 2734 20 27095 69d7 sched.o.after
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Get rid of 'sched_entity::fair_key'.
As a side effect, 'current' is not kept withing the tree for
SCHED_NORMAL/BATCH tasks anymore. This simplifies some parts of code
(e.g. entity_tick() and yield_task_fair()) and also somewhat optimizes
them (e.g. a single update_curr() now vs. dequeue/enqueue() before in
entity_tick()).
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Fix a problem in the 'sched-group' patch for !CONFIG_FAIR_GROUP_SCHED.
description:
sched_setscheduler()
{
...
if (task_running()) p->sched_class->put_prev_entity();
[ this one sets up cfs_rq->curr to NULL ]
...
if (task_running) p->sched_class->set_curr_task();
[ and this one is a _NOP_ (empty) for !CONFIG_FAIR_GROUP_SCHED ]
As a result, the task continues to run with cfs_rq->curr == NULL... no
crashes (due to checks for !NULL in place) but e.g. update_curr()
effectively becomes a NOP... i.e. runtime statistics for this task is
not accounted untill it's rescheduled anew.
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Add interface to control cpu bandwidth allocation to task-groups.
(not yet configurable, due to missing CONFIG_CONTAINERS)
Signed-off-by: Srivatsa Vaddagiri <vatsa@linux.vnet.ibm.com>
Signed-off-by: Dhaval Giani <dhaval@linux.vnet.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Better min_vruntime tracking: update it every time 'curr' is
updated - not just when a task is enqueued into the tree.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
remove wait_runtime based fields and features, now that the CFS
math has been changed over to the vruntime metric.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
remove the wait_runtime-limit fields and the code depending on it, now
that the math has been changed over to rely on the vruntime metric.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
'struct load_stat' is redundant now so let's get rid of it.
Signed-off-by: Dmitry Adamushko <dmitry.adamushko@gmail.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
micro-optimization: update cfs_rq->exec_clock only if
CONFIG_SCHED_DEBUG=y.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Handle vruntime overflow by centering the key space around min_vruntime.
( otherwise we could overflow 64-bit vruntime in a few days with SCHED_IDLE
tasks - or in a few years with nice +19. )
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
add support for tree based vruntime averages.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
remove SCHED_FEAT_SKIP_INITIAL - it was off by default and even
when enabled it never made any real difference.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
clean up new task placement.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
increase wakeup granularity - we were overscheduling a bit.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
add proper new task placement for the vruntime based math too.
( note: introduces a swap() macro, but the swap token is too
widely used in the kernel namespace for a generic version
to be added without changing non-scheduler code - so this
cleanup will be done separately. )
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
optimize vruntime based scheduling.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
move sched_feat() definitions so that it can be used sooner by generic
code too.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
introduce se->vruntime as a sum of weighted delta-exec's, and use that
as the key into the tree.
the idea to use absolute virtual time as the basic metric of scheduling
has been first raised by William Lee Irwin, advanced by Tong Li and first
prototyped by Roman Zippel in the "Really Fair Scheduler" (RFS) patchset.
also see:
http://lkml.org/lkml/2007/9/2/76
for a simpler variant of this patch.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
clean up calc_weighted() - we always use the normalized shift so
it's not needed to pass that in. Also, push the non-nice0 branch
into the function.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
suggested by Roman Zippel: uninline __enqueue_entity() and
__dequeue_entity().
this reduces code size:
text data bss dec hex filename
25385 2386 16 27787 6c8b sched.o.before
25257 2386 16 27659 6c0b sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Peter Zijlstra suggested to simplify SCHED_FEAT_* checks via the
sched_feat(x) macro.
No code changed:
text data bss dec hex filename
38895 3550 24 42469 a5e5 sched.o.before
38895 3550 24 42469 a5e5 sched.o.after
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
cleanup: simplify cfs_rq_curr() methods - now that the cfs_rq->curr
pointer is unconditionally present, remove the wrappers.
kernel/sched.o:
text data bss dec hex filename
11784 224 2012 14020 36c4 sched.o.before
11784 224 2012 14020 36c4 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Noticed by Roman Zippel: use cfs_rq->curr in the !group-scheduling
case too. Small micro-optimization and cleanup effect:
text data bss dec hex filename
36269 3482 24 39775 9b5f sched.o.before
36177 3486 24 39687 9b07 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
CPU load calculations are statistical anyway, and there's little benefit
from having it calculated on every scheduling event. So remove this code,
it gets rid of a divide from the scheduler wakeup and context-switch
fastpath.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
remove the stat_gran code - it was disabled by default and it causes
unnecessary overhead.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
use constants if !CONFIG_SCHED_DEBUG.
this speeds up the code and reduces code-size:
text data bss dec hex filename
27464 3014 16 30494 771e sched.o.before
26929 3010 20 29959 7507 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
track the maximum amount of time a task has executed while
the CPU load was at least 2x. (i.e. at least two nice-0
tasks were runnable)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
to get full child-runs-first semantics make sure the parent is
rescheduled.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
add /proc/sys/kernel/sched_compat_yield to make sys_sched_yield()
more agressive, by moving the yielding task to the last position
in the rbtree.
with sched_compat_yield=0:
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
2539 mingo 20 0 1576 252 204 R 50 0.0 0:02.03 loop_yield
2541 mingo 20 0 1576 244 196 R 50 0.0 0:02.05 loop
with sched_compat_yield=1:
PID USER PR NI VIRT RES SHR S %CPU %MEM TIME+ COMMAND
2584 mingo 20 0 1576 248 196 R 99 0.0 0:52.45 loop
2582 mingo 20 0 1576 256 204 R 0 0.0 0:00.00 loop_yield
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
fix ideal_runtime:
- do not scale it using niced_granularity()
it is against sum_exec_delta, so its wall-time, not fair-time.
- move the whole check into __check_preempt_curr_fair()
so that wakeup preemption can also benefit from the new logic.
this also results in code size reduction:
text data bss dec hex filename
13391 228 1204 14823 39e7 sched.o.before
13369 228 1204 14801 39d1 sched.o.after
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Second preparatory patch for fix-ideal runtime:
Mark prev_sum_exec_runtime at the beginning of our run, the same spot
that adds our wait period to wait_runtime. This seems a more natural
location to do this, and it also reduces the code a bit:
text data bss dec hex filename
13397 228 1204 14829 39ed sched.o.before
13391 228 1204 14823 39e7 sched.o.after
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Preparatory patch for fix-ideal-runtime:
simplify __check_preempt_curr_fair(): get rid of the integer return.
text data bss dec hex filename
13404 228 1204 14836 39f4 sched.o.before
13393 228 1204 14825 39e9 sched.o.after
functionality is unchanged.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
the cfs_rq->wait_runtime debug/statistics counter was not maintained
properly - fix this.
this also removes some code:
text data bss dec hex filename
13420 228 1204 14852 3a04 sched.o.before
13404 228 1204 14836 39f4 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
fix niced_granularity(). This resulted in under-scheduling for
CPU-bound negative nice level tasks (and this in turn caused
higher than necessary latencies in nice-0 tasks).
Signed-off-by: Ingo Molnar <mingo@elte.hu>
cleanup: we have the 'se' and 'curr' entity-pointers already,
no need to use p->se and current->se.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
small schedstat fix: the cfs_rq->wait_runtime 'sum of all runtimes'
statistics counters missed newly forked tasks and thus had a constant
negative skew. Fix this.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Peter Zijlstra noticed the following bug in SCHED_FEAT_SKIP_INITIAL (which
is disabled by default at the moment): it relies on se.wait_start_fair
being 0 while update_stats_wait_end() did not recognize a 0 value,
so instead of 'skipping' the initial interval we gave the new child
a maximum boost of +runtime-limit ...
(No impact on the default kernel, but nice to fix for completeness.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
update the fair-clock before using it for the key value.
[ mingo@elte.hu: small cleanups. ]
Signed-off-by: Ting Yang <tingy@cs.umass.edu>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
de-HZ-ification of the granularity defaults unearthed a pre-existing
property of CFS: while it correctly converges to the granularity goal,
it does not prevent run-time fluctuations in the range of
[-gran ... 0 ... +gran].
With the increase of the granularity due to the removal of HZ
dependencies, this becomes visible in chew-max output (with 5 tasks
running):
out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40
out: 27 . 27. 32 | flu: 0 . 0 | ran: 17 . 13 | per: 44 . 40
out: 27 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 36 . 40
out: 29 . 27. 32 | flu: 2 . 0 | ran: 17 . 13 | per: 46 . 40
out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40
out: 29 . 27. 32 | flu: 0 . 0 | ran: 18 . 13 | per: 47 . 40
out: 28 . 27. 32 | flu: 0 . 0 | ran: 9 . 13 | per: 37 . 40
average slice is the ideal 13 msecs and the period is picture-perfect 40
msecs. But the 'ran' field fluctuates around 13.33 msecs and there's no
mechanism in CFS to keep that from happening: it's a perfectly valid
solution that CFS finds.
to fix this we add a granularity/preemption rule that knows about
the "target latency", which makes tasks that run longer than the ideal
latency run a bit less. The simplest approach is to simply decrease the
preemption granularity when a task overruns its ideal latency. For this
we have to track how much the task executed since its last preemption.
( this adds a new field to task_struct, but we can eliminate that
overhead in 2.6.24 by putting all the scheduler timestamps into an
anonymous union. )
with this change in place, chew-max output is fluctuation-less all
around:
out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40
out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40
out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40
out: 28 . 27. 39 | flu: 0 . 2 | ran: 13 . 13 | per: 41 . 40
out: 28 . 27. 39 | flu: 0 . 1 | ran: 13 . 13 | per: 41 . 40
out: 28 . 27. 39 | flu: 0 . 1 | ran: 13 . 13 | per: 41 . 40
this patch has no impact on any fastpath or on any globally observable
scheduling property. (unless you have sharp enough eyes to see
millisecond-level ruckles in glxgears smoothness :-)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Mike Galbraith <efault@gmx.de>
There is an Amarok song switch time increase (regression) under
hefty load.
What is happening is that sleeper_bonus is never consumed, and only
rarely goes below runtime_limit, so for the most part, Amarok isn't
getting any bonus at all. We're keeping sleeper_bonus right at
runtime_limit (sched_latency == sched_runtime_limit == 40ms) forever, ie
we don't consume if we're lower that that, and don't add if we're above
it. One Amarok thread waking (or anybody else) will push us past the
threshold, so the next thread waking gets nada, but will reap pain from
the previous thread waking until we drop back to runtime_limit. It
looks to me like under load, some random task gets a bonus, and
everybody else pays, whether deserving or not.
This diff fixed the regression for me at any load rate.
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
due to adaptive granularity scheduling the role of sched_granularity
has changed to "minimum granularity", so rename the variable (and the
tunable) accordingly.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Instead of specifying the preemption granularity, specify the wanted
latency. By fixing the granlarity to a constany the wakeup latency
it a function of the number of running tasks on the rq.
Invert this relation.
sysctl_sched_granularity becomes a minimum for the dynamic granularity
computed from the new sysctl_sched_latency.
Then use this latency to do more intelligent granularity decisions: if
there are fewer tasks running then we can schedule coarser. This helps
performance while still always keeping the latency target.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
fix task startup penalty miscalculation: sysctl_sched_granularity is
unsigned int and wait_runtime is long so we first have to convert it
to long before turning it negative ...
Signed-off-by: Ingo Molnar <mingo@elte.hu>
current code:
delta = calc_delta_mine(delta_exec, curr->load.weight, lw);
delta = min((u64)delta, cfs_rq->sleeper_bonus);
Notice that this calc_delta_mine() line is exactly delta_mine, which
gives:
delta = min((u64)delta_mine, cfs_rq->sleeper_bonus);
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
current code:
delta = min(cfs_rq->sleeper_bonus, (u64)delta_exec);
delta = calc_delta_mine(delta, curr->load.weight, lw);
delta = min((u64)delta, cfs_rq->sleeper_bonus);
drop the first min(), because we clip against sleeper_bonus in the 3rd line
again. That gives:
delta = calc_delta_mine(delta_exec, curr->load.weight, lw);
delta = min((u64)delta, cfs_rq->sleeper_bonus);
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
make the bonus balance more consistent: do not hand out a bonus if
there's too much in flight already, and only deduct as much from a
runner as it has the capacity. This makes the bonus engine a zero-sum
game (as intended).
this also simplifies the code:
text data bss dec hex filename
34770 2998 24 37792 93a0 sched.o.before
34749 2998 24 37771 938b sched.o.after
and it also avoids overscheduling in sleep-happy workloads like
hackbench.c.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove HZ dependency from the granularity default. Use 10 msec for
the base granularity, 1 msec for wakeup granularity and 25 msec for
batch wakeup granularity. (These defaults are close to the values
that the default HZ=250 setting got previously, and thus it's the
most common setting.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
when I built with CONFIG_FAIR_GROUP_SCHED=y, I need the following change
to make things right.
[ From: mingo@elte.hu ]
this config option is not upstream-configurable right now but lets fix
this for completeness.
Signed-off-by: Bruce Ashfield <bruce.ashfield@windriver.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Peter Ziljstra noticed that the sleeper bonus deduction code
was not properly rate-limited: a task that scheduled more
frequently would get a disproportionately large deduction.
So limit the deduction to delta_exec.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
refine the granularity of negative nice level tasks: let them
reschedule more often to offset the effect of them consuming
their wait_runtime proportionately slower. (This makes nice-0
task scheduling smoother in the presence of negatively
reniced tasks.)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
the key has to be rescaled to /weight even if it has a positive value.
(this change only affects the scheduling of reniced tasks)
Signed-off-by: Ingo Molnar <mingo@elte.hu>
clean up set_curr_task_fair().
( identity transformation that causes no change in functionality. )
text data bss dec hex filename
39170 3750 36 42956 a7cc sched.o.before
39170 3750 36 42956 a7cc sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove __update_rq_clock() call from entity_tick().
no change in functionality because scheduler_tick() already calls
__update_rq_clock().
Signed-off-by: Ingo Molnar <mingo@elte.hu>
final step: remove all (now superfluous) 'u64 now' variables.
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from ->task_new().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from ->put_prev_task().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from ->pick_next_task().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from ->dequeue_task().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from ->enqueue_task().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from put_prev_entity().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from pick_next_entity().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from set_next_entity().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from dequeue_entity().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from enqueue_entity().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from enqueue_sleeper().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from __enqueue_sleeper().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from update_stats_curr_end().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from update_stats_dequeue().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from update_stats_curr_start().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from update_stats_wait_end().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from __update_stats_wait_end().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from update_stats_enqueue().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from update_stats_wait_start().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from update_curr().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
remove the 'u64 now' parameter from print_cfs_rq().
( identity transformation that causes no change in functionality. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
change all 'now' timestamp uses in assignments to rq->clock.
( this is an identity transformation that causes no functionality change:
all such new rq->clock is necessarily preceded by an update_rq_clock()
call. )
Signed-off-by: Ingo Molnar <mingo@elte.hu>
eliminate __rq_clock() use by changing it to:
__update_rq_clock(rq)
now = rq->clock;
identity transformation - no change in behavior.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
eliminate rq_clock() use by changing it to:
update_rq_clock(rq)
now = rq->clock;
identity transformation - no change in behavior.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
There are two problems with balance_tasks() and how it used:
1. The variables best_prio and best_prio_seen (inherited from the old
move_tasks()) were only required to handle problems caused by the
active/expired arrays, the order in which they were processed and the
possibility that the task with the highest priority could be on either.
These issues are no longer present and the extra overhead associated
with their use is unnecessary (and possibly wrong).
2. In the absence of CONFIG_FAIR_GROUP_SCHED being set, the same
this_best_prio variable needs to be used by all scheduling classes or
there is a risk of moving too much load. E.g. if the highest priority
task on this at the beginning is a fairly low priority task and the rt
class migrates a task (during its turn) then that moved task becomes the
new highest priority task on this_rq but when the sched_fair class
initializes its copy of this_best_prio it will get the priority of the
original highest priority task as, due to the run queue locks being
held, the reschedule triggered by pull_task() will not have taken place.
This could result in inappropriate overriding of skip_for_load and
excessive load being moved.
The attached patch addresses these problems by deleting all reference to
best_prio and best_prio_seen and making this_best_prio a reference
parameter to the various functions involved.
load_balance_fair() has also been modified so that this_best_prio is
only reset (in the loop) if CONFIG_FAIR_GROUP_SCHED is set. This should
preserve the effect of helping spread groups' higher priority tasks
around the available CPUs while improving system performance when
CONFIG_FAIR_GROUP_SCHED isn't set.
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
small delta_exec accounting fix: increase delta_exec and increase
sum_exec_runtime even if the task is not on the runqueue anymore.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
sched_fair.c defines print_cfs_stats, and sched_debug.c uses it, but sched.c
includes both sched_fair.c and sched_debug.c, so all the references to
print_cfs_stats occur in the same compilation unit. Thus, mark
print_cfs_stats static.
Eliminates a sparse warning:
warning: symbol 'print_cfs_stats' was not declared. Should it be static?
Signed-off-by: Josh Triplett <josh@kernel.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The move_tasks() function is currently multiplexed with two distinct
capabilities:
1. attempt to move a specified amount of weighted load from one run
queue to another; and
2. attempt to move a specified number of tasks from one run queue to
another.
The first of these capabilities is used in two places, load_balance()
and load_balance_idle(), and in both of these cases the return value of
move_tasks() is used purely to decide if tasks/load were moved and no
notice of the actual number of tasks moved is taken.
The second capability is used in exactly one place,
active_load_balance(), to attempt to move exactly one task and, as
before, the return value is only used as an indicator of success or failure.
This multiplexing of sched_task() was introduced, by me, as part of the
smpnice patches and was motivated by the fact that the alternative, one
function to move specified load and one to move a single task, would
have led to two functions of roughly the same complexity as the old
move_tasks() (or the new balance_tasks()). However, the new modular
design of the new CFS scheduler allows a simpler solution to be adopted
and this patch addresses that solution by:
1. adding a new function, move_one_task(), to be used by
active_load_balance(); and
2. making move_tasks() a single purpose function that tries to move a
specified weighted load and returns 1 for success and 0 for failure.
One of the consequences of these changes is that neither move_one_task()
or the new move_tasks() care how many tasks sched_class.load_balance()
moves and this enables its interface to be simplified by returning the
amount of load moved as its result and removing the load_moved pointer
from the argument list. This helps simplify the new move_tasks() and
slightly reduces the amount of work done in each of
sched_class.load_balance()'s implementations.
Further simplification, e.g. changes to balance_tasks(), are possible
but (slightly) complicated by the special needs of load_balance_fair()
so I've left them to a later patch (if this one gets accepted).
NB Since move_tasks() gets called with two run queue locks held even
small reductions in overhead are worthwhile.
[ mingo@elte.hu ]
this change also reduces code size nicely:
text data bss dec hex filename
39216 3618 24 42858 a76a sched.o.before
39173 3618 24 42815 a73f sched.o.after
Signed-off-by: Peter Williams <pwil3058@bigpond.net.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
batch up the sleeper bonus sum a bit more. Anything below
sched-granularity is too small to make a practical difference
anyway.
this optimization reduces the math in high-frequency scheduling
scenarios.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
move the rest of the debugging/instrumentation code to under
CONFIG_SCHEDSTATS too. This reduces code size and speeds code up:
text data bss dec hex filename
33044 4122 28 37194 914a sched.o.before
32708 4122 28 36858 8ffa sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
make use of the new schedstat_set() API to eliminate two #ifdef sections.
No functional changes:
text data bss dec hex filename
29009 4122 28 33159 8187 sched.o.before
29009 4122 28 33159 8187 sched.o.after
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Ingo Molnar
Peter Zijlstra
Balbir Singh
Srivatsa Vaddagiri
Arjan van de Ven
Steven Rostedt
Dmitry Adamushko
Gregory Haskins
Zou Nan hai
Adrian Bunk
Peter Williams
Mike Galbraith
Alexey Dobriyan
Ting Yang
Bruce Ashfield
Josh Triplett