In the CPU-offline process, it calls mmdrop() after idle entry and the
subsequent call to cpuhp_report_idle_dead(). Once execution passes the
call to rcu_report_dead(), RCU is ignoring the CPU, which results in
lockdep complaining when mmdrop() uses RCU from either memcg or
debugobjects below.
Fix it by cleaning up the active_mm state from BP instead. Every arch
which has CONFIG_HOTPLUG_CPU should have already called idle_task_exit()
from AP. The only exception is parisc because it switches them to
&init_mm unconditionally (see smp_boot_one_cpu() and smp_cpu_init()),
but the patch will still work there because it calls mmgrab(&init_mm) in
smp_cpu_init() and then should call mmdrop(&init_mm) in finish_cpu().
WARNING: suspicious RCU usage
-----------------------------
kernel/workqueue.c:710 RCU or wq_pool_mutex should be held!
other info that might help us debug this:
RCU used illegally from offline CPU!
Call Trace:
dump_stack+0xf4/0x164 (unreliable)
lockdep_rcu_suspicious+0x140/0x164
get_work_pool+0x110/0x150
__queue_work+0x1bc/0xca0
queue_work_on+0x114/0x120
css_release+0x9c/0xc0
percpu_ref_put_many+0x204/0x230
free_pcp_prepare+0x264/0x570
free_unref_page+0x38/0xf0
__mmdrop+0x21c/0x2c0
idle_task_exit+0x170/0x1b0
pnv_smp_cpu_kill_self+0x38/0x2e0
cpu_die+0x48/0x64
arch_cpu_idle_dead+0x30/0x50
do_idle+0x2f4/0x470
cpu_startup_entry+0x38/0x40
start_secondary+0x7a8/0xa80
start_secondary_resume+0x10/0x14
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Qian Cai <cai@lca.pw>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> (powerpc)
Link: https://lkml.kernel.org/r/20200401214033.8448-1-cai@lca.pw
Function sched_init_granularity() is only called from __init
functions, so mark it __init as well.
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20200406074750.56533-1-songmuchun@bytedance.com
In order to prevent possible hardlockup of sched_cfs_period_timer()
loop, loop count is introduced to denote whether to scale quota and
period or not. However, scale is done between forwarding period timer
and refilling cfs bandwidth runtime, which means that period timer is
forwarded with old "period" while runtime is refilled with scaled
"quota".
Move do_sched_cfs_period_timer() before scaling to solve this.
Fixes: 2e8e192263 ("sched/fair: Limit sched_cfs_period_timer() loop to avoid hard lockup")
Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Ben Segall <bsegall@google.com>
Reviewed-by: Phil Auld <pauld@redhat.com>
Link: https://lkml.kernel.org/r/20200420024421.22442-3-changhuaixin@linux.alibaba.com
Introduce a new function put_prev_task_balance() to do the balance
when necessary, and then put previous task back to the run queue.
This function is extracted from pick_next_task() to prepare for
future usage by other type of task picking logic.
No functional change.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/5a99860cf66293db58a397d6248bcb2eee326776.1587464698.git.yu.c.chen@intel.com
After Commit 6e2df0581f ("sched: Fix pick_next_task() vs 'change'
pattern race"), there is no need to expose newidle_balance() as it
is only used within fair.c file. Change this function back to static again.
No functional change.
Reported-by: kbuild test robot <lkp@intel.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/83cd3030b031ca5d646cd5e225be10e7a0fdd8f5.1587464698.git.yu.c.chen@intel.com
That flag is set unconditionally in sd_init(), and no one checks for it
anymore. Remove it.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200415210512.805-5-valentin.schneider@arm.com
The SD_LOAD_BALANCE flag is set unconditionally for all domains in
sd_init(). By making the sched_domain->flags syctl interface read-only, we
have removed the last piece of code that could clear that flag - as such,
it will now be always present. Rather than to keep carrying it along, we
can work towards getting rid of it entirely.
cpusets don't need it because they can make CPUs be attached to the NULL
domain (e.g. cpuset with sched_load_balance=0), or to a partitioned
root_domain, i.e. a sched_domain hierarchy that doesn't span the entire
system (e.g. root cpuset with sched_load_balance=0 and sibling cpusets with
sched_load_balance=1).
isolcpus apply the same "trick": isolated CPUs are explicitly taken out of
the sched_domain rebuild (using housekeeping_cpumask()), so they get the
NULL domain treatment as well.
Remove the checks against SD_LOAD_BALANCE.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200415210512.805-4-valentin.schneider@arm.com
Writing to the sysctl of a sched_domain->flags directly updates the value of
the field, and goes nowhere near update_top_cache_domain(). This means that
the cached domain pointers can end up containing stale data (e.g. the
domain pointed to doesn't have the relevant flag set anymore).
Explicit domain walks that check for flags will be affected by
the write, but this won't be in sync with the cached pointers which will
still point to the domains that were cached at the last sched_domain
build.
In other words, writing to this interface is playing a dangerous game. It
could be made to trigger an update of the cached sched_domain pointers when
written to, but this does not seem to be worth the trouble. Make it
read-only.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200415210512.805-3-valentin.schneider@arm.com
The last use of that parameter was removed by commit
57abff067a ("sched/fair: Rework find_idlest_group()")
Get rid of the parameter.
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/20200415210512.805-2-valentin.schneider@arm.com
We only consider group_balance_cpu() after there is no idle
cpu. So, just do comparison before return at these two cases.
Signed-off-by: Peng Wang <rocking@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/245c792f0e580b3ca342ad61257f4c066ee0f84f.1586594833.git.rocking@linux.alibaba.com
This is mostly a revert of commit:
baa9be4ffb ("sched/fair: Fix throttle_list starvation with low CFS quota")
The primary use of distribute_running was to determine whether to add
throttled entities to the head or the tail of the throttled list. Now
that we always add to the tail, we can remove this field.
The other use of distribute_running is in the slack_timer, so that we
don't start a distribution while one is already running. However, even
in the event that this race occurs, it is fine to have two distributions
running (especially now that distribute grabs the cfs_b->lock to
determine remaining quota before assigning).
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Tested-by: Phil Auld <pauld@redhat.com>
Link: https://lkml.kernel.org/r/20200410225208.109717-3-joshdon@google.com
There is a race window in which an entity begins throttling before quota
is added to the pool, but does not finish throttling until after we have
finished with distribute_cfs_runtime(). This entity is not observed by
distribute_cfs_runtime() because it was not on the throttled list at the
time that distribution was running. This race manifests as rare
period-length statlls for such entities.
Rather than heavy-weight the synchronization with the progress of
distribution, we can fix this by aborting throttling if bandwidth has
become available. Otherwise, we immediately add the entity to the
throttled list so that it can be observed by a subsequent distribution.
Additionally, we can remove the case of adding the throttled entity to
the head of the throttled list, and simply always add to the tail.
Thanks to 26a8b12747, distribute_cfs_runtime() no longer holds onto
its own pool of runtime. This means that if we do hit the !assign and
distribute_running case, we know that distribution is about to end.
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Ben Segall <bsegall@google.com>
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Link: https://lkml.kernel.org/r/20200410225208.109717-2-joshdon@google.com
Pull in Christoph Hellwig's series that changes the sysctl's ->proc_handler
methods to take kernel pointers instead. It gets rid of the set_fs address
space overrides used by BPF. As per discussion, pull in the feature branch
into bpf-next as it relates to BPF sysctl progs.
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20200427071508.GV23230@ZenIV.linux.org.uk/T/
A running task's state can be sampled in a consistent manner (for example,
for diagnostic purposes) simply by invoking smp_call_function_single()
on its CPU, which may be obtained using task_cpu(), then having the
IPI handler verify that the desired task is in fact still running.
However, if the task is not running, this sampling can in theory be done
immediately and directly. In practice, the task might start running at
any time, including during the sampling period. Gaining a consistent
sample of a not-running task therefore requires that something be done
to lock down the target task's state.
This commit therefore adds a try_invoke_on_locked_down_task() function
that invokes a specified function if the specified task can be locked
down, returning true if successful and if the specified function returns
true. Otherwise this function simply returns false. Given that the
function passed to try_invoke_on_nonrunning_task() might be invoked with
a runqueue lock held, that function had better be quite lightweight.
The function is passed the target task's task_struct pointer and the
argument passed to try_invoke_on_locked_down_task(), allowing easy access
to task state and to a location for further variables to be passed in
and out.
Note that the specified function will be called even if the specified
task is currently running. The function can use ->on_rq and task_curr()
to quickly and easily determine the task's state, and can return false
if this state is not to the function's liking. The caller of the
try_invoke_on_locked_down_task() would then see the false return value,
and could take appropriate action, for example, trying again later or
sending an IPI if matters are more urgent.
It is expected that use cases such as the RCU CPU stall warning code will
simply return false if the task is currently running. However, there are
use cases involving nohz_full CPUs where the specified function might
instead fall back to an alternative sampling scheme that relies on heavier
synchronization (such as memory barriers) in the target task.
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Ben Segall <bsegall@google.com>
Cc: Mel Gorman <mgorman@suse.de>
[ paulmck: Apply feedback from Peter Zijlstra and Steven Rostedt. ]
[ paulmck: Invoke if running to handle feedback from Mathieu Desnoyers. ]
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Instead of having all the sysctl handlers deal with user pointers, which
is rather hairy in terms of the BPF interaction, copy the input to and
from userspace in common code. This also means that the strings are
always NUL-terminated by the common code, making the API a little bit
safer.
As most handler just pass through the data to one of the common handlers
a lot of the changes are mechnical.
Signed-off-by: Christoph Hellwig <hch@lst.de>
Acked-by: Andrey Ignatov <rdna@fb.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
uclamp_fork() resets the uclamp values to their default when the
reset-on-fork flag is set. It also checks whether the task has a RT
policy, and sets its uclamp.min to 1024 accordingly. However, during
reset-on-fork, the task's policy is lowered to SCHED_NORMAL right after,
hence leading to an erroneous uclamp.min setting for the new task if it
was forked from RT.
Fix this by removing the unnecessary check on rt_task() in
uclamp_fork() as this doesn't make sense if the reset-on-fork flag is
set.
Fixes: 1a00d99997 ("sched/uclamp: Set default clamps for RT tasks")
Reported-by: Chitti Babu Theegala <ctheegal@codeaurora.org>
Signed-off-by: Quentin Perret <qperret@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Patrick Bellasi <patrick.bellasi@matbug.net>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Link: https://lkml.kernel.org/r/20200416085956.217587-1-qperret@google.com
Work around this warning:
kernel/sched/cputime.c: In function ‘kcpustat_field’:
kernel/sched/cputime.c:1007:6: warning: ‘val’ may be used uninitialized in this function [-Wmaybe-uninitialized]
because GCC can't see that val is used only when err is 0.
Acked-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200327214334.GF8015@zn.tnic
The "isolcpus=" parameter allows sub-parameters before the cpulist is
specified, and if the parser detects an unknown sub-parameters the whole
parameter will be ignored.
This design is incompatible with itself when new sub-parameters are added.
An older kernel will not recognize the new sub-parameter and will
invalidate the whole parameter so the CPU isolation will not take
effect. It emits a warning:
isolcpus: Error, unknown flag
The better and compatible way is to allow "isolcpus=" to skip unknown
sub-parameters, so that even if new sub-parameters are added an older
kernel will still be able to behave as usual even if with the new
sub-parameter specified on the command line.
Ideally this should have been there when the first sub-parameter for
"isolcpus=" was introduced.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200403223517.406353-1-peterx@redhat.com
-----BEGIN PGP SIGNATURE-----
iQFSBAABCAA8FiEEq68RxlopcLEwq+PEeb4+QwBBGIYFAl6TbaUeHHRvcnZhbGRz
QGxpbnV4LWZvdW5kYXRpb24ub3JnAAoJEHm+PkMAQRiGhgkH/iWpiKvosA20HJjC
rBqYeJPxQsgZTuBieWJ+MeVxbpcF7RlM4c+glyvg3QJhHwIEG58dl6LBrQbAyBAR
aFHNojr1iAYOruVCGnU3pA008YZiwUIDv/ZQ4DF8fmIU2vI2mJ6qHBv3XDl4G2uR
Nwz8Eu9AgIwZM5coomVOSmoWyFy7Vxmb7W+3t5VmKsvOWx4ib9kyQtOIkvQDEl7j
XCbWfI0xDQr6LFOm4jnCi5R/LhJ2LIqqIvHHrunbpszM8IwK797jCXz4im+dmd5Y
+km46N7a8pDqri36xXz1gdBAU3eG7Pt1NyvfjwRVTdX4GquQ2MT0GoojxbLxUP3y
3pEsQuE=
=whbL
-----END PGP SIGNATURE-----
Merge tag 'v5.7-rc1' into locking/kcsan, to resolve conflicts and refresh
Resolve these conflicts:
arch/x86/Kconfig
arch/x86/kernel/Makefile
Do a minor "evil merge" to move the KCSAN entry up a bit by a few lines
in the Kconfig to reduce the probability of future conflicts.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Requested and effective uclamp values can be a bit tricky to decipher when
playing with cgroup hierarchies. Add them to a task's procfs when
SCHED_DEBUG is enabled.
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200226124543.31986-4-valentin.schneider@arm.com
The printing macros in debug.c keep redefining the same output
format. Collect each output format in a single definition, and reuse that
definition in the other macros. While at it, add a layer of parentheses and
replace printf's with the newly introduced macros.
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200226124543.31986-3-valentin.schneider@arm.com
Most printing macros for procfs are defined globally in debug.c, and they
are re-defined (to the exact same thing) within proc_sched_show_task().
Get rid of the duplicate defines.
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200226124543.31986-2-valentin.schneider@arm.com
The following commit:
5e83eafbfd ("sched/fair: Remove the rq->cpu_load[] update code")
eliminated the last use case for rq->last_load_update_tick, so remove
the field as well.
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Vincent Donnefort <vincent.donnefort@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/1584710495-308969-1-git-send-email-vincent.donnefort@arm.com
The kernel test robot triggered a warning with the following race:
task-ctx A interrupt-ctx B
worker
-> process_one_work()
-> work_item()
-> schedule();
-> sched_submit_work()
-> wq_worker_sleeping()
-> ->sleeping = 1
atomic_dec_and_test(nr_running)
__schedule(); *interrupt*
async_page_fault()
-> local_irq_enable();
-> schedule();
-> sched_submit_work()
-> wq_worker_sleeping()
-> if (WARN_ON(->sleeping)) return
-> __schedule()
-> sched_update_worker()
-> wq_worker_running()
-> atomic_inc(nr_running);
-> ->sleeping = 0;
-> sched_update_worker()
-> wq_worker_running()
if (!->sleeping) return
In this context the warning is pointless everything is fine.
An interrupt before wq_worker_sleeping() will perform the ->sleeping
assignment (0 -> 1 > 0) twice.
An interrupt after wq_worker_sleeping() will trigger the warning and
nr_running will be decremented (by A) and incremented once (only by B, A
will skip it). This is the case until the ->sleeping is zeroed again in
wq_worker_running().
Remove the WARN statement because this condition may happen. Document
that preemption around wq_worker_sleeping() needs to be disabled to
protect ->sleeping and not just as an optimisation.
Fixes: 6d25be5782 ("sched/core, workqueues: Distangle worker accounting from rq lock")
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Link: https://lkml.kernel.org/r/20200327074308.GY11705@shao2-debian
A negative imbalance value was observed after imbalance calculation,
this happens when the local sched group type is group_fully_busy,
and the average load of local group is greater than the selected
busiest group. Fix this problem by comparing the average load of the
local and busiest group before imbalance calculation formula.
Suggested-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Phil Auld <pauld@redhat.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Aubrey Li <aubrey.li@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/1585201349-70192-1-git-send-email-aubrey.li@intel.com
Currently, there is a potential race between distribute_cfs_runtime()
and assign_cfs_rq_runtime(). Race happens when cfs_b->runtime is read,
distributes without holding lock and finds out there is not enough
runtime to charge against after distribution. Because
assign_cfs_rq_runtime() might be called during distribution, and use
cfs_b->runtime at the same time.
Fibtest is the tool to test this race. Assume all gcfs_rq is throttled
and cfs period timer runs, slow threads might run and sleep, returning
unused cfs_rq runtime and keeping min_cfs_rq_runtime in their local
pool. If all this happens sufficiently quickly, cfs_b->runtime will drop
a lot. If runtime distributed is large too, over-use of runtime happens.
A runtime over-using by about 70 percent of quota is seen when we
test fibtest on a 96-core machine. We run fibtest with 1 fast thread and
95 slow threads in test group, configure 10ms quota for this group and
see the CPU usage of fibtest is 17.0%, which is far more than the
expected 10%.
On a smaller machine with 32 cores, we also run fibtest with 96
threads. CPU usage is more than 12%, which is also more than expected
10%. This shows that on similar workloads, this race do affect CPU
bandwidth control.
Solve this by holding lock inside distribute_cfs_runtime().
Fixes: c06f04c704 ("sched: Fix potential near-infinite distribute_cfs_runtime() loop")
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Huaixin Chang <changhuaixin@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/lkml/20200325092602.22471-1-changhuaixin@linux.alibaba.com/
sched/core.c uses update_avg() for rq->avg_idle and sched/fair.c uses an
open-coded version (with the exact same decay factor) for
rq->avg_scan_cost. On top of that, select_idle_cpu() expects to be able to
compare these two fields.
The only difference between the two is that rq->avg_scan_cost is computed
using a pure division rather than a shift. Turns out it actually matters,
first of all because the shifted value can be negative, and the standard
has this to say about it:
"""
The result of E1 >> E2 is E1 right-shifted E2 bit positions. [...] If E1
has a signed type and a negative value, the resulting value is
implementation-defined.
"""
Not only this, but (arithmetic) right shifting a negative value (using 2's
complement) is *not* equivalent to dividing it by the corresponding power
of 2. Let's look at a few examples:
-4 -> 0xF..FC
-4 >> 3 -> 0xF..FF == -1 != -4 / 8
-8 -> 0xF..F8
-8 >> 3 -> 0xF..FF == -1 == -8 / 8
-9 -> 0xF..F7
-9 >> 3 -> 0xF..FE == -2 != -9 / 8
Make update_avg() use a division, and export it to the private scheduler
header to reuse it where relevant. Note that this still lets compilers use
a shift here, but should prevent any unwanted surprise. The disassembly of
select_idle_cpu() remains unchanged on arm64, and ttwu_do_wakeup() gains 2
instructions; the diff sort of looks like this:
- sub x1, x1, x0
+ subs x1, x1, x0 // set condition codes
+ add x0, x1, #0x7
+ csel x0, x0, x1, mi // x0 = x1 < 0 ? x0 : x1
add x0, x3, x0, asr #3
which does the right thing (i.e. gives us the expected result while still
using an arithmetic shift)
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200330090127.16294-1-valentin.schneider@arm.com
- Support for locked CSD objects in smp_call_function_single_async()
which allows to simplify callsites in the scheduler core and MIPS
- Treewide consolidation of CPU hotplug functions which ensures the
consistency between the sysfs interface and kernel state. The low level
functions cpu_up/down() are now confined to the core code and not
longer accessible from random code.
-----BEGIN PGP SIGNATURE-----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=jwCg
-----END PGP SIGNATURE-----
Merge tag 'smp-core-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core SMP updates from Thomas Gleixner:
"CPU (hotplug) updates:
- Support for locked CSD objects in smp_call_function_single_async()
which allows to simplify callsites in the scheduler core and MIPS
- Treewide consolidation of CPU hotplug functions which ensures the
consistency between the sysfs interface and kernel state. The low
level functions cpu_up/down() are now confined to the core code and
not longer accessible from random code"
* tag 'smp-core-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (22 commits)
cpu/hotplug: Ignore pm_wakeup_pending() for disable_nonboot_cpus()
cpu/hotplug: Hide cpu_up/down()
cpu/hotplug: Move bringup of secondary CPUs out of smp_init()
torture: Replace cpu_up/down() with add/remove_cpu()
firmware: psci: Replace cpu_up/down() with add/remove_cpu()
xen/cpuhotplug: Replace cpu_up/down() with device_online/offline()
parisc: Replace cpu_up/down() with add/remove_cpu()
sparc: Replace cpu_up/down() with add/remove_cpu()
powerpc: Replace cpu_up/down() with add/remove_cpu()
x86/smp: Replace cpu_up/down() with add/remove_cpu()
arm64: hibernate: Use bringup_hibernate_cpu()
cpu/hotplug: Provide bringup_hibernate_cpu()
arm64: Use reboot_cpu instead of hardconding it to 0
arm64: Don't use disable_nonboot_cpus()
ARM: Use reboot_cpu instead of hardcoding it to 0
ARM: Don't use disable_nonboot_cpus()
ia64: Replace cpu_down() with smp_shutdown_nonboot_cpus()
cpu/hotplug: Create a new function to shutdown nonboot cpus
cpu/hotplug: Add new {add,remove}_cpu() functions
sched/core: Remove rq.hrtick_csd_pending
...
Pull scheduler updates from Ingo Molnar:
"The main changes in this cycle are:
- Various NUMA scheduling updates: harmonize the load-balancer and
NUMA placement logic to not work against each other. The intended
result is better locality, better utilization and fewer migrations.
- Introduce Thermal Pressure tracking and optimizations, to improve
task placement on thermally overloaded systems.
- Implement frequency invariant scheduler accounting on (some) x86
CPUs. This is done by observing and sampling the 'recent' CPU
frequency average at ~tick boundaries. The CPU provides this data
via the APERF/MPERF MSRs. This hopefully makes our capacity
estimates more precise and keeps tasks on the same CPU better even
if it might seem overloaded at a lower momentary frequency. (As
usual, turbo mode is a complication that we resolve by observing
the maximum frequency and renormalizing to it.)
- Add asymmetric CPU capacity wakeup scan to improve capacity
utilization on asymmetric topologies. (big.LITTLE systems)
- PSI fixes and optimizations.
- RT scheduling capacity awareness fixes & improvements.
- Optimize the CONFIG_RT_GROUP_SCHED constraints code.
- Misc fixes, cleanups and optimizations - see the changelog for
details"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (62 commits)
threads: Update PID limit comment according to futex UAPI change
sched/fair: Fix condition of avg_load calculation
sched/rt: cpupri_find: Trigger a full search as fallback
kthread: Do not preempt current task if it is going to call schedule()
sched/fair: Improve spreading of utilization
sched: Avoid scale real weight down to zero
psi: Move PF_MEMSTALL out of task->flags
MAINTAINERS: Add maintenance information for psi
psi: Optimize switching tasks inside shared cgroups
psi: Fix cpu.pressure for cpu.max and competing cgroups
sched/core: Distribute tasks within affinity masks
sched/fair: Fix enqueue_task_fair warning
thermal/cpu-cooling, sched/core: Move the arch_set_thermal_pressure() API to generic scheduler code
sched/rt: Remove unnecessary push for unfit tasks
sched/rt: Allow pulling unfitting task
sched/rt: Optimize cpupri_find() on non-heterogenous systems
sched/rt: Re-instate old behavior in select_task_rq_rt()
sched/rt: cpupri_find: Implement fallback mechanism for !fit case
sched/fair: Fix reordering of enqueue/dequeue_task_fair()
sched/fair: Fix runnable_avg for throttled cfs
...
Pull locking updates from Ingo Molnar:
"The main changes in this cycle were:
- Continued user-access cleanups in the futex code.
- percpu-rwsem rewrite that uses its own waitqueue and atomic_t
instead of an embedded rwsem. This addresses a couple of
weaknesses, but the primary motivation was complications on the -rt
kernel.
- Introduce raw lock nesting detection on lockdep
(CONFIG_PROVE_RAW_LOCK_NESTING=y), document the raw_lock vs. normal
lock differences. This too originates from -rt.
- Reuse lockdep zapped chain_hlocks entries, to conserve RAM
footprint on distro-ish kernels running into the "BUG:
MAX_LOCKDEP_CHAIN_HLOCKS too low!" depletion of the lockdep
chain-entries pool.
- Misc cleanups, smaller fixes and enhancements - see the changelog
for details"
* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits)
fs/buffer: Make BH_Uptodate_Lock bit_spin_lock a regular spinlock_t
thermal/x86_pkg_temp: Make pkg_temp_lock a raw_spinlock_t
Documentation/locking/locktypes: Minor copy editor fixes
Documentation/locking/locktypes: Further clarifications and wordsmithing
m68knommu: Remove mm.h include from uaccess_no.h
x86: get rid of user_atomic_cmpxchg_inatomic()
generic arch_futex_atomic_op_inuser() doesn't need access_ok()
x86: don't reload after cmpxchg in unsafe_atomic_op2() loop
x86: convert arch_futex_atomic_op_inuser() to user_access_begin/user_access_end()
objtool: whitelist __sanitizer_cov_trace_switch()
[parisc, s390, sparc64] no need for access_ok() in futex handling
sh: no need of access_ok() in arch_futex_atomic_op_inuser()
futex: arch_futex_atomic_op_inuser() calling conventions change
completion: Use lockdep_assert_RT_in_threaded_ctx() in complete_all()
lockdep: Add posixtimer context tracing bits
lockdep: Annotate irq_work
lockdep: Add hrtimer context tracing bits
lockdep: Introduce wait-type checks
completion: Use simple wait queues
sched/swait: Prepare usage in completions
...
The warning was intended to spot complete_all() users from hardirq
context on PREEMPT_RT. The warning as-is will also trigger in interrupt
handlers, which are threaded on PREEMPT_RT, which was not intended.
Use lockdep_assert_RT_in_threaded_ctx() which triggers in non-preemptive
context on PREEMPT_RT.
Fixes: a5c6234e10 ("completion: Use simple wait queues")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200323152019.4qjwluldohuh3by5@linutronix.de
completion uses a wait_queue_head_t to enqueue waiters.
wait_queue_head_t contains a spinlock_t to protect the list of waiters
which excludes it from being used in truly atomic context on a PREEMPT_RT
enabled kernel.
The spinlock in the wait queue head cannot be replaced by a raw_spinlock
because:
- wait queues can have custom wakeup callbacks, which acquire other
spinlock_t locks and have potentially long execution times
- wake_up() walks an unbounded number of list entries during the wake up
and may wake an unbounded number of waiters.
For simplicity and performance reasons complete() should be usable on
PREEMPT_RT enabled kernels.
completions do not use custom wakeup callbacks and are usually single
waiter, except for a few corner cases.
Replace the wait queue in the completion with a simple wait queue (swait),
which uses a raw_spinlock_t for protecting the waiter list and therefore is
safe to use inside truly atomic regions on PREEMPT_RT.
There is no semantical or functional change:
- completions use the exclusive wait mode which is what swait provides
- complete() wakes one exclusive waiter
- complete_all() wakes all waiters while holding the lock which protects
the wait queue against newly incoming waiters. The conversion to swait
preserves this behaviour.
complete_all() might cause unbound latencies with a large number of waiters
being woken at once, but most complete_all() usage sites are either in
testing or initialization code or have only a really small number of
concurrent waiters which for now does not cause a latency problem. Keep it
simple for now.
The fixup of the warning check in the USB gadget driver is just a straight
forward conversion of the lockless waiter check from one waitqueue type to
the other.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Davidlohr Bueso <dbueso@suse.de>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lkml.kernel.org/r/20200321113242.317954042@linutronix.de
As a preparation to use simple wait queues for completions:
- Provide swake_up_all_locked() to support complete_all()
- Make __prepare_to_swait() public available
This is done to enable the usage of complete() within truly atomic contexts
on a PREEMPT_RT enabled kernel.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200321113242.228481202@linutronix.de
In update_sg_wakeup_stats(), the comment says:
Computing avg_load makes sense only when group is fully
busy or overloaded.
But, the code below this comment does not check like this.
From reading the code about avg_load in other functions, I
confirm that avg_load should be calculated in fully busy or
overloaded case. The comment is correct and the checking
condition is wrong. So, change that condition.
Fixes: 57abff067a ("sched/fair: Rework find_idlest_group()")
Signed-off-by: Tao Zhou <ouwen210@hotmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Link: https://lkml.kernel.org/r/Message-ID:
If we failed to find a fitting CPU, in cpupri_find(), we only fallback
to the level we found a hit at.
But Steve suggested to fallback to a second full scan instead as this
could be a better effort.
https://lore.kernel.org/lkml/20200304135404.146c56eb@gandalf.local.home/
We trigger the 2nd search unconditionally since the argument about
triggering a full search is that the recorded fall back level might have
become empty by then. Which means storing any data about what happened
would be meaningless and stale.
I had a humble try at timing it and it seemed okay for the small 6 CPUs
system I was running on
https://lore.kernel.org/lkml/20200305124324.42x6ehjxbnjkklnh@e107158-lin.cambridge.arm.com/
On large system this second full scan could be expensive. But there are
no users outside capacity awareness for this fitness function at the
moment. Heterogeneous systems tend to be small with 8cores in total.
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Link: https://lkml.kernel.org/r/20200310142219.syxzn5ljpdxqtbgx@e107158-lin.cambridge.arm.com
During load_balancing, a group with spare capacity will try to pull some
utilizations from an overloaded group. In such case, the load balance
looks for the runqueue with the highest utilization. Nevertheless, it
should also ensure that there are some pending tasks to pull otherwise
the load balance will fail to pull a task and the spread of the load will
be delayed.
This situation is quite transient but it's possible to highlight the
effect with a short run of sysbench test so the time to spread task impacts
the global result significantly.
Below are the average results for 15 iterations on an arm64 octo core:
sysbench --test=cpu --num-threads=8 --max-requests=1000 run
tip/sched/core +patchset
total time: 172ms 158ms
per-request statistics:
avg: 1.337ms 1.244ms
max: 21.191ms 10.753ms
The average max doesn't fully reflect the wide spread of the value which
ranges from 1.350ms to more than 41ms for the tip/sched/core and from
1.350ms to 21ms with the patch.
Other factors like waiting for an idle load balance or cache hotness
can delay the spreading of the tasks which explains why we can still
have up to 21ms with the patch.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200312165429.990-1-vincent.guittot@linaro.org
During our testing, we found a case that shares no longer
working correctly, the cgroup topology is like:
/sys/fs/cgroup/cpu/A (shares=102400)
/sys/fs/cgroup/cpu/A/B (shares=2)
/sys/fs/cgroup/cpu/A/B/C (shares=1024)
/sys/fs/cgroup/cpu/D (shares=1024)
/sys/fs/cgroup/cpu/D/E (shares=1024)
/sys/fs/cgroup/cpu/D/E/F (shares=1024)
The same benchmark is running in group C & F, no other tasks are
running, the benchmark is capable to consumed all the CPUs.
We suppose the group C will win more CPU resources since it could
enjoy all the shares of group A, but it's F who wins much more.
The reason is because we have group B with shares as 2, since
A->cfs_rq.load.weight == B->se.load.weight == B->shares/nr_cpus,
so A->cfs_rq.load.weight become very small.
And in calc_group_shares() we calculate shares as:
load = max(scale_load_down(cfs_rq->load.weight), cfs_rq->avg.load_avg);
shares = (tg_shares * load) / tg_weight;
Since the 'cfs_rq->load.weight' is too small, the load become 0
after scale down, although 'tg_shares' is 102400, shares of the se
which stand for group A on root cfs_rq become 2.
While the se of D on root cfs_rq is far more bigger than 2, so it
wins the battle.
Thus when scale_load_down() scale real weight down to 0, it's no
longer telling the real story, the caller will have the wrong
information and the calculation will be buggy.
This patch add check in scale_load_down(), so the real weight will
be >= MIN_SHARES after scale, after applied the group C wins as
expected.
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Michael Wang <yun.wang@linux.alibaba.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/38e8e212-59a1-64b2-b247-b6d0b52d8dc1@linux.alibaba.com
The task->flags is a 32-bits flag, in which 31 bits have already been
consumed. So it is hardly to introduce other new per process flag.
Currently there're still enough spaces in the bit-field section of
task_struct, so we can define the memstall state as a single bit in
task_struct instead.
This patch also removes an out-of-date comment pointed by Matthew.
Suggested-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Yafang Shao <laoar.shao@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/1584408485-1921-1-git-send-email-laoar.shao@gmail.com
When switching tasks running on a CPU, the psi state of a cgroup
containing both of these tasks does not change. Right now, we don't
exploit that, and can perform many unnecessary state changes in nested
hierarchies, especially when most activity comes from one leaf cgroup.
This patch implements an optimization where we only update cgroups
whose state actually changes during a task switch. These are all
cgroups that contain one task but not the other, up to the first
shared ancestor. When both tasks are in the same group, we don't need
to update anything at all.
We can identify the first shared ancestor by walking the groups of the
incoming task until we see TSK_ONCPU set on the local CPU; that's the
first group that also contains the outgoing task.
The new psi_task_switch() is similar to psi_task_change(). To allow
code reuse, move the task flag maintenance code into a new function
and the poll/avg worker wakeups into the shared psi_group_change().
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200316191333.115523-3-hannes@cmpxchg.org
For simplicity, cpu pressure is defined as having more than one
runnable task on a given CPU. This works on the system-level, but it
has limitations in a cgrouped reality: When cpu.max is in use, it
doesn't capture the time in which a task is not executing on the CPU
due to throttling. Likewise, it doesn't capture the time in which a
competing cgroup is occupying the CPU - meaning it only reflects
cgroup-internal competitive pressure, not outside pressure.
Enable tracking of currently executing tasks, and then change the
definition of cpu pressure in a cgroup from
NR_RUNNING > 1
to
NR_RUNNING > ON_CPU
which will capture the effects of cpu.max as well as competition from
outside the cgroup.
After this patch, a cgroup running `stress -c 1` with a cpu.max
setting of 5000 10000 shows ~50% continuous CPU pressure.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200316191333.115523-2-hannes@cmpxchg.org
Currently, when updating the affinity of tasks via either cpusets.cpus,
or, sched_setaffinity(); tasks not currently running within the newly
specified mask will be arbitrarily assigned to the first CPU within the
mask.
This (particularly in the case that we are restricting masks) can
result in many tasks being assigned to the first CPUs of their new
masks.
This:
1) Can induce scheduling delays while the load-balancer has a chance to
spread them between their new CPUs.
2) Can antogonize a poor load-balancer behavior where it has a
difficult time recognizing that a cross-socket imbalance has been
forced by an affinity mask.
This change adds a new cpumask interface to allow iterated calls to
distribute within the intersection of the provided masks.
The cases that this mainly affects are:
- modifying cpuset.cpus
- when tasks join a cpuset
- when modifying a task's affinity via sched_setaffinity(2)
Signed-off-by: Paul Turner <pjt@google.com>
Signed-off-by: Josh Don <joshdon@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Qais Yousef <qais.yousef@arm.com>
Tested-by: Qais Yousef <qais.yousef@arm.com>
Link: https://lkml.kernel.org/r/20200311010113.136465-1-joshdon@google.com
When a cfs rq is throttled, the latter and its child are removed from the
leaf list but their nr_running is not changed which includes staying higher
than 1. When a task is enqueued in this throttled branch, the cfs rqs must
be added back in order to ensure correct ordering in the list but this can
only happens if nr_running == 1.
When cfs bandwidth is used, we call unconditionnaly list_add_leaf_cfs_rq()
when enqueuing an entity to make sure that the complete branch will be
added.
Similarly unthrottle_cfs_rq() can stop adding cfs in the list when a parent
is throttled. Iterate the remaining entity to ensure that the complete
branch will be added in the list.
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Tested-by: Christian Borntraeger <borntraeger@de.ibm.com>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: stable@vger.kernel.org
Cc: stable@vger.kernel.org #v5.1+
Link: https://lkml.kernel.org/r/20200306135257.25044-1-vincent.guittot@linaro.org
drivers/base/arch_topology.c is only built if CONFIG_GENERIC_ARCH_TOPOLOGY=y,
resulting in such build failures:
cpufreq_cooling.c:(.text+0x1e7): undefined reference to `arch_set_thermal_pressure'
Move it to sched/core.c instead, and keep it enabled on x86 despite
us not having a arch_scale_thermal_pressure() facility there, to
build-test this thing.
Cc: Thara Gopinath <thara.gopinath@linaro.org>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Now smp_call_function_single_async() provides the protection that
we'll return with -EBUSY if the csd object is still pending, then we
don't need the rq.hrtick_csd_pending any more.
Signed-off-by: Peter Xu <peterx@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20191216213125.9536-4-peterx@redhat.com
In task_woken_rt() and switched_to_rto() we try trigger push-pull if the
task is unfit.
But the logic is found lacking because if the task was the only one
running on the CPU, then rt_rq is not in overloaded state and won't
trigger a push.
The necessity of this logic was under a debate as well, a summary of
the discussion can be found in the following thread:
https://lore.kernel.org/lkml/20200226160247.iqvdakiqbakk2llz@e107158-lin.cambridge.arm.com/
Remove the logic for now until a better approach is agreed upon.
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 804d402fb6 ("sched/rt: Make RT capacity-aware")
Link: https://lkml.kernel.org/r/20200302132721.8353-6-qais.yousef@arm.com
When implemented RT Capacity Awareness; the logic was done such that if
a task was running on a fitting CPU, then it was sticky and we would try
our best to keep it there.
But as Steve suggested, to adhere to the strict priority rules of RT
class; allow pulling an RT task to unfitting CPU to ensure it gets a
chance to run ASAP.
LINK: https://lore.kernel.org/lkml/20200203111451.0d1da58f@oasis.local.home/
Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 804d402fb6 ("sched/rt: Make RT capacity-aware")
Link: https://lkml.kernel.org/r/20200302132721.8353-5-qais.yousef@arm.com
By introducing a new cpupri_find_fitness() function that takes the
fitness_fn as an argument and only called when asym_system static key is
enabled.
cpupri_find() is now a wrapper function that calls cpupri_find_fitness()
passing NULL as a fitness_fn, hence disabling the logic that handles
fitness by default.
LINK: https://lore.kernel.org/lkml/c0772fca-0a4b-c88d-fdf2-5715fcf8447b@arm.com/
Reported-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 804d402fb6 ("sched/rt: Make RT capacity-aware")
Link: https://lkml.kernel.org/r/20200302132721.8353-4-qais.yousef@arm.com
When RT Capacity Aware support was added, the logic in select_task_rq_rt
was modified to force a search for a fitting CPU if the task currently
doesn't run on one.
But if the search failed, and the search was only triggered to fulfill
the fitness request; we could end up selecting a new CPU unnecessarily.
Fix this and re-instate the original behavior by ensuring we bail out
in that case.
This behavior change only affected asymmetric systems that are using
util_clamp to implement capacity aware. None asymmetric systems weren't
affected.
LINK: https://lore.kernel.org/lkml/20200218041620.GD28029@codeaurora.org/
Reported-by: Pavan Kondeti <pkondeti@codeaurora.org>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 804d402fb6 ("sched/rt: Make RT capacity-aware")
Link: https://lkml.kernel.org/r/20200302132721.8353-3-qais.yousef@arm.com
When searching for the best lowest_mask with a fitness_fn passed, make
sure we record the lowest_level that returns a valid lowest_mask so that
we can use that as a fallback in case we fail to find a fitting CPU at
all levels.
The intention in the original patch was not to allow a down migration to
unfitting CPU. But this missed the case where we are already running on
unfitting one.
With this change now RT tasks can still move between unfitting CPUs when
they're already running on such CPU.
And as Steve suggested; to adhere to the strict priority rules of RT, if
a task is already running on a fitting CPU but due to priority it can't
run on it, allow it to downmigrate to unfitting CPU so it can run.
Reported-by: Pavan Kondeti <pkondeti@codeaurora.org>
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 804d402fb6 ("sched/rt: Make RT capacity-aware")
Link: https://lkml.kernel.org/r/20200302132721.8353-2-qais.yousef@arm.com
Link: https://lore.kernel.org/lkml/20200203142712.a7yvlyo2y3le5cpn@e107158-lin/
Even when a cgroup is throttled, the group se of a child cgroup can still
be enqueued and its gse->on_rq stays true. When a task is enqueued on such
child, we still have to update the load_avg and increase
h_nr_running of the throttled cfs. Nevertheless, the 1st
for_each_sched_entity() loop is skipped because of gse->on_rq == true and the
2nd loop because the cfs is throttled whereas we have to update both
load_avg with the old h_nr_running and increase h_nr_running in such case.
The same sequence can happen during dequeue when se moves to parent before
breaking in the 1st loop.
Note that the update of load_avg will effectively happen only once in order
to sync up to the throttled time. Next call for updating load_avg will stop
early because the clock stays unchanged.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 6d4d22468d ("sched/fair: Reorder enqueue/dequeue_task_fair path")
Link: https://lkml.kernel.org/r/20200306084208.12583-1-vincent.guittot@linaro.org
When a cfs_rq is throttled, its group entity is dequeued and its running
tasks are removed. We must update runnable_avg with the old h_nr_running
and update group_se->runnable_weight with the new h_nr_running at each
level of the hierarchy.
Reviewed-by: Ben Segall <bsegall@google.com>
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 9f68395333 ("sched/pelt: Add a new runnable average signal")
Link: https://lkml.kernel.org/r/20200227154115.8332-1-vincent.guittot@linaro.org
Since commit 06a76fe08d ("sched/deadline: Move DL related code
from sched/core.c to sched/deadline.c"), DL related code moved to
deadline.c.
Make the following two functions static since they're only used in
deadline.c:
dl_change_utilization()
init_dl_rq_bw_ratio()
Signed-off-by: Yu Chen <chen.yu@easystack.cn>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200228100329.16927-1-chen.yu@easystack.cn
EAS already requires asymmetric CPU capacities to be enabled, and mixing
this with SMT is an aberration, but better be safe than sorry.
Reviewed-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Acked-by: Quentin Perret <qperret@google.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200227191433.31994-2-valentin.schneider@arm.com
Qian Cai reported the following bug:
The linux-next commit ff7db0bf24 ("sched/numa: Prefer using an idle CPU as a
migration target instead of comparing tasks") introduced a boot warning,
[ 86.520534][ T1] WARNING: suspicious RCU usage
[ 86.520540][ T1] 5.6.0-rc3-next-20200227 #7 Not tainted
[ 86.520545][ T1] -----------------------------
[ 86.520551][ T1] kernel/sched/fair.c:5914 suspicious rcu_dereference_check() usage!
[ 86.520555][ T1]
[ 86.520555][ T1] other info that might help us debug this:
[ 86.520555][ T1]
[ 86.520561][ T1]
[ 86.520561][ T1] rcu_scheduler_active = 2, debug_locks = 1
[ 86.520567][ T1] 1 lock held by systemd/1:
[ 86.520571][ T1] #0: ffff8887f4b14848 (&mm->mmap_sem#2){++++}, at: do_page_fault+0x1d2/0x998
[ 86.520594][ T1]
[ 86.520594][ T1] stack backtrace:
[ 86.520602][ T1] CPU: 1 PID: 1 Comm: systemd Not tainted 5.6.0-rc3-next-20200227 #7
task_numa_migrate() checks for idle cores when updating NUMA-related statistics.
This relies on reading a RCU-protected structure in test_idle_cores() via this
call chain
task_numa_migrate
-> update_numa_stats
-> numa_idle_core
-> test_idle_cores
While the locking could be fine-grained, it is more appropriate to acquire
the RCU lock for the entire scan of the domain. This patch removes the
warning triggered at boot time.
Reported-by: Qian Cai <cai@lca.pw>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: ff7db0bf24 ("sched/numa: Prefer using an idle CPU as a migration target instead of comparing tasks")
Link: https://lkml.kernel.org/r/20200227191804.GJ3818@techsingularity.net
Building against the tip/sched/core as ff7db0bf24 ("sched/numa: Prefer
using an idle CPU as a migration target instead of comparing tasks") with
the arm64 defconfig (which doesn't have CONFIG_SCHED_SMT set) leads to:
kernel/sched/fair.c:1525:20: warning: 'test_idle_cores' declared 'static' but never defined [-Wunused-function]
static inline bool test_idle_cores(int cpu, bool def);
^~~~~~~~~~~~~~~
Rather than define it in its own CONFIG_SCHED_SMT #define island, bunch it
up with test_idle_cores().
Reported-by: Anshuman Khandual <anshuman.khandual@arm.com>
Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org>
Reviewed-by: Lukasz Luba <lukasz.luba@arm.com>
[mgorman@techsingularity.net: Edit changelog, minor style change]
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: ff7db0bf24 ("sched/numa: Prefer using an idle CPU as a migration target instead of comparing tasks")
Link: https://lkml.kernel.org/r/20200303110258.1092-3-mgorman@techsingularity.net
Thermal pressure follows pelt signals which means the decay period for
thermal pressure is the default pelt decay period. Depending on SoC
characteristics and thermal activity, it might be beneficial to decay
thermal pressure slower, but still in-tune with the pelt signals. One way
to achieve this is to provide a command line parameter to set a decay
shift parameter to an integer between 0 and 10.
Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200222005213.3873-10-thara.gopinath@linaro.org
cpu_capacity initially reflects the maximum possible capacity of a CPU.
Thermal pressure on a CPU means this maximum possible capacity is
unavailable due to thermal events. This patch subtracts the average
thermal pressure for a CPU from its maximum possible capacity so that
cpu_capacity reflects the remaining maximum capacity.
Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200222005213.3873-8-thara.gopinath@linaro.org
Introduce support in scheduler periodic tick and other CFS bookkeeping
APIs to trigger the process of computing average thermal pressure for a
CPU. Also consider avg_thermal.load_avg in others_have_blocked which
allows for decay of pelt signals.
Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200222005213.3873-7-thara.gopinath@linaro.org
Extrapolating on the existing framework to track rt/dl utilization using
pelt signals, add a similar mechanism to track thermal pressure. The
difference here from rt/dl utilization tracking is that, instead of
tracking time spent by a CPU running a RT/DL task through util_avg, the
average thermal pressure is tracked through load_avg. This is because
thermal pressure signal is weighted time "delta" capacity unlike util_avg
which is binary. "delta capacity" here means delta between the actual
capacity of a CPU and the decreased capacity a CPU due to a thermal event.
In order to track average thermal pressure, a new sched_avg variable
avg_thermal is introduced. Function update_thermal_load_avg can be called
to do the periodic bookkeeping (accumulate, decay and average) of the
thermal pressure.
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Thara Gopinath <thara.gopinath@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200222005213.3873-2-thara.gopinath@linaro.org
As the vtime is sampled under loose seqcount protection by kcpustat, the
vtime fields may change as the code flows. Where logic dictates a field
has a static value, use a READ_ONCE.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Frederic Weisbecker <frederic@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Fixes: 74722bb223 ("sched/vtime: Bring up complete kcpustat accessor")
Link: https://lkml.kernel.org/r/20200123180849.28486-1-frederic@kernel.org
sgs->group_weight is not set while gathering statistics in
update_sg_wakeup_stats(). This means that a group can be classified as
fully busy with 0 running tasks if utilization is high enough.
This path is mainly used for fork and exec.
Fixes: 57abff067a ("sched/fair: Rework find_idlest_group()")
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lore.kernel.org/r/20200218144534.4564-1-vincent.guittot@linaro.org
When domains are imbalanced or overloaded a search of all CPUs on the
target domain is searched and compared with task_numa_compare. In some
circumstances, a candidate is found that is an obvious win.
o A task can move to an idle CPU and an idle CPU is found
o A swap candidate is found that would move to its preferred domain
This patch terminates the search when either condition is met.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-14-mgorman@techsingularity.net
When swapping tasks for NUMA balancing, it is preferred that tasks move
to or remain on their preferred node. When considering an imbalance,
encourage tasks to move to their preferred node and discourage tasks from
moving away from their preferred node.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-13-mgorman@techsingularity.net
Multiple tasks can attempt to select and idle CPU but fail because
numa_migrate_on is already set and the migration fails. Instead of failing,
scan for an alternative idle CPU. select_idle_sibling is not used because
it requires IRQs to be disabled and it ignores numa_migrate_on allowing
multiple tasks to stack. This scan may still fail if there are idle
candidate CPUs due to races but if this occurs, it's best that a task
stay on an available CPU that move to a contended one.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-12-mgorman@techsingularity.net
task_numa_find_cpu() can scan a node multiple times. Minimally it scans to
gather statistics and later to find a suitable target. In some cases, the
second scan will simply pick an idle CPU if the load is not imbalanced.
This patch caches information on an idle core while gathering statistics
and uses it immediately if load is not imbalanced to avoid a second scan
of the node runqueues. Preference is given to an idle core rather than an
idle SMT sibling to avoid packing HT siblings due to linearly scanning the
node cpumask.
As a side-effect, even when the second scan is necessary, the importance
of using select_idle_sibling is much reduced because information on idle
CPUs is cached and can be reused.
Note that this patch actually makes is harder to move to an idle CPU
as multiple tasks can race for the same idle CPU due to a race checking
numa_migrate_on. This is addressed in the next patch.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-11-mgorman@techsingularity.net
Take into account the new runnable_avg signal to classify a group and to
mitigate the volatility of util_avg in face of intensive migration or
new task with random utilization.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-10-mgorman@techsingularity.net
Now that runnable_load_avg has been removed, we can replace it by a new
signal that will highlight the runnable pressure on a cfs_rq. This signal
track the waiting time of tasks on rq and can help to better define the
state of rqs.
At now, only util_avg is used to define the state of a rq:
A rq with more that around 80% of utilization and more than 1 tasks is
considered as overloaded.
But the util_avg signal of a rq can become temporaly low after that a task
migrated onto another rq which can bias the classification of the rq.
When tasks compete for the same rq, their runnable average signal will be
higher than util_avg as it will include the waiting time and we can use
this signal to better classify cfs_rqs.
The new runnable_avg will track the runnable time of a task which simply
adds the waiting time to the running time. The runnable _avg of cfs_rq
will be the /Sum of se's runnable_avg and the runnable_avg of group entity
will follow the one of the rq similarly to util_avg.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-9-mgorman@techsingularity.net
Now that runnable_load_avg is no more used, we can remove it to make
space for a new signal.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-8-mgorman@techsingularity.net
The standard load balancer generally tries to keep the number of running
tasks or idle CPUs balanced between NUMA domains. The NUMA balancer allows
tasks to move if there is spare capacity but this causes a conflict and
utilisation between NUMA nodes gets badly skewed. This patch uses similar
logic between the NUMA balancer and load balancer when deciding if a task
migrating to its preferred node can use an idle CPU.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-7-mgorman@techsingularity.net
Similarly to what has been done for the normal load balancer, we can
replace runnable_load_avg by load_avg in numa load balancing and track the
other statistics like the utilization and the number of running tasks to
get to better view of the current state of a node.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-6-mgorman@techsingularity.net
The walk through the cgroup hierarchy during the enqueue/dequeue of a task
is split in 2 distinct parts for throttled cfs_rq without any added value
but making code less readable.
Change the code ordering such that everything related to a cfs_rq
(throttled or not) will be done in the same loop.
In addition, the same steps ordering is used when updating a cfs_rq:
- update_load_avg
- update_cfs_group
- update *h_nr_running
This reordering enables the use of h_nr_running in PELT algorithm.
No functional and performance changes are expected and have been noticed
during tests.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: "Dietmar Eggemann <dietmar.eggemann@arm.com>"
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-5-mgorman@techsingularity.net
sched:sched_stick_numa is meant to fire when a task is unable to migrate
to the preferred node but from the trace, it's possibile to tell the
difference between "no CPU found", "migration to idle CPU failed" and
"tasks could not be swapped". Extend the tracepoint accordingly.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
[ Minor edits. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-4-mgorman@techsingularity.net
sched:sched_stick_numa is meant to fire when a task is unable to migrate
to the preferred node. The case where no candidate CPU could be found is
not traced which is an important gap. The tracepoint is not fired when
the task is not allowed to run on any CPU on the preferred node or the
task is already running on the target CPU but neither are interesting
corner cases.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Valentin Schneider <valentin.schneider@arm.com>
Cc: Phil Auld <pauld@redhat.com>
Cc: Hillf Danton <hdanton@sina.com>
Link: https://lore.kernel.org/r/20200224095223.13361-3-mgorman@techsingularity.net
Capacity-awareness in the wake-up path previously involved disabling
wake_affine in certain scenarios. We have just made select_idle_sibling()
capacity-aware, so this isn't needed anymore.
Remove wake_cap() entirely.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
[Changelog tweaks]
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[Changelog tweaks]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lkml.kernel.org/r/20200206191957.12325-5-valentin.schneider@arm.com
The last remaining user of this macro has just been removed, get rid of it.
Suggested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lkml.kernel.org/r/20200206191957.12325-4-valentin.schneider@arm.com
SD_BALANCE_WAKE was previously added to lower sched_domain levels on
asymmetric CPU capacity systems by commit:
9ee1cda5ee ("sched/core: Enable SD_BALANCE_WAKE for asymmetric capacity systems")
to enable the use of find_idlest_cpu() and friends to find an appropriate
CPU for tasks.
That responsibility has now been shifted to select_idle_sibling() and
friends, and hence the flag can be removed. Note that this causes
asymmetric CPU capacity systems to no longer enter the slow wakeup path
(find_idlest_cpu()) on wakeups - only on execs and forks (which is aligned
with all other mainline topologies).
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
[Changelog tweaks]
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lkml.kernel.org/r/20200206191957.12325-3-valentin.schneider@arm.com
Issue
=====
On asymmetric CPU capacity topologies, we currently rely on wake_cap() to
drive select_task_rq_fair() towards either:
- its slow-path (find_idlest_cpu()) if either the previous or
current (waking) CPU has too little capacity for the waking task
- its fast-path (select_idle_sibling()) otherwise
Commit:
3273163c67 ("sched/fair: Let asymmetric CPU configurations balance at wake-up")
points out that this relies on the assumption that "[...]the CPU capacities
within an SD_SHARE_PKG_RESOURCES domain (sd_llc) are homogeneous".
This assumption no longer holds on newer generations of big.LITTLE
systems (DynamIQ), which can accommodate CPUs of different compute capacity
within a single LLC domain. To hopefully paint a better picture, a regular
big.LITTLE topology would look like this:
+---------+ +---------+
| L2 | | L2 |
+----+----+ +----+----+
|CPU0|CPU1| |CPU2|CPU3|
+----+----+ +----+----+
^^^ ^^^
LITTLEs bigs
which would result in the following scheduler topology:
DIE [ ] <- sd_asym_cpucapacity
MC [ ] [ ] <- sd_llc
0 1 2 3
Conversely, a DynamIQ topology could look like:
+-------------------+
| L3 |
+----+----+----+----+
| L2 | L2 | L2 | L2 |
+----+----+----+----+
|CPU0|CPU1|CPU2|CPU3|
+----+----+----+----+
^^^^^ ^^^^^
LITTLEs bigs
which would result in the following scheduler topology:
MC [ ] <- sd_llc, sd_asym_cpucapacity
0 1 2 3
What this means is that, on DynamIQ systems, we could pass the wake_cap()
test (IOW presume the waking task fits on the CPU capacities of some LLC
domain), thus go through select_idle_sibling().
This function operates on an LLC domain, which here spans both bigs and
LITTLEs, so it could very well pick a CPU of too small capacity for the
task, despite there being fitting idle CPUs - it very much depends on the
CPU iteration order, on which we have absolutely no guarantees
capacity-wise.
Implementation
==============
Introduce yet another select_idle_sibling() helper function that takes CPU
capacity into account. The policy is to pick the first idle CPU which is
big enough for the task (task_util * margin < cpu_capacity). If no
idle CPU is big enough, we pick the idle one with the highest capacity.
Unlike other select_idle_sibling() helpers, this one operates on the
sd_asym_cpucapacity sched_domain pointer, which is guaranteed to span all
known CPU capacities in the system. As such, this will work for both
"legacy" big.LITTLE (LITTLEs & bigs split at MC, joined at DIE) and for
newer DynamIQ systems (e.g. LITTLEs and bigs in the same MC domain).
Note that this limits the scope of select_idle_sibling() to
select_idle_capacity() for asymmetric CPU capacity systems - the LLC domain
will not be scanned, and no further heuristic will be applied.
Signed-off-by: Morten Rasmussen <morten.rasmussen@arm.com>
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Quentin Perret <qperret@google.com>
Link: https://lkml.kernel.org/r/20200206191957.12325-2-valentin.schneider@arm.com
Pull scheduler fixes from Ingo Molnar:
"Misc fixes all over the place:
- Fix NUMA over-balancing between lightly loaded nodes. This is
fallout of the big load-balancer rewrite.
- Fix the NOHZ remote loadavg update logic, which fixes anomalies
like reported 150 loadavg on mostly idle CPUs.
- Fix XFS performance/scalability
- Fix throttled groups unbound task-execution bug
- Fix PSI procfs boundary condition
- Fix the cpu.uclamp.{min,max} cgroup configuration write checks
- Fix DocBook annotations
- Fix RCU annotations
- Fix overly CPU-intensive housekeeper CPU logic loop on large CPU
counts"
* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/fair: Fix kernel-doc warning in attach_entity_load_avg()
sched/core: Annotate curr pointer in rq with __rcu
sched/psi: Fix OOB write when writing 0 bytes to PSI files
sched/fair: Allow a per-CPU kthread waking a task to stack on the same CPU, to fix XFS performance regression
sched/fair: Prevent unlimited runtime on throttled group
sched/nohz: Optimize get_nohz_timer_target()
sched/uclamp: Reject negative values in cpu_uclamp_write()
sched/fair: Allow a small load imbalance between low utilisation SD_NUMA domains
timers/nohz: Update NOHZ load in remote tick
sched/core: Don't skip remote tick for idle CPUs
Fix kernel-doc warning in kernel/sched/fair.c, caused by a recent
function parameter removal:
../kernel/sched/fair.c:3526: warning: Excess function parameter 'flags' description in 'attach_entity_load_avg'
Fixes: a4f9a0e51b ("sched/fair: Remove redundant call to cpufreq_update_util()")
Signed-off-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lkml.kernel.org/r/cbe964e4-6879-fd08-41c9-ef1917414af4@infradead.org
Issuing write() with count parameter set to 0 on any file under
/proc/pressure/ will cause an OOB write because of the access to
buf[buf_size-1] when NUL-termination is performed. Fix this by checking
for buf_size to be non-zero.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Link: https://lkml.kernel.org/r/20200203212216.7076-1-surenb@google.com
The following XFS commit:
8ab39f11d9 ("xfs: prevent CIL push holdoff in log recovery")
changed the logic from using bound workqueues to using unbound
workqueues. Functionally this makes sense but it was observed at the
time that the dbench performance dropped quite a lot and CPU migrations
were increased.
The current pattern of the task migration is straight-forward. With XFS,
an IO issuer delegates work to xlog_cil_push_work ()on an unbound kworker.
This runs on a nearby CPU and on completion, dbench wakes up on its old CPU
as it is still idle and no migration occurs. dbench then queues the real
IO on the blk_mq_requeue_work() work item which runs on a bound kworker
which is forced to run on the same CPU as dbench. When IO completes,
the bound kworker wakes dbench but as the kworker is a bound but,
real task, the CPU is not considered idle and dbench gets migrated by
select_idle_sibling() to a new CPU. dbench may ping-pong between two CPUs
for a while but ultimately it starts a round-robin of all CPUs sharing
the same LLC. High-frequency migration on each IO completion has poor
performance overall. It has negative implications both in commication
costs and power management. mpstat confirmed that at low thread counts
that all CPUs sharing an LLC has low level of activity.
Note that even if the CIL patch was reverted, there still would
be migrations but the impact is less noticeable. It turns out that
individually the scheduler, XFS, blk-mq and workqueues all made sensible
decisions but in combination, the overall effect was sub-optimal.
This patch special cases the IO issue/completion pattern and allows
a bound kworker waker and a task wakee to stack on the same CPU if
there is a strong chance they are directly related. The expectation
is that the kworker is likely going back to sleep shortly. This is not
guaranteed as the IO could be queued asynchronously but there is a very
strong relationship between the task and kworker in this case that would
justify stacking on the same CPU instead of migrating. There should be
few concerns about kworker starvation given that the special casing is
only when the kworker is the waker.
DBench on XFS
MMTests config: io-dbench4-async modified to run on a fresh XFS filesystem
UMA machine with 8 cores sharing LLC
5.5.0-rc7 5.5.0-rc7
tipsched-20200124 kworkerstack
Amean 1 22.63 ( 0.00%) 20.54 * 9.23%*
Amean 2 25.56 ( 0.00%) 23.40 * 8.44%*
Amean 4 28.63 ( 0.00%) 27.85 * 2.70%*
Amean 8 37.66 ( 0.00%) 37.68 ( -0.05%)
Amean 64 469.47 ( 0.00%) 468.26 ( 0.26%)
Stddev 1 1.00 ( 0.00%) 0.72 ( 28.12%)
Stddev 2 1.62 ( 0.00%) 1.97 ( -21.54%)
Stddev 4 2.53 ( 0.00%) 3.58 ( -41.19%)
Stddev 8 5.30 ( 0.00%) 5.20 ( 1.92%)
Stddev 64 86.36 ( 0.00%) 94.53 ( -9.46%)
NUMA machine, 48 CPUs total, 24 CPUs share cache
5.5.0-rc7 5.5.0-rc7
tipsched-20200124 kworkerstack-v1r2
Amean 1 58.69 ( 0.00%) 30.21 * 48.53%*
Amean 2 60.90 ( 0.00%) 35.29 * 42.05%*
Amean 4 66.77 ( 0.00%) 46.55 * 30.28%*
Amean 8 81.41 ( 0.00%) 68.46 * 15.91%*
Amean 16 113.29 ( 0.00%) 107.79 * 4.85%*
Amean 32 199.10 ( 0.00%) 198.22 * 0.44%*
Amean 64 478.99 ( 0.00%) 477.06 * 0.40%*
Amean 128 1345.26 ( 0.00%) 1372.64 * -2.04%*
Stddev 1 2.64 ( 0.00%) 4.17 ( -58.08%)
Stddev 2 4.35 ( 0.00%) 5.38 ( -23.73%)
Stddev 4 6.77 ( 0.00%) 6.56 ( 3.00%)
Stddev 8 11.61 ( 0.00%) 10.91 ( 6.04%)
Stddev 16 18.63 ( 0.00%) 19.19 ( -3.01%)
Stddev 32 38.71 ( 0.00%) 38.30 ( 1.06%)
Stddev 64 100.28 ( 0.00%) 91.24 ( 9.02%)
Stddev 128 186.87 ( 0.00%) 160.34 ( 14.20%)
Dbench has been modified to report the time to complete a single "load
file". This is a more meaningful metric for dbench that a throughput
metric as the benchmark makes many different system calls that are not
throughput-related
Patch shows a 9.23% and 48.53% reduction in the time to process a load
file with the difference partially explained by the number of CPUs sharing
a LLC. In a separate run, task migrations were almost eliminated by the
patch for low client counts. In case people have issue with the metric
used for the benchmark, this is a comparison of the throughputs as
reported by dbench on the NUMA machine.
dbench4 Throughput (misleading but traditional)
5.5.0-rc7 5.5.0-rc7
tipsched-20200124 kworkerstack-v1r2
Hmean 1 321.41 ( 0.00%) 617.82 * 92.22%*
Hmean 2 622.87 ( 0.00%) 1066.80 * 71.27%*
Hmean 4 1134.56 ( 0.00%) 1623.74 * 43.12%*
Hmean 8 1869.96 ( 0.00%) 2212.67 * 18.33%*
Hmean 16 2673.11 ( 0.00%) 2806.13 * 4.98%*
Hmean 32 3032.74 ( 0.00%) 3039.54 ( 0.22%)
Hmean 64 2514.25 ( 0.00%) 2498.96 * -0.61%*
Hmean 128 1778.49 ( 0.00%) 1746.05 * -1.82%*
Note that this is somewhat specific to XFS and ext4 shows no performance
difference as it does not rely on kworkers in the same way. No major
problem was observed running other workloads on different machines although
not all tests have completed yet.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200128154006.GD3466@techsingularity.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Group RT scheduler contains protection against setting zero runtime for
cgroup with RT tasks. Right now function tg_set_rt_bandwidth() iterates
over all CPU cgroups and calls tg_has_rt_tasks() for any cgroup which
runtime is zero (not only for changed one). Default RT runtime is zero,
thus tg_has_rt_tasks() will is called for almost at CPU cgroups.
This protection already is slightly racy: runtime limit could be changed
between cpu_cgroup_can_attach() and cpu_cgroup_attach() because changing
cgroup attribute does not lock cgroup_mutex while attach does not lock
rt_constraints_mutex. Changing task scheduler class also races with
changing rt runtime: check in __sched_setscheduler() isn't protected.
Function tg_has_rt_tasks() iterates over all threads in the system.
This gives NR_CGROUPS * NR_TASKS operations under single tasklist_lock
locked for read tg_set_rt_bandwidth(). Any concurrent attempt of locking
tasklist_lock for write (for example fork) will stuck with disabled irqs.
This patch makes two optimizations:
1) Remove locking tasklist_lock and iterate only tasks in cgroup
2) Call tg_has_rt_tasks() iff rt runtime changes from non-zero to zero
All changed code is under CONFIG_RT_GROUP_SCHED.
Testcase:
# mkdir /sys/fs/cgroup/cpu/test{1..10000}
# echo 0 | tee /sys/fs/cgroup/cpu/test*/cpu.rt_runtime_us
At the same time without patch fork time will be >100ms:
# perf trace -e clone --duration 100 stress-ng --fork 1
Also remote ping will show timings >100ms caused by irq latency.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@yandex-team.ru>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/157996383820.4651.11292439232549211693.stgit@buzz
Currently we loop through all threads of a core to evaluate if the core is
idle or not. This is unnecessary. If a thread of a core is not idle, skip
evaluating other threads of a core. Also while clearing the cpumask, bits
of all CPUs of a core can be cleared in one-shot.
Collecting ticks on a Power 9 SMT 8 system around select_idle_core
while running schbench shows us
(units are in ticks, hence lesser is better)
Without patch
N Min Max Median Avg Stddev
x 130 151 1083 284 322.72308 144.41494
With patch
N Min Max Median Avg Stddev Improvement
x 164 88 610 201 225.79268 106.78943 30.03%
Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Link: https://lkml.kernel.org/r/20191206172422.6578-1-srikar@linux.vnet.ibm.com
Implement arch_scale_freq_capacity() for 'modern' x86. This function
is used by the scheduler to correctly account usage in the face of
DVFS.
The present patch addresses Intel processors specifically and has positive
performance and performance-per-watt implications for the schedutil cpufreq
governor, bringing it closer to, if not on-par with, the powersave governor
from the intel_pstate driver/framework.
Large performance gains are obtained when the machine is lightly loaded and
no regression are observed at saturation. The benchmarks with the largest
gains are kernel compilation, tbench (the networking version of dbench) and
shell-intensive workloads.
1. FREQUENCY INVARIANCE: MOTIVATION
* Without it, a task looks larger if the CPU runs slower
2. PECULIARITIES OF X86
* freq invariance accounting requires knowing the ratio freq_curr/freq_max
2.1 CURRENT FREQUENCY
* Use delta_APERF / delta_MPERF * freq_base (a.k.a "BusyMHz")
2.2 MAX FREQUENCY
* It varies with time (turbo). As an approximation, we set it to a
constant, i.e. 4-cores turbo frequency.
3. EFFECTS ON THE SCHEDUTIL FREQUENCY GOVERNOR
* The invariant schedutil's formula has no feedback loop and reacts faster
to utilization changes
4. KNOWN LIMITATIONS
* In some cases tasks can't reach max util despite how hard they try
5. PERFORMANCE TESTING
5.1 MACHINES
* Skylake, Broadwell, Haswell
5.2 SETUP
* baseline Linux v5.2 w/ non-invariant schedutil. Tested freq_max = 1-2-3-4-8-12
active cores turbo w/ invariant schedutil, and intel_pstate/powersave
5.3 BENCHMARK RESULTS
5.3.1 NEUTRAL BENCHMARKS
* NAS Parallel Benchmark (HPC), hackbench
5.3.2 NON-NEUTRAL BENCHMARKS
* tbench (10-30% better), kernbench (10-15% better),
shell-intensive-scripts (30-50% better)
* no regressions
5.3.3 SELECTION OF DETAILED RESULTS
5.3.4 POWER CONSUMPTION, PERFORMANCE-PER-WATT
* dbench (5% worse on one machine), kernbench (3% worse),
tbench (5-10% better), shell-intensive-scripts (10-40% better)
6. MICROARCH'ES ADDRESSED HERE
* Xeon Core before Scalable Performance processors line (Xeon Gold/Platinum
etc have different MSRs semantic for querying turbo levels)
7. REFERENCES
* MMTests performance testing framework, github.com/gormanm/mmtests
+-------------------------------------------------------------------------+
| 1. FREQUENCY INVARIANCE: MOTIVATION
+-------------------------------------------------------------------------+
For example; suppose a CPU has two frequencies: 500 and 1000 Mhz. When
running a task that would consume 1/3rd of a CPU at 1000 MHz, it would
appear to consume 2/3rd (or 66.6%) when running at 500 MHz, giving the
false impression this CPU is almost at capacity, even though it can go
faster [*]. In a nutshell, without frequency scale-invariance tasks look
larger just because the CPU is running slower.
[*] (footnote: this assumes a linear frequency/performance relation; which
everybody knows to be false, but given realities its the best approximation
we can make.)
+-------------------------------------------------------------------------+
| 2. PECULIARITIES OF X86
+-------------------------------------------------------------------------+
Accounting for frequency changes in PELT signals requires the computation of
the ratio freq_curr / freq_max. On x86 neither of those terms is readily
available.
2.1 CURRENT FREQUENCY
====================
Since modern x86 has hardware control over the actual frequency we run
at (because amongst other things, Turbo-Mode), we cannot simply use
the frequency as requested through cpufreq.
Instead we use the APERF/MPERF MSRs to compute the effective frequency
over the recent past. Also, because reading MSRs is expensive, don't
do so every time we need the value, but amortize the cost by doing it
every tick.
2.2 MAX FREQUENCY
=================
Obtaining freq_max is also non-trivial because at any time the hardware can
provide a frequency boost to a selected subset of cores if the package has
enough power to spare (eg: Turbo Boost). This means that the maximum frequency
available to a given core changes with time.
The approach taken in this change is to arbitrarily set freq_max to a constant
value at boot. The value chosen is the "4-cores (4C) turbo frequency" on most
microarchitectures, after evaluating the following candidates:
* 1-core (1C) turbo frequency (the fastest turbo state available)
* around base frequency (a.k.a. max P-state)
* something in between, such as 4C turbo
To interpret these options, consider that this is the denominator in
freq_curr/freq_max, and that ratio will be used to scale PELT signals such as
util_avg and load_avg. A large denominator will undershoot (util_avg looks a
bit smaller than it really is), viceversa with a smaller denominator PELT
signals will tend to overshoot. Given that PELT drives frequency selection
in the schedutil governor, we will have:
freq_max set to | effect on DVFS
--------------------+------------------
1C turbo | power efficiency (lower freq choices)
base freq | performance (higher util_avg, higher freq requests)
4C turbo | a bit of both
4C turbo proves to be a good compromise in a number of benchmarks (see below).
+-------------------------------------------------------------------------+
| 3. EFFECTS ON THE SCHEDUTIL FREQUENCY GOVERNOR
+-------------------------------------------------------------------------+
Once an architecture implements a frequency scale-invariant utilization (the
PELT signal util_avg), schedutil switches its frequency selection formula from
freq_next = 1.25 * freq_curr * util [non-invariant util signal]
to
freq_next = 1.25 * freq_max * util [invariant util signal]
where, in the second formula, freq_max is set to the 1C turbo frequency (max
turbo). The advantage of the second formula, whose usage we unlock with this
patch, is that freq_next doesn't depend on the current frequency in an
iterative fashion, but can jump to any frequency in a single update. This
absence of feedback in the formula makes it quicker to react to utilization
changes and more robust against pathological instabilities.
Compare it to the update formula of intel_pstate/powersave:
freq_next = 1.25 * freq_max * Busy%
where again freq_max is 1C turbo and Busy% is the percentage of time not spent
idling (calculated with delta_MPERF / delta_TSC); essentially the same as
invariant schedutil, and largely responsible for intel_pstate/powersave good
reputation. The non-invariant schedutil formula is derived from the invariant
one by approximating util_inv with util_raw * freq_curr / freq_max, but this
has limitations.
Testing shows improved performances due to better frequency selections when
the machine is lightly loaded, and essentially no change in behaviour at
saturation / overutilization.
+-------------------------------------------------------------------------+
| 4. KNOWN LIMITATIONS
+-------------------------------------------------------------------------+
It's been shown that it is possible to create pathological scenarios where a
CPU-bound task cannot reach max utilization, if the normalizing factor
freq_max is fixed to a constant value (see [Lelli-2018]).
If freq_max is set to 4C turbo as we do here, one needs to peg at least 5
cores in a package doing some busywork, and observe that none of those task
will ever reach max util (1024) because they're all running at less than the
4C turbo frequency.
While this concern still applies, we believe the performance benefit of
frequency scale-invariant PELT signals outweights the cost of this limitation.
[Lelli-2018]
https://lore.kernel.org/lkml/20180517150418.GF22493@localhost.localdomain/
+-------------------------------------------------------------------------+
| 5. PERFORMANCE TESTING
+-------------------------------------------------------------------------+
5.1 MACHINES
============
We tested the patch on three machines, with Skylake, Broadwell and Haswell
CPUs. The details are below, together with the available turbo ratios as
reported by the appropriate MSRs.
* 8x-SKYLAKE-UMA:
Single socket E3-1240 v5, Skylake 4 cores/8 threads
Max EFFiciency, BASE frequency and available turbo levels (MHz):
EFFIC 800 |********
BASE 3500 |***********************************
4C 3700 |*************************************
3C 3800 |**************************************
2C 3900 |***************************************
1C 3900 |***************************************
* 80x-BROADWELL-NUMA:
Two sockets E5-2698 v4, 2x Broadwell 20 cores/40 threads
Max EFFiciency, BASE frequency and available turbo levels (MHz):
EFFIC 1200 |************
BASE 2200 |**********************
8C 2900 |*****************************
7C 3000 |******************************
6C 3100 |*******************************
5C 3200 |********************************
4C 3300 |*********************************
3C 3400 |**********************************
2C 3600 |************************************
1C 3600 |************************************
* 48x-HASWELL-NUMA
Two sockets E5-2670 v3, 2x Haswell 12 cores/24 threads
Max EFFiciency, BASE frequency and available turbo levels (MHz):
EFFIC 1200 |************
BASE 2300 |***********************
12C 2600 |**************************
11C 2600 |**************************
10C 2600 |**************************
9C 2600 |**************************
8C 2600 |**************************
7C 2600 |**************************
6C 2600 |**************************
5C 2700 |***************************
4C 2800 |****************************
3C 2900 |*****************************
2C 3100 |*******************************
1C 3100 |*******************************
5.2 SETUP
=========
* The baseline is Linux v5.2 with schedutil (non-invariant) and the intel_pstate
driver in passive mode.
* The rationale for choosing the various freq_max values to test have been to
try all the 1-2-3-4C turbo levels (note that 1C and 2C turbo are identical
on all machines), plus one more value closer to base_freq but still in the
turbo range (8C turbo for both 80x-BROADWELL-NUMA and 48x-HASWELL-NUMA).
* In addition we've run all tests with intel_pstate/powersave for comparison.
* The filesystem is always XFS, the userspace is openSUSE Leap 15.1.
* 8x-SKYLAKE-UMA is capable of HWP (Hardware-Managed P-States), so the runs
with active intel_pstate on this machine use that.
This gives, in terms of combinations tested on each machine:
* 8x-SKYLAKE-UMA
* Baseline: Linux v5.2, non-invariant schedutil, intel_pstate passive
* intel_pstate active + powersave + HWP
* invariant schedutil, freq_max = 1C turbo
* invariant schedutil, freq_max = 3C turbo
* invariant schedutil, freq_max = 4C turbo
* both 80x-BROADWELL-NUMA and 48x-HASWELL-NUMA
* [same as 8x-SKYLAKE-UMA, but no HWP capable]
* invariant schedutil, freq_max = 8C turbo
(which on 48x-HASWELL-NUMA is the same as 12C turbo, or "all cores turbo")
5.3 BENCHMARK RESULTS
=====================
5.3.1 NEUTRAL BENCHMARKS
------------------------
Tests that didn't show any measurable difference in performance on any of the
test machines between non-invariant schedutil and our patch are:
* NAS Parallel Benchmarks (NPB) using either MPI or openMP for IPC, any
computational kernel
* flexible I/O (FIO)
* hackbench (using threads or processes, and using pipes or sockets)
5.3.2 NON-NEUTRAL BENCHMARKS
----------------------------
What follow are summary tables where each benchmark result is given a score.
* A tilde (~) means a neutral result, i.e. no difference from baseline.
* Scores are computed with the ratio result_new / result_baseline, so a tilde
means a score of 1.00.
* The results in the score ratio are the geometric means of results running
the benchmark with different parameters (eg: for kernbench: using 1, 2, 4,
... number of processes; for pgbench: varying the number of clients, and so
on).
* The first three tables show higher-is-better kind of tests (i.e. measured in
operations/second), the subsequent three show lower-is-better kind of tests
(i.e. the workload is fixed and we measure elapsed time, think kernbench).
* "gitsource" is a name we made up for the test consisting in running the
entire unit tests suite of the Git SCM and measuring how long it takes. We
take it as a typical example of shell-intensive serialized workload.
* In the "I_PSTATE" column we have the results for intel_pstate/powersave. Other
columns show invariant schedutil for different values of freq_max. 4C turbo
is circled as it's the value we've chosen for the final implementation.
80x-BROADWELL-NUMA (comparison ratio; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
pgbench-ro 1.14 ~ ~ | 1.11 | 1.14
pgbench-rw ~ ~ ~ | ~ | ~
netperf-udp 1.06 ~ 1.06 | 1.05 | 1.07
netperf-tcp ~ 1.03 ~ | 1.01 | 1.02
tbench4 1.57 1.18 1.22 | 1.30 | 1.56
+------+
8x-SKYLAKE-UMA (comparison ratio; higher is better)
+------+
I_PSTATE/HWP 1C 3C | 4C |
pgbench-ro ~ ~ ~ | ~ |
pgbench-rw ~ ~ ~ | ~ |
netperf-udp ~ ~ ~ | ~ |
netperf-tcp ~ ~ ~ | ~ |
tbench4 1.30 1.14 1.14 | 1.16 |
+------+
48x-HASWELL-NUMA (comparison ratio; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 12C
pgbench-ro 1.15 ~ ~ | 1.06 | 1.16
pgbench-rw ~ ~ ~ | ~ | ~
netperf-udp 1.05 0.97 1.04 | 1.04 | 1.02
netperf-tcp 0.96 1.01 1.01 | 1.01 | 1.01
tbench4 1.50 1.05 1.13 | 1.13 | 1.25
+------+
In the table above we see that active intel_pstate is slightly better than our
4C-turbo patch (both in reference to the baseline non-invariant schedutil) on
read-only pgbench and much better on tbench. Both cases are notable in which
it shows that lowering our freq_max (to 8C-turbo and 12C-turbo on
80x-BROADWELL-NUMA and 48x-HASWELL-NUMA respectively) helps invariant
schedutil to get closer.
If we ignore active intel_pstate and focus on the comparison with baseline
alone, there are several instances of double-digit performance improvement.
80x-BROADWELL-NUMA (comparison ratio; lower is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
dbench4 1.23 0.95 0.95 | 0.95 | 0.95
kernbench 0.93 0.83 0.83 | 0.83 | 0.82
gitsource 0.98 0.49 0.49 | 0.49 | 0.48
+------+
8x-SKYLAKE-UMA (comparison ratio; lower is better)
+------+
I_PSTATE/HWP 1C 3C | 4C |
dbench4 ~ ~ ~ | ~ |
kernbench ~ ~ ~ | ~ |
gitsource 0.92 0.55 0.55 | 0.55 |
+------+
48x-HASWELL-NUMA (comparison ratio; lower is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
dbench4 ~ ~ ~ | ~ | ~
kernbench 0.94 0.90 0.89 | 0.90 | 0.90
gitsource 0.97 0.69 0.69 | 0.69 | 0.69
+------+
dbench is not very remarkable here, unless we notice how poorly active
intel_pstate is performing on 80x-BROADWELL-NUMA: 23% regression versus
non-invariant schedutil. We repeated that run getting consistent results. Out
of scope for the patch at hand, but deserving future investigation. Other than
that, we previously ran this campaign with Linux v5.0 and saw the patch doing
better on dbench a the time. We haven't checked closely and can only speculate
at this point.
On the NUMA boxes kernbench gets 10-15% improvements on average; we'll see in
the detailed tables that the gains concentrate on low process counts (lightly
loaded machines).
The test we call "gitsource" (running the git unit test suite, a long-running
single-threaded shell script) appears rather spectacular in this table (gains
of 30-50% depending on the machine). It is to be noted, however, that
gitsource has no adjustable parameters (such as the number of jobs in
kernbench, which we average over in order to get a single-number summary
score) and is exactly the kind of low-parallelism workload that benefits the
most from this patch. When looking at the detailed tables of kernbench or
tbench4, at low process or client counts one can see similar numbers.
5.3.3 SELECTION OF DETAILED RESULTS
-----------------------------------
Machine : 48x-HASWELL-NUMA
Benchmark : tbench4 (i.e. dbench4 over the network, actually loopback)
Varying parameter : number of clients
Unit : MB/sec (higher is better)
5.2.0 vanilla (BASELINE) 5.2.0 intel_pstate 5.2.0 1C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Hmean 1 126.73 +- 0.31% ( ) 315.91 +- 0.66% ( 149.28%) 125.03 +- 0.76% ( -1.34%)
Hmean 2 258.04 +- 0.62% ( ) 614.16 +- 0.51% ( 138.01%) 269.58 +- 1.45% ( 4.47%)
Hmean 4 514.30 +- 0.67% ( ) 1146.58 +- 0.54% ( 122.94%) 533.84 +- 1.99% ( 3.80%)
Hmean 8 1111.38 +- 2.52% ( ) 2159.78 +- 0.38% ( 94.33%) 1359.92 +- 1.56% ( 22.36%)
Hmean 16 2286.47 +- 1.36% ( ) 3338.29 +- 0.21% ( 46.00%) 2720.20 +- 0.52% ( 18.97%)
Hmean 32 4704.84 +- 0.35% ( ) 4759.03 +- 0.43% ( 1.15%) 4774.48 +- 0.30% ( 1.48%)
Hmean 64 7578.04 +- 0.27% ( ) 7533.70 +- 0.43% ( -0.59%) 7462.17 +- 0.65% ( -1.53%)
Hmean 128 6998.52 +- 0.16% ( ) 6987.59 +- 0.12% ( -0.16%) 6909.17 +- 0.14% ( -1.28%)
Hmean 192 6901.35 +- 0.25% ( ) 6913.16 +- 0.10% ( 0.17%) 6855.47 +- 0.21% ( -0.66%)
5.2.0 3C-turbo 5.2.0 4C-turbo 5.2.0 12C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Hmean 1 128.43 +- 0.28% ( 1.34%) 130.64 +- 3.81% ( 3.09%) 153.71 +- 5.89% ( 21.30%)
Hmean 2 311.70 +- 6.15% ( 20.79%) 281.66 +- 3.40% ( 9.15%) 305.08 +- 5.70% ( 18.23%)
Hmean 4 641.98 +- 2.32% ( 24.83%) 623.88 +- 5.28% ( 21.31%) 906.84 +- 4.65% ( 76.32%)
Hmean 8 1633.31 +- 1.56% ( 46.96%) 1714.16 +- 0.93% ( 54.24%) 2095.74 +- 0.47% ( 88.57%)
Hmean 16 3047.24 +- 0.42% ( 33.27%) 3155.02 +- 0.30% ( 37.99%) 3634.58 +- 0.15% ( 58.96%)
Hmean 32 4734.31 +- 0.60% ( 0.63%) 4804.38 +- 0.23% ( 2.12%) 4674.62 +- 0.27% ( -0.64%)
Hmean 64 7699.74 +- 0.35% ( 1.61%) 7499.72 +- 0.34% ( -1.03%) 7659.03 +- 0.25% ( 1.07%)
Hmean 128 6935.18 +- 0.15% ( -0.91%) 6942.54 +- 0.10% ( -0.80%) 7004.85 +- 0.12% ( 0.09%)
Hmean 192 6901.62 +- 0.12% ( 0.00%) 6856.93 +- 0.10% ( -0.64%) 6978.74 +- 0.10% ( 1.12%)
This is one of the cases where the patch still can't surpass active
intel_pstate, not even when freq_max is as low as 12C-turbo. Otherwise, gains are
visible up to 16 clients and the saturated scenario is the same as baseline.
The scores in the summary table from the previous sections are ratios of
geometric means of the results over different clients, as seen in this table.
Machine : 80x-BROADWELL-NUMA
Benchmark : kernbench (kernel compilation)
Varying parameter : number of jobs
Unit : seconds (lower is better)
5.2.0 vanilla (BASELINE) 5.2.0 intel_pstate 5.2.0 1C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 2 379.68 +- 0.06% ( ) 330.20 +- 0.43% ( 13.03%) 285.93 +- 0.07% ( 24.69%)
Amean 4 200.15 +- 0.24% ( ) 175.89 +- 0.22% ( 12.12%) 153.78 +- 0.25% ( 23.17%)
Amean 8 106.20 +- 0.31% ( ) 95.54 +- 0.23% ( 10.03%) 86.74 +- 0.10% ( 18.32%)
Amean 16 56.96 +- 1.31% ( ) 53.25 +- 1.22% ( 6.50%) 48.34 +- 1.73% ( 15.13%)
Amean 32 34.80 +- 2.46% ( ) 33.81 +- 0.77% ( 2.83%) 30.28 +- 1.59% ( 12.99%)
Amean 64 26.11 +- 1.63% ( ) 25.04 +- 1.07% ( 4.10%) 22.41 +- 2.37% ( 14.16%)
Amean 128 24.80 +- 1.36% ( ) 23.57 +- 1.23% ( 4.93%) 21.44 +- 1.37% ( 13.55%)
Amean 160 24.85 +- 0.56% ( ) 23.85 +- 1.17% ( 4.06%) 21.25 +- 1.12% ( 14.49%)
5.2.0 3C-turbo 5.2.0 4C-turbo 5.2.0 8C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 2 284.08 +- 0.13% ( 25.18%) 283.96 +- 0.51% ( 25.21%) 285.05 +- 0.21% ( 24.92%)
Amean 4 153.18 +- 0.22% ( 23.47%) 154.70 +- 1.64% ( 22.71%) 153.64 +- 0.30% ( 23.24%)
Amean 8 87.06 +- 0.28% ( 18.02%) 86.77 +- 0.46% ( 18.29%) 86.78 +- 0.22% ( 18.28%)
Amean 16 48.03 +- 0.93% ( 15.68%) 47.75 +- 1.99% ( 16.17%) 47.52 +- 1.61% ( 16.57%)
Amean 32 30.23 +- 1.20% ( 13.14%) 30.08 +- 1.67% ( 13.57%) 30.07 +- 1.67% ( 13.60%)
Amean 64 22.59 +- 2.02% ( 13.50%) 22.63 +- 0.81% ( 13.32%) 22.42 +- 0.76% ( 14.12%)
Amean 128 21.37 +- 0.67% ( 13.82%) 21.31 +- 1.15% ( 14.07%) 21.17 +- 1.93% ( 14.63%)
Amean 160 21.68 +- 0.57% ( 12.76%) 21.18 +- 1.74% ( 14.77%) 21.22 +- 1.00% ( 14.61%)
The patch outperform active intel_pstate (and baseline) by a considerable
margin; the summary table from the previous section says 4C turbo and active
intel_pstate are 0.83 and 0.93 against baseline respectively, so 4C turbo is
0.83/0.93=0.89 against intel_pstate (~10% better on average). There is no
noticeable difference with regard to the value of freq_max.
Machine : 8x-SKYLAKE-UMA
Benchmark : gitsource (time to run the git unit test suite)
Varying parameter : none
Unit : seconds (lower is better)
5.2.0 vanilla 5.2.0 intel_pstate/hwp 5.2.0 1C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 858.85 +- 1.16% ( ) 791.94 +- 0.21% ( 7.79%) 474.95 ( 44.70%)
5.2.0 3C-turbo 5.2.0 4C-turbo
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
Amean 475.26 +- 0.20% ( 44.66%) 474.34 +- 0.13% ( 44.77%)
In this test, which is of interest as representing shell-intensive
(i.e. fork-intensive) serialized workloads, invariant schedutil outperforms
intel_pstate/powersave by a whopping 40% margin.
5.3.4 POWER CONSUMPTION, PERFORMANCE-PER-WATT
---------------------------------------------
The following table shows average power consumption in watt for each
benchmark. Data comes from turbostat (package average), which in turn is read
from the RAPL interface on CPUs. We know the patch affects CPU frequencies so
it's reasonable to ignore other power consumers (such as memory or I/O). Also,
we don't have a power meter available in the lab so RAPL is the best we have.
turbostat sampled average power every 10 seconds for the entire duration of
each benchmark. We took all those values and averaged them (i.e. with don't
have detail on a per-parameter granularity, only on whole benchmarks).
80x-BROADWELL-NUMA (power consumption, watts)
+--------+
BASELINE I_PSTATE 1C 3C | 4C | 8C
pgbench-ro 130.01 142.77 131.11 132.45 | 134.65 | 136.84
pgbench-rw 68.30 60.83 71.45 71.70 | 71.65 | 72.54
dbench4 90.25 59.06 101.43 99.89 | 101.10 | 102.94
netperf-udp 65.70 69.81 66.02 68.03 | 68.27 | 68.95
netperf-tcp 88.08 87.96 88.97 88.89 | 88.85 | 88.20
tbench4 142.32 176.73 153.02 163.91 | 165.58 | 176.07
kernbench 92.94 101.95 114.91 115.47 | 115.52 | 115.10
gitsource 40.92 41.87 75.14 75.20 | 75.40 | 75.70
+--------+
8x-SKYLAKE-UMA (power consumption, watts)
+--------+
BASELINE I_PSTATE/HWP 1C 3C | 4C |
pgbench-ro 46.49 46.68 46.56 46.59 | 46.52 |
pgbench-rw 29.34 31.38 30.98 31.00 | 31.00 |
dbench4 27.28 27.37 27.49 27.41 | 27.38 |
netperf-udp 22.33 22.41 22.36 22.35 | 22.36 |
netperf-tcp 27.29 27.29 27.30 27.31 | 27.33 |
tbench4 41.13 45.61 43.10 43.33 | 43.56 |
kernbench 42.56 42.63 43.01 43.01 | 43.01 |
gitsource 13.32 13.69 17.33 17.30 | 17.35 |
+--------+
48x-HASWELL-NUMA (power consumption, watts)
+--------+
BASELINE I_PSTATE 1C 3C | 4C | 12C
pgbench-ro 128.84 136.04 129.87 132.43 | 132.30 | 134.86
pgbench-rw 37.68 37.92 37.17 37.74 | 37.73 | 37.31
dbench4 28.56 28.73 28.60 28.73 | 28.70 | 28.79
netperf-udp 56.70 60.44 56.79 57.42 | 57.54 | 57.52
netperf-tcp 75.49 75.27 75.87 76.02 | 76.01 | 75.95
tbench4 115.44 139.51 119.53 123.07 | 123.97 | 130.22
kernbench 83.23 91.55 95.58 95.69 | 95.72 | 96.04
gitsource 36.79 36.99 39.99 40.34 | 40.35 | 40.23
+--------+
A lower power consumption isn't necessarily better, it depends on what is done
with that energy. Here are tables with the ratio of performance-per-watt on
each machine and benchmark. Higher is always better; a tilde (~) means a
neutral ratio (i.e. 1.00).
80x-BROADWELL-NUMA (performance-per-watt ratios; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 8C
pgbench-ro 1.04 1.06 0.94 | 1.07 | 1.08
pgbench-rw 1.10 0.97 0.96 | 0.96 | 0.97
dbench4 1.24 0.94 0.95 | 0.94 | 0.92
netperf-udp ~ 1.02 1.02 | ~ | 1.02
netperf-tcp ~ 1.02 ~ | ~ | 1.02
tbench4 1.26 1.10 1.06 | 1.12 | 1.26
kernbench 0.98 0.97 0.97 | 0.97 | 0.98
gitsource ~ 1.11 1.11 | 1.11 | 1.13
+------+
8x-SKYLAKE-UMA (performance-per-watt ratios; higher is better)
+------+
I_PSTATE/HWP 1C 3C | 4C |
pgbench-ro ~ ~ ~ | ~ |
pgbench-rw 0.95 0.97 0.96 | 0.96 |
dbench4 ~ ~ ~ | ~ |
netperf-udp ~ ~ ~ | ~ |
netperf-tcp ~ ~ ~ | ~ |
tbench4 1.17 1.09 1.08 | 1.10 |
kernbench ~ ~ ~ | ~ |
gitsource 1.06 1.40 1.40 | 1.40 |
+------+
48x-HASWELL-NUMA (performance-per-watt ratios; higher is better)
+------+
I_PSTATE 1C 3C | 4C | 12C
pgbench-ro 1.09 ~ 1.09 | 1.03 | 1.11
pgbench-rw ~ 0.86 ~ | ~ | 0.86
dbench4 ~ 1.02 1.02 | 1.02 | ~
netperf-udp ~ 0.97 1.03 | 1.02 | ~
netperf-tcp 0.96 ~ ~ | ~ | ~
tbench4 1.24 ~ 1.06 | 1.05 | 1.11
kernbench 0.97 0.97 0.98 | 0.97 | 0.96
gitsource 1.03 1.33 1.32 | 1.32 | 1.33
+------+
These results are overall pleasing: in plenty of cases we observe
performance-per-watt improvements. The few regressions (read/write pgbench and
dbench on the Broadwell machine) are of small magnitude. kernbench loses a few
percentage points (it has a 10-15% performance improvement, but apparently the
increase in power consumption is larger than that). tbench4 and gitsource, which
benefit the most from the patch, keep a positive score in this table which is
a welcome surprise; that suggests that in those particular workloads the
non-invariant schedutil (and active intel_pstate, too) makes some rather
suboptimal frequency selections.
+-------------------------------------------------------------------------+
| 6. MICROARCH'ES ADDRESSED HERE
+-------------------------------------------------------------------------+
The patch addresses Xeon Core processors that use MSR_PLATFORM_INFO and
MSR_TURBO_RATIO_LIMIT to advertise their base frequency and turbo frequencies
respectively. This excludes the recent Xeon Scalable Performance processors
line (Xeon Gold, Platinum etc) whose MSRs have to be parsed differently.
Subsequent patches will address:
* Xeon Scalable Performance processors and Atom Goldmont/Goldmont Plus
* Xeon Phi (Knights Landing, Knights Mill)
* Atom Silvermont
+-------------------------------------------------------------------------+
| 7. REFERENCES
+-------------------------------------------------------------------------+
Tests have been run with the help of the MMTests performance testing
framework, see github.com/gormanm/mmtests. The configuration file names for
the benchmark used are:
db-pgbench-timed-ro-small-xfs
db-pgbench-timed-rw-small-xfs
io-dbench4-async-xfs
network-netperf-unbound
network-tbench
scheduler-unbound
workload-kerndevel-xfs
workload-shellscripts-xfs
hpc-nas-c-class-mpi-full-xfs
hpc-nas-c-class-omp-full
All those benchmarks are generally available on the web:
pgbench: https://www.postgresql.org/docs/10/pgbench.html
netperf: https://hewlettpackard.github.io/netperf/
dbench/tbench: https://dbench.samba.org/
gitsource: git unit test suite, github.com/git/git
NAS Parallel Benchmarks: https://www.nas.nasa.gov/publications/npb.html
hackbench: https://people.redhat.com/mingo/cfs-scheduler/tools/hackbench.c
Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Giovanni Gherdovich <ggherdovich@suse.cz>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Doug Smythies <dsmythies@telus.net>
Acked-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Link: https://lkml.kernel.org/r/20200122151617.531-2-ggherdovich@suse.cz
When a running task is moved on a throttled task group and there is no
other task enqueued on the CPU, the task can keep running using 100% CPU
whatever the allocated bandwidth for the group and although its cfs rq is
throttled. Furthermore, the group entity of the cfs_rq and its parents are
not enqueued but only set as curr on their respective cfs_rqs.
We have the following sequence:
sched_move_task
-dequeue_task: dequeue task and group_entities.
-put_prev_task: put task and group entities.
-sched_change_group: move task to new group.
-enqueue_task: enqueue only task but not group entities because cfs_rq is
throttled.
-set_next_task : set task and group_entities as current sched_entity of
their cfs_rq.
Another impact is that the root cfs_rq runnable_load_avg at root rq stays
null because the group_entities are not enqueued. This situation will stay
the same until an "external" event triggers a reschedule. Let trigger it
immediately instead.
Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Ben Segall <bsegall@google.com>
Link: https://lkml.kernel.org/r/1579011236-31256-1-git-send-email-vincent.guittot@linaro.org
On a machine, CPU 0 is used for housekeeping, the other 39 CPUs in the
same socket are in nohz_full mode. We can observe huge time burn in the
loop for seaching nearest busy housekeeper cpu by ftrace.
2) | get_nohz_timer_target() {
2) 0.240 us | housekeeping_test_cpu();
2) 0.458 us | housekeeping_test_cpu();
...
2) 0.292 us | housekeeping_test_cpu();
2) 0.240 us | housekeeping_test_cpu();
2) 0.227 us | housekeeping_any_cpu();
2) + 43.460 us | }
This patch optimizes the searching logic by finding a nearest housekeeper
CPU in the housekeeping cpumask, it can minimize the worst searching time
from ~44us to < 10us in my testing. In addition, the last iterated busy
housekeeper can become a random candidate while current CPU is a better
fallback if it is a housekeeper.
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Frederic Weisbecker <frederic@kernel.org>
Link: https://lkml.kernel.org/r/1578876627-11938-1-git-send-email-wanpengli@tencent.com
The check to ensure that the new written value into cpu.uclamp.{min,max}
is within range, [0:100], wasn't working because of the signed
comparison
7301 if (req.percent > UCLAMP_PERCENT_SCALE) {
7302 req.ret = -ERANGE;
7303 return req;
7304 }
# echo -1 > cpu.uclamp.min
# cat cpu.uclamp.min
42949671.96
Cast req.percent into u64 to force the comparison to be unsigned and
work as intended in capacity_from_percent().
# echo -1 > cpu.uclamp.min
sh: write error: Numerical result out of range
Fixes: 2480c09313 ("sched/uclamp: Extend CPU's cgroup controller")
Signed-off-by: Qais Yousef <qais.yousef@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/20200114210947.14083-1-qais.yousef@arm.com
The CPU load balancer balances between different domains to spread load
and strives to have equal balance everywhere. Communicating tasks can
migrate so they are topologically close to each other but these decisions
are independent. On a lightly loaded NUMA machine, two communicating tasks
pulled together at wakeup time can be pushed apart by the load balancer.
In isolation, the load balancer decision is fine but it ignores the tasks
data locality and the wakeup/LB paths continually conflict. NUMA balancing
is also a factor but it also simply conflicts with the load balancer.
This patch allows a fixed degree of imbalance of two tasks to exist
between NUMA domains regardless of utilisation levels. In many cases,
this prevents communicating tasks being pulled apart. It was evaluated
whether the imbalance should be scaled to the domain size. However, no
additional benefit was measured across a range of workloads and machines
and scaling adds the risk that lower domains have to be rebalanced. While
this could change again in the future, such a change should specify the
use case and benefit.
The most obvious impact is on netperf TCP_STREAM -- two simple
communicating tasks with some softirq offload depending on the
transmission rate.
2-socket Haswell machine 48 core, HT enabled
netperf-tcp -- mmtests config config-network-netperf-unbound
baseline lbnuma-v3
Hmean 64 568.73 ( 0.00%) 577.56 * 1.55%*
Hmean 128 1089.98 ( 0.00%) 1128.06 * 3.49%*
Hmean 256 2061.72 ( 0.00%) 2104.39 * 2.07%*
Hmean 1024 7254.27 ( 0.00%) 7557.52 * 4.18%*
Hmean 2048 11729.20 ( 0.00%) 13350.67 * 13.82%*
Hmean 3312 15309.08 ( 0.00%) 18058.95 * 17.96%*
Hmean 4096 17338.75 ( 0.00%) 20483.66 * 18.14%*
Hmean 8192 25047.12 ( 0.00%) 27806.84 * 11.02%*
Hmean 16384 27359.55 ( 0.00%) 33071.88 * 20.88%*
Stddev 64 2.16 ( 0.00%) 2.02 ( 6.53%)
Stddev 128 2.31 ( 0.00%) 2.19 ( 5.05%)
Stddev 256 11.88 ( 0.00%) 3.22 ( 72.88%)
Stddev 1024 23.68 ( 0.00%) 7.24 ( 69.43%)
Stddev 2048 79.46 ( 0.00%) 71.49 ( 10.03%)
Stddev 3312 26.71 ( 0.00%) 57.80 (-116.41%)
Stddev 4096 185.57 ( 0.00%) 96.15 ( 48.19%)
Stddev 8192 245.80 ( 0.00%) 100.73 ( 59.02%)
Stddev 16384 207.31 ( 0.00%) 141.65 ( 31.67%)
In this case, there was a sizable improvement to performance and
a general reduction in variance. However, this is not univeral.
For most machines, the impact was roughly a 3% performance gain.
Ops NUMA base-page range updates 19796.00 292.00
Ops NUMA PTE updates 19796.00 292.00
Ops NUMA PMD updates 0.00 0.00
Ops NUMA hint faults 16113.00 143.00
Ops NUMA hint local faults % 8407.00 142.00
Ops NUMA hint local percent 52.18 99.30
Ops NUMA pages migrated 4244.00 1.00
Without the patch, only 52.18% of sampled accesses are local. In an
earlier changelog, 100% of sampled accesses are local and indeed on
most machines, this was still the case. In this specific case, the
local sampled rates was 99.3% but note the "base-page range updates"
and "PTE updates". The activity with the patch is negligible as were
the number of faults. The small number of pages migrated were related to
shared libraries. A 2-socket Broadwell showed better results on average
but are not presented for brevity as the performance was similar except
it showed 100% of the sampled NUMA hints were local. The patch holds up
for a 4-socket Haswell, an AMD EPYC and AMD Epyc 2 machine.
For dbench, the impact depends on the filesystem used and the number of
clients. On XFS, there is little difference as the clients typically
communicate with workqueues which have a separate class of scheduler
problem at the moment. For ext4, performance is generally better,
particularly for small numbers of clients as NUMA balancing activity is
negligible with the patch applied.
A more interesting example is the Facebook schbench which uses a
number of messaging threads to communicate with worker threads. In this
configuration, one messaging thread is used per NUMA node and the number of
worker threads is varied. The 50, 75, 90, 95, 99, 99.5 and 99.9 percentiles
for response latency is then reported.
Lat 50.00th-qrtle-1 44.00 ( 0.00%) 37.00 ( 15.91%)
Lat 75.00th-qrtle-1 53.00 ( 0.00%) 41.00 ( 22.64%)
Lat 90.00th-qrtle-1 57.00 ( 0.00%) 42.00 ( 26.32%)
Lat 95.00th-qrtle-1 63.00 ( 0.00%) 43.00 ( 31.75%)
Lat 99.00th-qrtle-1 76.00 ( 0.00%) 51.00 ( 32.89%)
Lat 99.50th-qrtle-1 89.00 ( 0.00%) 52.00 ( 41.57%)
Lat 99.90th-qrtle-1 98.00 ( 0.00%) 55.00 ( 43.88%)
Lat 50.00th-qrtle-2 42.00 ( 0.00%) 42.00 ( 0.00%)
Lat 75.00th-qrtle-2 48.00 ( 0.00%) 47.00 ( 2.08%)
Lat 90.00th-qrtle-2 53.00 ( 0.00%) 52.00 ( 1.89%)
Lat 95.00th-qrtle-2 55.00 ( 0.00%) 53.00 ( 3.64%)
Lat 99.00th-qrtle-2 62.00 ( 0.00%) 60.00 ( 3.23%)
Lat 99.50th-qrtle-2 63.00 ( 0.00%) 63.00 ( 0.00%)
Lat 99.90th-qrtle-2 68.00 ( 0.00%) 66.00 ( 2.94%
For higher worker threads, the differences become negligible but it's
interesting to note the difference in wakeup latency at low utilisation
and mpstat confirms that activity was almost all on one node until
the number of worker threads increase.
Hackbench generally showed neutral results across a range of machines.
This is different to earlier versions of the patch which allowed imbalances
for higher degrees of utilisation. perf bench pipe showed negligible
differences in overall performance as the differences are very close to
the noise.
An earlier prototype of the patch showed major regressions for NAS C-class
when running with only half of the available CPUs -- 20-30% performance
hits were measured at the time. With this version of the patch, the impact
is negligible with small gains/losses within the noise measured. This is
because the number of threads far exceeds the small imbalance the aptch
cares about. Similarly, there were report of regressions for the autonuma
benchmark against earlier versions but again, normal load balancing now
applies for that workload.
In general, the patch simply seeks to avoid unnecessary cross-node
migrations in the basic case where imbalances are very small. For low
utilisation communicating workloads, this patch generally behaves better
with less NUMA balancing activity. For high utilisation, there is no
change in behaviour.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Valentin Schneider <valentin.schneider@arm.com>
Reviewed-by: Vincent Guittot <vincent.guittot@linaro.org>
Reviewed-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Acked-by: Phil Auld <pauld@redhat.com>
Tested-by: Phil Auld <pauld@redhat.com>
Link: https://lkml.kernel.org/r/20200114101319.GO3466@techsingularity.net
The way loadavg is tracked during nohz only pays attention to the load
upon entering nohz. This can be particularly noticeable if full nohz is
entered while non-idle, and then the cpu goes idle and stays that way for
a long time.
Use the remote tick to ensure that full nohz cpus report their deltas
within a reasonable time.
[ swood: Added changelog and removed recheck of stopped tick. ]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Scott Wood <swood@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/1578736419-14628-3-git-send-email-swood@redhat.com
This will be used in the next patch to get a loadavg update from
nohz cpus. The delta check is skipped because idle_sched_class
doesn't update se.exec_start.
Signed-off-by: Scott Wood <swood@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Link: https://lkml.kernel.org/r/1578736419-14628-2-git-send-email-swood@redhat.com
Pull scheduler updates from Ingo Molnar:
"These were the main changes in this cycle:
- More -rt motivated separation of CONFIG_PREEMPT and
CONFIG_PREEMPTION.
- Add more low level scheduling topology sanity checks and warnings
to filter out nonsensical topologies that break scheduling.
- Extend uclamp constraints to influence wakeup CPU placement
- Make the RT scheduler more aware of asymmetric topologies and CPU
capacities, via uclamp metrics, if CONFIG_UCLAMP_TASK=y
- Make idle CPU selection more consistent
- Various fixes, smaller cleanups, updates and enhancements - please
see the git log for details"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (58 commits)
sched/fair: Define sched_idle_cpu() only for SMP configurations
sched/topology: Assert non-NUMA topology masks don't (partially) overlap
idle: fix spelling mistake "iterrupts" -> "interrupts"
sched/fair: Remove redundant call to cpufreq_update_util()
sched/psi: create /proc/pressure and /proc/pressure/{io|memory|cpu} only when psi enabled
sched/fair: Fix sgc->{min,max}_capacity calculation for SD_OVERLAP
sched/fair: calculate delta runnable load only when it's needed
sched/cputime: move rq parameter in irqtime_account_process_tick
stop_machine: Make stop_cpus() static
sched/debug: Reset watchdog on all CPUs while processing sysrq-t
sched/core: Fix size of rq::uclamp initialization
sched/uclamp: Fix a bug in propagating uclamp value in new cgroups
sched/fair: Load balance aggressively for SCHED_IDLE CPUs
sched/fair : Improve update_sd_pick_busiest for spare capacity case
watchdog: Remove soft_lockup_hrtimer_cnt and related code
sched/rt: Make RT capacity-aware
sched/fair: Make EAS wakeup placement consider uclamp restrictions
sched/fair: Make task_fits_capacity() consider uclamp restrictions
sched/uclamp: Rename uclamp_util_with() into uclamp_rq_util_with()
sched/uclamp: Make uclamp util helpers use and return UL values
...
Peter Zijlstra