sched/debug: Change SCHED_WARN_ON() to WARN_ON_ONCE()

The scheduler has this special SCHED_WARN() facility that
depends on CONFIG_SCHED_DEBUG.

Since CONFIG_SCHED_DEBUG is getting removed, convert
S

sched/debug: Change SCHED_WARN_ON() to WARN_ON_ONCE()

The scheduler has this special SCHED_WARN() facility that
depends on CONFIG_SCHED_DEBUG.

Since CONFIG_SCHED_DEBUG is getting removed, convert
SCHED_WARN() to WARN_ON_ONCE().

Note that the warning output isn't 100% equivalent:

#define SCHED_WARN_ON(x) WARN_ONCE(x, #x)

Because SCHED_WARN_ON() would output the 'x' condition
as well, while WARN_ONCE() will only show a backtrace.

Hopefully these are rare enough to not really matter.

If it does, we should probably introduce a new WARN_ON()
variant that outputs the condition in stringified form,
or improve WARN_ON() itself.

Signed-off-by: Ingo Molnar <[email protected]>
Tested-by: Shrikanth Hegde <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Juri Lelli <[email protected]>
Cc: Vincent Guittot <[email protected]>
Cc: Dietmar Eggemann <[email protected]>
Cc: Steven Rostedt <[email protected]>
Cc: Ben Segall <[email protected]>
Cc: Mel Gorman <[email protected]>
Cc: Valentin Schneider <[email protected]>
Cc: Linus Torvalds <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

psi: Fix race when task wakes up before psi_sched_switch() adjusts flags

When running hackbench in a cgroup with bandwidth throttling enabled,
following PSI splat was observed:

psi: inconsisten

psi: Fix race when task wakes up before psi_sched_switch() adjusts flags

When running hackbench in a cgroup with bandwidth throttling enabled,
following PSI splat was observed:

psi: inconsistent task state! task=1831:hackbench cpu=8 psi_flags=14 clear=0 set=4

When investigating the series of events leading up to the splat,
following sequence was observed:

[008] d..2.: sched_switch: ... ==> next_comm=hackbench next_pid=1831 next_prio=120
...
[008] dN.2.: dequeue_entity(task delayed): task=hackbench pid=1831 cfs_rq->throttled=0
[008] dN.2.: pick_task_fair: check_cfs_rq_runtime() throttled cfs_rq on CPU8
# CPU8 goes into newidle balance and releases the rq lock
...
# CPU15 on same LLC Domain is trying to wakeup hackbench(pid=1831)
[015] d..4.: psi_flags_change: psi: task state: task=1831:hackbench cpu=8 psi_flags=14 clear=0 set=4 final=14 # Splat (cfs_rq->throttled=1)
[015] d..4.: sched_wakeup: comm=hackbench pid=1831 prio=120 target_cpu=008 # Task has woken on a throttled hierarchy
[008] d..2.: sched_switch: prev_comm=hackbench prev_pid=1831 prev_prio=120 prev_state=S ==> ...

psi_dequeue() relies on psi_sched_switch() to set the correct PSI flags
for the blocked entity, however, with the introduction of DELAY_DEQUEUE,
the block task can wakeup when newidle balance drops the runqueue lock
during __schedule().

If a task wakes before psi_sched_switch() adjusts the PSI flags, skip
any modifications in psi_enqueue() which would still see the flags of a
running task and not a blocked one. Instead, rely on psi_sched_switch()
to do the right thing.

Since the status returned by try_to_block_task() may no longer be true
by the time schedule reaches psi_sched_switch(), check if the task is
blocked or not using a combination of task_on_rq_queued() and
p->se.sched_delayed checks.

[ prateek: Commit message, testing, early bailout in psi_enqueue() ]

Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue") # 1a6151017ee5
Signed-off-by: Chengming Zhou <[email protected]>
Signed-off-by: K Prateek Nayak <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Chengming Zhou <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

delayacct: add delay min to record delay peak

Delay accounting can now calculate the average delay of processes, detect
the overall system load, and also record the 'delay max' to identify
potential

delayacct: add delay min to record delay peak

Delay accounting can now calculate the average delay of processes, detect
the overall system load, and also record the 'delay max' to identify
potential abnormal delays. However, 'delay min' can help us identify
another useful delay peak. By comparing the difference between 'delay
max' and 'delay min', we can understand the optimization space for
latency, providing a reference for the optimization of latency
performance.

Use case
=========
bash-4.4# ./getdelays -d -t 242
print delayacct stats ON
TGID 242
CPU count real total virtual total delay total delay average delay max delay min
39 156000000 156576579 2111069 0.054ms 0.212296ms 0.031307ms
IO count delay total delay average delay max delay min
0 0 0.000ms 0.000000ms 0.000000ms
SWAP count delay total delay average delay max delay min
0 0 0.000ms 0.000000ms 0.000000ms
RECLAIM count delay total delay average delay max delay min
0 0 0.000ms 0.000000ms 0.000000ms
THRASHING count delay total delay average delay max delay min
0 0 0.000ms 0.000000ms 0.000000ms
COMPACT count delay total delay average delay max delay min
0 0 0.000ms 0.000000ms 0.000000ms
WPCOPY count delay total delay average delay max delay min
156 11215873 0.072ms 0.207403ms 0.033913ms
IRQ count delay total delay average delay max delay min
0 0 0.000ms 0.000000ms 0.000000ms

Link: https://lkml.kernel.org/r/[email protected]
Co-developed-by: Wang Yong <[email protected]>
Signed-off-by: Wang Yong <[email protected]>
Co-developed-by: xu xin <[email protected]>
Signed-off-by: xu xin <[email protected]>
Signed-off-by: Wang Yaxin <[email protected]>
Co-developed-by: Kun Jiang <[email protected]>
Signed-off-by: Kun Jiang <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Fan Yu <[email protected]>
Cc: Peilin He <[email protected]>
Cc: tuqiang <[email protected]>
Cc: ye xingchen <[email protected]>
Cc: Yunkai Zhang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

show more ...

delayacct: add delay max to record delay peak

Introduce the use cases of delay max, which can help quickly detect
potential abnormal delays in the system and record the types and specific
details of

delayacct: add delay max to record delay peak

Introduce the use cases of delay max, which can help quickly detect
potential abnormal delays in the system and record the types and specific
details of delay spikes.

Problem
========
Delay accounting can track the average delay of processes to show
system workload. However, when a process experiences a significant
delay, maybe a delay spike, which adversely affects performance,
getdelays can only display the average system delay over a period
of time. Yet, average delay is unhelpful for diagnosing delay peak.
It is not even possible to determine which type of delay has spiked,
as this information might be masked by the average delay.

Solution
=========
the 'delay max' can display delay peak since the system's startup,
which can record potential abnormal delays over time, including
the type of delay and the maximum delay. This is helpful for
quickly identifying crash caused by delay.

Use case
=========
bash# ./getdelays -d -p 244
print delayacct stats ON
PID 244

CPU count real total virtual total delay total delay average delay max
68 192000000 213676651 705643 0.010ms 0.306381ms
IO count delay total delay average delay max
0 0 0.000ms 0.000000ms
SWAP count delay total delay average delay max
0 0 0.000ms 0.000000ms
RECLAIM count delay total delay average delay max
0 0 0.000ms 0.000000ms
THRASHING count delay total delay average delay max
0 0 0.000ms 0.000000ms
COMPACT count delay total delay average delay max
0 0 0.000ms 0.000000ms
WPCOPY count delay total delay average delay max
235 15648284 0.067ms 0.263842ms
IRQ count delay total delay average delay max
0 0 0.000ms 0.000000ms

[[email protected]: update docs and fix some spelling errors]
Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Co-developed-by: Wang Yong <[email protected]>
Signed-off-by: Wang Yong <[email protected]>
Co-developed-by: xu xin <[email protected]>
Signed-off-by: xu xin <[email protected]>
Co-developed-by: Wang Yaxin <[email protected]>
Signed-off-by: Wang Yaxin <[email protected]>
Signed-off-by: Kun Jiang <[email protected]>
Cc: Balbir Singh <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Fan Yu <[email protected]>
Cc: Peilin He <[email protected]>
Cc: tuqiang <[email protected]>
Cc: Yang Yang <[email protected]>
Cc: ye xingchen <[email protected]>
Cc: Yunkai Zhang <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

show more ...

sched: psi: pass enqueue/dequeue flags to psi callbacks directly

What psi needs to do on each enqueue and dequeue has gotten more
subtle, and the generic sched code trying to distill this into a boo

sched: psi: pass enqueue/dequeue flags to psi callbacks directly

What psi needs to do on each enqueue and dequeue has gotten more
subtle, and the generic sched code trying to distill this into a bool
for the callbacks is awkward.

Pass the flags directly and let psi parse them. For that to work, the
#include "stats.h" (which has the psi callback implementations) needs
to be below the flag definitions in "sched.h". Move that section
further down, next to some of the other accounting stuff.

This also puts the ENQUEUE_SAVE/RESTORE branch behind the psi jump
label, slightly reducing overhead when PSI=y but runtime disabled.

Suggested-by: Peter Zijlstra <[email protected]>
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...

sched/psi: Fix mistaken CPU pressure indication after corrupted task state bug

Since sched_delayed tasks remain queued even after blocking, the load
balancer can migrate them between runqueues while

sched/psi: Fix mistaken CPU pressure indication after corrupted task state bug

Since sched_delayed tasks remain queued even after blocking, the load
balancer can migrate them between runqueues while PSI considers them
to be asleep. As a result, it misreads the migration requeue followed
by a wakeup as a double queue:

psi: inconsistent task state! task=... cpu=... psi_flags=4 clear=. set=4

First, call psi_enqueue() after p->sched_class->enqueue_task(). A
wakeup will clear p->se.sched_delayed while a migration will not, so
psi can use that flag to tell them apart.

Then teach psi to migrate any "sleep" state when delayed-dequeue tasks
are being migrated.

Delayed-dequeue tasks can be revived by ttwu_runnable(), which will
call down with a new ENQUEUE_DELAYED. Instead of further complicating
the wakeup conditional in enqueue_task(), identify migration contexts
instead and default to wakeup handling for all other cases.

It's not just the warning in dmesg, the task state corruption causes a
permanent CPU pressure indication, which messes with workload/machine
health monitoring.

Debugged-by-and-original-fix-by: K Prateek Nayak <[email protected]>
Fixes: 152e11f6df29 ("sched/fair: Implement delayed dequeue")
Closes: https://lore.kernel.org/lkml/[email protected]/
Closes: https://lore.kernel.org/all/[email protected]/
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Tested-by: K Prateek Nayak <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...

sched: Move psi_account_irqtime() out of update_rq_clock_task() hotpath

It was reported that in moving to 6.1, a larger then 10%
regression was seen in the performance of
clock_gettime(CLOCK_THREAD_

sched: Move psi_account_irqtime() out of update_rq_clock_task() hotpath

It was reported that in moving to 6.1, a larger then 10%
regression was seen in the performance of
clock_gettime(CLOCK_THREAD_CPUTIME_ID,...).

Using a simple reproducer, I found:
5.10:
100000000 calls in 24345994193 ns => 243.460 ns per call
100000000 calls in 24288172050 ns => 242.882 ns per call
100000000 calls in 24289135225 ns => 242.891 ns per call

6.1:
100000000 calls in 28248646742 ns => 282.486 ns per call
100000000 calls in 28227055067 ns => 282.271 ns per call
100000000 calls in 28177471287 ns => 281.775 ns per call

The cause of this was finally narrowed down to the addition of
psi_account_irqtime() in update_rq_clock_task(), in commit
52b1364ba0b1 ("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ
pressure").

In my initial attempt to resolve this, I leaned towards moving
all accounting work out of the clock_gettime() call path, but it
wasn't very pretty, so it will have to wait for a later deeper
rework. Instead, Peter shared this approach:

Rework psi_account_irqtime() to use its own psi_irq_time base
for accounting, and move it out of the hotpath, calling it
instead from sched_tick() and __schedule().

In testing this, we found the importance of ensuring
psi_account_irqtime() is run under the rq_lock, which Johannes
Weiner helpfully explained, so also add some lockdep annotations
to make that requirement clear.

With this change the performance is back in-line with 5.10:
6.1+fix:
100000000 calls in 24297324597 ns => 242.973 ns per call
100000000 calls in 24318869234 ns => 243.189 ns per call
100000000 calls in 24291564588 ns => 242.916 ns per call

Reported-by: Jimmy Shiu <[email protected]>
Originally-by: Peter Zijlstra <[email protected]>
Signed-off-by: John Stultz <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Chengming Zhou <[email protected]>
Reviewed-by: Qais Yousef <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched: Fix spelling in comments

Do a spell-checking pass.

Signed-off-by: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Signed-off-by: Ing

sched: Fix spelling in comments

Do a spell-checking pass.

Signed-off-by: Ingo Molnar <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: [email protected]
Signed-off-by: Ingo Molnar <[email protected]>

show more ...

sched/psi: Use task->psi_flags to clear in CPU migration

The commit d583d360a620 ("psi: Fix psi state corruption when schedule()
races with cgroup move") fixed a race problem by making cgroup_move_t

sched/psi: Use task->psi_flags to clear in CPU migration

The commit d583d360a620 ("psi: Fix psi state corruption when schedule()
races with cgroup move") fixed a race problem by making cgroup_move_task()
use task->psi_flags instead of looking at the scheduler state.

We can extend task->psi_flags usage to CPU migration, which should be
a minor optimization for performance and code simplicity.

Signed-off-by: Chengming Zhou <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure

Now PSI already tracked workload pressure stall information for
CPU, memory and IO. Apart from these, IRQ/SOFTIRQ could have
obvious impact on so

sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure

Now PSI already tracked workload pressure stall information for
CPU, memory and IO. Apart from these, IRQ/SOFTIRQ could have
obvious impact on some workload productivity, such as web service
workload.

When CONFIG_IRQ_TIME_ACCOUNTING, we can get IRQ/SOFTIRQ delta time
from update_rq_clock_task(), in which we can record that delta
to CPU curr task's cgroups as PSI_IRQ_FULL status.

Note we don't use PSI_IRQ_SOME since IRQ/SOFTIRQ always happen in
the current task on the CPU, make nothing productive could run
even if it were runnable, so we only use PSI_IRQ_FULL.

Signed-off-by: Chengming Zhou <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched/psi: Move private helpers to sched/stats.h

This patch move psi_task_change/psi_task_switch declarations out of
PSI public header, since they are only needed for implementing the
PSI stats trac

sched/psi: Move private helpers to sched/stats.h

This patch move psi_task_change/psi_task_switch declarations out of
PSI public header, since they are only needed for implementing the
PSI stats tracking in sched/stats.h

psi_task_switch is obvious, psi_task_change can't be public helper
since it doesn't check psi_disabled static key. And there is no
any user now, so put it in sched/stats.h too.

Signed-off-by: Chengming Zhou <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies

Remove all headers, except the ones required to make this header
build standalone.

Also include stats.h in sched.h

sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies

Remove all headers, except the ones required to make this header
build standalone.

Also include stats.h in sched.h explicitly - dependencies already
require this.

Summary of the build speedup gained through the last ~15 scheduler build &
header dependency patches:

Cumulative scheduler (kernel/sched/) build time speedup on a
Linux distribution's config, which enables all scheduler features,
compared to the vanilla kernel:

_____________________________________________________________________________
|
| Vanilla kernel (v5.13-rc7):
|_____________________________________________________________________________
|
| Performance counter stats for 'make -j96 kernel/sched/' (3 runs):
|
| 126,975,564,374 instructions # 1.45 insn per cycle ( +- 0.00% )
| 87,637,847,671 cycles # 3.959 GHz ( +- 0.30% )
| 22,136.96 msec cpu-clock # 7.499 CPUs utilized ( +- 0.29% )
|
| 2.9520 +- 0.0169 seconds time elapsed ( +- 0.57% )
|_____________________________________________________________________________
|
| Patched kernel:
|_____________________________________________________________________________
|
| Performance counter stats for 'make -j96 kernel/sched/' (3 runs):
|
| 50,420,496,914 instructions # 1.47 insn per cycle ( +- 0.00% )
| 34,234,322,038 cycles # 3.946 GHz ( +- 0.31% )
| 8,675.81 msec cpu-clock # 3.053 CPUs utilized ( +- 0.45% )
|
| 2.8420 +- 0.0181 seconds time elapsed ( +- 0.64% )
|_____________________________________________________________________________

Summary:

- CPU time used to build the scheduler dropped by -60.9%, a reduction
from 22.1 clock-seconds to 8.7 clock-seconds.

- Wall-clock time to build the scheduler dropped by -3.9%, a reduction
from 2.95 seconds to 2.84 seconds.

Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Peter Zijlstra <[email protected]>

show more ...

sched/headers: Standardize kernel/sched/sched.h header dependencies

kernel/sched/sched.h is a weird mix of ad-hoc headers included
in the middle of the header.

Two of them rely on being included in

sched/headers: Standardize kernel/sched/sched.h header dependencies

kernel/sched/sched.h is a weird mix of ad-hoc headers included
in the middle of the header.

Two of them rely on being included in the middle of kernel/sched/sched.h,
due to definitions they require:

- "stat.h" needs the rq definitions.
- "autogroup.h" needs the task_group definition.

Move the inclusion of these two files out of kernel/sched/sched.h, and
include them in all files that require them.

Move of the rest of the header dependencies to the top of the
kernel/sched/sched.h file.

Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Peter Zijlstra <[email protected]>

show more ...

sched/headers: Add header guard to kernel/sched/stats.h and kernel/sched/autogroup.h

Protect against multiple inclusion.

Also include "sched.h" in "stat.h", as it relies on it.

Signed-off-by: Ingo

sched/headers: Add header guard to kernel/sched/stats.h and kernel/sched/autogroup.h

Protect against multiple inclusion.

Also include "sched.h" in "stat.h", as it relies on it.

Signed-off-by: Ingo Molnar <[email protected]>
Reviewed-by: Peter Zijlstra <[email protected]>

show more ...

psi: Fix PSI_MEM_FULL state when tasks are in memstall and doing reclaim

We've noticed cases where tasks in a cgroup are stalled on memory but
there is little memory FULL pressure since tasks stay o

psi: Fix PSI_MEM_FULL state when tasks are in memstall and doing reclaim

We've noticed cases where tasks in a cgroup are stalled on memory but
there is little memory FULL pressure since tasks stay on the runqueue
in reclaim.

A simple example involves a single threaded program that keeps leaking
and touching large amounts of memory. It runs in a cgroup with swap
enabled, memory.high set at 10M and cpu.max ratio set at 5%. Though
there is significant CPU pressure and memory SOME, there is barely any
memory FULL since the task enters reclaim and stays on the runqueue.
However, this memory-bound task is effectively stalled on memory and
we expect memory FULL to match memory SOME in this scenario.

The code is confused about memstall && running, thinking there is a
stalled task and a productive task when there's only one task: a
reclaimer that's counted as both. To fix this, we redefine the
condition for PSI_MEM_FULL to check that all running tasks are in an
active memstall instead of checking that there are no running tasks.

case PSI_MEM_FULL:
- return unlikely(tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]);
+ return unlikely(tasks[NR_MEMSTALL] &&
+ tasks[NR_RUNNING] == tasks[NR_MEMSTALL_RUNNING]);

This will capture reclaimers. It will also capture tasks that called
psi_memstall_enter() and are about to sleep, but this should be
negligible noise.

Signed-off-by: Brian Chen <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched: Make schedstats helpers independent of fair sched class

The original prototype of the schedstats helpers are

update_stats_wait_*(struct cfs_rq *cfs_rq, struct sched_entity *se)

The cfs_rq

sched: Make schedstats helpers independent of fair sched class

The original prototype of the schedstats helpers are

update_stats_wait_*(struct cfs_rq *cfs_rq, struct sched_entity *se)

The cfs_rq in these helpers is used to get the rq_clock, and the se is
used to get the struct sched_statistics and the struct task_struct. In
order to make these helpers available by all sched classes, we can pass
the rq, sched_statistics and task_struct directly.

Then the new helpers are

update_stats_wait_*(struct rq *rq, struct task_struct *p,
struct sched_statistics *stats)

which are independent of fair sched class.

To avoid vmlinux growing too large or introducing ovehead when
!schedstat_enabled(), some new helpers after schedstat_enabled() are also
introduced, Suggested by Mel. These helpers are in sched/stats.c,

__update_stats_wait_*(struct rq *rq, struct task_struct *p,
struct sched_statistics *stats)

The size of vmlinux as follows,
Before After
Size of vmlinux 826308552 826304640
The size is a litte smaller as some functions are not inlined again after
the change.

I also compared the sched performance with 'perf bench sched pipe',
suggested by Mel. The result as followsi (in usecs/op),
Before After
kernel.sched_schedstats=0 5.2~5.4 5.2~5.4
kernel.sched_schedstats=1 5.3~5.5 5.3~5.5

[These data is a little difference with the prev version, that is
because my old test machine is destroyed so I have to use a new
different test machine.]
Almost no difference.

No functional change.

[[email protected]: reported build failure in prev version]

Signed-off-by: Yafang Shao <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched: Make struct sched_statistics independent of fair sched class

If we want to use the schedstats facility to trace other sched classes, we
should make it independent of fair sched class. The str

sched: Make struct sched_statistics independent of fair sched class

If we want to use the schedstats facility to trace other sched classes, we
should make it independent of fair sched class. The struct sched_statistics
is the schedular statistics of a task_struct or a task_group. So we can
move it into struct task_struct and struct task_group to achieve the goal.

After the patch, schestats are orgnized as follows,

struct task_struct {
...
struct sched_entity se;
struct sched_rt_entity rt;
struct sched_dl_entity dl;
...
struct sched_statistics stats;
...
};

Regarding the task group, schedstats is only supported for fair group
sched, and a new struct sched_entity_stats is introduced, suggested by
Peter -

struct sched_entity_stats {
struct sched_entity se;
struct sched_statistics stats;
} __no_randomize_layout;

Then with the se in a task_group, we can easily get the stats.

The sched_statistics members may be frequently modified when schedstats is
enabled, in order to avoid impacting on random data which may in the same
cacheline with them, the struct sched_statistics is defined as cacheline
aligned.

As this patch changes the core struct of scheduler, so I verified the
performance it may impact on the scheduler with 'perf bench sched
pipe', suggested by Mel. Below is the result, in which all the values
are in usecs/op.
Before After
kernel.sched_schedstats=0 5.2~5.4 5.2~5.4
kernel.sched_schedstats=1 5.3~5.5 5.3~5.5
[These data is a little difference with the earlier version, that is
because my old test machine is destroyed so I have to use a new
different test machine.]

Almost no impact on the sched performance.

No functional change.

[[email protected]: reported build failure in earlier version]

Signed-off-by: Yafang Shao <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Mel Gorman <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched: Introduce task_is_running()

Replace a bunch of 'p->state == TASK_RUNNING' with a new helper:
task_is_running(p).

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Davidl

sched: Introduce task_is_running()

Replace a bunch of 'p->state == TASK_RUNNING' with a new helper:
task_is_running(p).

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Davidlohr Bueso <[email protected]>
Acked-by: Geert Uytterhoeven <[email protected]>
Acked-by: Will Deacon <[email protected]>
Link: https://lore.kernel.org/r/[email protected]

show more ...

sched,stats: Further simplify sched_info

There's no point doing delta==0 updates.

Suggested-by: Mel Gorman <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>

sched: Simplify sched_info_on()

The situation around sched_info is somewhat complicated, it is used by
sched_stats and delayacct and, indirectly, kvm.

If SCHEDSTATS=Y (but disabled by default) sche

sched: Simplify sched_info_on()

The situation around sched_info is somewhat complicated, it is used by
sched_stats and delayacct and, indirectly, kvm.

If SCHEDSTATS=Y (but disabled by default) sched_info_on() is
unconditionally true -- this is the case for all distro kernel configs
I checked.

If for some reason SCHEDSTATS=N, but TASK_DELAY_ACCT=Y, then
sched_info_on() can return false when delayacct is disabled,
presumably because there would be no other users left; except kvm is.

Instead of complicating matters further by accurately accounting
sched_stat and kvm state, simply unconditionally enable when
SCHED_INFO=Y, matching the common distro case.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Thomas Gleixner <[email protected]>
Reviewed-by: Ingo Molnar <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...

sched: Rename sched_info_{queued,dequeued}

For consistency, rename {queued,dequeued} to {enqueue,dequeue}.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Rik van Riel <ri

sched: Rename sched_info_{queued,dequeued}

For consistency, rename {queued,dequeued} to {enqueue,dequeue}.

Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Rik van Riel <[email protected]>
Reviewed-by: Thomas Gleixner <[email protected]>
Reviewed-by: Ingo Molnar <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Acked-by: Balbir Singh <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...

psi: Optimize task switch inside shared cgroups

The commit 36b238d57172 ("psi: Optimize switching tasks inside shared
cgroups") only update cgroups whose state actually changes during a
task switch

psi: Optimize task switch inside shared cgroups

The commit 36b238d57172 ("psi: Optimize switching tasks inside shared
cgroups") only update cgroups whose state actually changes during a
task switch only in task preempt case, not in task sleep case.

We actually don't need to clear and set TSK_ONCPU state for common cgroups
of next and prev task in sleep case, that can save many psi_group_change
especially when most activity comes from one leaf cgroup.

sleep before:
psi_dequeue()
while ((group = iterate_groups(prev))) # all ancestors
psi_group_change(prev, .clear=TSK_RUNNING|TSK_ONCPU)
psi_task_switch()
while ((group = iterate_groups(next))) # all ancestors
psi_group_change(next, .set=TSK_ONCPU)

sleep after:
psi_dequeue()
nop
psi_task_switch()
while ((group = iterate_groups(next))) # until (prev & next)
psi_group_change(next, .set=TSK_ONCPU)
while ((group = iterate_groups(prev))) # all ancestors
psi_group_change(prev, .clear=common?TSK_RUNNING:TSK_RUNNING|TSK_ONCPU)

When a voluntary sleep switches to another task, we remove one call of
psi_group_change() for every common cgroup ancestor of the two tasks.

Co-developed-by: Muchun Song <[email protected]>
Signed-off-by: Muchun Song <[email protected]>
Signed-off-by: Chengming Zhou <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...

psi: Use ONCPU state tracking machinery to detect reclaim

Move the reclaim detection from the timer tick to the task state
tracking machinery using the recently added ONCPU state. And we
also add ta

psi: Use ONCPU state tracking machinery to detect reclaim

Move the reclaim detection from the timer tick to the task state
tracking machinery using the recently added ONCPU state. And we
also add task psi_flags changes checking in the psi_task_switch()
optimization to update the parents properly.

In terms of performance and cost, this ONCPU task state tracking
is not cheaper than previous timer tick in aggregate. But the code is
simpler and shorter this way, so it's a maintainability win. And
Johannes did some testing with perf bench, the performace and cost
changes would be acceptable for real workloads.

Thanks to Johannes Weiner for pointing out the psi_task_switch()
optimization things and the clearer changelog.

Co-developed-by: Muchun Song <[email protected]>
Signed-off-by: Muchun Song <[email protected]>
Signed-off-by: Chengming Zhou <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Signed-off-by: Ingo Molnar <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...

psi: Move PF_MEMSTALL out of task->flags

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 s

psi: Move PF_MEMSTALL out of task->flags

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 <[email protected]>
Signed-off-by: Yafang Shao <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Johannes Weiner <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...

psi: Optimize switching tasks inside shared cgroups

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,

psi: Optimize switching tasks inside shared cgroups

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 <[email protected]>
Signed-off-by: Johannes Weiner <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

show more ...