iowait is a bogus metric, but it's helpful in the sense that it allows
short waits to not enter sleep states that have a higher exit latency
than would've otherwise have been picked for iowait'ing tasks. However,
it's harmless in that lots of applications and monitoring assumes that
iowait is busy time, or otherwise use it as a health metric.
Particularly for async IO it's entirely nonsensical.
Split the iowait part into two parts - one that tracks whether the task
needs boosting for short waits, and one that marks whether the task
needs to be accounted as such. ->in_iowait_acct nests inside of
->in_iowait, both for efficiency reasons, but also so that the
relationship between the two is clear. A waiter may set ->in_wait alone
and not care about the accounting.
Existing users of nr_iowait() for accounting purposes are switched to
use nr_iowait_acct(), which leaves the governor using nr_iowait() as it
only cares about iowaiters, not the accounting side.
Utilize that there's enough space in rq->nr_iowait to store both values
in there, shifting the accounting side by half the size of the type.
Thank you to Thomas Gleixner for that [1] suggestion.
[1] https://lore.kernel.org/lkml/87sf1b6o9w.ffs@tglx/
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
arch/s390/appldata/appldata_base.c | 2 +-
arch/s390/appldata/appldata_os.c | 2 +-
fs/proc/stat.c | 2 +-
include/linux/sched.h | 6 +++
include/linux/sched/stat.h | 5 ++-
kernel/sched/core.c | 62 +++++++++++++++++++++++-------
kernel/sched/sched.h | 1 +
kernel/time/tick-sched.c | 6 +--
8 files changed, 65 insertions(+), 21 deletions(-)
diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
index c2978cb03b36..6844b5294a8b 100644
--- a/arch/s390/appldata/appldata_base.c
+++ b/arch/s390/appldata/appldata_base.c
@@ -423,4 +423,4 @@ EXPORT_SYMBOL_GPL(si_swapinfo);
#endif
EXPORT_SYMBOL_GPL(nr_threads);
EXPORT_SYMBOL_GPL(nr_running);
-EXPORT_SYMBOL_GPL(nr_iowait);
+EXPORT_SYMBOL_GPL(nr_iowait_acct);
diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
index a363d30ce739..fa4b278aca6c 100644
--- a/arch/s390/appldata/appldata_os.c
+++ b/arch/s390/appldata/appldata_os.c
@@ -100,7 +100,7 @@ static void appldata_get_os_data(void *data)
os_data->nr_threads = nr_threads;
os_data->nr_running = nr_running();
- os_data->nr_iowait = nr_iowait();
+ os_data->nr_iowait = nr_iowait_acct();
os_data->avenrun[0] = avenrun[0] + (FIXED_1/200);
os_data->avenrun[1] = avenrun[1] + (FIXED_1/200);
os_data->avenrun[2] = avenrun[2] + (FIXED_1/200);
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index da60956b2915..149be7a884fb 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -180,7 +180,7 @@ static int show_stat(struct seq_file *p, void *v)
(unsigned long long)boottime.tv_sec,
total_forks,
nr_running(),
- nr_iowait());
+ nr_iowait_acct());
seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index dcfc2830ed8e..26c69db5484b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -924,7 +924,13 @@ struct task_struct {
/* Bit to tell TOMOYO we're in execve(): */
unsigned in_execve:1;
+ /* task is in iowait */
unsigned in_iowait:1;
+ /*
+ * task is in iowait and should be accounted as such. can only be set
+ * if ->in_iowait is also set.
+ */
+ unsigned in_iowait_acct:1;
#ifndef TIF_RESTORE_SIGMASK
unsigned restore_sigmask:1;
#endif
diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
index 0108a38bb64d..31e8a44b3d71 100644
--- a/include/linux/sched/stat.h
+++ b/include/linux/sched/stat.h
@@ -19,8 +19,9 @@ DECLARE_PER_CPU(unsigned long, process_counts);
extern int nr_processes(void);
extern unsigned int nr_running(void);
extern bool single_task_running(void);
-extern unsigned int nr_iowait(void);
-extern unsigned int nr_iowait_cpu(int cpu);
+unsigned int nr_iowait_acct(void);
+unsigned int nr_iowait_acct_cpu(int cpu);
+unsigned int nr_iowait_cpu(int cpu);
static inline int sched_info_on(void)
{
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 63f6d44f460c..d52d3118dd73 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3721,30 +3721,47 @@ static inline cpumask_t *alloc_user_cpus_ptr(int node)
#endif /* !CONFIG_SMP */
+/*
+ * Store iowait and iowait_acct state in the same variable. The lower bits
+ * hold the iowait state, and the upper bits hold the iowait_acct state.
+ */
static void task_iowait_inc(struct task_struct *p)
{
#ifdef CONFIG_64BIT
- atomic_long_inc(&task_rq(p)->nr_iowait);
+ long val = 1 + ((long) p->in_iowait_acct << 32);
+ atomic_long_add(val, &task_rq(p)->nr_iowait);
#else
- atomic_inc(&task_rq(p)->nr_iowait);
+ int val = 1 + ((int) p->in_iowait_acct << 16);
+ atomic_add(val, &task_rq(p)->nr_iowait);
#endif
}
static void task_iowait_dec(struct task_struct *p)
{
#ifdef CONFIG_64BIT
- atomic_long_dec(&task_rq(p)->nr_iowait);
+ long val = 1 + ((long) p->in_iowait_acct << 32);
+ atomic_long_sub(val, &task_rq(p)->nr_iowait);
#else
- atomic_dec(&task_rq(p)->nr_iowait);
+ int val = 1 + ((int) p->in_iowait_acct << 16);
+ atomic_sub(val, &task_rq(p)->nr_iowait);
#endif
}
int rq_iowait(struct rq *rq)
{
#ifdef CONFIG_64BIT
- return atomic_long_read(&rq->nr_iowait);
+ return atomic_long_read(&rq->nr_iowait) & ((1UL << 32) - 1);
+#else
+ return atomic_read(&rq->nr_iowait) & ((1U << 16) - 1);
+#endif
+}
+
+int rq_iowait_acct(struct rq *rq)
+{
+#ifdef CONFIG_64BIT
+ return atomic_long_read(&rq->nr_iowait) >> 32;
#else
- return atomic_read(&rq->nr_iowait);
+ return atomic_read(&rq->nr_iowait) >> 16;
#endif
}
@@ -5497,7 +5514,12 @@ unsigned long long nr_context_switches(void)
* it does become runnable.
*/
-unsigned int nr_iowait_cpu(int cpu)
+unsigned int nr_iowait_acct_cpu(int cpu)
+{
+ return rq_iowait_acct(cpu_rq(cpu));
+}
+
+unsigned nr_iowait_cpu(int cpu)
{
return rq_iowait(cpu_rq(cpu));
}
@@ -5532,12 +5554,12 @@ unsigned int nr_iowait_cpu(int cpu)
* Task CPU affinities can make all that even more 'interesting'.
*/
-unsigned int nr_iowait(void)
+unsigned int nr_iowait_acct(void)
{
unsigned int i, sum = 0;
for_each_possible_cpu(i)
- sum += nr_iowait_cpu(i);
+ sum += nr_iowait_acct_cpu(i);
return sum;
}
@@ -9032,18 +9054,32 @@ int __sched yield_to(struct task_struct *p, bool preempt)
}
EXPORT_SYMBOL_GPL(yield_to);
+/*
+ * Returns a token which is comprised of the two bits of iowait wait state -
+ * one is whether we're making ourselves as in iowait for cpufreq reasons,
+ * and the other is if the task should be accounted as such.
+ */
long io_schedule_prepare(void)
{
- long old_iowait = current->in_iowait;
-
+#ifdef CONFIG_64BIT
+ long token = current->in_iowait + ((long) current->in_iowait_acct << 32);
+#else
+ int token = current->in_iowait + (current->in_iowait_acct << 16);
+#endif
current->in_iowait = 1;
+ current->in_iowait_acct = 1;
blk_flush_plug(current->plug, true);
- return old_iowait;
+ return token;
}
void io_schedule_finish(long token)
{
- current->in_iowait = token;
+ current->in_iowait = token & 0x01;
+#ifdef CONFIG_64BIT
+ current->in_iowait_acct = token >> 32;
+#else
+ current->in_iowait_acct = token >> 16;
+#endif
}
/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index c2802d066615..85fdd6028682 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -3478,5 +3478,6 @@ extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
int rq_iowait(struct rq *rq);
+int rq_iowait_acct(struct rq *rq);
#endif /* _KERNEL_SCHED_SCHED_H */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 269e21590df5..52f377c5871d 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -728,7 +728,7 @@ static void tick_nohz_stop_idle(struct tick_sched *ts, ktime_t now)
delta = ktime_sub(now, ts->idle_entrytime);
write_seqcount_begin(&ts->idle_sleeptime_seq);
- if (nr_iowait_cpu(smp_processor_id()) > 0)
+ if (nr_iowait_acct_cpu(smp_processor_id()) > 0)
ts->iowait_sleeptime = ktime_add(ts->iowait_sleeptime, delta);
else
ts->idle_sleeptime = ktime_add(ts->idle_sleeptime, delta);
@@ -801,7 +801,7 @@ u64 get_cpu_idle_time_us(int cpu, u64 *last_update_time)
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
return get_cpu_sleep_time_us(ts, &ts->idle_sleeptime,
- !nr_iowait_cpu(cpu), last_update_time);
+ !nr_iowait_acct_cpu(cpu), last_update_time);
}
EXPORT_SYMBOL_GPL(get_cpu_idle_time_us);
@@ -827,7 +827,7 @@ u64 get_cpu_iowait_time_us(int cpu, u64 *last_update_time)
struct tick_sched *ts = &per_cpu(tick_cpu_sched, cpu);
return get_cpu_sleep_time_us(ts, &ts->iowait_sleeptime,
- nr_iowait_cpu(cpu), last_update_time);
+ nr_iowait_acct_cpu(cpu), last_update_time);
}
EXPORT_SYMBOL_GPL(get_cpu_iowait_time_us);
--
2.43.0On Tue, Apr 16, 2024 at 06:11:21AM -0600, Jens Axboe wrote: > iowait is a bogus metric, but it's helpful in the sense that it allows > short waits to not enter sleep states that have a higher exit latency > than would've otherwise have been picked for iowait'ing tasks. However, > it's harmless in that lots of applications and monitoring assumes that > iowait is busy time, or otherwise use it as a health metric. > Particularly for async IO it's entirely nonsensical. Let me get this straight, all of this is about working around cpuidle menu governor insaity? Rafael, how far along are we with fully deprecating that thing? Yes it still exists, but should people really be using it still?
On Wednesday, April 24, 2024 12:01:27 PM CEST Peter Zijlstra wrote: > On Tue, Apr 16, 2024 at 06:11:21AM -0600, Jens Axboe wrote: > > iowait is a bogus metric, but it's helpful in the sense that it allows > > short waits to not enter sleep states that have a higher exit latency > > than would've otherwise have been picked for iowait'ing tasks. However, > > it's harmless in that lots of applications and monitoring assumes that > > iowait is busy time, or otherwise use it as a health metric. > > Particularly for async IO it's entirely nonsensical. > > Let me get this straight, all of this is about working around > cpuidle menu governor insaity? > > Rafael, how far along are we with fully deprecating that thing? Yes it > still exists, but should people really be using it still? Well, they appear to be used to it ...
On 24/04/2024 11:01, Peter Zijlstra wrote:
> On Tue, Apr 16, 2024 at 06:11:21AM -0600, Jens Axboe wrote:
>> iowait is a bogus metric, but it's helpful in the sense that it allows
>> short waits to not enter sleep states that have a higher exit latency
>> than would've otherwise have been picked for iowait'ing tasks. However,
>> it's harmless in that lots of applications and monitoring assumes that
>> iowait is busy time, or otherwise use it as a health metric.
>> Particularly for async IO it's entirely nonsensical.
>
> Let me get this straight, all of this is about working around
> cpuidle menu governor insaity?
>
> Rafael, how far along are we with fully deprecating that thing? Yes it
> still exists, but should people really be using it still?
>
Well there is also the iowait boost handling in schedutil and intel_pstate
which, at least in synthetic benchmarks, does have an effect [1].
io_uring (the only user of iowait but not iowait_acct) works around both.
See commit ("8a796565cec3 io_uring: Use io_schedule* in cqring wait")
[1]
https://lore.kernel.org/lkml/20240304201625.100619-1-christian.loehle@arm.com/#t
Kind Regards,
Christian
On Wed, Apr 24, 2024 at 11:08:42AM +0100, Christian Loehle wrote:
> On 24/04/2024 11:01, Peter Zijlstra wrote:
> > On Tue, Apr 16, 2024 at 06:11:21AM -0600, Jens Axboe wrote:
> >> iowait is a bogus metric, but it's helpful in the sense that it allows
> >> short waits to not enter sleep states that have a higher exit latency
> >> than would've otherwise have been picked for iowait'ing tasks. However,
> >> it's harmless in that lots of applications and monitoring assumes that
> >> iowait is busy time, or otherwise use it as a health metric.
> >> Particularly for async IO it's entirely nonsensical.
> >
> > Let me get this straight, all of this is about working around
> > cpuidle menu governor insaity?
> >
> > Rafael, how far along are we with fully deprecating that thing? Yes it
> > still exists, but should people really be using it still?
> >
>
> Well there is also the iowait boost handling in schedutil and intel_pstate
> which, at least in synthetic benchmarks, does have an effect [1].
Those are cpufreq not cpuidle and at least they don't use nr_iowait. The
original Changelog mentioned idle states, and I hate on menu for using
nr_iowait.
> io_uring (the only user of iowait but not iowait_acct) works around both.
>
> See commit ("8a796565cec3 io_uring: Use io_schedule* in cqring wait")
>
> [1]
> https://lore.kernel.org/lkml/20240304201625.100619-1-christian.loehle@arm.com/#t
So while I agree with most of the short-commings listed in that set,
however that patch is quite terrifying.
I would prefer to start with something a *lot* simpler. How about a tick
driven decay of iops count per task. And that whole step array
*shudder*.
On 25/04/2024 11:16, Peter Zijlstra wrote:
> On Wed, Apr 24, 2024 at 11:08:42AM +0100, Christian Loehle wrote:
>> On 24/04/2024 11:01, Peter Zijlstra wrote:
>>> On Tue, Apr 16, 2024 at 06:11:21AM -0600, Jens Axboe wrote:
>>>> iowait is a bogus metric, but it's helpful in the sense that it allows
>>>> short waits to not enter sleep states that have a higher exit latency
>>>> than would've otherwise have been picked for iowait'ing tasks. However,
>>>> it's harmless in that lots of applications and monitoring assumes that
>>>> iowait is busy time, or otherwise use it as a health metric.
>>>> Particularly for async IO it's entirely nonsensical.
>>>
>>> Let me get this straight, all of this is about working around
>>> cpuidle menu governor insaity?
>>>
>>> Rafael, how far along are we with fully deprecating that thing? Yes it
>>> still exists, but should people really be using it still?
>>>
>>
>> Well there is also the iowait boost handling in schedutil and intel_pstate
>> which, at least in synthetic benchmarks, does have an effect [1].
>
> Those are cpufreq not cpuidle and at least they don't use nr_iowait. The
> original Changelog mentioned idle states, and I hate on menu for using
> nr_iowait.
I'd say they care about any regression, but I'll let Jens answer that.
The original change also mentions cpufreq and Jens did mention in an
earlier version that he doesn't care, for them it's all just increased
latency ;)
https://lore.kernel.org/lkml/00d36e83-c9a5-412d-bf49-2e109308d6cd@arm.com/T/#m216536520bc31846aff5875993d22f446a37b297
>
>> io_uring (the only user of iowait but not iowait_acct) works around both.
>>
>> See commit ("8a796565cec3 io_uring: Use io_schedule* in cqring wait")
>>
>> [1]
>> https://lore.kernel.org/lkml/20240304201625.100619-1-christian.loehle@arm.com/#t
>
> So while I agree with most of the short-commings listed in that set,
> however that patch is quite terrifying.
Not disagreeing with you on that.
>
> I would prefer to start with something a *lot* simpler. How about a tick
> driven decay of iops count per task. And that whole step array
> *shudder*.
It's an attempt of solving unnecessary boosting based upon what is there for
us to work with now: iowait wakeups.
There are many workloads with e.g. > 5000 iowait wakeups per second that don't
benefit from boosting at all (and therefore it's a complete energy waste).
I don't see anything obvious how we would attempt to detect non-boost-worthy
scenarios with a tick driven decay count, but please do elaborate.
(If you *really* care about IO throughput, the task wakeup path is hopefully
not critical anyway (i.e. you do everything in your power to have IO pending
during that time) and then we don't need boosting, but just looking
at a tick-length period doesn't let us distinguish those scenarios AFAICS.)
Regards,
Christian
On 16/04/2024 13:11, Jens Axboe wrote:
> iowait is a bogus metric, but it's helpful in the sense that it allows
> short waits to not enter sleep states that have a higher exit latency
> than would've otherwise have been picked for iowait'ing tasks. However,
> it's harmless in that lots of applications and monitoring assumes that
s/harmless/harmful ?
> iowait is busy time, or otherwise use it as a health metric.
> Particularly for async IO it's entirely nonsensical.
>
> Split the iowait part into two parts - one that tracks whether the task
> needs boosting for short waits, and one that marks whether the task
> needs to be accounted as such. ->in_iowait_acct nests inside of
> ->in_iowait, both for efficiency reasons, but also so that the
> relationship between the two is clear. A waiter may set ->in_wait alone
s/in_wait/in_iowait/
> and not care about the accounting.
>
> Existing users of nr_iowait() for accounting purposes are switched to
> use nr_iowait_acct(), which leaves the governor using nr_iowait() as it
> only cares about iowaiters, not the accounting side.
>
> Utilize that there's enough space in rq->nr_iowait to store both values
> in there, shifting the accounting side by half the size of the type.
> Thank you to Thomas Gleixner for that [1] suggestion.
>
> [1] https://lore.kernel.org/lkml/87sf1b6o9w.ffs@tglx/
>
> Signed-off-by: Jens Axboe <axboe@kernel.dk>
Again this is just a tiny symptom of iowait being bogus, but I understand
your problem and have nothing simple to offer you as of now.
Daniel's comment mentioned below is still spot on.
Any behavior piggybacked ontop of iowait is also non-sensical without
any definition of what "iowait" is actually supposed to mean.
Are we returning to the same rq real soon? Maybe, maybe not.
Are we on the critical path to higher IO throughput and should be run
with a high frequency after wakeup? Maybe, maybe not (Probably not?).
Apart from that obligatory nagging and my comments below this looks okay.
> ---
> arch/s390/appldata/appldata_base.c | 2 +-
> arch/s390/appldata/appldata_os.c | 2 +-
> fs/proc/stat.c | 2 +-
> include/linux/sched.h | 6 +++
> include/linux/sched/stat.h | 5 ++-
> kernel/sched/core.c | 62 +++++++++++++++++++++++-------
> kernel/sched/sched.h | 1 +
> kernel/time/tick-sched.c | 6 +--
> 8 files changed, 65 insertions(+), 21 deletions(-)
>
> diff --git a/arch/s390/appldata/appldata_base.c b/arch/s390/appldata/appldata_base.c
> index c2978cb03b36..6844b5294a8b 100644
> --- a/arch/s390/appldata/appldata_base.c
> +++ b/arch/s390/appldata/appldata_base.c
> @@ -423,4 +423,4 @@ EXPORT_SYMBOL_GPL(si_swapinfo);
> #endif
> EXPORT_SYMBOL_GPL(nr_threads);
> EXPORT_SYMBOL_GPL(nr_running);
> -EXPORT_SYMBOL_GPL(nr_iowait);
> +EXPORT_SYMBOL_GPL(nr_iowait_acct);
> diff --git a/arch/s390/appldata/appldata_os.c b/arch/s390/appldata/appldata_os.c
> index a363d30ce739..fa4b278aca6c 100644
> --- a/arch/s390/appldata/appldata_os.c
> +++ b/arch/s390/appldata/appldata_os.c
> @@ -100,7 +100,7 @@ static void appldata_get_os_data(void *data)
>
> os_data->nr_threads = nr_threads;
> os_data->nr_running = nr_running();
> - os_data->nr_iowait = nr_iowait();
> + os_data->nr_iowait = nr_iowait_acct();
> os_data->avenrun[0] = avenrun[0] + (FIXED_1/200);
> os_data->avenrun[1] = avenrun[1] + (FIXED_1/200);
> os_data->avenrun[2] = avenrun[2] + (FIXED_1/200);
> diff --git a/fs/proc/stat.c b/fs/proc/stat.c
> index da60956b2915..149be7a884fb 100644
> --- a/fs/proc/stat.c
> +++ b/fs/proc/stat.c
> @@ -180,7 +180,7 @@ static int show_stat(struct seq_file *p, void *v)
> (unsigned long long)boottime.tv_sec,
> total_forks,
> nr_running(),
> - nr_iowait());
> + nr_iowait_acct());
>
> seq_put_decimal_ull(p, "softirq ", (unsigned long long)sum_softirq);
>
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index dcfc2830ed8e..26c69db5484b 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -924,7 +924,13 @@ struct task_struct {
>
> /* Bit to tell TOMOYO we're in execve(): */
> unsigned in_execve:1;
> + /* task is in iowait */
> unsigned in_iowait:1;
> + /*
> + * task is in iowait and should be accounted as such. can only be set
> + * if ->in_iowait is also set.
> + */
> + unsigned in_iowait_acct:1;
> #ifndef TIF_RESTORE_SIGMASK
> unsigned restore_sigmask:1;
> #endif
> diff --git a/include/linux/sched/stat.h b/include/linux/sched/stat.h
> index 0108a38bb64d..31e8a44b3d71 100644
> --- a/include/linux/sched/stat.h
> +++ b/include/linux/sched/stat.h
> @@ -19,8 +19,9 @@ DECLARE_PER_CPU(unsigned long, process_counts);
> extern int nr_processes(void);
> extern unsigned int nr_running(void);
> extern bool single_task_running(void);
> -extern unsigned int nr_iowait(void);
> -extern unsigned int nr_iowait_cpu(int cpu);
> +unsigned int nr_iowait_acct(void);
> +unsigned int nr_iowait_acct_cpu(int cpu);
> +unsigned int nr_iowait_cpu(int cpu);
>
> static inline int sched_info_on(void)
> {
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 63f6d44f460c..d52d3118dd73 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -3721,30 +3721,47 @@ static inline cpumask_t *alloc_user_cpus_ptr(int node)
>
> #endif /* !CONFIG_SMP */
>
> +/*
> + * Store iowait and iowait_acct state in the same variable. The lower bits
> + * hold the iowait state, and the upper bits hold the iowait_acct state.
> + */
> static void task_iowait_inc(struct task_struct *p)
> {
> #ifdef CONFIG_64BIT
> - atomic_long_inc(&task_rq(p)->nr_iowait);
> + long val = 1 + ((long) p->in_iowait_acct << 32);
Are we not doing declarations at the beginning of the block anymore?
> + atomic_long_add(val, &task_rq(p)->nr_iowait);
> #else
> - atomic_inc(&task_rq(p)->nr_iowait);
> + int val = 1 + ((int) p->in_iowait_acct << 16);
> + atomic_add(val, &task_rq(p)->nr_iowait);
> #endif
> }
>
> static void task_iowait_dec(struct task_struct *p)
> {
> #ifdef CONFIG_64BIT
> - atomic_long_dec(&task_rq(p)->nr_iowait);
> + long val = 1 + ((long) p->in_iowait_acct << 32);
> + atomic_long_sub(val, &task_rq(p)->nr_iowait);
> #else
> - atomic_dec(&task_rq(p)->nr_iowait);
> + int val = 1 + ((int) p->in_iowait_acct << 16);
> + atomic_sub(val, &task_rq(p)->nr_iowait);
> #endif
> }
>
> int rq_iowait(struct rq *rq)
> {
> #ifdef CONFIG_64BIT
> - return atomic_long_read(&rq->nr_iowait);
> + return atomic_long_read(&rq->nr_iowait) & ((1UL << 32) - 1);
> +#else
> + return atomic_read(&rq->nr_iowait) & ((1U << 16) - 1);
> +#endif
> +}
> +
> +int rq_iowait_acct(struct rq *rq)
> +{
> +#ifdef CONFIG_64BIT
> + return atomic_long_read(&rq->nr_iowait) >> 32;
> #else
> - return atomic_read(&rq->nr_iowait);
> + return atomic_read(&rq->nr_iowait) >> 16;
> #endif
> }
>
> @@ -5497,7 +5514,12 @@ unsigned long long nr_context_switches(void)
> * it does become runnable.
> */
>
> -unsigned int nr_iowait_cpu(int cpu)
> +unsigned int nr_iowait_acct_cpu(int cpu)
There is a comment above here by Daniel referring to "these two
interfaces [...]", originally referring to nr_iowait_cpu() and
get_iowait_load().
get_iowait_load() was removed in commit a7fe5190c03f ("cpuidle: menu: Remove get_loadavg() from the performance multiplier")
but nr_iowait_cpu() remains, so the comment should remain above it.
Rewording is also way overdue, although that's hardly on your
patch ;)
> +{
> + return rq_iowait_acct(cpu_rq(cpu));
> +}
> +
> +unsigned nr_iowait_cpu(int cpu)
unsigned int
> {
> return rq_iowait(cpu_rq(cpu));
> }
> @@ -5532,12 +5554,12 @@ unsigned int nr_iowait_cpu(int cpu)
> * Task CPU affinities can make all that even more 'interesting'.
> */
>
> -unsigned int nr_iowait(void)
> +unsigned int nr_iowait_acct(void)
> {
> unsigned int i, sum = 0;
>
> for_each_possible_cpu(i)
> - sum += nr_iowait_cpu(i);
> + sum += nr_iowait_acct_cpu(i);
>
> return sum;
> }
> @@ -9032,18 +9054,32 @@ int __sched yield_to(struct task_struct *p, bool preempt)
> }
> EXPORT_SYMBOL_GPL(yield_to);
> [snip]
On 16/04/2024 15:10, Christian Loehle wrote:
>>[snip]
>> + atomic_long_add(val, &task_rq(p)->nr_iowait);
>> #else
>> - atomic_inc(&task_rq(p)->nr_iowait);
>> + int val = 1 + ((int) p->in_iowait_acct << 16);
>> + atomic_add(val, &task_rq(p)->nr_iowait);
>> #endif
>> }
>>
>> static void task_iowait_dec(struct task_struct *p)
>> {
>> #ifdef CONFIG_64BIT
>> - atomic_long_dec(&task_rq(p)->nr_iowait);
>> + long val = 1 + ((long) p->in_iowait_acct << 32);
>> + atomic_long_sub(val, &task_rq(p)->nr_iowait);
>> #else
>> - atomic_dec(&task_rq(p)->nr_iowait);
>> + int val = 1 + ((int) p->in_iowait_acct << 16);
>> + atomic_sub(val, &task_rq(p)->nr_iowait);
>> #endif
>> }
>>
>> int rq_iowait(struct rq *rq)
>> {
>> #ifdef CONFIG_64BIT
>> - return atomic_long_read(&rq->nr_iowait);
>> + return atomic_long_read(&rq->nr_iowait) & ((1UL << 32) - 1);
>> +#else
>> + return atomic_read(&rq->nr_iowait) & ((1U << 16) - 1);
>> +#endif
>> +}
>> +
>> +int rq_iowait_acct(struct rq *rq)
>> +{
>> +#ifdef CONFIG_64BIT
>> + return atomic_long_read(&rq->nr_iowait) >> 32;
>> #else
>> - return atomic_read(&rq->nr_iowait);
>> + return atomic_read(&rq->nr_iowait) >> 16;
>> #endif
>> }
>>
>> @@ -5497,7 +5514,12 @@ unsigned long long nr_context_switches(void)
>> * it does become runnable.
>> */
>>
>> -unsigned int nr_iowait_cpu(int cpu)
>> +unsigned int nr_iowait_acct_cpu(int cpu)
>
> There is a comment above here by Daniel referring to "these two
> interfaces [...]", originally referring to nr_iowait_cpu() and
> get_iowait_load().
> get_iowait_load() was removed in commit a7fe5190c03f ("cpuidle: menu: Remove get_loadavg() from the performance multiplier")
> but nr_iowait_cpu() remains, so the comment should remain above it.
> Rewording is also way overdue, although that's hardly on your
> patch ;)
>
FWIW, but also feel free to reword yourself.
From ba66fe24c64f5615b9820b0fe24857ecbf18fc5f Mon Sep 17 00:00:00 2001
From: Christian Loehle <christian.loehle@arm.com>
Date: Tue, 16 Apr 2024 15:20:22 +0100
Subject: [PATCH] sched/core: Reword comment about iowait interface
The original comment referenced an interface which was removed in
the meantime by commit a7fe5190c03f ("cpuidle: menu: Remove
get_loadavg() from the performance multiplier").
Furthermore the function has moved so move the comment accordingly.
Signed-off-by: Christian Loehle <christian.loehle@arm.com>
---
kernel/sched/core.c | 13 +++++++------
1 file changed, 7 insertions(+), 6 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d52d3118dd73..bb10b9bc37d6 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5507,18 +5507,19 @@ unsigned long long nr_context_switches(void)
return sum;
}
-/*
- * Consumers of these two interfaces, like for example the cpuidle menu
- * governor, are using nonsensical data. Preferring shallow idle state selection
- * for a CPU that has IO-wait which might not even end up running the task when
- * it does become runnable.
- */
unsigned int nr_iowait_acct_cpu(int cpu)
{
return rq_iowait_acct(cpu_rq(cpu));
}
+/*
+ * Consumers of this interface like the cpuidle menu governor are using
+ * nonsensical data. Preferring shallow idle state selection for a CPU that
+ * has IO-wait which might not even end up being selected for the task again
+ * when it does become runnable.
+ */
+
unsigned nr_iowait_cpu(int cpu)
{
return rq_iowait(cpu_rq(cpu));
--
2.34.1
© 2016 - 2026 Red Hat, Inc.