Huaixin Chang (2):
sched/fair: Add cfs bandwidth burst statistics
sched/fair: Add document for burstable CFS bandwidth
Documentation/admin-guide/cgroup-v2.rst | 8 ++++
Documentation/scheduler/sched-bwc.rst | 85 +++++++++++++++++++++++++++++----
kernel/sched/core.c | 13 +++--
kernel/sched/fair.c | 9 ++++
kernel/sched/sched.h | 3 ++
5 files changed, 105 insertions(+), 13 deletions(-)
--
2.14.4.44.g2045bb6
Two new statistics are introduced to show the internal of burst feature
and explain why burst helps or not.
nr_bursts: number of periods bandwidth burst occurs
burst_usec: cumulative wall-time that any cpus has
used above quota in respective periods
Co-developed-by: Shanpei Chen <[email protected]>
Signed-off-by: Shanpei Chen <[email protected]>
Co-developed-by: Tianchen Ding <[email protected]>
Signed-off-by: Tianchen Ding <[email protected]>
Signed-off-by: Huaixin Chang <[email protected]>
---
kernel/sched/core.c | 13 ++++++++++---
kernel/sched/fair.c | 9 +++++++++
kernel/sched/sched.h | 3 +++
3 files changed, 22 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 2d9ff40f4661..9a286c8a1354 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -10088,6 +10088,9 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
seq_printf(sf, "wait_sum %llu\n", ws);
}
+ seq_printf(sf, "nr_bursts %d\n", cfs_b->nr_burst);
+ seq_printf(sf, "burst_usec %llu\n", cfs_b->burst_time);
+
return 0;
}
#endif /* CONFIG_CFS_BANDWIDTH */
@@ -10184,16 +10187,20 @@ static int cpu_extra_stat_show(struct seq_file *sf,
{
struct task_group *tg = css_tg(css);
struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
- u64 throttled_usec;
+ u64 throttled_usec, burst_usec;
throttled_usec = cfs_b->throttled_time;
do_div(throttled_usec, NSEC_PER_USEC);
+ burst_usec = cfs_b->burst_time;
+ do_div(burst_usec, NSEC_PER_USEC);
seq_printf(sf, "nr_periods %d\n"
"nr_throttled %d\n"
- "throttled_usec %llu\n",
+ "throttled_usec %llu\n"
+ "nr_bursts %d\n"
+ "burst_usec %llu\n",
cfs_b->nr_periods, cfs_b->nr_throttled,
- throttled_usec);
+ throttled_usec, cfs_b->nr_burst, burst_usec);
}
#endif
return 0;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 44c452072a1b..464371f364f1 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -4655,11 +4655,20 @@ static inline u64 sched_cfs_bandwidth_slice(void)
*/
void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
{
+ s64 runtime;
+
if (unlikely(cfs_b->quota == RUNTIME_INF))
return;
cfs_b->runtime += cfs_b->quota;
+ runtime = cfs_b->runtime_snap - cfs_b->runtime;
+ if (runtime > 0) {
+ cfs_b->burst_time += runtime;
+ cfs_b->nr_burst++;
+ }
+
cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst);
+ cfs_b->runtime_snap = cfs_b->runtime;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 14a41a243f7b..80e4322727b4 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -367,6 +367,7 @@ struct cfs_bandwidth {
u64 quota;
u64 runtime;
u64 burst;
+ u64 runtime_snap;
s64 hierarchical_quota;
u8 idle;
@@ -379,7 +380,9 @@ struct cfs_bandwidth {
/* Statistics: */
int nr_periods;
int nr_throttled;
+ int nr_burst;
u64 throttled_time;
+ u64 burst_time;
#endif
};
--
2.14.4.44.g2045bb6
Basic description of usage and effect for CFS Bandwidth Control Burst.
Co-developed-by: Shanpei Chen <[email protected]>
Signed-off-by: Shanpei Chen <[email protected]>
Co-developed-by: Tianchen Ding <[email protected]>
Signed-off-by: Tianchen Ding <[email protected]>
Signed-off-by: Huaixin Chang <[email protected]>
---
Documentation/admin-guide/cgroup-v2.rst | 8 ++++
Documentation/scheduler/sched-bwc.rst | 85 +++++++++++++++++++++++++++++----
2 files changed, 83 insertions(+), 10 deletions(-)
diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 5c7377b5bd3e..c79477089c53 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1016,6 +1016,8 @@ All time durations are in microseconds.
- nr_periods
- nr_throttled
- throttled_usec
+ - nr_bursts
+ - burst_usec
cpu.weight
A read-write single value file which exists on non-root
@@ -1047,6 +1049,12 @@ All time durations are in microseconds.
$PERIOD duration. "max" for $MAX indicates no limit. If only
one number is written, $MAX is updated.
+ cpu.max.burst
+ A read-write single value file which exists on non-root
+ cgroups. The default is "0".
+
+ The burst in the range [0, $QUOTA].
+
cpu.pressure
A read-write nested-keyed file.
diff --git a/Documentation/scheduler/sched-bwc.rst b/Documentation/scheduler/sched-bwc.rst
index 1fc73555f5c4..0b2a3b2e3369 100644
--- a/Documentation/scheduler/sched-bwc.rst
+++ b/Documentation/scheduler/sched-bwc.rst
@@ -22,39 +22,89 @@ cfs_quota units at each period boundary. As threads consume this bandwidth it
is transferred to cpu-local "silos" on a demand basis. The amount transferred
within each of these updates is tunable and described as the "slice".
+Burst feature
+-------------
+This feature borrows time now against our future underrun, at the cost of
+increased interference against the other system users. All nicely bounded.
+
+Traditional (UP-EDF) bandwidth control is something like:
+
+ (U = \Sum u_i) <= 1
+
+This guaranteeds both that every deadline is met and that the system is
+stable. After all, if U were > 1, then for every second of walltime,
+we'd have to run more than a second of program time, and obviously miss
+our deadline, but the next deadline will be further out still, there is
+never time to catch up, unbounded fail.
+
+The burst feature observes that a workload doesn't always executes the full
+quota; this enables one to describe u_i as a statistical distribution.
+
+For example, have u_i = {x,e}_i, where x is the p(95) and x+e p(100)
+(the traditional WCET). This effectively allows u to be smaller,
+increasing the efficiency (we can pack more tasks in the system), but at
+the cost of missing deadlines when all the odds line up. However, it
+does maintain stability, since every overrun must be paired with an
+underrun as long as our x is above the average.
+
+That is, suppose we have 2 tasks, both specify a p(95) value, then we
+have a p(95)*p(95) = 90.25% chance both tasks are within their quota and
+everything is good. At the same time we have a p(5)p(5) = 0.25% chance
+both tasks will exceed their quota at the same time (guaranteed deadline
+fail). Somewhere in between there's a threshold where one exceeds and
+the other doesn't underrun enough to compensate; this depends on the
+specific CDFs.
+
+At the same time, we can say that the worst case deadline miss, will be
+\Sum e_i; that is, there is a bounded tardiness (under the assumption
+that x+e is indeed WCET).
+
+The interferenece when using burst is valued by the possibilities for
+missing the deadline and the average WCET. Test results showed that when
+there many cgroups or CPU is under utilized, the interference is
+limited. More details are shown in:
+https://lore.kernel.org/lkml/[email protected]/
+
Management
----------
-Quota and period are managed within the cpu subsystem via cgroupfs.
+Quota, period and burst are managed within the cpu subsystem via cgroupfs.
.. note::
The cgroupfs files described in this section are only applicable
to cgroup v1. For cgroup v2, see
:ref:`Documentation/admin-guide/cgroup-v2.rst <cgroup-v2-cpu>`.
-- cpu.cfs_quota_us: the total available run-time within a period (in
- microseconds)
+- cpu.cfs_quota_us: run-time replenished within a period (in microseconds)
- cpu.cfs_period_us: the length of a period (in microseconds)
- cpu.stat: exports throttling statistics [explained further below]
+- cpu.cfs_burst_us: the maximum accumulated run-time (in microseconds)
The default values are::
cpu.cfs_period_us=100ms
- cpu.cfs_quota=-1
+ cpu.cfs_quota_us=-1
+ cpu.cfs_burst_us=0
A value of -1 for cpu.cfs_quota_us indicates that the group does not have any
bandwidth restriction in place, such a group is described as an unconstrained
bandwidth group. This represents the traditional work-conserving behavior for
CFS.
-Writing any (valid) positive value(s) will enact the specified bandwidth limit.
-The minimum quota allowed for the quota or period is 1ms. There is also an
-upper bound on the period length of 1s. Additional restrictions exist when
-bandwidth limits are used in a hierarchical fashion, these are explained in
-more detail below.
+Writing any (valid) positive value(s) no smaller than cpu.cfs_burst_us will
+enact the specified bandwidth limit. The minimum quota allowed for the quota or
+period is 1ms. There is also an upper bound on the period length of 1s.
+Additional restrictions exist when bandwidth limits are used in a hierarchical
+fashion, these are explained in more detail below.
Writing any negative value to cpu.cfs_quota_us will remove the bandwidth limit
and return the group to an unconstrained state once more.
+A value of 0 for cpu.cfs_burst_us indicates that the group can not accumulate
+any unused bandwidth. It makes the traditional bandwidth control behavior for
+CFS unchanged. Writing any (valid) positive value(s) no larger than
+cpu.cfs_quota_us into cpu.cfs_burst_us will enact the cap on unused bandwidth
+accumulation.
+
Any updates to a group's bandwidth specification will result in it becoming
unthrottled if it is in a constrained state.
@@ -74,7 +124,7 @@ for more fine-grained consumption.
Statistics
----------
-A group's bandwidth statistics are exported via 3 fields in cpu.stat.
+A group's bandwidth statistics are exported via 5 fields in cpu.stat.
cpu.stat:
@@ -82,6 +132,9 @@ cpu.stat:
- nr_throttled: Number of times the group has been throttled/limited.
- throttled_time: The total time duration (in nanoseconds) for which entities
of the group have been throttled.
+- nr_bursts: Number of periods burst occurs.
+- burst_usec: Cumulative wall-time that any CPUs has used above quota in
+ respective periods
This interface is read-only.
@@ -179,3 +232,15 @@ Examples
By using a small period here we are ensuring a consistent latency
response at the expense of burst capacity.
+
+4. Limit a group to 40% of 1 CPU, and allow accumulate up to 20% of 1 CPU
+ additionally, in case accumulation has been done.
+
+ With 50ms period, 20ms quota will be equivalent to 40% of 1 CPU.
+ And 10ms burst will be equivalent to 20% of 1 CPU.
+
+ # echo 20000 > cpu.cfs_quota_us /* quota = 20ms */
+ # echo 50000 > cpu.cfs_period_us /* period = 50ms */
+ # echo 10000 > cpu.cfs_burst_us /* burst = 10ms */
+
+ Larger buffer setting (no larger than quota) allows greater burst capacity.
--
2.14.4.44.g2045bb6
Ping.
The statistics code is further simplified than the one discussed before. Mind having a look at it?
> On Jul 30, 2021, at 3:09 PM, Huaixin Chang <[email protected]> wrote:
>
> Two new statistics are introduced to show the internal of burst feature
> and explain why burst helps or not.
>
> nr_bursts: number of periods bandwidth burst occurs
> burst_usec: cumulative wall-time that any cpus has
> used above quota in respective periods
>
> Co-developed-by: Shanpei Chen <[email protected]>
> Signed-off-by: Shanpei Chen <[email protected]>
> Co-developed-by: Tianchen Ding <[email protected]>
> Signed-off-by: Tianchen Ding <[email protected]>
> Signed-off-by: Huaixin Chang <[email protected]>
> ---
> kernel/sched/core.c | 13 ++++++++++---
> kernel/sched/fair.c | 9 +++++++++
> kernel/sched/sched.h | 3 +++
> 3 files changed, 22 insertions(+), 3 deletions(-)
>
> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
> index 2d9ff40f4661..9a286c8a1354 100644
> --- a/kernel/sched/core.c
> +++ b/kernel/sched/core.c
> @@ -10088,6 +10088,9 @@ static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
> seq_printf(sf, "wait_sum %llu\n", ws);
> }
>
> + seq_printf(sf, "nr_bursts %d\n", cfs_b->nr_burst);
> + seq_printf(sf, "burst_usec %llu\n", cfs_b->burst_time);
> +
> return 0;
> }
> #endif /* CONFIG_CFS_BANDWIDTH */
> @@ -10184,16 +10187,20 @@ static int cpu_extra_stat_show(struct seq_file *sf,
> {
> struct task_group *tg = css_tg(css);
> struct cfs_bandwidth *cfs_b = &tg->cfs_bandwidth;
> - u64 throttled_usec;
> + u64 throttled_usec, burst_usec;
>
> throttled_usec = cfs_b->throttled_time;
> do_div(throttled_usec, NSEC_PER_USEC);
> + burst_usec = cfs_b->burst_time;
> + do_div(burst_usec, NSEC_PER_USEC);
>
> seq_printf(sf, "nr_periods %d\n"
> "nr_throttled %d\n"
> - "throttled_usec %llu\n",
> + "throttled_usec %llu\n"
> + "nr_bursts %d\n"
> + "burst_usec %llu\n",
> cfs_b->nr_periods, cfs_b->nr_throttled,
> - throttled_usec);
> + throttled_usec, cfs_b->nr_burst, burst_usec);
> }
> #endif
> return 0;
> diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
> index 44c452072a1b..464371f364f1 100644
> --- a/kernel/sched/fair.c
> +++ b/kernel/sched/fair.c
> @@ -4655,11 +4655,20 @@ static inline u64 sched_cfs_bandwidth_slice(void)
> */
> void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
> {
> + s64 runtime;
> +
> if (unlikely(cfs_b->quota == RUNTIME_INF))
> return;
>
> cfs_b->runtime += cfs_b->quota;
> + runtime = cfs_b->runtime_snap - cfs_b->runtime;
> + if (runtime > 0) {
> + cfs_b->burst_time += runtime;
> + cfs_b->nr_burst++;
> + }
> +
> cfs_b->runtime = min(cfs_b->runtime, cfs_b->quota + cfs_b->burst);
> + cfs_b->runtime_snap = cfs_b->runtime;
> }
>
> static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 14a41a243f7b..80e4322727b4 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -367,6 +367,7 @@ struct cfs_bandwidth {
> u64 quota;
> u64 runtime;
> u64 burst;
> + u64 runtime_snap;
> s64 hierarchical_quota;
>
> u8 idle;
> @@ -379,7 +380,9 @@ struct cfs_bandwidth {
> /* Statistics: */
> int nr_periods;
> int nr_throttled;
> + int nr_burst;
> u64 throttled_time;
> + u64 burst_time;
> #endif
> };
>
> --
> 2.14.4.44.g2045bb6
>
>
On Fri, Jul 30, 2021 at 03:09:54PM +0800, Huaixin Chang wrote:
> Huaixin Chang (2):
> sched/fair: Add cfs bandwidth burst statistics
> sched/fair: Add document for burstable CFS bandwidth
Acked-by: Tejun Heo <[email protected]>
Thanks.
--
tejun