From: Parth Shah <parth@linux.ibm.com>
To: peterz@infradead.org, mingo@redhat.com
Cc: linux-kernel@vger.kernel.org, linux-pm@vger.kernel.org,
patrick.bellasi@arm.com, dietmar.eggemann@arm.com,
daniel.lezcano@linaro.org, subhra.mazumdar@oracle.com
Subject: [RFC v4 1/8] sched/core: Add manual jitter classification using sched_setattr syscall
Date: Thu, 25 Jul 2019 12:38:50 +0530 [thread overview]
Message-ID: <20190725070857.6639-2-parth@linux.ibm.com> (raw)
In-Reply-To: <20190725070857.6639-1-parth@linux.ibm.com>
Jitter tasks are short/bursty tasks, typically performing some housekeeping
work and are less important in the overall scheme of things.
So provide a way to mark the task as jitter with the use of additional flag
to the existing task attribute. Also provide an interface from the
userspace which uses sched_setattr syscall to mark tasks as jitter.
Signed-off-by: Parth Shah <parth@linux.ibm.com>
---
include/linux/sched.h | 1 +
include/uapi/linux/sched.h | 4 +++-
kernel/sched/core.c | 9 +++++++++
3 files changed, 13 insertions(+), 1 deletion(-)
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1113dd4706ae..e03b85166e34 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1463,6 +1463,7 @@ extern struct pid *cad_pid;
#define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_mask */
#define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MEMALLOC_NOCMA 0x10000000 /* All allocation request will have _GFP_MOVABLE cleared */
+#define PF_CAN_BE_PACKED 0x20000000 /* Provide hints to the scheduler to pack such tasks */
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezable */
#define PF_SUSPEND_TASK 0x80000000 /* This thread called freeze_processes() and should not be frozen */
diff --git a/include/uapi/linux/sched.h b/include/uapi/linux/sched.h
index 617bb59aa8ba..fccb1c57d037 100644
--- a/include/uapi/linux/sched.h
+++ b/include/uapi/linux/sched.h
@@ -55,6 +55,7 @@
#define SCHED_FLAG_KEEP_PARAMS 0x10
#define SCHED_FLAG_UTIL_CLAMP_MIN 0x20
#define SCHED_FLAG_UTIL_CLAMP_MAX 0x40
+#define SCHED_FLAG_TASK_PACKING 0x80
#define SCHED_FLAG_KEEP_ALL (SCHED_FLAG_KEEP_POLICY | \
SCHED_FLAG_KEEP_PARAMS)
@@ -66,6 +67,7 @@
SCHED_FLAG_RECLAIM | \
SCHED_FLAG_DL_OVERRUN | \
SCHED_FLAG_KEEP_ALL | \
- SCHED_FLAG_UTIL_CLAMP)
+ SCHED_FLAG_UTIL_CLAMP | \
+ SCHED_FLAG_TASK_PACKING)
#endif /* _UAPI_LINUX_SCHED_H */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fa43ce3962e7..e7cda4aa8696 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4498,6 +4498,8 @@ static void __setscheduler_params(struct task_struct *p,
p->rt_priority = attr->sched_priority;
p->normal_prio = normal_prio(p);
set_load_weight(p, true);
+ if (attr->sched_flags & SCHED_FLAG_TASK_PACKING)
+ p->flags |= PF_CAN_BE_PACKED;
}
/* Actually do priority change: must hold pi & rq lock. */
@@ -4557,6 +4559,8 @@ static int __sched_setscheduler(struct task_struct *p,
struct rq_flags rf;
int reset_on_fork;
int queue_flags = DEQUEUE_SAVE | DEQUEUE_MOVE | DEQUEUE_NOCLOCK;
+ unsigned long long task_packing_flag =
+ attr->sched_flags & SCHED_FLAG_TASK_PACKING;
struct rq *rq;
/* The pi code expects interrupts enabled */
@@ -4686,6 +4690,8 @@ static int __sched_setscheduler(struct task_struct *p,
goto change;
if (attr->sched_flags & SCHED_FLAG_UTIL_CLAMP)
goto change;
+ if (task_packing_flag)
+ goto change;
p->sched_reset_on_fork = reset_on_fork;
task_rq_unlock(rq, p, &rf);
@@ -5181,6 +5187,9 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
attr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
#endif
+ if (p->flags & PF_CAN_BE_PACKED)
+ attr.sched_flags |= SCHED_FLAG_TASK_PACKING;
+
rcu_read_unlock();
retval = sched_read_attr(uattr, &attr, size);
--
2.17.1
next prev parent reply other threads:[~2019-07-25 7:09 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-25 7:08 [RFC v4 0/8] TurboSched: A scheduler for sustaining Turbo Frequencies for longer durations Parth Shah
2019-07-25 7:08 ` Parth Shah [this message]
2019-07-25 7:08 ` [RFC v4 2/8] sched: Introduce switch to enable TurboSched mode Parth Shah
2019-07-25 7:08 ` [RFC v4 3/8] sched/core: Update turbo_sched count only when required Parth Shah
2019-07-25 7:08 ` [RFC v4 4/8] sched/fair: Define core capacity to limit task packing Parth Shah
2019-07-25 7:08 ` [RFC v4 5/8] powerpc: Define Core Capacity for POWER systems Parth Shah
2019-07-25 7:08 ` [RFC v4 6/8] sched/fair: Tune task wake-up logic to pack jitter tasks Parth Shah
2019-07-25 7:08 ` [RFC v4 7/8] sched/fair: Bound non idle core search within LLC domain Parth Shah
2019-07-25 7:08 ` [RFC v4 8/8] powerpc: Set turbo domain to NUMA node for task packing Parth Shah
2019-07-28 13:31 ` [RFC v4 0/8] TurboSched: A scheduler for sustaining Turbo Frequencies for longer durations Pavel Machek
2019-07-31 16:39 ` Parth Shah
2019-07-31 17:32 ` Pavel Machek
2019-08-02 11:12 ` Parth Shah
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20190725070857.6639-2-parth@linux.ibm.com \
--to=parth@linux.ibm.com \
--cc=daniel.lezcano@linaro.org \
--cc=dietmar.eggemann@arm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-pm@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=patrick.bellasi@arm.com \
--cc=peterz@infradead.org \
--cc=subhra.mazumdar@oracle.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).