From: "Joel Fernandes (Google)" <joel@joelfernandes.org>
To: Nishanth Aravamudan <naravamudan@digitalocean.com>,
Julien Desfossez <jdesfossez@digitalocean.com>,
Peter Zijlstra <peterz@infradead.org>,
Tim Chen <tim.c.chen@linux.intel.com>,
Vineeth Pillai <viremana@linux.microsoft.com>,
Aaron Lu <aaron.lwe@gmail.com>,
Aubrey Li <aubrey.intel@gmail.com>,
tglx@linutronix.de, linux-kernel@vger.kernel.org
Cc: mingo@kernel.org, torvalds@linux-foundation.org,
fweisbec@gmail.com, keescook@chromium.org, kerrnel@google.com,
Phil Auld <pauld@redhat.com>,
Valentin Schneider <valentin.schneider@arm.com>,
Mel Gorman <mgorman@techsingularity.net>,
Pawan Gupta <pawan.kumar.gupta@linux.intel.com>,
Paolo Bonzini <pbonzini@redhat.com>,
joel@joelfernandes.org, vineeth@bitbyteword.org,
Chen Yu <yu.c.chen@intel.com>,
Christian Brauner <christian.brauner@ubuntu.com>,
Agata Gruza <agata.gruza@intel.com>,
Antonio Gomez Iglesias <antonio.gomez.iglesias@intel.com>,
graf@amazon.com, konrad.wilk@oracle.com, dfaggioli@suse.com,
pjt@google.com, rostedt@goodmis.org, derkling@google.com,
benbjiang@tencent.com,
Alexandre Chartre <alexandre.chartre@oracle.com>,
James.Bottomley@hansenpartnership.com, OWeisse@umich.edu,
Dhaval Giani <dhaval.giani@oracle.com>,
Junaid Shahid <junaids@google.com>,
jsbarnes@google.com, chris.hyser@oracle.com,
Ben Segall <bsegall@google.com>, Josh Don <joshdon@google.com>,
Hao Luo <haoluo@google.com>,
Tom Lendacky <thomas.lendacky@amd.com>,
Aubrey Li <aubrey.li@linux.intel.com>,
"Paul E. McKenney" <paulmck@kernel.org>,
Tim Chen <tim.c.chen@intel.com>
Subject: [PATCH -tip 08/32] sched/fair: Fix forced idle sibling starvation corner case
Date: Tue, 17 Nov 2020 18:19:38 -0500 [thread overview]
Message-ID: <20201117232003.3580179-9-joel@joelfernandes.org> (raw)
In-Reply-To: <20201117232003.3580179-1-joel@joelfernandes.org>
From: Vineeth Pillai <viremana@linux.microsoft.com>
If there is only one long running local task and the sibling is
forced idle, it might not get a chance to run until a schedule
event happens on any cpu in the core.
So we check for this condition during a tick to see if a sibling
is starved and then give it a chance to schedule.
Tested-by: Julien Desfossez <jdesfossez@digitalocean.com>
Reviewed-by: Joel Fernandes (Google) <joel@joelfernandes.org>
Signed-off-by: Vineeth Pillai <viremana@linux.microsoft.com>
Signed-off-by: Julien Desfossez <jdesfossez@digitalocean.com>
Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org>
---
kernel/sched/core.c | 15 ++++++++-------
kernel/sched/fair.c | 40 ++++++++++++++++++++++++++++++++++++++++
kernel/sched/sched.h | 2 +-
3 files changed, 49 insertions(+), 8 deletions(-)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 1bd0b0bbb040..52d0e83072a4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5206,16 +5206,15 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
/* reset state */
rq->core->core_cookie = 0UL;
+ if (rq->core->core_forceidle) {
+ need_sync = true;
+ rq->core->core_forceidle = false;
+ }
for_each_cpu(i, smt_mask) {
struct rq *rq_i = cpu_rq(i);
rq_i->core_pick = NULL;
- if (rq_i->core_forceidle) {
- need_sync = true;
- rq_i->core_forceidle = false;
- }
-
if (i != cpu)
update_rq_clock(rq_i);
}
@@ -5335,8 +5334,10 @@ next_class:;
if (!rq_i->core_pick)
continue;
- if (is_task_rq_idle(rq_i->core_pick) && rq_i->nr_running)
- rq_i->core_forceidle = true;
+ if (is_task_rq_idle(rq_i->core_pick) && rq_i->nr_running &&
+ !rq_i->core->core_forceidle) {
+ rq_i->core->core_forceidle = true;
+ }
if (i == cpu) {
rq_i->core_pick = NULL;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index f53681cd263e..42965c4fd71f 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -10692,6 +10692,44 @@ static void rq_offline_fair(struct rq *rq)
#endif /* CONFIG_SMP */
+#ifdef CONFIG_SCHED_CORE
+static inline bool
+__entity_slice_used(struct sched_entity *se, int min_nr_tasks)
+{
+ u64 slice = sched_slice(cfs_rq_of(se), se);
+ u64 rtime = se->sum_exec_runtime - se->prev_sum_exec_runtime;
+
+ return (rtime * min_nr_tasks > slice);
+}
+
+#define MIN_NR_TASKS_DURING_FORCEIDLE 2
+static inline void task_tick_core(struct rq *rq, struct task_struct *curr)
+{
+ if (!sched_core_enabled(rq))
+ return;
+
+ /*
+ * If runqueue has only one task which used up its slice and
+ * if the sibling is forced idle, then trigger schedule to
+ * give forced idle task a chance.
+ *
+ * sched_slice() considers only this active rq and it gets the
+ * whole slice. But during force idle, we have siblings acting
+ * like a single runqueue and hence we need to consider runnable
+ * tasks on this cpu and the forced idle cpu. Ideally, we should
+ * go through the forced idle rq, but that would be a perf hit.
+ * We can assume that the forced idle cpu has atleast
+ * MIN_NR_TASKS_DURING_FORCEIDLE - 1 tasks and use that to check
+ * if we need to give up the cpu.
+ */
+ if (rq->core->core_forceidle && rq->cfs.nr_running == 1 &&
+ __entity_slice_used(&curr->se, MIN_NR_TASKS_DURING_FORCEIDLE))
+ resched_curr(rq);
+}
+#else
+static inline void task_tick_core(struct rq *rq, struct task_struct *curr) {}
+#endif
+
/*
* scheduler tick hitting a task of our scheduling class.
*
@@ -10715,6 +10753,8 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
update_misfit_status(curr, rq);
update_overutilized_status(task_rq(curr));
+
+ task_tick_core(rq, curr);
}
/*
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 63b28e1843ee..be656ca8693d 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1069,12 +1069,12 @@ struct rq {
unsigned int core_enabled;
unsigned int core_sched_seq;
struct rb_root core_tree;
- unsigned char core_forceidle;
/* shared state */
unsigned int core_task_seq;
unsigned int core_pick_seq;
unsigned long core_cookie;
+ unsigned char core_forceidle;
#endif
};
--
2.29.2.299.gdc1121823c-goog
next prev parent reply other threads:[~2020-11-17 23:22 UTC|newest]
Thread overview: 150+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-17 23:19 [PATCH -tip 00/32] Core scheduling (v9) Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 01/32] sched: Wrap rq::lock access Joel Fernandes (Google)
2020-11-19 23:31 ` Singh, Balbir
2020-11-20 16:55 ` Joel Fernandes
2020-11-22 8:52 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 02/32] sched: Introduce sched_class::pick_task() Joel Fernandes (Google)
2020-11-19 23:56 ` Singh, Balbir
2020-11-20 16:58 ` Joel Fernandes
2020-11-25 23:19 ` Balbir Singh
2020-11-25 16:28 ` Vincent Guittot
2020-11-26 9:07 ` Peter Zijlstra
2020-11-26 10:17 ` Vincent Guittot
2020-11-26 12:40 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 03/32] sched/fair: Fix pick_task_fair crashes due to empty rbtree Joel Fernandes (Google)
2020-11-20 10:15 ` Singh, Balbir
2020-11-20 18:11 ` Vineeth Pillai
2020-11-23 22:31 ` Balbir Singh
2020-11-24 8:31 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 04/32] sched: Core-wide rq->lock Joel Fernandes (Google)
2020-11-22 9:11 ` Balbir Singh
2020-11-24 8:16 ` Peter Zijlstra
2020-11-26 0:35 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 05/32] sched/fair: Add a few assertions Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 06/32] sched: Basic tracking of matching tasks Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 07/32] sched: Add core wide task selection and scheduling Joel Fernandes (Google)
2020-11-17 23:19 ` Joel Fernandes (Google) [this message]
2020-11-22 10:35 ` [PATCH -tip 08/32] sched/fair: Fix forced idle sibling starvation corner case Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 09/32] sched/fair: Snapshot the min_vruntime of CPUs on force idle Joel Fernandes (Google)
2020-11-22 11:44 ` Balbir Singh
2020-11-23 12:31 ` Vineeth Pillai
2020-11-23 23:31 ` Balbir Singh
2020-11-24 9:09 ` Peter Zijlstra
2020-11-25 23:17 ` Balbir Singh
2020-11-26 8:23 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 10/32] sched: Fix priority inversion of cookied task with sibling Joel Fernandes (Google)
2020-11-22 22:41 ` Balbir Singh
2020-11-24 18:30 ` Joel Fernandes
2020-11-25 23:05 ` Balbir Singh
2020-11-26 8:29 ` Peter Zijlstra
2020-11-26 22:27 ` Balbir Singh
2020-12-01 17:49 ` Joel Fernandes
2020-11-17 23:19 ` [PATCH -tip 11/32] sched: Enqueue task into core queue only after vruntime is updated Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 12/32] sched: Simplify the core pick loop for optimized case Joel Fernandes (Google)
2020-11-24 12:04 ` Peter Zijlstra
2020-11-24 17:04 ` Joel Fernandes
2020-11-25 8:37 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 13/32] sched: Trivial forced-newidle balancer Joel Fernandes (Google)
2020-11-23 4:38 ` Balbir Singh
2020-11-23 15:07 ` Li, Aubrey
2020-11-23 23:35 ` Balbir Singh
2020-11-24 0:32 ` Li, Aubrey
2020-11-25 21:28 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 14/32] sched: migration changes for core scheduling Joel Fernandes (Google)
2020-11-22 23:54 ` Balbir Singh
2020-11-23 4:36 ` Li, Aubrey
2020-11-24 15:42 ` Peter Zijlstra
2020-11-25 3:12 ` Li, Aubrey
2020-11-25 22:57 ` Balbir Singh
2020-11-26 3:20 ` Li, Aubrey
2020-11-26 8:32 ` Balbir Singh
2020-11-26 9:26 ` Li, Aubrey
2020-11-30 9:33 ` Balbir Singh
2020-11-30 12:29 ` Li, Aubrey
2020-12-02 14:09 ` Li, Aubrey
2020-12-03 1:06 ` Li, Aubrey
2020-11-30 10:35 ` Vincent Guittot
2020-11-30 12:32 ` Li, Aubrey
2020-11-17 23:19 ` [PATCH -tip 15/32] sched: Improve snapshotting of min_vruntime for CGroups Joel Fernandes (Google)
2020-11-24 10:27 ` Peter Zijlstra
2020-11-24 17:07 ` Joel Fernandes
2020-11-25 8:41 ` Peter Zijlstra
2020-11-24 10:41 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 16/32] irq_work: Cleanup Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 17/32] arch/x86: Add a new TIF flag for untrusted tasks Joel Fernandes (Google)
2020-11-23 5:18 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 18/32] kernel/entry: Add support for core-wide protection of kernel-mode Joel Fernandes (Google)
2020-11-24 16:09 ` Peter Zijlstra
2020-11-24 17:52 ` Joel Fernandes
2020-11-25 9:37 ` Peter Zijlstra
2020-12-01 17:55 ` Joel Fernandes
2020-11-26 5:37 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 19/32] entry/idle: Enter and exit kernel protection during idle entry and exit Joel Fernandes (Google)
2020-11-24 16:13 ` Peter Zijlstra
2020-11-24 18:03 ` Joel Fernandes
2020-11-25 8:49 ` Peter Zijlstra
2020-12-01 18:24 ` Joel Fernandes
2020-11-17 23:19 ` [PATCH -tip 20/32] entry/kvm: Protect the kernel when entering from guest Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 21/32] sched: CGroup tagging interface for core scheduling Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 22/32] sched: Split the cookie and setup per-task cookie on fork Joel Fernandes (Google)
2020-11-25 11:07 ` Peter Zijlstra
2020-12-01 18:56 ` Joel Fernandes
2020-11-25 11:10 ` Peter Zijlstra
2020-12-01 19:20 ` Joel Fernandes
2020-12-01 19:34 ` Peter Zijlstra
2020-12-02 6:36 ` Josh Don
2020-12-02 7:54 ` Peter Zijlstra
2020-12-04 0:20 ` Josh Don
2020-12-06 17:49 ` Joel Fernandes
2020-11-25 11:11 ` Peter Zijlstra
2020-12-01 19:16 ` Joel Fernandes
2020-11-25 11:15 ` Peter Zijlstra
2020-12-01 19:11 ` Joel Fernandes
2020-12-01 19:20 ` Peter Zijlstra
2020-12-06 18:15 ` Joel Fernandes
2020-11-25 12:54 ` Peter Zijlstra
2020-12-01 18:38 ` Joel Fernandes
2020-11-25 13:03 ` Peter Zijlstra
2020-12-01 18:52 ` Joel Fernandes
2020-11-30 23:05 ` Balbir Singh
2020-11-17 23:19 ` [PATCH -tip 23/32] sched: Add a per-thread core scheduling interface Joel Fernandes (Google)
2020-11-25 13:08 ` Peter Zijlstra
2020-12-01 19:36 ` Joel Fernandes
2020-12-02 21:47 ` Chris Hyser
2020-12-02 23:13 ` chris hyser
2020-12-06 17:34 ` Joel Fernandes
2020-12-07 21:48 ` chris hyser
2020-12-09 18:52 ` Chris Hyser
2020-12-14 19:31 ` Joel Fernandes
2020-12-14 19:44 ` chris hyser
2020-12-14 23:25 ` Joel Fernandes
2020-12-15 14:56 ` chris hyser
2020-12-15 16:23 ` chris hyser
2020-12-15 18:13 ` Dhaval Giani
2020-12-16 0:35 ` Joel Fernandes
2020-11-17 23:19 ` [PATCH -tip 24/32] sched: Release references to the per-task cookie on exit Joel Fernandes (Google)
2020-11-25 13:03 ` Peter Zijlstra
2020-11-17 23:19 ` [PATCH -tip 25/32] sched: Refactor core cookie into struct Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 26/32] sched: Add a second-level tag for nested CGroup usecase Joel Fernandes (Google)
2020-11-25 13:42 ` Peter Zijlstra
2020-11-30 23:10 ` Balbir Singh
2020-12-01 20:08 ` Joel Fernandes
2020-12-02 6:18 ` Josh Don
2020-12-02 8:02 ` Peter Zijlstra
2020-12-02 18:53 ` Tejun Heo
2020-12-04 0:51 ` Josh Don
2020-12-04 15:45 ` Tejun Heo
2020-11-17 23:19 ` [PATCH -tip 27/32] sched/debug: Add CGroup node for printing group cookie if SCHED_DEBUG Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 28/32] kselftest: Add tests for core-sched interface Joel Fernandes (Google)
2020-11-17 23:19 ` [PATCH -tip 29/32] sched: Move core-scheduler interfacing code to a new file Joel Fernandes (Google)
2020-11-17 23:20 ` [PATCH -tip 30/32] Documentation: Add core scheduling documentation Joel Fernandes (Google)
2020-11-17 23:20 ` [PATCH -tip 31/32] sched: Add a coresched command line option Joel Fernandes (Google)
2020-11-19 23:39 ` Randy Dunlap
2020-11-25 13:45 ` Peter Zijlstra
2020-11-26 0:11 ` Balbir Singh
2020-11-17 23:20 ` [PATCH -tip 32/32] sched: Debug bits Joel Fernandes (Google)
2020-12-01 0:21 ` Balbir Singh
2021-01-15 15:10 ` Joel Fernandes
2020-11-24 11:48 ` [PATCH -tip 00/32] Core scheduling (v9) Vincent Guittot
2020-11-24 15:08 ` Joel Fernandes
2020-12-03 6:16 ` Ning, Hongyu
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=20201117232003.3580179-9-joel@joelfernandes.org \
--to=joel@joelfernandes.org \
--cc=James.Bottomley@hansenpartnership.com \
--cc=OWeisse@umich.edu \
--cc=aaron.lwe@gmail.com \
--cc=agata.gruza@intel.com \
--cc=alexandre.chartre@oracle.com \
--cc=antonio.gomez.iglesias@intel.com \
--cc=aubrey.intel@gmail.com \
--cc=aubrey.li@linux.intel.com \
--cc=benbjiang@tencent.com \
--cc=bsegall@google.com \
--cc=chris.hyser@oracle.com \
--cc=christian.brauner@ubuntu.com \
--cc=derkling@google.com \
--cc=dfaggioli@suse.com \
--cc=dhaval.giani@oracle.com \
--cc=fweisbec@gmail.com \
--cc=graf@amazon.com \
--cc=haoluo@google.com \
--cc=jdesfossez@digitalocean.com \
--cc=joshdon@google.com \
--cc=jsbarnes@google.com \
--cc=junaids@google.com \
--cc=keescook@chromium.org \
--cc=kerrnel@google.com \
--cc=konrad.wilk@oracle.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mingo@kernel.org \
--cc=naravamudan@digitalocean.com \
--cc=pauld@redhat.com \
--cc=paulmck@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=pjt@google.com \
--cc=rostedt@goodmis.org \
--cc=tglx@linutronix.de \
--cc=thomas.lendacky@amd.com \
--cc=tim.c.chen@intel.com \
--cc=tim.c.chen@linux.intel.com \
--cc=torvalds@linux-foundation.org \
--cc=valentin.schneider@arm.com \
--cc=vineeth@bitbyteword.org \
--cc=viremana@linux.microsoft.com \
--cc=yu.c.chen@intel.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).