From: "Jan H. Schönherr" <jschoenh@amazon.de>
To: Ingo Molnar <mingo@redhat.com>, Peter Zijlstra <peterz@infradead.org>
Cc: "Jan H. Schönherr" <jschoenh@amazon.de>, linux-kernel@vger.kernel.org
Subject: [RFC 57/60] cosched: Add sysfs interface to configure coscheduling on cgroups
Date: Fri, 7 Sep 2018 23:40:44 +0200 [thread overview]
Message-ID: <20180907214047.26914-58-jschoenh@amazon.de> (raw)
In-Reply-To: <20180907214047.26914-1-jschoenh@amazon.de>
Add the sysfs interface to configure the scheduling domain hierarchy
level at which coscheduling should happen for a cgroup. By default,
task groups are created with a value of zero corresponding to regular
task groups without any coscheduling.
Note, that you cannot specify a value that goes beyond that of the
root task group. The value for the root task group cannot be configured
via this interface. It has to be configured with a command line
argument, which will be added later.
The function sdrq_update_root() will be filled in a follow-up commit.
Signed-off-by: Jan H. Schönherr <jschoenh@amazon.de>
---
kernel/sched/core.c | 44 +++++++++++++++++++++++++++++++++++++++++
kernel/sched/cosched.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++
kernel/sched/sched.h | 4 ++++
3 files changed, 101 insertions(+)
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 75de3b83a8c6..ad2ff9bc535c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -6336,6 +6336,9 @@ void sched_offline_group(struct task_group *tg)
{
unsigned long flags;
+ /* Don't let offlining/destruction worry about coscheduling aspects */
+ cosched_set_scheduled(tg, 0);
+
/* End participation in shares distribution: */
unregister_fair_sched_group(tg);
@@ -6529,7 +6532,33 @@ static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
return (u64) scale_load_down(tg->shares);
}
+#endif /* CONFIG_FAIR_GROUP_SCHED */
+
+#ifdef CONFIG_COSCHEDULING
+static int cpu_scheduled_write_u64(struct cgroup_subsys_state *css, struct cftype *cftype,
+ u64 val)
+{
+ struct task_group *tg = css_tg(css);
+
+ if (tg == &root_task_group)
+ return -EACCES;
+
+ if (val > root_task_group.scheduled)
+ return -EINVAL;
+
+ cosched_set_scheduled(tg, val);
+ return 0;
+}
+static u64 cpu_scheduled_read_u64(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+ struct task_group *tg = css_tg(css);
+
+ return cosched_get_scheduled(tg);
+}
+#endif /* !CONFIG_COSCHEDULING */
+
+#ifdef CONFIG_FAIR_GROUP_SCHED
#ifdef CONFIG_CFS_BANDWIDTH
static DEFINE_MUTEX(cfs_constraints_mutex);
@@ -6825,6 +6854,13 @@ static struct cftype cpu_legacy_files[] = {
.write_u64 = cpu_shares_write_u64,
},
#endif
+#ifdef CONFIG_COSCHEDULING
+ {
+ .name = "scheduled",
+ .read_u64 = cpu_scheduled_read_u64,
+ .write_u64 = cpu_scheduled_write_u64,
+ },
+#endif
#ifdef CONFIG_CFS_BANDWIDTH
{
.name = "cfs_quota_us",
@@ -7012,6 +7048,14 @@ static struct cftype cpu_files[] = {
.write_s64 = cpu_weight_nice_write_s64,
},
#endif
+#ifdef CONFIG_COSCHEDULING
+ /* FIXME: This is not conform to cgroup-v2 conventions. */
+ {
+ .name = "scheduled",
+ .read_u64 = cpu_scheduled_read_u64,
+ .write_u64 = cpu_scheduled_write_u64,
+ },
+#endif
#ifdef CONFIG_CFS_BANDWIDTH
{
.name = "max",
diff --git a/kernel/sched/cosched.c b/kernel/sched/cosched.c
index f2d51079b3db..7c8b8c8d2814 100644
--- a/kernel/sched/cosched.c
+++ b/kernel/sched/cosched.c
@@ -515,6 +515,59 @@ void cosched_offline_group(struct task_group *tg)
list_del_rcu(&cfs->sdrq.tg_siblings);
}
+static void sdrq_update_root(struct sdrq *sdrq)
+{
+ /* TBD */
+}
+
+void cosched_set_scheduled(struct task_group *tg, int level)
+{
+ struct cfs_rq *cfs_rq;
+ unsigned long flags;
+
+ raw_spin_lock_irqsave(&tg->lock, flags);
+
+ /*
+ * Update the is_root-fields of all hierarchical CFS runqueues in this
+ * task group. To avoid repetitive enqueues and dequeues on every level
+ * change, we chose pre- or post-order traversal.
+ */
+ if (level > tg->scheduled) {
+ /*
+ * roots move upwards: start reconfiguration at the top, so
+ * that everything is dequeued/enqueued only when we reach
+ * the previous scheduling level.
+ */
+ tg->scheduled = level;
+ taskgroup_for_each_cfsrq_topdown(tg, cfs_rq)
+ sdrq_update_root(&cfs_rq->sdrq);
+ }
+ if (level < tg->scheduled) {
+ /*
+ * roots move downwards: start reconfiguration at the bottom,
+ * so that we do the dequeuing/enqueuing immediately, when we
+ * reach the new scheduling level.
+ */
+ tg->scheduled = level;
+ taskgroup_for_each_cfsrq(tg, cfs_rq)
+ sdrq_update_root(&cfs_rq->sdrq);
+ }
+
+ raw_spin_unlock_irqrestore(&tg->lock, flags);
+}
+
+int cosched_get_scheduled(struct task_group *tg)
+{
+ unsigned long flags;
+ int level;
+
+ raw_spin_lock_irqsave(&tg->lock, flags);
+ level = tg->scheduled;
+ raw_spin_unlock_irqrestore(&tg->lock, flags);
+
+ return level;
+}
+
/*****************************************************************************
* Locking related functions
*****************************************************************************/
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index f6146feb7e55..e257451e05a5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1212,6 +1212,8 @@ void cosched_init_sdrq(struct task_group *tg, struct cfs_rq *cfs,
struct cfs_rq *sd_parent, struct cfs_rq *tg_parent);
void cosched_online_group(struct task_group *tg);
void cosched_offline_group(struct task_group *tg);
+void cosched_set_scheduled(struct task_group *tg, int level);
+int cosched_get_scheduled(struct task_group *tg);
struct rq *rq_lock_owned(struct rq *rq, struct rq_owner_flags *orf);
void rq_unlock_owned(struct rq *rq, struct rq_owner_flags *orf);
void rq_chain_init(struct rq_chain *rc, struct rq *rq);
@@ -1226,6 +1228,8 @@ static inline void cosched_init_sdrq(struct task_group *tg, struct cfs_rq *cfs,
struct cfs_rq *tg_parent) { }
static inline void cosched_online_group(struct task_group *tg) { }
static inline void cosched_offline_group(struct task_group *tg) { }
+static inline void cosched_set_scheduled(struct task_group *tg, int level) { }
+static inline int cosched_get_scheduled(struct task_group *tg) { return 0; }
static inline struct rq *rq_lock_owned(struct rq *rq, struct rq_owner_flags *orf) { return rq; }
static inline void rq_unlock_owned(struct rq *rq, struct rq_owner_flags *orf) { }
static inline void rq_chain_init(struct rq_chain *rc, struct rq *rq) { }
--
2.9.3.1.gcba166c.dirty
next prev parent reply other threads:[~2018-09-07 21:43 UTC|newest]
Thread overview: 114+ messages / expand[flat|nested] mbox.gz Atom feed top
2018-09-07 21:39 [RFC 00/60] Coscheduling for Linux Jan H. Schönherr
2018-09-07 21:39 ` [RFC 01/60] sched: Store task_group->se[] pointers as part of cfs_rq Jan H. Schönherr
2018-09-07 21:39 ` [RFC 02/60] sched: Introduce set_entity_cfs() to place a SE into a certain CFS runqueue Jan H. Schönherr
2018-09-07 21:39 ` [RFC 03/60] sched: Setup sched_domain_shared for all sched_domains Jan H. Schönherr
2018-09-07 21:39 ` [RFC 04/60] sched: Replace sd_numa_mask() hack with something sane Jan H. Schönherr
2018-09-07 21:39 ` [RFC 05/60] sched: Allow to retrieve the sched_domain_topology Jan H. Schönherr
2018-09-07 21:39 ` [RFC 06/60] sched: Add a lock-free variant of resched_cpu() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 07/60] sched: Reduce dependencies of init_tg_cfs_entry() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 08/60] sched: Move init_entity_runnable_average() into init_tg_cfs_entry() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 09/60] sched: Do not require a CFS in init_tg_cfs_entry() Jan H. Schönherr
2018-09-07 21:39 ` [RFC 10/60] sched: Use parent_entity() in more places Jan H. Schönherr
2018-09-07 21:39 ` [RFC 11/60] locking/lockdep: Increase number of supported lockdep subclasses Jan H. Schönherr
2018-09-07 21:39 ` [RFC 12/60] locking/lockdep: Make cookie generator accessible Jan H. Schönherr
2018-09-07 21:40 ` [RFC 13/60] sched: Remove useless checks for root task-group Jan H. Schönherr
2018-09-07 21:40 ` [RFC 14/60] sched: Refactor sync_throttle() to accept a CFS runqueue as argument Jan H. Schönherr
2018-09-07 21:40 ` [RFC 15/60] sched: Introduce parent_cfs_rq() and use it Jan H. Schönherr
2018-09-07 21:40 ` [RFC 16/60] sched: Preparatory code movement Jan H. Schönherr
2018-09-07 21:40 ` [RFC 17/60] sched: Introduce and use generic task group CFS traversal functions Jan H. Schönherr
2018-09-07 21:40 ` [RFC 18/60] sched: Fix return value of SCHED_WARN_ON() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 19/60] sched: Add entity variants of enqueue_task_fair() and dequeue_task_fair() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 20/60] sched: Let {en,de}queue_entity_fair() work with a varying amount of tasks Jan H. Schönherr
2018-09-07 21:40 ` [RFC 21/60] sched: Add entity variants of put_prev_task_fair() and set_curr_task_fair() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 22/60] cosched: Add config option for coscheduling support Jan H. Schönherr
2018-09-07 21:40 ` [RFC 23/60] cosched: Add core data structures for coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 24/60] cosched: Do minimal pre-SMP coscheduler initialization Jan H. Schönherr
2018-09-07 21:40 ` [RFC 25/60] cosched: Prepare scheduling domain topology for coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 26/60] cosched: Construct runqueue hierarchy Jan H. Schönherr
2018-09-07 21:40 ` [RFC 27/60] cosched: Add some small helper functions for later use Jan H. Schönherr
2018-09-07 21:40 ` [RFC 28/60] cosched: Add is_sd_se() to distinguish SD-SEs from TG-SEs Jan H. Schönherr
2018-09-07 21:40 ` [RFC 29/60] cosched: Adjust code reflecting on the total number of CFS tasks on a CPU Jan H. Schönherr
2018-09-07 21:40 ` [RFC 30/60] cosched: Disallow share modification on task groups for now Jan H. Schönherr
2018-09-07 21:40 ` [RFC 31/60] cosched: Don't disable idle tick " Jan H. Schönherr
2018-09-07 21:40 ` [RFC 32/60] cosched: Specialize parent_cfs_rq() for hierarchical runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 33/60] cosched: Allow resched_curr() to be called " Jan H. Schönherr
2018-09-07 21:40 ` [RFC 34/60] cosched: Add rq_of() variants for different use cases Jan H. Schönherr
2018-09-07 21:40 ` [RFC 35/60] cosched: Adjust rq_lock() functions to work with hierarchical runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 36/60] cosched: Use hrq_of() for rq_clock() and rq_clock_task() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 37/60] cosched: Use hrq_of() for (indirect calls to) ___update_load_sum() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 38/60] cosched: Skip updates on non-CPU runqueues in cfs_rq_util_change() Jan H. Schönherr
2018-09-07 21:40 ` [RFC 39/60] cosched: Adjust task group management for hierarchical runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 40/60] cosched: Keep track of task group hierarchy within each SD-RQ Jan H. Schönherr
2018-09-07 21:40 ` [RFC 41/60] cosched: Introduce locking for leader activities Jan H. Schönherr
2018-09-07 21:40 ` [RFC 42/60] cosched: Introduce locking for (mostly) enqueuing and dequeuing Jan H. Schönherr
2018-09-07 21:40 ` [RFC 43/60] cosched: Add for_each_sched_entity() variant for owned entities Jan H. Schönherr
2018-09-07 21:40 ` [RFC 44/60] cosched: Perform various rq_of() adjustments in scheduler code Jan H. Schönherr
2018-09-07 21:40 ` [RFC 45/60] cosched: Continue to account all load on per-CPU runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 46/60] cosched: Warn on throttling attempts of non-CPU runqueues Jan H. Schönherr
2018-09-07 21:40 ` [RFC 47/60] cosched: Adjust SE traversal and locking for common leader activities Jan H. Schönherr
2018-09-07 21:40 ` [RFC 48/60] cosched: Adjust SE traversal and locking for yielding and buddies Jan H. Schönherr
2018-09-07 21:40 ` [RFC 49/60] cosched: Adjust locking for enqueuing and dequeueing Jan H. Schönherr
2018-09-07 21:40 ` [RFC 50/60] cosched: Propagate load changes across hierarchy levels Jan H. Schönherr
2018-09-07 21:40 ` [RFC 51/60] cosched: Hacky work-around to avoid observing zero weight SD-SE Jan H. Schönherr
2018-09-07 21:40 ` [RFC 52/60] cosched: Support SD-SEs in enqueuing and dequeuing Jan H. Schönherr
2018-09-07 21:40 ` [RFC 53/60] cosched: Prevent balancing related functions from crossing hierarchy levels Jan H. Schönherr
2018-09-07 21:40 ` [RFC 54/60] cosched: Support idling in a coscheduled set Jan H. Schönherr
2018-09-07 21:40 ` [RFC 55/60] cosched: Adjust task selection for coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 56/60] cosched: Adjust wakeup preemption rules " Jan H. Schönherr
2018-09-07 21:40 ` Jan H. Schönherr [this message]
2018-09-07 21:40 ` [RFC 58/60] cosched: Switch runqueues between regular scheduling and coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 59/60] cosched: Handle non-atomicity during switches to and from coscheduling Jan H. Schönherr
2018-09-07 21:40 ` [RFC 60/60] cosched: Add command line argument to enable coscheduling Jan H. Schönherr
2018-09-10 2:50 ` Randy Dunlap
2018-09-12 0:24 ` [RFC 00/60] Coscheduling for Linux Nishanth Aravamudan
2018-09-12 19:34 ` Jan H. Schönherr
2018-09-12 23:15 ` Nishanth Aravamudan
2018-09-13 11:31 ` Jan H. Schönherr
2018-09-13 18:16 ` Nishanth Aravamudan
2018-09-12 23:18 ` Jan H. Schönherr
2018-09-13 3:05 ` Nishanth Aravamudan
2018-09-13 19:19 ` [RFC 61/60] cosched: Accumulated fixes and improvements Jan H. Schönherr
2018-09-26 17:25 ` Nishanth Aravamudan
2018-09-26 21:05 ` Nishanth Aravamudan
2018-10-01 9:13 ` Jan H. Schönherr
2018-09-14 11:12 ` [RFC 00/60] Coscheduling for Linux Peter Zijlstra
2018-09-14 16:25 ` Jan H. Schönherr
2018-09-15 8:48 ` Task group cleanups and optimizations (was: Re: [RFC 00/60] Coscheduling for Linux) Jan H. Schönherr
2018-09-17 9:48 ` Peter Zijlstra
2018-09-18 13:22 ` Jan H. Schönherr
2018-09-18 13:38 ` Peter Zijlstra
2018-09-18 13:54 ` Jan H. Schönherr
2018-09-18 13:42 ` Peter Zijlstra
2018-09-18 14:35 ` Rik van Riel
2018-09-19 9:23 ` Jan H. Schönherr
2018-11-23 16:51 ` Frederic Weisbecker
2018-12-04 13:23 ` Jan H. Schönherr
2018-09-17 11:33 ` [RFC 00/60] Coscheduling for Linux Peter Zijlstra
2018-11-02 22:13 ` Nishanth Aravamudan
2018-09-17 12:25 ` Peter Zijlstra
2018-09-26 9:58 ` Jan H. Schönherr
2018-09-27 18:36 ` Subhra Mazumdar
2018-11-23 16:29 ` Frederic Weisbecker
2018-09-17 13:37 ` Peter Zijlstra
2018-09-26 9:35 ` Jan H. Schönherr
2018-09-18 14:40 ` Rik van Riel
2018-09-24 15:23 ` Jan H. Schönherr
2018-09-24 18:01 ` Rik van Riel
2018-09-18 0:33 ` Subhra Mazumdar
2018-09-18 11:44 ` Jan H. Schönherr
2018-09-19 21:53 ` Subhra Mazumdar
2018-09-24 15:43 ` Jan H. Schönherr
2018-09-27 18:12 ` Subhra Mazumdar
2018-10-04 13:29 ` Jon Masters
2018-10-17 2:09 ` Frederic Weisbecker
2018-10-19 11:40 ` Jan H. Schönherr
2018-10-19 14:52 ` Frederic Weisbecker
2018-10-19 15:16 ` Rik van Riel
2018-10-19 15:33 ` Frederic Weisbecker
2018-10-19 15:45 ` Rik van Riel
2018-10-19 19:07 ` Jan H. Schönherr
2018-10-19 0:26 ` Subhra Mazumdar
2018-10-26 23:44 ` Jan H. Schönherr
2018-10-29 22:52 ` Subhra Mazumdar
2018-10-26 23:05 ` Subhra Mazumdar
2018-10-27 0:07 ` Jan H. Schönherr
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=20180907214047.26914-58-jschoenh@amazon.de \
--to=jschoenh@amazon.de \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=peterz@infradead.org \
/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).