Skip to content

sched: Add on_rq states and remove several double rq locks

Kirill Tkhai lkml 2 versions – New

Get series with b4
b4 am 20140730213219.27604.11218.stgit@localhost

Versions newest first · linked by author and title

  1. v3 Latest5 patches 0 repliesNew
  2. v25 patches 12 repliesSuperseded

Patches in v3 No applies recorded yet

#Subject and filesSizeRepliesApplied
1/5sched: Wrapper for checking task_struct::on_rqkernel/sched/core.c kernel/sched/deadline.c kernel/sched/fair.c +3 more+75 -680 replies
2/5sched: Teach scheduler to understand ONRQ_MIGRATING statekernel/sched/core.c kernel/sched/sched.h+17 -30 replies
3/5sched: Remove double_rq_lock() from __migrate_task()kernel/sched/core.c+15 -80 replies
4/5sched/fair: Remove double_lock_balance() from active_load_balance_cpu_stop()kernel/sched/fair.c+38 -170 replies
5/5sched/fair: Remove double_lock_balance() from load_balance()kernel/sched/fair.c+70 -290 replies

Reviews trailers per patch

No Reviewed-by, Acked-by or Tested-by trailers for v3 yet.

Read the v3 thread

Cover letter [PATCH v3 0/5] sched: Add on_rq states and remove several double rq locks

This series aims to get rid of some places where locks of two RQs are held at the same time.

Patch [1/5] is a preparation/cleanup. It replaces old (task_struct::on_rq == 1) with new (task_struct::on_rq == ONRQ_QUEUED) everywhere. No functional changes.

Patch [2/5] is main in the series. It introduces new ONRQ_MIGRATING state and teaches scheduler to understand it (we need little changes in try_to_wake_up() and task_rq_lock() family). This will be used in the following way:

        (we are changing task's rq)

        raw_spin_lock(&src_rq->lock);

	p = ...; /* Some src_rq task */

        dequeue_task(src_rq, p, 0);
        p->on_rq = ONRQ_MIGRATING;
        set_task_cpu(p, dst_cpu);
        raw_spin_unlock(&src_rq->lock);

	/*
	 * Now p os dequeued, and both
         * RQ locks are unlocked, but
	 * its on_rq is not zero.
	 * Nobody can manipulate p
	 * while it's migrating,
	 * even when spinlocks are
	 * unlocked.
	 */

        raw_spin_lock(&dst_rq->lock);
        p->on_rq = ONRQ_QUEUED;
        enqueue_task(dst_rq, p, 0);
        raw_spin_unlock(&dst_rq->lock);

Patches [3,4,5/5] remove double locks and use new ONRQ_MIGRATING state. They allow unlocked using of 3-4 function, which looks safe for me.

The profit is double_rq_lock() is not need now, so we reduce the total time when RQs are locked.

---

Kirill Tkhai (5):
sched: Wrapper for checking task_struct::on_rq
sched: Teach scheduler to understand ONRQ_MIGRATING state
sched: Remove double_rq_lock() from __migrate_task() sched/fair: Remove double_lock_balance() from active_load_balance_cpu_stop() sched/fair: Remove double_lock_balance() from load_balance()

 kernel/sched/core.c      |  115 +++++++++++++++++--------------
 kernel/sched/deadline.c  |   14 ++--
 kernel/sched/fair.c      |  172 +++++++++++++++++++++++++++++++---------------
 kernel/sched/rt.c        |   16 ++--
 kernel/sched/sched.h     |   13 +++
 kernel/sched/stop_task.c |    2 -
 6 files changed, 211 insertions(+), 121 deletions(-)

--