linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Marcelo Tosatti <mtosatti@redhat.com>
To: Frederic Weisbecker <frederic@kernel.org>
Cc: linux-kernel@vger.kernel.org, Marcelo Tosatti <mtosatti@redhat.com>
Subject: [patch 1/2] nohz: try to avoid IPI when configuring per-CPU posix timer
Date: Tue, 25 Aug 2020 15:41:48 -0300	[thread overview]
Message-ID: <20200825184414.442457749@fuller.cnet> (raw)
In-Reply-To: 20200825184147.948670309@fuller.cnet

When enabling per-CPU posix timers, an IPI to nohz_full CPUs might be
performed (to re-read the dependencies and possibly not re-enter
nohz_full on a given CPU).

A common case is for applications that run on nohz_full= CPUs 
to not use POSIX timers (eg DPDK). This patch skips the IPI 
in case the task allowed mask does not intersect with nohz_full= CPU mask,
when going through tick_nohz_dep_set_signal.

This reduces interruptions to nohz_full= CPUs.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

---
 include/linux/tick.h           |   11 +++++++----
 kernel/time/posix-cpu-timers.c |    4 ++--
 kernel/time/tick-sched.c       |   27 +++++++++++++++++++++++++--
 3 files changed, 34 insertions(+), 8 deletions(-)

Index: linux-2.6/include/linux/tick.h
===================================================================
--- linux-2.6.orig/include/linux/tick.h
+++ linux-2.6/include/linux/tick.h
@@ -207,7 +207,8 @@ extern void tick_nohz_dep_set_task(struc
 				   enum tick_dep_bits bit);
 extern void tick_nohz_dep_clear_task(struct task_struct *tsk,
 				     enum tick_dep_bits bit);
-extern void tick_nohz_dep_set_signal(struct signal_struct *signal,
+extern void tick_nohz_dep_set_signal(struct task_struct *tsk,
+				     struct signal_struct *signal,
 				     enum tick_dep_bits bit);
 extern void tick_nohz_dep_clear_signal(struct signal_struct *signal,
 				       enum tick_dep_bits bit);
@@ -252,11 +253,12 @@ static inline void tick_dep_clear_task(s
 	if (tick_nohz_full_enabled())
 		tick_nohz_dep_clear_task(tsk, bit);
 }
-static inline void tick_dep_set_signal(struct signal_struct *signal,
+static inline void tick_dep_set_signal(struct task_struct *tsk,
+				       struct signal_struct *signal,
 				       enum tick_dep_bits bit)
 {
 	if (tick_nohz_full_enabled())
-		tick_nohz_dep_set_signal(signal, bit);
+		tick_nohz_dep_set_signal(tsk, signal, bit);
 }
 static inline void tick_dep_clear_signal(struct signal_struct *signal,
 					 enum tick_dep_bits bit)
@@ -284,7 +286,8 @@ static inline void tick_dep_set_task(str
 				     enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_task(struct task_struct *tsk,
 				       enum tick_dep_bits bit) { }
-static inline void tick_dep_set_signal(struct signal_struct *signal,
+static inline void tick_dep_set_signal(struct task_struct *tsk,
+				       struct signal_struct *signal,
 				       enum tick_dep_bits bit) { }
 static inline void tick_dep_clear_signal(struct signal_struct *signal,
 					 enum tick_dep_bits bit) { }
Index: linux-2.6/kernel/time/posix-cpu-timers.c
===================================================================
--- linux-2.6.orig/kernel/time/posix-cpu-timers.c
+++ linux-2.6/kernel/time/posix-cpu-timers.c
@@ -523,7 +523,7 @@ static void arm_timer(struct k_itimer *t
 	if (CPUCLOCK_PERTHREAD(timer->it_clock))
 		tick_dep_set_task(p, TICK_DEP_BIT_POSIX_TIMER);
 	else
-		tick_dep_set_signal(p->signal, TICK_DEP_BIT_POSIX_TIMER);
+		tick_dep_set_signal(p, p->signal, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 /*
@@ -1358,7 +1358,7 @@ void set_process_cpu_timer(struct task_s
 	if (*newval < *nextevt)
 		*nextevt = *newval;
 
-	tick_dep_set_signal(tsk->signal, TICK_DEP_BIT_POSIX_TIMER);
+	tick_dep_set_signal(tsk, tsk->signal, TICK_DEP_BIT_POSIX_TIMER);
 }
 
 static int do_cpu_nanosleep(const clockid_t which_clock, int flags,
Index: linux-2.6/kernel/time/tick-sched.c
===================================================================
--- linux-2.6.orig/kernel/time/tick-sched.c
+++ linux-2.6/kernel/time/tick-sched.c
@@ -302,6 +302,27 @@ static void tick_nohz_dep_set_all(atomic
 }
 
 /*
+ * Set bit on nohz full dependency, kicking all cpus
+ * only if task can run on nohz full CPUs.
+ */
+static void tick_nohz_dep_set_all_cond(struct task_struct *tsk,
+				       atomic_t *dep,
+				       enum tick_dep_bits bit)
+{
+	int prev;
+	unsigned long flags;
+
+	prev = atomic_fetch_or(BIT(bit), dep);
+	if (prev)
+		return;
+
+	raw_spin_lock_irqsave(&tsk->pi_lock, flags);
+	if (cpumask_intersects(&tsk->cpus_mask, tick_nohz_full_mask))
+		tick_nohz_full_kick_all();
+	raw_spin_unlock_irqrestore(&tsk->pi_lock, flags);
+}
+
+/*
  * Set a global tick dependency. Used by perf events that rely on freq and
  * by unstable clock.
  */
@@ -382,9 +403,11 @@ EXPORT_SYMBOL_GPL(tick_nohz_dep_clear_ta
  * Set a per-taskgroup tick dependency. Posix CPU timers need this in order to elapse
  * per process timers.
  */
-void tick_nohz_dep_set_signal(struct signal_struct *sig, enum tick_dep_bits bit)
+void tick_nohz_dep_set_signal(struct task_struct *tsk,
+			      struct signal_struct *sig,
+			      enum tick_dep_bits bit)
 {
-	tick_nohz_dep_set_all(&sig->tick_dep_mask, bit);
+	tick_nohz_dep_set_all_cond(tsk, &sig->tick_dep_mask, bit);
 }
 
 void tick_nohz_dep_clear_signal(struct signal_struct *sig, enum tick_dep_bits bit)



  reply	other threads:[~2020-08-25 18:46 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-08-25 18:41 [patch 0/2] posix-timers: avoid nohz_full= IPIs via task cpu masks Marcelo Tosatti
2020-08-25 18:41 ` Marcelo Tosatti [this message]
2020-09-01 23:38   ` [patch 1/2] nohz: try to avoid IPI when configuring per-CPU posix timer Frederic Weisbecker
2020-09-02 19:42     ` Marcelo Tosatti
2020-08-25 18:41 ` [patch 2/2] nohz: try to avoid IPI when setting tick dependency for task Marcelo Tosatti
2020-09-03 15:01   ` Frederic Weisbecker
2020-09-10 18:51     ` Marcelo Tosatti

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=20200825184414.442457749@fuller.cnet \
    --to=mtosatti@redhat.com \
    --cc=frederic@kernel.org \
    --cc=linux-kernel@vger.kernel.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).