public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
To: linux-kernel@vger.kernel.org
Cc: mingo@elte.hu, laijs@cn.fujitsu.com, dipankar@in.ibm.com,
	akpm@linux-foundation.org, mathieu.desnoyers@polymtl.ca,
	josh@joshtriplett.org, dvhltc@us.ibm.com, niv@us.ibm.com,
	tglx@linutronix.de, peterz@infradead.org, rostedt@goodmis.org,
	Valdis.Kletnieks@vt.edu, dhowells@redhat.com, npiggin@suse.de,
	jens.axboe@oracle.com,
	"Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Subject: [PATCH tip/core/rcu 2/6] rcu: prevent RCU IPI storms in presence of high call_rcu() load
Date: Wed, 14 Oct 2009 10:15:55 -0700	[thread overview]
Message-ID: <12555405592133-git-send-email-> (raw)
In-Reply-To: <20091014171517.GA13635@linux.vnet.ibm.com>

From: Paul E. McKenney <paulmck@linux.vnet.ibm.com>

As the number of callbacks on a given CPU rises, invoke
force_quiescent_state() only every blimit number of callbacks
(defaults to 10,000), and even then only if no other CPU has invoked
force_quiescent_state() in the meantime.

Reported-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
 kernel/rcutree.c |   29 ++++++++++++++++++++++++-----
 kernel/rcutree.h |    4 ++++
 2 files changed, 28 insertions(+), 5 deletions(-)

diff --git a/kernel/rcutree.c b/kernel/rcutree.c
index 705f02a..ddbf111 100644
--- a/kernel/rcutree.c
+++ b/kernel/rcutree.c
@@ -958,7 +958,7 @@ static void rcu_offline_cpu(int cpu)
  * Invoke any RCU callbacks that have made it to the end of their grace
  * period.  Thottle as specified by rdp->blimit.
  */
-static void rcu_do_batch(struct rcu_data *rdp)
+static void rcu_do_batch(struct rcu_state *rsp, struct rcu_data *rdp)
 {
 	unsigned long flags;
 	struct rcu_head *next, *list, **tail;
@@ -1011,6 +1011,13 @@ static void rcu_do_batch(struct rcu_data *rdp)
 	if (rdp->blimit == LONG_MAX && rdp->qlen <= qlowmark)
 		rdp->blimit = blimit;
 
+	/* Reset ->qlen_last_fqs_check trigger if enough CBs have drained. */
+	if (rdp->qlen == 0 && rdp->qlen_last_fqs_check != 0) {
+		rdp->qlen_last_fqs_check = 0;
+		rdp->n_force_qs_snap = rsp->n_force_qs;
+	} else if (rdp->qlen < rdp->qlen_last_fqs_check - qhimark)
+		rdp->qlen_last_fqs_check = rdp->qlen;
+
 	local_irq_restore(flags);
 
 	/* Re-raise the RCU softirq if there are callbacks remaining. */
@@ -1224,7 +1231,7 @@ __rcu_process_callbacks(struct rcu_state *rsp, struct rcu_data *rdp)
 	}
 
 	/* If there are callbacks ready, invoke them. */
-	rcu_do_batch(rdp);
+	rcu_do_batch(rsp, rdp);
 }
 
 /*
@@ -1288,10 +1295,20 @@ __call_rcu(struct rcu_head *head, void (*func)(struct rcu_head *rcu),
 		rcu_start_gp(rsp, nestflag);  /* releases rnp_root->lock. */
 	}
 
-	/* Force the grace period if too many callbacks or too long waiting. */
-	if (unlikely(++rdp->qlen > qhimark)) {
+	/*
+	 * Force the grace period if too many callbacks or too long waiting.
+	 * Enforce hysteresis, and don't invoke force_quiescent_state()
+	 * if some other CPU has recently done so.  Also, don't bother
+	 * invoking force_quiescent_state() if the newly enqueued callback
+	 * is the only one waiting for a grace period to complete.
+	 */
+	if (unlikely(++rdp->qlen > rdp->qlen_last_fqs_check + qhimark)) {
 		rdp->blimit = LONG_MAX;
-		force_quiescent_state(rsp, 0);
+		if (rsp->n_force_qs == rdp->n_force_qs_snap &&
+		    *rdp->nxttail[RCU_DONE_TAIL] != head)
+			force_quiescent_state(rsp, 0);
+		rdp->n_force_qs_snap = rsp->n_force_qs;
+		rdp->qlen_last_fqs_check = rdp->qlen;
 	} else if ((long)(ACCESS_ONCE(rsp->jiffies_force_qs) - jiffies) < 0)
 		force_quiescent_state(rsp, 1);
 	local_irq_restore(flags);
@@ -1523,6 +1540,8 @@ rcu_init_percpu_data(int cpu, struct rcu_state *rsp, int preemptable)
 	rdp->beenonline = 1;	 /* We have now been online. */
 	rdp->preemptable = preemptable;
 	rdp->passed_quiesc_completed = lastcomp - 1;
+	rdp->qlen_last_fqs_check = 0;
+	rdp->n_force_qs_snap = rsp->n_force_qs;
 	rdp->blimit = blimit;
 	spin_unlock(&rnp->lock);		/* irqs remain disabled. */
 
diff --git a/kernel/rcutree.h b/kernel/rcutree.h
index b40ac57..599161f 100644
--- a/kernel/rcutree.h
+++ b/kernel/rcutree.h
@@ -167,6 +167,10 @@ struct rcu_data {
 	struct rcu_head *nxtlist;
 	struct rcu_head **nxttail[RCU_NEXT_SIZE];
 	long		qlen;		/* # of queued callbacks */
+	long		qlen_last_fqs_check;
+					/* qlen at last check for QS forcing */
+	unsigned long	n_force_qs_snap;
+					/* did other CPU force QS recently? */
 	long		blimit;		/* Upper limit on a processed batch */
 
 #ifdef CONFIG_NO_HZ
-- 
1.5.2.5


  parent reply	other threads:[~2009-10-14 17:29 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2009-10-14 17:15 [PATCH tip/core/rcu 0/6] rcu: fix synchronize_rcu_expedited(), update docs, improve perf Paul E. McKenney
2009-10-14 17:15 ` [PATCH tip/core/rcu 1/6] rcu: Update trace.txt documentation to reflect recent changes Paul E. McKenney
2009-10-15  9:25   ` [tip:core/rcu] " tip-bot for Paul E. McKenney
2009-10-14 17:15 ` Paul E. McKenney [this message]
2009-10-15  3:31   ` [PATCH tip/core/rcu 2/6] rcu: prevent RCU IPI storms in presence of high call_rcu() load Nick Piggin
2009-10-15  4:37     ` Paul E. McKenney
2009-10-15  9:24   ` [tip:core/rcu] rcu: Prevent " tip-bot for Paul E. McKenney
2009-10-15 11:04   ` [PATCH tip/core/rcu 2/6] rcu: prevent " Nick Piggin
2009-10-15 11:20     ` Ingo Molnar
2009-10-15 16:07     ` Paul E. McKenney
2009-10-14 17:15 ` [PATCH tip/core/rcu 3/6] rcu: stopgap fix for synchronize_rcu_expedited() for TREE_PREEMPT_RCU Paul E. McKenney
2009-10-15  9:25   ` [tip:core/rcu] rcu: Stopgap " tip-bot for Paul E. McKenney
2009-10-14 17:15 ` [PATCH tip/core/rcu 4/6] rcu: add exports for synchronize_rcu_expedited() Paul E. McKenney
2009-10-14 17:15 ` [PATCH tip/core/rcu 5/6] rcu: add rnp->blocked_tasks to tracing Paul E. McKenney
2009-10-14 20:26   ` Josh Triplett
2009-10-14 23:36     ` Paul E. McKenney
2009-10-15  9:25       ` [tip:core/rcu] rcu: Add " tip-bot for Paul E. McKenney
2009-10-14 17:15 ` [PATCH tip/core/rcu 6/6] rcu: Update trace.txt documentation for blocked-tasks lists Paul E. McKenney
2009-10-15  9:25   ` [tip:core/rcu] " tip-bot for Paul E. McKenney
2009-10-14 20:28 ` [PATCH tip/core/rcu 0/6] rcu: fix synchronize_rcu_expedited(), update docs, improve perf Josh Triplett
2009-10-15  9:21 ` Ingo Molnar
2009-10-15  9:35   ` Josh Triplett
2009-10-15 11:19     ` Ingo Molnar
2009-10-15 16:14       ` Paul E. McKenney

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=12555405592133-git-send-email- \
    --to=paulmck@linux.vnet.ibm.com \
    --cc=Valdis.Kletnieks@vt.edu \
    --cc=akpm@linux-foundation.org \
    --cc=dhowells@redhat.com \
    --cc=dipankar@in.ibm.com \
    --cc=dvhltc@us.ibm.com \
    --cc=jens.axboe@oracle.com \
    --cc=josh@joshtriplett.org \
    --cc=laijs@cn.fujitsu.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mathieu.desnoyers@polymtl.ca \
    --cc=mingo@elte.hu \
    --cc=niv@us.ibm.com \
    --cc=npiggin@suse.de \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=tglx@linutronix.de \
    /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