mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Ben Hutchings <ben@decadent.org.uk>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: akpm@linux-foundation.org,
	"Tim Chen" <tim.c.chen@linux.intel.com>,
	"Linus Torvalds" <torvalds@linux-foundation.org>,
	"Suruchi Kadu" <suruchi.a.kadu@intel.com>,
	"Steven Rostedt" <rostedt@goodmis.org>,
	"Peter Zijlstra (Intel)" <peterz@infradead.org>,
	"Doug Nelson" <doug.nelson@intel.com>,
	"Shawn Bohrer" <sbohrer@rgmadvisors.com>,
	"Ingo Molnar" <mingo@kernel.org>
Subject: [PATCH 3.2 19/24] sched/rt: Reduce rq lock contention by eliminating locking of non-feasible target
Date: Tue, 03 Mar 2015 22:11:28 +0000	[thread overview]
Message-ID: <lsq.1425420688.621882078@decadent.org.uk> (raw)
In-Reply-To: <lsq.1425420688.806916072@decadent.org.uk>

3.2.68-rc1 review patch.  If anyone has any objections, please let me know.

------------------

From: Tim Chen <tim.c.chen@linux.intel.com>

commit 80e3d87b2c5582db0ab5e39610ce3707d97ba409 upstream.

This patch adds checks that prevens futile attempts to move rt tasks
to a CPU with active tasks of equal or higher priority.

This reduces run queue lock contention and improves the performance of
a well known OLTP benchmark by 0.7%.

Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Shawn Bohrer <sbohrer@rgmadvisors.com>
Cc: Suruchi Kadu <suruchi.a.kadu@intel.com>
Cc: Doug Nelson<doug.nelson@intel.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1421430374.2399.27.camel@schen9-desk2.jf.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
[bwh: Backported to 3.2: adjust filename]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
---
 kernel/sched_rt.c | 17 ++++++++++++++++-
 1 file changed, 16 insertions(+), 1 deletion(-)

--- a/kernel/sched_rt.c
+++ b/kernel/sched_rt.c
@@ -1067,7 +1067,12 @@ select_task_rq_rt(struct task_struct *p,
 	    (p->rt.nr_cpus_allowed > 1)) {
 		int target = find_lowest_rq(p);
 
-		if (target != -1)
+		/*
+		 * Don't bother moving it if the destination CPU is
+		 * not running a lower priority task.
+		 */
+		if (target != -1 &&
+		    p->prio < cpu_rq(target)->rt.highest_prio.curr)
 			cpu = target;
 	}
 	rcu_read_unlock();
@@ -1346,6 +1351,16 @@ static struct rq *find_lock_lowest_rq(st
 
 		lowest_rq = cpu_rq(cpu);
 
+		if (lowest_rq->rt.highest_prio.curr <= task->prio) {
+			/*
+			 * Target rq has tasks of equal or higher priority,
+			 * retrying does not release any lock and is unlikely
+			 * to yield a different result.
+			 */
+			lowest_rq = NULL;
+			break;
+		}
+
 		/* if the prio of this runqueue changed, try again */
 		if (double_lock_balance(rq, lowest_rq)) {
 			/*


  parent reply	other threads:[~2015-03-03 23:23 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2015-03-03 22:11 [PATCH 3.2 00/24] 3.2.68-rc1 review Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 15/24] nilfs2: fix deadlock of segment constructor over I_SYNC flag Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 02/24] x86: mm/fault: Fix semaphore imbalance Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 13/24] net: sctp: fix passing wrong parameter header to param_type2af in sctp_process_param Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 04/24] ASoC: atmel_ssc_dai: fix start event for I2S mode Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 18/24] [media] media/rc: Send sync space information on the lirc device Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 01/24] PCI: quirks: Fix backport of quirk_io() Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 17/24] staging: comedi: cb_pcidas64: fix incorrect AI range code handling Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 08/24] caif: remove wrong dev_net_set() call Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 10/24] gpio: sysfs: fix memory leak in gpiod_export_link Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 14/24] mm: pagewalk: call pte_hole() for VM_PFNMAP during walk_page_range Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 20/24] time: adjtimex: Validate the ADJ_FREQUENCY values Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 07/24] lib/checksum.c: fix build for generic csum_tcpudp_nofold Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 03/24] MIPS: IRQ: Fix disable_irq on CPU IRQs Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 24/24] Bluetooth: ath3k: workaround the compatibility issue with xHCI controller Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 16/24] Drivers: hv: vmbus: incorrect device name is printed when child device is unregistered Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 12/24] MIPS: Fix C0_Pagegrain[IEC] support Ben Hutchings
2015-03-03 23:24   ` David Daney
2015-03-04  0:25     ` Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 21/24] ntp: Fixup adjtimex freq validation on 32-bit systems Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 09/24] MIPS: Fix kernel lockup or crash after CPU offline/online Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 05/24] ALSA: ak411x: Fix stall in work callback Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 06/24] lib/checksum.c: fix carry in csum_tcpudp_nofold Ben Hutchings
2015-03-03 22:11 ` Ben Hutchings [this message]
2015-03-03 22:11 ` [PATCH 3.2 11/24] gpio: sysfs: fix memory leak in gpiod_sysfs_set_active_low Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 23/24] ipv6: fib: fix fib dump restart Ben Hutchings
2015-03-03 22:11 ` [PATCH 3.2 22/24] " Ben Hutchings
2015-03-04  0:28 ` [PATCH 3.2 00/24] 3.2.68-rc1 review Ben Hutchings
2015-03-04  1:01 ` Guenter Roeck
2015-03-04  2:09   ` Ben Hutchings

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=lsq.1425420688.621882078@decadent.org.uk \
    --to=ben@decadent.org.uk \
    --cc=akpm@linux-foundation.org \
    --cc=doug.nelson@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=sbohrer@rgmadvisors.com \
    --cc=stable@vger.kernel.org \
    --cc=suruchi.a.kadu@intel.com \
    --cc=tim.c.chen@linux.intel.com \
    --cc=torvalds@linux-foundation.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

all inboxes | Powered by JetHome®