summaryrefslogtreecommitdiffstats
path: root/patches/0004-tick-Add-tick-skew-boot-option.patch
diff options
context:
space:
mode:
Diffstat (limited to 'patches/0004-tick-Add-tick-skew-boot-option.patch')
-rw-r--r--patches/0004-tick-Add-tick-skew-boot-option.patch106
1 files changed, 106 insertions, 0 deletions
diff --git a/patches/0004-tick-Add-tick-skew-boot-option.patch b/patches/0004-tick-Add-tick-skew-boot-option.patch
new file mode 100644
index 0000000..995edce
--- /dev/null
+++ b/patches/0004-tick-Add-tick-skew-boot-option.patch
@@ -0,0 +1,106 @@
+From bf48ba64a0969750c739692a2ce24ba9ba05c29e Mon Sep 17 00:00:00 2001
+From: Mike Galbraith <mgalbraith@suse.de>
+Date: Tue, 8 May 2012 12:20:58 +0200
+Subject: [PATCH 004/254] tick: Add tick skew boot option
+
+Let the user decide whether power consumption or jitter is the
+more important consideration for their machines.
+
+Quoting removal commit af5ab277ded04bd9bc6b048c5a2f0e7d70ef0867:
+
+"Historically, Linux has tried to make the regular timer tick on the
+ various CPUs not happen at the same time, to avoid contention on
+ xtime_lock.
+
+ Nowadays, with the tickless kernel, this contention no longer happens
+ since time keeping and updating are done differently. In addition,
+ this skew is actually hurting power consumption in a measurable way on
+ many-core systems."
+
+Problems:
+
+ - Contrary to the above, systems do encounter contention on both
+ xtime_lock and RCU structure locks when the tick is synchronized.
+
+ - Moderate sized RT systems suffer intolerable jitter due to the tick
+ being synchronized.
+
+ - SGI reports the same for their large systems.
+
+ - Fully utilized systems reap no power saving benefit from skew removal,
+ but do suffer from resulting induced lock contention.
+
+ - 0209f649 rcu: limit rcu_node leaf-level fanout
+ This patch was born to combat lock contention which testing showed
+ to have been _induced by_ skew removal. Skew the tick, contention
+ disappeared virtually completely.
+
+[ tglx: build fix ]
+
+Signed-off-by: Mike Galbraith <mgalbraith@suse.de>
+Link: http://lkml.kernel.org/r/1336472458.21924.78.camel@marge.simpson.net
+Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
+---
+ Documentation/kernel-parameters.txt | 9 +++++++++
+ kernel/time/tick-sched.c | 18 ++++++++++++++++++
+ 2 files changed, 27 insertions(+)
+
+diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
+index c1601e5..1e0150e 100644
+--- a/Documentation/kernel-parameters.txt
++++ b/Documentation/kernel-parameters.txt
+@@ -2426,6 +2426,15 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
+
+ sched_debug [KNL] Enables verbose scheduler debug messages.
+
++ skew_tick= [KNL] Offset the periodic timer tick per cpu to mitigate
++ xtime_lock contention on larger systems, and/or RCU lock
++ contention on all systems with CONFIG_MAXSMP set.
++ Format: { "0" | "1" }
++ 0 -- disable. (may be 1 via CONFIG_CMDLINE="skew_tick=1"
++ 1 -- enable.
++ Note: increases power consumption, thus should only be
++ enabled if running jitter sensitive (HPC/RT) workloads.
++
+ security= [SECURITY] Choose a security module to enable at boot.
+ If this boot parameter is not specified, only the first
+ security module asking for security registration will be
+diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
+index 6a3a5b9..efd3866 100644
+--- a/kernel/time/tick-sched.c
++++ b/kernel/time/tick-sched.c
+@@ -814,6 +814,16 @@ static enum hrtimer_restart tick_sched_timer(struct hrtimer *timer)
+ return HRTIMER_RESTART;
+ }
+
++static int sched_skew_tick;
++
++static int __init skew_tick(char *str)
++{
++ get_option(&str, &sched_skew_tick);
++
++ return 0;
++}
++early_param("skew_tick", skew_tick);
++
+ /**
+ * tick_setup_sched_timer - setup the tick emulation timer
+ */
+@@ -831,6 +841,14 @@ void tick_setup_sched_timer(void)
+ /* Get the next period (per cpu) */
+ hrtimer_set_expires(&ts->sched_timer, tick_init_jiffy_update());
+
++ /* Offset the tick to avert xtime_lock contention. */
++ if (sched_skew_tick) {
++ u64 offset = ktime_to_ns(tick_period) >> 1;
++ do_div(offset, num_possible_cpus());
++ offset *= smp_processor_id();
++ hrtimer_add_expires_ns(&ts->sched_timer, offset);
++ }
++
+ for (;;) {
+ hrtimer_forward(&ts->sched_timer, now, tick_period);
+ hrtimer_start_expires(&ts->sched_timer,
+--
+1.7.10.4
+