tick-sched: add specific do_timer_cpu value for nohz off mode

Show and modify the tick_do_timer_cpu via sysfs.  This determines the cpu
on which global time (jiffies) updates occur.  Modification can only be
done on systems with nohz mode turned off.

While not necessarily harmful, doing jiffies updates on an application cpu
does cause some extra overhead that HPC benchmarking people notice.  They
prefer to have OS activity isolated to certain cpus.  They like
reproducibility of results, and having jiffies updates bouncing around
introduces variability.

Signed-off-by: Dimitri Sivanich <sivanich@sgi.com>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

diff --git a/Documentation/ABI/testing/sysfs-devices-system-timekeeping b/Documentation/ABI/testing/sysfs-devices-system-timekeeping
new file mode 100644 (file)
index 0000000..a904c6d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-devices-system-timekeeping
@@ -0,0 +1,16 @@
+What:          /sys/devices/system/timekeeping/
+Date:          November 2011
+Contact:       Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:   Timekeeping attributes
+
+
+What:          /sys/devices/system/timekeeping/timekeeping0/jiffies_cpu
+Date:          November 2011
+Contact:       Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:   Show and modify the kernel's tick_do_timer_cpu.  This
+               determines the cpu on which global time (jiffies) updates
+               occur.  This can only be modified on systems running with
+               the nohz mode turned off (nohz=off).
+
+               Possible values are:
+                       0 - <num online cpus>

diff --git a/drivers/base/sys.c b/drivers/base/sys.c
index 9dff77bfe1e348a0ed3a3e4f450d192b6a4ac580..67d81a228d43f721e7a37c98e4a4a8ddbb29675b 100644 (file)
--- a/drivers/base/sys.c
+++ b/drivers/base/sys.c
@@ -339,13 +339,11 @@ int __init system_bus_init(void)
        return 0;
 }
 
-#define to_ext_attr(x) container_of(x, struct sysdev_ext_attribute, attr)
-
 ssize_t sysdev_store_ulong(struct sys_device *sysdev,
                           struct sysdev_attribute *attr,
                           const char *buf, size_t size)
 {
-       struct sysdev_ext_attribute *ea = to_ext_attr(attr);
+       struct sysdev_ext_attribute *ea = SYSDEV_TO_EXT_ATTR(attr);
        char *end;
        unsigned long new = simple_strtoul(buf, &end, 0);
        if (end == buf)
@@ -360,7 +358,7 @@ ssize_t sysdev_show_ulong(struct sys_device *sysdev,
                          struct sysdev_attribute *attr,
                          char *buf)
 {
-       struct sysdev_ext_attribute *ea = to_ext_attr(attr);
+       struct sysdev_ext_attribute *ea = SYSDEV_TO_EXT_ATTR(attr);
        return snprintf(buf, PAGE_SIZE, "%lx\n", *(unsigned long *)(ea->var));
 }
 EXPORT_SYMBOL_GPL(sysdev_show_ulong);
@@ -369,7 +367,7 @@ ssize_t sysdev_store_int(struct sys_device *sysdev,
                           struct sysdev_attribute *attr,
                           const char *buf, size_t size)
 {
-       struct sysdev_ext_attribute *ea = to_ext_attr(attr);
+       struct sysdev_ext_attribute *ea = SYSDEV_TO_EXT_ATTR(attr);
        char *end;
        long new = simple_strtol(buf, &end, 0);
        if (end == buf || new > INT_MAX || new < INT_MIN)
@@ -384,7 +382,7 @@ ssize_t sysdev_show_int(struct sys_device *sysdev,
                          struct sysdev_attribute *attr,
                          char *buf)
 {
-       struct sysdev_ext_attribute *ea = to_ext_attr(attr);
+       struct sysdev_ext_attribute *ea = SYSDEV_TO_EXT_ATTR(attr);
        return snprintf(buf, PAGE_SIZE, "%d\n", *(int *)(ea->var));
 }
 EXPORT_SYMBOL_GPL(sysdev_show_int);

diff --git a/include/linux/sysdev.h b/include/linux/sysdev.h
index 20f63d3e6144654f0124170827eab474a1b41faa..7ab0c81cab1d37bf39135d4bda4e2e2b34a6867f 100644 (file)
--- a/include/linux/sysdev.h
+++ b/include/linux/sysdev.h
@@ -132,6 +132,8 @@ struct sysdev_ext_attribute {
        void *var;
 };
 
+#define SYSDEV_TO_EXT_ATTR(x) container_of(x, struct sysdev_ext_attribute, attr)
+
 /*
  * Support for simple variable sysdev attributes.
  * The pointer to the variable is stored in a sysdev_ext_attribute

diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index 31cc06163ed540df59acadb4ee194adc640a71c0..8fb8d6e4a0314f3eec3b85531ed22185271bfcf4 100644 (file)
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -843,6 +843,73 @@ void tick_cancel_sched_timer(int cpu)
 }
 #endif
 
+#ifdef CONFIG_SYSFS
+/*
+ * Allow modification of tick_do_timer_cpu when nohz mode is off.
+ */
+static ssize_t sysfs_store_do_timer_cpu(struct sys_device *dev,
+                                               struct sysdev_attribute *attr,
+                                               const char *buf, size_t size)
+{
+       struct sysdev_ext_attribute *ea = SYSDEV_TO_EXT_ATTR(attr);
+       unsigned int new;
+       int rv;
+
+#ifdef CONFIG_NO_HZ
+       /* nohz mode not supported */
+       if (tick_nohz_enabled)
+               return -EINVAL;
+#endif
+
+       rv = kstrtouint(buf, 0, &new);
+       if (rv)
+               return rv;
+
+       /* Protect against cpu-hotplug */
+       get_online_cpus();
+
+       if (new >= nr_cpu_ids || !cpu_online(new)) {
+               put_online_cpus();
+               return -ERANGE;
+       }
+
+       *(unsigned int *)(ea->var) = new;
+
+       put_online_cpus();
+
+       return size;
+}
+
+static struct sysdev_ext_attribute attr_jiffies_cpu = {
+                       _SYSDEV_ATTR(jiffies_cpu, 0644, sysdev_show_int,
+                                       sysfs_store_do_timer_cpu),
+                       &tick_do_timer_cpu };
+
+static struct sysdev_class timekeeping_sysclass = {
+       .name = "timekeeping",
+};
+
+static struct sys_device device_timekeeping = {
+       .id     = 0,
+       .cls    = &timekeeping_sysclass,
+};
+
+static int __init init_timekeeping_sysfs(void)
+{
+       int error = sysdev_class_register(&timekeeping_sysclass);
+
+       if (!error)
+               error = sysdev_register(&device_timekeeping);
+       if (!error)
+               error = sysdev_create_file(
+                               &device_timekeeping,
+                               &attr_jiffies_cpu.attr);
+       return error;
+}
+
+device_initcall(init_timekeeping_sysfs);
+#endif /* SYSFS */
+
 /**
  * Async notification about clocksource changes
  */