On Mon, Apr 06, 2015 at 03:45:56PM -0400, cmetcalf@xxxxxxxxxx wrote:
> From: Chris Metcalf <cmetcalf@xxxxxxxxxx>
>
> Change the default behavior of watchdog so it only runs on the
> housekeeping cores when nohz_full is enabled at build and boot time.
>
> Allow modifying the set of cores the watchdog is currently running
> on with a new kernel.watchdog_exclude sysctl.
Assuming the first patch gets accepted, this implementation looks fine by
me.
Acked-by: Don Zickus <dzickus@xxxxxxxxxx>
>
> Signed-off-by: Chris Metcalf <cmetcalf@xxxxxxxxxx>
> ---
> Documentation/lockup-watchdogs.txt | 6 ++++++
> Documentation/sysctl/kernel.txt | 9 +++++++++
> include/linux/nmi.h | 3 +++
> kernel/sysctl.c | 7 +++++++
> kernel/watchdog.c | 33 +++++++++++++++++++++++++++++++++
> 5 files changed, 58 insertions(+)
>
> diff --git a/Documentation/lockup-watchdogs.txt b/Documentation/lockup-watchdogs.txt
> index ab0baa692c13..4f86aec1d69d 100644
> --- a/Documentation/lockup-watchdogs.txt
> +++ b/Documentation/lockup-watchdogs.txt
> @@ -61,3 +61,9 @@ As explained above, a kernel knob is provided that allows
> administrators to configure the period of the hrtimer and the perf
> event. The right value for a particular environment is a trade-off
> between fast response to lockups and detection overhead.
> +
> +By default, the watchdog runs on all online cores. However, on a
> +kernel configured with NO_HZ_FULL, by default the watchdog runs only
> +on the housekeeping cores, not the cores specified in the "nohz_full"
> +boot argument. In either case, the set of cores excluded from running
> +the watchdog may be adjusted via the kernel.watchdog_exclude sysctl.
> diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
> index c831001c45f1..799a1fee3f26 100644
> --- a/Documentation/sysctl/kernel.txt
> +++ b/Documentation/sysctl/kernel.txt
> @@ -923,6 +923,15 @@ and nmi_watchdog.
>
> ==============================================================
>
> +watchdog_exclude:
> +
> +This value can be used to control on which cpus the watchdog is
> +prohibited from running. The default exclude mask is empty, but if
> +NO_HZ_FULL is enabled in the kernel config, and cores are specified
> +with the nohz_full= boot argument, those cores are excluded by default.
> +
> +==============================================================
> +
> watchdog_thresh:
>
> This value can be used to control the frequency of hrtimer and NMI
> diff --git a/include/linux/nmi.h b/include/linux/nmi.h
> index 3d46fb4708e0..5094386b4fb1 100644
> --- a/include/linux/nmi.h
> +++ b/include/linux/nmi.h
> @@ -67,6 +67,7 @@ extern int nmi_watchdog_enabled;
> extern int soft_watchdog_enabled;
> extern int watchdog_user_enabled;
> extern int watchdog_thresh;
> +extern unsigned long *watchdog_exclude_mask_bits;
> extern int sysctl_softlockup_all_cpu_backtrace;
> struct ctl_table;
> extern int proc_watchdog(struct ctl_table *, int ,
> @@ -77,6 +78,8 @@ extern int proc_soft_watchdog(struct ctl_table *, int ,
> void __user *, size_t *, loff_t *);
> extern int proc_watchdog_thresh(struct ctl_table *, int ,
> void __user *, size_t *, loff_t *);
> +extern int proc_watchdog_exclude(struct ctl_table *, int,
> + void __user *, size_t *, loff_t *);
> #endif
>
> #ifdef CONFIG_HAVE_ACPI_APEI_NMI
> diff --git a/kernel/sysctl.c b/kernel/sysctl.c
> index 2082b1a88fb9..b934a4a01f0a 100644
> --- a/kernel/sysctl.c
> +++ b/kernel/sysctl.c
> @@ -881,6 +881,13 @@ static struct ctl_table kern_table[] = {
> .extra2 = &one,
> },
> {
> + .procname = "watchdog_exclude",
> + .data = &watchdog_exclude_mask_bits,
> + .maxlen = NR_CPUS,
> + .mode = 0644,
> + .proc_handler = proc_watchdog_exclude,
> + },
> + {
> .procname = "softlockup_panic",
> .data = &softlockup_panic,
> .maxlen = sizeof(int),
> diff --git a/kernel/watchdog.c b/kernel/watchdog.c
> index f2be11ab7e08..3f4fbb208437 100644
> --- a/kernel/watchdog.c
> +++ b/kernel/watchdog.c
> @@ -19,6 +19,7 @@
> #include <linux/sysctl.h>
> #include <linux/smpboot.h>
> #include <linux/sched/rt.h>
> +#include <linux/tick.h>
>
> #include <asm/irq_regs.h>
> #include <linux/kvm_para.h>
> @@ -56,6 +57,8 @@ int __read_mostly sysctl_softlockup_all_cpu_backtrace;
> #else
> #define sysctl_softlockup_all_cpu_backtrace 0
> #endif
> +static cpumask_var_t watchdog_exclude_mask;
> +unsigned long *watchdog_exclude_mask_bits;
>
> static int __read_mostly watchdog_running;
> static u64 __read_mostly sample_period;
> @@ -841,12 +844,42 @@ out:
> mutex_unlock(&watchdog_proc_mutex);
> return err;
> }
> +
> +int proc_watchdog_exclude(struct ctl_table *table, int write,
> + void __user *buffer, size_t *lenp, loff_t *ppos)
> +{
> + int err;
> +
> + mutex_lock(&watchdog_proc_mutex);
> + err = proc_do_large_bitmap(table, write, buffer, lenp, ppos);
> + if (!err && write && watchdog_enabled && watchdog_thresh) {
> + watchdog_disable_all_cpus();
> + watchdog_enable_all_cpus();
> + }
> + mutex_unlock(&watchdog_proc_mutex);
> + return err;
> +}
> +
> #endif /* CONFIG_SYSCTL */
>
> void __init lockup_detector_init(void)
> {
> set_sample_period();
>
> + alloc_bootmem_cpumask_var(&watchdog_exclude_mask);
> + watchdog_threads.exclude_mask = watchdog_exclude_mask;
> +
> +#ifdef CONFIG_NO_HZ_FULL
> + if (!cpumask_empty(tick_nohz_full_mask))
> + pr_info("Disabling watchdog on nohz_full cores by default\n");
> + cpumask_copy(watchdog_exclude_mask, tick_nohz_full_mask);
> +#else
> + cpumask_clear(watchdog_exclude_mask);
> +#endif
> +
> + /* The sysctl API requires a variable holding a pointer to the mask. */
> + watchdog_exclude_mask_bits = cpumask_bits(watchdog_exclude_mask);
> +
> if (watchdog_enabled)
> watchdog_enable_all_cpus();
> }
> --
> 2.1.2
>
--
To unsubscribe from this list: send the line "unsubscribe linux-doc" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
