From 5f329089431aac08bf759fa2bcb34077a6aa1f4e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Fernando=20Luis=20V=C3=A1zquez=20Cao?= Date: Thu, 9 Feb 2012 17:42:21 -0500 Subject: watchdog: Update Kconfig entries The soft and hard lockup thresholds have changed so the corresponding Kconfig entries need to be updated accordingly. Add a reference to watchdog_thresh while at it. Signed-off-by: Fernando Luis Vazquez Cao Signed-off-by: Don Zickus Link: http://lkml.kernel.org/r/1328827342-6253-2-git-send-email-dzickus@redhat.com Signed-off-by: Ingo Molnar --- lib/Kconfig.debug | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) (limited to 'lib/Kconfig.debug') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8745ac7d1f75..9739c0b45e93 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -166,18 +166,21 @@ config LOCKUP_DETECTOR hard and soft lockups. Softlockups are bugs that cause the kernel to loop in kernel - mode for more than 60 seconds, without giving other tasks a + mode for more than 20 seconds, without giving other tasks a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. Hardlockups are bugs that cause the CPU to loop in kernel mode - for more than 60 seconds, without letting other interrupts have a + for more than 10 seconds, without letting other interrupts have a chance to run. The current stack trace is displayed upon detection and the system will stay locked up. The overhead should be minimal. A periodic hrtimer runs to - generate interrupts and kick the watchdog task every 10-12 seconds. - An NMI is generated every 60 seconds or so to check for hardlockups. + generate interrupts and kick the watchdog task every 4 seconds. + An NMI is generated every 10 seconds or so to check for hardlockups. + + The frequency of hrtimer and NMI events and the soft and hard lockup + thresholds can be controlled through the sysctl watchdog_thresh. config HARDLOCKUP_DETECTOR def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \ @@ -189,7 +192,8 @@ config BOOTPARAM_HARDLOCKUP_PANIC help Say Y here to enable the kernel to panic on "hard lockups", which are bugs that cause the kernel to loop in kernel - mode with interrupts disabled for more than 60 seconds. + mode with interrupts disabled for more than 10 seconds (configurable + using the watchdog_thresh sysctl). Say N if unsure. @@ -206,8 +210,8 @@ config BOOTPARAM_SOFTLOCKUP_PANIC help Say Y here to enable the kernel to panic on "soft lockups", which are bugs that cause the kernel to loop in kernel - mode for more than 60 seconds, without giving other tasks a - chance to run. + mode for more than 20 seconds (configurable using the watchdog_thresh + sysctl), without giving other tasks a chance to run. The panic can be used in combination with panic_timeout, to cause the system to reboot automatically after a -- cgit v1.2.3 From 5c8806a037ad4f53259146060b32600566475e29 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Fri, 6 Jan 2012 15:10:44 -0800 Subject: rcu: Move RCU_TRACE to lib/Kconfig.debug The RCU_TRACE kernel parameter has always been intended for debugging, not for production use. Formalize this by moving RCU_TRACE from init/Kconfig to lib/Kconfig.debug. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- lib/Kconfig.debug | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'lib/Kconfig.debug') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 8745ac7d1f75..3cc419d05f2f 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -927,6 +927,16 @@ config RCU_CPU_STALL_VERBOSE Say Y if you want to enable such checks. +config RCU_TRACE + bool "Enable tracing for RCU" + depends on DEBUG_KERNEL + help + This option provides tracing in RCU which presents stats + in debugfs for debugging RCU implementation. + + Say Y here if you want to enable RCU tracing + Say N if you are unsure. + config KPROBES_SANITY_TEST bool "Kprobes sanity tests" depends on DEBUG_KERNEL -- cgit v1.2.3 From a858af2875fb291d0f4b0a4419fefbf03c2379c0 Mon Sep 17 00:00:00 2001 From: "Paul E. McKenney" Date: Mon, 16 Jan 2012 13:29:10 -0800 Subject: rcu: Print scheduling-clock information on RCU CPU stall-warning messages There have been situations where RCU CPU stall warnings were caused by issues in scheduling-clock timer initialization. To make it easier to track these down, this commit causes the RCU CPU stall-warning messages to print out the number of scheduling-clock interrupts taken in the current grace period for each stalled CPU. Signed-off-by: Paul E. McKenney Signed-off-by: Paul E. McKenney --- lib/Kconfig.debug | 14 ++++++++++++++ 1 file changed, 14 insertions(+) (limited to 'lib/Kconfig.debug') diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 3cc419d05f2f..d27a2aa3e815 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -927,6 +927,20 @@ config RCU_CPU_STALL_VERBOSE Say Y if you want to enable such checks. +config RCU_CPU_STALL_INFO + bool "Print additional diagnostics on RCU CPU stall" + depends on (TREE_RCU || TREE_PREEMPT_RCU) && DEBUG_KERNEL + default n + help + For each stalled CPU that is aware of the current RCU grace + period, print out additional per-CPU diagnostic information + regarding scheduling-clock ticks, idle state, and, + for RCU_FAST_NO_HZ kernels, idle-entry state. + + Say N if you are unsure. + + Say Y if you want to enable such diagnostics. + config RCU_TRACE bool "Enable tracing for RCU" depends on DEBUG_KERNEL -- cgit v1.2.3