1Using RCU's CPU Stall Detector
   3The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
   4detector, which detects conditions that unduly delay RCU grace periods.
   5This module parameter enables CPU stall detection by default, but
   6may be overridden via boot-time parameter or at runtime via sysfs.
   7The stall detector's idea of what constitutes "unduly delayed" is
   8controlled by a set of kernel configuration variables and cpp macros:
  12        This kernel configuration parameter defines the period of time
  13        that RCU will wait from the beginning of a grace period until it
  14        issues an RCU CPU stall warning.  This time period is normally
  15        sixty seconds.
  17        This configuration parameter may be changed at runtime via the
  18        /sys/module/rcutree/parameters/rcu_cpu_stall_timeout, however
  19        this parameter is checked only at the beginning of a cycle.
  20        So if you are 30 seconds into a 70-second stall, setting this
  21        sysfs parameter to (say) five will shorten the timeout for the
  22        -next- stall, or the following warning for the current stall
  23        (assuming the stall lasts long enough).  It will not affect the
  24        timing of the next warning for the current stall.
  26        Stall-warning messages may be enabled and disabled completely via
  27        /sys/module/rcutree/parameters/rcu_cpu_stall_suppress.
  31        This kernel configuration parameter causes the stall warning to
  32        also dump the stacks of any tasks that are blocking the current
  33        RCU-preempt grace period.
  37        This kernel configuration parameter causes the stall warning to
  38        print out additional per-CPU diagnostic information, including
  39        information on scheduling-clock ticks and RCU's idle-CPU tracking.
  43        Although the lockdep facility is extremely useful, it does add
  44        some overhead.  Therefore, under CONFIG_PROVE_RCU, the
  45        RCU_STALL_DELAY_DELTA macro allows five extra seconds before
  46        giving an RCU CPU stall warning message.
  50        The CPU stall detector tries to make the offending CPU print its
  51        own warnings, as this often gives better-quality stack traces.
  52        However, if the offending CPU does not detect its own stall in
  53        the number of jiffies specified by RCU_STALL_RAT_DELAY, then
  54        some other CPU will complain.  This delay is normally set to
  55        two jiffies.
  57When a CPU detects that it is stalling, it will print a message similar
  58to the following:
  60INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
  62This message indicates that CPU 5 detected that it was causing a stall,
  63and that the stall was affecting RCU-sched.  This message will normally be
  64followed by a stack dump of the offending CPU.  On TREE_RCU kernel builds,
  65RCU and RCU-sched are implemented by the same underlying mechanism,
  66while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
  67by rcu_preempt_state.
  69On the other hand, if the offending CPU fails to print out a stall-warning
  70message quickly enough, some other CPU will print a message similar to
  71the following:
  73INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
  75This message indicates that CPU 2 detected that CPUs 3 and 5 were both
  76causing stalls, and that the stall was affecting RCU-bh.  This message
  77will normally be followed by stack dumps for each CPU.  Please note that
  78TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
  79and that the tasks will be indicated by PID, for example, "P3421".
  80It is even possible for a rcu_preempt_state stall to be caused by both
  81CPUs -and- tasks, in which case the offending CPUs and tasks will all
  82be called out in the list.
  84Finally, if the grace period ends just as the stall warning starts
  85printing, there will be a spurious stall-warning message:
  87INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
  89This is rare, but does happen from time to time in real life.
  91If the CONFIG_RCU_CPU_STALL_INFO kernel configuration parameter is set,
  92more information is printed with the stall-warning message, for example:
  94        INFO: rcu_preempt detected stall on CPU
  95        0: (63959 ticks this GP) idle=241/3fffffffffffffff/0
  96           (t=65000 jiffies)
  98In kernels with CONFIG_RCU_FAST_NO_HZ, even more information is
 101        INFO: rcu_preempt detected stall on CPU
 102        0: (64628 ticks this GP) idle=dd5/3fffffffffffffff/0 drain=0 . timer=-1
 103           (t=65000 jiffies)
 105The "(64628 ticks this GP)" indicates that this CPU has taken more
 106than 64,000 scheduling-clock interrupts during the current stalled
 107grace period.  If the CPU was not yet aware of the current grace
 108period (for example, if it was offline), then this part of the message
 109indicates how many grace periods behind the CPU is.
 111The "idle=" portion of the message prints the dyntick-idle state.
 112The hex number before the first "/" is the low-order 12 bits of the
 113dynticks counter, which will have an even-numbered value if the CPU is
 114in dyntick-idle mode and an odd-numbered value otherwise.  The hex
 115number between the two "/"s is the value of the nesting, which will
 116be a small positive number if in the idle loop and a very large positive
 117number (as shown above) otherwise.
 119For CONFIG_RCU_FAST_NO_HZ kernels, the "drain=0" indicates that the
 120CPU is not in the process of trying to force itself into dyntick-idle
 121state, the "." indicates that the CPU has not given up forcing RCU
 122into dyntick-idle mode (it would be "H" otherwise), and the "timer=-1"
 123indicates that the CPU has not recented forced RCU into dyntick-idle
 124mode (it would otherwise indicate the number of microseconds remaining
 125in this forced state).
 128Multiple Warnings From One Stall
 130If a stall lasts long enough, multiple stall-warning messages will be
 131printed for it.  The second and subsequent messages are printed at
 132longer intervals, so that the time between (say) the first and second
 133message will be about three times the interval between the beginning
 134of the stall and the first message.
 137What Causes RCU CPU Stall Warnings?
 139So your kernel printed an RCU CPU stall warning.  The next question is
 140"What caused it?"  The following problems can result in RCU CPU stall
 143o       A CPU looping in an RCU read-side critical section.
 145o       A CPU looping with interrupts disabled.  This condition can
 146        result in RCU-sched and RCU-bh stalls.
 148o       A CPU looping with preemption disabled.  This condition can
 149        result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
 150        stalls.
 152o       A CPU looping with bottom halves disabled.  This condition can
 153        result in RCU-sched and RCU-bh stalls.
 155o       For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
 156        without invoking schedule().
 158o       A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
 159        happen to preempt a low-priority task in the middle of an RCU
 160        read-side critical section.   This is especially damaging if
 161        that low-priority task is not permitted to run on any other CPU,
 162        in which case the next RCU grace period can never complete, which
 163        will eventually cause the system to run out of memory and hang.
 164        While the system is in the process of running itself out of
 165        memory, you might see stall-warning messages.
 167o       A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
 168        is running at a higher priority than the RCU softirq threads.
 169        This will prevent RCU callbacks from ever being invoked,
 170        and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
 171        RCU grace periods from ever completing.  Either way, the
 172        system will eventually run out of memory and hang.  In the
 173        CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
 174        messages.
 176o       A hardware or software issue shuts off the scheduler-clock
 177        interrupt on a CPU that is not in dyntick-idle mode.  This
 178        problem really has happened, and seems to be most likely to
 179        result in RCU CPU stall warnings for CONFIG_NO_HZ=n kernels.
 181o       A bug in the RCU implementation.
 183o       A hardware failure.  This is quite unlikely, but has occurred
 184        at least once in real life.  A CPU failed in a running system,
 185        becoming unresponsive, but not causing an immediate crash.
 186        This resulted in a series of RCU CPU stall warnings, eventually
 187        leading the realization that the CPU had failed.
 189The RCU, RCU-sched, and RCU-bh implementations have CPU stall warning.
 190SRCU does not have its own CPU stall warnings, but its calls to
 191synchronize_sched() will result in RCU-sched detecting RCU-sched-related
 192CPU stalls.  Please note that RCU only detects CPU stalls when there is
 193a grace period in progress.  No grace period, no CPU stall warnings.
 195To diagnose the cause of the stall, inspect the stack traces.
 196The offending function will usually be near the top of the stack.
 197If you have a series of stall warnings from a single extended stall,
 198comparing the stack traces can often help determine where the stall
 199is occurring, which will usually be in the function nearest the top of
 200that portion of the stack which remains the same from trace to trace.
 201If you can reliably trigger the stall, ftrace can be quite helpful.
 203RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE
 204and with RCU's event tracing.
 205 kindly hosted by Redpill Linpro AS, provider of Linux consulting and operations services since 1995.