1 Using RCU's CPU Stall Detector
3 The rcu_cpu_stall_suppress module parameter enables RCU's CPU stall
4 detector, which detects conditions that unduly delay RCU grace periods.
5 This module parameter enables CPU stall detection by default, but
6 may be overridden via boot-time parameter or at runtime via sysfs.
7 The stall detector's idea of what constitutes "unduly delayed" is
8 controlled by a set of kernel configuration variables and cpp macros:
10 CONFIG_RCU_CPU_STALL_TIMEOUT
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
17 RCU_SECONDS_TILL_STALL_RECHECK
19 This macro defines the period of time that RCU will wait after
20 issuing a stall warning until it issues another stall warning
21 for the same stall. This time period is normally set to three
22 times the check interval plus thirty seconds.
26 The CPU stall detector tries to make the offending CPU print its
27 own warnings, as this often gives better-quality stack traces.
28 However, if the offending CPU does not detect its own stall in
29 the number of jiffies specified by RCU_STALL_RAT_DELAY, then
30 some other CPU will complain. This delay is normally set to
33 When a CPU detects that it is stalling, it will print a message similar
36 INFO: rcu_sched_state detected stall on CPU 5 (t=2500 jiffies)
38 This message indicates that CPU 5 detected that it was causing a stall,
39 and that the stall was affecting RCU-sched. This message will normally be
40 followed by a stack dump of the offending CPU. On TREE_RCU kernel builds,
41 RCU and RCU-sched are implemented by the same underlying mechanism,
42 while on TREE_PREEMPT_RCU kernel builds, RCU is instead implemented
45 On the other hand, if the offending CPU fails to print out a stall-warning
46 message quickly enough, some other CPU will print a message similar to
49 INFO: rcu_bh_state detected stalls on CPUs/tasks: { 3 5 } (detected by 2, 2502 jiffies)
51 This message indicates that CPU 2 detected that CPUs 3 and 5 were both
52 causing stalls, and that the stall was affecting RCU-bh. This message
53 will normally be followed by stack dumps for each CPU. Please note that
54 TREE_PREEMPT_RCU builds can be stalled by tasks as well as by CPUs,
55 and that the tasks will be indicated by PID, for example, "P3421".
56 It is even possible for a rcu_preempt_state stall to be caused by both
57 CPUs -and- tasks, in which case the offending CPUs and tasks will all
58 be called out in the list.
60 Finally, if the grace period ends just as the stall warning starts
61 printing, there will be a spurious stall-warning message:
63 INFO: rcu_bh_state detected stalls on CPUs/tasks: { } (detected by 4, 2502 jiffies)
65 This is rare, but does happen from time to time in real life.
67 So your kernel printed an RCU CPU stall warning. The next question is
68 "What caused it?" The following problems can result in RCU CPU stall
71 o A CPU looping in an RCU read-side critical section.
73 o A CPU looping with interrupts disabled. This condition can
74 result in RCU-sched and RCU-bh stalls.
76 o A CPU looping with preemption disabled. This condition can
77 result in RCU-sched stalls and, if ksoftirqd is in use, RCU-bh
80 o A CPU looping with bottom halves disabled. This condition can
81 result in RCU-sched and RCU-bh stalls.
83 o For !CONFIG_PREEMPT kernels, a CPU looping anywhere in the kernel
84 without invoking schedule().
86 o A CPU-bound real-time task in a CONFIG_PREEMPT kernel, which might
87 happen to preempt a low-priority task in the middle of an RCU
88 read-side critical section. This is especially damaging if
89 that low-priority task is not permitted to run on any other CPU,
90 in which case the next RCU grace period can never complete, which
91 will eventually cause the system to run out of memory and hang.
92 While the system is in the process of running itself out of
93 memory, you might see stall-warning messages.
95 o A CPU-bound real-time task in a CONFIG_PREEMPT_RT kernel that
96 is running at a higher priority than the RCU softirq threads.
97 This will prevent RCU callbacks from ever being invoked,
98 and in a CONFIG_TREE_PREEMPT_RCU kernel will further prevent
99 RCU grace periods from ever completing. Either way, the
100 system will eventually run out of memory and hang. In the
101 CONFIG_TREE_PREEMPT_RCU case, you might see stall-warning
104 o A bug in the RCU implementation.
106 o A hardware failure. This is quite unlikely, but has occurred
107 at least once in real life. A CPU failed in a running system,
108 becoming unresponsive, but not causing an immediate crash.
109 This resulted in a series of RCU CPU stall warnings, eventually
110 leading the realization that the CPU had failed.
112 The RCU, RCU-sched, and RCU-bh implementations have CPU stall
113 warning. SRCU does not have its own CPU stall warnings, but its
114 calls to synchronize_sched() will result in RCU-sched detecting
115 RCU-sched-related CPU stalls. Please note that RCU only detects
116 CPU stalls when there is a grace period in progress. No grace period,
117 no CPU stall warnings.
119 To diagnose the cause of the stall, inspect the stack traces.
120 The offending function will usually be near the top of the stack.
121 If you have a series of stall warnings from a single extended stall,
122 comparing the stack traces can often help determine where the stall
123 is occurring, which will usually be in the function nearest the top of
124 that portion of the stack which remains the same from trace to trace.
125 If you can reliably trigger the stall, ftrace can be quite helpful.
127 RCU bugs can often be debugged with the help of CONFIG_RCU_TRACE.