Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
doc: Update stallwarn.rst
This commit updates stallwarn.rst to reflect RCU additions and changes
over the past few years.
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
+25
-18
+25
-18
Documentation/RCU/stallwarn.rst
+25
-18
Documentation/RCU/stallwarn.rst
···
25
25
26
26
- A CPU looping with bottom halves disabled.
27
27
28
-
- For !CONFIG_PREEMPTION kernels, a CPU looping anywhere in the kernel
29
-
without invoking schedule(). If the looping in the kernel is
30
-
really expected and desirable behavior, you might need to add
31
-
some calls to cond_resched().
28
+
- For !CONFIG_PREEMPTION kernels, a CPU looping anywhere in the
29
+
kernel without potentially invoking schedule(). If the looping
30
+
in the kernel is really expected and desirable behavior, you
31
+
might need to add some calls to cond_resched().
32
32
33
33
- Booting Linux using a console connection that is too slow to
34
34
keep up with the boot-time console-message rate. For example,
···
108
108
109
109
- A bug in the RCU implementation.
110
110
111
-
- A hardware failure. This is quite unlikely, but has occurred
112
-
at least once in real life. A CPU failed in a running system,
113
-
becoming unresponsive, but not causing an immediate crash.
114
-
This resulted in a series of RCU CPU stall warnings, eventually
115
-
leading the realization that the CPU had failed.
111
+
- A hardware failure. This is quite unlikely, but is not at all
112
+
uncommon in large datacenter. In one memorable case some decades
113
+
back, a CPU failed in a running system, becoming unresponsive,
114
+
but not causing an immediate crash. This resulted in a series
115
+
of RCU CPU stall warnings, eventually leading the realization
116
+
that the CPU had failed.
116
117
117
-
The RCU, RCU-sched, and RCU-tasks implementations have CPU stall warning.
118
-
Note that SRCU does *not* have CPU stall warnings. Please note that
119
-
RCU only detects CPU stalls when there is a grace period in progress.
120
-
No grace period, no CPU stall warnings.
118
+
The RCU, RCU-sched, RCU-tasks, and RCU-tasks-trace implementations have
119
+
CPU stall warning. Note that SRCU does *not* have CPU stall warnings.
120
+
Please note that RCU only detects CPU stalls when there is a grace period
121
+
in progress. No grace period, no CPU stall warnings.
121
122
122
123
To diagnose the cause of the stall, inspect the stack traces.
123
124
The offending function will usually be near the top of the stack.
···
206
205
rcupdate.rcu_task_stall_timeout
207
206
-------------------------------
208
207
209
-
This boot/sysfs parameter controls the RCU-tasks stall warning
210
-
interval. A value of zero or less suppresses RCU-tasks stall
211
-
warnings. A positive value sets the stall-warning interval
212
-
in seconds. An RCU-tasks stall warning starts with the line:
208
+
This boot/sysfs parameter controls the RCU-tasks and
209
+
RCU-tasks-trace stall warning intervals. A value of zero or less
210
+
suppresses RCU-tasks stall warnings. A positive value sets the
211
+
stall-warning interval in seconds. An RCU-tasks stall warning
212
+
starts with the line:
213
213
214
214
INFO: rcu_tasks detected stalls on tasks:
215
215
216
216
And continues with the output of sched_show_task() for each
217
217
task stalling the current RCU-tasks grace period.
218
+
219
+
An RCU-tasks-trace stall warning starts (and continues) similarly:
220
+
221
+
INFO: rcu_tasks_trace detected stalls on tasks
218
222
219
223
220
224
Interpreting RCU's CPU Stall-Detector "Splats"
···
254
248
is in dyntick-idle mode and an odd-numbered value otherwise. The hex
255
249
number between the two "/"s is the value of the nesting, which will be
256
250
a small non-negative number if in the idle loop (as shown above) and a
257
-
very large positive number otherwise.
251
+
very large positive number otherwise. The number following the final
252
+
"/" is the NMI nesting, which will be a small non-negative number.
258
253
259
254
The "softirq=" portion of the message tracks the number of RCU softirq
260
255
handlers that the stalled CPU has executed. The number before the "/"