kthread: Document ways of reducing OS jitter due to per-CPU kthreads

The Linux kernel uses a number of per-CPU kthreads, any of which might
contribute to OS jitter at any time.  The usual approach to normal
kthreads, namely to bind them to a "housekeeping" CPU, does not work
with these kthreads because they cannot operate correctly if moved to
some other CPU.  This commit therefore lists ways of controlling OS
jitter from the Linux kernel's per-CPU kthreads.  It also lists some
ways of diagnosing excessive jitter.

Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Cc: Kevin Hilman <khilman@linaro.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Olivier Baetz <olivier.baetz@novasparks.com>
Cc: Pradeep Satyanarayana <pradeeps@linux.vnet.ibm.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Borislav Petkov <bp@suse.de>

1 files changed, 202 insertions, 0 deletions

diff --git a/Documentation/kernel-per-CPU-kthreads.txt b/Documentation/kernel-per-CPU-kthreads.txt
new file mode 100644
index 000000000000..cbf7ae412da4
--- /dev/null
+++ b/Documentation/kernel-per-CPU-kthreads.txt
@@ -0,0 +1,202 @@
+REDUCING OS JITTER DUE TO PER-CPU KTHREADS
+
+This document lists per-CPU kthreads in the Linux kernel and presents
+options to control their OS jitter.  Note that non-per-CPU kthreads are
+not listed here.  To reduce OS jitter from non-per-CPU kthreads, bind
+them to a "housekeeping" CPU dedicated to such work.
+
+
+REFERENCES
+
+o       Documentation/IRQ-affinity.txt:  Binding interrupts to sets of CPUs.
+
+o       Documentation/cgroups:  Using cgroups to bind tasks to sets of CPUs.
+
+o       man taskset:  Using the taskset command to bind tasks to sets
+        of CPUs.
+
+o       man sched_setaffinity:  Using the sched_setaffinity() system
+        call to bind tasks to sets of CPUs.
+
+o       /sys/devices/system/cpu/cpuN/online:  Control CPU N's hotplug state,
+        writing "0" to offline and "1" to online.
+
+o       In order to locate kernel-generated OS jitter on CPU N:
+
+                cd /sys/kernel/debug/tracing
+                echo 1 > max_graph_depth # Increase the "1" for more detail
+                echo function_graph > current_tracer
+                # run workload
+                cat per_cpu/cpuN/trace
+
+
+KTHREADS
+
+Name: ehca_comp/%u
+Purpose: Periodically process Infiniband-related work.
+To reduce its OS jitter, do any of the following:
+1.      Don't use eHCA Infiniband hardware, instead choosing hardware
+        that does not require per-CPU kthreads.  This will prevent these
+        kthreads from being created in the first place.  (This will
+        work for most people, as this hardware, though important, is
+        relatively old and is produced in relatively low unit volumes.)
+2.      Do all eHCA-Infiniband-related work on other CPUs, including
+        interrupts.
+3.      Rework the eHCA driver so that its per-CPU kthreads are
+        provisioned only on selected CPUs.
+
+
+Name: irq/%d-%s
+Purpose: Handle threaded interrupts.
+To reduce its OS jitter, do the following:
+1.      Use irq affinity to force the irq threads to execute on
+        some other CPU.
+
+Name: kcmtpd_ctr_%d
+Purpose: Handle Bluetooth work.
+To reduce its OS jitter, do one of the following:
+1.      Don't use Bluetooth, in which case these kthreads won't be
+        created in the first place.
+2.      Use irq affinity to force Bluetooth-related interrupts to
+        occur on some other CPU and furthermore initiate all
+        Bluetooth activity on some other CPU.
+
+Name: ksoftirqd/%u
+Purpose: Execute softirq handlers when threaded or when under heavy load.
+To reduce its OS jitter, each softirq vector must be handled
+separately as follows:
+TIMER_SOFTIRQ:  Do all of the following:
+1.      To the extent possible, keep the CPU out of the kernel when it
+        is non-idle, for example, by avoiding system calls and by forcing
+        both kernel threads and interrupts to execute elsewhere.
+2.      Build with CONFIG_HOTPLUG_CPU=y.  After boot completes, force
+        the CPU offline, then bring it back online.  This forces
+        recurring timers to migrate elsewhere.  If you are concerned
+        with multiple CPUs, force them all offline before bringing the
+        first one back online.  Once you have onlined the CPUs in question,
+        do not offline any other CPUs, because doing so could force the
+        timer back onto one of the CPUs in question.
+NET_TX_SOFTIRQ and NET_RX_SOFTIRQ:  Do all of the following:
+1.      Force networking interrupts onto other CPUs.
+2.      Initiate any network I/O on other CPUs.
+3.      Once your application has started, prevent CPU-hotplug operations
+        from being initiated from tasks that might run on the CPU to
+        be de-jittered.  (It is OK to force this CPU offline and then
+        bring it back online before you start your application.)
+BLOCK_SOFTIRQ:  Do all of the following:
+1.      Force block-device interrupts onto some other CPU.
+2.      Initiate any block I/O on other CPUs.
+3.      Once your application has started, prevent CPU-hotplug operations
+        from being initiated from tasks that might run on the CPU to
+        be de-jittered.  (It is OK to force this CPU offline and then
+        bring it back online before you start your application.)
+BLOCK_IOPOLL_SOFTIRQ:  Do all of the following:
+1.      Force block-device interrupts onto some other CPU.
+2.      Initiate any block I/O and block-I/O polling on other CPUs.
+3.      Once your application has started, prevent CPU-hotplug operations
+        from being initiated from tasks that might run on the CPU to
+        be de-jittered.  (It is OK to force this CPU offline and then
+        bring it back online before you start your application.)
+TASKLET_SOFTIRQ: Do one or more of the following:
+1.      Avoid use of drivers that use tasklets.  (Such drivers will contain
+        calls to things like tasklet_schedule().)
+2.      Convert all drivers that you must use from tasklets to workqueues.
+3.      Force interrupts for drivers using tasklets onto other CPUs,
+        and also do I/O involving these drivers on other CPUs.
+SCHED_SOFTIRQ: Do all of the following:
+1.      Avoid sending scheduler IPIs to the CPU to be de-jittered,
+        for example, ensure that at most one runnable kthread is present
+        on that CPU.  If a thread that expects to run on the de-jittered
+        CPU awakens, the scheduler will send an IPI that can result in
+        a subsequent SCHED_SOFTIRQ.
+2.      Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y,
+        CONFIG_NO_HZ_FULL=y, and, in addition, ensure that the CPU
+        to be de-jittered is marked as an adaptive-ticks CPU using the
+        "nohz_full=" boot parameter.  This reduces the number of
+        scheduler-clock interrupts that the de-jittered CPU receives,
+        minimizing its chances of being selected to do the load balancing
+        work that runs in SCHED_SOFTIRQ context.
+3.      To the extent possible, keep the CPU out of the kernel when it
+        is non-idle, for example, by avoiding system calls and by
+        forcing both kernel threads and interrupts to execute elsewhere.
+        This further reduces the number of scheduler-clock interrupts
+        received by the de-jittered CPU.
+HRTIMER_SOFTIRQ:  Do all of the following:
+1.      To the extent possible, keep the CPU out of the kernel when it
+        is non-idle.  For example, avoid system calls and force both
+        kernel threads and interrupts to execute elsewhere.
+2.      Build with CONFIG_HOTPLUG_CPU=y.  Once boot completes, force the
+        CPU offline, then bring it back online.  This forces recurring
+        timers to migrate elsewhere.  If you are concerned with multiple
+        CPUs, force them all offline before bringing the first one
+        back online.  Once you have onlined the CPUs in question, do not
+        offline any other CPUs, because doing so could force the timer
+        back onto one of the CPUs in question.
+RCU_SOFTIRQ:  Do at least one of the following:
+1.      Offload callbacks and keep the CPU in either dyntick-idle or
+        adaptive-ticks state by doing all of the following:
+        a.      Build with CONFIG_RCU_NOCB_CPU=y, CONFIG_RCU_NOCB_CPU_ALL=y,
+                CONFIG_NO_HZ_FULL=y, and, in addition ensure that the CPU
+                to be de-jittered is marked as an adaptive-ticks CPU using
+                the "nohz_full=" boot parameter.  Bind the rcuo kthreads
+                to housekeeping CPUs, which can tolerate OS jitter.
+        b.      To the extent possible, keep the CPU out of the kernel
+                when it is non-idle, for example, by avoiding system
+                calls and by forcing both kernel threads and interrupts
+                to execute elsewhere.
+2.      Enable RCU to do its processing remotely via dyntick-idle by
+        doing all of the following:
+        a.      Build with CONFIG_NO_HZ=y and CONFIG_RCU_FAST_NO_HZ=y.
+        b.      Ensure that the CPU goes idle frequently, allowing other
+                CPUs to detect that it has passed through an RCU quiescent
+                state.  If the kernel is built with CONFIG_NO_HZ_FULL=y,
+                userspace execution also allows other CPUs to detect that
+                the CPU in question has passed through a quiescent state.
+        c.      To the extent possible, keep the CPU out of the kernel
+                when it is non-idle, for example, by avoiding system
+                calls and by forcing both kernel threads and interrupts
+                to execute elsewhere.
+
+Name: rcuc/%u
+Purpose: Execute RCU callbacks in CONFIG_RCU_BOOST=y kernels.
+To reduce its OS jitter, do at least one of the following:
+1.      Build the kernel with CONFIG_PREEMPT=n.  This prevents these
+        kthreads from being created in the first place, and also obviates
+        the need for RCU priority boosting.  This approach is feasible
+        for workloads that do not require high degrees of responsiveness.
+2.      Build the kernel with CONFIG_RCU_BOOST=n.  This prevents these
+        kthreads from being created in the first place.  This approach
+        is feasible only if your workload never requires RCU priority
+        boosting, for example, if you ensure frequent idle time on all
+        CPUs that might execute within the kernel.
+3.      Build with CONFIG_RCU_NOCB_CPU=y and CONFIG_RCU_NOCB_CPU_ALL=y,
+        which offloads all RCU callbacks to kthreads that can be moved
+        off of CPUs susceptible to OS jitter.  This approach prevents the
+        rcuc/%u kthreads from having any work to do, so that they are
+        never awakened.
+4.      Ensure that the CPU never enters the kernel, and, in particular,
+        avoid initiating any CPU hotplug operations on this CPU.  This is
+        another way of preventing any callbacks from being queued on the
+        CPU, again preventing the rcuc/%u kthreads from having any work
+        to do.
+
+Name: rcuob/%d, rcuop/%d, and rcuos/%d
+Purpose: Offload RCU callbacks from the corresponding CPU.
+To reduce its OS jitter, do at least one of the following:
+1.      Use affinity, cgroups, or other mechanism to force these kthreads
+        to execute on some other CPU.
+2.      Build with CONFIG_RCU_NOCB_CPUS=n, which will prevent these
+        kthreads from being created in the first place.  However, please
+        note that this will not eliminate OS jitter, but will instead
+        shift it to RCU_SOFTIRQ.
+
+Name: watchdog/%u
+Purpose: Detect software lockups on each CPU.
+To reduce its OS jitter, do at least one of the following:
+1.      Build with CONFIG_LOCKUP_DETECTOR=n, which will prevent these
+        kthreads from being created in the first place.
+2.      Echo a zero to /proc/sys/kernel/watchdog to disable the
+        watchdog timer.
+3.      Echo a large number of /proc/sys/kernel/watchdog_thresh in
+        order to reduce the frequency of OS jitter due to the watchdog
+        timer down to a level that is acceptable for your workload.