• Home
  • Raw
  • Download

Lines Matching +full:back +full:- +full:end

2 Reducing OS jitter due to per-cpu kthreads
5 This document lists per-CPU kthreads in the Linux kernel and presents
6 options to control their OS jitter. Note that non-per-CPU kthreads are
7 not listed here. To reduce OS jitter from non-per-CPU kthreads, bind
13 - Documentation/core-api/irq/irq-affinity.rst: Binding interrupts to sets of CPUs.
15 - Documentation/admin-guide/cgroup-v1: Using cgroups to bind tasks to sets of CPUs.
17 - man taskset: Using the taskset command to bind tasks to sets
20 - man sched_setaffinity: Using the sched_setaffinity() system
23 - /sys/devices/system/cpu/cpuN/online: Control CPU N's hotplug state,
26 - In order to locate kernel-generated OS jitter on CPU N:
41 Periodically process Infiniband-related work.
46 that does not require per-CPU kthreads. This will prevent these
50 2. Do all eHCA-Infiniband-related work on other CPUs, including
52 3. Rework the eHCA driver so that its per-CPU kthreads are
57 irq/%d-%s
77 2. Use irq affinity to force Bluetooth-related interrupts to
91 -------------
96 is non-idle, for example, by avoiding system calls and by forcing
99 the CPU offline, then bring it back online. This forces
102 first one back online. Once you have onlined the CPUs in question,
104 timer back onto one of the CPUs in question.
107 ---------------------------------
113 3. Once your application has started, prevent CPU-hotplug operations
115 be de-jittered. (It is OK to force this CPU offline and then
116 bring it back online before you start your application.)
119 -------------
123 1. Force block-device interrupts onto some other CPU.
125 3. Once your application has started, prevent CPU-hotplug operations
127 be de-jittered. (It is OK to force this CPU offline and then
128 bring it back online before you start your application.)
131 ----------------
135 1. Force block-device interrupts onto some other CPU.
136 2. Initiate any block I/O and block-I/O polling on other CPUs.
137 3. Once your application has started, prevent CPU-hotplug operations
139 be de-jittered. (It is OK to force this CPU offline and then
140 bring it back online before you start your application.)
143 ---------------
154 -------------
158 1. Avoid sending scheduler IPIs to the CPU to be de-jittered,
160 on that CPU. If a thread that expects to run on the de-jittered
163 2. CONFIG_NO_HZ_FULL=y and ensure that the CPU to be de-jittered
164 is marked as an adaptive-ticks CPU using the "nohz_full="
165 boot parameter. This reduces the number of scheduler-clock
166 interrupts that the de-jittered CPU receives, minimizing its
170 is non-idle, for example, by avoiding system calls and by
172 This further reduces the number of scheduler-clock interrupts
173 received by the de-jittered CPU.
176 ---------------
181 is non-idle. For example, avoid system calls and force both
184 CPU offline, then bring it back online. This forces recurring
187 back online. Once you have onlined the CPUs in question, do not
189 back onto one of the CPUs in question.
192 -----------
196 1. Offload callbacks and keep the CPU in either dyntick-idle or
197 adaptive-ticks state by doing all of the following:
200 de-jittered is marked as an adaptive-ticks CPU using the
204 when it is non-idle, for example, by avoiding system
208 2. Enable RCU to do its processing remotely via dyntick-idle by
218 when it is non-idle, for example, by avoiding system
230 1. Run your workload at a real-time priority, which will allow
248 b. Limit your CPU frequency so that a CPU-frequency
253 avoid the CPU-frequency governor periodically running
258 c. As of v3.18, Christoph Lameter's on-demand vmstat workers
265 will make your virtual-memory statistics update more
267 a real-time priority, thus preempting vmstat_update(),
268 but if your workload is CPU-bound, this is a bad idea.
270 (based on an earlier one from Gilad Ben-Yossef) that
272 …workloads at https://lore.kernel.org/r/00000140e9dfd6bd-40db3d4f-c1be-434f-8132-7820f81bb586-00000…
273 d. If running on high-end powerpc servers, build with
287 CONFIG_PMAC_RACKMETER=n to disable the CPU-meter,