Lines Matching refs:that

4 This document describes Kconfig options and boot parameters that can
21 3.	Omit scheduling-clock ticks on CPUs that are either idle or that
34 are incapable of omitting scheduling-clock ticks.  It turns out that
37 that use short bursts of CPU, where there are very frequent idle
75 1,500 OS instances might find that half of its CPU time was consumed by
90 An idle CPU that is not receiving scheduling-clock interrupts is said to
94 There is also a boot parameter "nohz=" that can be used to disable
104 Note that omitting scheduling-clock ticks for CPUs with only one runnable
121 "nohz_full=1,6-8" says that CPUs 1, 6, 7, and 8 are to be adaptive-ticks
122 CPUs.  Note that you are prohibited from marking all of the CPUs as
124 online to handle timekeeping tasks in order to ensure that system
129 "nohz_full=" mask that includes the boot CPU will result in a boot-time
130 error message, and the boot CPU will be removed from the mask.  Note that
131 this means that your system must have at least two CPUs in order for
135 that all CPUs other than the boot CPU are adaptive-ticks CPUs.  This
137 so that if both the CONFIG_NO_HZ_FULL_ALL=y Kconfig parameter and
139 prevail so that only CPU 1 will be an adaptive-ticks CPU.
147 for example, if that CPU enqueues an RCU callback.
154 	extends down into the implementation, so that all of the costs
180 However, the drawbacks listed above mean that adaptive ticks should not
188 common being when that CPU has RCU callbacks pending.
193 that the RCU callbacks are processed in a timely fashion.
209 		CPUs to be offloaded.  Note that the callbacks will be
210 		offloaded to "rcuo" kthreads, and that those kthreads
221 	CONFIG_RCU_NOCB_CPU_ALL=y.  This means that the "rcu_nocbs=" boot
226 or adaptive-tick mode.  That said, note that it is up to userspace to
236 your workload isn't affected that much by OS jitter, or is it because
244 This test procedure will produce a trace that will allow you to evaluate
246 If this trace shows that you have removed OS jitter as much as is
247 possible, then you can conclude that your workload is not all that
250 Note: this test requires that your system have at least two CPUs.
260 	dyntick-idle mode, an option that most of them take.  However,
274 		However, please note that use of this parameter can cause
276 		to degrade your latencies -- and that this degradation can
277 		be even worse than that of dyntick-idle.  Furthermore,
290 	needed.  To give but one example, consider a CPU that has one
302 	there is little point in interrupting that CPU until the current
312 	Especially given that you have the straightforward option of
324 	operations (such as kernel module unload operations) that