Lines Matching +full:wakeup +full:- +full:latency
1 # SPDX-License-Identifier: GPL-2.0-only
16 See Documentation/trace/ftrace-design.rst
21 See Documentation/trace/ftrace-design.rst
26 See Documentation/trace/ftrace-design.rst
46 See Documentation/trace/ftrace-design.rst
51 See Documentation/trace/ftrace-design.rst
56 Arch supports the gcc options -pg with -mfentry
61 Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
66 Arch supports objtool --mcount
148 bool "Boot-time Tracing support"
167 by using a compiler feature to insert a small, 5-byte No-Operation
172 small and not measurable even in micro-benchmarks.
196 replace them with a No-Op instruction) on boot up. During
252 stack-trace saved. If this is configured with DYNAMIC_FTRACE
271 bool "Interrupts-off Latency Tracer"
281 This option measures the time spent in irqs-off critical
285 disabled by default and can be runtime (re-)started
291 enabled. This option and the preempt-off timing option can be
295 bool "Preemption-off Latency Tracer"
305 This option measures the time spent in preemption-off critical
309 disabled by default and can be runtime (re-)started
315 enabled. This option and the irqs-off timing option can be
319 bool "Scheduling Latency Tracer"
325 This tracer tracks the latency of the highest priority task
343 hwlat_detector/width - time in usecs for how long to spin for
344 hwlat_detector/window - time in usecs between the start of each
349 for "window - width" microseconds, where the system can
360 file. Every time a latency is greater than tracing_thresh, it will
367 In the context of high-performance computing (HPC), the Operating
371 can cause noise to the system. Moreover, hardware-related jobs can
378 increasing a per-cpu interference counter. It saves an interference
383 hardware noise counter increases, pointing to a hardware-related
403 to find sources of wakeup latencies of real-time threads.
405 The tracer creates a per-cpu kernel thread with real-time priority.
406 The tracer thread sets a periodic timer to wakeup itself, and goes
407 to sleep waiting for the timer to fire. At the wakeup, the thread
408 then computes a wakeup latency value as the difference between
413 timer latency observed at the hardirq context before the
414 activation of the thread. The second is the timer latency observed
433 default and can be enabled at run-time.
483 or irq latency tracers are enabled, as those need to swap as well
500 The "all branch" profiler will profile every if-statement in the
593 bool "Enable kprobes-based dynamic events"
606 This option is also required by perf-probe subcommand of perf tools.
619 functions are protected from kprobe-events to prevent an infinite
630 bool "Enable uprobes-based dynamic events"
644 This option is required if you plan to use perf-probe subcommand
682 depends on $(cc-option,-mrecord-mcount)
704 tracing_map is a special-purpose lock-free map for tracing,
705 separated out as a stand-alone facility in order to allow it
716 Synthetic events are user-defined trace events that can be
720 by way of an in-kernel API.
743 Inter-event tracing of quantities such as latencies is also
753 Allow user-space to inject a specific trace event into the ring
915 TBD - enable a way to actually call the syscalls as we test their
972 tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers"
975 Select this option to build a test module that can help test latency
981 irq-disabled critical sections for 500us:
984 What's more, if you want to attach the test on the cpu which the latency
991 tristate "Test module for in-kernel synthetic event generation"
995 functionality of in-kernel synthetic event definition and
1004 tristate "Test module for in-kernel kprobe event generation"
1008 functionality of in-kernel kprobe event definition.
1025 - Helps developers verify that nothing is broken.
1027 - Provides educational information to support the details
1029 Documentation/trace/histogram-design.rst.