Lines Matching +full:entry +full:- +full:latency
1 # SPDX-License-Identifier: GPL-2.0-only
21 API, which will be used by other function-entry hooking
27 See Documentation/trace/ftrace-design.rst
32 See Documentation/trace/ftrace-design.rst
40 See Documentation/trace/ftrace-design.rst
69 See Documentation/trace/ftrace-design.rst
74 See Documentation/trace/ftrace-design.rst
79 Arch supports the gcc options -pg with -mfentry
84 Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
89 Arch supports objtool --mcount
94 Arch supports the objtool options --mcount with --mnop.
192 bool "Boot-time Tracing support"
211 by using a compiler feature to insert a small, 5-byte No-Operation
216 small and not measurable even in micro-benchmarks (at least on
227 and its entry.
242 enable it via the trace option funcgraph-retval.
253 replace them with a No-Op instruction) on boot up. During
328 stack-trace saved. If this is configured with DYNAMIC_FTRACE
347 bool "Interrupts-off Latency Tracer"
357 This option measures the time spent in irqs-off critical
361 disabled by default and can be runtime (re-)started
367 enabled. This option and the preempt-off timing option can be
371 bool "Preemption-off Latency Tracer"
381 This option measures the time spent in preemption-off critical
385 disabled by default and can be runtime (re-)started
391 enabled. This option and the irqs-off timing option can be
395 bool "Scheduling Latency Tracer"
401 This tracer tracks the latency of the highest priority task
420 hwlat_detector/width - time in usecs for how long to spin for
421 hwlat_detector/window - time in usecs between the start of each
426 for "window - width" microseconds, where the system can
437 file. Every time a latency is greater than tracing_thresh, it will
445 In the context of high-performance computing (HPC), the Operating
449 can cause noise to the system. Moreover, hardware-related jobs can
455 note of the entry and exit point of any source of interferences,
456 increasing a per-cpu interference counter. It saves an interference
459 observes these interferences' entry events. When a noise happens
461 hardware noise counter increases, pointing to a hardware-related
481 to find sources of wakeup latencies of real-time threads.
483 The tracer creates a per-cpu kernel thread with real-time priority.
486 then computes a wakeup latency value as the difference between
491 timer latency observed at the hardirq context before the
492 activation of the thread. The second is the timer latency observed
511 default and can be enabled at run-time.
531 Basic tracer to catch the syscall entry and exit events.
561 or irq latency tracers are enabled, as those need to swap as well
578 The "all branch" profiler will profile every if-statement in the
671 bool "Enable fprobe-based dynamic events"
677 This allows user to add tracing events on the function entry and
679 and the kprobe events on function entry and exit will be
691 kernel function entry or a tracepoint.
697 bool "Enable kprobes-based dynamic events"
710 This option is also required by perf-probe subcommand of perf tools.
723 functions are protected from kprobe-events to prevent an infinite
734 bool "Enable uprobes-based dynamic events"
748 This option is required if you plan to use perf-probe subcommand
786 depends on $(cc-option,-mrecord-mcount)
809 tracing_map is a special-purpose lock-free map for tracing,
810 separated out as a stand-alone facility in order to allow it
821 Synthetic events are user-defined trace events that can be
825 by way of an in-kernel API.
837 User trace events are user-defined trace events that
863 Inter-event tracing of quantities such as latencies is also
873 Allow user-space to inject a specific trace event into the ring
1048 TBD - enable a way to actually call the syscalls as we test their
1059 is not done correctly, it will cause non-deterministic failures.
1119 tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers"
1122 Select this option to build a test module that can help test latency
1128 irq-disabled critical sections for 500us:
1131 What's more, if you want to attach the test on the cpu which the latency
1138 tristate "Test module for in-kernel synthetic event generation"
1142 functionality of in-kernel synthetic event definition and
1151 tristate "Test module for in-kernel kprobe event generation"
1155 functionality of in-kernel kprobe event definition.
1172 - Helps developers verify that nothing is broken.
1174 - Provides educational information to support the details
1176 Documentation/trace/histogram-design.rst.