Lines Matching +full:buffer +full:- +full:enable
1 # SPDX-License-Identifier: GPL-2.0-only
20 Enable generic return hooking feature. This is an internal
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
45 See Documentation/trace/ftrace-design.rst
95 See Documentation/trace/ftrace-design.rst
100 Arch supports the gcc options -pg with -mfentry
105 Arch supports the gcc options -pg with -mrecord-mcount and -nop-mcount
110 Arch supports objtool --mcount
115 Arch supports the objtool options --mcount with --mnop.
116 An architecture can select this if it wants to enable nop'ing
217 Enable the kernel tracing infrastructure.
235 bool "Boot-time Tracing support"
239 Enable developer to setup ftrace subsystem via supplemental
253 Enable the kernel to trace every kernel function. This is done
254 by using a compiler feature to insert a small, 5-byte No-Operation
259 small and not measurable even in micro-benchmarks (at least on
269 Enable the kernel to trace a function at both its return
285 enable it via the trace option funcgraph-retval.
296 enable it via the trace option funcgraph-retaddr.
306 enabled via the trace option func-args (for the function tracer) and
307 funcgraph-args (for the function graph tracer)
317 replace them with a No-Op instruction) on boot up. During
364 Enable this to allow some of the tracing infrastructure to be traced
411 stack-trace saved. If this is configured with DYNAMIC_FTRACE
415 To enable the stack tracer on bootup, pass in 'stacktrace'
430 bool "Interrupts-off Latency Tracer"
439 This option measures the time spent in irqs-off critical
443 disabled by default and can be runtime (re-)started
449 enabled. This option and the preempt-off timing option can be
453 bool "Preemption-off Latency Tracer"
462 This option measures the time spent in preemption-off critical
466 disabled by default and can be runtime (re-)started
472 enabled. This option and the irqs-off timing option can be
500 hwlat_detector/width - time in usecs for how long to spin for
501 hwlat_detector/window - time in usecs between the start of each
506 for "window - width" microseconds, where the system can
516 To enable this tracer, echo in "hwlat" into the current_tracer
518 be recorded into the ring buffer.
525 In the context of high-performance computing (HPC), the Operating
529 can cause noise to the system. Moreover, hardware-related jobs can
536 increasing a per-cpu interference counter. It saves an interference
541 hardware noise counter increases, pointing to a hardware-related
552 To enable this tracer, echo in "osnoise" into the current_tracer
561 to find sources of wakeup latencies of real-time threads.
563 The tracer creates a per-cpu kernel thread with real-time priority.
591 default and can be enabled at run-time.
628 bool "Create a snapshot trace buffer"
630 Allow tracing users to take snapshot of the current buffer using the
644 Allow doing a snapshot of a single CPU buffer instead of a
650 After which, only the tracing buffer for CPU 2 was swapped with
651 the main tracing buffer, and the other CPU buffers remain the same.
674 The "all branch" profiler will profile every if-statement in the
675 kernel. This profiler will also enable the likely/unlikely
685 Only enable it if you want to analyse the branching behavior.
734 events into a running trace buffer to see when and where the
758 echo 1 > /sys/block/sda/sda1/trace/enable
767 bool "Enable fprobe-based dynamic events"
791 bool "Dump of dynamic probe event fetch-arguments"
795 This shows the dump of fetch-arguments of dynamic probe events
799 it might be a security risk. Only enable it if you need to debug
805 bool "Enable kprobes-based dynamic events"
818 This option is also required by perf-probe subcommand of perf tools.
831 functions are protected from kprobe-events to prevent an infinite
842 bool "Enable uprobes-based dynamic events"
856 This option is required if you plan to use perf-probe subcommand
860 bool "Enable event-based dynamic events"
889 bool "Enable BPF programs to override a kprobed function"
903 depends on $(cc-option,-mrecord-mcount)
926 tracing_map is a special-purpose lock-free map for tracing,
927 separated out as a stand-alone facility in order to allow it
938 Synthetic events are user-defined trace events that can be
942 by way of an in-kernel API.
954 User trace events are user-defined trace events that
980 Inter-event tracing of quantities such as latencies is also
990 Allow user-space to inject a specific trace event into the ring
991 buffer. This is mainly used for testing purpose.
1026 tristate "Ring buffer benchmark stress tester"
1029 This option creates a test to stress the ring buffer and benchmark it.
1030 It creates its own ring buffer such that it will not interfere with
1031 any other users of the ring buffer (such as ftrace). It then creates
1108 bool "Record functions that recurse in the ring buffer"
1113 The ring buffer has its own internal recursion. Although when
1122 bool "Enable GCOV profiling on ftrace subsystem"
1125 Enable GCOV profiling on ftrace subsystem for checking
1160 This option will also enable testing every syscall event.
1165 TBD - enable a way to actually call the syscalls as we test their
1176 is not done correctly, it will cause non-deterministic failures.
1183 bool "Ring buffer startup self test"
1186 Run a simple self test on the ring buffer on boot up. Late in the
1189 into the ring buffer. Another thread is created to send IPIs
1191 to the ring buffer, to test/stress the nesting ability.
1199 It will output the stats of each per cpu buffer: What
1206 bool "Verify ring buffer time stamp deltas"
1209 This will audit the time stamps on the ring buffer sub
1210 buffer to make sure that all the time deltas for the
1211 events on a sub buffer matches the current time stamp.
1215 that all the deltas on the previous sub buffer do not
1219 and should only be used to test the logic of the ring buffer.
1226 bool "Enable persistent ring buffer error injection test"
1230 buffer is named "ptracingtest". and if so, it will corrupt some
1232 persistent ring buffer can recover from some of its sub-buffers
1235 ring buffer, e.g.
1242 echo 1 > events/enable
1245 echo c > /proc/sysrq-trigger
1250 Note that events for the test ring buffer needs to be enabled
1251 prior to crashing the kernel so that the ring buffer has content
1254 ring buffer, it should not be used for any other purpose other
1279 irq-disabled critical sections for 500us:
1289 tristate "Test module for in-kernel synthetic event generation"
1293 functionality of in-kernel synthetic event definition and
1296 To test, insert the module, and then check the trace buffer
1302 tristate "Test module for in-kernel kprobe event generation"
1306 functionality of in-kernel kprobe event definition.
1308 To test, insert the module, and then check the trace buffer
1323 - Helps developers verify that nothing is broken.
1325 - Provides educational information to support the details
1327 Documentation/trace/histogram-design.rst.
1349 This trace remote includes a ring-buffer writer implementation using