Lines Matching refs:a
89 Adds a very slight overhead to tracing when enabled.
151 by using a compiler feature to insert a small, 5-byte No-Operation
153 sequence is then dynamically patched into a tracer call when
165 Enable the kernel to trace a function at both its return
168 draw a call graph for each thread with some information like
170 address on the current task structure into a stack of calls.
202 The default measurement method is a maximum search, which is
227 The default measurement method is a maximum search, which is
253 spinning in a loop looking for interruptions caused by
254 something other than the kernel. For example, if a
255 System Management Interrupt (SMI) takes a noticeable amount of
257 if a system is reliable for Real Time tasks.
275 periodically non responsive. Do not run this tracer on a
279 file. Every time a latency is greater than tracing_thresh, it will
300 bool "Create a snapshot trace buffer"
314 Allow doing a snapshot of a single CPU buffer instead of a
323 When this is enabled, this adds a little more overhead to the
328 and already adds the overhead (plus a lot more).
338 The branch profiling is a software profiler. It will add hooks
339 into the C conditionals to test which path a branch takes.
342 are annotated with a likely or unlikely macro.
348 Either of the above profilers adds a bit of overhead to the system.
354 No branch profiling. Branch profiling adds a bit of overhead.
367 Note: this will add a significant overhead; only turn this
383 This configuration, when enabled, will impose a great overhead
403 "Trace likely/unlikely profiler" is that this is not a
405 events into a running trace buffer to see when and where the
421 kernel executes, and keeping a maximum stack depth value and
445 on a given queue. Tracing allows you to see any traffic happening
446 on a block device queue. For more information (and the userspace
489 recursion or any unexpected execution path which leads to a kernel
539 replace them with a No-Op instruction) on boot up. During
540 compile time, a table is made of all the locations that ftrace
551 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
566 When a 1 is echoed into this file profiling begins, and when a
574 bool "Enable BPF programs to override a kprobed function"
579 Allows BPF to override the execution of a probed function and
580 set a different return value. This is used for error injection.
591 bool "Perform a startup test on ftrace"
595 This option performs a series of startup tests on ftrace. On bootup
596 a series of tests are made to verify that the tracer is
605 This option performs a test on all trace events in the system.
608 This may take some time run as there are a lot of events.
616 with the event enabled. This adds a bit more time for kernel boot
619 TBD - enable a way to actually call the syscalls as we test their
639 tracing_map is a special-purpose lock-free map for tracing,
640 separated out as a stand-alone facility in order to allow it
655 reading a debugfs/tracefs file. They're useful for
670 This is a dumb module for testing mmiotrace. It is very dangerous
671 as it will write garbage to IO memory starting at a given address.
680 When the tracepoint is enabled, it kicks off a kernel thread that
686 The string written to the tracepoint is a static string of 128 bytes
687 to keep the time the same. The initial string is simply a write of
691 As it is a tight loop, it benchmarks as hot cache. That's fine because
710 This option creates a test to stress the ring buffer and benchmark it.
713 a producer and consumer that will run for 10 seconds and sleep for
715 it recorded and give a rough estimate of how long each iteration took.
726 Run a simple self test on the ring buffer on boot up. Late in the
728 a thread per cpu. Each thread will write various size events
732 If any anomalies are discovered, a warning will be displayed
749 Select this option to build a test module that can help test latency
750 tracers by executing a preempt or irq disable section with a user
754 For example, the following invocation forces a one-time irq-disabled
769 To fix this, there's a special macro in the kernel that can be used
797 Note that on a kernel compiled with this config, ftrace will