Lines Matching refs:a
96 Adds a very slight overhead to tracing when enabled.
174 by using a compiler feature to insert a small, 5-byte No-Operation
176 sequence is then dynamically patched into a tracer call when
188 Enable the kernel to trace a function at both its return
191 draw a call graph for each thread with some information like
193 address on the current task structure into a stack of calls.
203 replace them with a No-Op instruction) on boot up. During
204 compile time, a table is made of all the locations that ftrace
215 This way a CONFIG_FUNCTION_TRACER kernel is slightly larger, but
240 When a 1 is echoed into this file profiling begins, and when a
258 kernel executes, and keeping a maximum stack depth value and
291 The default measurement method is a maximum search, which is
315 The default measurement method is a maximum search, which is
342 spinning in a loop looking for interruptions caused by
343 something other than the kernel. For example, if a
344 System Management Interrupt (SMI) takes a noticeable amount of
346 if a system is reliable for Real Time tasks.
364 periodically non responsive. Do not run this tracer on a
368 file. Every time a latency is greater than tracing_thresh, it will
383 The osnoise tracer leverages the hwlat_detector by running a similar
387 increasing a per-cpu interference counter. It saves an interference
390 observes these interferences' entry events. When a noise happens
392 hardware noise counter increases, pointing to a hardware-related
398 In addition to the tracer, a set of tracepoints were added to
414 The tracer creates a per-cpu kernel thread with real-time priority.
415 The tracer thread sets a periodic timer to wakeup itself, and goes
417 then computes a wakeup latency value as the difference between
465 bool "Create a snapshot trace buffer"
479 Allow doing a snapshot of a single CPU buffer instead of a
488 When this is enabled, this adds a little more overhead to the
493 and already adds the overhead (plus a lot more).
503 The branch profiling is a software profiler. It will add hooks
504 into the C conditionals to test which path a branch takes.
507 are annotated with a likely or unlikely macro.
513 Either of the above profilers adds a bit of overhead to the system.
519 No branch profiling. Branch profiling adds a bit of overhead.
532 Note: this will add a significant overhead; only turn this
547 This configuration, when enabled, will impose a great overhead
567 "Trace likely/unlikely profiler" is that this is not a
569 events into a running trace buffer to see when and where the
585 on a given queue. Tracing allows you to see any traffic happening
586 on a block device queue. For more information (and the userspace
629 recursion or any unexpected execution path which leads to a kernel
672 bool "Enable BPF programs to override a kprobed function"
677 Allows BPF to override the execution of a probed function and
678 set a different return value. This is used for error injection.
713 tracing_map is a special-purpose lock-free map for tracing,
714 separated out as a stand-alone facility in order to allow it
747 reading a debugfs/tracefs file. They're useful for
762 Allow user-space to inject a specific trace event into the ring
771 When the tracepoint is enabled, it kicks off a kernel thread that
777 The string written to the tracepoint is a static string of 128 bytes
778 to keep the time the same. The initial string is simply a write of
782 As it is a tight loop, it benchmarks as hot cache. That's fine because
801 This option creates a test to stress the ring buffer and benchmark it.
804 a producer and consumer that will run for 10 seconds and sleep for
806 it recorded and give a rough estimate of how long each iteration took.
822 To fix this, there's a special macro in the kernel that can be used
847 it adds overhead. This option will create a file in the tracefs
849 that triggered a recursion.
862 the functions that caused a recursion to happen.
889 Note that on a kernel compiled with this config, ftrace will
896 bool "Perform a startup test on ftrace"
900 This option performs a series of startup tests on ftrace. On bootup
901 a series of tests are made to verify that the tracer is
910 This option performs a test on all trace events in the system.
913 This may take some time run as there are a lot of events.
921 with the event enabled. This adds a bit more time for kernel boot
924 TBD - enable a way to actually call the syscalls as we test their
931 Run a simple self test on the ring buffer on boot up. Late in the
933 a thread per cpu. Each thread will write various size events
937 If any anomalies are discovered, a warning will be displayed
956 events on a sub buffer matches the current time stamp.
974 This is a dumb module for testing mmiotrace. It is very dangerous
975 as it will write garbage to IO memory starting at a given address.
981 tristate "Test module to create a preempt / IRQ disable delay thread to test latency tracers"
984 Select this option to build a test module that can help test latency
985 tracers by executing a preempt or irq disable section with a user
989 For example, the following invocation generates a burst of three
1003 This option creates a test module to check the base
1016 This option creates a test module to check the base
1029 dump out a bunch of internal details about the hist triggers
1032 The hist_debug file serves a couple of purposes: