summaryrefslogtreecommitdiffstats
path: root/Documentation/trace
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-12-29 14:21:49 -0500
committerLinus Torvalds <torvalds@linux-foundation.org>2018-12-29 14:21:49 -0500
commit3868772b99e3146d02cf47e739d79022eba1d77c (patch)
treed32c0283496e6955937b618981766b5f0878724f /Documentation/trace
parent6f9d71c9c759b1e7d31189a4de228983192c7dc7 (diff)
parent942104a21ce4951420ddf6c6b3179a0627301f7e (diff)
Merge tag 'docs-5.0' of git://git.lwn.net/linux
Pull documentation update from Jonathan Corbet: "A fairly normal cycle for documentation stuff. We have a new document on perf security, more Italian translations, more improvements to the memory-management docs, improvements to the pathname lookup documentation, and the usual array of smaller fixes. As is often the case, there are a few reaches outside of Documentation/ to adjust kerneldoc comments" * tag 'docs-5.0' of git://git.lwn.net/linux: (38 commits) docs: improve pathname-lookup document structure configfs: fix wrong name of struct in documentation docs/mm-api: link slab_common.c to "The Slab Cache" section slab: make kmem_cache_create{_usercopy} description proper kernel-doc doc:process: add links where missing docs/core-api: make mm-api.rst more structured x86, boot: documentation whitespace fixup Documentation: devres: note checking needs when converting doc:it: add some process/* translations doc:it: fixes in process/1.Intro Documentation: convert path-lookup from markdown to resturctured text Documentation/admin-guide: update admin-guide index.rst Documentation/admin-guide: introduce perf-security.rst file scripts/kernel-doc: Fix struct and struct field attribute processing Documentation: dev-tools: Fix typos in index.rst Correct gen_init_cpio tool's documentation Document /proc/pid PID reuse behavior Documentation: update path-lookup.md for parallel lookups Documentation: Use "while" instead of "whilst" dmaengine: Add mailing list address to the documentation ...
Diffstat (limited to 'Documentation/trace')
-rw-r--r--Documentation/trace/ftrace.rst14
1 files changed, 7 insertions, 7 deletions
diff --git a/Documentation/trace/ftrace.rst b/Documentation/trace/ftrace.rst
index f82434f2795e..0131df7f5968 100644
--- a/Documentation/trace/ftrace.rst
+++ b/Documentation/trace/ftrace.rst
@@ -24,13 +24,13 @@ It can be used for debugging or analyzing latencies and
24performance issues that take place outside of user-space. 24performance issues that take place outside of user-space.
25 25
26Although ftrace is typically considered the function tracer, it 26Although ftrace is typically considered the function tracer, it
27is really a frame work of several assorted tracing utilities. 27is really a framework of several assorted tracing utilities.
28There's latency tracing to examine what occurs between interrupts 28There's latency tracing to examine what occurs between interrupts
29disabled and enabled, as well as for preemption and from a time 29disabled and enabled, as well as for preemption and from a time
30a task is woken to the task is actually scheduled in. 30a task is woken to the task is actually scheduled in.
31 31
32One of the most common uses of ftrace is the event tracing. 32One of the most common uses of ftrace is the event tracing.
33Through out the kernel is hundreds of static event points that 33Throughout the kernel is hundreds of static event points that
34can be enabled via the tracefs file system to see what is 34can be enabled via the tracefs file system to see what is
35going on in certain parts of the kernel. 35going on in certain parts of the kernel.
36 36
@@ -462,7 +462,7 @@ of ftrace. Here is a list of some of the key files:
462 462
463 mono_raw: 463 mono_raw:
464 This is the raw monotonic clock (CLOCK_MONOTONIC_RAW) 464 This is the raw monotonic clock (CLOCK_MONOTONIC_RAW)
465 which is montonic but is not subject to any rate adjustments 465 which is monotonic but is not subject to any rate adjustments
466 and ticks at the same rate as the hardware clocksource. 466 and ticks at the same rate as the hardware clocksource.
467 467
468 boot: 468 boot:
@@ -914,8 +914,8 @@ The above is mostly meaningful for kernel developers.
914 current trace and the next trace. 914 current trace and the next trace.
915 915
916 - '$' - greater than 1 second 916 - '$' - greater than 1 second
917 - '@' - greater than 100 milisecond 917 - '@' - greater than 100 millisecond
918 - '*' - greater than 10 milisecond 918 - '*' - greater than 10 millisecond
919 - '#' - greater than 1000 microsecond 919 - '#' - greater than 1000 microsecond
920 - '!' - greater than 100 microsecond 920 - '!' - greater than 100 microsecond
921 - '+' - greater than 10 microsecond 921 - '+' - greater than 10 microsecond
@@ -2541,7 +2541,7 @@ At compile time every C file object is run through the
2541recordmcount program (located in the scripts directory). This 2541recordmcount program (located in the scripts directory). This
2542program will parse the ELF headers in the C object to find all 2542program will parse the ELF headers in the C object to find all
2543the locations in the .text section that call mcount. Starting 2543the locations in the .text section that call mcount. Starting
2544with gcc verson 4.6, the -mfentry has been added for x86, which 2544with gcc version 4.6, the -mfentry has been added for x86, which
2545calls "__fentry__" instead of "mcount". Which is called before 2545calls "__fentry__" instead of "mcount". Which is called before
2546the creation of the stack frame. 2546the creation of the stack frame.
2547 2547
@@ -2978,7 +2978,7 @@ The following commands are supported:
2978 When the function is hit, it will dump the contents of the ftrace 2978 When the function is hit, it will dump the contents of the ftrace
2979 ring buffer to the console. This is useful if you need to debug 2979 ring buffer to the console. This is useful if you need to debug
2980 something, and want to dump the trace when a certain function 2980 something, and want to dump the trace when a certain function
2981 is hit. Perhaps its a function that is called before a tripple 2981 is hit. Perhaps it's a function that is called before a triple
2982 fault happens and does not allow you to get a regular dump. 2982 fault happens and does not allow you to get a regular dump.
2983 2983
2984- cpudump: 2984- cpudump: