diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-21 12:15:07 -0400 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2009-09-21 12:15:07 -0400 |
| commit | 43c1266ce4dc06bfd236cec31e11e9ecd69c0bef (patch) | |
| tree | 40a86739ca4c36200f447f655b01c57cfe646e26 /init | |
| parent | b8c7f1dc5ca4e0d10709182233cdab932cef593d (diff) | |
| parent | 57c0c15b5244320065374ad2c54f4fbec77a6428 (diff) | |
Merge branch 'perfcounters-rename-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'perfcounters-rename-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
perf: Tidy up after the big rename
perf: Do the big rename: Performance Counters -> Performance Events
perf_counter: Rename 'event' to event_id/hw_event
perf_counter: Rename list_entry -> group_entry, counter_list -> group_list
Manually resolved some fairly trivial conflicts with the tracing tree in
include/trace/ftrace.h and kernel/trace/trace_syscalls.c.
Diffstat (limited to 'init')
| -rw-r--r-- | init/Kconfig | 45 |
1 files changed, 31 insertions, 14 deletions
diff --git a/init/Kconfig b/init/Kconfig index 0121c0ea3e03..0aa6579504cc 100644 --- a/init/Kconfig +++ b/init/Kconfig | |||
| @@ -916,31 +916,36 @@ config AIO | |||
| 916 | by some high performance threaded applications. Disabling | 916 | by some high performance threaded applications. Disabling |
| 917 | this option saves about 7k. | 917 | this option saves about 7k. |
| 918 | 918 | ||
| 919 | config HAVE_PERF_COUNTERS | 919 | config HAVE_PERF_EVENTS |
| 920 | bool | 920 | bool |
| 921 | help | 921 | help |
| 922 | See tools/perf/design.txt for details. | 922 | See tools/perf/design.txt for details. |
| 923 | 923 | ||
| 924 | menu "Performance Counters" | 924 | menu "Kernel Performance Events And Counters" |
| 925 | 925 | ||
| 926 | config PERF_COUNTERS | 926 | config PERF_EVENTS |
| 927 | bool "Kernel Performance Counters" | 927 | bool "Kernel performance events and counters" |
| 928 | default y if PROFILING | 928 | default y if (PROFILING || PERF_COUNTERS) |
| 929 | depends on HAVE_PERF_COUNTERS | 929 | depends on HAVE_PERF_EVENTS |
| 930 | select ANON_INODES | 930 | select ANON_INODES |
| 931 | help | 931 | help |
| 932 | Enable kernel support for performance counter hardware. | 932 | Enable kernel support for various performance events provided |
| 933 | by software and hardware. | ||
| 934 | |||
| 935 | Software events are supported either build-in or via the | ||
| 936 | use of generic tracepoints. | ||
| 933 | 937 | ||
| 934 | Performance counters are special hardware registers available | 938 | Most modern CPUs support performance events via performance |
| 935 | on most modern CPUs. These registers count the number of certain | 939 | counter registers. These registers count the number of certain |
| 936 | types of hw events: such as instructions executed, cachemisses | 940 | types of hw events: such as instructions executed, cachemisses |
| 937 | suffered, or branches mis-predicted - without slowing down the | 941 | suffered, or branches mis-predicted - without slowing down the |
| 938 | kernel or applications. These registers can also trigger interrupts | 942 | kernel or applications. These registers can also trigger interrupts |
| 939 | when a threshold number of events have passed - and can thus be | 943 | when a threshold number of events have passed - and can thus be |
| 940 | used to profile the code that runs on that CPU. | 944 | used to profile the code that runs on that CPU. |
| 941 | 945 | ||
| 942 | The Linux Performance Counter subsystem provides an abstraction of | 946 | The Linux Performance Event subsystem provides an abstraction of |
| 943 | these hardware capabilities, available via a system call. It | 947 | these software and hardware cevent apabilities, available via a |
| 948 | system call and used by the "perf" utility in tools/perf/. It | ||
| 944 | provides per task and per CPU counters, and it provides event | 949 | provides per task and per CPU counters, and it provides event |
| 945 | capabilities on top of those. | 950 | capabilities on top of those. |
| 946 | 951 | ||
| @@ -948,17 +953,29 @@ config PERF_COUNTERS | |||
| 948 | 953 | ||
| 949 | config EVENT_PROFILE | 954 | config EVENT_PROFILE |
| 950 | bool "Tracepoint profiling sources" | 955 | bool "Tracepoint profiling sources" |
| 951 | depends on PERF_COUNTERS && EVENT_TRACING | 956 | depends on PERF_EVENTS && EVENT_TRACING |
| 952 | default y | 957 | default y |
| 953 | help | 958 | help |
| 954 | Allow the use of tracepoints as software performance counters. | 959 | Allow the use of tracepoints as software performance events. |
| 955 | 960 | ||
| 956 | When this is enabled, you can create perf counters based on | 961 | When this is enabled, you can create perf events based on |
| 957 | tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID | 962 | tracepoints using PERF_TYPE_TRACEPOINT and the tracepoint ID |
| 958 | found in debugfs://tracing/events/*/*/id. (The -e/--events | 963 | found in debugfs://tracing/events/*/*/id. (The -e/--events |
| 959 | option to the perf tool can parse and interpret symbolic | 964 | option to the perf tool can parse and interpret symbolic |
| 960 | tracepoints, in the subsystem:tracepoint_name format.) | 965 | tracepoints, in the subsystem:tracepoint_name format.) |
| 961 | 966 | ||
| 967 | config PERF_COUNTERS | ||
| 968 | bool "Kernel performance counters (old config option)" | ||
| 969 | depends on HAVE_PERF_EVENTS | ||
| 970 | help | ||
| 971 | This config has been obsoleted by the PERF_EVENTS | ||
| 972 | config option - please see that one for details. | ||
| 973 | |||
| 974 | It has no effect on the kernel whether you enable | ||
| 975 | it or not, it is a compatibility placeholder. | ||
| 976 | |||
| 977 | Say N if unsure. | ||
| 978 | |||
| 962 | endmenu | 979 | endmenu |
| 963 | 980 | ||
| 964 | config VM_EVENT_COUNTERS | 981 | config VM_EVENT_COUNTERS |
