linux/tools/perf
Michael Ellerman e9a7c41447 perf tools: Add support for pinned modifier
This commit adds support for a new modifier "D", which requests that the
event, or group of events, be pinned to the PMU.

The "p" modifier is already taken for precise, and "P" may be used in
future to mean "fully precise".

So we use "D", which stands for pinneD - and looks like a padlock, or if
you're using the ":D" syntax perf smiles at you.

This is an oft-requested feature from our HW folks, who want to be able
to run a large number of events, but also want 100% accurate results for
instructions per cycle.

Comparison of results with and without pinning:

$ perf stat -e '{cycles,instructions}:D' -e cycles,instructions,...

  79,590,480,683 cycles         #  0.000 GHz
 166,123,716,524 instructions   #  2.09  insns per cycle
                                #  0.11  stalled cycles per insn

  79,352,134,463 cycles         #  0.000 GHz                     [11.11%]
 165,178,301,818 instructions   #  2.08  insns per cycle
                                #  0.11  stalled cycles per insn [11.13%]

As you can see although perf does a very good job of scaling the values
in the non-pinned case, there is some small discrepancy.

The patch is fairly straight forward, the one detail is that we need to
make sure we only request pinning for the group leader when we have a
group.

Signed-off-by: Michael Ellerman <michael@ellerman.id.au>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Tested-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1375795686-4226-1-git-send-email-michael@ellerman.id.au
[ Use perf_evsel__is_group_leader instead of open coded equivalent, as
  suggested by Jiri Olsa ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-08-07 17:35:40 -03:00
..
arch perf tools: Fix compile of util/tsc.c 2013-08-07 17:35:24 -03:00
bench perf bench: Fix memcpy benchmark for large sizes 2013-07-22 12:41:56 -03:00
config perf tools: Use default include path notation for libtraceevent headers 2013-07-12 13:45:54 -03:00
Documentation perf tools: Add support for pinned modifier 2013-08-07 17:35:40 -03:00
python perf python: Remove duplicate TID bit from mask 2013-08-07 17:35:25 -03:00
scripts perf script: Fix broken include in Context.xs 2013-07-10 13:47:00 -03:00
tests perf tests: Add kcore to the object code reading test 2013-08-07 17:35:34 -03:00
ui perf ui/gtk: Fix segmentation fault on perf_hpp__for_each_format loop 2013-08-07 17:35:39 -03:00
util perf tools: Add support for pinned modifier 2013-08-07 17:35:40 -03:00
.gitignore perf tools: Ignore compiled python binaries 2012-09-07 12:10:58 -03:00
bash_completion perf tools: Complete tracepoint event names 2012-10-04 12:44:52 -03:00
builtin-annotate.c perf tools: Add support for weight v7 (modified) 2013-04-01 12:19:43 -03:00
builtin-bench.c perf tools: Make numa benchmark optional 2013-01-30 10:36:21 -03:00
builtin-buildid-cache.c perf buildid-cache: Add --update option 2013-02-14 14:59:27 -03:00
builtin-buildid-list.c perf symbols: Generalize filter in __fprintf_buildid methods 2012-12-09 08:46:07 -03:00
builtin-diff.c perf diff: Add generic order option for compute sorting 2013-07-12 13:54:16 -03:00
builtin-evlist.c perf evlist: Pass the event_group info via perf_attr_details 2013-02-06 18:09:28 -03:00
builtin-help.c perf help: Fix --help for builtins 2012-10-22 12:35:49 -02:00
builtin-inject.c perf symbols: Load kernel maps before using 2013-08-07 17:35:31 -03:00
builtin-kmem.c perf tools: struct thread has a tid not a pid 2013-07-12 13:53:50 -03:00
builtin-kvm.c perf kvm stat report: Add option to analyze specific VM 2013-08-07 17:35:39 -03:00
builtin-list.c perf list: List kernel supplied event aliases 2013-07-12 13:53:53 -03:00
builtin-lock.c perf record: Remove -f/--force option 2013-07-08 17:37:25 -03:00
builtin-mem.c perf tools: Add new mem command for memory access profiling 2013-04-01 12:21:44 -03:00
builtin-probe.c perf tools: Introduce tools/lib/lk library 2013-03-15 13:06:00 -03:00
builtin-record.c perf tools: Remove event types framework completely 2013-07-15 16:28:22 -03:00
builtin-report.c perf tools: Support callchain sorting based on addresses 2013-07-22 12:42:18 -03:00
builtin-sched.c perf tools: struct thread has a tid not a pid 2013-07-12 13:53:50 -03:00
builtin-script.c perf symbols: Load kernel maps before using 2013-08-07 17:35:31 -03:00
builtin-stat.c perf stat: Flush output after each line in interval mode 2013-08-07 17:35:29 -03:00
builtin-timechart.c perf timechart: Remove event types framework only user 2013-07-15 16:14:47 -03:00
builtin-top.c perf annotate: Allow disassembly using /proc/kcore 2013-08-07 17:35:34 -03:00
builtin-trace.c perf trace: Beautify 'connect' result 2013-08-07 17:35:25 -03:00
builtin.h perf tools: Add new mem command for memory access profiling 2013-04-01 12:21:44 -03:00
command-list.txt perf tools: Add new mem command for memory access profiling 2013-04-01 12:21:44 -03:00
CREDITS
design.txt perf tools: Update ioctl documentation for PERF_IOC_FLAG_GROUP 2012-05-31 11:38:42 -03:00
Makefile perf tests: Add test for reading object code 2013-08-07 17:35:30 -03:00
MANIFEST perf tools: Introduce tools/lib/lk library 2013-03-15 13:06:00 -03:00
perf-archive.sh perf archive: Make 'f' the last parameter for tar 2012-09-17 13:10:42 -03:00
perf.c perf tools: Convert needless static variable to local 2013-04-01 12:22:48 -03:00
perf.h perf tools: Add support for weight v7 (modified) 2013-04-01 12:19:43 -03:00