This patch allows perf record setting event's attr.inherit bit by
config terms like:
# perf record -e cycles/no-inherit/ ...
# perf record -e cycles/inherit/ ...
So user can control inherit bit for each event separately.
In following example, a.out fork()s in main then do some complex
CPU intensive computations in both of its children.
Basic result with and without inherit:
# perf record -e cycles -e instructions ./a.out
[ perf record: Woken up 9 times to write data ]
[ perf record: Captured and wrote 2.205 MB perf.data (47920 samples) ]
# perf report --stdio
# ...
# Samples: 23K of event 'cycles'
# Event count (approx.): 23641752891
...
# Samples: 24K of event 'instructions'
# Event count (approx.): 30428312415
# perf record -i -e cycles -e instructions ./a.out
[ perf record: Woken up 5 times to write data ]
[ perf record: Captured and wrote 1.111 MB perf.data (24019 samples) ]
...
# Samples: 12K of event 'cycles'
# Event count (approx.): 11699501775
...
# Samples: 12K of event 'instructions'
# Event count (approx.): 15058023559
Cancel inherit for one event when globally enable:
# perf record -e cycles/no-inherit/ -e instructions ./a.out
[ perf record: Woken up 7 times to write data ]
[ perf record: Captured and wrote 1.660 MB perf.data (36004 samples) ]
...
# Samples: 12K of event 'cycles/no-inherit/'
# Event count (approx.): 11895759282
...
# Samples: 24K of event 'instructions'
# Event count (approx.): 30668000441
Enable inherit for one event when globally disable:
# perf record -i -e cycles/inherit/ -e instructions ./a.out
[ perf record: Woken up 7 times to write data ]
[ perf record: Captured and wrote 1.654 MB perf.data (35868 samples) ]
...
# Samples: 23K of event 'cycles/inherit/'
# Event count (approx.): 23285400229
...
# Samples: 11K of event 'instructions'
# Event count (approx.): 14969050259
Committer note:
One can check if the bit was set, in addition to seeing the result in
the perf.data file size as above by doing one of:
# perf record -e cycles -e instructions -a usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.911 MB perf.data (63 samples) ]
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, freq: 1, sample_id_all: 1, exclude_guest: 1
#
So, the inherit bit was set in both, now, if we disable it globally using
--no-inherit:
# perf record --no-inherit -e cycles -e instructions -a usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.910 MB perf.data (56 samples) ]
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, freq: 1, sample_id_all: 1, exclude_guest: 1
No inherit bit set, then disabling it and setting just on the cycles event:
# perf record --no-inherit -e cycles/inherit/ -e instructions -a usleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.909 MB perf.data (48 samples) ]
# perf evlist -v
cycles/inherit/: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1
instructions: size: 112, config: 0x1, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ID|CPU|PERIOD, read_format: ID, disabled: 1, freq: 1, sample_id_all: 1, exclude_guest: 1
#
We can see it as well in by using a more verbose level of debug messages in
the tool that sets up the perf_event_attr, 'perf record' in this case:
[root@zoo ~]# perf record -vv --no-inherit -e cycles/inherit/ -e instructions -a usleep 1
------------------------------------------------------------
perf_event_attr:
size 112
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|ID|CPU|PERIOD
read_format ID
disabled 1
inherit 1
mmap 1
comm 1
freq 1
task 1
sample_id_all 1
exclude_guest 1
mmap2 1
comm_exec 1
------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
sys_perf_event_open: pid -1 cpu 1 group_fd -1 flags 0x8
sys_perf_event_open: pid -1 cpu 2 group_fd -1 flags 0x8
sys_perf_event_open: pid -1 cpu 3 group_fd -1 flags 0x8
------------------------------------------------------------
perf_event_attr:
size 112
config 0x1
{ sample_period, sample_freq } 4000
sample_type IP|TID|TIME|ID|CPU|PERIOD
read_format ID
disabled 1
freq 1
sample_id_all 1
exclude_guest 1
------------------------------------------------------------
sys_perf_event_open: pid -1 cpu 0 group_fd -1 flags 0x8
<SNIP>
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexei Starovoitov <ast@plumgrid.com>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Li Zefan <lizefan@huawei.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Zefan Li <lizefan@huawei.com>
Cc: pi3orama@163.com
Link: http://lkml.kernel.org/r/1446029705-199659-2-git-send-email-wangnan0@huawei.com
[ s/u64/bool/ for the perf_evsel_config_term inherit field - jolsa]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Recently 'perf <tool> -h' was made aware of arguments and would show
just the help for the arguments specified, but that required a strict
form, i.e.:
$ perf -h --tui
worked, but:
$ perf -h tui
didn't.
Make it support both cases and also look at the option help when neither
matches, so that he following examples works:
$ perf report -h interface
Usage: perf report [<options>]
--gtk Use the GTK2 interface
--stdio Use the stdio interface
--tui Use the TUI interface
$ perf report -h stack
Usage: perf report [<options>]
-g, --call-graph <print_type,threshold[,print_limit],order,
sort_key[,branch]>
Display call graph (stack chain/backtrace):
print_type: call graph printing style (graph|flat|fractal|none)
threshold: minimum call graph inclusion threshold (<percent>)
print_limit: maximum number of call graph entry (<number>)
order: call graph order (caller|callee)
sort_key: call graph sort key (function|address)
branch: include last branch info to call graph (branch)
Default: graph,0.5,caller,function
--max-stack <n> Set the maximum stack depth when parsing the
callchain, anything beyond the specified depth
will be ignored. Default: 127
$
Suggested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-xzqvamzqv3cv0p6w3inhols3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently if an option name is ambiguous it only prints first two
matched option names but no help. It'd be better it could show all
possible names and help messages too.
Before:
$ perf report --show
Error: Ambiguous option: show (could be --show-total-period or
--show-ref-call-graph)
Usage: perf report [<options>]
After:
$ perf report --show
Error: Ambiguous option: show (could be --show-total-period or
--show-ref-call-graph)
Usage: perf report [<options>]
-n, --show-nr-samples
Show a column with the number of samples
--showcpuutilization
Show sample percentage for different cpu modes
-I, --show-info Display extended information about perf.data file
--show-total-period
Show a column with the sum of periods
--show-ref-call-graph
Show callgraph from reference event
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1445701767-12731-1-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/core improvements from Arnaldo Carvalho de Melo:
New user-visible features:
- Show ordered command line options when -h is used or when an
unknown option is specified. (Arnaldo Carvalho de Melo)
- If options are passed after -h, show just its descriptions, not
all options. (Arnaldo Carvalho de Melo)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Some tools have a lot of options, so, providing a way to show help just
for some of them may come handy:
$ perf report -h --tui
Usage: perf report [<options>]
--tui Use the TUI interface
$ perf report -h --tui --showcpuutilization -b -c
Usage: perf report [<options>]
-b, --branch-stack use branch records for per branch histogram filling
-c, --comms <comm[,comm...]>
only consider symbols in these comms
--showcpuutilization
Show sample percentage for different cpu modes
--tui Use the TUI interface
$
Using it with perf bash completion is also handy, just make sure you
source the needed file:
$ . ~/git/linux/tools/perf/perf-completion.sh
Then press tab/tab after -- to see a list of options, put them after -h
and only the options chosen will have its help presented:
$ perf report -h --
--asm-raw --demangle-kernel --group
--kallsyms --pretty --stdio
--branch-history --disassembler-style --gtk
--max-stack --showcpuutilization --symbol-filter
--branch-stack --dsos --header
--mem-mode --show-info --symbols
--call-graph --dump-raw-trace --header-only
--modules --show-nr-samples --symfs
--children --exclude-other --hide-unresolved
--objdump --show-ref-call-graph --threads
--column-widths --fields --ignore-callees
--parent --show-total-period --tid
--comms --field-separator --input
--percentage --socket-filter --tui
--cpu --force --inverted
--percent-limit --sort --verbose
--demangle --full-source-path --itrace
--pid --source --vmlinux
$ perf report -h --socket-filter
Usage: perf report [<options>]
--socket-filter <n>
only show processor socket that match with this filter
Suggested-by: Ingo Molnar <mingo@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/n/tip-83mcdd3wj0379jcgea8w0fxa@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
User visible changes:
- The default for callchains is back to 'callee' when --children is not used.
(Namhyung Kim)
- Move the 'use_offset' option to the right place where the annotate code
expects it to be to be able to properly handle it. (Namhyung Kim)
- Don't die when an unknown 'annotate' option is found in the perf config
file (usually ~/.perfconfig), just warn the user. (Arnaldo Carvalho de Melo)
Infrastructure changes:
- Support %ps/%pS in libtraceevent. (Scott Wood)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The --call-graph option is complex so we should provide better guide for
users. Also change help message to be consistent with config option
names. Now perf top will show help like below:
$ perf top --call-graph
Error: option `call-graph' requires a value
Usage: perf top [<options>]
--call-graph <record_mode[,record_size],print_type,threshold[,print_limit],order,sort_key[,branch]>
setup and enables call-graph (stack chain/backtrace):
record_mode: call graph recording mode (fp|dwarf|lbr)
record_size: if record_mode is 'dwarf', max size of stack recording (<bytes>)
default: 8192 (bytes)
print_type: call graph printing style (graph|flat|fractal|none)
threshold: minimum call graph inclusion threshold (<percent>)
print_limit: maximum number of call graph entry (<number>)
order: call graph order (caller|callee)
sort_key: call graph sort key (function|address)
branch: include last branch info to call graph (branch)
Default: fp,graph,0.5,caller,function
Requested-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1445524112-5201-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Currently 'perf top --call-graph' option is same as 'perf record'. But
'perf top' also need to receive display options in 'perf report'. To do
that, change parse_callchain_report_opt() to allow record options too.
Now perf top can receive display options like below:
$ perf top --call-graph
Error: option `call-graph' requires a value
Usage: perf top [<options>]
--call-graph
<mode[,dump_size],output_type,min_percent[,print_limit],call_order[,branch]>
setup and enables call-graph (stack chain/backtrace)
recording: fp dwarf lbr, output_type (graph, flat,
fractal, or none), min percent threshold, optional
print limit, callchain order, key (function or
address), add branches
$ perf top --call-graph callee,graph,fp
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Brendan Gregg <brendan.d.gregg@gmail.com>
Cc: Chandler Carruth <chandlerc@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Cc: Wang Nan <wangnan0@huawei.com>
Link: http://lkml.kernel.org/r/1445495330-25416-2-git-send-email-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Commits such as 65dd297ac2 ("xfs: %pF is only for function
pointers") caused a regression because pretty_print() didn't support
%ps/%pS. The current %pf/%pF implementation in pretty_print() is what
%ps/%pS is supposed to do, so use the same code for %ps/%pS.
Addressing the incorrect %pf/%pF implementation is beyond the scope of
this patch.
Signed-off-by: Scott Wood <scottwood@freescale.com>
Acked-by: Steven Rostedt <rostedt@goodmis.org>
Cc: Dave Chinner <david@fromorbit.com>
Link: http://lkml.kernel.org/r/20150831211637.GA12848@home.buserror.net
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Perf will core dump if --per-socket/core -a are applied for perf stat.
The root cause is that cpu_map__build_map set refcnt of evlist's cpu_map
to 1. It should set refcnt for the newly created cpu_map, not evlist's
cpu_map.
Here is the example:
# perf stat -e cycles --per-socket -a sleep 1
Performance counter stats for 'system wide':
S0 36 30,196,257 cycles
S1 28 15,823,536 cycles
1.001126828 seconds time elapsed
*** Error in `./perf': corrupted double-linked list: 0x00000000021f9090 ***
======= Backtrace: =========
/lib64/libc.so.6[0x3002e7bbe7]
/lib64/libc.so.6[0x3002e7d2b5]
./perf(perf_evsel__delete+0x28)[0x485bdd]
./perf[0x4800e8]
./perf(perf_evlist__delete+0x5e)[0x482cd5]
./perf(cmd_stat+0xf25)[0x432328]
./perf[0x4768e0]
./perf[0x476ad6]
./perf[0x476b41]
./perf(main+0x1d0)[0x476db2]
/lib64/libc.so.6(__libc_start_main+0xf5)[0x3002e21b45]
./perf[0x4202c5]
Signed-off-by: Kan Liang <kan.liang@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: Andi Kleen <ak@linux.intel.com>
Link: http://lkml.kernel.org/r/1444388363-35936-1-git-send-email-kan.liang@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Pull perf/core improvements and fixes:
User visible changes:
- 'perf bench mem' now prefaults unconditionally, no sense in
providing modes where page faults are measured. (Ingo Molnar)
- Harmonize -l/--nr_loops accross 'perf bench'. (Ingo Molnar)
- Various 'perf bench' consistency improvements. (Ingo Molnar)
- Suppress libtraceevent warnings in non-verbose 'perf test' mode.
(Namhyung Kim)
- Move some tracepoint event test error messages to the verbose mode
of 'perf test'. (Namhyung Kim)
- Make 'perf help' usage message consistent with other tools. (Yunlong Song)
Build fixes:
- Fix 'perf bench' build with gcc 4.4.7. (Arnaldo Carvalho de Melo)
Infrastructure changes:
- 'perf stat' prep work for the 'perf stat scripting' patchkit. (Jiri Olsa)
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
We have three benchmarking subsystems that specify some sort of 'number
of loops' parameter - but all of them do it inconsistently:
numa: -l/--nr_loops
sched messaging: -l/--loops
mem memset/memcpy: -i/--iterations
Harmonize them to -l/--nr_loops by picking the numa variant - which is
also the most likely one to have existing scripting which we don't want
to break.
Plus improve the parameter help texts to indicate the default value for
the nr_loops variable to keep users from guessing ...
Also propagate the naming to internal variables.
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1445241870-24854-13-git-send-email-mingo@kernel.org
[ Let the harmonisation reach the perf-bench man page as well ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
