summaryrefslogtreecommitdiffstats
path: root/tools/perf/builtin-stat.c (follow)
Commit message (Collapse)AuthorAgeFilesLines
* tools/perf/stat: Add event unit and scale supportStephane Eranian2013-11-271-30/+84
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds perf stat support for handling event units and scales as exported by the kernel. The kernel can export PMU events actual unit and scaling factor via sysfs: $ ls -1 /sys/devices/power/events/energy-* /sys/devices/power/events/energy-cores /sys/devices/power/events/energy-cores.scale /sys/devices/power/events/energy-cores.unit /sys/devices/power/events/energy-pkg /sys/devices/power/events/energy-pkg.scale /sys/devices/power/events/energy-pkg.unit $ cat /sys/devices/power/events/energy-cores.scale 2.3283064365386962890625e-10 $ cat cat /sys/devices/power/events/energy-cores.unit Joules This patch modifies the pmu event alias code to check for the presence of the .unit and .scale files to load the corresponding values. They are then used by perf stat transparently: # perf stat -a -e power/energy-pkg/,power/energy-cores/,cycles -I 1000 sleep 1000 # time counts unit events 1.000214717 3.07 Joules power/energy-pkg/ [100.00%] 1.000214717 0.53 Joules power/energy-cores/ 1.000214717 12965028 cycles [100.00%] 2.000749289 3.01 Joules power/energy-pkg/ 2.000749289 0.52 Joules power/energy-cores/ 2.000749289 15817043 cycles When the event does not have an explicit unit exported by the kernel, nothing is printed. In csv output mode, there will be an empty field. Special thanks to Jiri for providing the supporting code in the parser to trigger reading of the scale and unit files. Signed-off-by: Stephane Eranian <eranian@google.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Cc: zheng.z.yan@intel.com Cc: bp@alien8.de Cc: maria.n.dimakopoulou@gmail.com Cc: acme@redhat.com Link: http://lkml.kernel.org/r/1384275531-10892-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
* perf target: Shorten perf_target__ to target__Arnaldo Carvalho de Melo2013-11-121-11/+10
| | | | | | | | | | | | | | | | | | | | Getting unwieldly long, for this app domain should be descriptive enough and the use of __ to separate the class from the method names should help with avoiding clashes with other code bases. Reported-by: David Ahern <dsahern@gmail.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/20131112113427.GA4053@ghostprotocols.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Enhance option parse error messageNamhyung Kim2013-11-041-15/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Print related option help messages only when it failed to process options. While at it, modify parse_options_usage() to skip usage part so that it can be used for showing multiple option help messages naturally like below: $ perf stat -Bx, ls -B option not supported with -x usage: perf stat [<options>] [<command>] -B, --big-num print large numbers with thousands' separators -x, --field-separator <separator> print counts with custom separator Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Ingo Molnar <mingo@kernel.org> Reviewed-by: Ingo Molnar <mingo@kernel.org> Enthusiastically-Supported-by: Ingo Molnar <mingo@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1383291195-24386-6-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Add units to nanosec-based countersDavid Ahern2013-10-111-1/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Ingo pointed out that the task-clock counter should have the units explicitly stated since it is not a counter. Before: perf stat -a -- sleep 1 Performance counter stats for 'sleep 1': 16186.874834 task-clock # 16.154 CPUs utilized ... After: perf stat -a -- sleep 1 Performance counter stats for 'system wide': 16146.402138 task-clock (msec) # 16.125 CPUs utilized ... Reported-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1380400080-9211-4-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Don't require a workload when using system wide or CPU optionsDavid Ahern2013-10-111-1/+2
| | | | | | | | | | | | | | | | | The "perf stat" command can do system wide counters or one or more cpus. For these options do not require a workload to be specified. v2: use perf_target__none per Namhyung's comment. Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/52497F3C.9070908@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Fix misleading message when specifying cpu list or system wideDavid Ahern2013-10-111-1/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The "perf stat" tool displays the command run in its summary output which is misleading when using a cpu list or system wide collection. Before: perf stat -a -- sleep 1 Performance counter stats for 'sleep 1': 16152.670249 task-clock # 16.132 CPUs utilized 417 context-switches # 0.002 M/sec 7 cpu-migrations # 0.030 K/sec ... After: perf stat -a -- sleep 1 Performance counter stats for 'system wide': 16206.931120 task-clock # 16.144 CPUs utilized 395 context-switches # 0.002 M/sec 5 cpu-migrations # 0.030 K/sec ... or perf stat -C1 -- sleep 1 Performance counter stats for 'CPU(s) 1': 1001.669257 task-clock # 1.000 CPUs utilized 4,264 context-switches # 0.004 M/sec 3 cpu-migrations # 0.003 K/sec ... Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1380400080-9211-2-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Don't print bogus data on -e instructionsRamkumar Ramachandra2013-10-111-4/+3
| | | | | | | | | | | | | | | | | | | | | | | | | When only the instructions event is requested: $ perf stat -e instructions git s M builtin-stat.c Performance counter stats for 'git s': 917,453,420 instructions # 0.00 insns per cycle 0.213002926 seconds time elapsed The 0.00 insns per cycle comment in the output is totally bogus and misleading. It happens because update_shadow_stats() doesn't touch runtime_cycles_stats when only the instructions event is requested. So, omit printing the bogus data altogether. Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1380616604-4077-1-git-send-email-artagnon@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Don't print bogus data on -e cyclesRamkumar Ramachandra2013-10-111-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | When only the cycles event is requested: $ perf stat -e cycles dd if=/dev/zero of=/dev/null count=1000000 1000000+0 records in 1000000+0 records out 512000000 bytes (512 MB) copied, 0.26123 s, 2.0 GB/s Performance counter stats for 'dd if=/dev/zero of=/dev/null count=1000000': 911,626,453 cycles # 0.000 GHz 0.262113350 seconds time elapsed The 0.000 GHz comment in the output is totally bogus and misleading. It happens because update_shadow_stats() doesn't touch runtime_nsecs_stats; it is only written when a requested counter matches a SW_TASK_CLOCK. In our case, since we have only requested HW_CPU_CYCLES, runtime_nsecs_stats is unavailable. So, omit printing the comment altogether. Signed-off-by: Ramkumar Ramachandra <artagnon@gmail.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1380539585-23859-3-git-send-email-artagnon@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* Merge branch 'perf/urgent' into tools/perf/buildIngo Molnar2013-10-081-0/+1
|\
| * perf stat: Set child_pid after perf_evlist__prepare_workload()Namhyung Kim2013-10-041-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The commit acf2892270dc ("perf stat: Use perf_evlist__prepare/ start_workload()") converted to use the function but forgot to update child_pid. Fix it. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1380531671-28076-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* | tools/perf/stat: Add perf stat --transactionAndi Kleen2013-10-041-1/+143
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | Add support to perf stat to print the basic transactional execution statistics: Total cycles, Cycles in Transaction, Cycles in aborted transsactions using the in_tx and in_tx_checkpoint qualifiers. Transaction Starts and Elision Starts, to compute the average transaction length. This is a reasonable overview over the success of the transactions. Also support architectures that have a transaction aborted cycles counter like POWER8. Since that is awkward to handle in the kernel abstract handle both cases here. Enable with a new --transaction / -T option. This requires measuring these events in a group, since they depend on each other. This is implemented by using TM sysfs events exported by the kernel Signed-off-by: Andi Kleen <ak@linux.intel.com> Acked-by: Arnaldo Carvalho de Melo <acme@infradead.org> Signed-off-by: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1377128846-977-5-git-send-email-andi@firstfloor.org Signed-off-by: Ingo Molnar <mingo@kernel.org>
* perf stat: Flush output after each line in interval modeAndi Kleen2013-08-071-0/+2
| | | | | | | | | | | | | | | | | When interval mode is outputting to a pipe, each measurement should be flushed individually, so that the reader sees it timely. With a terminal each line is automatically flushed by stdio, but that is disabled with non terminal output. Simply fflush output after each time interval Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1375490473-1503-5-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Add support for --initial-delay optionAndi Kleen2013-08-071-1/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When measuring workloads the startup phase -- doing page faults, dynamic linking, opening files -- is often very different from the rest of the workload. Especially with smaller kernels and using counter multiplexing this can give significant measurement errors. Multiplexing assumes that the workload is mostly the same over longer periods. But at startup there is typically some spike of activity which is relatively short. If many groups are multiplexing the one group seeing the spike, and which is then scaled up over the time to run all groups, may see a significant error. Also in general it's often not useful to measure the startup, because it is so different from the rest. One way around this is to use interval mode and discard the first sample, but this can be awkward because interval mode doesn't support intervals of less than 100ms, and also a useful interval is not necessarily the same as a useful startup delay. This patch adds a new --initial-delay / -D option to skip measuring for the startup phase. The time can be specified in ms Here's a simple example: perf stat -e page-faults bash -c 'for i in $(seq 100000) ; do true ; done' ... 3,721 page-faults ... If we just wait 20 ms the number of page faults is 1/3 less: perf stat -D 20 -e page-faults bash -c 'for i in $(seq 100000) ; do true ; done' ... 2,823 page-faults ... So we filtered out most of the startup noise from bash. Signed-off-by: Andi Kleen <ak@linux.intel.com> Reviewed-by: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1375490473-1503-4-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Fix per-socket output bug for uncore eventsStephane Eranian2013-07-081-3/+4
| | | | | | | | | | | | | | | | | | | | | | | | | This patch fixes a problem reported by Andi Kleen on perf stat when measuring uncore events: # perf stat --per-socket -e uncore_pcu/event=0x0/ -I1000 -a sleep 2 It would not report counts for the second socket. That was due to a cpu mapping bug in print_aggr(). This patch also fixes the socket numbering bug for <not counted> events. Reported-by: Andi Kleen <ak@linux.intel.com> Signed-off-by: Stephane Eranian <eranian@google.com> Tested-by: Andi Kleen <ak@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: zheng.z.yan@intel.com Link: http://lkml.kernel.org/r/20130705170645.GA32519@quad Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Avoid sending SIGTERM to random processesStephane Eranian2013-07-081-1/+22
| | | | | | | | | | | | | | | | | This patch fixes a problem with perf stat whereby on termination it may send a SIGTERM signal to random processes on systems with high PID recycling. I got some actual bug reports on this. There is race between the SIGCHLD and sig_atexit() handlers. This patch addresses this problem by clearing child_pid in the SIGCHLD handler. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20130604154426.GA2928@quad Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Add per-core aggregationStephane Eranian2013-03-251-3/+28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds the --per-core option to perf stat. This option is used to aggregate system-wide counts on a per physical core basis. On processors with hyperthreading, this means counts of all HT threads running on a physical core are aggregated. This mode is useful to find imblance between physical cores running an uniform workload. Cores are identified by socket: S0-C1, means physical core 1 on socket 0. Note that cores are identified using their physical core id, thus their numbering may not be continuous. Per core aggregation can be combined with interval printing: # perf stat -a --per-core -I 1000 -e cycles sleep 1000 # time core cpus counts events 1.000090030 S0-C0 1 4,765,747 cycles 1.000090030 S0-C1 1 5,580,647 cycles 1.000090030 S0-C2 1 221,181 cycles 1.000090030 S0-C3 1 266,092 cycles Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1360846649-6411-4-git-send-email-eranian@google.com [ committer note: Remove parts already applied on 86ee6e1 to keep bisectability ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Rename --aggr-socket to --per-socketStephane Eranian2013-03-251-1/+1
| | | | | | | | | | | | | | To make it more obvious what this option does as suggested by Andi on LKML. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1360846649-6411-3-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Refactor aggregation codeStephane Eranian2013-03-251-88/+119
| | | | | | | | | | | | | | | | | | | | | | Refactor aggregation code by introducing a single aggr_mode variable and an enum for aggregation. Also refactor cpumap code having to do with cpu to socket mappings. All in preparation for extended modes, such as cpu -> core. Also fix socket aggregation and ensure that sockets are printed in increasing order. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1360846649-6411-2-git-send-email-eranian@google.com [ committer note: Fixup conflicts with a7e191c "--repeat forever" and acf2892 "Use perf_evlist__prepare/start_workload()" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Introduce evlist methods to allocate/free the statsArnaldo Carvalho de Melo2013-03-181-24/+43
| | | | | | | | | | | | | | | Reducing the noise in the main logic. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-o219lnci04hlilxi6711wtcr@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Introduce --repeat foreverFrederik Deweerdt2013-03-151-5/+40
| | | | | | | | | | | | | | | | The following patch causes 'perf stat --repeat 0' to be interpreted as 'forever', displaying the stats for every run. We act as if a single run was asked, and reset the stats in each iteration. In this mode SIGINT is passed to perf to be able to stop the loop with Ctrl+C. Signed-off-by: Frederik Deweerdt <frederik.deweerdt@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20130301180227.GA24385@ks398093.ip-192-95-24.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Use perf_evlist__prepare/start_workload()Namhyung Kim2013-03-151-51/+7
| | | | | | | | | | | | | | The perf stat had an open code to the duplicated work. Use the helper as it now can be called without struct perf_record_opts. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1362987798-24969-7-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evlist: Add thread_map__nr() helperNamhyung Kim2013-03-151-2/+2
| | | | | | | | | | | | | | Introduce and use the thread_map__nr() function to protect a possible NULL pointer dereference and cleanup the code a bit. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1362987798-24969-3-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evlist: Remove cpus and threads arguments from perf_evlist__new()Namhyung Kim2013-03-151-1/+1
| | | | | | | | | | | | | | | It's almost always used with NULL for both arguments. Get rid of the arguments from the signature and use perf_evlist__set_maps() if needed. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1362987798-24969-1-git-send-email-namhyung@kernel.org [ committer note: replaced spaces with tabs in some of the affected lines ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Add per processor socket count aggregationStephane Eranian2013-02-061-11/+115
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds per-processor socket count aggregation for system-wide mode measurements. This is a useful mode to detect imbalance between sockets. To enable this mode, use --aggr-socket in addition to -a. (system-wide). The output includes the socket number and the number of online processors on that socket. This is useful to gauge the amount of aggregation. # ./perf stat -I 1000 -a --aggr-socket -e cycles sleep 2 # time socket cpus counts events 1.000097680 S0 4 5,788,785 cycles 2.000379943 S0 4 27,361,546 cycles 2.001167808 S0 4 818,275 cycles Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1360161962-9675-3-git-send-email-eranian@google.com [ committer note: Added missing man page entry based on above comments ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evsel: Fix memory leaks on evsel->countsNamhyung Kim2013-01-301-0/+1
| | | | | | | | | | | | | The ->counts field was never freed in the current code. Add perf_evsel__free_counts() function to free it properly. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1359078284-32080-1-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Add interval printingStephane Eranian2013-01-301-15/+142
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds a new printing mode for perf stat. It allows interval printing. That means perf stat can now print event deltas at regular time interval. This is useful to detect phases in programs. The -I option enables interval printing. It expects an interval duration in milliseconds. Minimum is 100ms. Once, activated perf stat prints events deltas since last printout. All modes are supported. $ perf stat -I 1000 -e cycles noploop 10 noploop for 10 seconds # time counts events 1.000109853 2,388,560,546 cycles 2.000262846 2,393,332,358 cycles 3.000354131 2,393,176,537 cycles 4.000439503 2,393,203,790 cycles 5.000527075 2,393,167,675 cycles 6.000609052 2,393,203,670 cycles 7.000691082 2,393,175,678 cycles The output format makes it easy to feed into a plotting program such as gnuplot when the -I option is used in combination with the -x option: $ perf stat -x, -I 1000 -e cycles noploop 10 noploop for 10 seconds 1.000084113,2378775498,cycles 2.000245798,2391056897,cycles 3.000354445,2392089414,cycles 4.000459115,2390936603,cycles 5.000565341,2392108173,cycles Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1359460064-3060-3-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evsel: Introduce perf_evsel__open_strerror methodArnaldo Carvalho de Melo2013-01-241-11/+5
| | | | | | | | | | | | | | | | | That consolidates the error messages in 'record', 'stat' and 'top', that now get a consistent set of messages and allow other tools to use the new method to report problems using whatever UI toolkit. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-1cudb7wl996kz7ilz83ctvhr@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evsel: Do missing feature fallbacks in just one placeArnaldo Carvalho de Melo2013-01-241-27/+3
| | | | | | | | | | | | | | | | Instead of doing it in stat, top, record or any other tool that opens event descriptors. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-vr8hzph83d5t2mdlkf565h84@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evsel: Convert to _is_group_leader methodNamhyung Kim2012-12-091-1/+1
| | | | | | | | | | | | | | | | | | Convert perf_evsel__is_group_member to perf_evsel__is_group_leader. This is because the most usecases are using negative form to check whether the given evsel is a leader or not and it's IMHO somewhat ambiguous - leader also *is* a member of the group. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1354171126-14387-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evsel: Introduce is_group_member methodArnaldo Carvalho de Melo2012-11-141-1/+2
| | | | | | | | | | | | | | | | To clarify what is being tested, instead of assuming that evsel->leader == NULL means either an 'isolated' evsel or a 'group leader'. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-lvdbvimaxw9nc5een5vmem0c@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf tools: Fix attributes for '{}' defined event groupsJiri Olsa2012-11-141-7/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | Fixing events attributes for groups defined via '{}'. Currently 'enable_on_exec' attribute in record command and both 'disabled ' and 'enable_on_exec' attributes in stat command are set based on the 'group' option. This eliminates proper setup for '{}' defined groups as they don't set 'group' option. Making above attributes values based on the 'evsel->leader' as this is common to both group definition. Moving perf_evlist__set_leader call within builtin-record ahead perf_evlist__config_attrs call, because the latter needs possible group leader links in place. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1352741644-16809-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Add --pre and --post commandPeter Zijlstra2012-10-261-6/+36
| | | | | | | | | | | | | | | | | In order to measure kernel builds, one has to do some pre/post cleanup work in order to do the repeat build. So provide --pre and --post command hooks to allow doing just that. perf stat --repeat 10 --null --sync --pre 'make -s O=defconfig-build/clean' \ -- make -s -j64 O=defconfig-build/ bzImage Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: Stephane Eranian <eranian@gmail.com> Link: http://lkml.kernel.org/r/1350992414.13456.5.camel@twins [ committer note: Added respective entries in Documentation/perf-stat.txt ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Don't use globals where not needed toArnaldo Carvalho de Melo2012-10-021-169/+159
| | | | | | | | | | | | | | | | Some variables were global but used in just one function, so move it to where it belongs. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-spa8e7nnohtn1z32q2l2ae2c@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evlist: Renane set_filters method to apply_filtersArnaldo Carvalho de Melo2012-09-261-1/+1
| | | | | | | | | | | | | | | | | | | | | Because that is what it really does, i.e. it applies the filters that were parsed from the command line and stashed into the evsels they refer to. We'll need the set_filter method name to actually apply a filter to all the evsels in an evlist, for instance, to ask that a syswide tracer doesn't trace itself. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-v9x3q9rv4caxtox7wtjpchq5@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Check PMU cpumask fileYan, Zheng2012-09-171-10/+20
| | | | | | | | | | | | | | If user doesn't explicitly specify CPU list, perf-stat only collects events on CPUs listed in the PMU cpumask file. Signed-off-by: "Yah, Zheng" <zheng.z.yan@intel.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1347263631-23175-3-git-send-email-zheng.z.yan@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Move stats related code to util/stat.cXiao Guangrong2012-09-171-54/+2
| | | | | | | | | | | | | | | | | Then, the code can be shared between kvm events and perf stat. Signed-off-by: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com> [ Dong Hao <haodong@linux.vnet.ibm.com>: rebase it on acme's git tree ] Signed-off-by: Dong Hao <haodong@linux.vnet.ibm.com> Cc: Avi Kivity <avi@redhat.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: kvm@vger.kernel.org Cc: Marcelo Tosatti <mtosatti@redhat.com> Cc: Runzhen Wang <runzhen@linux.vnet.ibm.com> Cc: Xiao Guangrong <xiaoguangrong@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1347870675-31495-3-git-send-email-haodong@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf tools: Use __maybe_used for unused variablesIrina Tirdea2012-09-111-12/+28
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | perf defines both __used and __unused variables to use for marking unused variables. The variable __used is defined to __attribute__((__unused__)), which contradicts the kernel definition to __attribute__((__used__)) for new gcc versions. On Android, __used is also defined in system headers and this leads to warnings like: warning: '__used__' attribute ignored __unused is not defined in the kernel and is not a standard definition. If __unused is included everywhere instead of __used, this leads to conflicts with glibc headers, since glibc has a variables with this name in its headers. The best approach is to use __maybe_unused, the definition used in the kernel for __attribute__((unused)). In this way there is only one definition in perf sources (instead of 2 definitions that point to the same thing: __used and __unused) and it works on both Linux and Android. This patch simply replaces all instances of __used and __unused with __maybe_unused. Signed-off-by: Irina Tirdea <irina.tirdea@intel.com> Acked-by: Pekka Enberg <penberg@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/1347315303-29906-7-git-send-email-irina.tirdea@intel.com [ committer note: fixed up conflict with a116e05 in builtin-sched.c ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Remove use of die/exit and handle errorsDavid Ahern2012-09-051-3/+4
| | | | | | | | | | | Allows perf to clean up properly on program termination. Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1346005487-62961-5-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evlist: Introduce evsel list accessorsArnaldo Carvalho de Melo2012-08-151-1/+1
| | | | | | | | | | | | | | | | | | | | | To replace the longer list_entry constructs for things that are widely used: perf_evlist__{first,last}(evlist) perf_evsel__next(evsel) Acked-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-ng7azq26wg1jd801qqpcozwp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf evlist: Rename __group method to __set_leaderArnaldo Carvalho de Melo2012-08-151-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Just like was done for parse_events__set_leader. Also we need to have the list_entry set_leader method in evlist.c so that we don't grow another dep in the python binding: # ~acme/git/linux/tools/perf/python/twatch.py Traceback (most recent call last): File "/home/acme/git/linux/tools/perf/python/twatch.py", line 16, in <module> import perf ImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: parse_events__set_leader And also remove a pr_debug from evsel.c so that we avoid this one too: # ~acme/git/linux/tools/perf/python/twatch.py Traceback (most recent call last): File "/home/acme/git/linux/tools/perf/python/twatch.py", line 16, in <module> import perf ImportError: /home/acme/git/build/perf/python/perf.so: undefined symbol: eprintf Acked-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Namhyung Kim <namhyung@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-0hk9dazg9pora9jylkqngovm@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf tools: Enable grouping logic for parsed eventsJiri Olsa2012-08-141-8/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds a functionality that allows to create event groups based on the way they are specified on the command line. Adding functionality to the '{}' group syntax introduced in earlier patch. The current '--group/-g' option behaviour remains intact. If you specify it for record/stat/top command, all the specified events become members of a single group with the first event as a group leader. With the new '{}' group syntax you can create group like: # perf record -e '{cycles,faults}' ls resulting in single event group containing 'cycles' and 'faults' events, with cycles event as group leader. All groups are created with regards to threads and cpus. Thus recording an event group within a 2 threads on server with 4 CPUs will create 8 separate groups. Examples (first event in brackets is group leader): # 1 group (cpu-clock,task-clock) perf record --group -e cpu-clock,task-clock ls perf record -e '{cpu-clock,task-clock}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock},{minor-faults,major-faults}' ls # 1 group (cpu-clock,task-clock,minor-faults,major-faults) perf record --group -e cpu-clock,task-clock -e minor-faults,major-faults ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults}' ls # 2 groups (cpu-clock,task-clock) (minor-faults,major-faults) perf record -e '{cpu-clock,task-clock} -e '{minor-faults,major-faults}' \ -e instructions ls # 1 group # (cpu-clock,task-clock,minor-faults,major-faults,instructions) perf record --group -e cpu-clock,task-clock \ -e minor-faults,major-faults -e instructions ls perf record -e '{cpu-clock,task-clock,minor-faults,major-faults,instructions}' ls It's possible to use standard event modifier for a group, which spans over all events in the group and updates each event modifier settings, for example: # perf record -r '{faults:k,cache-references}:p' resulting in ':kp' modifier being used for 'faults' and ':p' modifier being used for 'cache-references' event. Reviewed-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <peterz@infradead.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: Arnaldo Carvalho de Melo <acme@ghostprotocols.net> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ulrich Drepper <drepper@gmail.com> Link: http://lkml.kernel.org/n/tip-ho42u0wcr8mn1otkalqi13qp@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* Merge tag 'perf-core-for-mingo' of ↵Ingo Molnar2012-06-201-6/+6
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf improvements from Arnaldo Carvalho de Melo: * Replace event_name with perf_evsel__name, that handles the event modifiers and doesn't use static variables. * GTK browser improvements, from Namhyung Kim * Fix possible NULL pointer deref in the TUI annotate browser, from Samuel Liao * Add sort by source file:line number, using addr2line. * Allow printing histogram text snapshots at any point in top/report. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Ingo Molnar <mingo@kernel.org>
| * perf tools: Move all users of event_name to perf_evsel__nameArnaldo Carvalho de Melo2012-06-191-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | So that we don't use global variables that could make us misreport event names when having a multi window top, for instance. Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-mccancovi1u0wdkg8ncth509@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* | perf stat: Fix default output fileStephane Eranian2012-06-111-1/+7
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The following commit: commit 56f3bae70638b33477a6015fd362ccfe354fd3ee Author: Jim Cromie <jim.cromie@gmail.com> Date: Wed Sep 7 17:14:00 2011 -0600 perf stat: Add --log-fd <N> option to redirect stderr elsewhere introduced a bug in the way perf stat outputs the results by default, i.e., without the --log-fd or --output option. It would default to writing to file descriptor 0, i.e., stdin. Writing to stdin is allowed and is equivalent to writing to stdout. However, there is a major difference for any script that was already capturing the output of perf stat via redirection: perf stat >/tmp/log .... or perf stat 2>/tmp/log .... They would not capture anything anymore. They would have to do: perf stat 0>/tmp/log ... This breaks compatibility with existing scripts and does not look very natural. This patch fixes the problem by looking at output_fd only when it was modified by user (> 0). It also checks that the value if positive. Passing --log-fd 0 is ignored. I would also argue that defaulting to stderr for the results is not the right thing to do, though this patch does not address this specific issue. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Jim Cromie <jim.cromie@gmail.com> Link: http://lkml.kernel.org/r/20120515111111.GA9870@quad Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* perf stat: Initialize default events wrt exclude_{guest,host}Arnaldo Carvalho de Melo2012-05-301-4/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When no event is specified the tools use perf_evlist__add_default(), that will call event_attr_init to initialize the KVM exclusion bits. When the change was made to the tools so that by default guest samples would be excluded, the changes were made just to the parsing routines and to perf_evlist__add_default(), not to perf_evlist__add_attrs, that is used so far just by perf stat to add multiple events, according to the level of detail specified. Recently the tools were changed to reconstruct the event name from all the details in perf_event_attr, not just from .type and .config, but taking into account all the feature bits (.exclude_{guest,host,user,kernel,etc}, .precise_ip, etc). That is when we noticed that the default for perf stat wasn't the one for the rest of the tools, i.e. the .exclude_guest bit wasn't being set. I.e. the default, that doesn't call event_attr_init was showing the :HG modifier: $ perf stat usleep 1 Performance counter stats for 'usleep 1': 0.942119 task-clock # 0.454 CPUs utilized 1 context-switches # 0.001 M/sec 0 CPU-migrations # 0.000 K/sec 126 page-faults # 0.134 M/sec 693,193 cycles:HG # 0.736 GHz [40.11%] 407,461 stalled-cycles-frontend:HG # 58.78% frontend cycles idle [72.29%] 365,403 stalled-cycles-backend:HG # 52.71% backend cycles idle 465,982 instructions:HG # 0.67 insns per cycle # 0.87 stalled cycles per insn 89,760 branches:HG # 95.275 M/sec 6,178 branch-misses:HG # 6.88% of all branches 0.002077228 seconds time elapsed While if one explicitely specifies the same events, which will make the parsing code to be called and thus event_attr_init is called: $ perf stat -e task-clock,context-switches,migrations,page-faults,cycles,stalled-cycles-frontend,stalled-cycles-backend,instructions,branches,branch-misses usleep 1 Performance counter stats for 'usleep 1': 1.040349 task-clock # 0.500 CPUs utilized 2 context-switches # 0.002 M/sec 0 CPU-migrations # 0.000 K/sec 127 page-faults # 0.122 M/sec 587,966 cycles # 0.565 GHz [13.18%] 459,167 stalled-cycles-frontend # 78.09% frontend cycles idle 390,249 stalled-cycles-backend # 66.37% backend cycles idle 504,006 instructions # 0.86 insns per cycle # 0.91 stalled cycles per insn 96,455 branches # 92.714 M/sec 6,522 branch-misses # 6.76% of all branches [96.12%] 0.002078681 seconds time elapsed Fix it by introducing a perf_evlist__add_default_attrs method that will call evlist_attr_init in all the perf_event_attr entries before adding the events. Reported-by: Ingo Molnar <mingo@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-4eysr236r0pgiyum9epwxw7s@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* Merge remote-tracking branch 'tip/perf/urgent' into perf/coreArnaldo Carvalho de Melo2012-05-181-5/+30
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Merge reason: We are going to queue up a dependent patch: "perf tools: Move parse event automated tests to separated object" That depends on: commit e7c72d8 perf tools: Add 'G' and 'H' modifiers to event parsing Conflicts: tools/perf/builtin-stat.c Conflicted with the recent 'perf_target' patches when checking the result of perf_evsel open routines to see if a retry is needed to cope with older kernels where the exclude guest/host perf_event_attr bits were not used. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf stat: handle ENXIO error for perf_event_openDavid Ahern2012-05-091-1/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | perf stat on PPC currently fails to run: $ perf stat -- sleep 1 Error: open_counter returned with 6 (No such device or address). /bin/dmesg may provide additional information. Fatal: Not all events could be opened. The problem is that until 2.6.37 (behavior changed with commit b0a873e) perf on PPC returns ENXIO when hw_perf_event_init() fails. With this patch we get the expected behavior: $ perf stat -v -- sleep 1 cycles event is not supported by the kernel. stalled-cycles-frontend event is not supported by the kernel. stalled-cycles-backend event is not supported by the kernel. instructions event is not supported by the kernel. branches event is not supported by the kernel. branch-misses event is not supported by the kernel. ... Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1336490956-57145-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * perf stat: Fix case where guest/host monitoring is not supported by kernelStephane Eranian2012-05-011-4/+29
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | By default, perf stat sets exclude_guest = 1. But when you run perf on a kernel which does not support host/guest filtering, then you get an error saying the event in unsupported. This comes from the fact that when the perf_event_attr struct passed by the user is larger than the one known to the kernel there is safety check which ensures that all unknown bits are zero. But here, exclude_guest is 1 (part of the unknown bits) and thus the perf_event_open() syscall return EINVAL. To my surprise, running perf record on the same kernel did not exhibit the problem. The reason is that perf record handles the problem by catching the error and retrying with guest/host excludes set to zero. For some reason, this was not done with perf stat. This patch fixes this problem. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: Gleb Natapov <gleb@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Joerg Roedel <joro@8bytes.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> Link: http://lkml.kernel.org/r/20120427124538.GA7230@quad Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* | perf target: Rename functions to avoid double negationNamhyung Kim2012-05-161-7/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Rename perf_target__no_{cpu,task} to perf_target__has_{cpu,task} because it's more intuitive and easy to parse (for human beings) when used with negation. The names are came out from David Ahern. It is intended to be a mechanical substitution without any functional change. The perf_target__none remains unchanged since I couldn't find a right name and it is hardly used with negation. Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Suggested-by: David Ahern <dsahern@gmail.com> Suggested-by: Ingo Molnar <mingo@kernel.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1337161549-9870-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
* | perf stat: handle ENXIO error for perf_event_openDavid Ahern2012-05-091-1/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | perf stat on PPC currently fails to run: $ perf stat -- sleep 1 Error: open_counter returned with 6 (No such device or address). /bin/dmesg may provide additional information. Fatal: Not all events could be opened. The problem is that until 2.6.37 (behavior changed with commit b0a873e) perf on PPC returns ENXIO when hw_perf_event_init() fails. With this patch we get the expected behavior: $ perf stat -v -- sleep 1 cycles event is not supported by the kernel. stalled-cycles-frontend event is not supported by the kernel. stalled-cycles-backend event is not supported by the kernel. instructions event is not supported by the kernel. branches event is not supported by the kernel. branch-misses event is not supported by the kernel. ... Signed-off-by: David Ahern <dsahern@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1336490956-57145-1-git-send-email-dsahern@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-20 11:29:05 +0100