- 08 Jan, 2016 17 commits
-
-
Jiri Olsa authored
The find_map helper is already there, so let's use it. Also we're going to introduce wider search in following patch, so it'll be easier to make this change on single place. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Tested-by:
Noel Grandin <noelgrandin@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1452158050-28061-4-git-send-email-jolsa@kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Jiri Olsa authored
Replacing them with perf_evsel__(enable|disable). Signed-off-by:
-
Adrian Hunter authored
perf evlist: Make perf_evlist__open() open evsels with their cpus and threads (like perf record does) 'perf record' uses perf_evsel__open() to open events and passes the evsel->cpus and evsel->threads. Many tests and some tools instead use perf_evlist__open() which passes instead evlist->cpus and evlist->threads. Make perf_evlist__open() follow the 'perf record' behaviour so that a consistent approach is taken. Signed-off-by:
Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Noel Grandin <noelgrandin@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1452158050-28061-3-git-send-email-jolsa@kernel.orgSigned-off-by:
-
Namhyung Kim authored
Currently perf report only shows a help message "For a higher level overview, try: perf report --sort comm,dso" unconditionally (even if the sort keys were used). Add more help tips and show randomly. Load tips from ${prefix}/share/doc/perf-tip/tips.txt file. $ perf report | tail 0.10% swapper [kernel.vmlinux] [k] irq_exit 0.09% swapper [kernel.vmlinux] [k] flush_smp_call_function_queue 0.08% swapper [kernel.vmlinux] [k] native_write_msr_safe 0.03% swapper [kernel.vmlinux] [k] group_sched_in 0.01% perf [kernel.vmlinux] [k] native_write_msr_safe # # (Tip: Search options using a keyword: perf report -h <keyword>) # Signed-off-by:Namhyung Kim <namhyung@kernel.org> Acked-by:
Ingo Molnar <mingo@kernel.org> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/1452166913-27046-1-git-send-email-namhyung@kernel.org [ Renamed it to perf_tip() and the parameter dirname to dirpath to fix the build on older distros ] Signed-off-by:
-
Namhyung Kim authored
These are necessary for multi threaded sample processing: - hists__get__get_rotate_entries_in() - hists__collapse_insert_entry() - __hists__init() Signed-off-by:
-
Jiri Olsa authored
Using perf_hpp__register_sort_field interface instead of directly adding the entry. Signed-off-by:
-
Jiri Olsa authored
We currently set 'overhead' and 'overhead_children' as default sort keys within perf_hpp__init function by directly adding into the sort list. This patch adds 'overhead' and 'overhead_children' in text form into sort_keys and let them be added by standard sort dimension interface. We need to eliminate dirrect sort_list additions to be able to add support for hists specific sort keys. Signed-off-by:
-
Jiri Olsa authored
It's no longer needed. Signed-off-by:
-
Jiri Olsa authored
Besides lockdep we use all the 'tools/lib' code in perf, so include it completely in tags. Signed-off-by:
-
Jiri Olsa authored
Adding code to align event names, so we get aligned output in case of multiple events with different names. Before: $ perf script :13757 13757 163918.230829: cpu/mem-snp-none/P: ffff88085f20d010 :13757 13757 163918.230832: cpu/mem-loads,ldlat=30/P: 7f5a5f719f00 :13757 13757 163918.230835: cpu/mem-loads,ldlat=30/P: 7f5a5f719f00 :13758 13758 163918.230838: cpu/mem-snp-none/P: ffff88085f4ad810 :13758 13758 163918.154093: cpu/mem-stores/P: ffff88085bb53f28 :13757 13757 163918.155264: cpu/mem-snp-hitm/P: 601080 ... After: $ perf script :13757 13757 163918.228831: cpu/mem-snp-none/P: ffffffff81a841c0 :13757 13757 163918.228834: cpu/mem-loads,ldlat=30/P: 7f5a5f719f08 :13757 13757 163918.228837: cpu/mem-loads,ldlat=30/P: 7f5a5f719f08 :13758 13758 163918.228837: cpu/mem-snp-none/P: ffff88085f4ad800 :13758 13758 163918.154093: cpu/mem-stores/P: ffff88085bb53f28 :13757 13757 163918.155264: cpu/mem-snp-hitm/P: 601080 ... Signed-off-by:
David Ahern <dsahern@gmail.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Noel Grandin <noelgrandin@gmail.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1452158050-28061-9-git-send-email-jolsa@kernel.orgSigned-off-by:
-
Wang Nan authored
These lost headers are found in arm64 cross buildings, failing to build perf using tarballs generated using: $ make perf-targz-src-pkg Signed-off-by:
Wang Nan <wangnan0@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1452263041-225488-3-git-send-email-wangnan0@huawei.comSigned-off-by:
-
Jiri Olsa authored
The trace command still appears in help message when you run simple 'perf' command. It's because the generate-cmdlist.sh does not care about the HAVE_LIBAUDIT_SUPPORT dependency of trace command and puts it into generated common_cmds array. Wrapping trace command under HAVE_LIBAUDIT_SUPPORT dependency, which will exclude it from common_cmds array if HAVE_LIBAUDIT_SUPPORT is not set. Signed-off-by:
-
Namhyung Kim authored
The event group view feature is to see related events together. To use the group view, events should be recorded as a group with a dedicated syntax of surrounding events by braces (-e '{ evt1, evt2, ... }'). Also 'perf report' also requires the --group option to enable it. However it's almost always beneficial to use the group view to see the group events as it's more expressive. And I think it's more natural to see events together if they are recorded as a group. Thus this patch changes the default value to enable it. If users don't want to see like it and keep the original behavior, they can set the report.group config variable to false and/or use --no-group option in the 'perf report' command line. Requested-by: -
Namhyung Kim authored
It missed to decay periods in callchains when decaying hist entries. This resulted in more than 100 percent overhead in callchains in the fractal style output. Reported-by:
Arnaldo Carvalho de Melo <acme@kernel.org> Signed-off-by:
-
Arnaldo Carvalho de Melo authored
So that lib/find_bit.c doesn't requires anything inside tools/perf/ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: George Spelvin <linux@horizon.com Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Wang Nan <wangnan0@huawei.com> Cc: Yury Norov <yury.norov@gmail.com> Link: http://lkml.kernel.org/n/tip-7lxe7jgohaac5faodndhdmvk@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Need to move the bitmap.[ch] things from tools/perf/ to tools/lib, will be done in the next patches. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: George Spelvin <linux@horizon.com Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Wang Nan <wangnan0@huawei.com> Cc: Yury Norov <yury.norov@gmail.com> Link: http://lkml.kernel.org/n/tip-5fys65wkd7gu8j7a7xgukc5t@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
The commit that introduced it should've moved it to the same place, plus the 'tools/' prefix, but instead moved it to a bogus tools/lib/util/ directory, being the only file there. Move it to tools/lib/find_bit.c, picking the name for the file where these routines live since: 8f6f19dd ("lib: move find_last_bit to lib/find_next_bit.c") Next step is to make tools/lib/find_bit.c to differ from lib/find_bit.c just in removing what is not used by tools/. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: George Spelvin <linux@horizon.com Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk> Cc: Wang Nan <wangnan0@huawei.com> Cc: Yury Norov <yury.norov@gmail.com> Link: http://lkml.kernel.org/n/tip-p391cex5mqvahp4pwrton87n@git.kernel.orgSigned-off-by:
-
- 07 Jan, 2016 7 commits
-
-
Arnaldo Carvalho de Melo authored
Before: $ perf test -v cqm 48: Test intel cqm nmi context read : --- start --- test child forked, pid 1681 parse_events failed test child finished with -2 ---- end ---- Test intel cqm nmi context read: Skip $ After: $ perf test -v cqm 48: Test intel cqm nmi context read : --- start --- test child forked, pid 1681 parse_events failed, is "intel_cqm/llc_occupancy/" available? test child finished with -2 ---- end ---- Test intel cqm nmi context read: Skip $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Matt Fleming <matt.fleming@intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-eidpiv5x4nkbsx37xwikbnir@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
We were asking for a 4kHz sample_freq, making the test fail needlessly when the system reduced /proc/sys/kernel/perf_event_max_sample_rate below that. Before: # perf test -vv dummy 23: Test using a dummy software event to keep tracking : --- start --- test child forked, pid 32421 ------------------------------------------------------------ perf_event_attr: type 1 size 112 config 0x9 { sample_period, sample_freq } 4000 sample_type IP|TID|ID|PERIOD <SNIP> sys_perf_event_open failed, error -22 Unable to open dummy and cycles event test child finished with -2 ---- end ---- Test using a dummy software event to keep tracking: Skip # [root@zoo ~]# cat /proc/sys/kernel/perf_event_max_sample_rate 1000 After: [root@zoo ~]# perf test dummy 23: Test using a dummy software event to keep tracking : Ok Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-487iquegrs2379e5n0pi0tcp@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
Fixing this problem, introduced recently: $ perf test python 16: Try 'import perf' in python, checking link problems : FAILED! In verbose mode we find out what is missing: $ perf test -v python 16: Try 'import perf' in python, checking link problems : --- start --- test child forked, pid 24894 Traceback (most recent call last): File "<stdin>", line 1, in <module> ImportError: /tmp/build/perf/python/perf.so: undefined symbol: find_next_bit test child finished with -1 ---- end ---- Try 'import perf' in python, checking link problems: FAILED! $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Fixes: f77b57ad ("perf cpu_map: Add cpu_map__new_event function") Link: http://lkml.kernel.org/n/tip-rajx0zkz6czdrnvvwf0jp76p@git.kernel.orgSigned-off-by: -
Arnaldo Carvalho de Melo authored
We're not looking at PERF_RECORD_SAMPLE entries and now by default we use PERF_COUNT_SW_DUMMY, so just remove that setting. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-cly7cnotktv5rqao13pkorem@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
As we're test just the !PERF_RECORD_SAMPLE records. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-qp8radcz3il4q9wbnseh337d@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
For case where all we need is an evlist with just an "dummy" evsel, like in some 'perf test' entries. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-q52le0pblm2k3ncvyilelr9z@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
We were asking for a 4kHz sample_freq, making the test fail needlessly when the system reduced /proc/sys/kernel/perf_event_max_sample_rate below that. In this test we only look at the PERF_SAMPLE_TIME fields in PERF_RECORD_ meta events, no need to set sample_freq. Thanks to Namhyung for suggesting that max_sample_rate could be the reason for the test failure, seeing the 'perf test -vv' output I sent. Before: # echo 1000 > /proc/sys/kernel/perf_event_max_sample_rate # perf test TSC 45: Test converting perf time to TSC : FAILED! After: # perf test TSC 45: Test converting perf time to TSC : Ok # cat /proc/sys/kernel/perf_event_max_sample_rate 1000 Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-lcob05qhawkuvsyuu9g1fld5@git.kernel.orgSigned-off-by:
-
- 06 Jan, 2016 16 commits
-
-
Stephane Eranian authored
This patch fixes a bug in __perf_pmu__new_alias() whereby the alias->snapshot field was not initialized to false. This led to random alias->snapshot value for an alias and was breaking some measurements such as: $ perf stat -a -e uncore_imc/data_reads/ -I 1000 sleep 100 Because the event ended up being treated as snapshot mode, when it is not. Signed-off-by:
Stephane Eranian <eranian@google.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kan Liang <kan.liang@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1452106201-13073-1-git-send-email-eranian@google.comSigned-off-by:
-
Jiri Olsa authored
Adding stat-cpi.py as an example of how to do stat scripting. It computes the CPI metrics from cycles and instructions events. The CPI is based performance metric showing the Cycles Per Instructions ratio, which helps to identify cycles-hungry code. Following stat record/report/script combinations could be used: - get CPI for given workload $ perf stat -e cycles,instructions record ls SNIP Performance counter stats for 'ls': 2,904,431 cycles 3,346,878 instructions # 1.15 insns per cycle 0.001782686 seconds time elapsed $ perf script -s ./scripts/python/stat-cpi.py 0.001783: cpu -1, thread -1 -> cpi 0.867803 (2904431/3346878) $ perf stat -e cycles,instructions record ls | perf script -s ./scripts/python/stat-cpi.py SNIP 0.001730: cpu -1, thread -1 -> cpi 0.869026 (2928292/3369627) - get CPI systemwide: $ perf stat -e cycles,instructions -a -I 1000 record sleep 3 # time counts unit events 1.000158618 594,274,711 cycles (100.00%) 1.000158618 441,898,250 instructions 2.000350973 567,649,705 cycles (100.00%) 2.000350973 432,669,206 instructions 3.000559210 561,940,430 cycles (100.00%) 3.000559210 420,403,465 instructions 3.000670798 780,105 cycles (100.00%) 3.000670798 326,516 instructions $ perf script -s ./scripts/python/stat-cpi.py 1.000159: cpu -1, thread -1 -> cpi 1.344823 (594274711/441898250) 2.000351: cpu -1, thread -1 -> cpi 1.311972 (567649705/432669206) 3.000559: cpu -1, thread -1 -> cpi 1.336669 (561940430/420403465) 3.000671: cpu -1, thread -1 -> cpi 2.389178 (780105/326516) $ perf stat -e cycles,instructions -a -I 1000 record sleep 3 | perf script -s ./scripts/python/stat-cpi.py 1.000202: cpu -1, thread -1 -> cpi 1.035091 (940778881/908885530) 2.000392: cpu -1, thread -1 -> cpi 1.442600 (627493992/434974455) 3.000545: cpu -1, thread -1 -> cpi 1.353612 (741463930/547766890) 3.000622: cpu -1, thread -1 -> cpi 2.642110 (784083/296764) Signed-off-by:Kan Liang <kan.liang@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1452077397-31958-4-git-send-email-jolsa@kernel.orgSigned-off-by:
-
Jiri Olsa authored
If no script is specified for stat data, display stat events in raw form. $ perf stat record ls SNIP Performance counter stats for 'ls': 0.851585 task-clock (msec) # 0.717 CPUs utilized 0 context-switches # 0.000 K/sec 0 cpu-migrations # 0.000 K/sec 114 page-faults # 0.134 M/sec 2,620,918 cycles # 3.078 GHz <not supported> stalled-cycles-frontend <not supported> stalled-cycles-backend 2,714,111 instructions # 1.04 insns per cycle 542,434 branches # 636.970 M/sec 15,946 branch-misses # 2.94% of all branches 0.001186954 seconds time elapsed $ perf script CPU THREAD VAL ENA RUN TIME EVENT -1 26185 851585 851585 851585 1186954 task-clock -1 26185 0 851585 851585 1186954 context-switches -1 26185 0 851585 851585 1186954 cpu-migrations -1 26185 114 851585 851585 1186954 page-faults -1 26185 2620918 853340 853340 1186954 cycles -1 26185 0 0 0 1186954 stalled-cycles-frontend -1 26185 0 0 0 1186954 stalled-cycles-backend -1 26185 2714111 853340 853340 1186954 instructions -1 26185 542434 853340 853340 1186954 branches -1 26185 15946 853340 853340 1186954 branch-misses Signed-off-by: -
Jiri Olsa authored
We can't convert u16 cpu_map_entries::cpu[x] value directly to int, because it could hold -1, which would be converted as 65535. Adding special treatment for -1, which is not real cpu number, to be converted to (int -1). Reported-by:
-
Jiri Olsa authored
Add support to get stat events data in perf python scripts. The python script shall implement the following new interface to process stat data: def stat__<event_name>_[<modifier>](cpu, thread, time, val, ena, run): - is called for every stat event for given counter, if user monitors 'cycles,instructions:u" following callbacks should be defined: def stat__cycles(cpu, thread, time, val, ena, run): def stat__instructions_u(cpu, thread, time, val, ena, run): def stat__interval(time): - is called for every interval with its time, in non interval mode it's called after last stat event with total measured time in ns The rest of the current interface stays untouched.. Please check example CPI metrics script in following patch with command line examples in changelogs. Signed-off-by: -
Jiri Olsa authored
Implement struct scripting_ops::(process_stat|process_stat_interval) handlers - calling scripting handlers from stat events handlers. Signed-off-by:
-
Jiri Olsa authored
Python and perl scripting code will define those callbacks and get stat data. Signed-off-by:
-
Jiri Olsa authored
Adding processing of stat config event and initialize stat_config object. Signed-off-by:
-
Jiri Olsa authored
Adding processing of cpu/threads maps. Configuring session's evlist with these maps. Signed-off-by:
-
Jiri Olsa authored
For pipe sessions we need to keep sample_type zero, because script's perf_evsel__check_attr is triggered by sample_type != 0, and the check would fail on stat session. I was tempted to keep it zero unconditionally, but the pipe session is sufficient. In perf.data session we are guarded by HEADER_STAT feature. Signed-off-by:
-
Namhyung Kim authored
Signed-off-by:
-
Namhyung Kim authored
When a perf.data file has multiple events, it's likely to be similar (tracepoint) events. In that case, they might have same field name so add all of them to sort keys instead of bailing out. Signed-off-by:
-
Jiri Olsa authored
Using FEATURE-DUMP in bpf subproject for features detection in case bpf is built via perf. Keeping the current features detection otherwise. Signed-off-by:
-
Jiri Olsa authored
Changing the contents of the FEATURE-DUMP file, so it looks like: feature-backtrace=1 feature-dwarf=0 feature-fortify-source=1 feature-sync-compare-and-swap=0 This way it could get included in sub projects, so they won't be forced to redo features detection. Also now storing the complete set of features. Signed-off-by:
-
Jiri Olsa authored
The feature_assign macro generates feature value assignment for name, like: $(call feature_assign,dwarf) == feature-dwarf=1 This will be used more in following patches. Signed-off-by:
-
Jiri Olsa authored
We decide what dwarf unwind to choose way after the Makefile.feature makefile is included. The $(dwarf-post-unwind) is not even set at that time. For the same reason it was never included in FEATURE-DUMP file. Moving it into perf VF=1 verbose display. $ make VF=1 BUILD: Doing 'make -j4' parallel build Auto-detecting system features: ... dwarf: [ on ] ... ... LIBUNWIND_DIR: ... LIBDW_DIR: ... DWARF post unwind library: libunwind ... Signed-off-by:
-
