To make the output more readable, I think it's better to remove 0's in
the output. Also the dummy event has no event stats so it just wasts
the space. Let's use the --skip-empty option to suppress it.
$ perf report --stat --skip-empty
Aggregated stats:
TOTAL events: 16530
MMAP events: 226
COMM events: 1596
EXIT events: 2
THROTTLE events: 121
UNTHROTTLE events: 117
FORK events: 1595
SAMPLE events: 719
MMAP2 events: 12147
CGROUP events: 2
FINISHED_ROUND events: 2
THREAD_MAP events: 1
CPU_MAP events: 1
TIME_CONV events: 1
cycles stats:
SAMPLE events: 719
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210427013717.1651674-5-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Each struct hists have events_stats but most of the fields were not
used. It's to count number of samples and periods whether filtered or
not. And other fields are used only by evlist.
So it'd be better to split hists_stats and events_stats to reduce
wasted memory in the struct hists. This makes the output of event
statistics in the perf report compact by skipping 0 events in each
evsel/hists.
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/r/20210427013717.1651674-3-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The pipeline stage cycles details can be recorded on powerpc from the
contents of Performance Monitor Unit (PMU) registers. On ISA v3.1
platform, sampling registers exposes the cycles spent in different
pipeline stages. Patch adds perf tools support to present two of the
cycle counter information along with memory latency (weight).
Re-use the field 'ins_lat' for storing the first pipeline stage cycle.
This is stored in 'var2_w' field of 'perf_sample_weight'.
Add a new field 'p_stage_cyc' to store the second pipeline stage cycle
which is stored in 'var3_w' field of perf_sample_weight.
Add new sort function 'Pipeline Stage Cycle' and include this in
default_mem_sort_order[]. This new sort function may be used to denote
some other pipeline stage in another architecture. So add this to list
of sort entries that can have dynamic header string.
Signed-off-by: Athira Rajeev <atrajeev@linux.vnet.ibm.com>
Reviewed-by: Madhavan Srinivasan <maddy@linux.ibm.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kajol Jain <kjain@linux.ibm.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Link: https://lore.kernel.org/r/1616425047-1666-5-git-send-email-atrajeev@linux.vnet.ibm.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The instruction latency information can be recorded on some platforms,
e.g., the Intel Sapphire Rapids server. With both memory latency
(weight) and the new instruction latency information, users can easily
locate the expensive load instructions, and also understand the time
spent in different stages. The users can optimize their applications in
different pipeline stages.
The 'weight' field is shared among different architectures. Reusing the
'weight' field may impacts other architectures. Add a new field to store
the instruction latency.
Like the 'weight' support, introduce a 'ins_lat' for the global
instruction latency, and a 'local_ins_lat' for the local instruction
latency version.
Add new sort functions, INSTR Latency and Local INSTR Latency,
accordingly.
Add local_ins_lat to the default_mem_sort_order[].
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/1612296553-21962-7-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Two new data source fields, to indicate the block reasons of a load
instruction, are introduced on the Intel Sapphire Rapids server. The
fields can be used by the memory profiling.
Add a new sort function, SORT_MEM_BLOCKED, for the two fields.
For the previous platforms or the block reason is unknown, print "N/A"
for the block reason.
Add blocked as a default mem sort key for perf report and perf mem
report.
Committer testing:
So in machines without this capability we get a "N/A" filling the new "Blocked"
column:
$ perf mem record ls
arch certs CREDITS Documentation include ipc Kconfig lib MAINTAINERS mm samples security usr block
COPYING crypto drivers fs init Kbuild kernel LICENSES Makefile net README scripts sound tools
virt
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.008 MB perf.data (17 samples) ]
$
$ perf mem report --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Total Lost Samples: 0
#
# Samples: 6 of event 'cpu/mem-loads,ldlat=30/Pu'
# Total weight : 1381
# Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked
#
# Overhead Samples Local Weight Memory access Symbol Shared Object Data Symbol Data Object Snoop TLB access Locked Blocked
# ........ ....... ............ .................... ....................... ............. ...................... ............ ..... ............ ...... .......
#
32.87% 1 454 Local RAM or RAM hit [.] _dl_relocate_object ld-2.31.so [.] 0x00007fe91cef3078 libc-2.31.so Hit L1 or L2 hit No N/A
25.56% 1 353 LFB or LFB hit [.] strcmp ld-2.31.so [.] 0x00005586973855ca ls None L1 or L2 hit No N/A
22.59% 1 312 LFB or LFB hit [.] _dl_cache_libcmp ld-2.31.so [.] 0x00007fe91d0e3b18 ld.so.cache None L1 or L2 hit No N/A
8.47% 1 117 LFB or LFB hit [.] _dl_relocate_object ld-2.31.so [.] 0x00007fe91ceee570 libc-2.31.so None L1 or L2 hit No N/A
6.88% 1 95 LFB or LFB hit [.] _dl_relocate_object ld-2.31.so [.] 0x00007fe91ceed490 libc-2.31.so None L1 or L2 hit No N/A
3.62% 1 50 LFB or LFB hit [.] _dl_cache_libcmp ld-2.31.so [.] 0x00007fe91d0ebe60 ld.so.cache None L1 or L2 hit No N/A
# Samples: 11 of event 'cpu/mem-stores/Pu'
# Total weight : 11
# Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked
#
# Overhead Samples Local Weight Memory access Symbol Shared Object Data Symbol Data Object Snoop TLB access Locked Blocked
# ........ ....... ............ ............. ....................... ............. ...................... ........... ..... .......... ...... .......
#
9.09% 1 0 L1 hit [.] __strcoll_l libc-2.31.so [.] 0x00007fffe5648fc8 [stack] N/A N/A N/A N/A
9.09% 1 0 L1 hit [.] _dl_lookup_symbol_x ld-2.31.so [.] 0x00007fffe56490b8 [stack] N/A N/A N/A N/A
9.09% 1 0 L1 hit [.] _dl_name_match_p ld-2.31.so [.] 0x00007fffe56487d8 [stack] N/A N/A N/A N/A
9.09% 1 0 L1 hit [.] _dl_start ld-2.31.so [.] start_time+0x0 ld-2.31.so N/A N/A N/A N/A
9.09% 1 0 L1 hit [.] _dl_sysdep_start ld-2.31.so [.] 0x00007fffe56494b8 [stack] N/A N/A N/A N/A
9.09% 1 0 L1 hit [.] do_lookup_x ld-2.31.so [.] 0x00007fffe5648ff8 [stack] N/A N/A N/A N/A
9.09% 1 0 L1 hit [.] do_lookup_x ld-2.31.so [.] 0x00007fffe5649064 [stack] N/A N/A N/A N/A
9.09% 1 0 L1 hit [.] do_lookup_x ld-2.31.so [.] 0x00007fffe5649130 [stack] N/A N/A N/A N/A
9.09% 1 0 L1 miss [.] _dl_start ld-2.31.so [.] _rtld_global+0xaf8 ld-2.31.so N/A N/A N/A N/A
9.09% 1 0 L1 miss [.] _dl_start ld-2.31.so [.] _rtld_global+0xc28 ld-2.31.so N/A N/A N/A N/A
9.09% 1 0 L1 miss [.] _dl_start ld-2.31.so [.] 0x00007fffe56495b8 [stack] N/A N/A N/A N/A
# (Tip: Show user configuration overrides: perf config --user --list)
$
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Madhavan Srinivasan <maddy@linux.vnet.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lore.kernel.org/lkml/1612296553-21962-4-git-send-email-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf_evlist__ is for 'struct perf_evlist' methods, in tools/lib/perf/,
go on completing this split.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As it is a 'struct evsel' method, not part of tools/lib/perf/, aka
libperf, to whom the perf_ prefix belongs.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As it is a 'struct evsel' method, not part of tools/lib/perf/, aka
libperf, to whom the perf_ prefix belongs.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As those are 'struct evsel' methods, not part of tools/lib/perf/, aka
libperf, to whom the perf_ prefix belongs.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As it is a 'struct evsel' method, not part of tools/lib/perf/, aka
libperf, to whom the perf_ prefix belongs.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
As they are 'struct evsel' methods or related routines, not part of
tools/lib/perf/, aka libperf, to whom the perf_ prefix belongs.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Perf checks the duplicate entries in a callchain before adding an entry.
However the check is very slow especially with deeper call stack.
Almost ~50% elapsed time of perf report is spent on the check when the
call stack is always depth of 32.
The hist_entry__cmp() is used to compare the new entry with the old
entries. It will go through all the available sorts in the sort_list,
and call the specific cmp of each sort, which is very slow.
Actually, for most cases, there are no duplicate entries in callchain.
The symbols are usually different. It's much faster to do a quick check
for symbols first. Only do the full cmp when the symbols are exactly the
same.
The quick check is only to check symbols, not dso. Export
_sort__sym_cmp.
$ perf record --call-graph lbr ./tchain_edit_64
Without the patch
$time perf report --stdio
real 0m21.142s
user 0m21.110s
sys 0m0.033s
With the patch
$time perf report --stdio
real 0m10.977s
user 0m10.948s
sys 0m0.027s
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200319202517.23423-18-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The cgroup sort key is to show cgroup membership of each task.
Currently it shows full path in the cgroupfs (not relative to the root
of cgroup namespace) since it'd be more intuitive IMHO. Otherwise root
cgroup in different namespaces will all show same name - "/".
The cgroup sort key should come before cgroup_id otherwise
sort_dimension__add() will match it to cgroup_id as it only matches with
the given substring.
For example it will look like following. Note that record patch adding
--all-cgroups patch will come later.
$ perf record -a --namespace --all-cgroups cgtest
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.208 MB perf.data (4090 samples) ]
$ perf report -s cgroup_id,cgroup,pid
...
# Overhead cgroup id (dev/inode) Cgroup Pid:Command
# ........ ..................... .......... ...............
#
93.96% 0/0x0 / 0:swapper
1.25% 3/0xeffffffb / 278:looper0
0.86% 3/0xf000015f /sub/cgrp1 280:cgtest
0.37% 3/0xf0000160 /sub/cgrp2 281:cgtest
0.34% 3/0xf0000163 /sub/cgrp3 282:cgtest
0.22% 3/0xeffffffb /sub 278:looper0
0.20% 3/0xeffffffb / 280:cgtest
0.15% 3/0xf0000163 /sub/cgrp3 285:looper3
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20200325124536.2800725-6-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The low level index of raw branch records for the most recent branch can
be recorded in a sample with PERF_SAMPLE_BRANCH_HW_INDEX
branch_sample_type. Extend struct branch_stack to support it.
However, if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied, only nr and
entries[] will be output by kernel. The pointer of entries[] could be
wrong, since the output format is different with new struct
branch_stack. Add a variable no_hw_idx in struct perf_sample to
indicate whether the hw_idx is output. Add get_branch_entry() to return
corresponding pointer of entries[0].
To make dummy branch sample consistent as new branch sample, add hw_idx
in struct dummy_branch_stack for cs-etm and intel-pt.
Apply the new struct branch_stack for synthetic events as well.
Extend test case sample-parsing to support new struct branch_stack.
Committer notes:
Renamed get_branch_entries() to perf_sample__branch_entries() to have
proper namespacing and pave the way for this to be moved to libperf,
eventually.
Add 'static' to that inline as it is in a header.
Add 'hw_idx' to 'struct dummy_branch_stack' in cs-etm.c to fix the build
on arm64.
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mathieu Poirier <mathieu.poirier@linaro.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Pavel Gerasimov <pavel.gerasimov@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Vitaly Slobodskoy <vitaly.slobodskoy@intel.com>
Link: http://lore.kernel.org/lkml/20200228163011.19358-2-kan.liang@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
One more step on the merge of 'struct maps' with 'struct map_groups'.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-61rra2wg392rhvdgw421wzpt@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
One more step on the merge of 'struct maps' with 'struct map_groups'.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-foo95pyyp3bhocbt7yd8qrvq@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
And fill it whenever we setup a a 'struct map_symbol', now we need to
use it, next cset.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-fzwfcnddenz1o7uj1fzw3g46@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
So that we pass that substructure around and with it consolidate lots of
functions that receive a (map, symbol) pair and now can receive just a
'struct map_symbol' pointer.
This further paves the way to add 'struct map_groups' to 'struct
map_symbol' so that we can have all we need for annotation so that we
can ditch 'struct map'->groups, i.e. have the map_groups pointer in a
more central place, avoiding the pointer in the 'struct map' that have
tons of instances.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-fs90ttd9q12l7989fo7pw81q@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
perf report:
Jin Yao:
- Introduce --total-cycles, for basic block profiling, further using data
obtained from LBR, an example should suffice:
# perf record -b
^C[ perf record: Woken up 595 times to write data ]
[ perf record: Captured and wrote 156.672 MB perf.data (196873 samples) ]
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY
# perf report --total-cycles --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Total Lost Samples: 0
#
# Samples: 6M of event 'cycles'
# Event count (approx.): 6299936
#
# Sampled Sampled Avg Avg
# Cycles% Cycles Cycles% Cycles [Program Block Range] Shared Object
# ....... ...... ....... ..... .................................... ................
#
2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux]
0.72% 544.5K 0.03% 230 [entry_64.S:657 -> entry_64.S:662] [kernel.vmlinux]
0.56% 541.8K 0.09% 672 [compiler.h:199 -> common.c:300] [kernel.vmlinux]
0.39% 293.2K 0.01% 104 [list_debug.c:43 -> list_debug.c:61] [kernel.vmlinux]
0.36% 278.6K 0.03% 272 [entry_64.S:1289 -> entry_64.S:1308] [kernel.vmlinux]
perf record:
Adrian Hunter:
- Allow storing perf.data in a directory together with a copy of /proc/kcore.
Jiwei Sun:
- Add support for limit perf output file size, i.e.:
# perf record --all-cpus -F 10000 --max-size=4M sleep 10h
[ perf record: perf size limit reached (4097 KB), stopping session ]
[ perf record: Woken up 6 times to write data ]
[ perf record: Captured and wrote 4.048 MB perf.data (54094 samples) ]
Terminated
# ls -lah perf.data
-rw-------. 1 root root 4.1M Nov 7 15:27 perf.data
#
perf stat:
Jiri Olsa:
- Add --per-node agregation support:
In live mode:
# perf stat -a -I 1000 -e cycles --per-node
# time node cpus counts unit events
1.000542550 N0 20 6,202,097 cycles
1.000542550 N1 20 639,559 cycles
2.002040063 N0 20 7,412,495 cycles
2.002040063 N1 20 2,185,577 cycles
3.003451699 N0 20 6,508,917 cycles
3.003451699 N1 20 765,607 cycles
...
Or in the record/report stat session:
# perf stat record -a -I 1000 -e cycles
# time counts unit events
1.000536937 10,008,468 cycles
2.002090152 9,578,539 cycles
3.003625233 7,647,869 cycles
4.005135036 7,032,086 cycles
^C 4.340902364 3,923,893 cycles
# perf stat report --per-node
# time node cpus counts unit events
1.000536937 N0 20 9,355,086 cycles
1.000536937 N1 20 653,382 cycles
2.002090152 N0 20 7,712,838 cycles
2.002090152 N1 20 1,865,701 cycles
...
perf probe:
Masami Hiramatsu:
Various fixes related to recent additions to the DWARF format:
- Fix to find range-only function instance
- Walk function lines in lexical blocks
- Fix to show function entry line as probe-able
- Fix wrong address verification
- Fix to probe a function which has no entry pc
- Fix to probe an inline function which has no entry pc
- Fix to list probe event with correct line number
- Fix to show inlined function callsite without entry_pc
- Fix to show ranges of variables in functions without entry_pc
- Return a better scope DIE if there is no best scope
- Skip end-of-sequence and non statement lines
- Filter out instances except for inlined subroutine and subprogram
- Fix to show calling lines of inlined functions
- Skip overlapped location on searching variables
perf inject:
Adrian Hunter:
- Do not strip evsels with --strip, as they are needed for create_gcov
(see the autofdo example in tools/perf/Documentation/intel-pt.txt).
Intel PT:
Adrian Hunter:
- Intel PT uses an auxtrace_cache to store the results of code-walking, to avoid
repeated decoding. Add an auxtrace_cache__remove to handle text poke events.
core:
Andi Kleen:
- Always preserve errno while cleaning up perf_event_open failures.
llvm:
Arnaldo Carvalho de Melo:
- No need to tell that the request for saving a .o file for BPF events, as
expressed in ~/.perfconfig was satisfied, make that a debug message.
perf vendor events:
Intel:
Haiyan Song:
- Update CascadelakeX events to v1.05.
- Update all the Intel JSON metrics from TMAM 3.6.
Treewide:
Ian Rogers:
- Improve error paths, plugging leaks found using LLVM tools
such as libFuzzer.
jevents:
Yunfeng Ye:
- Fix resource leak in process_mapfile() and main()
perf kvm:
Igor Lubashev:
- Use evlist layer api when possible.
libsubcmd:
James Clark:
- Move EXTRA_FLAGS to the end to allow overriding existing flags.
- Use -O0 with DEBUG=1
perf diff:
Jin Yao:
- Don't use hack to skip column length calculation
CoreSight ETM:
Leo yan:
- Fix definition of macro TO_CS_QUEUE_NR
ARM64:
John Garry:
- Do not try to include libelf header files when its feature detection
failed, fixing the cross build for ARM64.
perf tests:
Leo Yan:
- Fix out of bounds memory access in the backward ring buffer test.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
-----BEGIN PGP SIGNATURE-----
iHUEABYIAB0WIQR2GiIUctdOfX2qHhGyPKLppCJ+JwUCXcRowQAKCRCyPKLppCJ+
JxHcAQCTtl9N3zkNjLWif1i6AGKNU9TzYpup+jDR5J83ggLqgQD+O931nR9wXUOe
9bDUr45cNw3ZkRbc1558hKPWIsceJgU=
=Rko+
-----END PGP SIGNATURE-----
Merge tag 'perf-core-for-mingo-5.5-20191107' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core
Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo:
perf report:
Jin Yao:
- Introduce --total-cycles, for basic block profiling, further using data
obtained from LBR, an example should suffice:
# perf record -b
^C[ perf record: Woken up 595 times to write data ]
[ perf record: Captured and wrote 156.672 MB perf.data (196873 samples) ]
# perf evlist -v
cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|BRANCH_STACK, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, branch_sample_type: ANY
# perf report --total-cycles --stdio
# To display the perf.data header info, please use --header/--header-only options.
#
# Total Lost Samples: 0
#
# Samples: 6M of event 'cycles'
# Event count (approx.): 6299936
#
# Sampled Sampled Avg Avg
# Cycles% Cycles Cycles% Cycles [Program Block Range] Shared Object
# ....... ...... ....... ..... .................................... ................
#
2.17% 1.7M 0.08% 607 [compiler.h:199 -> common.c:221] [kernel.vmlinux]
0.72% 544.5K 0.03% 230 [entry_64.S:657 -> entry_64.S:662] [kernel.vmlinux]
0.56% 541.8K 0.09% 672 [compiler.h:199 -> common.c:300] [kernel.vmlinux]
0.39% 293.2K 0.01% 104 [list_debug.c:43 -> list_debug.c:61] [kernel.vmlinux]
0.36% 278.6K 0.03% 272 [entry_64.S:1289 -> entry_64.S:1308] [kernel.vmlinux]
perf record:
Adrian Hunter:
- Allow storing perf.data in a directory together with a copy of /proc/kcore.
Jiwei Sun:
- Add support for limit perf output file size, i.e.:
# perf record --all-cpus -F 10000 --max-size=4M sleep 10h
[ perf record: perf size limit reached (4097 KB), stopping session ]
[ perf record: Woken up 6 times to write data ]
[ perf record: Captured and wrote 4.048 MB perf.data (54094 samples) ]
Terminated
# ls -lah perf.data
-rw-------. 1 root root 4.1M Nov 7 15:27 perf.data
#
perf stat:
Jiri Olsa:
- Add --per-node agregation support:
In live mode:
# perf stat -a -I 1000 -e cycles --per-node
# time node cpus counts unit events
1.000542550 N0 20 6,202,097 cycles
1.000542550 N1 20 639,559 cycles
2.002040063 N0 20 7,412,495 cycles
2.002040063 N1 20 2,185,577 cycles
3.003451699 N0 20 6,508,917 cycles
3.003451699 N1 20 765,607 cycles
...
Or in the record/report stat session:
# perf stat record -a -I 1000 -e cycles
# time counts unit events
1.000536937 10,008,468 cycles
2.002090152 9,578,539 cycles
3.003625233 7,647,869 cycles
4.005135036 7,032,086 cycles
^C 4.340902364 3,923,893 cycles
# perf stat report --per-node
# time node cpus counts unit events
1.000536937 N0 20 9,355,086 cycles
1.000536937 N1 20 653,382 cycles
2.002090152 N0 20 7,712,838 cycles
2.002090152 N1 20 1,865,701 cycles
...
perf probe:
Masami Hiramatsu:
Various fixes related to recent additions to the DWARF format:
- Fix to find range-only function instance
- Walk function lines in lexical blocks
- Fix to show function entry line as probe-able
- Fix wrong address verification
- Fix to probe a function which has no entry pc
- Fix to probe an inline function which has no entry pc
- Fix to list probe event with correct line number
- Fix to show inlined function callsite without entry_pc
- Fix to show ranges of variables in functions without entry_pc
- Return a better scope DIE if there is no best scope
- Skip end-of-sequence and non statement lines
- Filter out instances except for inlined subroutine and subprogram
- Fix to show calling lines of inlined functions
- Skip overlapped location on searching variables
perf inject:
Adrian Hunter:
- Do not strip evsels with --strip, as they are needed for create_gcov
(see the autofdo example in tools/perf/Documentation/intel-pt.txt).
Intel PT:
Adrian Hunter:
- Intel PT uses an auxtrace_cache to store the results of code-walking, to avoid
repeated decoding. Add an auxtrace_cache__remove to handle text poke events.
core:
Andi Kleen:
- Always preserve errno while cleaning up perf_event_open failures.
llvm:
Arnaldo Carvalho de Melo:
- No need to tell that the request for saving a .o file for BPF events, as
expressed in ~/.perfconfig was satisfied, make that a debug message.
perf vendor events:
Intel:
Haiyan Song:
- Update CascadelakeX events to v1.05.
- Update all the Intel JSON metrics from TMAM 3.6.
Treewide:
Ian Rogers:
- Improve error paths, plugging leaks found using LLVM tools
such as libFuzzer.
jevents:
Yunfeng Ye:
- Fix resource leak in process_mapfile() and main()
perf kvm:
Igor Lubashev:
- Use evlist layer api when possible.
libsubcmd:
James Clark:
- Move EXTRA_FLAGS to the end to allow overriding existing flags.
- Use -O0 with DEBUG=1
perf diff:
Jin Yao:
- Don't use hack to skip column length calculation
CoreSight ETM:
Leo yan:
- Fix definition of macro TO_CS_QUEUE_NR
ARM64:
John Garry:
- Do not try to include libelf header files when its feature detection
failed, fixing the cross build for ARM64.
perf tests:
Leo Yan:
- Fix out of bounds memory access in the backward ring buffer test.
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This patch provides helper routines to support new columns for block
info output.
The new columns are:
Sampled Cycles%
Sampled Cycles
Avg Cycles%
Avg Cycles
[Program Block Range]
Shared Object
v5:
---
1. Move more block related functions from builtin-report.c to
block-info.c
2. Set ms (map+sym) in block hist_entry. Because this info
is needed for reporting the block range (i.e. source line)
Committer notes:
Remove unused set_fmt() function, some build were not completing with:
util/block-info.c:396:20: error: unused function 'set_fmt' [-Werror,-Wunused-function]
static inline void set_fmt(struct block_fmt *block_fmt,
^
1 error generated.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191107074719.26139-5-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We can get the per sample cycles by hist__account_cycles(). It's also
useful to know the total cycles of all samples in order to get the
cycles coverage for a single program block in further. For example:
coverage = per block sampled cycles / total sampled cycles
This patch creates a new argument 'total_cycles' in hist__account_cycles(),
which will be added with the cycles of each sample.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191107074719.26139-4-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We have already implemented some block-info related functions.
Now it's time to do some cleanup, refactoring and move the
functions and structures to new block-info.h/block-info.c.
v4:
---
Move code for skipping column length calculation to patch:
'perf diff: Don't use hack to skip column length calculation'
v3:
---
1. Rename the patch title
2. Rename from block.h/block.c to block-info.h/block-info.c
3. Move more common part to block-info, such as
block_info__process_sym.
4. Remove the nasty hack for skipping calculation of column
length
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191107074719.26139-3-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Previously we use a nasty hack to skip the hists__calc_col_len for block
since this function is not very suitable for block column length
calculation.
This patch removes the hack code and add a check at the entry of
hists__calc_col_len to skip for block case.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lore.kernel.org/lkml/20191107074719.26139-2-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The final sort might get confused when the comparison is done over
bigger numbers than int like for -s time.
Check the following report for longer workloads:
$ perf report -s time -F time,overhead --stdio
Fix hist_entry__sort() to properly return int64_t and not possible cut
int.
Fixes: 043ca389a3 ("perf tools: Use hpp formats to sort final output")
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: stable@vger.kernel.org # v3.16+
Link: http://lore.kernel.org/lkml/20191104232711.16055-1-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The mem_info struct goes to mem-events.h and branch_info goes to
branch.h, where they belong, this way we can remove several headers from
symbols.h and trim the include dependency tree more.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-aupw71xnravcsu2xoabfmhpc@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Now that sort.h isn't included by any other header, we can check where
it is really needed, i.e. we can remove it and be sure that it isn't
being obtained indirectly.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-tom8k0lbsxd9joprr8zpu6w1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
So that we can reduce the header dependency tree further, in the process
noticed that lots of places were getting even things like build-id
routines and 'struct perf_tool' definition indirectly, so fix all those
too.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-ti0btma9ow5ndrytyoqdk62j@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
All we need there is a forward declaration for 'union perf_event', so
remove it from there and add missing header directives in places using
things from this indirect include.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-7ftk0ztstqub1tirjj8o8xbl@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
And fix the fallout, adding it to places that must have it since they
use its definitions.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-1s3jel4i26chq2g0lydoz7i3@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The event group feature links relevant hist entries among events so that
they can be displayed together. During the link process, each hist
entry in non-leader events is connected to a hist entry in the leader
event. This is done in order of events specified in the command line so
it assumes that events are linked in the order.
But 'perf top' can break the assumption since it does the link process
multiple times. For example, a hist entry can be in the third event
only at first so it's linked after the leader. Some time later, second
event has a hist entry for it and it'll be linked after the entry of the
third event.
This makes the code compilicated to deal with such unordered entries.
This patch simply unlink all the entries after it's printed so that they
can assume the correct order after the repeated link process. Also it'd
be easy to deal with decaying old entries IMHO.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Link: http://lkml.kernel.org/r/20190827231555.121411-2-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When he have an event group we have multiple struct hist instances, one
per evsel, and in each of these hists we may have hist_entries that
point to the same thing being observed, say a symbol, i.e. if we're
looking at instructions and cycles, then we'll have one hist_entry in
the "instructions" evsel and another in the "cycles" evsel.
We need to link those to then show one column for each. When we're
looking at some other pair of events, say instructions and cache misses,
we may have just the "instructions" hist entry and not one for "cache
misses", as instructions not necessarily generate cache misses, as the
logic expects one hist_entry per evsel, we end up adding "dummy"
hist_entries.
This is enough for 'perf report', that does this matching operation
(hists__match()) just once after processing all events, but for 'perf
top', we do this at each refresh, so we may finally find events matching
and then we need to trow away the dummies and link with the real events.
So if we find a match, traverse the link of matches and trow away
dummies for that hists.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-dwvtjqqifsbsczeb35q6mqkk@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
When we have multiple events in a group we link hist_entries in the
non-leader evsel hists to the one in the leader that points to the same
sorting criteria, in hists__match().
For 'perf report' we do this just once and then print the results, but
for 'perf top' we need to look if this was already done in the previous
refresh of the screen, so check for that and don't try to link again.
This is part of having 'perf top' using the hists browser for showing
multiple events in multiple columns.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-iwvb37rgb7upswhruwpcdnhw@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Move the nr_members member from perf's evsel to libperf's perf_evsel.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190721112506.12306-60-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Move the perf_event_attr struct fron 'struct evsel' to 'struct perf_evsel'.
Committer notes:
Fixed up these:
tools/perf/arch/arm/util/auxtrace.c
tools/perf/arch/arm/util/cs-etm.c
tools/perf/arch/arm64/util/arm-spe.c
tools/perf/arch/s390/util/auxtrace.c
tools/perf/util/cs-etm.c
Also
cc1: warnings being treated as errors
tests/sample-parsing.c: In function 'do_test':
tests/sample-parsing.c:162: error: missing initializer
tests/sample-parsing.c:162: error: (near initialization for 'evsel.core.cpus')
struct evsel evsel = {
.needs_swap = false,
- .core.attr = {
- .sample_type = sample_type,
- .read_format = read_format,
+ .core = {
+ . attr = {
+ .sample_type = sample_type,
+ .read_format = read_format,
+ },
[perfbuilder@a70e4eeb5549 /]$ gcc --version |& head -1
gcc (GCC) 4.4.7
Also we don't need to include perf_event.h in
tools/perf/lib/include/perf/evsel.h, forward declaring 'struct
perf_event_attr' is enough. And this even fixes the build in some
systems where things are used somewhere down the include path from
perf_event.h without defining __always_inline.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190721112506.12306-43-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Rename struct perf_evlist to struct evlist, so we don't have a name
clash when we add struct perf_evlist in libperf.
Committer notes:
Added fixes to build on arm64, from Jiri and from me
(tools/perf/util/cs-etm.c)
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190721112506.12306-6-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Rename struct perf_evsel to struct evsel, so we don't have a name clash
when we add struct perf_evsel in libperf.
Committer notes:
Added fixes for arm64, provided by Jiri.
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Alexey Budankov <alexey.budankov@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Michael Petlan <mpetlan@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20190721112506.12306-5-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
To allow for destructors to check if they're operating on a object still
in a list, and to avoid going from use after free list entries into
still valid, or even also other already removed from list entries.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-deh17ub44atyox3j90e6rksu@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
In places where the equivalent was already being done, i.e.:
free(a);
a = NULL;
And in placs where struct members are being freed so that if we have
some erroneous reference to its struct, then accesses to freed members
will result in segfaults, which we can detect faster than use after free
to areas that may still have something seemingly valid.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-jatyoofo5boc1bsvoig6bb6i@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Eroding a bit more the tools/perf/util/util.h hodpodge header.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https://lkml.kernel.org/n/tip-natazosyn9rwjka25tvcnyi0@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The hist__account_cycles() can account cycles per basic block. The basic
block information is saved in cycles_hist structure.
This patch processes each symbol, get basic blocks from cycles_hist and
add the basic block entries to a new hists (in 'struct block_hist').
Using a hists is because we need to compare, sort and print the basic
blocks later.
v6:
---
Since 'ops' argument is removed from hists__add_entry_block,
update the code accordingly. No functional change.
v5:
---
Since now we still carry block_info in 'struct hist_entry'
we don't need to use our own new/free ops for hist entries.
And the block_info is released in hist_entry__delete.
v3:
---
1. In v2, we put block stuffs in 'struct hist_entry', but
it's not a good design. In v3, we create a new
'struct block_hist' and cast the 'struct hist_entry' to
'struct block_hist' in some places, which can avoid adding
new stuffs in 'struct hist_entry'.
2. abs() -> labs(), in block_cycles_diff_cmp().
v2:
---
v1 adds the basic block entries to per data-file hists
but v2 adds the basic block entries to per symbol hists.
That is to keep current perf-diff format. Will show the
result in next patches.
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-5-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The block_info contains the program basic block information, i.e,
contains the start address and the end address of this basic block and
how much cycles it takes.
We need to compare, sort and even print out the basic block by some
orders, i.e. sort by cycles.
For this purpose, we add block_info field to hist_entry. In order not to
impact current interface, we creates a new function
hists__add_entry_block.
v6:
---
Remove the 'ops' argument in hists__add_entry_block
Signed-off-by: Jin Yao <yao.jin@linux.intel.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Jin Yao <yao.jin@intel.com>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/1561713784-30533-3-git-send-email-yao.jin@linux.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
The namespaces and comm fields of a thread are protected by rwsem and
require write access for it. So it ended up using a cast to remove
the const qualifier. Let's get rid of the const then.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Suggested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Hari Bathini <hbathini@linux.vnet.ibm.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Krister Johansen <kjlx@templeofstupid.com>
Link: http://lkml.kernel.org/r/20190527061149.168640-1-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We need to map__put() before returning from failure of
sample__resolve_callchain().
Detected with gcc's ASan.
Signed-off-by: Changbin Du <changbin.du@gmail.com>
Reviewed-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Daniel Borkmann <daniel@iogearbox.net>
Cc: Krister Johansen <kjlx@templeofstupid.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Fixes: 9c68ae98c6 ("perf callchain: Reference count maps")
Link: http://lkml.kernel.org/r/20190316080556.3075-10-changbin.du@gmail.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Now 'perf report' can show whole time periods with 'perf script', but
the user still has to find individual samples of interest manually.
It would be expensive and complicated to search for the right samples in
the whole perf file. Typically users only need to look at a small number
of samples for useful analysis.
Also the full scripts tend to show samples of all CPUs and all threads
mixed up, which can be very confusing on larger systems.
Add a new --samples option to save a small random number of samples per
hist entry.
Use a reservoir sample technique to select a representatve number of
samples.
Then allow browsing the samples using 'perf script' as part of the hist
entry context menu. This automatically adds the right filters, so only
the thread or cpu of the sample is displayed. Then we use less' search
functionality to directly jump the to the time stamp of the selected
sample.
It uses different menus for assembler and source display. Assembler
needs xed installed and source needs debuginfo.
Currently it only supports as many samples as fit on the screen due to
some limitations in the slang ui code.
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20190311174605.GA29294@tassilo.jf.intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Add a time sort key to perf report to display samples for different time
quantums separately. This allows easier analysis of workloads that
change over time, and also will allow looking at the context of samples.
% perf record ...
% perf report --sort time,overhead,symbol --time-quantum 1ms --stdio
...
0.67% 277061.87300 [.] _dl_start
0.50% 277061.87300 [.] f1
0.50% 277061.87300 [.] f2
0.33% 277061.87300 [.] main
0.29% 277061.87300 [.] _dl_lookup_symbol_x
0.29% 277061.87300 [.] dl_main
0.29% 277061.87300 [.] do_lookup_x
0.17% 277061.87300 [.] _dl_debug_initialize
0.17% 277061.87300 [.] _dl_init_paths
0.08% 277061.87300 [.] check_match
0.04% 277061.87300 [.] _dl_count_modids
1.33% 277061.87400 [.] f1
1.33% 277061.87400 [.] f2
1.33% 277061.87400 [.] main
1.17% 277061.87500 [.] main
1.08% 277061.87500 [.] f1
1.08% 277061.87500 [.] f2
1.00% 277061.87600 [.] main
0.83% 277061.87600 [.] f1
0.83% 277061.87600 [.] f2
1.00% 277061.87700 [.] main
Committer notes:
Rename 'time' argument to hist_time() to htime to overcome this in older
distros:
cc1: warnings being treated as errors
util/hist.c: In function 'hist_time':
util/hist.c:251: error: declaration of 'time' shadows a global declaration
/usr/include/time.h:186: error: shadowed declaration is here
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20190311144502.15423-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
We can't allocate he->srcline unconditionaly, only when new hist_entry
is created. Moving he->srcline allocation into hist_entry__init
function.
Original-patch-by: Jonas Rabenstein <jonas.rabenstein@studium.uni-erlangen.de>
Suggested-by: Namhyung Kim <namhyung@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Nageswara R Sastry <nasastry@in.ibm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com>
Link: http://lkml.kernel.org/r/20190305152536.21035-4-jolsa@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
