perf/core improvements and fixes
Arnaldo Carvalho de Melo
maintainerHi Ingo,
Please consider pulling, I'll try and be strict from now on wrt
new stuff versus fixes, which will got to a perf/urgent branch.
- Arnaldo
Test results at the end of this message, as usual.
The following changes since commit 770e96125515daf1c7bc179323f2e0d488dfe6ac:
Merge tag 'perf-core-for-mingo-4.14-20170901' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2017-09-05 07:14:28 +0200)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.14-20170912
for you to fetch changes up to f94843e82778769422e7e6a02b9ce39d5eb882f6:
perf vendor events: Add JSON metrics for Skylake server (2017-09-11 17:22:40 -0300)
----------------------------------------------------------------
perf/core improvements and fixes:
- Support direct --user-regs arguments in 'perf record', previously the only way to sample PERF_SAMPLE_REGS_USER was implicitly selecting it when recording callchains (Andi Kleen)
- Support showing sampled user regs in 'perf script' (Andi Kleen)
- Introduce the concept of weak groups in 'perf stat': try to set up a group, but if it's not schedulable fallback to not using a group. That gives us the best of both worlds: groups if they work, but still a usable fallback if they don't. E.g: (Andi Kleen)
% perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}:W' -a sleep 1
125,366,055 branches (80.02%)
9,208,402 branch-misses # 7.35% of all branches (80.01%)
24,560,249 l1d.replacement (80.00%)
43,174,971 l2_lines_in.all (80.05%)
31,891,457 l2_rqsts.all_code_rd (79.92%)- Support metrics in 'stat' and 'list'. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC). (Andi Kleen)
- Add Intel processors vendor event metrics JSON files (Andi Kleen)
- Add 'pid' and 'tid' options to 'perf sched timehist' (David Ahern)
- Improve TUI progress bar by showing how many bytes from a total were processed (Jiri Olsa)
- Make tools/lib/api make DEBUG=1 build use -D_FORTIFY_SOURCE=2 not to cripple debuginfo, just like tools/perf/ does (Jiri Olsa)
- Avoid leaking the 'perf.data' file to workloads started from the 'perf record' command line by using the O_CLOEXEC open flag (Jiri Olsa)
- Add 'python-clean' make target (Jiri Olsa)
- Use scandir() to replace readdir(), prep work to have the synthesizing of PERF_RECORD_ entries for existing threads be multithreaded, making 'perf top' bearable on high core count systems such as Intel's Knights Landing/Mill (Kan Liang)
- Fix building when libunwind's 'unwind.h' file is present in the include path, clashing with tools/perf/util/unwind.h (Milian Wolff)
- Support running perf binaries with a dash in their name (Milian Wolff)
- Allow creating a ~/.perfconfig file when setting a variable to its default value, previously it would bail out and not write such a file (Taeung Song)
- Avoid writing ~/.perfconfig repeatedly when processing changes to multiple variables (Taeung Song)
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
----------------------------------------------------------------
Andi Kleen (25):
perf tools: Support weak groups in 'perf stat'
perf vendor events: Support metric_group and no event name in JSON parser perf stat: Factor out generic metric printing
perf stat: Print generic metric header even for failed expressions perf pmu: Extract function to get JSON alias map
perf stat: Support JSON metrics in perf stat
perf list: Add metric groups to perf list
perf stat: Don't use ctx for saved values lookup
perf stat: Support duration_time for metrics
perf stat: Hide internal duration_time counter
perf stat: Update walltime_nsecs_stats in interval mode
perf record: Support direct --user-regs arguments
perf script: Support user regs
perf stat: Fall weak group back even for EBADF
perf vendor events: Add JSON metrics for Broadwell
perf vendor events: Add JSON metrics for Skylake
perf vendor events: Add JSON metrics for Sandy Bridge
perf vendor events: Add JSON metrics for Sandy Bridge EP perf vendor events: Add JSON metrics for Ivy Bridge
perf vendor events: Add JSON metrics for Haswell
perf vendor events: Add JSON metrics for Ivy Town
perf vendor events: Add JSON metrics for Haswell EP
perf vendor events: Add JSON metrics for Broadwell Server perf vendor events: Add JSON metrics for Broadwell DE
perf vendor events: Add JSON metrics for Skylake server
Arnaldo Carvalho de Melo (2):
tools include linux: Guard against redefinition of some macros perf tools: Make copyfile_offset() static
David Ahern (1):
perf sched timehist: Add pid and tid options
Jiri Olsa (7):
tools lib api: Fix make DEBUG=1 build
perf tools: Open perf.data with O_CLOEXEC flag perf tools: Add python-clean target
perf ui progress: Make sure we always define step value perf ui progress: Fix progress update
perf ui progress: Add ui specific init function perf ui progress: Add size info into progress bar
Kan Liang (1):
perf tools: Use scandir() to replace readdir()
Milian Wolff (2):
perf tests: Fix compile when libunwind's unwind.h is available perf tools: Support running perf binaries with a dash in their name
Taeung Song (3):
perf config: Check not only section->from_system_config but also item's perf config: Write a config file just once
perf config: Allow creating empty config set for config file autogeneration
tools/include/linux/compiler-gcc.h | 9 +- tools/lib/api/Makefile | 8 +- tools/perf/Documentation/perf-list.txt | 9 +- tools/perf/Documentation/perf-record.txt | 2 + tools/perf/Documentation/perf-sched.txt | 8 + tools/perf/Documentation/perf-script.txt | 4 +- tools/perf/Documentation/perf-stat.txt | 7 + tools/perf/Makefile.perf | 8 +- tools/perf/builtin-config.c | 24 +- tools/perf/builtin-list.c | 7 + tools/perf/builtin-record.c | 3 + tools/perf/builtin-sched.c | 4 + tools/perf/builtin-script.c | 30 +- tools/perf/builtin-stat.c | 82 +++- tools/perf/perf.c | 14 +- tools/perf/perf.h | 1 + .../pmu-events/arch/x86/broadwell/bdw-metrics.json | 164 +++++++ .../arch/x86/broadwellde/bdwde-metrics.json | 164 +++++++ .../arch/x86/broadwellx/bdx-metrics.json | 164 +++++++ .../pmu-events/arch/x86/haswell/hsw-metrics.json | 158 +++++++ .../pmu-events/arch/x86/haswellx/hsx-metrics.json | 158 +++++++ .../pmu-events/arch/x86/ivybridge/ivb-metrics.json | 164 +++++++ .../pmu-events/arch/x86/ivytown/ivt-metrics.json | 164 +++++++ .../pmu-events/arch/x86/jaketown/jkt-metrics.json | 140 ++++++ .../arch/x86/sandybridge/snb-metrics.json | 140 ++++++ .../pmu-events/arch/x86/skylake/skl-metrics.json | 164 +++++++ .../pmu-events/arch/x86/skylakex/skx-metrics.json | 182 ++++++++ tools/perf/pmu-events/jevents.c | 24 +- tools/perf/pmu-events/jevents.h | 2 +- tools/perf/pmu-events/pmu-events.h | 1 + tools/perf/tests/builtin-test.c | 1 + tools/perf/tests/dwarf-unwind.c | 2 +- tools/perf/ui/progress.c | 15 +- tools/perf/ui/progress.h | 12 +- tools/perf/ui/tui/progress.c | 32 +- tools/perf/util/Build | 1 + tools/perf/util/config.c | 5 +- tools/perf/util/data.c | 14 +- tools/perf/util/dso.c | 1 + tools/perf/util/event.c | 46 +- tools/perf/util/evlist.h | 1 + tools/perf/util/evsel.c | 7 +- tools/perf/util/evsel.h | 1 + tools/perf/util/metricgroup.c | 489 +++++++++++++++++++++ tools/perf/util/metricgroup.h | 31 ++ tools/perf/util/namespaces.c | 1 + tools/perf/util/parse-events.c | 11 +- tools/perf/util/parse-events.l | 3 +- tools/perf/util/pmu.c | 55 ++- tools/perf/util/pmu.h | 2 + tools/perf/util/probe-file.c | 1 + tools/perf/util/session.c | 2 +- tools/perf/util/stat-shadow.c | 110 +++-- tools/perf/util/stat.h | 4 +- tools/perf/util/util.c | 3 +- tools/perf/util/util.h | 2 - tools/perf/util/zlib.c | 1 + 57 files changed, 2734 insertions(+), 128 deletions(-) create mode 100644 tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json create mode 100644 tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json create mode 100644 tools/perf/util/metricgroup.c create mode 100644 tools/perf/util/metricgroup.h
Test results:
The first ones are container (docker) based builds of tools/perf with and without libelf support, objtool where it is supported and samples/bpf/, ditto. Where clang is available, it is also used to build perf with/without libelf.
Several are cross builds, the ones with -x-ARCH and the android one, and those may not have all the features built, due to lack of multi-arch devel packages, available and being used so far on just a few, like debian:experimental-x-{arm64,mipsel}.
The 'perf test' one will perform a variety of tests exercising tools/perf/util/, tools/lib/{bpf,traceevent,etc}, as well as run perf commands with a variety of command line event specifications to then intercept the sys_perf_event syscall to check that the perf_event_attr fields are set up as expected, among a variety of other unit tests.
Then there is the 'make -C tools/perf build-test' ones, that build tools/perf/ with a variety of feature sets, exercising the build with an incomplete set of features as well as with a complete one. It is planned to have it run on each of the containers mentioned above, using some container orchestration infrastructure. Get in contact if interested in helping having this in place. Tue Sep 12 09:49:13 -03 2017
[root@jouet ~]# waitp 23628 ; time dm
1 alpine:3.4: Ok
2 alpine:3.5: Ok
3 alpine:3.6: Ok
4 alpine:edge: Ok
5 android-ndk:r12b-arm: Ok
6 android-ndk:r15c-arm: Ok
7 archlinux:latest: Ok
8 centos:5: Ok
9 centos:6: Ok
10 centos:7: Ok
11 debian:7: Ok
12 debian:8: Ok
13 debian:9: Ok
14 debian:experimental: Ok
15 debian:experimental-x-arm64: Ok
16 debian:experimental-x-mips: Ok
17 debian:experimental-x-mips64: Ok
18 debian:experimental-x-mipsel: Ok
19 fedora:20: Ok
20 fedora:21: Ok
21 fedora:22: Ok
22 fedora:23: Ok
23 fedora:24: Ok
24 fedora:24-x-ARC-uClibc: Ok
25 fedora:25: Ok
26 fedora:26: Ok
27 fedora:rawhide: Ok
28 mageia:5: Ok
29 opensuse:13.2: Ok
30 opensuse:42.1: Ok
31 opensuse:42.2: Ok
32 opensuse:42.3: Ok
33 opensuse:tumbleweed: Ok
34 oraclelinux:6: Ok
35 oraclelinux:7: Ok
36 ubuntu:12.04.5: Ok
37 ubuntu:14.04.4: Ok
38 ubuntu:14.04.4-x-linaro-arm64: Ok
39 ubuntu:15.10: Ok
40 ubuntu:16.04: Ok
41 ubuntu:16.04-x-arm: Ok
42 ubuntu:16.04-x-arm64: Ok
43 ubuntu:16.04-x-powerpc: Ok
44 ubuntu:16.04-x-powerpc64: Ok
45 ubuntu:16.04-x-powerpc64el: Ok
46 ubuntu:16.04-x-s390: Ok
47 ubuntu:16.10: Ok
48 ubuntu:17.04: Ok
49 ubuntu:17.10: Ok
#
# uname -a Linux jouet 4.13.0-rc7+ #3 SMP Sat Sep 2 09:04:44 -03 2017 x86_64 x86_64 x86_64 GNU/Linux # perf test 1: vmlinux symtab matches kallsyms : Ok 2: Detect openat syscall event : Ok 3: Detect openat syscall event on all cpus : Ok 4: Read samples using the mmap interface : Ok 5: Test data source output : Ok 6: Parse event definition strings : Ok 7: Simple expression parser : Ok 8: PERF_RECORD_* events & perf_sample fields : Ok 9: Parse perf pmu format : Ok 10: DSO data read : Ok 11: DSO data cache : Ok 12: DSO data reopen : Ok 13: Roundtrip evsel->name : Ok 14: Parse sched tracepoints fields : Ok 15: syscalls:sys_enter_openat event fields : Ok 16: Setup struct perf_event_attr : Ok 17: Match and link multiple hists : Ok 18: 'import perf' in python : Ok 19: Breakpoint overflow signal handler : Ok 20: Breakpoint overflow sampling : Ok 21: Number of exit events of a simple workload : Ok 22: Software clock events period values : Ok 23: Object code reading : Ok 24: Sample parsing : Ok 25: Use a dummy software event to keep tracking : Ok 26: Parse with no sample_id_all bit set : Ok 27: Filter hist entries : Ok 28: Lookup mmap thread : Ok 29: Share thread mg : Ok 30: Sort output of hist entries : Ok 31: Cumulate child hist entries : Ok 32: Track with sched_switch : Ok 33: Filter fds with revents mask in a fdarray : Ok 34: Add fd to a fdarray, making it autogrow : Ok 35: kmod_path__parse : Ok 36: Thread map : Ok 37: LLVM search and compile : 37.1: Basic BPF llvm compile : Ok 37.2: kbuild searching : Ok 37.3: Compile source for BPF prologue generation : Ok 37.4: Compile source for BPF relocation : Ok 38: Session topology : Ok 39: BPF filter : 39.1: Basic BPF filtering : Ok 39.2: BPF pinning : Ok 39.3: BPF prologue generation : Ok 39.4: BPF relocation checker : Ok 40: Synthesize thread map : Ok 41: Remove thread map : Ok 42: Synthesize cpu map : Ok 43: Synthesize stat config : Ok 44: Synthesize stat : Ok 45: Synthesize stat round : Ok 46: Synthesize attr update : Ok 47: Event times : Ok 48: Read backward ring buffer : Ok 49: Print cpu map : Ok 50: Probe SDT events : Ok 51: is_printable_array : Ok 52: Print bitmap : Ok 53: perf hooks : Ok 54: builtin clang support : Skip (not compiled in) 55: unit_number__scnprintf : Ok 56: x86 rdpmc : Ok 57: Convert perf time to TSC : Ok 58: DWARF unwind : Ok 59: x86 instruction decoder - new instructions : Ok 60: Intel cqm nmi context read : Skip 61: Use vfs_getname probe to get syscall args filenames : Ok 62: probe libc's inet_pton & backtrace it with ping : Ok 63: Check open filename arg using perf trace + vfs_getname: Ok 64: Add vfs_getname probe to get syscall args filenames : Ok #
[acme@jouet linux]$ time make -C tools/perf build-test
make: Entering directory '/home/acme/git/linux/tools/perf'
- tarpkg: ./tests/perf-targz-src-pkg .
make_no_backtrace_O: make NO_BACKTRACE=1
make_minimal_O: make NO_LIBPERL=1 NO_LIBPYTHON=1 NO_NEWT=1 NO_GTK2=1 NO_DEMANGLE=1 NO_LIBELF=1 NO_LIBUNWIND=1 NO_BACKTRACE=1 NO_LIBNUMA=1 NO_LIBAUDIT=1 NO_LIBBIONIC=1 NO_LIBDW_DWARF_UNWIND=1 NO_AUXTRACE=1 NO_LIBBPF=1 NO_LIBCRYPTO=1 NO_SDT=1 NO_JVMTI=1
make_static_O: make LDFLAGS=-static
make_with_babeltrace_O: make LIBBABELTRACE=1
make_no_auxtrace_O: make NO_AUXTRACE=1
make_no_libpython_O: make NO_LIBPYTHON=1
make_help_O: make help
make_no_libperl_O: make NO_LIBPERL=1
make_no_demangle_O: make NO_DEMANGLE=1
make_clean_all_O: make clean all
make_no_libelf_O: make NO_LIBELF=1
make_install_O: make install
make_tags_O: make tags
make_no_libnuma_O: make NO_LIBNUMA=1
make_no_libbionic_O: make NO_LIBBIONIC=1
make_debug_O: make DEBUG=1
make_no_libaudit_O: make NO_LIBAUDIT=1
make_no_gtk2_O: make NO_GTK2=1
make_perf_o_O: make perf.o
make_no_newt_O: make NO_NEWT=1
make_util_pmu_bison_o_O: make util/pmu-bison.o
make_install_prefix_slash_O: make install prefix=/tmp/krava/
make_with_clangllvm_O: make LIBCLANGLLVM=1
make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1
make_util_map_o_O: make util/map.o
make_install_bin_O: make install-bin
make_pure_O: make
make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
make_no_libunwind_O: make NO_LIBUNWIND=1
make_doc_O: make doc
make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1
make_no_libbpf_O: make NO_LIBBPF=1
make_no_slang_O: make NO_SLANG=1
make_install_prefix_O: make install prefix=/tmp/krava
OK
make: Leaving directory '/home/acme/git/linux/tools/perf'
$
Arnaldo Carvalho de Melo
maintainerPATCH 1/41 perf sched timehist: Add pid and tid options
From: David Ahern <[email protected]>
Add options to only show event for specific pid(s) and tid(s).
Signed-off-by David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/Documentation/perf-sched.txt | 8 ++++++++ tools/perf/builtin-sched.c | 4 ++++ 2 files changed, 12 insertions(+)
tools/perf/Documentation/perf-sched.txt +8 -0
@@ -106,6 +106,14 @@ OPTIONS for 'perf sched timehist' --max-stack:: Maximum number of functions to display in backtrace, default 5. +-p=:: +--pid=:: + Only show events for given process ID (comma separated list). + +-t=:: +--tid=:: + Only show events for given thread ID (comma separated list). + -s:: --summary:: Show only a summary of scheduling by thread with min, max, and average
tools/perf/builtin-sched.c +4 -0
@@ -3363,6 +3363,10 @@ int cmd_sched(int argc, const char **argv)OPT_STRING (0 ,"time" , &sched.time_str,"str" ,"Time span for analysis (start,stop)" ),OPT_BOOLEAN (0 ,"state" , &sched.show_state,"Show task state when sched-out" ), +OPT_STRING ('p' ,"pid" , &symbol_conf.pid_list_str,"pid[,pid...]" , +"analyze events only for given process id(s)" ), +OPT_STRING ('t' ,"tid" , &symbol_conf.tid_list_str,"tid[,tid...]" , +"analyze events only for given thread id(s)" ), OPT_PARENT(sched_options) };
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 2/41 perf tools: Support weak groups in 'perf stat'
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Setting up groups can be complicated due to the complicated scheduling restrictions of different PMUs.
User tools usually don't understand all these restrictions.
Still in many cases it is useful to set up groups and they work most of the time. However if the group is set up wrong some members will not report any value because they never get scheduled.
Add a concept of a 'weak group': try to set up a group, but if it's not schedulable fallback to not using a group. That gives us the best of both worlds: groups if they work, but still a usable fallback if they don't.
In theory it would be possible to have more complex fallback strategies (e.g. try to split the group in half), but the simple fallback of not using a group seems to work for now.
So far the weak group is only implemented for perf stat, not for record.
Here's an unschedulable group (on IvyBridge with SMT on)
% perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1
73,806,067 branches
4,848,144 branch-misses # 6.57% of all branches
14,754,458 l1d.replacement
24,905,558 l2_lines_in.all
<not supported> l2_rqsts.all_code_rd <------- will never report anythingWith the weak group:
% perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}:W' -a sleep 1
125,366,055 branches (80.02%)
9,208,402 branch-misses # 7.35% of all branches (80.01%)
24,560,249 l1d.replacement (80.00%)
43,174,971 l2_lines_in.all (80.05%)
31,891,457 l2_rqsts.all_code_rd (79.92%)The extra event scheduled with some extra multiplexing
v2: Move fallback code to separate function.
Add comment on for_each_group_member
Adjust to new perf_evsel__close interface
v3: Fix debug print out.
Committer testing:
Before:
# perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1Performance counter stats for 'system wide':
<not counted> branches
<not counted> branch-misses
<not counted> l1d.replacement
<not counted> l2_lines_in.all
<not supported> l2_rqsts.all_code_rd1.002147212 seconds time elapsed
# perf stat -e '{branches,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}' -a sleep 1Performance counter stats for 'system wide':
83,207,892 branches
11,065,444 l1d.replacement
28,484,024 l2_lines_in.all
12,186,179 l2_rqsts.all_code_rd1.001739493 seconds time elapsed
After:
# perf stat -e '{branches,branch-misses,l1d.replacement,l2_lines_in.all,l2_rqsts.all_code_rd}':W -a sleep 1Performance counter stats for 'system wide':
543,323,909 branches (80.01%)
27,100,512 branch-misses # 4.99% of all branches (80.02%)
50,402,905 l1d.replacement (80.03%)
67,385,892 l2_lines_in.all (80.01%)
21,352,885 l2_rqsts.all_code_rd (79.94%)1.001086658 seconds time elapsed
#
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
[ Add a "'perf stat' only, for now" comment in the man page, suggested by Jiri ]
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/Documentation/perf-list.txt | 2 ++ tools/perf/builtin-stat.c | 35 ++++++++++++++++++++++++++++++++++ tools/perf/util/evsel.h | 1 + tools/perf/util/parse-events.c | 8 +++++++- tools/perf/util/parse-events.l | 2 +- 5 files changed, 46 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-list.txt +2 -0
@@ -47,6 +47,8 @@ counted. The following modifiers exist: P - use maximum detected precise level S - read sample value (PERF_SAMPLE_READ) D - pin the event to the PMU + W - group is weak and will fallback to non-group if not schedulable, + only supported in 'perf stat' for now. The 'p' modifier can be used for specifying how precise the instruction address should be. The 'p' modifier can be specified multiple times:
tools/perf/builtin-stat.c +35 -0
@@ -582,6 +582,32 @@ static bool perf_evsel__should_store_id(struct perf_evsel *counter)return STAT_RECORD || counter->attr.read_format &PERF_FORMAT_ID ; } +static struct perf_evsel *perf_evsel__reset_weak_group (struct perf_evsel *evsel) +{ +struct perf_evsel *c2, *leader; +bool is_open = true; + + leader = evsel->leader; +pr_debug ("Weak group for %s/%d failed\n" , + leader->name, leader->nr_members); + +/* +* for_each_group_member doesn't work here because it doesn't +* include the first entry. +*/ +evlist__for_each_entry (evsel_list, c2) { +if (c2 == evsel) + is_open = false; +if (c2->leader == leader) { +if (is_open) +perf_evsel__close (c2); + c2->leader = c2; + c2->nr_members =0 ; + } + } +return leader; +} +static int __run_perf_stat (int argc,const char **argv) {int interval = stat_config.interval;
@@ -618,6 +644,15 @@ static int __run_perf_stat(int argc, const char **argv)evlist__for_each_entry (evsel_list, counter) { try_again:if (create_perf_stat_counter (counter) <0 ) { + +/* Weak group failed. Reset the group. */ +if (errno ==EINVAL && + counter->leader != counter && + counter->weak_group) { + counter =perf_evsel__reset_weak_group (counter); + goto try_again; + } +/* * PPC returns ENXIO for HW counters until 2.6.37 * (behavior changed with commit b0a873e).
tools/perf/util/evsel.h +1 -0
@@ -137,6 +137,7 @@ struct perf_evsel {const char * metric_name;struct perf_evsel **metric_events;bool collect_stat; +bool weak_group; };union u64_swap {
tools/perf/util/parse-events.c +7 -1
@@ -1366,6 +1366,7 @@ struct event_modifier {int exclude_GH;int sample_read;int pinned; +int weak; }; static int get_event_modifier(struct event_modifier *mod, char *str,
@@ -1384,6 +1385,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str,int exclude = eu | ek | eh;int exclude_GH = evsel ? evsel->exclude_GH :0 ; +int weak =0 ;memset (mod,0 ,sizeof (*mod));
@@ -1421,6 +1423,8 @@ static int get_event_modifier(struct event_modifier *mod, char *str, sample_read =1 ; }else if (*str =='D' ) { pinned =1 ; + }else if (*str =='W' ) { + weak =1 ; }else break ;
@@ -1451,6 +1455,7 @@ static int get_event_modifier(struct event_modifier *mod, char *str, mod->exclude_GH = exclude_GH; mod->sample_read = sample_read; mod->pinned = pinned; + mod->weak = weak;return 0 ; }
@@ -1464,7 +1469,7 @@ static int check_modifier(char *str)char *p = str;/* The sizeof includes 0 byte as well. */ -if (strlen (str) > (sizeof ("ukhGHpppPSDI" ) -1 )) +if (strlen (str) > (sizeof ("ukhGHpppPSDIW" ) -1 ))return -1 ;while (*p) {
@@ -1504,6 +1509,7 @@ int parse_events__modifier_event(struct list_head *list, char *str, bool add) evsel->exclude_GH = mod.exclude_GH; evsel->sample_read = mod.sample_read; evsel->precise_max = mod.precise_max; + evsel->weak_group = mod.weak;if (perf_evsel__is_group_leader (evsel)) evsel->attr.pinned = mod.pinned;
tools/perf/util/parse-events.l +1 -1
@@ -161,7 +161,7 @@ name [a-zA-Z_*?][a-zA-Z0-9_*?.]* name_minus [a-zA-Z_*?][a-zA-Z0-9\-_*?.:]* drv_cfg_term [a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)? /* If you add a modifier you need to update check_modifier() */ -modifier_event [ukhpPGHSDI]+ +modifier_event [ukhpPGHSDIW]+ modifier_bp [rwx]{1,3} %%
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 3/41 perf vendor events: Support metric_group and no event name in JSON parser
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Some enhancements to the JSON parser to prepare for metrics support
- Parse the new MetricGroup field
- Support JSON events with no event name, that have only MetricName.
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/pmu-events/jevents.c | 24 ++++++++++++++++++------ tools/perf/pmu-events/jevents.h | 2 +- tools/perf/pmu-events/pmu-events.h | 1 + 3 files changed, 20 insertions(+), 7 deletions(-)
tools/perf/pmu-events/jevents.c +18 -6
@@ -292,7 +292,7 @@ static int print_events_table_entry(void *data, char *name, char *event, char *desc, char *long_desc, char *pmu, char *unit, char *perpkg, char *metric_expr, - char *metric_name) + char *metric_name, char *metric_group) { struct perf_entry_data *pd = data;FILE *outfp = pd->outfp;
@@ -304,8 +304,10 @@ static int print_events_table_entry(void *data, char *name, char *event,*/ fprintf (outfp,"{\n" ); -fprintf (outfp,"\t.name = \"%s\",\n" , name); -fprintf (outfp,"\t.event = \"%s\",\n" , event); +if (name) +fprintf (outfp,"\t.name = \"%s\",\n" , name); +if (event) +fprintf (outfp,"\t.event = \"%s\",\n" , event);fprintf (outfp,"\t.desc = \"%s\",\n" , desc);fprintf (outfp,"\t.topic = \"%s\",\n" , topic);if (long_desc && long_desc[0 ])
@@ -320,6 +322,8 @@ static int print_events_table_entry(void *data, char *name, char *event,fprintf (outfp,"\t.metric_expr = \"%s\",\n" , metric_expr);if (metric_name)fprintf (outfp,"\t.metric_name = \"%s\",\n" , metric_name); +if (metric_group) +fprintf (outfp,"\t.metric_group = \"%s\",\n" , metric_group);fprintf (outfp,"},\n" );return 0 ;
@@ -357,6 +361,9 @@ static char *real_event(const char *name, char *event) {int i; +if (!name) +return NULL ; +for (i =0 ; fixed[i].name; i++)if (!strcasecmp (name, fixed[i].name))return (char *)fixed[i].event;
@@ -369,7 +376,7 @@ int json_events(const char *fn,char *long_desc, char *pmu, char *unit, char *perpkg, char *metric_expr, - char *metric_name), + char *metric_name, char *metric_group), void *data) { int err = -EIO;
@@ -397,6 +404,7 @@ int json_events(const char *fn,char *unit =NULL ;char *metric_expr =NULL ;char *metric_name =NULL ; +char *metric_group =NULL ;unsigned long long eventcode =0 ;struct msrmap *msr =NULL ;jsmntok_t *msrval =NULL ;
@@ -476,6 +484,8 @@ int json_events(const char *fn,addfield (map, &perpkg,"" ,"" , val); }else if (json_streq (map, field,"MetricName" )) {addfield (map, &metric_name,"" ,"" , val); + }else if (json_streq (map, field,"MetricGroup" )) { +addfield (map, &metric_group,"" ,"" , val); }else if (json_streq (map, field,"MetricExpr" )) {addfield (map, &metric_expr,"" ,"" , val);for (s = metric_expr; *s; s++)
@@ -501,10 +511,11 @@ int json_events(const char *fn,addfield (map, &event,"," , filter,NULL );if (msr !=NULL )addfield (map, &event,"," , msr->pname, msrval); -fixname (name); +if (name) +fixname (name); err =func (data, name,real_event (name, event), desc, long_desc, - pmu, unit, perpkg, metric_expr, metric_name); + pmu, unit, perpkg, metric_expr, metric_name, metric_group);free (event);free (desc);free (name);
@@ -516,6 +527,7 @@ int json_events(const char *fn,free (unit);free (metric_expr);free (metric_name); +free (metric_group);if (err)break ; tok += j;
tools/perf/pmu-events/jevents.h +1 -1
@@ -6,7 +6,7 @@ int json_events(const char *fn,char *long_desc, char *pmu, char *unit, char *perpkg, char *metric_expr, - char *metric_name), + char *metric_name, char *metric_group), void *data);char *get_cpu_str (void );
tools/perf/pmu-events/pmu-events.h +1 -0
@@ -15,6 +15,7 @@ struct pmu_event {const char *perpkg;const char *metric_expr;const char *metric_name; +const char *metric_group; };/*
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 4/41 perf stat: Factor out generic metric printing
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
The 'perf stat' shadow metric printing already supports generic metrics. Factor out the code doing that into a separate function that can be re-used in a later patch.
No behavior changes.
v2: Fix indentation
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/stat-shadow.c | 69 ++++++++++++++++++++++++++----------------- 1 file changed, 42 insertions(+), 27 deletions(-)
tools/perf/util/stat-shadow.c +42 -27
@@ -627,6 +627,46 @@ static void print_smi_cost(int cpu, struct perf_evsel *evsel, out->print_metric (out->ctx,NULL ,"%4.0f" ,"SMI#" , smi_num); } +static void generic_metric (const char *metric_expr, +struct perf_evsel **metric_events, +char *name, +const char *metric_name, +double avg, +int cpu, +int ctx, +struct perf_stat_output_ctx *out) +{ +print_metric_t print_metric = out->print_metric; +struct parse_ctx pctx; +double ratio; +int i; +void *ctxp = out->ctx; + +expr__ctx_init (&pctx); +expr__add_id (&pctx, name, avg); +for (i =0 ; metric_events[i]; i++) { +struct saved_value *v; + + v =saved_value_lookup (metric_events[i], cpu, ctx, false); +if (!v) +break ; +expr__add_id (&pctx, metric_events[i]->name,avg_stats (&v->stats)); + } +if (!metric_events[i]) { +const char *p = metric_expr; + +if (expr__parse (&ratio, &pctx, &p) ==0 ) +print_metric (ctxp,NULL ,"%8.1f" , + metric_name ? + metric_name : + out->force_header ? name :"" , + ratio); +else +print_metric (ctxp,NULL ,NULL ,"" ,0 ); + }else +print_metric (ctxp,NULL ,NULL ,"" ,0 ); +} +void perf_stat__print_shadow_stats (struct perf_evsel *evsel,double avg,int cpu,struct perf_stat_output_ctx *out)
@@ -819,33 +859,8 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,else print_metric (ctxp,NULL ,NULL , name,0 ); }else if (evsel->metric_expr) { -struct parse_ctx pctx; -int i; - -expr__ctx_init (&pctx); -expr__add_id (&pctx, evsel->name, avg); -for (i =0 ; evsel->metric_events[i]; i++) { -struct saved_value *v; - - v =saved_value_lookup (evsel->metric_events[i], cpu, ctx, false); -if (!v) -break ; -expr__add_id (&pctx, evsel->metric_events[i]->name, -avg_stats (&v->stats)); - } -if (!evsel->metric_events[i]) { -const char *p = evsel->metric_expr; - -if (expr__parse (&ratio, &pctx, &p) ==0 ) -print_metric (ctxp,NULL ,"%8.1f" , - evsel->metric_name ? - evsel->metric_name : - out->force_header ? evsel->name :"" , - ratio); -else -print_metric (ctxp,NULL ,NULL ,"" ,0 ); - }else -print_metric (ctxp,NULL ,NULL ,"" ,0 ); +generic_metric (evsel->metric_expr, evsel->metric_events, evsel->name, + evsel->metric_name, avg, cpu, ctx, out); }else if (runtime_nsecs_stats[cpu].n !=0 ) {char unit ='M' ;char unit_buf[10 ];
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 5/41 perf stat: Print generic metric header even for failed expressions
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Print the generic metric header even when the expression evaluation failed. Otherwise an expression that fails on the first collections due to division by zero may suddenly reappear later without an header.
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/stat-shadow.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
tools/perf/util/stat-shadow.c +3 -1
@@ -662,7 +662,9 @@ static void generic_metric(const char *metric_expr, out->force_header ? name :"" , ratio); else - print_metric(ctxp, NULL, NULL, "", 0); + print_metric(ctxp, NULL, NULL, + out->force_header ? + (metric_name ? metric_name : name) : "", 0); }else print_metric (ctxp,NULL ,NULL ,"" ,0 ); }
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 6/41 perf pmu: Extract function to get JSON alias map
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Extract the code to get the per cpu JSON alias into a separate function for reuse. No behavior changes.
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/pmu.c | 49 +++++++++++++++++++++++++++++++++---------------- tools/perf/util/pmu.h | 2 ++ 2 files changed, 35 insertions(+), 16 deletions(-)
tools/perf/util/pmu.c +33 -16
@@ -516,16 +516,8 @@ char * __weak get_cpuid_str(void)return NULL ; } -/* -* From the pmu_events_map, find the table of PMU events that corresponds -* to the current running CPU. Then, add all PMU events from that table -* as aliases. -*/ -static void pmu_add_cpu_aliases (struct list_head *head,const char *name) +static char *perf_pmu__getcpuid (void ) { -int i; -struct pmu_events_map *map; -struct pmu_event *pe;char *cpuid;static bool printed;
@@ -535,22 +527,50 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)if (!cpuid) cpuid =get_cpuid_str ();if (!cpuid) -return ; +return NULL ;if (!printed) {pr_debug ("Using CPUID %s\n" , cpuid); printed = true; } +return cpuid; +} + +struct pmu_events_map *perf_pmu__find_map (void ) +{ +struct pmu_events_map *map; +char *cpuid =perf_pmu__getcpuid (); +int i; i =0 ; -while (1 ) { +for (;;) { map = &pmu_events_map[i++]; -if (!map->table) - goto out; +if (!map->table) { + map =NULL ; +break ; + }if (!strcmp (map->cpuid, cpuid))break ; } +free (cpuid); +return map; +} + +/* +* From the pmu_events_map, find the table of PMU events that corresponds +* to the current running CPU. Then, add all PMU events from that table +* as aliases. +*/ +static void pmu_add_cpu_aliases (struct list_head *head,const char *name) +{ +int i; +struct pmu_events_map *map; +struct pmu_event *pe; + + map =perf_pmu__find_map (); +if (!map) +return ;/* * Found a matching PMU events table. Create aliases
@@ -575,9 +595,6 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name) (char *)pe->metric_expr, (char *)pe->metric_name); } - -out: -free (cpuid); } struct perf_event_attr * __weak
tools/perf/util/pmu.h +2 -0
@@ -90,4 +90,6 @@ int perf_pmu__test(void);struct perf_event_attr *perf_pmu__get_default_config (struct perf_pmu *pmu); +struct pmu_events_map *perf_pmu__find_map (void ); +#endif /* __PMU_H */
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 7/41 perf stat: Support JSON metrics in perf stat
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add generic support for standalone metrics specified in JSON files to perf stat. A metric is a formula that uses multiple events to compute a higher level result (e.g. IPC).
Previously metrics were always tied to an event and automatically enabled with that event. But now change it that we can have standalone metrics. They are in the same JSON data structure as events, but don't have an event name.
We also allow to organize the metrics in metric groups, which allows a short cut to select several related metrics at once.
Add a new -M / --metrics option to perf stat that adds the metrics or metric groups specified.
Add the core code to manage and parse the metric groups. They are collected from the JSON data structures into a separate rblist. When computing shadow values look for metrics in that list. Then they are computed using the existing saved values infrastructure in stat-shadow.c
The actual JSON metrics are in a separate pull request.
% perf stat -M Summary --metric-only -a sleep 1
Performance counter stats for 'system wide':
Instructions CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 317614222.0 1392930775.0 0.0 0.0 0.2 0.1
1.001497549 seconds time elapsed
% perf stat -M GFLOPs flops
Performance counter stats for 'flops':
3,999,541,471 fp_comp_ops_exe.sse_scalar_single # 1.2 GFLOPs (66.65%)
14 fp_comp_ops_exe.sse_scalar_double (66.65%)
0 fp_comp_ops_exe.sse_packed_double (66.67%)
0 fp_comp_ops_exe.sse_packed_single (66.70%)
0 simd_fp_256.packed_double (66.70%)
0 simd_fp_256.packed_single (66.67%)
0 duration_time3.238372845 seconds time elapsed
v2: Add missing header file
v3: Move find_map to pmu.c
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/Documentation/perf-stat.txt | 7 + tools/perf/builtin-stat.c | 18 +- tools/perf/util/Build | 1 + tools/perf/util/metricgroup.c | 313 +++++++++++++++++++++++++++++++++ tools/perf/util/metricgroup.h | 31 ++++ tools/perf/util/pmu.c | 5 +- tools/perf/util/stat-shadow.c | 22 ++- tools/perf/util/stat.h | 4 +- 8 files changed, 395 insertions(+), 6 deletions(-) create mode 100644 tools/perf/util/metricgroup.c create mode 100644 tools/perf/util/metricgroup.h
tools/perf/Documentation/perf-stat.txt +7 -0
@@ -199,6 +199,13 @@ Aggregate counts per processor socket for system-wide mode measurements. --per-core:: Aggregate counts per physical processor for system-wide mode measurements. +-M:: +--metrics:: +Print metrics or metricgroups specified in a comma separated list. +For a group all metrics from the group are added. +The events from the metrics are automatically measured. +See perf list output for the possble metrics and metricgroups. + -A:: --no-aggr:: Do not aggregate counts across all monitored CPUs.
tools/perf/builtin-stat.c +16 -2
@@ -65,6 +65,7 @@#include "util/tool.h" #include "util/group.h" #include "util/string2.h" +#include "util/metricgroup.h" #include "asm/bug.h" #include <linux/time64.h>
@@ -133,6 +134,8 @@ static const char *smi_cost_attrs = {static struct perf_evlist *evsel_list; +static struct rblist metric_events; +static struct target target = { .uid =UINT_MAX , };
@@ -1234,7 +1237,7 @@ static void printout(int id, int nr, struct perf_evsel *counter, double uval,perf_stat__print_shadow_stats (counter, uval,first_shadow_cpu (counter, id), - &out); + &out, &metric_events);if (!csv_output && !metric_only) {print_noise (counter, noise);print_running (run, ena);
@@ -1565,7 +1568,8 @@ static void print_metric_headers(const char *prefix, bool no_indent) os.evsel = counter;perf_stat__print_shadow_stats (counter,0 ,0 , - &out); + &out, + &metric_events); }fputc ('\n' , stat_config.output); }
@@ -1789,6 +1793,13 @@ static int enable_metric_only(const struct option *opt __maybe_unused,return 0 ; } +static int parse_metric_groups (const struct option *opt, +const char *str, +int unset__maybe_unused ) +{ +return metricgroup__parse_groups (opt, str, &metric_events); +} +static const struct option stat_options[] = {OPT_BOOLEAN ('T' ,"transaction" , &transaction_run,"hardware transaction statistics" ),
@@ -1854,6 +1865,9 @@ static const struct option stat_options[] = { "measure topdown level 1 statistics"),OPT_BOOLEAN (0 ,"smi-cost" , &smi_cost,"measure SMI cost" ), +OPT_CALLBACK ('M' ,"metrics" , &evsel_list,"metric/metric group list" , +"monitor specified metrics or metric groups (separated by ,)" , + parse_metric_groups), OPT_END() };
tools/perf/util/Build +1 -0
@@ -34,6 +34,7 @@ libperf-y += dso.o libperf-y += symbol.o libperf-y += symbol_fprintf.o libperf-y += color.o +libperf-y += metricgroup.o libperf-y += header.o libperf-y += callchain.o libperf-y += values.o
tools/perf/util/metricgroup.c new file +313 -0
313 lines not on this page · raw message
tools/perf/util/metricgroup.h new file +31 -0
@@ -0,0 +1,31 @@ +#ifndef METRICGROUP_H +#define METRICGROUP_H 1 + +#include "linux/list.h" +#include "rblist.h" +#include <subcmd/parse-options.h> +#include "evlist.h" +#include "strbuf.h" + +struct metric_event { +struct rb_node nd; +struct perf_evsel *evsel; +struct list_head head;/* list of metric_expr */ +}; + +struct metric_expr { +struct list_head nd; +const char *metric_expr; +const char *metric_name; +struct perf_evsel **metric_events; +}; + +struct metric_event *metricgroup__lookup (struct rblist *metric_events, +struct perf_evsel *evsel, +bool create); +int metricgroup__parse_groups (const struct option *opt, +const char *str, +struct rblist *metric_events); + +void metricgroup__print (bool metrics,bool groups,char *filter,bool raw); +#endif
tools/perf/util/pmu.c +4 -1
@@ -580,8 +580,11 @@ static void pmu_add_cpu_aliases(struct list_head *head, const char *name)const char *pname; pe = &map->table[i++]; -if (!pe->name) +if (!pe->name) { +if (pe->metric_group || pe->metric_name) +continue ;break ; + } pname = pe->pmu ? pe->pmu :"cpu" ;if (strncmp (pname, name,strlen (pname)))
tools/perf/util/stat-shadow.c +20 -2
@@ -6,6 +6,7 @@#include "rblist.h" #include "evlist.h" #include "expr.h" +#include "metricgroup.h" enum {CTX_BIT_USER =1 <<0 ,
@@ -671,13 +672,16 @@ static void generic_metric(const char *metric_expr,void perf_stat__print_shadow_stats (struct perf_evsel *evsel,double avg,int cpu, -struct perf_stat_output_ctx *out) +struct perf_stat_output_ctx *out, +struct rblist *metric_events) {void *ctxp = out->ctx;print_metric_t print_metric = out->print_metric;double total, ratio =0.0 , total2;const char *color =NULL ;int ctx =evsel_context (evsel); +struct metric_event *me; +int num =1 ;if (perf_evsel__match (evsel,HARDWARE ,HW_INSTRUCTIONS )) { total =avg_stats (&runtime_cycles_stats[ctx][cpu]);
@@ -880,6 +884,20 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, }else if (perf_stat_evsel__is (evsel,SMI_NUM )) {print_smi_cost (cpu, evsel, out); }else { -print_metric (ctxp,NULL ,NULL ,NULL ,0 ); + num =0 ; } + +if ((me =metricgroup__lookup (metric_events, evsel, false)) !=NULL ) { +struct metric_expr *mexp; + + list_for_each_entry (mexp, &me->head, nd) { +if (num++ >0 ) + out->new_line (ctxp); +generic_metric (mexp->metric_expr, mexp->metric_events, + evsel->name, mexp->metric_name, + avg, cpu, ctx, out); + } + } +if (num ==0 ) +print_metric (ctxp,NULL ,NULL ,NULL ,0 ); }
tools/perf/util/stat.h +3 -1
@@ -91,9 +91,11 @@ struct perf_stat_output_ctx {bool force_header; }; +struct rblist ;void perf_stat__print_shadow_stats (struct perf_evsel *evsel,double avg,int cpu, -struct perf_stat_output_ctx *out); +struct perf_stat_output_ctx *out, +struct rblist *metric_events);void perf_stat__collect_metric_expr (struct perf_evlist *);int perf_evlist__alloc_stats (struct perf_evlist *evlist,bool alloc_raw);
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 8/41 perf list: Add metric groups to perf list
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add code to perf list to print metric groups, and metrics that don't have an event name. The metricgroup code collects the eventgroups and events into a rblist, and then prints them according to the configured filters.
The metricgroups are printed by default, but can be limited by perf list metric or perf list metricgroup
% perf list metricgroup
..
Metric Groups:
DSB:
DSB_Coverage
[Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)]
FLOPS:
GFLOPs
[Giga Floating Point Operations Per Second]
Frontend:
IFetch_Line_Utilization
[Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions]
Frontend_Bandwidth:
DSB_Coverage
[Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)]
Memory_BW:
MLP
[Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)]
v2: Check return value of asprintf to fix warning on FC26 Fix key in lookup/addition for the groups list
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/Documentation/perf-list.txt | 7 +- tools/perf/builtin-list.c | 7 ++ tools/perf/util/metricgroup.c | 176 +++++++++++++++++++++++++++++++++ tools/perf/util/parse-events.c | 3 + 4 files changed, 192 insertions(+), 1 deletion(-)
tools/perf/Documentation/perf-list.txt +6 -1
@@ -8,7 +8,8 @@ perf-list - List all symbolic event types SYNOPSIS -------- [verse] -'perf list' [--no-desc] [--long-desc] [hw|sw|cache|tracepoint|pmu|sdt|event_glob] +'perf list' [--no-desc] [--long-desc] + [hw|sw|cache|tracepoint|pmu|sdt|metric|metricgroup|event_glob] DESCRIPTION -----------
@@ -248,6 +249,10 @@ To limit the list use: . 'sdt' to list all Statically Defined Tracepoint events. +. 'metric' to list metrics + +. 'metricgroup' to list metricgroups with metrics. + . If none of the above is matched, it will apply the supplied glob to all events, printing the ones that match.
tools/perf/builtin-list.c +7 -0
@@ -15,6 +15,7 @@#include "util/cache.h" #include "util/pmu.h" #include "util/debug.h" +#include "util/metricgroup.h" #include <subcmd/parse-options.h> static bool desc_flag = true;
@@ -79,6 +80,10 @@ int cmd_list(int argc, const char **argv) long_desc_flag, details_flag); else if (strcmp(argv[i], "sdt") == 0) print_sdt_events(NULL, NULL, raw_dump); + else if (strcmp(argv[i], "metric") == 0) + metricgroup__print(true, false, NULL, raw_dump); + else if (strcmp(argv[i], "metricgroup") == 0) + metricgroup__print(false, true, NULL, raw_dump); else if ((sep = strchr(argv[i], ':')) != NULL) {int sep_idx;
@@ -96,6 +101,7 @@ int cmd_list(int argc, const char **argv) s[sep_idx] ='\0' ;print_tracepoint_events (s, s + sep_idx +1 , raw_dump);print_sdt_events (s, s + sep_idx +1 , raw_dump); +metricgroup__print (true, true, s, raw_dump);free (s); }else {if (asprintf (&s,"*%s*" , argv[i]) <0 ) {
@@ -112,6 +118,7 @@ int cmd_list(int argc, const char **argv) details_flag);print_tracepoint_events (NULL , s, raw_dump);print_sdt_events (NULL , s, raw_dump); +metricgroup__print (true, true,NULL , raw_dump);free (s); } }
tools/perf/util/metricgroup.c +176 -0
182 lines not on this page · raw message
tools/perf/util/parse-events.c +3 -0
@@ -28,6 +28,7 @@#include "probe-file.h" #include "asm/bug.h" #include "util/parse-branch-options.h" +#include "metricgroup.h" #define MAX_NAME_LEN 100
@@ -2380,6 +2381,8 @@ void print_events(const char *event_glob, bool name_only, bool quiet_flag,print_tracepoint_events (NULL ,NULL , name_only);print_sdt_events (NULL ,NULL , name_only); + +metricgroup__print (true, true,NULL , name_only); }int parse_events__is_hardcoded_term (struct parse_events_term *term)
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 9/41 perf stat: Don't use ctx for saved values lookup
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
We don't need to use ctx to look up events for saved values. The context is already part of the evsel pointer, which is the primary key.
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/stat-shadow.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-)
tools/perf/util/stat-shadow.c +5 -11
@@ -56,7 +56,6 @@ struct saved_value {struct rb_node rb_node;struct perf_evsel *evsel;int cpu; -int ctx;struct stats stats; };
@@ -67,8 +66,6 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry) rb_node);const struct saved_value *b = entry; -if (a->ctx != b->ctx) -return a->ctx - b->ctx;if (a->cpu != b->cpu)return a->cpu - b->cpu;if (a->evsel == b->evsel)
@@ -90,13 +87,12 @@ static struct rb_node *saved_value_new(struct rblist *rblist __maybe_unused, }static struct saved_value *saved_value_lookup (struct perf_evsel *evsel, -int cpu,int ctx, +int cpu,bool create) {struct rb_node *nd;struct saved_value dm = { .cpu = cpu, - .ctx = ctx, .evsel = evsel, }; nd =rblist__find (&runtime_saved_values, &dm);
@@ -232,8 +228,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,update_stats (&runtime_aperf_stats[ctx][cpu], count[0 ]);if (counter->collect_stat) { -struct saved_value *v =saved_value_lookup (counter, cpu, ctx, - true); +struct saved_value *v =saved_value_lookup (counter, cpu, true);update_stats (&v->stats, count[0 ]); } }
@@ -634,7 +629,6 @@ static void generic_metric(const char *metric_expr,const char *metric_name, double avg, int cpu, - int ctx, struct perf_stat_output_ctx *out) { print_metric_t print_metric = out->print_metric;
@@ -648,7 +642,7 @@ static void generic_metric(const char *metric_expr,for (i =0 ; metric_events[i]; i++) {struct saved_value *v; - v =saved_value_lookup (metric_events[i], cpu, ctx, false); + v =saved_value_lookup (metric_events[i], cpu, false);if (!v)break ;expr__add_id (&pctx, metric_events[i]->name,avg_stats (&v->stats));
@@ -866,7 +860,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel,print_metric (ctxp,NULL ,NULL , name,0 ); }else if (evsel->metric_expr) {generic_metric (evsel->metric_expr, evsel->metric_events, evsel->name, - evsel->metric_name, avg, cpu, ctx, out); + evsel->metric_name, avg, cpu, out); }else if (runtime_nsecs_stats[cpu].n !=0 ) {char unit ='M' ;char unit_buf[10 ];
@@ -895,7 +889,7 @@ void perf_stat__print_shadow_stats(struct perf_evsel *evsel, out->new_line (ctxp);generic_metric (mexp->metric_expr, mexp->metric_events, evsel->name, mexp->metric_name, - avg, cpu, ctx, out); + avg, cpu, out); } }if (num ==0 )
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 10/41 perf stat: Support duration_time for metrics
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Some of the metrics formulas (like GFLOPs) need to know how long the measurement period is. Support an internal event called duration_time, which reports time in second. It maps to the dummy event, but is special cased for statistics to report the walltime duration.
So far it is not printed, but only used internally for metrics.
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/parse-events.l | 1 + tools/perf/util/stat-shadow.c | 17 +++++++++++++---- 2 files changed, 14 insertions(+), 4 deletions(-)
tools/perf/util/parse-events.l +1 -0
@@ -288,6 +288,7 @@ cpu-migrations|migrations { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COU alignment-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); } emulation-faults { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); } dummy { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } +duration_time { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); } bpf-output { return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); } /*
tools/perf/util/stat-shadow.c +13 -4
@@ -641,11 +641,20 @@ static void generic_metric(const char *metric_expr,expr__add_id (&pctx, name, avg);for (i =0 ; metric_events[i]; i++) {struct saved_value *v; +struct stats *stats; +double scale; - v =saved_value_lookup (metric_events[i], cpu, false); -if (!v) -break ; -expr__add_id (&pctx, metric_events[i]->name,avg_stats (&v->stats)); +if (!strcmp (metric_events[i]->name,"duration_time" )) { + stats = &walltime_nsecs_stats; + scale =1e-9 ; + }else { + v =saved_value_lookup (metric_events[i], cpu, false); +if (!v) +break ; + stats = &v->stats; + scale =1.0 ; + } +expr__add_id (&pctx, metric_events[i]->name,avg_stats (stats)*scale); }if (!metric_events[i]) {const char *p = metric_expr;
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 11/41 perf stat: Hide internal duration_time counter
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Some perf stat metrics use an internal "duration_time" metric. It is not correctly printed however. So hide it during output to avoid confusing users with 0 counts.
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/builtin-stat.c | 27 ++++++++++++++++++++++++--- 1 file changed, 24 insertions(+), 3 deletions(-)
tools/perf/builtin-stat.c +24 -3
@@ -195,6 +195,11 @@ static struct perf_stat_config stat_config = { .scale = true, }; +static bool is_duration_time (struct perf_evsel *evsel) +{ +return !strcmp (evsel->name,"duration_time" ); +} +static inline void diff_timespec (struct timespec *r,struct timespec *a,struct timespec *b) {
@@ -1363,6 +1368,9 @@ static void print_aggr(char *prefix) ad.id = id = aggr_map->map[s]; first = true;evlist__for_each_entry (evsel_list, counter) { +if (is_duration_time (counter)) +continue ; + ad.val = ad.ena = ad.run =0 ; ad.nr =0 ;if (!collect_data (counter, aggr_cb, &ad))
@@ -1506,6 +1514,8 @@ static void print_no_aggr_metric(char *prefix)if (prefix)fputs (prefix, stat_config.output);evlist__for_each_entry (evsel_list, counter) { +if (is_duration_time (counter)) +continue ;if (first) {aggr_printout (counter, cpu,0 ); first = false;
@@ -1560,6 +1570,8 @@ static void print_metric_headers(const char *prefix, bool no_indent)/* Print metrics headers only */ evlist__for_each_entry (evsel_list, counter) { +if (is_duration_time (counter)) +continue ; os.evsel = counter; out.ctx = &os; out.print_metric = print_metric_header;
@@ -1707,12 +1719,18 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)print_aggr (prefix);break ;case AGGR_THREAD : -evlist__for_each_entry (evsel_list, counter) +evlist__for_each_entry (evsel_list, counter) { +if (is_duration_time (counter)) +continue ;print_aggr_thread (counter, prefix); + }break ;case AGGR_GLOBAL : -evlist__for_each_entry (evsel_list, counter) +evlist__for_each_entry (evsel_list, counter) { +if (is_duration_time (counter)) +continue ;print_counter_aggr (counter, prefix); + }if (metric_only)fputc ('\n' , stat_config.output);break ;
@@ -1720,8 +1738,11 @@ static void print_counters(struct timespec *ts, int argc, const char **argv)if (metric_only)print_no_aggr_metric (prefix);else { -evlist__for_each_entry (evsel_list, counter) +evlist__for_each_entry (evsel_list, counter) { +if (is_duration_time (counter)) +continue ;print_counter (counter, prefix); + } }break ;case AGGR_UNSET :
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 12/41 perf stat: Update walltime_nsecs_stats in interval mode
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Some metrics (like GFLOPs) need walltime_nsecs_stats for each interval. Compute it for each interval instead of only at the end.
Pointed out by Jiri.
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/builtin-stat.c | 2 ++ 1 file changed, 2 insertions(+)
tools/perf/builtin-stat.c +2 -0
@@ -415,6 +415,8 @@ static void process_interval(void)pr_err ("failed to write stat round event\n" ); } +init_stats (&walltime_nsecs_stats); +update_stats (&walltime_nsecs_stats, stat_config.interval *1000000 );print_counters (&rs,0 ,NULL ); }
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 13/41 tools include linux: Guard against redefinition of some macros
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
When cross building to android r15c (and older versions) on Fedora 26 we notice these:
/opt/android-ndk-r15c/platforms/android-24/arch-arm/usr/include/sys/cdefs.h:332:0: note: this is the location of the previous definition
For __aligned, __packed and __noreturn, so guard those with ifdefs to avoid drowning useful warnings in these.
Cc Adrian Hunter <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Wang Nan <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/include/linux/compiler-gcc.h | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-)
tools/include/linux/compiler-gcc.h +6 -3
@@ -21,11 +21,14 @@#define __must_be_array (a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0]))#define noinline __attribute__((noinline)) - +#ifndef __packed#define __packed __attribute__((packed)) - +#endif +#ifndef __noreturn#define __noreturn __attribute__((noreturn)) - +#endif +#ifndef __aligned#define __aligned (x) __attribute__((aligned(x))) +#endif #define __printf (a, b) __attribute__((format(printf, a, b)))#define __scanf (a, b) __attribute__((format(scanf, a, b)))
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 14/41 perf record: Support direct --user-regs arguments
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
USER_REGS can currently only collected implicitely with call graph recording. Sometimes it is useful to see them separately, and filter them. Add a new --user-regs option to record that is similar to --intr-regs, but acts on user regs.
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/Documentation/perf-record.txt | 2 ++ tools/perf/builtin-record.c | 3 +++ tools/perf/perf.h | 1 + tools/perf/util/evsel.c | 7 ++++++- 4 files changed, 12 insertions(+), 1 deletion(-)
tools/perf/Documentation/perf-record.txt +2 -0
@@ -377,6 +377,8 @@ symbolic names, e.g. on x86, ax, si. To list the available registers use --intr-regs=\?. To name registers, pass a comma separated list such as --intr-regs=ax,bx. The list of register is architecture dependent. +--user-regs:: +Capture user registers at sample time. Same arguments as -I. --running-time:: Record running and enabled time for read events (:S)
tools/perf/builtin-record.c +3 -0
@@ -1643,6 +1643,9 @@ static struct option __record_options[] = {OPT_CALLBACK_OPTARG ('I' ,"intr-regs" , &record.opts.sample_intr_regs,NULL ,"any register" ,"sample selected machine registers on interrupt," " use -I ? to list register names" , parse_regs), +OPT_CALLBACK_OPTARG (0 ,"user-regs" , &record.opts.sample_user_regs,NULL ,"any register" , +"sample selected machine registers on interrupt," +" use -I ? to list register names" , parse_regs),OPT_BOOLEAN (0 ,"running-time" , &record.opts.running_time,"Record running/enabled time of read (:S) events" ), OPT_CALLBACK('k', "clockid", &record.opts,
tools/perf/perf.h +1 -0
@@ -65,6 +65,7 @@ struct record_opts {unsigned int user_freq;u64 branch_stack;u64 sample_intr_regs; +u64 sample_user_regs;u64 default_interval;u64 user_interval;size_t auxtrace_snapshot_size;
tools/perf/util/evsel.c +6 -1
@@ -678,7 +678,7 @@ void perf_evsel__config_callchain(struct perf_evsel *evsel,if (!function) {perf_evsel__set_sample_bit (evsel,REGS_USER );perf_evsel__set_sample_bit (evsel,STACK_USER ); - attr->sample_regs_user =PERF_REGS_MASK ; + attr->sample_regs_user |=PERF_REGS_MASK ; attr->sample_stack_user = param->dump_size; attr->exclude_callchain_user =1 ; }else {
@@ -931,6 +931,11 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts,perf_evsel__set_sample_bit (evsel,REGS_INTR ); } +if (opts->sample_user_regs) { + attr->sample_regs_user |= opts->sample_user_regs; +perf_evsel__set_sample_bit (evsel,REGS_USER ); + } +if (target__has_cpu (&opts->target) || opts->sample_cpu)perf_evsel__set_sample_bit (evsel,CPU );
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 15/41 perf script: Support user regs
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Teach perf script to print user regs.
% perf record --user-regs=ip,sp ...
% perf script -F ip,sym,uregs
...
ffffffff9e060c24 native_write_msr ABI:2 SP:0x7ffd0ea06c38 IP:0x7fe77f55b637 ffffffff9e060c24 native_write_msr ABI:2 SP:0x7ffd0ea06c38 IP:0x7fe77f55b637 ffffffff9e060c24 native_write_msr ABI:2 SP:0x7ffd0ea06c38 IP:0x7fe77f55b637 ffffffff9e060c24 native_write_msr ABI:2 SP:0x7ffd0ea06c38 IP:0x7fe77f55b637
ffffffff9e00cc12 intel_pmu_handle_irq ABI:2 SP:0x7ffd0ea06c38 IP:0x7fe77f55b637
v2: Rebased on top of phys-addr patches
Signed-off-by Andi Kleen <[email protected]>
[ Use PRIu64 for regs->abi in print_sample_uregs() ]
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/Documentation/perf-script.txt | 4 ++-- tools/perf/builtin-script.c | 30 +++++++++++++++++++++++++++++- 2 files changed, 31 insertions(+), 3 deletions(-)
tools/perf/Documentation/perf-script.txt +2 -2
@@ -116,8 +116,8 @@ OPTIONS --fields:: Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, - srcline, period, iregs, brstack, brstacksym, flags, bpf-output, brstackinsn, brstackoff, - callindent, insn, insnlen, synth, phys_addr. + srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, + brstackoff, callindent, insn, insnlen, synth, phys_addr. Field list can be prepended with the type, trace, sw or hw, to indicate to which event type the field list applies. e.g., -F sw:comm,tid,time,ip,sym and -F trace:time,cpu,trace
tools/perf/builtin-script.c +29 -1
@@ -88,6 +88,7 @@ enum perf_output_field {PERF_OUTPUT_BRSTACKOFF =1U <<24 ,PERF_OUTPUT_SYNTH =1U <<25 ,PERF_OUTPUT_PHYS_ADDR =1U <<26 , + PERF_OUTPUT_UREGS = 1U << 27, }; struct output_option {
@@ -109,6 +110,7 @@ struct output_option { {.str = "srcline", .field = PERF_OUTPUT_SRCLINE}, {.str = "period", .field = PERF_OUTPUT_PERIOD}, {.str = "iregs", .field = PERF_OUTPUT_IREGS}, + {.str = "uregs", .field = PERF_OUTPUT_UREGS}, {.str = "brstack", .field = PERF_OUTPUT_BRSTACK}, {.str = "brstacksym", .field = PERF_OUTPUT_BRSTACKSYM}, {.str = "data_src", .field = PERF_OUTPUT_DATA_SRC},
@@ -385,6 +387,11 @@ static int perf_evsel__check_attr(struct perf_evsel *evsel, PERF_OUTPUT_IREGS))return -EINVAL ; +if (PRINT_FIELD (UREGS ) && +perf_evsel__check_stype (evsel,PERF_SAMPLE_REGS_USER ,"UREGS" , +PERF_OUTPUT_UREGS )) +return -EINVAL ; +if (PRINT_FIELD (PHYS_ADDR ) &&perf_evsel__check_stype (evsel,PERF_SAMPLE_PHYS_ADDR ,"PHYS_ADDR" ,PERF_OUTPUT_PHYS_ADDR ))
@@ -509,6 +516,24 @@ static void print_sample_iregs(struct perf_sample *sample, } } +static void print_sample_uregs (struct perf_sample *sample, +struct perf_event_attr *attr) +{ +struct regs_dump *regs = &sample->user_regs; +uint64_t mask = attr->sample_regs_user; +unsigned i =0 , r; + +if (!regs || !regs->regs) +return ; + +printf (" ABI:%" PRIu64" " , regs->abi); + +for_each_set_bit (r, (unsigned long *) &mask,sizeof (mask) *8 ) { +u64 val = regs->regs[i++]; +printf ("%5s:0x%" PRIx64" " ,perf_reg_name (r), val); + } +} +static void print_sample_start (struct perf_sample *sample,struct thread *thread,struct perf_evsel *evsel)
@@ -1444,6 +1469,9 @@ static void process_event(struct perf_script *script,if (PRINT_FIELD (IREGS ))print_sample_iregs (sample, attr); +if (PRINT_FIELD (UREGS )) +print_sample_uregs (sample, attr); +if (PRINT_FIELD (BRSTACK ))print_sample_brstack (sample, thread, attr);else if (PRINT_FIELD (BRSTACKSYM ))
@@ -2739,7 +2767,7 @@ int cmd_script(int argc, const char **argv) "+field to add and -field to remove." "Valid types: hw,sw,trace,raw,synth. " "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso," - "addr,symoff,period,iregs,brstack,brstacksym,flags," + "addr,symoff,period,iregs,uregs,brstack,brstacksym,flags," "bpf-output,callindent,insn,insnlen,brstackinsn,synth,phys_addr", parse_output_fields), OPT_BOOLEAN('a', "all-cpus", &system_wide,
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 16/41 perf tests: Fix compile when libunwind's unwind.h is available
In reply to Arnaldo Carvalho de MeloFrom: Milian Wolff <[email protected]>
When cross compiling perf and I want to link against a self-compiled libunwind, I usually make the custom path where the libunwind headers exist visible by adding the libunwind prefix to the include path when compiling perf, i.e.:
~~~~~
$ ls $HOME/projects/compiled/other/include/ libunwind-coredump.h libunwind.h libunwind-x86_64.h libunwind-common.h libunwind-dynamic.h libunwind-ptrace.h unwind.h $ make EXTRA_CFLAGS="-I$HOME/projects/compiled/other/include/ ~~~~~~
Note the unwind.h header from libunwind which leads to compile errors when compiling tests/dwarf-unwind.c, since it shadows perf's util/unwind.h:
~~~~~tests/dwarf-unwind.c:41:32: error: ‘struct unwind_entry’ declared inside parameter list will not be visible outside of this definition or declaration [-Werror]
static int unwind_entry(struct unwind_entry *entry, void *arg)
^~~~~~~~~~~~
tests/dwarf-unwind.c: In function ‘unwind_entry’:
tests/dwarf-unwind.c:44:22: error: dereferencing pointer to incomplete type ‘struct unwind_entry’
char *symbol = entry->sym ? entry->sym->name : NULL;
^~
tests/dwarf-unwind.c: In function ‘unwind_thread’:
tests/dwarf-unwind.c:92:8: error: implicit declaration of function ‘unwind__get_entries’; did you mean ‘unwind_entry’? [-Werror=implicit-function-declaration]
err = unwind__get_entries(unwind_entry, &cnt, thread,
^~~~~~~~~~~~~~~~~~~
unwind_entrytests/dwarf-unwind.c:92:8: error: nested extern declaration of ‘unwind__get_entries’ [-Werror=nested-externs]
~~~~~~
Fix this compile error by specificing an explicit include of perf's unwind.h in the util folder.
Signed-off-by Milian Wolff <[email protected]>
Cc David Ahern <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Yao Jin <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/tests/dwarf-unwind.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/tests/dwarf-unwind.c +1 -1
@@ -6,7 +6,7 @@#include "debug.h" #include "machine.h" #include "event.h" -#include "unwind.h" +#include "../util/unwind.h" #include "perf_regs.h" #include "map.h" #include "thread.h"
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 17/41 tools lib api: Fix make DEBUG=1 build
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Do not use -D_FORTIFY_SOURCE=2 for DEBUG build as it seems to mess up with debuginfo, which results in bad gdb experience.
We already do that for tools/perf/.
Signed-off-by Jiri Olsa <[email protected]>
Cc David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/lib/api/Makefile | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-)
tools/lib/api/Makefile +7 -1
@@ -17,13 +17,19 @@ MAKEFLAGS += --no-print-directory LIBFILE = $(OUTPUT)libapi.a CFLAGS := $(EXTRA_WARNINGS) $(EXTRA_CFLAGS) -CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -D_FORTIFY_SOURCE=2 -fPIC +CFLAGS += -ggdb3 -Wall -Wextra -std=gnu99 -U_FORTIFY_SOURCE -fPIC +ifeq ($(DEBUG),0) ifeq ($(CC_NO_CLANG), 0) CFLAGS += -O3 else CFLAGS += -O6 endif +endif + +ifeq ($(DEBUG),0) + CFLAGS += -D_FORTIFY_SOURCE +endif # Treat warnings as errors unless directed not to ifneq ($(WERROR),0)
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 18/41 perf tools: Open perf.data with O_CLOEXEC flag
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Do not carry the perf.data file descriptor into the workload process and close it when perf executes the workload.
Signed-off-by Jiri Olsa <[email protected]>
Cc David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
[ Add definitions for O_CLOEXEC for older systems ]
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/data.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-)
tools/perf/util/data.c +12 -1
@@ -10,6 +10,16 @@#include "util.h" #include "debug.h" +#ifndef O_CLOEXEC +#ifdef __sparc__ +#define O_CLOEXEC 0x400000 +#elif defined(__alpha__) || defined(__hppa__) +#define O_CLOEXEC 010000000 +#else +#define O_CLOEXEC 02000000 +#endif +#endif +static bool check_pipe (struct perf_data_file *file) {struct stat st;
@@ -96,7 +106,8 @@ static int open_file_write(struct perf_data_file *file)if (check_backup (file))return -1 ; - fd =open (file->path,O_CREAT |O_RDWR |O_TRUNC ,S_IRUSR |S_IWUSR ); + fd =open (file->path,O_CREAT |O_RDWR |O_TRUNC |O_CLOEXEC , +S_IRUSR |S_IWUSR );if (fd <0 ) pr_err("failed to open %s : %s\n", file->path,
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 19/41 perf tools: Add python-clean target
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
To be able to cleanup only python related binaries.
Signed-off-by Jiri Olsa <[email protected]>
Cc David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/Makefile.perf | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-)
tools/perf/Makefile.perf +5 -3
@@ -173,7 +173,7 @@ AWK = awk # non-config cases config := 1 -NON_CONFIG_TARGETS := clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf +NON_CONFIG_TARGETS := clean python-clean TAGS tags cscope help install-doc install-man install-html install-info install-pdf doc man html info pdf ifdef MAKECMDGOALS ifeq ($(filter-out $(NON_CONFIG_TARGETS),$(MAKECMDGOALS)),)
@@ -802,7 +802,10 @@ config-clean: $(call QUIET_CLEAN, config) $(Q)$(MAKE) -C $(srctree)/tools/build/feature/ $(if $(OUTPUT),OUTPUT=$(OUTPUT)feature/,) clean >/dev/null -clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean +python-clean: + $(python-clean) + +clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clean config-clean fixdep-clean python-clean $(call QUIET_CLEAN, core-objs) $(RM) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(LANG_BINDINGS) $(Q)find $(if $(OUTPUT),$(OUTPUT),.) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete $(Q)$(RM) $(OUTPUT).config-detected
@@ -819,7 +822,6 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea $(OUTPUT)$(vhost_virtio_ioctl_array) \ $(OUTPUT)$(perf_ioctl_array) $(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean - $(python-clean) # # To provide FEATURE-DUMP into $(FEATURE_DUMP_COPY)
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 20/41 perf ui progress: Make sure we always define step value
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Unlikely, but we could have ui_progress__init being called with total < 16, which would set the next and step variables to 0. That would force unnecessary ui_progress__ops->update calls because 'next' would never raise.
Forcing the next and step values to be always > 0.
Signed-off-by Jiri Olsa <[email protected]>
Cc David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/ui/progress.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/ui/progress.c +1 -1
@@ -25,7 +25,7 @@ void ui_progress__update(struct ui_progress *p, u64 adv)void ui_progress__init (struct ui_progress *p,u64 total,const char *title) { p->curr =0 ; - p->next = p->step = total /16 ; + p->next = p->step = total /16 ?:1 ; p->total = total; p->title = title;
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 21/41 perf ui progress: Fix progress update
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
We currently update the 'next' variable only with a single step value. But it's possible the 'adv' update is bigger than single 'step' value. This would leave 'next' value under counted and force unnecessary ui_progress__ops->update calls.
Calculate the amount of steps we need for 'adv' update and increase the 'next' with that amounts of steps.
Signed-off-by Jiri Olsa <[email protected]>
Cc David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/ui/progress.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-)
tools/perf/ui/progress.c +6 -1
@@ -1,3 +1,4 @@ +#include <linux/kernel.h> #include "../cache.h" #include "progress.h"
@@ -14,10 +15,14 @@ struct ui_progress_ops *ui_progress__ops = &null_progress__ops;void ui_progress__update (struct ui_progress *p,u64 adv) { +u64 last = p->curr; + p->curr += adv;if (p->curr >= p->next) { - p->next += p->step; +u64 nr =DIV_ROUND_UP (p->curr - last, p->step); + + p->next += nr * p->step; ui_progress__ops->update (p); } }
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 22/41 perf ui progress: Add ui specific init function
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Adding ui specific init function allowing to setup the progress bar width based on current screen scales.
Adding TUI init function to get more grained update of the progress bar.
Signed-off-by Jiri Olsa <[email protected]>
Cc David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/ui/progress.c | 2 ++ tools/perf/ui/progress.h | 1 + tools/perf/ui/tui/progress.c | 9 +++++++-- 3 files changed, 10 insertions(+), 2 deletions(-)
tools/perf/ui/progress.c +2 -0
@@ -34,6 +34,8 @@ void ui_progress__init(struct ui_progress *p, u64 total, const char *title) p->total = total; p->title = title; +if (ui_progress__ops->init) + ui_progress__ops->init (p); }void ui_progress__finish (void )
tools/perf/ui/progress.h +1 -0
@@ -14,6 +14,7 @@ void ui_progress__init(struct ui_progress *p, u64 total, const char *title);void ui_progress__update (struct ui_progress *p,u64 adv);struct ui_progress_ops { +void (*init)(struct ui_progress *p);void (*update)(struct ui_progress *p);void (*finish)(void ); };
tools/perf/ui/tui/progress.c +7 -2
@@ -5,6 +5,11 @@#include "tui.h" #include "../browser.h" +static void __tui_progress__init (struct ui_progress *p) +{ + p->next = p->step = p->total / (SLtt_Screen_Cols -2 ) ?:1 ; +} +static void tui_progress__update (struct ui_progress *p) {int bar, y;
@@ -49,8 +54,8 @@ static void tui_progress__finish(void)pthread_mutex_unlock (&ui__lock); } -static struct ui_progress_ops tui_progress__ops = -{ +static struct ui_progress_ops tui_progress__ops = { + .init = __tui_progress__init, .update = tui_progress__update, .finish = tui_progress__finish, };
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 23/41 perf ui progress: Add size info into progress bar
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Adding the size values '[current/total]' into progress bar, to show more detailed progress of data reading.
Adding new ui_progress__init_size function to specify we want to display the size.
Signed-off-by Jiri Olsa <[email protected]>
Cc David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/ui/progress.c | 4 +++- tools/perf/ui/progress.h | 11 ++++++++++- tools/perf/ui/tui/progress.c | 23 ++++++++++++++++++++++- tools/perf/util/session.c | 2 +- 4 files changed, 36 insertions(+), 4 deletions(-)
tools/perf/ui/progress.c +3 -1
@@ -27,12 +27,14 @@ void ui_progress__update(struct ui_progress *p, u64 adv) } } -void ui_progress__init (struct ui_progress *p,u64 total,const char *title) +void __ui_progress__init (struct ui_progress *p,u64 total, +const char *title,bool size) { p->curr =0 ; p->next = p->step = total /16 ?:1 ; p->total = total; p->title = title; + p->size = size;if (ui_progress__ops->init) ui_progress__ops->init (p);
tools/perf/ui/progress.h +10 -1
@@ -8,9 +8,18 @@ void ui_progress__finish(void);struct ui_progress {const char *title;u64 curr, next, step, total; +bool size; }; -void ui_progress__init (struct ui_progress *p,u64 total,const char *title); +void __ui_progress__init (struct ui_progress *p,u64 total, +const char *title,bool size); + +#define ui_progress__init (p, total, title) \ + __ui_progress__init(p, total, title, false) + +#define ui_progress__init_size (p, total, title) \ + __ui_progress__init(p, total, title, true) +void ui_progress__update (struct ui_progress *p,u64 adv);struct ui_progress_ops {
tools/perf/ui/tui/progress.c +22 -1
@@ -1,8 +1,10 @@ +#include <linux/kernel.h> #include "../cache.h" #include "../progress.h" #include "../libslang.h" #include "../ui.h" #include "tui.h" +#include "units.h" #include "../browser.h" static void __tui_progress__init (struct ui_progress *p)
@@ -10,8 +12,22 @@ static void __tui_progress__init(struct ui_progress *p) p->next = p->step = p->total / (SLtt_Screen_Cols -2 ) ?:1 ; } +static int get_title (struct ui_progress *p,char *buf,size_t size) +{ +char buf_cur[20 ]; +char buf_tot[20 ]; +int ret; + + ret =unit_number__scnprintf (buf_cur,sizeof (buf_cur), p->curr); + ret +=unit_number__scnprintf (buf_tot,sizeof (buf_tot), p->total); + +return ret +scnprintf (buf, size,"%s [%s/%s]" , + p->title, buf_cur, buf_tot); +} +static void tui_progress__update (struct ui_progress *p) { +char buf[100 ], *title = (char *) p->title;int bar, y;/* * FIXME: We should have a per UI backend way of showing progress,
@@ -23,13 +39,18 @@ static void tui_progress__update(struct ui_progress *p)if (p->total ==0 )return ; +if (p->size) { +get_title (p, buf,sizeof (buf)); + title = buf; + } +ui__refresh_dimensions (false);pthread_mutex_lock (&ui__lock); y = SLtt_Screen_Rows /2 -2 ;SLsmg_set_color (0 );SLsmg_draw_box (y,0 ,3 , SLtt_Screen_Cols);SLsmg_gotorc (y++,1 ); -SLsmg_write_string ((char *)p->title); +SLsmg_write_string (title);SLsmg_fill_region (y,1 ,1 , SLtt_Screen_Cols -2 ,' ' );SLsmg_set_color (HE_COLORSET_SELECTED ); bar = ((SLtt_Screen_Cols -2 ) * p->curr) / p->total;
tools/perf/util/session.c +1 -1
@@ -1847,7 +1847,7 @@ static int __perf_session__process_events(struct perf_session *session,if (data_offset + data_size < file_size) file_size = data_offset + data_size; -ui_progress__init (&prog, file_size,"Processing events..." ); +ui_progress__init_size (&prog, file_size,"Processing events..." ); mmap_size =MMAP_SIZE ;if (mmap_size > file_size) {
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 24/41 perf tools: Use scandir() to replace readdir()
In reply to Arnaldo Carvalho de MeloFrom: Kan Liang <[email protected]>
In perf_event__synthesize_threads() perf goes through all proc files serially by readdir.
scandir() does a snapshoot of /proc, which is multithreading friendly.
It's possible that some threads which are added during event synthesize. But the number of lost threads should be small. They should not impact the final analysis.
Signed-off-by Kan Liang <[email protected]>
Cc Adrian Hunter <[email protected]>
Cc Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Lukasz Odzioba <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/event.c | 45 +++++++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 20 deletions(-)
tools/perf/util/event.c +25 -20
@@ -683,12 +683,14 @@ int perf_event__synthesize_threads(struct perf_tool *tool,bool mmap_data, unsigned int proc_map_timeout) { - DIR *proc; -char proc_path[PATH_MAX ]; -struct dirent *dirent; union perf_event *comm_event, *mmap_event, *fork_event;union perf_event *namespaces_event; +char proc_path[PATH_MAX ]; +struct dirent **dirent;int err =-1 ; +char *end; +pid_t pid; +int n, i;if (machine__is_default_guest (machine))return 0 ;
@@ -712,29 +714,32 @@ int perf_event__synthesize_threads(struct perf_tool *tool, goto out_free_fork;snprintf (proc_path,sizeof (proc_path),"%s/proc" , machine->root_dir); - proc =opendir (proc_path); + n =scandir (proc_path, &dirent,0 , alphasort); -if (proc ==NULL ) +if (n <0 ) goto out_free_namespaces; -while ((dirent =readdir (proc)) !=NULL ) { -char *end; -pid_t pid =strtol (dirent->d_name, &end,10 ); - -if (*end)/* only interested in proper numerical dirents */ +for (i =0 ; i < n; i++) { +if (!isdigit (dirent[i]->d_name[0 ]))continue ; -/* -* We may race with exiting thread, so don't stop just because -* one thread couldn't be synthesized. -*/ -__event__synthesize_thread (comm_event, mmap_event, fork_event, - namespaces_event, pid,1 , process, - tool, machine, mmap_data, - proc_map_timeout); - } + pid = (pid_t )strtol (dirent[i]->d_name, &end,10 ); +/* only interested in proper numerical dirents */ +if (!*end) { +/* +* We may race with exiting thread, so don't stop just because +* one thread couldn't be synthesized. +*/ +__event__synthesize_thread (comm_event, mmap_event, fork_event, + namespaces_event, pid,1 , process, + tool, machine, mmap_data, + proc_map_timeout); + } +free (dirent[i]); + } +free (dirent); err =0 ; -closedir (proc); + out_free_namespaces:free (namespaces_event); out_free_fork:
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 25/41 perf config: Check not only section->from_system_config but also item's
In reply to Arnaldo Carvalho de MeloFrom: Taeung Song <[email protected]>
Currently section->from_system_config is being checked multiple times. item->from_system_config should be checked instead, when iterating thru the items in a section. Fix it.
Signed-off-by Taeung Song <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Namhyung Kim <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/builtin-config.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-config.c +1 -1
@@ -59,7 +59,7 @@ static int set_config(struct perf_config_set *set, const char *file_name,fprintf (fp,"[%s]\n" , section->name);perf_config_items__for_each_entry (§ion->items, item) { -if (!use_system_config && section->from_system_config) +if (!use_system_config && item->from_system_config)continue ;if (item->value) fprintf(fp, "\t%s = %s\n",
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 26/41 perf config: Write a config file just once
In reply to Arnaldo Carvalho de MeloFrom: Taeung Song <[email protected]>
Currently set_config() can be repeatedly called for each input config on the below case:
$ perf config kmem.default=slab report.children=false ...
But it's a waste, so only once write a config file gathering all given config key=value pairs.
Signed-off-by Taeung Song <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Namhyung Kim <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/builtin-config.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-)
tools/perf/builtin-config.c +16 -6
@@ -34,8 +34,7 @@ static struct option config_options[] = { OPT_END() }; -static int set_config (struct perf_config_set *set,const char *file_name, -const char *var,const char *value) +static int set_config (struct perf_config_set *set,const char *file_name) {struct perf_config_section *section =NULL ;struct perf_config_item *item =NULL ;
@@ -49,7 +48,6 @@ static int set_config(struct perf_config_set *set, const char *file_name,if (!fp)return -1 ; -perf_config_set__collect (set, file_name, var, value);fprintf (fp,"%s\n" , first_line);/* overwrite configvariables */
@@ -161,6 +159,7 @@ int cmd_config(int argc, const char **argv)struct perf_config_set *set;char *user_config =mkpath ("%s/.perfconfig" ,getenv ("HOME" ));const char *config_filename; +bool changed = false; argc =parse_options (argc, argv, config_options, config_usage,PARSE_OPT_STOP_AT_NON_OPTION );
@@ -231,15 +230,26 @@ int cmd_config(int argc, const char **argv) goto out_err; } }else { -if (set_config (set, config_filename, var, value) <0 ) { -pr_err ("Failed to set '%s=%s' on %s\n" , - var, value, config_filename); +if (perf_config_set__collect (set, config_filename, + var, value) <0 ) { +pr_err ("Failed to add '%s=%s'\n" , + var, value);free (arg); goto out_err; } + changed = true; }free (arg); } + +if (!changed) +break ; + +if (set_config (set, config_filename) <0 ) { +pr_err ("Failed to set the configs on %s\n" , + config_filename); + goto out_err; + } } ret =0 ;
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 27/41 perf config: Allow creating empty config set for config file autogeneration
In reply to Arnaldo Carvalho de MeloFrom: Taeung Song <[email protected]>
When there isn't a config file (e.g. ~/.perfconfig) or it has nothing, the config set wasn't created.
If the config set does not exist, a config file can't be autogenerated.
So allow creating a empty config set in the above case, then we can support the config file autogeneration.
Before:
$ rm -f ~/.perfconfig $ perf config --user report.children=false
$ cat ~/.perfconfig cat: /root/.perfconfig: No such file or directory
But I think it should work even if there isn't a config file.
After:
$ rm -f ~/.perfconfig $ perf config --user report.children=false
$ cat ~/.perfconfig
# this file is auto-generated.
[report]
children = falseNOTE:
As a result, if perf_config_set__init() fails, it looks as if the config set isn't freed. But it isn't a problem. Because the config set will be freed by perf_config_set__delete() at the end of cmd_config().
Signed-off-by Taeung Song <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Namhyung Kim <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/util/config.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-)
tools/perf/util/config.c +1 -4
@@ -700,10 +700,7 @@ struct perf_config_set *perf_config_set__new(void)if (set) {INIT_LIST_HEAD (&set->sections); -if (perf_config_set__init (set) <0 ) { -perf_config_set__delete (set); - set =NULL ; - } +perf_config_set__init (set); }return set;
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 28/41 perf tools: Make copyfile_offset() static
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
There are no usage outside util.c and this is the only remaining reason for fcntl.h to be included in util.h, to get the loff_t definition in Alpine Linux, so make it static.
Cc Adrian Hunter <[email protected]>
Cc David Ahern <[email protected]>
Cc Jiri Olsa <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Wang Nan <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/tests/builtin-test.c | 1 + tools/perf/util/data.c | 1 + tools/perf/util/dso.c | 1 + tools/perf/util/event.c | 1 + tools/perf/util/evlist.h | 1 + tools/perf/util/namespaces.c | 1 + tools/perf/util/pmu.c | 1 + tools/perf/util/probe-file.c | 1 + tools/perf/util/util.c | 3 ++- tools/perf/util/util.h | 2 -- tools/perf/util/zlib.c | 1 + 11 files changed, 11 insertions(+), 3 deletions(-)
tools/perf/tests/builtin-test.c +1 -0
@@ -3,6 +3,7 @@* * Builtin regression testing command: ever growing number of sanity tests */ +#include <fcntl.h> #include <errno.h> #include <unistd.h> #include <string.h>
tools/perf/util/data.c +1 -0
@@ -3,6 +3,7 @@#include <sys/types.h> #include <sys/stat.h> #include <errno.h> +#include <fcntl.h> #include <unistd.h> #include <string.h>
tools/perf/util/dso.c +1 -0
@@ -6,6 +6,7 @@#include <sys/stat.h> #include <unistd.h> #include <errno.h> +#include <fcntl.h> #include "compress.h" #include "path.h" #include "symbol.h"
tools/perf/util/event.c +1 -0
@@ -1,5 +1,6 @@#include <dirent.h> #include <errno.h> +#include <fcntl.h> #include <inttypes.h> #include <linux/kernel.h> #include <linux/types.h>
tools/perf/util/evlist.h +1 -0
@@ -6,6 +6,7 @@#include <linux/refcount.h> #include <linux/list.h> #include <api/fd/array.h> +#include <fcntl.h> #include <stdio.h> #include "../perf.h" #include "event.h"
tools/perf/util/namespaces.c +1 -0
@@ -11,6 +11,7 @@#include "event.h" #include <sys/types.h> #include <sys/stat.h> +#include <fcntl.h> #include <limits.h> #include <sched.h> #include <stdlib.h>
tools/perf/util/pmu.c +1 -0
@@ -2,6 +2,7 @@#include <linux/compiler.h> #include <sys/types.h> #include <errno.h> +#include <fcntl.h> #include <sys/stat.h> #include <unistd.h> #include <stdio.h>
tools/perf/util/probe-file.c +1 -0
@@ -15,6 +15,7 @@* */ #include <errno.h> +#include <fcntl.h> #include <sys/stat.h> #include <sys/types.h> #include <sys/uio.h>
tools/perf/util/util.c +2 -1
@@ -6,6 +6,7 @@#include <sys/stat.h> #include <sys/utsname.h> #include <dirent.h> +#include <fcntl.h> #include <inttypes.h> #include <signal.h> #include <stdio.h>
@@ -174,7 +175,7 @@ static int slow_copyfile(const char *from, const char *to, struct nsinfo *nsi)return err; } -int copyfile_offset (int ifd,loff_t off_in,int ofd,loff_t off_out,u64 size) +static int copyfile_offset (int ifd,loff_t off_in,int ofd,loff_t off_out,u64 size) {void *ptr;loff_t pgoff;
tools/perf/util/util.h +0 -2
@@ -5,7 +5,6 @@/* glibc 2.20 deprecates _BSD_SOURCE in favour of _DEFAULT_SOURCE */ #define _DEFAULT_SOURCE 1 -#include <fcntl.h> #include <stdbool.h> #include <stddef.h> #include <stdlib.h>
@@ -35,7 +34,6 @@ bool lsdir_no_dot_filter(const char *name, struct dirent *d);int copyfile (const char *from,const char *to);int copyfile_mode (const char *from,const char *to,mode_t mode);int copyfile_ns (const char *from,const char *to,struct nsinfo *nsi); -int copyfile_offset (int fromfd,loff_t from_ofs,int tofd,loff_t to_ofs,u64 size);ssize_t readn (int fd,void *buf,size_t n);ssize_t writen (int fd,const void *buf,size_t n);
tools/perf/util/zlib.c +1 -0
@@ -1,3 +1,4 @@ +#include <fcntl.h> #include <stdio.h> #include <unistd.h> #include <sys/stat.h>
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 29/41 perf tools: Support running perf binaries with a dash in their name
In reply to Arnaldo Carvalho de MeloFrom: Milian Wolff <[email protected]>
Previously the part behind "perf-" was interpreted as an internal perf command. If the suffix could not be handled, the execution was stopped. This makes it impossible to launch perf binaries that got renamed to have the perf- prefix. This is e.g. the case for appimages (e.g. "perf-x86_64.AppImage"), but would also apply to all other scenarios where users symlink or rename perf themselves:
Status quo with the broken behavior:
$ ln -s ./perf ./perf-custom-suffix $ ./perf-custom-suffix list cannot handle custom-suffix internally$
Also note the missing newline at the end of the error message.
With this patch applied, the above works properly:
$ ./perf-custom-suffix list
List of pre-defined events (to be used in -e):
...
Signed-off-by Milian Wolff <[email protected]>
Acked-by David Ahern <[email protected]>
Cc Namhyung Kim <[email protected]>
Cc Peter Zijlstra <[email protected]>
Cc Yao Jin <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/perf.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-)
tools/perf/perf.c +10 -4
@@ -467,15 +467,21 @@ int main(int argc, const char **argv)* - cannot execute it externally (since it would just do * the same thing over again) * -* So we just directly call the internal command handler, and -* die if that one cannot handle it. +* So we just directly call the internal command handler. If that one +* fails to handle this, then maybe we just run a renamed perf binary +* that contains a dash in its name. To handle this scenario, we just +* fall through and ignore the "xxxx" part of the command string. */ if (strstarts (cmd,"perf-" )) { cmd +=5 ; argv[0 ] = cmd;handle_internal_command (argc, argv); -fprintf (stderr,"cannot handle %s internally" , cmd); - goto out; +/* +* If the command is handled, the above function does not +* return undo changes and fall through in such a case. +*/ + cmd -=5 ; + argv[0 ] = cmd; }if (strstarts (cmd,"trace" )) {#ifdef HAVE_LIBAUDIT_SUPPORT
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 30/41 perf stat: Fall weak group back even for EBADF
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
It's not possible to run a package event and a per cpu event in the same group. This is used by some of the power metrics. They work correctly when not using a group.
Normally weak groups should handle that, but in this case EBADF is returned instead of the normal EINVAL.
$ strace -e perf_event_open ./perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
Using CPUID GenuineIntel-6-3E
perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, PERF_FLAG_FD_CLOEXEC) = -1 EINVAL (Invalid argument)
perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument)
perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument)
perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = -1 EINVAL (Invalid argument)
perf_event_open({type=0x17 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, -1, 0) = 3
perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 0, 3, 0) = 4
perf_event_open({type=0x7 /* PERF_TYPE_??? */, size=PERF_ATTR_SIZE_VER5, config=0, ...}, -1, 1, 0, 0) = -1 EBADF (Bad file descriptor)and perf errors out.
Make weak groups trigger a fall back for EBADF too. Then this case works correctly:
$ perf stat -v -e '{cstate_pkg/c2-residency/,msr/tsc/}:W' -a sleep 1
Using CPUID GenuineIntel-6-3E
Weak group for cstate_pkg/c2-residency//2 failed
cstate_pkg/c2-residency/: 476709882 1000598460 1000598460
msr/tsc/: 39625837911 12007369110 12007369110Performance counter stats for 'system wide':
476,709,882 cstate_pkg/c2-residency/
39,625,837,911 msr/tsc/
1.000697588 seconds time elapsedThis fixes perf stat -M Power ...
$ perf stat -M Power --metric-only -a sleep 1
Performance counter stats for 'system wide':
Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.0 0.7 30.0 0.0 0.9 0.1 0.4 0.0
1.001240740 seconds time elapsed
Signed-off-by Andi Kleen <[email protected]>
Acked-by Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- tools/perf/builtin-stat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-stat.c +1 -1
@@ -656,7 +656,7 @@ static int __run_perf_stat(int argc, const char **argv)if (create_perf_stat_counter (counter) <0 ) {/* Weak group failed. Reset the group. */ -if (errno ==EINVAL && +if ((errno ==EINVAL || errno ==EBADF ) && counter->leader != counter && counter->weak_group) { counter =perf_evsel__reset_weak_group (counter);
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 31/41 perf vendor events: Add JSON metrics for Broadwell
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Broadwell.
Commiter testing:
# uname -a Linux jouet 4.13.0-rc7+ #3 SMP Sat Sep 2 09:04:44 -03 2017 x86_64 x86_64 x86_64 GNU/Linux # grep "model name" /proc/cpuinfo | head -1 model name : Intel(R) Core(TM) i7-5600U CPU @ 2.60GHz # perf list metricgroup
List of pre-defined events (to be used in -e):
Metric Groups:
DSB
FLOPS
Frontend
Frontend_Bandwidth
Memory_BW
Memory_Bound
Memory_Lat
Pipeline
Ports_Utilization
Power
SMT
Summary
TLB
TopDownL1
Unknown_Branches
# perf stat -M Power --metric-only -a sleep 1
Performance counter stats for 'system wide':
Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
1.1 0.0 0.0 0.0 0.0 0.0 0.0 0.0
1.003502904 seconds time elapsed
#
# perf stat -M Memory_BW --metric-only -a sleep 1
Performance counter stats for 'system wide':
MLP
1.7
1.001364525 seconds time elapsed#
# perf stat -M TLB --metric-only -a sleep 1
Performance counter stats for 'system wide':
Page_Walks_Utilization
0.1
1.005962198 seconds time elapsed#
# perf stat -M Summary --metric-only -a sleep 1
Performance counter stats for 'system wide':
Instructions CPI CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization 7281856697.0 0.0 11150898087.0 1.0 0.0 1.0 0.7
1.012134025 seconds time elapsed
#
Running in verbose mode shows which counters and expressions are being used:
# perf stat -v -M Summary --metric-only -a sleep 1
Using CPUID GenuineIntel-6-3D
metric expr 1 / inst_retired.any / cycles for CPI
found event inst_retired.any
found event cycles
metric expr cpu_clk_unhalted.thread for CLKS
found event cpu_clk_unhalted.thread
metric expr inst_retired.any for Instructions
found event inst_retired.any
metric expr cpu_clk_unhalted.ref_tsc / msr@tsc@ for CPU_Utilization
found event cpu_clk_unhalted.ref_tsc
found event msr/tsc/
metric expr ( 1*( fp_arith_inst_retired.scalar_single + fp_arith_inst_retired.scalar_double ) + 2* fp_arith_inst_retired.128b_packed_double + 4*( fp_arith_inst_retired.128b_packed_single + fp_arith_inst_retired.256b_packed_double ) + 8* fp_arith_inst_retired.256b_packed_single ) / 1000000000 / duration_time for GFLOPs
found event fp_arith_inst_retired.scalar_single
found event fp_arith_inst_retired.scalar_double
found event fp_arith_inst_retired.128b_packed_double
found event fp_arith_inst_retired.128b_packed_single
found event fp_arith_inst_retired.256b_packed_double
found event fp_arith_inst_retired.256b_packed_single
found event duration_time
metric expr 1 - cpu_clk_thread_unhalted.one_thread_active / ( cpu_clk_thread_unhalted.ref_xclk_any / 2 ) if #smt_on else 0 for SMT_2T_Utilization
found event cpu_clk_thread_unhalted.one_thread_active
found event cpu_clk_thread_unhalted.ref_xclk_any
metric expr cpu_clk_unhalted.ref_tsc:u / cpu_clk_unhalted.ref_tsc for Kernel_Utilization
found event cpu_clk_unhalted.ref_tsc:u
found event cpu_clk_unhalted.ref_tsc
adding {inst_retired.any,cycles}:W,{cpu_clk_unhalted.thread}:W,{inst_retired.any}:W,{cpu_clk_unhalted.ref_tsc,msr/tsc/}:W,{fp_arith_inst_retired.scalar_single,fp_arith_inst_retired.scalar_double,fp_arith_inst_retired.128b_packed_double,fp_arith_inst_retired.128b_packed_single,fp_arith_inst_retired.256b_packed_double,fp_arith_inst_retired.256b_packed_single,duration_time}:W,{cpu_clk_thread_unhalted.one_thread_active,cpu_clk_thread_unhalted.ref_xclk_any}:W,{cpu_clk_unhalted.ref_tsc:u,cpu_clk_unhalted.ref_tsc}:W
inst_retired.any -> cpu/event=0xc0/
cpu_clk_unhalted.thread -> cpu/event=0x3c/
inst_retired.any -> cpu/event=0xc0/
cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/
fp_arith_inst_retired.scalar_single -> cpu/umask=0x2,period=2000003,event=0xc7/
fp_arith_inst_retired.scalar_double -> cpu/umask=0x1,period=2000003,event=0xc7/
fp_arith_inst_retired.128b_packed_double -> cpu/umask=0x4,period=2000003,event=0xc7/
fp_arith_inst_retired.128b_packed_single -> cpu/umask=0x8,period=2000003,event=0xc7/
fp_arith_inst_retired.256b_packed_double -> cpu/umask=0x10,period=2000003,event=0xc7/
fp_arith_inst_retired.256b_packed_single -> cpu/umask=0x20,period=2000003,event=0xc7/
cpu_clk_thread_unhalted.one_thread_active -> cpu/umask=0x2,period=2000003,event=0x3c/
cpu_clk_thread_unhalted.ref_xclk_any -> cpu/umask=0x1,any=1,period=2000003,event=0x3c/
cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/
cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/
Weak group for fp_arith_inst_retired.scalar_single/7 failed
Weak group for cpu_clk_unhalted.ref_tsc:u/2 failed
inst_retired.any: 8704146437 4026374016 619883741
cycles: 11180800018 4026374016 619883741
cpu_clk_unhalted.thread: 11140030295 4026323772 931621933
inst_retired.any: 8643115117 4026260510 1243595906
cpu_clk_unhalted.ref_tsc: 10201638510 4026184297 1247351077
msr/tsc/: 10378022785 4026184297 1247351077
fp_arith_inst_retired.scalar_single: 134697 4026102728 1559210545
fp_arith_inst_retired.scalar_double: 274339 4026007348 1870014984
fp_arith_inst_retired.128b_packed_double: 1639 4025886054 1866736918
fp_arith_inst_retired.128b_packed_single: 0 4025776614 2175106569
fp_arith_inst_retired.256b_packed_double: 0 4025681734 1235551129
fp_arith_inst_retired.256b_packed_single: 0 4025582962 1232398454
duration_time: 0 4025552913 4025552913
cpu_clk_thread_unhalted.one_thread_active: 10505 4025474649 923893076
cpu_clk_thread_unhalted.ref_xclk_any: 394992110 4025474649 923893076
cpu_clk_unhalted.ref_tsc:u: 5341421014 4025360315 1231634198
cpu_clk_unhalted.ref_tsc: 10258278508 4025252611 307909362Performance counter stats for 'system wide':
Instructions CPI CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization
8704146437.0 0.0 11140030295.0 1.0 0.0 1.0 0.5
1.006783654 seconds time elapsed
#
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/broadwell/bdw-metrics.json | 164 +++++++++++++++++++++ 1 file changed, 164 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json
tools/perf/pmu-events/arch/x86/broadwell/bdw-metrics.json new file +164 -0
@@ -0,0 +1,164 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 32/41 perf vendor events: Add JSON metrics for Skylake
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Skylake.
Committer testing:
# grep "model name" /proc/cpuinfo | head -1 model name : Intel(R) Core(TM) i5-7500 CPU @ 3.40GHz # uname -a Linux seventh 4.12.0-rc6+ #1 SMP Fri Jun 30 16:40:55 -03 2017 x86_64 x86_64 x86_64 GNU/Linux # perf stat --metric-only -M Summary -a sleep 1
Performance counter stats for 'system wide':
Instructions CPI CLKS CPU_Utilization GFLOPs SMT_2T_Utilization Kernel_Utilization
34021097.0 0.0 119424171.0 0.0 0.0 0.0 0.0
1.001001793 seconds time elapsed
# perf list metricgroup
List of pre-defined events (to be used in -e):
Metric Groups:
DSB
FLOPS
Frontend
Frontend_Bandwidth
Memory_BW
Memory_Bound
Memory_Lat
Pipeline
Ports_Utilization
Power
SMT
Summary
TLB
TopDownL1
Unknown_Branches
# perf stat --metric-only -M Ports_Utilization -a sleep 1
Performance counter stats for 'system wide':
ILP
1475828.0
1.000688547 seconds time elapsed
# perf stat -v --metric-only -M Ports_Utilization -a sleep 1
Using CPUID GenuineIntel-6-9E
metric expr uops_executed.thread / ( uops_executed.core_cycles_ge_1 / 2) if #smt_on else uops_executed.core_cycles_ge_1 for ILP
found event uops_executed.thread
found event uops_executed.core_cycles_ge_1
adding {uops_executed.thread,uops_executed.core_cycles_ge_1}:W
uops_executed.thread -> cpu/umask=0x1,period=2000003,event=0xb1/
uops_executed.core_cycles_ge_1 -> cpu/umask=0x2,period=2000003,cmask=1,event=0xb1/
uops_executed.thread: 8115271 4002547654 4002547654
uops_executed.core_cycles_ge_1: 3282969 4002547654 4002547654Performance counter stats for 'system wide':
ILP
3282969.0
1.000719870 seconds time elapsed
#
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/skylake/skl-metrics.json | 164 +++++++++++++++++++++ 1 file changed, 164 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json
tools/perf/pmu-events/arch/x86/skylake/skl-metrics.json new file +164 -0
@@ -0,0 +1,164 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE_16B.IFDATA_STALL - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS + MEM_LOAD_RETIRED.FB_HIT )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles )", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 33/41 perf vendor events: Add JSON metrics for Sandy Bridge
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Sandy Bridge.
Committer testing:
# grep "model name" /proc/cpuinfo | head -1
model name : Intel(R) Core(TM) i5-2400 CPU @ 3.10GHz
# perf list metricgroupList of pre-defined events (to be used in -e):
Metric Groups:
DSB
FLOPS
Frontend
Frontend_Bandwidth
Pipeline
Ports_Utilization
Power
SMT
Summary
TopDownL1
# perf stat -M Power --metric-only -a sleep 1
Performance counter stats for 'system wide':
Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
0.8 0.0 98.1 0.0 0.0 0.0 23.4 0.0
1.001153658 seconds time elapsed
# perf stat -v -M Power --metric-only -a sleep 1
Using CPUID GenuineIntel-6-2A
metric expr cpu_clk_unhalted.thread / cpu_clk_unhalted.ref_tsc for Turbo_Utilization
found event cpu_clk_unhalted.thread
found event cpu_clk_unhalted.ref_tsc
metric expr (cstate_core@c3\-residency@ / msr@tsc@) * 100 for C3_Core_Residency
found event cstate_core/c3-residency/
found event msr/tsc/
metric expr (cstate_core@c6\-residency@ / msr@tsc@) * 100 for C6_Core_Residency
found event cstate_core/c6-residency/
found event msr/tsc/
metric expr (cstate_core@c7\-residency@ / msr@tsc@) * 100 for C7_Core_Residency
found event cstate_core/c7-residency/
found event msr/tsc/
metric expr (cstate_pkg@c2\-residency@ / msr@tsc@) * 100 for C2_Pkg_Residency
found event cstate_pkg/c2-residency/
found event msr/tsc/
metric expr (cstate_pkg@c3\-residency@ / msr@tsc@) * 100 for C3_Pkg_Residency
found event cstate_pkg/c3-residency/
found event msr/tsc/
metric expr (cstate_pkg@c6\-residency@ / msr@tsc@) * 100 for C6_Pkg_Residency
found event cstate_pkg/c6-residency/
found event msr/tsc/
metric expr (cstate_pkg@c7\-residency@ / msr@tsc@) * 100 for C7_Pkg_Residency
found event cstate_pkg/c7-residency/
found event msr/tsc/
adding {cpu_clk_unhalted.thread,cpu_clk_unhalted.ref_tsc}:W,{cstate_core/c3-residency/,msr/tsc/}:W,{cstate_core/c6-residency/,msr/tsc/}:W,{cstate_core/c7-residency/,msr/tsc/}:W,{cstate_pkg/c2-residency/,msr/tsc/}:W,{cstate_pkg/c3-residency/,msr/tsc/}:W,{cstate_pkg/c6-residency/,msr/tsc/}:W,{cstate_pkg/c7-residency/,msr/tsc/}:W
cpu_clk_unhalted.thread -> cpu/event=0x3c/
cpu_clk_unhalted.ref_tsc -> cpu/umask=0x3,period=2000003,event=0/
Weak group for cstate_pkg/c2-residency//2 failed
Weak group for cstate_pkg/c3-residency//2 failed
Weak group for cstate_pkg/c6-residency//2 failed
Weak group for cstate_pkg/c7-residency//2 failed
cpu_clk_unhalted.thread: 5564185 4002833569 4002833569
cpu_clk_unhalted.ref_tsc: 7325424 4002833569 4002833569
cstate_core/c3-residency/: 68293 4003027101 4003027101
msr/tsc/: 12451294472 4003027101 4003027101
cstate_core/c6-residency/: 12238830163 4003260984 4003260984
msr/tsc/: 12452017806 4003260984 4003260984
cstate_core/c7-residency/: 0 4003489648 4003489648
msr/tsc/: 12452725162 4003489648 4003489648
cstate_pkg/c2-residency/: 1830054 1000913138 1000913138
msr/tsc/: 12453441079 4003717513 4003717513
cstate_pkg/c3-residency/: 0 1000973570 1000973570
msr/tsc/: 12454177865 4003954758 4003954758
cstate_pkg/c6-residency/: 2940448859 1001032370 1001032370
msr/tsc/: 12454833890 4004166118 4004166118
cstate_pkg/c7-residency/: 0 1001049818 1001049818
msr/tsc/: 12454919470 4004194204 4004194204Performance counter stats for 'system wide':
Turbo_Utilization C3_Core_Residency C6_Core_Residency C7_Core_Residency C2_Pkg_Residency C3_Pkg_Residency C6_Pkg_Residency C7_Pkg_Residency
0.8 0.0 98.3 0.0 0.0 0.0 23.6 0.0
1.001126519 seconds time elapsed
#
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../arch/x86/sandybridge/snb-metrics.json | 140 +++++++++++++++++++++ 1 file changed, 140 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json
tools/perf/pmu-events/arch/x86/sandybridge/snb-metrics.json new file +140 -0
@@ -0,0 +1,140 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_DISPATCHED.THREAD / ( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 34/41 perf vendor events: Add JSON metrics for Sandy Bridge EP
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Sandy Bridge EP.
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/jaketown/jkt-metrics.json | 140 +++++++++++++++++++++ 1 file changed, 140 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json
tools/perf/pmu-events/arch/x86/jaketown/jkt-metrics.json new file +140 -0
@@ -0,0 +1,140 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_DISPATCHED.THREAD / ( cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@ / 2) if #SMT_on else cpu@UOPS_DISPATCHED.CORE\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 35/41 perf vendor events: Add JSON metrics for Ivy Bridge
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Ivy Bridge.
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/ivybridge/ivb-metrics.json | 164 +++++++++++++++++++++ 1 file changed, 164 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json
tools/perf/pmu-events/arch/x86/ivybridge/ivb-metrics.json new file +164 -0
@@ -0,0 +1,164 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 36/41 perf vendor events: Add JSON metrics for Haswell
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Haswell.
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/haswell/hsw-metrics.json | 158 +++++++++++++++++++++ 1 file changed, 158 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json
tools/perf/pmu-events/arch/x86/haswell/hsw-metrics.json new file +158 -0
@@ -0,0 +1,158 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2)) if #SMT_on else (UOPS_EXECUTED.CORE / cpu@uops_executed.core\\,cmask\\=1@)", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - ( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION ) ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 37/41 perf vendor events: Add JSON metrics for Ivy Town
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Ivy Town.
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/ivytown/ivt-metrics.json | 164 +++++++++++++++++++++ 1 file changed, 164 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json
tools/perf/pmu-events/arch/x86/ivytown/ivt-metrics.json new file +164 -0
@@ -0,0 +1,164 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 32 * ( ICACHE.HIT + ICACHE.MISSES ) / 4) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFETCH_STALL ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_COMP_OPS_EXE.SSE_SCALAR_SINGLE + FP_COMP_OPS_EXE.SSE_SCALAR_DOUBLE ) + 2* FP_COMP_OPS_EXE.SSE_PACKED_DOUBLE + 4*( FP_COMP_OPS_EXE.SSE_PACKED_SINGLE + SIMD_FP_256.PACKED_DOUBLE ) + 8* SIMD_FP_256.PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 38/41 perf vendor events: Add JSON metrics for Haswell EP
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Haswell EP.
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/haswellx/hsx-metrics.json | 158 +++++++++++++++++++++ 1 file changed, 158 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json new file +158 -0
@@ -0,0 +1,158 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "( UOPS_EXECUTED.CORE / 2 / ( cpu@uops_executed.core\\,cmask\\=1@ / 2)) if #SMT_on else UOPS_EXECUTED.CORE / cpu@uops_executed.core\\,cmask\\=1@", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - ( 14 * ITLB_MISSES.STLB_HIT + ITLB_MISSES.WALK_DURATION ) ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION ) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 39/41 perf vendor events: Add JSON metrics for Broadwell Server
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Broadwell Server.
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../arch/x86/broadwellx/bdx-metrics.json | 164 +++++++++++++++++++++ 1 file changed, 164 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json new file +164 -0
@@ -0,0 +1,164 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_DURATION + DTLB_LOAD_MISSES.WALK_DURATION + DTLB_STORE_MISSES.WALK_DURATION + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED) ) / (2*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles)", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 40/41 perf vendor events: Add JSON metrics for Broadwell DE
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Broadwell DE
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../arch/x86/broadwellde/bdwde-metrics.json | 164 +++++++++++++++++++++ 1 file changed, 164 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json
tools/perf/pmu-events/arch/x86/broadwellde/bdwde-metrics.json new file +164 -0
@@ -0,0 +1,164 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , IDQ.MITE_UOPS / ( UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 16 * ( ICACHE.HIT + ICACHE.MISSES ) / 4.0 ) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded Icache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots", + "MetricExpr": "4*( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( cpu@uops_executed.core\\,cmask\\=1@ / 2) if #SMT_on else UOPS_EXECUTED.CYCLES_GE_1_UOP_EXEC", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "2* ( RS_EVENTS.EMPTY_CYCLES - ICACHE.IFDATA_STALL - ( 14 * ITLB_MISSES.STLB_HIT + cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + 7* ITLB_MISSES.WALK_COMPLETED ) ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_UOPS_RETIRED.L1_MISS + mem_load_uops_retired.hit_lfb )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( cpu@l1d_pend_miss.pending_cycles\\,any\\=1@ / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( cpu@ITLB_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_LOAD_MISSES.WALK_DURATION\\,cmask\\=1@ + cpu@DTLB_STORE_MISSES.WALK_DURATION\\,cmask\\=1@ + 7*(DTLB_STORE_MISSES.WALK_COMPLETED+DTLB_LOAD_MISSES.WALK_COMPLETED+ITLB_MISSES.WALK_COMPLETED)) / ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) if #SMT_on else cycles", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE ) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5
Arnaldo Carvalho de Melo
maintainerPATCH 41/41 perf vendor events: Add JSON metrics for Skylake server
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add JSON metrics for Skylake server
Signed-off-by Andi Kleen <[email protected]>
Cc Jiri Olsa <[email protected]>
Signed-off-by Arnaldo Carvalho de Melo <[email protected]>
--- .../pmu-events/arch/x86/skylakex/skx-metrics.json | 182 +++++++++++++++++++++ 1 file changed, 182 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json new file +182 -0
@@ -0,0 +1,182 @@ +[ + { + "BriefDescription": "Instructions Per Cycle (per logical thread)", + "MetricExpr": "INST_RETIRED.ANY / CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "TopDownL1", + "MetricName": "IPC" + }, + { + "BriefDescription": "Uops Per Instruction", + "MetricExpr": "UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY", + "MetricGroup": "Pipeline", + "MetricName": "UPI" + }, + { + "BriefDescription": "Rough Estimation of fraction of fetched lines bytes that were likely consumed by program instructions", + "MetricExpr": "min( 1 , UOPS_ISSUED.ANY / (UOPS_RETIRED.RETIRE_SLOTS / INST_RETIRED.ANY * 64 * ( ICACHE_64B.IFTAG_HIT + ICACHE_64B.IFTAG_MISS ) / 4.1) )", + "MetricGroup": "Frontend", + "MetricName": "IFetch_Line_Utilization" + }, + { + "BriefDescription": "Fraction of Uops delivered by the DSB (aka Decoded ICache; or Uop Cache)", + "MetricExpr": "IDQ.DSB_UOPS / ( IDQ.DSB_UOPS + LSD.UOPS + IDQ.MITE_UOPS + IDQ.MS_UOPS )", + "MetricGroup": "DSB; Frontend_Bandwidth", + "MetricName": "DSB_Coverage" + }, + { + "BriefDescription": "Cycles Per Instruction (threaded)", + "MetricExpr": "1 / INST_RETIRED.ANY / cycles", + "MetricGroup": "Pipeline;Summary", + "MetricName": "CPI" + }, + { + "BriefDescription": "Per-thread actual clocks when the logical processor is active. This is called 'Clockticks' in VTune.", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD", + "MetricGroup": "Summary", + "MetricName": "CLKS" + }, + { + "BriefDescription": "Total issue-pipeline slots (per-core)", + "MetricExpr": "4*cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )", + "MetricGroup": "TopDownL1", + "MetricName": "SLOTS" + }, + { + "BriefDescription": "Total number of retired Instructions", + "MetricExpr": "INST_RETIRED.ANY", + "MetricGroup": "Summary", + "MetricName": "Instructions" + }, + { + "BriefDescription": "Instructions Per Cycle (per physical core)", + "MetricExpr": "INST_RETIRED.ANY / cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )", + "MetricGroup": "SMT", + "MetricName": "CoreIPC" + }, + { + "BriefDescription": "Instruction-Level-Parallelism (average number of uops executed when there is at least 1 uop executed)", + "MetricExpr": "UOPS_EXECUTED.THREAD / ( UOPS_EXECUTED.CORE_CYCLES_GE_1 / 2) if #SMT_on else UOPS_EXECUTED.CORE_CYCLES_GE_1", + "MetricGroup": "Pipeline;Ports_Utilization", + "MetricName": "ILP" + }, + { + "BriefDescription": "Average Branch Address Clear Cost (fraction of cycles)", + "MetricExpr": "( RS_EVENTS.EMPTY_CYCLES - (ICACHE_16B.IFDATA_STALL +2* ICACHE_16B.IFDATA_STALL:c1:e1) - ICACHE_64B.IFTAG_STALL ) / RS_EVENTS.EMPTY_END", + "MetricGroup": "Unknown_Branches", + "MetricName": "BAClear_Cost" + }, + { + "BriefDescription": "Core actual clocks when any thread is active on the physical core", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if 1 else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 )", + "MetricGroup": "SMT", + "MetricName": "CORE_CLKS" + }, + { + "BriefDescription": "Actual Average Latency for L1 data-cache miss demand loads", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( MEM_LOAD_RETIRED.L1_MISS_PS + MEM_LOAD_RETIRED.FB_HIT_PS )", + "MetricGroup": "Memory_Bound;Memory_Lat", + "MetricName": "Load_Miss_Real_Latency" + }, + { + "BriefDescription": "Memory-Level-Parallelism (average number of L1 miss demand load when there is at least 1 such miss)", + "MetricExpr": "L1D_PEND_MISS.PENDING / ( L1D_PEND_MISS.PENDING_CYCLES_ANY / 2) if #SMT_on else L1D_PEND_MISS.PENDING_CYCLES", + "MetricGroup": "Memory_Bound;Memory_BW", + "MetricName": "MLP" + }, + { + "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses", + "MetricExpr": "( ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING + EPT.WALK_PENDING ) / ( 2 * cycles if not #SMT_on else (( CPU_CLK_UNHALTED.THREAD / 2) * (CPU_CLK_UNHALTED.ONE_THREAD_ACTIVE / CPU_CLK_UNHALTED.REF_XCLK )) if #EBS_Mode else ( CPU_CLK_UNHALTED.THREAD_ANY / 2 ) )", + "MetricGroup": "TLB", + "MetricName": "Page_Walks_Utilization" + }, + { + "BriefDescription": "L1 cache miss per kilo instruction for demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L1_MISS_PS / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses;", + "MetricName": "L1MPKI" + }, + { + "BriefDescription": "L2 cache miss per kilo instruction for demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L2_MISS_PS / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses;", + "MetricName": "L2MPKI" + }, + { + "BriefDescription": "L3 cache miss per kilo instruction for demand loads", + "MetricExpr": "1000 * MEM_LOAD_RETIRED.L3_MISS_PS / INST_RETIRED.ANY", + "MetricGroup": "Cache_Misses;", + "MetricName": "L3MPKI" + }, + { + "BriefDescription": "Average CPU Utilization", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC / msr@tsc@", + "MetricGroup": "Summary", + "MetricName": "CPU_Utilization" + }, + { + "BriefDescription": "Giga Floating Point Operations Per Second", + "MetricExpr": "( 1*( FP_ARITH_INST_RETIRED.SCALAR_SINGLE + FP_ARITH_INST_RETIRED.SCALAR_DOUBLE ) + 2* FP_ARITH_INST_RETIRED.128B_PACKED_DOUBLE + 4*( FP_ARITH_INST_RETIRED.128B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.256B_PACKED_DOUBLE ) + 8* (FP_ARITH_INST_RETIRED.256B_PACKED_SINGLE + FP_ARITH_INST_RETIRED.512B_PACKED_DOUBLE ) + 16* FP_ARITH_INST_RETIRED.512B_PACKED_SINGLE) / 1000000000 / duration_time", + "MetricGroup": "FLOPS;Summary", + "MetricName": "GFLOPs" + }, + { + "BriefDescription": "Average Frequency Utilization relative nominal frequency", + "MetricExpr": "CPU_CLK_UNHALTED.THREAD / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Power", + "MetricName": "Turbo_Utilization" + }, + { + "BriefDescription": "Fraction of cycles where both hardware threads were active", + "MetricExpr": "1 - CPU_CLK_THREAD_UNHALTED.ONE_THREAD_ACTIVE / ( CPU_CLK_THREAD_UNHALTED.REF_XCLK_ANY / 2 ) if #SMT_on else 0", + "MetricGroup": "SMT;Summary", + "MetricName": "SMT_2T_Utilization" + }, + { + "BriefDescription": "Fraction of cycles spent in Kernel mode", + "MetricExpr": "CPU_CLK_UNHALTED.REF_TSC:u / CPU_CLK_UNHALTED.REF_TSC", + "MetricGroup": "Summary", + "MetricName": "Kernel_Utilization" + }, + { + "BriefDescription": "C3 residency percent per core", + "MetricExpr": "(cstate_core@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Core_Residency" + }, + { + "BriefDescription": "C6 residency percent per core", + "MetricExpr": "(cstate_core@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Core_Residency" + }, + { + "BriefDescription": "C7 residency percent per core", + "MetricExpr": "(cstate_core@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Core_Residency" + }, + { + "BriefDescription": "C2 residency percent per package", + "MetricExpr": "(cstate_pkg@c2\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C2_Pkg_Residency" + }, + { + "BriefDescription": "C3 residency percent per package", + "MetricExpr": "(cstate_pkg@c3\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C3_Pkg_Residency" + }, + { + "BriefDescription": "C6 residency percent per package", + "MetricExpr": "(cstate_pkg@c6\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C6_Pkg_Residency" + }, + { + "BriefDescription": "C7 residency percent per package", + "MetricExpr": "(cstate_pkg@c7\\-residency@ / msr@tsc@) * 100", + "MetricGroup": "Power", + "MetricName": "C7_Pkg_Residency" + } +]
Signature · 1 line
2.13.5