perf/core improvements and fixes
Arnaldo Carvalho de Melo
maintainerHi Ingo,
There are some 'perf test' and container failures, but those
don't seem to have been introduced by patches in this series and are being investigated.
Please consider pulling,
- Arnaldo
Test results at the end of this message, as usual.
The following changes since commit f6751f178eeaf3da8c156d2a2fd7a0feccfab5ae:
tools/headers: Synchronize kernel x86 UAPI headers (2017-11-18 09:00:46 +0100)
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux.git tags/perf-core-for-mingo-4.15-20171124
for you to fetch changes up to 92f4ad912df4ac63f53ed0e95a7e0f51ef6eddfe:
perf intel-pt: Bring instruction decoder files into line with the kernel (2017-11-23 15:40:48 -0300)
----------------------------------------------------------------
perf/core improvements and fixes:
- Improve build messages for Intel PT related files that differ from the kernel (Adrian Hunter)
- Bring instruction decoder files into line with the kernel (Adrian Hunter)
- Allow computing 'perf stat' style metrics in 'perf script' (Andi Kleen)
- Fix -D output for user metadata events (Arnaldo Carvalho de Melo)
- Add perf tools tip for using 'perf buildid-cache' to add the Node.js USDT probes and have them usable via 'perf probe' (Hansuk Hong)
- Follow the upstream kernel UAPI header version 100% (Ingo Molnar)
- Fixup discontiguous/sparse numa nodes in 'perf bench numa' (Satheesh Rajendran)
- Fix a 'perf test' case and disable one, both for s390x (Thomas Richter)
----------------------------------------------------------------
Adrian Hunter (2):
perf intel-pt: Improve build messages for files that differ from the kernel perf intel-pt: Bring instruction decoder files into line with the kernel
Andi Kleen (3):
perf record: Synthesize unit/scale/... in event update perf record: Synthesize thread map and cpu map perf script: Allow computing 'perf stat' style metrics
Arnaldo Carvalho de Melo (1):
perf report: Fix -D output for user metadata events
Hansuk Hong (1):
perf buildid-cache: Document for Node.js USDT
Ingo Molnar (1):
tools headers: Follow the upstream UAPI header version 100% differ from the kernel
Satheesh Rajendran (1):
perf bench numa: Fixup discontiguous/sparse numa nodes
Thomas Richter (2):
perf test: Disable test cases 19 and 20 on s390x
perf test: Fix test 21 for s390xtools/perf/Documentation/perf-script.txt | 10 +++- tools/perf/Documentation/tips.txt | 1 + tools/perf/bench/numa.c | 56 ++++++++++++++++-- tools/perf/builtin-record.c | 24 ++++++++ tools/perf/builtin-script.c | 97 +++++++++++++++++++++++++++++++- tools/perf/builtin-stat.c | 62 ++------------------ tools/perf/check-headers.sh | 1 - tools/perf/tests/bp_signal.c | 2 +- tools/perf/tests/task-exit.c | 4 ++ tools/perf/util/header.c | 68 ++++++++++++++++++++++ tools/perf/util/header.h | 5 ++ tools/perf/util/intel-pt-decoder/Build | 24 +++++--- tools/perf/util/intel-pt-decoder/inat.h | 10 ++++ tools/perf/util/metricgroup.c | 4 ++ tools/perf/util/session.c | 3 +- 15 files changed, 293 insertions(+), 78 deletions(-)
Test results:
The first ones are container (docker) based builds of tools/perf with and without libelf support. Where clang is available, it is also used to build perf with/without libelf.
The objtool and samples/bpf/ builds are disabled now that I'm switching from using the sources in a local volume to fetching them from a http server to build it inside the container, to make it easier to build in a container cluster. Those will come back later.
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.
# dm 1 alpine:3.4: Ok gcc (Alpine 5.3.0) 5.3.0 2 alpine:3.5: Ok gcc (Alpine 6.2.1) 6.2.1 20160822 3 alpine:3.6: Ok gcc (Alpine 6.3.0) 6.3.0 4 alpine:edge: Ok gcc (Alpine 6.4.0) 6.4.0 5 android-ndk:r12b-arm: Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 6 android-ndk:r15c-arm: Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 7 centos:5: Ok gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55) 8 centos:6: Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-18) 9 centos:7: Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-16) 10 debian:7: Ok gcc (Debian 4.7.2-5) 4.7.2 11 debian:8: Ok gcc (Debian 4.9.2-10) 4.9.2 12 debian:9: Ok gcc (Debian 6.3.0-18) 6.3.0 20170516 13 debian:experimental: Ok gcc (Debian 7.2.0-16) 7.2.0 14 debian:experimental-x-arm64: Ok aarch64-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0 15 debian:experimental-x-mips: Ok mips-linux-gnu-gcc (Debian 7.2.0-11) 7.2.0 16 debian:experimental-x-mips64: Ok mips64-linux-gnuabi64-gcc (Debian 7.2.0-11) 7.2.0 17 fedora:20: Ok gcc (GCC) 4.8.3 20140911 (Red Hat 4.8.3-7) 18 fedora:21: Ok gcc (GCC) 4.9.2 20150212 (Red Hat 4.9.2-6) 19 fedora:22: Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 20 fedora:23: Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 21 fedora:24: Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1) 22 fedora:24-x-ARC-uClibc: Ok arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 23 fedora:25: Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1) 24 fedora:26: Ok gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2) 25 fedora:27: FAIL gcc (GCC) 7.2.1 20170915 (Red Hat 7.2.1-2)
perl/python hardened build CFLAGS mismatch, Jiri working on a fix.
26 fedora:rawhide: Ok gcc (GCC) 7.2.1 20170829 (Red Hat 7.2.1-1) 27 gentoo-stage3-amd64:latest: Ok gcc (Gentoo 5.4.0-r3 p1.7, pie-0.6.5) 5.4.0 28 mageia:5: Ok gcc (GCC) 4.9.2 29 mageia:6: Ok gcc (Mageia 5.4.0-5.mga6) 5.4.0 30 opensuse:42.1: Ok gcc (SUSE Linux) 4.8.5 31 opensuse:42.2: Ok gcc (SUSE Linux) 4.8.5 32 opensuse:42.3: Ok gcc (SUSE Linux) 4.8.5 33 opensuse:tumbleweed: Ok gcc (SUSE Linux) 7.2.1 20170901 [gcc-7-branch revision 251580] 34 oraclelinux:6: Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-18) 35 oraclelinux:7: Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-16) 36 ubuntu:12.04.5: Ok gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3 37 ubuntu:14.04.4: Ok gcc (Ubuntu 4.8.4-2ubuntu1~14.04.3) 4.8.4 38 ubuntu:14.04.4-x-linaro-arm64: Ok aarch64-linux-gnu-gcc 39 ubuntu:15.04: Ok gcc (Ubuntu 4.9.2-10ubuntu13) 4.9.2 40 ubuntu:16.04: Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.5) 5.4.0 20160609 41 ubuntu:16.04-x-arm: Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609 42 ubuntu:16.04-x-arm64: Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609 43 ubuntu:16.04-x-powerpc: Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609 44 ubuntu:16.04-x-powerpc64: Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.1) 5.4.0 20160609 45 ubuntu:16.04-x-powerpc64el: Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609 46 ubuntu:16.04-x-s390: Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.4) 5.4.0 20160609 47 ubuntu:16.10: Ok gcc (Ubuntu 6.2.0-5ubuntu12) 6.2.0 20161005 48 ubuntu:17.04: Ok gcc (Ubuntu 6.3.0-12ubuntu2) 6.3.0 20170406 49 ubuntu:17.10: Ok gcc (Ubuntu 7.2.0-8ubuntu3) 7.2.0
#
The BPF and LLVM test failures are being investigated, perhaps related to updating to clang 6.
# uname -a Linux jouet 4.14.0+ #2 SMP Thu Nov 16 12:09:19 -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 : FAILED! 37.3: Compile source for BPF prologue generation : Skip 37.4: Compile source for BPF relocation : Skip 38: Session topology : Ok 39: BPF filter : 39.1: Basic BPF filtering : FAILED! 39.2: BPF pinning : Skip 39.3: BPF prologue generation : Skip 39.4: BPF relocation checker : Skip 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: Use vfs_getname probe to get syscall args filenames : Ok 61: probe libc's inet_pton & backtrace it with ping : Ok 62: Check open filename arg using perf trace + vfs_getname: Ok 63: Add vfs_getname probe to get syscall args filenames : Ok #
$ make -C tools/perf build-test
make: Entering directory '/home/acme/git/linux/tools/perf'
- tarpkg: ./tests/perf-targz-src-pkg .
make_install_prefix_O: make install prefix=/tmp/krava
make_no_libbionic_O: make NO_LIBBIONIC=1
make_tags_O: make tags
make_no_newt_O: make NO_NEWT=1
make_no_libunwind_O: make NO_LIBUNWIND=1
make_no_backtrace_O: make NO_BACKTRACE=1
make_no_gtk2_O: make NO_GTK2=1
make_pure_O: make
make_util_map_o_O: make util/map.o
make_install_O: make install
make_install_bin_O: make install-bin
make_no_libnuma_O: make NO_LIBNUMA=1
make_no_demangle_O: make NO_DEMANGLE=1
make_perf_o_O: make perf.o
make_help_O: make help
make_no_libelf_O: make NO_LIBELF=1
make_no_libbpf_O: make NO_LIBBPF=1
make_install_prefix_slash_O: make install prefix=/tmp/krava/
make_no_libpython_O: make NO_LIBPYTHON=1
make_no_libaudit_O: make NO_LIBAUDIT=1
make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1
make_util_pmu_bison_o_O: make util/pmu-bison.o
make_clean_all_O: make clean all
make_with_clangllvm_O: make LIBCLANGLLVM=1
make_no_auxtrace_O: make NO_AUXTRACE=1
make_doc_O: make doc
make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1
make_with_babeltrace_O: make LIBBABELTRACE=1
make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
make_no_slang_O: make NO_SLANG=1
make_debug_O: make DEBUG=1
make_no_libperl_O: make NO_LIBPERL=1
make_static_O: make LDFLAGS=-static
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
OK
make: Leaving directory '/home/acme/git/linux/tools/perf'
$Arnaldo Carvalho de Melo
maintainerPATCH 1/11 tools headers: Follow the upstream UAPI header version 100% differ from the kernel
From: Ingo Molnar <[email protected]>
Remove this from check-headers.sh:
opts="--ignore-blank-lines --ignore-space-change"
as the easiest policy is to just follow the upstream UAPI header version 100%. Pure space-only changes are comparatively rare.
--- tools/perf/check-headers.sh | 1 - 1 file changed, 1 deletion(-)
tools/perf/check-headers.sh +0 -1
@@ -45,7 +45,6 @@ include/uapi/asm-generic/mman-common.h check () { file=$1 - opts="--ignore-blank-lines --ignore-space-change" shift while [ -n "$*" ]; do
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 2/11 perf bench numa: Fixup discontiguous/sparse numa nodes
In reply to Arnaldo Carvalho de MeloFrom: Satheesh Rajendran <[email protected]>
Certain systems are designed to have sparse/discontiguous nodes. On such systems, 'perf bench numa' hangs, shows wrong number of nodes and shows values for non-existent nodes. Handle this by only taking nodes that are exposed by kernel to userspace.
--- tools/perf/bench/numa.c | 56 ++++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 51 insertions(+), 5 deletions(-)
tools/perf/bench/numa.c +51 -5
@@ -216,6 +216,47 @@ static const char * const numa_usage[] = { NULL }; +/* +* To get number of numa nodes present. +*/ +static int nr_numa_nodes (void ) +{ +int i, nr_nodes =0 ; + +for (i =0 ; i < g->p.nr_nodes; i++) { +if (numa_bitmask_isbitset (numa_nodes_ptr, i)) + nr_nodes++; + } + +return nr_nodes; +} + +/* +* To check if given numa node is present. +*/ +static int is_node_present (int node) +{ +return numa_bitmask_isbitset (numa_nodes_ptr, node); +} + +/* +* To check given numa node has cpus. +*/ +static bool node_has_cpus (int node) +{ +struct bitmask *cpu =numa_allocate_cpumask (); +unsigned int i; + +if (cpu && !numa_node_to_cpus (node, cpu)) { +for (i =0 ; i < cpu->size; i++) { +if (numa_bitmask_isbitset (cpu, i)) +return true; + } + } + +return false;/* lets fall back to nocpus safely */ +} +static cpu_set_t bind_to_cpu (int target_cpu) {cpu_set_t orig_mask, mask;
@@ -244,12 +285,12 @@ static cpu_set_t bind_to_cpu(int target_cpu)static cpu_set_t bind_to_node (int target_node) { -int cpus_per_node = g->p.nr_cpus/g->p.nr_nodes; +int cpus_per_node = g->p.nr_cpus /nr_numa_nodes ();cpu_set_t orig_mask, mask;int cpu;int ret; -BUG_ON (cpus_per_node*g->p.nr_nodes != g->p.nr_cpus); +BUG_ON (cpus_per_node *nr_numa_nodes () != g->p.nr_cpus);BUG_ON (!cpus_per_node); ret =sched_getaffinity (0 ,sizeof (orig_mask), &orig_mask);
@@ -649,7 +690,7 @@ static int parse_setup_node_list(void)int i;for (i =0 ; i < mul; i++) { -if (t >= g->p.nr_tasks) { +if (t >= g->p.nr_tasks || !node_has_cpus (bind_node)) {printf ("\n# NOTE: ignoring bind NODEs starting at NODE#%d\n" , bind_node); goto out; }
@@ -964,6 +1005,8 @@ static void calc_convergence(double runtime_ns_max, double *convergence) sum =0 ;for (node =0 ; node < g->p.nr_nodes; node++) { +if (!is_node_present (node)) +continue ; nr = nodes[node]; nr_min =min (nr, nr_min); nr_max =max (nr, nr_max);
@@ -984,8 +1027,11 @@ static void calc_convergence(double runtime_ns_max, double *convergence) process_groups =0 ;for (node =0 ; node < g->p.nr_nodes; node++) { -int processes =count_node_processes (node); +int processes; +if (!is_node_present (node)) +continue ; + processes =count_node_processes (node); nr = nodes[node];tprintf (" %2d/%-2d" , nr, processes);
@@ -1291,7 +1337,7 @@ static void print_summary(void)printf ("\n ###\n" );printf (" # %d %s will execute (on %d nodes, %d CPUs):\n" , - g->p.nr_tasks, g->p.nr_tasks ==1 ?"task" :"tasks" , g->p.nr_nodes, g->p.nr_cpus); + g->p.nr_tasks, g->p.nr_tasks ==1 ?"task" :"tasks" ,nr_numa_nodes (), g->p.nr_cpus);printf (" # %5dx %5ldMB global shared mem operations\n" , g->p.nr_loops, g->p.bytes_global/1024 /1024 ); printf(" # %5dx %5ldMB process shared mem operations\n",
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 3/11 perf test: Disable test cases 19 and 20 on s390x
In reply to Arnaldo Carvalho de MeloFrom: Thomas Richter <[email protected]>
The s390x CPU sampling and measurement facilities do not support perf events of type PERF_TYPE_BREAKPOINT. The test cases are executed and fail with -ENOENT due to missing hardware support.
Disable the execution of both test cases based on a platform check. This is the same approach as done for PowerPC.
LPU-Reference: [email protected]
--- tools/perf/tests/bp_signal.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/tests/bp_signal.c +1 -1
@@ -296,7 +296,7 @@ bool test__bp_signal_is_supported(void)* instruction breakpoint using the perf event interface. * Once it's there we can release this. */ -#ifdef __powerpc__ +#if defined(__powerpc__) || defined(__s390x__)return false;#else return true;
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 4/11 perf test: Fix test 21 for s390x
In reply to Arnaldo Carvalho de MeloFrom: Thomas Richter <[email protected]>
Test case 21 (Number of exit events of a simple workload) fails on s390x. The reason is the invalid sample frequency supplied for this test. On s390x the minimum sample frequency is much higher (see output of /proc/service_levels).
Supply a save sample frequency value for s390x to fix this. The value will be adjusted by the s390x CPUMF frequency convertion function to a value well below the sysctl kernel.perf_event_max_sample_rate value.
LPU-Reference: [email protected]
--- tools/perf/tests/task-exit.c | 4 ++++ 1 file changed, 4 insertions(+)
tools/perf/tests/task-exit.c +4 -0
@@ -84,7 +84,11 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused evsel =perf_evlist__first (evlist); evsel->attr.task =1 ; +#ifdef __s390x__ + evsel->attr.sample_freq =1000000 ; +#else evsel->attr.sample_freq =1 ; +#endif evsel->attr.inherit =0 ; evsel->attr.watermark =0 ; evsel->attr.wakeup_events =1 ;
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 5/11 perf record: Synthesize unit/scale/... in event update
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Move the code to synthesize event updates for scale/unit/cpus to a common utility file, and use it both from stat and record.
This allows to access scale and other extra qualifiers from perf script.
--- tools/perf/builtin-record.c | 9 ++++++ tools/perf/builtin-stat.c | 62 +++-------------------------------------- tools/perf/util/header.c | 68 +++++++++++++++++++++++++++++++++++++++++++++ tools/perf/util/header.h | 5 ++++ 4 files changed, 86 insertions(+), 58 deletions(-)
tools/perf/builtin-record.c +9 -0
@@ -372,6 +372,8 @@ static int record__open(struct record *rec)ui__error ("%s\n" , msg); goto out; } + + pos->supported = true; }if (perf_evlist__apply_filters (evlist, &pos)) {
@@ -784,6 +786,13 @@ static int record__synthesize(struct record *rec, bool tail) perf_event__synthesize_guest_os, tool); } + err =perf_event__synthesize_extra_attr (&rec->tool, + rec->evlist, + process_synthesized_event, + data->is_pipe); +if (err) + goto out; + err =__machine__synthesize_threads (machine, tool, &opts->target, rec->evlist->threads, process_synthesized_event, opts->sample_address, opts->proc_map_timeout,1 );
tools/perf/builtin-stat.c +4 -58
76 lines not on this page · raw message
tools/perf/util/header.c +68 -0
74 lines not on this page · raw message
tools/perf/util/header.h +5 -0
@@ -107,6 +107,11 @@ int perf_event__synthesize_features(struct perf_tool *tool,struct perf_evlist *evlist, perf_event__handler_t process); +int perf_event__synthesize_extra_attr (struct perf_tool *tool, +struct perf_evlist *evsel_list, +perf_event__handler_t process, +bool is_pipe); +int perf_event__process_feature (struct perf_tool *tool,union perf_event *event,struct perf_session *session);
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 6/11 perf record: Synthesize thread map and cpu map
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Synthesize the per attr thread maps and cpu maps in 'perf record'.
This allows code from 'perf stat' called from 'perf script' to access this information.
Committer testing:
Please see the PERF_RECORD_THREAD_MAP and PERF_RECORD_CPU_MAP records, added by this patch:
$ perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.001 MB perf.data (8 samples) ] $ perf report -D | grep PERF_RECORD_ | head 0xe8 [0x20]: PERF_RECORD_TIME_CONV: unhandled! 0x108 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 23568 0x130 [0x18]: PERF_RECORD_CPU_MAP: 0-3 0 0x148 [0x28]: PERF_RECORD_COMM: perf:23568/23568 0x570 [0x8]: PERF_RECORD_FINISHED_ROUND 445342677837144 0x170 [0x28]: PERF_RECORD_COMM exec: sleep:23568/23568 445342677847339 0x198 [0x68]: PERF_RECORD_MMAP2 23568/23568: [0x564c943a4000(0x208000) @ 0 fd:00 3147174 2566255743]: r-xp /usr/bin/sleep 445342677862450 0x200 [0x70]: PERF_RECORD_MMAP2 23568/23568: [0x7f25968a8000(0x229000) @ 0 fd:00 3151761 2566238119]: r-xp /usr/lib64/ld-2.25.so 445342677873174 0x270 [0x60]: PERF_RECORD_MMAP2 23568/23568: [0x7ffc98176000(0x2000) @ 0 00:00 0 0]: r-xp [vdso] 445342677891928 0x2d0 [0x28]: PERF_RECORD_SAMPLE(IP, 0x4002): 23568/23568: 0xffffffff8f84c7e7 period: 1 addr: 0 $
--- tools/perf/builtin-record.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+)
tools/perf/builtin-record.c +15 -0
@@ -793,6 +793,21 @@ static int record__synthesize(struct record *rec, bool tail)if (err) goto out; + err =perf_event__synthesize_thread_map2 (&rec->tool, rec->evlist->threads, + process_synthesized_event, +NULL ); +if (err <0 ) { +pr_err ("Couldn't synthesize thread map.\n" ); +return err; + } + + err =perf_event__synthesize_cpu_map (&rec->tool, rec->evlist->cpus, + process_synthesized_event,NULL ); +if (err <0 ) { +pr_err ("Couldn't synthesize cpu map.\n" ); +return err; + } + err =__machine__synthesize_threads (machine, tool, &opts->target, rec->evlist->threads, process_synthesized_event, opts->sample_address, opts->proc_map_timeout,1 );
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 7/11 perf script: Allow computing 'perf stat' style metrics
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add support for computing 'perf stat' style metrics in 'perf script'.
When using leader sampling we can get metrics for each sampling period by computing formulas over the values of the different group members.
This allows things like fine grained IPC tracking through sampling, much more fine grained than with 'perf stat'.
The metric is still averaged over the sampling period, it is not just for the sampling point.
This patch adds a new metric output field for 'perf script' that uses the existing 'perf stat' metrics infrastructure to compute any metrics supported by 'perf stat'.
For example to sample IPC:
$ perf record -e '{ref-cycles,cycles,instructions}:S' -a sleep 1
$ perf script -F metric,ip,sym,time,cpu,comm
...
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: 7fd65937d6cc [unknown]
alsa-sink-ALC32 [000] 42815.856074: metric: 0.13 insn per cycle
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: ffffffff81655df0 __schedule
swapper [000] 42815.857961: metric: 0.23 insn per cycle
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: ffffffff8165ad0e _raw_spin_unlock_irqrestore
qemu-system-x86 [000] 42815.858130: metric: 0.46 insn per cycle
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: ffffffffa080e5f2 vmx_vcpu_run
:4972 [000] 42815.858312: metric: 0.45 insn per cycleTopDown:
This requires disabling SMT if you have it enabled, because SMT would require sampling per core, which is not supported.
$ perf record -e '{ref-cycles,topdown-fetch-bubbles,\
topdown-recovery-bubbles,\
topdown-slots-retired,topdown-total-slots,\
topdown-slots-issued}:S' -a sleep 1
$ perf script --header -I -F cpu,ip,sym,event,metric,period
...
[000] 121108 ref-cycles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 190350 topdown-fetch-bubbles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 2055 topdown-recovery-bubbles: ffffffff8165222e copy_user_enhanced_fast_string
[000] 148729 topdown-slots-retired: ffffffff8165222e copy_user_enhanced_fast_string
[000] 144324 topdown-total-slots: ffffffff8165222e copy_user_enhanced_fast_string
[000] 160852 topdown-slots-issued: ffffffff8165222e copy_user_enhanced_fast_string
[000] metric: 33.0% frontend bound
[000] metric: 3.5% bad speculation
[000] metric: 25.8% retiring
[000] metric: 37.7% backend bound
[000] 112112 ref-cycles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 357222 topdown-fetch-bubbles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 3325 topdown-recovery-bubbles: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 323553 topdown-slots-retired: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 270507 topdown-total-slots: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] 341226 topdown-slots-issued: ffffffff8165aec8 _raw_spin_lock_irqsave
[000] metric: 33.0% frontend bound
[000] metric: 2.9% bad speculation
[000] metric: 29.9% retiring
[000] metric: 34.2% backend bound
...v2:
Use evsel->priv for new fields
Port to new base line, support fp output.
Handle stats in ->stats, not ->priv
Minor cleanups
Extra explanation about the use of the term 'averaging', from Andi in the thread in the Link: tag below:
<quote Andi>
The current samples contains the sum of event counts for a sampling period.
EventA-1 EventA-2 EventA-3 EventA-4
EventB-1 EventB-2 EventC-3
gap with no events overflow
|-----------------------------------------------------------------| period-start period-end ^ ^ | | previous sample current sample
So EventA = 4 and EventB = 3 at the sample point
I generate a metric, let's say EventA / EventB. It applies to the whole period.
But the metric is over a longer time which does not have the same behavior. For example the gap above doesn't have any events, while they are clustered at the beginning and end of the sample period.
But we're summing everything together. The metric doesn't know that the gap is different than the busy period.
That's what I'm trying to express with averaging.
</quote>
--- tools/perf/Documentation/perf-script.txt | 10 +++- tools/perf/builtin-script.c | 97 +++++++++++++++++++++++++++++++- tools/perf/util/metricgroup.c | 4 ++ 3 files changed, 108 insertions(+), 3 deletions(-)
tools/perf/Documentation/perf-script.txt +9 -1
@@ -117,7 +117,7 @@ OPTIONS Comma separated list of fields to print. Options are: comm, tid, pid, time, cpu, event, trace, ip, sym, dso, addr, symoff, srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output, brstackinsn, - brstackoff, callindent, insn, insnlen, synth, phys_addr. + brstackoff, callindent, insn, insnlen, synth, phys_addr, metric. 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
@@ -217,6 +217,14 @@ OPTIONS The brstackoff field will print an offset into a specific dso/binary. + With the metric option perf script can compute metrics for + sampling periods, similar to perf stat. This requires + specifying a group with multiple metrics with the :S option + for perf record. perf will sample on the first event, and + compute metrics for all the events in the group. Please note + that the metric computed is averaged over the whole sampling + period, not just for the sample point. + -k:: --vmlinux=<file>:: vmlinux pathname
tools/perf/builtin-script.c +95 -2
144 lines not on this page · raw message
tools/perf/util/metricgroup.c +4 -0
@@ -38,6 +38,10 @@ struct metric_event *metricgroup__lookup(struct rblist *metric_events,struct metric_event me = { .evsel = evsel }; + +if (!metric_events) +return NULL ; + nd =rblist__find (metric_events, &me);if (nd) return container_of(nd, struct metric_event, nd);
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 8/11 perf buildid-cache: Document for Node.js USDT
In reply to Arnaldo Carvalho de MeloFrom: Hansuk Hong <[email protected]>
Add a tip for Node.js USDT(User-Level Statically Defined Tracing) probes in tips.txt
--- tools/perf/Documentation/tips.txt | 1 + 1 file changed, 1 insertion(+)
tools/perf/Documentation/tips.txt +1 -0
@@ -32,3 +32,4 @@ Order by the overhead of source file name and line number: perf report -s srclin System-wide collection from all CPUs: perf record -a Show current config key-value pairs: perf config --list Show user configuration overrides: perf config --user --list +To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 9/11 perf report: Fix -D output for user metadata events
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
The PERF_RECORD_USER_ events are synthesized by the tool to assist in processing the PERF_RECORD_ ones generated by the kernel, the printing of that information doesn't come with a perf_sample structure, so, when dumping the event fields using 'perf report -D' there were columns that end up not being printed.
To tidy up a bit this, fake a perf_sample structure with zeroes to have the missing columns printed and avoid the occasional surprise with that.
Before:
0 0x45b8 [0x68]: PERF_RECORD_MMAP -1/0: [0xffffffffc12ec000(0x4000) @ 0]: x /lib/modules/4.14.0+/kernel/fs/nls/nls_utf8.ko 0x4620 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 278200x4648 [0x18]: PERF_RECORD_CPU_MAP: 0-3
0 0x4660 [0x28]: PERF_RECORD_COMM: perf:27820/278200x4a58 [0x8]: PERF_RECORD_FINISHED_ROUND
447723433020976 0x4688 [0x28]: PERF_RECORD_SAMPLE(IP, 0x4001): 27820/27820: 0xffffffff8f1b6d7a period: 1 addr: 0
After:
$ perf report -D | grep PERF_RECORD_ | head 0 0xe8 [0x20]: PERF_RECORD_TIME_CONV: unhandled! 0 0x108 [0x28]: PERF_RECORD_THREAD_MAP nr: 1 thread: 32555 0 0x130 [0x18]: PERF_RECORD_CPU_MAP: 0-3 0 0x148 [0x28]: PERF_RECORD_COMM: perf:32555/32555 0 0x4e8 [0x8]: PERF_RECORD_FINISHED_ROUND 448743409421205 0x170 [0x28]: PERF_RECORD_COMM exec: sleep:32555/32555 448743409431883 0x198 [0x68]: PERF_RECORD_MMAP2 32555/32555: [0x55e11d75a000(0x208000) @ 0 fd:00 3147174 2566255743]: r-xp /usr/bin/sleep 448743409443873 0x200 [0x70]: PERF_RECORD_MMAP2 32555/32555: [0x7f0ced316000(0x229000) @ 0 fd:00 3151761 2566238119]: r-xp /usr/lib64/ld-2.25.so 448743409454790 0x270 [0x60]: PERF_RECORD_MMAP2 32555/32555: [0x7ffe84f6d000(0x2000) @ 0 00:00 0 0]: r-xp [vdso] 448743409479500 0x2d0 [0x28]: PERF_RECORD_SAMPLE(IP, 0x4002): 32555/32555: 0xffffffff8f84c7e7 period: 1 addr: 0 $
--- tools/perf/util/session.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-)
tools/perf/util/session.c +2 -1
@@ -1348,10 +1348,11 @@ static s64 perf_session__process_user_event(struct perf_session *session, {struct ordered_events *oe = &session->ordered_events;struct perf_tool *tool = session->tool; +struct perf_sample sample = { .time =0 , };int fd =perf_data__fd (session->data);int err; -dump_event (session->evlist, event, file_offset,NULL ); +dump_event (session->evlist, event, file_offset, &sample);/* These events are processed right away */ switch (event->header.type) {
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 10/11 perf intel-pt: Improve build messages for files that differ from the kernel
In reply to Arnaldo Carvalho de MeloFrom: Adrian Hunter <[email protected]>
Print file names of files that differ. For example, instead of:
Warning: Intel PT: x86 instruction decoder differs from kernel
print:
Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'
--- tools/perf/util/intel-pt-decoder/Build | 24 +++++++++++++++--------- 1 file changed, 15 insertions(+), 9 deletions(-)
tools/perf/util/intel-pt-decoder/Build +15 -9
@@ -11,15 +11,21 @@ $(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_table $(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: util/intel-pt-decoder/intel-pt-insn-decoder.c util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c @(diff -I 2>&1 | grep -q 'option requires an argument' && \ - test -d ../../kernel -a -d ../../tools -a -d ../perf && (( \ - diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null && \ - diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null && \ - diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null && \ - diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null && \ - diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null && \ - diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null && \ - diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) \ - || echo "Warning: Intel PT: x86 instruction decoder differs from kernel" >&2 )) || true + test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \ + ((diff -B -I'^#include' util/intel-pt-decoder/insn.c ../../arch/x86/lib/insn.c >/dev/null) || \ + (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/insn.c' differs from latest version at 'arch/x86/lib/insn.c'" >&2)) && \ + ((diff -B -I'^#include' util/intel-pt-decoder/inat.c ../../arch/x86/lib/inat.c >/dev/null) || \ + (echo "Warning: Intel PT: x86 instruction decoder C file at 'tools/perf/util/intel-pt-decoder/inat.c' differs from latest version at 'arch/x86/lib/inat.c'" >&2)) && \ + ((diff -B util/intel-pt-decoder/x86-opcode-map.txt ../../arch/x86/lib/x86-opcode-map.txt >/dev/null) || \ + (echo "Warning: Intel PT: x86 instruction decoder map file at 'tools/perf/util/intel-pt-decoder/x86-opcode-map.txt' differs from latest version at 'arch/x86/lib/x86-opcode-map.txt'" >&2)) && \ + ((diff -B util/intel-pt-decoder/gen-insn-attr-x86.awk ../../arch/x86/tools/gen-insn-attr-x86.awk >/dev/null) || \ + (echo "Warning: Intel PT: x86 instruction decoder script at 'tools/perf/util/intel-pt-decoder/gen-insn-attr-x86.awk' differs from latest version at 'arch/x86/tools/gen-insn-attr-x86.awk'" >&2)) && \ + ((diff -B -I'^#include' util/intel-pt-decoder/insn.h ../../arch/x86/include/asm/insn.h >/dev/null) || \ + (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/insn.h' differs from latest version at 'arch/x86/include/asm/insn.h'" >&2)) && \ + ((diff -B -I'^#include' util/intel-pt-decoder/inat.h ../../arch/x86/include/asm/inat.h >/dev/null) || \ + (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat.h' differs from latest version at 'arch/x86/include/asm/inat.h'" >&2)) && \ + ((diff -B -I'^#include' util/intel-pt-decoder/inat_types.h ../../arch/x86/include/asm/inat_types.h >/dev/null) || \ + (echo "Warning: Intel PT: x86 instruction decoder header at 'tools/perf/util/intel-pt-decoder/inat_types.h' differs from latest version at 'arch/x86/include/asm/inat_types.h'" >&2)))) || true $(call rule_mkdir) $(call if_changed_dep,cc_o_c)
Signature · 1 line
2.13.6
Arnaldo Carvalho de Melo
maintainerPATCH 11/11 perf intel-pt: Bring instruction decoder files into line with the kernel
In reply to Arnaldo Carvalho de MeloFrom: Adrian Hunter <[email protected]>
There are just a few new defines which do not affect perf tools.
--- tools/perf/util/intel-pt-decoder/inat.h | 10 ++++++++++ 1 file changed, 10 insertions(+)
tools/perf/util/intel-pt-decoder/inat.h +10 -0
@@ -97,6 +97,16 @@#define INAT_MAKE_GROUP (grp) ((grp << INAT_GRP_OFFS) | INAT_MODRM)#define INAT_MAKE_IMM (imm) (imm << INAT_IMM_OFFS) +/* Identifiers for segment registers */ +#define INAT_SEG_REG_IGNORE 0 +#define INAT_SEG_REG_DEFAULT 1 +#define INAT_SEG_REG_CS 2 +#define INAT_SEG_REG_SS 3 +#define INAT_SEG_REG_DS 4 +#define INAT_SEG_REG_ES 5 +#define INAT_SEG_REG_FS 6 +#define INAT_SEG_REG_GS 7 +/* Attribute search APIs */ extern insn_attr_t inat_get_opcode_attribute (insn_byte_t opcode);extern int inat_get_last_prefix_id (insn_byte_t last_pfx);
Signature · 1 line
2.13.6