perf/core improvements and fixes
Subsystems (2)
Arnaldo Carvalho de Melo
maintainerHi Ingo,
Please consider pulling,
Best regards,
- Arnaldo
Test results at the end of this message, as usual.
The following changes since commit b339da480315505aa28a723a983217ebcff95c86:
Merge tag 'perf-core-for-mingo-5.1-20190307' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent (2019-03-09 17:00:17 +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-5.1-20190311
for you to fetch changes up to dfcbc2f2994b8a3af3605a26dc29c07ad7378bf4:
tools lib bpf: Fix the build by adding a missing stdarg.h include (2019-03-11 17:14:31 -0300)
----------------------------------------------------------------
perf/core improvements and fixes:
kernel:
Stephane Eranian :
- Restore mmap record type correctly when handling PERF_RECORD_MMAP2 events, as the same template is used for all the threads interested in mmap events, some may want just PERF_RECORD_MMAP, while some may want the extra info in MMAP2 records.
perf probe:
Adrian Hunter:
- Fix getting the kernel map, because since changes related to x86 PTI entry trampolines handling, there are more than one kernel map.
perf script:
Andi Kleen:
- Support insn output for normal samples, i.e.:
perf script -F ip,sym,insn --xed
Will fetch the sample IP from the thread address space and feed it to Intel's XED disassembler, producing lines such as:
ffffffffa4068804 native_write_msr wrmsr
ffffffffa415b95e __hrtimer_next_event_base movq 0x18(%rax), %rdx
That match 'perf annotate's output.
- Make the --cpu filter apply to PERF_RECORD_COMM/FORK/... events, in addition to PERF_RECORD_SAMPLE.
perf report:
- Add a new --samples option to save a small random number of samples per hist entry, using a reservoir technique to select a representative number of samples.
Then allow browsing the samples using 'perf script' as part of the hist entry context menu. This automatically adds the right filters, so only the thread or CPU of the sample is displayed. Then we use less' search functionality to directly jump to the time stamp of the selected sample.
It uses different menus for assembler and source display. Assembler needs xed installed and source needs debuginfo.
- Fix the UI browser scripts pop up menu when there are many scripts available.
perf report:
Andi Kleen:
- Add 'time' sort option. E.g.:
% perf report --sort time,overhead,symbol --time-quantum 1ms --stdio
...
0.67% 277061.87300 [.] _dl_start
0.50% 277061.87300 [.] f1
0.50% 277061.87300 [.] f2
0.33% 277061.87300 [.] main
0.29% 277061.87300 [.] _dl_lookup_symbol_x
0.29% 277061.87300 [.] dl_main
0.29% 277061.87300 [.] do_lookup_x
0.17% 277061.87300 [.] _dl_debug_initialize
0.17% 277061.87300 [.] _dl_init_paths
0.08% 277061.87300 [.] check_match
0.04% 277061.87300 [.] _dl_count_modids
1.33% 277061.87400 [.] f1
1.33% 277061.87400 [.] f2
1.33% 277061.87400 [.] main
1.17% 277061.87500 [.] main
1.08% 277061.87500 [.] f1
1.08% 277061.87500 [.] f2
1.00% 277061.87600 [.] main
0.83% 277061.87600 [.] f1
0.83% 277061.87600 [.] f2
1.00% 277061.87700 [.] maintools headers:
Arnaldo Carvalho de Melo:
- Update x86's syscall_64.tbl, no change in tools/perf behaviour.
- Sync copies asm-generic/unistd.h and linux/in with the kernel sources.
perf data:
Jiri Olsa:
- Prep work to support having perf.data stored as a directory, with one file per CPU, that ultimately will allow having one ring buffer reading thread per CPU.
Vendor events:
Martin Liška:
- perf PMU events for AMD Family 17h.
perf script python:
Tony Jones:
- Add python3 support for the remaining Intel PT related scripts, with these we should have a clean build of perf with python3 while still supporting the build with python2.
libbpf:
Arnaldo Carvalho de Melo:
- Fix the build on uCLibc, adding the missing stdarg.h since we use va_list in one typedef.
----------------------------------------------------------------
Adrian Hunter (1):
perf probe: Fix getting the kernel map
Andi Kleen (14):
perf script: Support insn output for normal samples
perf report: Support output in nanoseconds
perf time-utils: Add utility function to print time stamps in nanoseconds perf report: Parse time quantum
perf report: Use less for scripts output
perf script: Filter COMM/FORK/.. events by CPU
perf report: Support time sort key
perf report: Support running scripts for current time range perf report: Support builtin perf script in scripts menu perf report: Implement browsing of individual samples
perf tools: Add some new tips describing the new options perf script: Add array bound checking to list_scripts
perf ui browser: Fix ui popup argv browser for many entries perf tools report: Add custom scripts to script menu
Arnaldo Carvalho de Melo (4):
perf tools: Update x86's syscall_64.tbl, no change in tools/perf behaviour tools headers uapi: Sync copy of asm-generic/unistd.h with the kernel sources tools headers uapi: Update linux/in.h copy
tools lib bpf: Fix the build by adding a missing stdarg.h include
Jiri Olsa (6):
perf data: Support having perf.data stored as a directory perf data: Don't store auxtrace index for directory data file perf data: Add perf_data__update_dir() function perf data: Make perf_data__size() work over directory perf header: Add DIR_FORMAT feature to describe directory data perf session: Add process callback to reader object
Martin Liška (1):
perf vendor events amd: perf PMU events for AMD Family 17h
Stephane Eranian (1):
perf/core: Restore mmap record type correctly
Tony Jones (4):
perf script python: Add Python3 support to exported-sql-viewer.py perf script python: Add Python3 support to export-to-postgresql.py perf script python: Add Python3 support to export-to-sqlite.py perf script python: Add printdate function to SQL exporters
kernel/events/core.c | 2 + tools/arch/arm64/include/uapi/asm/unistd.h | 2 + tools/include/uapi/asm-generic/unistd.h | 149 ++++++++--- tools/include/uapi/linux/in.h | 9 +- tools/lib/bpf/libbpf.h | 1 + tools/perf/Documentation/perf-config.txt | 14 + tools/perf/Documentation/perf-report.txt | 13 + tools/perf/Documentation/tips.txt | 7 + tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 6 +- tools/perf/arch/x86/util/Build | 1 + tools/perf/arch/x86/util/archinsn.c | 26 ++ tools/perf/builtin-record.c | 4 +- tools/perf/builtin-report.c | 45 ++++ tools/perf/builtin-script.c | 111 +++++--- tools/perf/builtin.h | 3 +- .../perf/pmu-events/arch/x86/amdfam17h/branch.json | 12 + .../perf/pmu-events/arch/x86/amdfam17h/cache.json | 287 +++++++++++++++++++++ tools/perf/pmu-events/arch/x86/amdfam17h/core.json | 134 ++++++++++ .../arch/x86/amdfam17h/floating-point.json | 168 ++++++++++++ .../perf/pmu-events/arch/x86/amdfam17h/memory.json | 162 ++++++++++++ .../perf/pmu-events/arch/x86/amdfam17h/other.json | 65 +++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + tools/perf/scripts/python/export-to-postgresql.py | 61 +++-- tools/perf/scripts/python/export-to-sqlite.py | 26 +- tools/perf/scripts/python/exported-sql-viewer.py | 42 ++- tools/perf/ui/browser.c | 10 +- tools/perf/ui/browsers/Build | 1 + tools/perf/ui/browsers/annotate.c | 2 +- tools/perf/ui/browsers/hists.c | 141 ++++++++-- tools/perf/ui/browsers/res_sample.c | 91 +++++++ tools/perf/ui/browsers/scripts.c | 274 ++++++++++---------- tools/perf/util/archinsn.h | 12 + tools/perf/util/data.c | 96 ++++++- tools/perf/util/data.h | 12 +- tools/perf/util/header.c | 44 +++- tools/perf/util/header.h | 5 + tools/perf/util/hist.c | 50 ++++ tools/perf/util/hist.h | 31 ++- tools/perf/util/probe-event.c | 6 +- tools/perf/util/session.c | 27 +- tools/perf/util/sort.c | 39 +++ tools/perf/util/sort.h | 10 + tools/perf/util/symbol.c | 4 + tools/perf/util/symbol_conf.h | 3 + tools/perf/util/time-utils.c | 8 + tools/perf/util/time-utils.h | 1 + 46 files changed, 1931 insertions(+), 287 deletions(-) create mode 100644 tools/perf/arch/x86/util/archinsn.c create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/branch.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/core.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/other.json create mode 100644 tools/perf/ui/browsers/res_sample.c create mode 100644 tools/perf/util/archinsn.h
Test results:
The first ones are container based builds of tools/perf with and without libelf support. Where clang is available, it is also used to build perf with/without libelf, and building with LIBCLANGLLVM=1 (built-in clang) with gcc and clang when clang and its devel libraries are installed.
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.
# export PERF_TARBALL=http://192.168.124.1/perf/perf-5.0.0.tar.xz 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:3.7 : Ok gcc (Alpine 6.4.0) 6.4.0 5 alpine:3.8 : Ok gcc (Alpine 6.4.0) 6.4.0 6 alpine:3.9 : Ok gcc (Alpine 8.2.0) 8.2.0 7 alpine:edge : Ok gcc (Alpine 8.2.0) 8.2.0 8 amazonlinux:1 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-28) 9 amazonlinux:2 : Ok gcc (GCC) 7.3.1 20180303 (Red Hat 7.3.1-5) 10 android-ndk:r12b-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 11 android-ndk:r15c-arm : Ok arm-linux-androideabi-gcc (GCC) 4.9.x 20150123 (prerelease) 12 centos:5 : Ok gcc (GCC) 4.1.2 20080704 (Red Hat 4.1.2-55) 13 centos:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23) 14 centos:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-36) 15 clearlinux:latest : Ok gcc (Clear Linux OS for Intel Architecture) 8.2.1 20180502 16 debian:7 : Ok gcc (Debian 4.7.2-5) 4.7.2 17 debian:8 : Ok gcc (Debian 4.9.2-10+deb8u2) 4.9.2 18 debian:9 : Ok gcc (Debian 6.3.0-18+deb9u1) 6.3.0 20170516 19 debian:experimental : Ok gcc (Debian 8.2.0-17) 8.2.1 20190204 20 debian:experimental-x-arm64 : Ok aarch64-linux-gnu-gcc (Debian 8.2.0-11) 8.2.0 21 debian:experimental-x-mips : Ok mips-linux-gnu-gcc (Debian 8.2.0-11) 8.2.0 22 debian:experimental-x-mips64 : Ok mips64-linux-gnuabi64-gcc (Debian 8.2.0-16) 8.2.0 23 fedora:20 : Ok gcc (GCC) 4.8.3 20140911 (Red Hat 4.8.3-7) 24 fedora:21 : Ok gcc (GCC) 4.9.2 20150212 (Red Hat 4.9.2-6) 25 fedora:22 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 26 fedora:23 : Ok gcc (GCC) 5.3.1 20160406 (Red Hat 5.3.1-6) 27 fedora:24 : Ok gcc (GCC) 6.3.1 20161221 (Red Hat 6.3.1-1) 28 fedora:24-x-ARC-uClibc : Ok arc-linux-gcc (ARCompact ISA Linux uClibc toolchain 2017.09-rc2) 7.1.1 20170710 29 fedora:25 : Ok gcc (GCC) 6.4.1 20170727 (Red Hat 6.4.1-1) 30 fedora:26 : Ok gcc (GCC) 7.3.1 20180130 (Red Hat 7.3.1-2) 31 fedora:27 : Ok gcc (GCC) 7.3.1 20180712 (Red Hat 7.3.1-6) 32 fedora:28 : Ok gcc (GCC) 8.2.1 20181215 (Red Hat 8.2.1-6) 33 fedora:29 : Ok gcc (GCC) 8.2.1 20181215 (Red Hat 8.2.1-6) 34 fedora:30 : Ok gcc (GCC) 9.0.1 20190203 (Red Hat 9.0.1-0.3) 35 fedora:rawhide : Ok gcc (GCC) 9.0.1 20190209 (Red Hat 9.0.1-0.4) 36 gentoo-stage3-amd64:latest : Ok gcc (Gentoo 7.3.0-r3 p1.4) 7.3.0 37 mageia:5 : Ok gcc (GCC) 4.9.2 38 mageia:6 : Ok gcc (Mageia 5.5.0-1.mga6) 5.5.0 39 opensuse:13.2 : Ok gcc (SUSE Linux) 4.8.3 20140627 [gcc-4_8-branch revision 212064] 40 opensuse:15.0 : Ok gcc (SUSE Linux) 7.3.1 20180323 [gcc-7-branch revision 258812] 41 opensuse:15.1 : Ok gcc (SUSE Linux) 7.4.0 42 opensuse:42.1 : Ok gcc (SUSE Linux) 4.8.5 43 opensuse:42.2 : Ok gcc (SUSE Linux) 4.8.5 44 opensuse:42.3 : Ok gcc (SUSE Linux) 4.8.5 45 opensuse:tumbleweed : Ok gcc (SUSE Linux) 8.2.1 20190103 [gcc-8-branch revision 267549] 46 oraclelinux:6 : Ok gcc (GCC) 4.4.7 20120313 (Red Hat 4.4.7-23.0.1) 47 oraclelinux:7 : Ok gcc (GCC) 4.8.5 20150623 (Red Hat 4.8.5-36.0.1) 48 ubuntu:12.04.5 : Ok gcc (Ubuntu/Linaro 4.6.3-1ubuntu5) 4.6.3 49 ubuntu:14.04.4 : Ok gcc (Ubuntu 4.8.4-2ubuntu1~14.04.4) 4.8.4 50 ubuntu:14.04.4-x-linaro-arm64 : Ok aarch64-linux-gnu-gcc (Linaro GCC 5.5-2017.10) 5.5.0 51 ubuntu:16.04 : Ok gcc (Ubuntu 5.4.0-6ubuntu1~16.04.11) 5.4.0 20160609 52 ubuntu:16.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 53 ubuntu:16.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 54 ubuntu:16.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 55 ubuntu:16.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 56 ubuntu:16.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu/IBM 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 57 ubuntu:16.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 5.4.0-6ubuntu1~16.04.9) 5.4.0 20160609 58 ubuntu:17.10 : Ok gcc (Ubuntu 7.2.0-8ubuntu3.2) 7.2.0 59 ubuntu:18.04 : Ok gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 60 ubuntu:18.04-x-arm : Ok arm-linux-gnueabihf-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0 61 ubuntu:18.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 7.3.0-27ubuntu1~18.04) 7.3.0 62 ubuntu:18.04-x-m68k : Ok m68k-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 63 ubuntu:18.04-x-powerpc : Ok powerpc-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 64 ubuntu:18.04-x-powerpc64 : Ok powerpc64-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 65 ubuntu:18.04-x-powerpc64el : Ok powerpc64le-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 66 ubuntu:18.04-x-riscv64 : Ok riscv64-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 67 ubuntu:18.04-x-s390 : Ok s390x-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 68 ubuntu:18.04-x-sh4 : Ok sh4-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 69 ubuntu:18.04-x-sparc64 : Ok sparc64-linux-gnu-gcc (Ubuntu 7.3.0-27ubuntu1~18.04) 7.3.0 70 ubuntu:18.10 : Ok gcc (Ubuntu 8.2.0-7ubuntu1) 8.2.0 71 ubuntu:19.04 : Ok gcc (Ubuntu 8.2.0-20ubuntu1) 8.2.0 72 ubuntu:19.04-x-alpha : Ok alpha-linux-gnu-gcc (Ubuntu 8.2.0-20ubuntu1) 8.2.0 73 ubuntu:19.04-x-arm64 : Ok aarch64-linux-gnu-gcc (Ubuntu/Linaro 8.2.0-20ubuntu1) 8.2.0 74 ubuntu:19.04-x-hppa : Ok hppa-linux-gnu-gcc (Ubuntu 8.2.0-20ubuntu1) 8.2.0 # # uname -a Linux quaco 5.0.0+ #1 SMP Thu Mar 7 10:32:55 -03 2019 x86_64 x86_64 x86_64 GNU/Linux # git log --oneline -1 dfcbc2f2994b tools lib bpf: Fix the build by adding a missing stdarg.h include # perf version --build-options perf version 5.0.gdfcbc2 dwarf: [ on ] # HAVE_DWARF_SUPPORT dwarf_getlocations: [ on ] # HAVE_DWARF_GETLOCATIONS_SUPPORT glibc: [ on ] # HAVE_GLIBC_SUPPORT gtk2: [ on ] # HAVE_GTK2_SUPPORT syscall_table: [ on ] # HAVE_SYSCALL_TABLE_SUPPORT libbfd: [ on ] # HAVE_LIBBFD_SUPPORT libelf: [ on ] # HAVE_LIBELF_SUPPORT libnuma: [ on ] # HAVE_LIBNUMA_SUPPORT numa_num_possible_cpus: [ on ] # HAVE_LIBNUMA_SUPPORT libperl: [ on ] # HAVE_LIBPERL_SUPPORT libpython: [ on ] # HAVE_LIBPYTHON_SUPPORT libslang: [ on ] # HAVE_SLANG_SUPPORT libcrypto: [ on ] # HAVE_LIBCRYPTO_SUPPORT libunwind: [ on ] # HAVE_LIBUNWIND_SUPPORT libdw-dwarf-unwind: [ on ] # HAVE_DWARF_SUPPORT zlib: [ on ] # HAVE_ZLIB_SUPPORT lzma: [ on ] # HAVE_LZMA_SUPPORT get_cpuid: [ on ] # HAVE_AUXTRACE_SUPPORT bpf: [ on ] # HAVE_LIBBPF_SUPPORT # 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: Breakpoint accounting : Ok 22: Watchpoint : 22.1: Read Only Watchpoint : Skip 22.2: Write Only Watchpoint : Ok 22.3: Read / Write Watchpoint : Ok 22.4: Modify Watchpoint : Ok 23: Number of exit events of a simple workload : Ok 24: Software clock events period values : Ok 25: Object code reading : Ok 26: Sample parsing : Ok 27: Use a dummy software event to keep tracking : Ok 28: Parse with no sample_id_all bit set : Ok 29: Filter hist entries : Ok 30: Lookup mmap thread : Ok 31: Share thread mg : Ok 32: Sort output of hist entries : Ok 33: Cumulate child hist entries : Ok 34: Track with sched_switch : Ok 35: Filter fds with revents mask in a fdarray : Ok 36: Add fd to a fdarray, making it autogrow : Ok 37: kmod_path__parse : Ok 38: Thread map : Ok 39: LLVM search and compile : 39.1: Basic BPF llvm compile : Ok 39.2: kbuild searching : Ok 39.3: Compile source for BPF prologue generation : Ok 39.4: Compile source for BPF relocation : Ok 40: Session topology : Ok 41: BPF filter : 41.1: Basic BPF filtering : Ok 41.2: BPF pinning : Ok 41.3: BPF prologue generation : Ok 41.4: BPF relocation checker : Ok 42: Synthesize thread map : Ok 43: Remove thread map : Ok 44: Synthesize cpu map : Ok 45: Synthesize stat config : Ok 46: Synthesize stat : Ok 47: Synthesize stat round : Ok 48: Synthesize attr update : Ok 49: Event times : Ok 50: Read backward ring buffer : Ok 51: Print cpu map : Ok 52: Probe SDT events : Ok 53: is_printable_array : Ok 54: Print bitmap : Ok 55: perf hooks : Ok 56: builtin clang support : Skip (not compiled in) 57: unit_number__scnprintf : Ok 58: mem2node : Ok 59: x86 rdpmc : Ok 60: Convert perf time to TSC : Ok 61: DWARF unwind : Ok 62: x86 instruction decoder - new instructions : Ok 63: x86 bp modify : Ok 64: probe libc's inet_pton & backtrace it with ping : Ok 65: Use vfs_getname probe to get syscall args filenames : Ok 66: Add vfs_getname probe to get syscall args filenames : Ok 67: Check open filename arg using perf trace + vfs_getname: Ok
$ make -C tools/perf build-test
make: Entering directory '/home/acme/git/perf/tools/perf'
- tarpkg: ./tests/perf-targz-src-pkg .
make_no_libnuma_O: make NO_LIBNUMA=1
make_clean_all_O: make clean all
make_no_auxtrace_O: make NO_AUXTRACE=1
make_no_newt_O: make NO_NEWT=1
make_no_backtrace_O: make NO_BACKTRACE=1
make_no_gtk2_O: make NO_GTK2=1
make_no_slang_O: make NO_SLANG=1
make_debug_O: make DEBUG=1
make_no_ui_O: make NO_NEWT=1 NO_SLANG=1 NO_GTK2=1
make_util_pmu_bison_o_O: make util/pmu-bison.o
make_no_libaudit_O: make NO_LIBAUDIT=1
make_install_prefix_O: make install prefix=/tmp/krava
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_no_libelf_O: make NO_LIBELF=1
make_help_O: make help
make_pure_O: make
make_static_O: make LDFLAGS=-static
make_no_scripts_O: make NO_LIBPYTHON=1 NO_LIBPERL=1
make_install_prefix_slash_O: make install prefix=/tmp/krava/
make_with_clangllvm_O: make LIBCLANGLLVM=1
make_install_bin_O: make install-bin
make_no_libunwind_O: make NO_LIBUNWIND=1
make_perf_o_O: make perf.o
make_no_libbpf_O: make NO_LIBBPF=1
make_no_libperl_O: make NO_LIBPERL=1
make_with_babeltrace_O: make LIBBABELTRACE=1
make_tags_O: make tags
make_install_O: make install
make_no_libbionic_O: make NO_LIBBIONIC=1
make_util_map_o_O: make util/map.o
make_no_libpython_O: make NO_LIBPYTHON=1
make_doc_O: make doc
make_cscope_O: make cscope
make_no_demangle_O: make NO_DEMANGLE=1
make_no_libdw_dwarf_unwind_O: make NO_LIBDW_DWARF_UNWIND=1
OK
make: Leaving directory '/home/acme/git/perf/tools/perf'
$Arnaldo Carvalho de Melo
maintainerPATCH 1/30 perf/core: Restore mmap record type correctly
From: Stephane Eranian <[email protected]>
On mmap(), perf_events generates a RECORD_MMAP record and then checks which events are interested in this record. There are currently 2 versions of mmap records: RECORD_MMAP and RECORD_MMAP2. MMAP2 is larger. The event configuration controls which version the user level tool accepts.
If the event->attr.mmap2=1 field then MMAP2 record is returned. The perf_event_mmap_output() takes care of this. It checks attr->mmap2 and corrects the record fields before putting it in the sampling buffer of the event. At the end the function restores the modified MMAP record fields.
The problem is that the function restores the size but not the type. Thus, if a subsequent event only accepts MMAP type, then it would instead receive an MMAP2 record with a size of MMAP record.
This patch fixes the problem by restoring the record type on exit.
--- kernel/events/core.c | 2 ++ 1 file changed, 2 insertions(+)
kernel/events/core.c +2 -0
@@ -7189,6 +7189,7 @@ static void perf_event_mmap_output(struct perf_event *event,struct perf_output_handle handle;struct perf_sample_data sample;int size = mmap_event->event_id.header.size; +u32 type = mmap_event->event_id.header.type;int ret;if (!perf_event_mmap_match (event, data))
@@ -7232,6 +7233,7 @@ static void perf_event_mmap_output(struct perf_event *event,perf_output_end (&handle); out: mmap_event->event_id.header.size = size; + mmap_event->event_id.header.type = type; }static void perf_event_mmap_event (struct perf_mmap_event *mmap_event)
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 2/30 perf script: Support insn output for normal samples
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
perf script -F +insn was only working for PT traces because the PT instruction decoder was filling in the insn/insn_len sample attributes. Support it for non PT samples too on x86 using the existing x86 instruction decoder.
This adds some extra checking to ensure that we don't try to decode instructions when using perf.data from a different architecture.
% perf record -a sleep 1 % perf script -F ip,sym,insn --xed ffffffff811704c9 remote_function movl %eax, 0x18(%rbx) ffffffff8100bb50 intel_bts_enable_local retq ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi) ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi) ffffffff81048612 native_apic_mem_write movl %esi, -0xa04000(%rdi) ffffffff810f1f79 generic_exec_single xor %eax, %eax ffffffff811704c9 remote_function movl %eax, 0x18(%rbx) ffffffff8100bb34 intel_bts_enable_local movl 0x2000(%rax), %edx ffffffff81048610 native_apic_mem_write mov %edi, %edi ...
Committer testing:
Before:
# perf script -F ip,sym,insn --xed | head -5 ffffffffa4068804 native_write_msr addb %al, (%rax) ffffffffa4068804 native_write_msr addb %al, (%rax) ffffffffa4068804 native_write_msr addb %al, (%rax) ffffffffa4068806 native_write_msr addb %al, (%rax) ffffffffa4068806 native_write_msr addb %al, (%rax) # perf script -F ip,sym,insn --xed | grep -v "addb %al, (%rax)" #
After:
# perf script -F ip,sym,insn --xed | head -5 ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) # perf script -F ip,sym,insn --xed | grep -v "addb %al, (%rax)" | head -5 ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068804 native_write_msr wrmsr ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) ffffffffa4068806 native_write_msr nopl %eax, (%rax,%rax,1) #
More examples:
# perf script -F ip,sym,insn --xed | grep -v native_write_msr | head ffffffffa416b90e tick_check_broadcast_expired btq %rax, 0x1a5f42a(%rip) ffffffffa4956bd0 nmi_cpu_backtrace pushq %r13 ffffffffa415b95e __hrtimer_next_event_base movq 0x18(%rax), %rdx ffffffffa4956bf3 nmi_cpu_backtrace popq %r12 ffffffffa4171d5c smp_call_function_single pause ffffffffa4956bdd nmi_cpu_backtrace mov %ebp, %r12d ffffffffa4797e4d menu_select cmp $0x190, %rax ffffffffa4171d5c smp_call_function_single pause ffffffffa405a7d8 nmi_cpu_backtrace_handler callq 0xffffffffa4956bd0 ffffffffa4797f7a menu_select shr $0x3, %rax #
Which matches the annotate output modulo resolving callqs:
# perf annotate --stdio2 nmi_cpu_backtrace_handler
Samples: 4 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 35908, [percent: local period]
nmi_cpu_backtrace_handler() /lib/modules/5.0.0+/build/vmlinux
Percent
Disassembly of section .text: ffffffff8105a7d0 <nmi_cpu_backtrace_handler>:
nmi_cpu_backtrace_handler():
nmi_trigger_cpumask_backtrace(mask, exclude_self,
nmi_raise_cpu_backtrace);
}
static int nmi_cpu_backtrace_handler(unsigned int cmd, struct pt_regs *regs)
{
24.45 → callq __fentry__
if (nmi_cpu_backtrace(regs))
mov %rsi,%rdi
75.55 → callq nmi_cpu_backtrace
return NMI_HANDLED;
movzbl %al,%eax
return NMI_DONE;
}
← retq
# # perf annotate --stdio2 __hrtimer_next_event_base
Samples: 4 of event 'cycles:ppp', 4000 Hz, Event count (approx.): 767977, [percent: local period]
__hrtimer_next_event_base() /lib/modules/5.0.0+/build/vmlinux
Percent
Disassembly of section .text: ffffffff8115b910 <__hrtimer_next_event_base>:
__hrtimer_next_event_base():
static ktime_t __hrtimer_next_event_base(struct hrtimer_cpu_base *cpu_base,
const struct hrtimer *exclude, unsigned int active, ktime_t expires_next)
{
→ callq __fentry__
<SNIP>
4a: add $0x1,%r14
77.31 mov 0x18(%rax),%rdx
shl $0x6,%r14
sub 0x38(%rbx,%r14,1),%rdx
if (expires < expires_next) {
cmp %r12,%rdx
↓ jge 68<SNIP>
--- tools/perf/arch/x86/util/Build | 1 + tools/perf/arch/x86/util/archinsn.c | 26 ++++++++++++++++++++++++++ tools/perf/builtin-script.c | 21 ++++++++++++++++++++- tools/perf/util/archinsn.h | 12 ++++++++++++ 4 files changed, 59 insertions(+), 1 deletion(-) create mode 100644 tools/perf/arch/x86/util/archinsn.c create mode 100644 tools/perf/util/archinsn.h
tools/perf/arch/x86/util/Build +1 -0
@@ -14,5 +14,6 @@ perf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o perf-$(CONFIG_AUXTRACE) += auxtrace.o +perf-$(CONFIG_AUXTRACE) += archinsn.o perf-$(CONFIG_AUXTRACE) += intel-pt.o perf-$(CONFIG_AUXTRACE) += intel-bts.o
tools/perf/arch/x86/util/archinsn.c new file +26 -0
@@ -0,0 +1,26 @@ +// SPDX-License-Identifier: GPL-2.0 +#include "perf.h" +#include "archinsn.h" +#include "util/intel-pt-decoder/insn.h" +#include "machine.h" +#include "thread.h" +#include "symbol.h" + +void arch_fetch_insn (struct perf_sample *sample, +struct thread *thread, +struct machine *machine) +{ +struct insn insn; +int len; +bool is64bit = false; + +if (!sample->ip) +return ; + len =thread__memcpy (thread, machine, sample->insn, sample->ip,sizeof (sample->insn), &is64bit); +if (len <=0 ) +return ; +insn_init (&insn, sample->insn, len, is64bit); +insn_get_length (&insn); +if (insn_complete (&insn) && insn.length <= len) + sample->insn_len = insn.length; +}
tools/perf/builtin-script.c +20 -1
@@ -29,10 +29,12 @@#include "util/time-utils.h" #include "util/path.h" #include "print_binary.h" +#include "archinsn.h" #include <linux/bitmap.h> #include <linux/kernel.h> #include <linux/stringify.h> #include <linux/time64.h> +#include <sys/utsname.h> #include "asm/bug.h" #include "util/mem-events.h" #include "util/dump-insn.h"
@@ -63,6 +65,7 @@ static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);static struct perf_stat_config stat_config;static int max_blocks; +static bool native_arch;unsigned int scripting_max_stack =PERF_MAX_STACK_DEPTH ;
@@ -1227,6 +1230,12 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,return len + dlen; } +__weak void arch_fetch_insn (struct perf_sample *sample__maybe_unused , +struct thread *thread__maybe_unused , +struct machine *machine__maybe_unused ) +{ +} + static int perf_sample__fprintf_insn(struct perf_sample *sample, struct perf_event_attr *attr, struct thread *thread,
@@ -1234,9 +1243,12 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample, {int printed =0 ; +if (sample->insn_len ==0 && native_arch) +arch_fetch_insn (sample, thread, machine); +if (PRINT_FIELD (INSNLEN )) printed +=fprintf (fp," ilen: %d" , sample->insn_len); -if (PRINT_FIELD (INSN )) { +if (PRINT_FIELD (INSN ) && sample->insn_len) {int i; printed +=fprintf (fp," insn:" );
@@ -3277,6 +3289,7 @@ int cmd_script(int argc, const char **argv) .set = false, .default_no_sample = true, }; +struct utsname uts;char *script_path =NULL ;const char **__argv;int i, j, err =0 ;
@@ -3615,6 +3628,12 @@ int cmd_script(int argc, const char **argv)if (symbol__init (&session->header.env) <0 ) goto out_delete; +uname (&uts); +if (!strcmp (uts.machine, session->header.env.arch) || + (!strcmp (uts.machine,"x86_64" ) && + !strcmp (session->header.env.arch,"i386" ))) + native_arch = true; + script.session = session;script__setup_sample_type (&script);
tools/perf/util/archinsn.h new file +12 -0
@@ -0,0 +1,12 @@ +#ifndef INSN_H +#define INSN_H 1 + +struct perf_sample ; +struct machine ; +struct thread ; + +void arch_fetch_insn (struct perf_sample *sample, +struct thread *thread, +struct machine *machine); + +#endif
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 3/30 perf report: Support output in nanoseconds
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Upcoming changes add timestamp output in perf report. Add a --ns argument similar to perf script to support nanoseconds resolution when needed.
--- tools/perf/Documentation/perf-report.txt | 3 +++ tools/perf/builtin-report.c | 1 + tools/perf/builtin-script.c | 11 +++++------ tools/perf/util/symbol.c | 1 + tools/perf/util/symbol_conf.h | 1 + 5 files changed, 11 insertions(+), 6 deletions(-)
tools/perf/Documentation/perf-report.txt +3 -0
@@ -477,6 +477,9 @@ include::itrace.txt[] Please note that not all mmaps are stored, options affecting which ones are include 'perf record --data', for instance. +--ns:: + Show time stamps in nanoseconds. + --stats:: Display overall events statistics without any further processing. (like the one at the end of the perf report -D command)
tools/perf/builtin-report.c +1 -0
@@ -1147,6 +1147,7 @@ int cmd_report(int argc, const char **argv)OPT_CALLBACK (0 ,"percent-type" , &report.annotation_opts,"local-period" ,"Set percent type local/global-period/hits" , annotate_parse_percent_type), +OPT_BOOLEAN (0 ,"ns" , &symbol_conf.nanosecs,"Show times in nanosecs" ),OPT_END () }; struct perf_data data = {
tools/perf/builtin-script.c +5 -6
@@ -60,7 +60,6 @@ static bool no_callchain;static bool latency_format;static bool system_wide;static bool print_flags; -static bool nanosecs;static const char *cpu_list; static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);static struct perf_stat_config stat_config;
@@ -691,7 +690,7 @@ static int perf_sample__fprintf_start(struct perf_sample *sample, secs = nsecs /NSEC_PER_SEC ; nsecs -= secs *NSEC_PER_SEC ; -if (nanosecs) +if (symbol_conf.nanosecs) printed +=fprintf (fp,"%5lu.%09llu: " , secs, nsecs);else {char sample_time[32 ];
@@ -3244,7 +3243,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused, {parse_output_fields (NULL ,"+insn,-event,-period" ,0 );itrace_parse_synth_opts (opt,"i0ns" ,0 ); - nanosecs = true; + symbol_conf.nanosecs = true;return 0 ; }
@@ -3262,7 +3261,7 @@ static int parse_call_trace(const struct option *opt __maybe_unused, {parse_output_fields (NULL ,"-ip,-addr,-event,-period,+callindent" ,0 );itrace_parse_synth_opts (opt,"cewp" ,0 ); - nanosecs = true; + symbol_conf.nanosecs = true;return 0 ; }
@@ -3272,7 +3271,7 @@ static int parse_callret_trace(const struct option *opt __maybe_unused, {parse_output_fields (NULL ,"-ip,-addr,-event,-period,+callindent,+flags" ,0 );itrace_parse_synth_opts (opt,"crewp" ,0 ); - nanosecs = true; + symbol_conf.nanosecs = true;return 0 ; }
@@ -3408,7 +3407,7 @@ int cmd_script(int argc, const char **argv)OPT_BOOLEAN ('f' ,"force" , &symbol_conf.force,"don't complain, do it" ),OPT_INTEGER (0 ,"max-blocks" , &max_blocks,"Maximum number of code blocks to dump with brstackinsn" ), -OPT_BOOLEAN (0 ,"ns" , &nanosecs, +OPT_BOOLEAN (0 ,"ns" , &symbol_conf.nanosecs,"Use 9 decimal places when displaying time" ), OPT_CALLBACK_OPTARG(0, "itrace", &itrace_synth_opts, NULL, "opts", "Instruction Tracing options\n" ITRACE_HELP,
tools/perf/util/symbol.c +1 -0
@@ -39,6 +39,7 @@ int vmlinux_path__nr_entries;char **vmlinux_path;struct symbol_conf symbol_conf = { + .nanosecs = false, .use_modules = true, .try_vmlinux_path = true, .demangle = true,
tools/perf/util/symbol_conf.h +1 -0
@@ -8,6 +8,7 @@ struct strlist;struct intlist ;struct symbol_conf { +bool nanosecs;unsigned short priv_size;bool try_vmlinux_path, init_annotation,
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 4/30 perf time-utils: Add utility function to print time stamps in nanoseconds
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add a utility function to print nanosecond timestamps.
--- tools/perf/util/time-utils.c | 8 ++++++++ tools/perf/util/time-utils.h | 1 + 2 files changed, 9 insertions(+)
tools/perf/util/time-utils.c +8 -0
@@ -453,6 +453,14 @@ int timestamp__scnprintf_usec(u64 timestamp, char *buf, size_t sz)return scnprintf (buf, sz,"%" PRIu64".%06" PRIu64, sec, usec); } +int timestamp__scnprintf_nsec (u64 timestamp,char *buf,size_t sz) +{ +u64 sec = timestamp /NSEC_PER_SEC , + nsec = timestamp %NSEC_PER_SEC ; + +return scnprintf (buf, sz,"%" PRIu64".%09" PRIu64, sec, nsec); +} +int fetch_current_timestamp (char *buf,size_t sz) {struct timeval tv;
tools/perf/util/time-utils.h +1 -0
@@ -30,6 +30,7 @@ int perf_time__parse_for_ranges(const char *str, struct perf_session *session, int *range_size, int *range_num);int timestamp__scnprintf_usec (u64 timestamp,char *buf,size_t sz); +int timestamp__scnprintf_nsec (u64 timestamp,char *buf,size_t sz);int fetch_current_timestamp (char *buf,size_t sz);
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 5/30 perf report: Parse time quantum
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Many workloads change over time. 'perf report' currently aggregates the whole time range reported in perf.data.
This patch adds an option for a time quantum to quantisize the perf.data over time.
This just adds the option, will be used in follow on patches for a time sort key.
--- tools/perf/Documentation/perf-report.txt | 4 +++ tools/perf/builtin-report.c | 42 ++++++++++++++++++++++++ tools/perf/util/symbol.c | 2 ++ tools/perf/util/symbol_conf.h | 1 + 4 files changed, 49 insertions(+)
tools/perf/Documentation/perf-report.txt +4 -0
@@ -497,6 +497,10 @@ include::itrace.txt[] The period/hits keywords set the base the percentage is computed on - the samples period or the number of samples (hits). +--time-quantum:: + Configure time quantum for time sort key. Default 100ms. + Accepts s, us, ms, ns units. + include::callchain-overhead-calculation.txt[] SEE ALSO
tools/perf/builtin-report.c +42 -0
63 lines not on this page · raw message
tools/perf/util/symbol.c +2 -0
@@ -6,6 +6,7 @@#include <string.h> #include <linux/kernel.h> #include <linux/mman.h> +#include <linux/time64.h> #include <sys/types.h> #include <sys/stat.h> #include <sys/param.h>
@@ -45,6 +46,7 @@ struct symbol_conf symbol_conf = { .demangle = true, .demangle_kernel = false, .cumulate_callchain = true, + .time_quantum = 100 * NSEC_PER_MSEC, /* 100ms */ .show_hist_headers = true, .symfs = "", .event_group = true,
tools/perf/util/symbol_conf.h +1 -0
@@ -56,6 +56,7 @@ struct symbol_conf { *sym_list_str, *col_width_list_str, *bt_stop_list_str; +unsigned long time_quantum;struct strlist *dso_list, *comm_list, *sym_list,
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 6/30 perf probe: Fix getting the kernel map
In reply to Arnaldo Carvalho de MeloFrom: Adrian Hunter <[email protected]>
Since commit 4d99e4136580 ("perf machine: Workaround missing maps for x86 PTI entry trampolines"), perf tools has been creating more than one kernel map, however 'perf probe' assumed there could be only one.
Fix by using machine__kernel_map() to get the main kernel map.
--- tools/perf/util/probe-event.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
tools/perf/util/probe-event.c +4 -2
@@ -160,8 +160,10 @@ static struct map *kernel_get_module_map(const char *module)if (module &&strchr (module,'/' ))return dso__new_map (module); -if (!module) - module ="kernel" ; +if (!module) { + pos =machine__kernel_map (host_machine); +return map__get (pos); + }for (pos =maps__first (maps); pos; pos =map__next (pos)) {/* short_name is "[module]" */
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 7/30 perf vendor events amd: perf PMU events for AMD Family 17h
In reply to Arnaldo Carvalho de MeloFrom: Martin Liška <[email protected]>
Thi patch adds PMC events for AMD Family 17 CPUs as defined in [1]. It covers events described in section: 2.1.13. Regex pattern in mapfile.csv covers all CPUs of the family.
[1] https://support.amd.com/TechDocs/54945_PPR_Family_17h_Models_00h-0Fh.pdf
--- .../pmu-events/arch/x86/amdfam17h/branch.json | 12 + .../pmu-events/arch/x86/amdfam17h/cache.json | 287 ++++++++++++++++++ .../pmu-events/arch/x86/amdfam17h/core.json | 134 ++++++++ .../arch/x86/amdfam17h/floating-point.json | 168 ++++++++++ .../pmu-events/arch/x86/amdfam17h/memory.json | 162 ++++++++++ .../pmu-events/arch/x86/amdfam17h/other.json | 65 ++++ tools/perf/pmu-events/arch/x86/mapfile.csv | 1 + 7 files changed, 829 insertions(+) create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/branch.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/cache.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/core.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/memory.json create mode 100644 tools/perf/pmu-events/arch/x86/amdfam17h/other.json
tools/perf/pmu-events/arch/x86/amdfam17h/branch.json new file +12 -0
@@ -0,0 +1,12 @@ +[ + { + "EventName": "bp_l1_btb_correct", + "EventCode": "0x8a", + "BriefDescription": "L1 BTB Correction." + }, + { + "EventName": "bp_l2_btb_correct", + "EventCode": "0x8b", + "BriefDescription": "L2 BTB Correction." + } +]
tools/perf/pmu-events/arch/x86/amdfam17h/cache.json new file +287 -0
287 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/amdfam17h/core.json new file +134 -0
134 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/amdfam17h/floating-point.json new file +168 -0
168 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/amdfam17h/memory.json new file +162 -0
162 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/amdfam17h/other.json new file +65 -0
65 lines not on this page · raw message
tools/perf/pmu-events/arch/x86/mapfile.csv +1 -0
@@ -33,3 +33,4 @@ GenuineIntel-6-25,v2,westmereep-sp,core GenuineIntel-6-2F,v2,westmereex,core GenuineIntel-6-55-[01234],v1,skylakex,core GenuineIntel-6-55-[56789ABCDEF],v1,cascadelakex,core +AuthenticAMD-23-[[:xdigit:]]+,v1,amdfam17h,core
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 8/30 perf data: Support having perf.data stored as a directory
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
The caller needs to set 'struct perf_data::is_dir flag and the path will be treated as a directory.
The 'struct perf_data::file' is initialized and open as 'path/header' file.
Add a check to the direcory interface functions to check the is_dir flag.
--- tools/perf/util/data.c | 49 ++++++++++++++++++++++++++++++++++++++- tools/perf/util/data.h | 6 +++++ tools/perf/util/session.c | 4 ++++ 3 files changed, 58 insertions(+), 1 deletion(-)
tools/perf/util/data.c +48 -1
@@ -34,6 +34,9 @@ int perf_data__create_dir(struct perf_data *data, int nr)struct perf_data_file *files =NULL ;int i, ret =-1 ; +if (WARN_ON (!data->is_dir)) +return -EINVAL ; + files =zalloc (nr *sizeof (*files));if (!files)return -ENOMEM ;
@@ -69,6 +72,9 @@ int perf_data__open_dir(struct perf_data *data)DIR *dir;int nr =0 ; +if (WARN_ON (!data->is_dir)) +return -EINVAL ; + dir =opendir (data->path);if (!dir)return -EINVAL ;
@@ -173,6 +179,16 @@ static int check_backup(struct perf_data *data)return 0 ; } +static bool is_dir (struct perf_data *data) +{ +struct stat st; + +if (stat (data->path, &st)) +return false; + +return (st.st_mode &S_IFMT ) ==S_IFDIR ; +} +static int open_file_read (struct perf_data *data) {struct stat st;
@@ -254,6 +270,30 @@ static int open_file_dup(struct perf_data *data)return open_file (data); } +static int open_dir (struct perf_data *data) +{ +int ret; + +/* +* So far we open only the header, so we can read the data version and +* layout. +*/ +if (asprintf (&data->file.path,"%s/header" , data->path) <0 ) +return -1 ; + +if (perf_data__is_write (data) && +mkdir (data->path,S_IRWXU ) <0 ) +return -1 ; + + ret =open_file (data); + +/* Cleanup whatever we managed to create so far. */ +if (ret &&perf_data__is_write (data)) +rm_rf_perf_data (data->path); + +return ret; +} +int perf_data__open (struct perf_data *data) {if (check_pipe (data))
@@ -265,11 +305,18 @@ int perf_data__open(struct perf_data *data)if (check_backup (data))return -1 ; -return open_file_dup (data); +if (perf_data__is_read (data)) + data->is_dir =is_dir (data); + +return perf_data__is_dir (data) ? +open_dir (data) :open_file_dup (data); }void perf_data__close (struct perf_data *data) { +if (perf_data__is_dir (data)) +perf_data__close_dir (data); +zfree (&data->file.path);close (data->file.fd); }
tools/perf/util/data.h +6 -0
@@ -19,6 +19,7 @@ struct perf_data {const char *path;struct perf_data_file file;bool is_pipe; +bool is_dir;bool force;enum perf_data_mode mode;
@@ -43,6 +44,11 @@ static inline int perf_data__is_pipe(struct perf_data *data)return data->is_pipe; } +static inline bool perf_data__is_dir (struct perf_data *data) +{ +return data->is_dir; +} +static inline int perf_data__fd (struct perf_data *data) {return data->file.fd;
tools/perf/util/session.c +4 -0
@@ -152,6 +152,10 @@ struct perf_session *perf_session__new(struct perf_data *data, }perf_evlist__init_trace_event_sample_raw (session->evlist); + +/* Open the directory data. */ +if (data->is_dir &&perf_data__open_dir (data)) + goto out_delete; } }else { session->machines.host.env = &perf_env;
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 9/30 perf data: Don't store auxtrace index for directory data file
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
We can't store the auxtrace index when we store into multiple files, because we keep only offset for it, not the file.
The auxtrace data will be processed correctly in the 'pipe' mode.
--- tools/perf/builtin-record.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/perf/builtin-record.c +1 -1
@@ -392,7 +392,7 @@ static int record__process_auxtrace(struct perf_tool *tool,size_t padding;u8 pad[8 ] = {0 }; -if (!perf_data__is_pipe (data)) { +if (!perf_data__is_pipe (data) && !perf_data__is_dir (data)) {off_t file_offset;int fd =perf_data__fd (data);int err;
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 10/30 perf data: Add perf_data__update_dir() function
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Add perf_data__update_dir() to update the size for every file within the perf.data directory.
--- tools/perf/util/data.c | 20 ++++++++++++++++++++ tools/perf/util/data.h | 1 + 2 files changed, 21 insertions(+)
tools/perf/util/data.c +20 -0
@@ -124,6 +124,26 @@ int perf_data__open_dir(struct perf_data *data)return ret; } +int perf_data__update_dir (struct perf_data *data) +{ +int i; + +if (WARN_ON (!data->is_dir)) +return -EINVAL ; + +for (i =0 ; i < data->dir.nr; i++) { +struct perf_data_file *file = &data->dir.files[i]; +struct stat st; + +if (fstat (file->fd, &st)) +return -1 ; + + file->size = st.st_size; + } + +return 0 ; +} +static bool check_pipe (struct perf_data *data) {struct stat st;
tools/perf/util/data.h +1 -0
@@ -79,4 +79,5 @@ int perf_data__switch(struct perf_data *data,int perf_data__create_dir (struct perf_data *data,int nr);int perf_data__open_dir (struct perf_data *data);void perf_data__close_dir (struct perf_data *data); +int perf_data__update_dir (struct perf_data *data);#endif /* __PERF_DATA_H */
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 11/30 perf data: Make perf_data__size() work over directory
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Make perf_data__size() return proper size for directory data, summing up all the individual file sizes.
--- tools/perf/util/data.c | 17 +++++++++++++++++ tools/perf/util/data.h | 6 +----- 2 files changed, 18 insertions(+), 5 deletions(-)
tools/perf/util/data.c +17 -0
@@ -393,3 +393,20 @@ int perf_data__switch(struct perf_data *data,free (new_filepath);return ret; } + +unsigned long perf_data__size (struct perf_data *data) +{ +u64 size = data->file.size; +int i; + +if (!data->is_dir) +return size; + +for (i =0 ; i < data->dir.nr; i++) { +struct perf_data_file *file = &data->dir.files[i]; + + size += file->size; + } + +return size; +}
tools/perf/util/data.h +1 -5
@@ -54,11 +54,6 @@ static inline int perf_data__fd(struct perf_data *data)return data->file.fd; } -static inline unsigned long perf_data__size (struct perf_data *data) -{ -return data->file.size; -} -int perf_data__open (struct perf_data *data);void perf_data__close (struct perf_data *data); ssize_t perf_data__write(struct perf_data *data,
@@ -80,4 +75,5 @@ int perf_data__create_dir(struct perf_data *data, int nr);int perf_data__open_dir (struct perf_data *data);void perf_data__close_dir (struct perf_data *data);int perf_data__update_dir (struct perf_data *data); +unsigned long perf_data__size (struct perf_data *data);#endif /* __PERF_DATA_H */
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 12/30 perf header: Add DIR_FORMAT feature to describe directory data
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
The data files layout is described by HEADER_DIR_FORMAT feature. Currently it holds only version number (1):
uint64_t version;
The current version holds only version value (1) means that data files:
- Follow the 'data.*' name format.
- Contain raw events data in standard perf format as read from kernel (and need to be sorted)
Future versions are expected to describe different data files layout according to special needs.
--- tools/perf/builtin-record.c | 2 ++ tools/perf/util/data.c | 10 +++++++-- tools/perf/util/data.h | 1 + tools/perf/util/header.c | 44 ++++++++++++++++++++++++++++++++++++- tools/perf/util/header.h | 5 +++++ 5 files changed, 59 insertions(+), 3 deletions(-)
tools/perf/builtin-record.c +2 -0
@@ -837,6 +837,8 @@ static void record__init_features(struct record *rec)if (!(rec->opts.use_clockid && rec->opts.clockid_res_ns))perf_header__clear_feat (&session->header,HEADER_CLOCKID ); +perf_header__clear_feat (&session->header,HEADER_DIR_FORMAT ); +perf_header__clear_feat (&session->header,HEADER_STAT ); }
tools/perf/util/data.c +8 -2
@@ -14,6 +14,7 @@#include "data.h" #include "util.h" #include "debug.h" +#include "header.h" static void close_dir (struct perf_data_file *files,int nr) {
@@ -41,8 +42,9 @@ int perf_data__create_dir(struct perf_data *data, int nr)if (!files)return -ENOMEM ; - data->dir.files = files; - data->dir.nr = nr; + data->dir.version =PERF_DIR_VERSION ; + data->dir.files = files; + data->dir.nr = nr;for (i =0 ; i < nr; i++) {struct perf_data_file *file = &files[i];
@@ -75,6 +77,10 @@ int perf_data__open_dir(struct perf_data *data)if (WARN_ON (!data->is_dir))return -EINVAL ; +/* The version is provided by DIR_FORMAT feature. */ +if (WARN_ON (data->dir.version !=PERF_DIR_VERSION )) +return -1 ; + dir =opendir (data->path);if (!dir)return -EINVAL ;
tools/perf/util/data.h +1 -0
@@ -24,6 +24,7 @@ struct perf_data {enum perf_data_mode mode;struct { +u64 version;struct perf_data_file *files;int nr; } dir;
tools/perf/util/header.c +43 -1
68 lines not on this page · raw message
tools/perf/util/header.h +5 -0
@@ -39,6 +39,7 @@ enum {HEADER_SAMPLE_TIME ,HEADER_MEM_TOPOLOGY ,HEADER_CLOCKID , +HEADER_DIR_FORMAT ,HEADER_LAST_FEATURE , HEADER_FEAT_BITS = 256, };
@@ -48,6 +49,10 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; +enum perf_dir_version { +PERF_DIR_VERSION =1 , +}; +struct perf_file_section {u64 offset;u64 size;
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 13/30 perf session: Add process callback to reader object
In reply to Arnaldo Carvalho de MeloFrom: Jiri Olsa <[email protected]>
Adding callback function to reader object so callers can process data in different ways.
--- tools/perf/util/session.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-)
tools/perf/util/session.c +19 -4
@@ -1847,10 +1847,17 @@ fetch_mmaped_event(struct perf_session *session,#define NUM_MMAPS 128#endif +struct reader ; + +typedef s64 (*reader_cb_t )(struct perf_session *session, +union perf_event *event, +u64 file_offset); +struct reader { -int fd; -u64 data_size; -u64 data_offset; +int fd; +u64 data_size; +u64 data_offset; +reader_cb_t process; }; static int
@@ -1921,7 +1928,7 @@ reader__process_events(struct reader *rd, struct perf_session *session, size = event->header.size;if (size <sizeof (struct perf_event_header ) || - (skip =perf_session__process_event (session, event, file_pos)) <0 ) { + (skip = rd->process (session, event, file_pos)) <0 ) {pr_err ("%#" PRIx64" [%#x]: failed to process type: %d\n" , file_offset + head, event->header.size, event->header.type);
@@ -1947,12 +1954,20 @@ reader__process_events(struct reader *rd, struct perf_session *session,return err; } +static s64 process_simple (struct perf_session *session, +union perf_event *event, +u64 file_offset) +{ +return perf_session__process_event (session, event, file_offset); +} +static int __perf_session__process_events (struct perf_session *session) {struct reader rd = { .fd =perf_data__fd (session->data), .data_size = session->header.data_size, .data_offset = session->header.data_offset, + .process = process_simple, };struct ordered_events *oe = &session->ordered_events;struct perf_tool *tool = session->tool;
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 14/30 perf report: Use less for scripts output
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
The UI viewer for scripts output has a lot of limitations: limited size, no search or save function, slow, and various other issues.
Just use 'less' to display directly on the terminal instead.
This won't work in GTK mode, but GTK doesn't support these context menus anyways. If that is ever done could use an terminal for the output.
--- tools/perf/ui/browsers/scripts.c | 130 ++++--------------------------- 1 file changed, 17 insertions(+), 113 deletions(-)
tools/perf/ui/browsers/scripts.c +17 -113
@@ -1,35 +1,12 @@// SPDX-License-Identifier: GPL-2.0 -#include <elf.h> -#include <inttypes.h> -#include <sys/ttydefaults.h> -#include <string.h> #include "../../util/sort.h" #include "../../util/util.h" #include "../../util/hist.h" #include "../../util/debug.h" #include "../../util/symbol.h" #include "../browser.h" -#include "../helpline.h" #include "../libslang.h" -/* 2048 lines should be enough for a script output */ -#define MAX_LINES 2048 - -/* 160 bytes for one output line */ -#define AVERAGE_LINE_LEN 160 - -struct script_line { -struct list_head node; -char line[AVERAGE_LINE_LEN ]; -}; - -struct perf_script_browser { -struct ui_browser b; -struct list_head entries; -const char *script_name; -int nr_lines; -}; -#define SCRIPT_NAMELEN 128#define SCRIPT_MAX_NO 64/*
@@ -73,69 +50,29 @@ static int list_scripts(char *script_name)return ret; } -static void script_browser__write (struct ui_browser *browser, -void *entry,int row) +static void run_script (char *cmd) { - struct script_line *sline = list_entry(entry, struct script_line, node); -bool current_entry =ui_browser__is_current_entry (browser, row); - -ui_browser__set_color (browser, current_entry ?HE_COLORSET_SELECTED : -HE_COLORSET_NORMAL ); - -ui_browser__write_nstring (browser, sline->line, browser->width); +pr_debug ("Running %s\n" , cmd); +SLang_reset_tty (); +if (system (cmd) <0 ) +pr_warning ("Cannot run %s\n" , cmd); +/* +* SLang doesn't seem to reset the whole terminal, so be more +* forceful to get back to the original state. +*/ +printf ("\033[c\033[H\033[J" ); +fflush (stdout); +SLang_init_tty (0 ,0 ,0 ); +SLsmg_refresh (); } -static int script_browser__run (struct perf_script_browser *browser) -{ -int key; - -if (ui_browser__show (&browser->b, browser->script_name, -"Press ESC to exit" ) <0 ) -return -1 ; - -while (1 ) { - key =ui_browser__run (&browser->b,0 ); - -/* We can add some special key handling here if needed */ -break ; - } - -ui_browser__hide (&browser->b); -return key; -} - -int script_browse (const char *script_opt) {char cmd[SCRIPT_FULLPATH_LEN *2 ], script_name[SCRIPT_FULLPATH_LEN ]; -char *line =NULL ; -size_t len =0 ; -ssize_t retlen; -int ret =-1 , nr_entries =0 ; -FILE *fp; -void *buf; -struct script_line *sline; - -struct perf_script_browser script = { - .b = { - .refresh = ui_browser__list_head_refresh, - .seek = ui_browser__list_head_seek, - .write = script_browser__write, - }, - .script_name = script_name, - }; - -INIT_LIST_HEAD (&script.entries); - -/* Save each line of the output in one struct script_line object. */ - buf =zalloc ((sizeof (*sline)) *MAX_LINES ); -if (!buf) -return -1 ; - sline = buf;memset (script_name,0 ,SCRIPT_FULLPATH_LEN );if (list_scripts (script_name)) - goto exit; +return -1 ;sprintf (cmd,"perf script -s %s " , script_name);
@@ -147,42 +84,9 @@ int script_browse(const char *script_opt)strcat (cmd, input_name); } -strcat (cmd," 2>&1" ); - - fp =popen (cmd,"r" ); -if (!fp) - goto exit; - -while ((retlen =getline (&line, &len, fp)) !=-1 ) { -strncpy (sline->line, line,AVERAGE_LINE_LEN ); - -/* If one output line is very large, just cut it short */ -if (retlen >=AVERAGE_LINE_LEN ) { - sline->line[AVERAGE_LINE_LEN -1 ] ='\0' ; - sline->line[AVERAGE_LINE_LEN -2 ] ='\n' ; - } -list_add_tail (&sline->node, &script.entries); - -if (script.b.width < retlen) - script.b.width = retlen; - -if (nr_entries++ >=MAX_LINES -1 ) -break ; - sline++; - } - -if (script.b.width >AVERAGE_LINE_LEN ) - script.b.width =AVERAGE_LINE_LEN ; - -free (line); -pclose (fp); +strcat (cmd," 2>&1 | less" ); - script.nr_lines = nr_entries; - script.b.nr_entries = nr_entries; - script.b.entries = &script.entries; +run_script (cmd); - ret =script_browser__run (&script); -exit: -free (buf); -return ret; +return 0 ; }
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 15/30 perf script python: Add Python3 support to exported-sql-viewer.py
In reply to Arnaldo Carvalho de MeloFrom: Tony Jones <[email protected]>
Support both Python2 and Python3 in the exported-sql-viewer.py script.
The use of 'from __future__' implies the minimum supported Python2 version is now v2.6
--- .../scripts/python/exported-sql-viewer.py | 42 ++++++++++++------- 1 file changed, 28 insertions(+), 14 deletions(-)
tools/perf/scripts/python/exported-sql-viewer.py +28 -14
@@ -88,11 +88,20 @@ # 7fab593ea956 48 89 15 3b 13 22 00 movq %rdx, 0x22133b(%rip) # 8107675243232 2 ls 22011 22011 hardware interrupt No 7fab593ea956 _dl_start+0x26 (ld-2.19.so) -> ffffffff86a012e0 page_fault ([kernel]) +from __future__ import print_function + import sys import weakref import threading import string -import cPickle +try: + # Python2 + import cPickle as pickle + # size of pickled integer big enough for record size + glb_nsz = 8 +except ImportError: + import pickle + glb_nsz = 16 import re import os from PySide.QtCore import *
@@ -102,6 +111,15 @@ from decimal import * from ctypes import * from multiprocessing import Process, Array, Value, Event +# xrange is range in Python3 +try: + xrange +except NameError: + xrange = range + +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + # Data formatting helpers def tohex(ip):
@@ -1004,10 +1022,6 @@ class ChildDataItemFinder(): glb_chunk_sz = 10000 -# size of pickled integer big enough for record size - -glb_nsz = 8 - # Background process for SQL data fetcher class SQLFetcherProcess():
@@ -1066,7 +1080,7 @@ class SQLFetcherProcess(): return True if space >= glb_nsz: # Use 0 (or space < glb_nsz) to mean there is no more at the top of the buffer - nd = cPickle.dumps(0, cPickle.HIGHEST_PROTOCOL) + nd = pickle.dumps(0, pickle.HIGHEST_PROTOCOL) self.buffer[self.local_head : self.local_head + len(nd)] = nd self.local_head = 0 if self.local_tail - self.local_head > sz:
@@ -1084,9 +1098,9 @@ class SQLFetcherProcess(): self.wait_event.wait() def AddToBuffer(self, obj): - d = cPickle.dumps(obj, cPickle.HIGHEST_PROTOCOL) + d = pickle.dumps(obj, pickle.HIGHEST_PROTOCOL) n = len(d) - nd = cPickle.dumps(n, cPickle.HIGHEST_PROTOCOL) + nd = pickle.dumps(n, pickle.HIGHEST_PROTOCOL) sz = n + glb_nsz self.WaitForSpace(sz) pos = self.local_head
@@ -1198,12 +1212,12 @@ class SQLFetcher(QObject): pos = self.local_tail if len(self.buffer) - pos < glb_nsz: pos = 0 - n = cPickle.loads(self.buffer[pos : pos + glb_nsz]) + n = pickle.loads(self.buffer[pos : pos + glb_nsz]) if n == 0: pos = 0 - n = cPickle.loads(self.buffer[0 : glb_nsz]) + n = pickle.loads(self.buffer[0 : glb_nsz]) pos += glb_nsz - obj = cPickle.loads(self.buffer[pos : pos + n]) + obj = pickle.loads(self.buffer[pos : pos + n]) self.local_tail = pos + n return obj
@@ -2973,7 +2987,7 @@ class DBRef(): def Main(): if (len(sys.argv) < 2): - print >> sys.stderr, "Usage is: exported-sql-viewer.py {<database name> | --help-only}" + printerr("Usage is: exported-sql-viewer.py {<database name> | --help-only}"); raise Exception("Too few arguments") dbname = sys.argv[1]
@@ -2986,8 +3000,8 @@ def Main(): is_sqlite3 = False try: - f = open(dbname) - if f.read(15) == "SQLite format 3": + f = open(dbname, "rb") + if f.read(15) == b'SQLite format 3': is_sqlite3 = True f.close() except:
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 16/30 perf script python: Add Python3 support to export-to-postgresql.py
In reply to Arnaldo Carvalho de MeloFrom: Tony Jones <[email protected]>
Support both Python2 and Python3 in the export-to-postgresql.py script.
The use of 'from __future__' implies the minimum supported Python2 version is now v2.6
--- .../scripts/python/export-to-postgresql.py | 58 +++++++++++++------ 1 file changed, 41 insertions(+), 17 deletions(-)
tools/perf/scripts/python/export-to-postgresql.py +41 -17
@@ -10,6 +10,8 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. +from __future__ import print_function + import os import sys import struct
@@ -199,6 +201,18 @@ import datetime from PySide.QtSql import * +if sys.version_info < (3, 0): + def toserverstr(str): + return str + def toclientstr(str): + return str +else: + # Assume UTF-8 server_encoding and client_encoding + def toserverstr(str): + return bytes(str, "UTF_8") + def toclientstr(str): + return bytes(str, "UTF_8") + # Need to access PostgreSQL C library directly to use COPY FROM STDIN from ctypes import * libpq = CDLL("libpq.so.5")
@@ -234,12 +248,14 @@ perf_db_export_mode = True perf_db_export_calls = False perf_db_export_callchains = False +def printerr(*args, **kw_args): + print(*args, file=sys.stderr, **kw_args) def usage(): - print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]") + printerr("where: columns 'all' or 'branches'") + printerr(" calls 'calls' => create calls and call_paths table") + printerr(" callchains 'callchains' => create call_paths table") raise Exception("Too few arguments") if (len(sys.argv) < 2):
@@ -273,7 +289,7 @@ def do_query(q, s): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +print(datetime.datetime.today(), "Creating database...") db = QSqlDatabase.addDatabase('QPSQL') query = QSqlQuery(db)
@@ -506,12 +522,12 @@ do_query(query, 'CREATE VIEW samples_view AS ' ' FROM samples') -file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0) -file_trailer = "\377\377" +file_header = struct.pack("!11sii", b"PGCOPY\n\377\r\n\0", 0, 0) +file_trailer = b"\377\377" def open_output_file(file_name): path_name = output_dir_name + "/" + file_name - file = open(path_name, "w+") + file = open(path_name, "wb+") file.write(file_header) return file
@@ -526,13 +542,13 @@ def copy_output_file_direct(file, table_name): # Use COPY FROM STDIN because security may prevent postgres from accessing the files directly def copy_output_file(file, table_name): - conn = PQconnectdb("dbname = " + dbname) + conn = PQconnectdb(toclientstr("dbname = " + dbname)) if (PQstatus(conn)): raise Exception("COPY FROM STDIN PQconnectdb failed") file.write(file_trailer) file.seek(0) sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')" - res = PQexec(conn, sql) + res = PQexec(conn, toclientstr(sql)) if (PQresultStatus(res) != 4): raise Exception("COPY FROM STDIN PQexec failed") data = file.read(65536)
@@ -566,7 +582,7 @@ if perf_db_export_calls: call_file = open_output_file("call_table.bin") def trace_begin(): - print datetime.datetime.today(), "Writing to intermediate files..." + print(datetime.datetime.today(), "Writing to intermediate files...") # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown") machine_table(0, 0, "unknown")
@@ -582,7 +598,7 @@ def trace_begin(): unhandled_count = 0 def trace_end(): - print datetime.datetime.today(), "Copying to database..." + print(datetime.datetime.today(), "Copying to database...") copy_output_file(evsel_file, "selected_events") copy_output_file(machine_file, "machines") copy_output_file(thread_file, "threads")
@@ -597,7 +613,7 @@ def trace_end(): if perf_db_export_calls: copy_output_file(call_file, "calls") - print datetime.datetime.today(), "Removing intermediate files..." + print(datetime.datetime.today(), "Removing intermediate files...") remove_output_file(evsel_file) remove_output_file(machine_file) remove_output_file(thread_file)
@@ -612,7 +628,7 @@ def trace_end(): if perf_db_export_calls: remove_output_file(call_file) os.rmdir(output_dir_name) - print datetime.datetime.today(), "Adding primary keys" + print(datetime.datetime.today(), "Adding primary keys") do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE machines ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE threads ADD PRIMARY KEY (id)')
@@ -627,7 +643,7 @@ def trace_end(): if perf_db_export_calls: do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)') - print datetime.datetime.today(), "Adding foreign keys" + print(datetime.datetime.today(), "Adding foreign keys") do_query(query, 'ALTER TABLE threads ' 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' 'ADD CONSTRAINT processfk FOREIGN KEY (process_id) REFERENCES threads (id)')
@@ -663,8 +679,8 @@ def trace_end(): do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" - print datetime.datetime.today(), "Done" + print(datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events") + print(datetime.datetime.today(), "Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count
@@ -674,12 +690,14 @@ def sched__sched_switch(*x): pass def evsel_table(evsel_id, evsel_name, *x): + evsel_name = toserverstr(evsel_name) n = len(evsel_name) fmt = "!hiqi" + str(n) + "s" value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name) evsel_file.write(value) def machine_table(machine_id, pid, root_dir, *x): + root_dir = toserverstr(root_dir) n = len(root_dir) fmt = "!hiqiii" + str(n) + "s" value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir)
@@ -690,6 +708,7 @@ def thread_table(thread_id, machine_id, process_id, pid, tid, *x): thread_file.write(value) def comm_table(comm_id, comm_str, *x): + comm_str = toserverstr(comm_str) n = len(comm_str) fmt = "!hiqi" + str(n) + "s" value = struct.pack(fmt, 2, 8, comm_id, n, comm_str)
@@ -701,6 +720,9 @@ def comm_thread_table(comm_thread_id, comm_id, thread_id, *x): comm_thread_file.write(value) def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): + short_name = toserverstr(short_name) + long_name = toserverstr(long_name) + build_id = toserverstr(build_id) n1 = len(short_name) n2 = len(long_name) n3 = len(build_id)
@@ -709,12 +731,14 @@ def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x): dso_file.write(value) def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x): + symbol_name = toserverstr(symbol_name) n = len(symbol_name) fmt = "!hiqiqiqiqiii" + str(n) + "s" value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name) symbol_file.write(value) def branch_type_table(branch_type, name, *x): + name = toserverstr(name) n = len(name) fmt = "!hiii" + str(n) + "s" value = struct.pack(fmt, 2, 4, branch_type, n, name)
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 17/30 perf script python: Add Python3 support to export-to-sqlite.py
In reply to Arnaldo Carvalho de MeloFrom: Tony Jones <[email protected]>
Support both Python2 and Python3 in the export-to-sqlite.py script
The use of 'from __future__' implies the minimum supported Python2 version is now v2.6
--- tools/perf/scripts/python/export-to-sqlite.py | 23 +++++++++++-------- 1 file changed, 14 insertions(+), 9 deletions(-)
tools/perf/scripts/python/export-to-sqlite.py +14 -9
@@ -10,6 +10,8 @@ # FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for # more details. +from __future__ import print_function + import os import sys import struct
@@ -60,11 +62,14 @@ perf_db_export_mode = True perf_db_export_calls = False perf_db_export_callchains = False +def printerr(*args, **keyword_args): + print(*args, file=sys.stderr, **keyword_args) + def usage(): - print >> sys.stderr, "Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]" - print >> sys.stderr, "where: columns 'all' or 'branches'" - print >> sys.stderr, " calls 'calls' => create calls and call_paths table" - print >> sys.stderr, " callchains 'callchains' => create call_paths table" + printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]"); + printerr("where: columns 'all' or 'branches'"); + printerr(" calls 'calls' => create calls and call_paths table"); + printerr(" callchains 'callchains' => create call_paths table"); raise Exception("Too few arguments") if (len(sys.argv) < 2):
@@ -100,7 +105,7 @@ def do_query_(q): return raise Exception("Query failed: " + q.lastError().text()) -print datetime.datetime.today(), "Creating database..." +print(datetime.datetime.today(), "Creating database ...") db_exists = False try:
@@ -378,7 +383,7 @@ if perf_db_export_calls: call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") def trace_begin(): - print datetime.datetime.today(), "Writing records..." + print(datetime.datetime.today(), "Writing records...") do_query(query, 'BEGIN TRANSACTION') # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown")
@@ -397,14 +402,14 @@ unhandled_count = 0 def trace_end(): do_query(query, 'END TRANSACTION') - print datetime.datetime.today(), "Adding indexes" + print(datetime.datetime.today(), "Adding indexes") if perf_db_export_calls: do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events" - print datetime.datetime.today(), "Done" + print(datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events") + print(datetime.datetime.today(), "Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 18/30 perf script python: Add printdate function to SQL exporters
In reply to Arnaldo Carvalho de MeloFrom: Tony Jones <[email protected]>
Introduce a printdate function to eliminate the repetitive use of datetime.datetime.today() in the SQL exporting scripts.
--- .../scripts/python/export-to-postgresql.py | 19 +++++++++++-------- tools/perf/scripts/python/export-to-sqlite.py | 13 ++++++++----- 2 files changed, 19 insertions(+), 13 deletions(-)
tools/perf/scripts/python/export-to-postgresql.py +11 -8
@@ -251,6 +251,9 @@ perf_db_export_callchains = False def printerr(*args, **kw_args): print(*args, file=sys.stderr, **kw_args) +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) + def usage(): printerr("Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>] [<callchains>]") printerr("where: columns 'all' or 'branches'")
@@ -289,7 +292,7 @@ def do_query(q, s): return raise Exception("Query failed: " + q.lastError().text()) -print(datetime.datetime.today(), "Creating database...") +printdate("Creating database...") db = QSqlDatabase.addDatabase('QPSQL') query = QSqlQuery(db)
@@ -582,7 +585,7 @@ if perf_db_export_calls: call_file = open_output_file("call_table.bin") def trace_begin(): - print(datetime.datetime.today(), "Writing to intermediate files...") + printdate("Writing to intermediate files...") # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown") machine_table(0, 0, "unknown")
@@ -598,7 +601,7 @@ def trace_begin(): unhandled_count = 0 def trace_end(): - print(datetime.datetime.today(), "Copying to database...") + printdate("Copying to database...") copy_output_file(evsel_file, "selected_events") copy_output_file(machine_file, "machines") copy_output_file(thread_file, "threads")
@@ -613,7 +616,7 @@ def trace_end(): if perf_db_export_calls: copy_output_file(call_file, "calls") - print(datetime.datetime.today(), "Removing intermediate files...") + printdate("Removing intermediate files...") remove_output_file(evsel_file) remove_output_file(machine_file) remove_output_file(thread_file)
@@ -628,7 +631,7 @@ def trace_end(): if perf_db_export_calls: remove_output_file(call_file) os.rmdir(output_dir_name) - print(datetime.datetime.today(), "Adding primary keys") + printdate("Adding primary keys") do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE machines ADD PRIMARY KEY (id)') do_query(query, 'ALTER TABLE threads ADD PRIMARY KEY (id)')
@@ -643,7 +646,7 @@ def trace_end(): if perf_db_export_calls: do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)') - print(datetime.datetime.today(), "Adding foreign keys") + printdate("Adding foreign keys") do_query(query, 'ALTER TABLE threads ' 'ADD CONSTRAINT machinefk FOREIGN KEY (machine_id) REFERENCES machines (id),' 'ADD CONSTRAINT processfk FOREIGN KEY (process_id) REFERENCES threads (id)')
@@ -679,8 +682,8 @@ def trace_end(): do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print(datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events") - print(datetime.datetime.today(), "Done") + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count
tools/perf/scripts/python/export-to-sqlite.py +8 -5
@@ -65,6 +65,9 @@ perf_db_export_callchains = False def printerr(*args, **keyword_args): print(*args, file=sys.stderr, **keyword_args) +def printdate(*args, **kw_args): + print(datetime.datetime.today(), *args, sep=' ', **kw_args) + def usage(): printerr("Usage is: export-to-sqlite.py <database name> [<columns>] [<calls>] [<callchains>]"); printerr("where: columns 'all' or 'branches'");
@@ -105,7 +108,7 @@ def do_query_(q): return raise Exception("Query failed: " + q.lastError().text()) -print(datetime.datetime.today(), "Creating database ...") +printdate("Creating database ...") db_exists = False try:
@@ -383,7 +386,7 @@ if perf_db_export_calls: call_query.prepare("INSERT INTO calls VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)") def trace_begin(): - print(datetime.datetime.today(), "Writing records...") + printdate("Writing records...") do_query(query, 'BEGIN TRANSACTION') # id == 0 means unknown. It is easier to create records for them than replace the zeroes with NULLs evsel_table(0, "unknown")
@@ -402,14 +405,14 @@ unhandled_count = 0 def trace_end(): do_query(query, 'END TRANSACTION') - print(datetime.datetime.today(), "Adding indexes") + printdate("Adding indexes") if perf_db_export_calls: do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)') do_query(query, 'CREATE INDEX pid_idx ON calls (parent_id)') if (unhandled_count): - print(datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events") - print(datetime.datetime.today(), "Done") + printdate("Warning: ", unhandled_count, " unhandled events") + printdate("Done") def trace_unhandled(event_name, context, event_fields_dict): global unhandled_count
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 19/30 perf tools: Update x86's syscall_64.tbl, no change in tools/perf behaviour
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
To pick the changes in 7948450d4556 ("x86/x32: use time64 versions of sigtimedwait and recvmmsg"), that doesn't cause any change in behaviour in tools/perf/ as it deals just with the x32 entries.
This silences this tools/perf build warning:
Warning: Kernel ABI header at 'tools/perf/arch/x86/entry/syscalls/syscall_64.tbl' differs from latest version at 'arch/x86/entry/syscalls/syscall_64.tbl' diff -u tools/perf/arch/x86/entry/syscalls/syscall_64.tbl arch/x86/entry/syscalls/syscall_64.tbl
--- tools/perf/arch/x86/entry/syscalls/syscall_64.tbl | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-)
tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +4 -2
@@ -343,6 +343,8 @@ 332 common statx __x64_sys_statx 333 common io_pgetevents __x64_sys_io_pgetevents 334 common rseq __x64_sys_rseq +# don't use numbers 387 through 423, add new calls after the last +# 'common' entry # # x32-specific system call numbers start at 512 to avoid cache impact
@@ -361,7 +363,7 @@ 520 x32 execve __x32_compat_sys_execve/ptregs 521 x32 ptrace __x32_compat_sys_ptrace 522 x32 rt_sigpending __x32_compat_sys_rt_sigpending -523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait +523 x32 rt_sigtimedwait __x32_compat_sys_rt_sigtimedwait_time64 524 x32 rt_sigqueueinfo __x32_compat_sys_rt_sigqueueinfo 525 x32 sigaltstack __x32_compat_sys_sigaltstack 526 x32 timer_create __x32_compat_sys_timer_create
@@ -375,7 +377,7 @@ 534 x32 preadv __x32_compat_sys_preadv64 535 x32 pwritev __x32_compat_sys_pwritev64 536 x32 rt_tgsigqueueinfo __x32_compat_sys_rt_tgsigqueueinfo -537 x32 recvmmsg __x32_compat_sys_recvmmsg +537 x32 recvmmsg __x32_compat_sys_recvmmsg_time64 538 x32 sendmmsg __x32_compat_sys_sendmmsg 539 x32 process_vm_readv __x32_compat_sys_process_vm_readv 540 x32 process_vm_writev __x32_compat_sys_process_vm_writev
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 20/30 tools headers uapi: Sync copy of asm-generic/unistd.h with the kernel sources
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
To get the changes in:
c8ce48f06503 ("asm-generic: Make time32 syscall numbers optional")
Silencing these tools/perf build warnings:
Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/unistd.h' differs from latest version at 'arch/arm64/include/uapi/asm/unistd.h' diff -u tools/arch/arm64/include/uapi/asm/unistd.h arch/arm64/include/uapi/asm/unistd.h
Warning: Kernel ABI header at 'tools/include/uapi/asm-generic/unistd.h' differs from latest version at 'include/uapi/asm-generic/unistd.h' diff -u tools/include/uapi/asm-generic/unistd.h include/uapi/asm-generic/unistd.h
Test built it under the ubuntu:14.04.4-x-linaro-arm64 cross build environment and looked at the syscall table at /tmp/build/perf/arch/arm64/include/generated/asm/syscalls.c, looks ok.
--- tools/arch/arm64/include/uapi/asm/unistd.h | 2 + tools/include/uapi/asm-generic/unistd.h | 149 ++++++++++++++++----- 2 files changed, 118 insertions(+), 33 deletions(-)
tools/arch/arm64/include/uapi/asm/unistd.h +2 -0
@@ -17,5 +17,7 @@#define __ARCH_WANT_RENAMEAT#define __ARCH_WANT_NEW_STAT +#define __ARCH_WANT_SET_GET_RLIMIT +#define __ARCH_WANT_TIME32_SYSCALLS#include <asm-generic/unistd.h>
tools/include/uapi/asm-generic/unistd.h +116 -33
296 lines not on this page · raw message
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 21/30 tools headers uapi: Update linux/in.h copy
In reply to Arnaldo Carvalho de MeloFrom: Arnaldo Carvalho de Melo <[email protected]>
To get the changes in:
4effd28c1245 ("bridge: join all-snoopers multicast address")
That do not generate any changes in tools/ use of this file.
Silences this tools/perf build warning:
Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h
--- tools/include/uapi/linux/in.h | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-)
tools/include/uapi/linux/in.h +5 -4
@@ -292,10 +292,11 @@ struct sockaddr_in {#define IN_LOOPBACK (a) ((((long int) (a)) & 0xff000000) == 0x7f000000)/* Defines for Multicast INADDR */ -#define INADDR_UNSPEC_GROUP 0xe0000000U/* 224.0.0.0 */ -#define INADDR_ALLHOSTS_GROUP 0xe0000001U/* 224.0.0.1 */ -#define INADDR_ALLRTRS_GROUP 0xe0000002U/* 224.0.0.2 */ -#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU/* 224.0.0.255 */ +#define INADDR_UNSPEC_GROUP 0xe0000000U/* 224.0.0.0 */ +#define INADDR_ALLHOSTS_GROUP 0xe0000001U/* 224.0.0.1 */ +#define INADDR_ALLRTRS_GROUP 0xe0000002U/* 224.0.0.2 */ +#define INADDR_ALLSNOOPERS_GROUP 0xe000006aU/* 224.0.0.106 */ +#define INADDR_MAX_LOCAL_GROUP 0xe00000ffU/* 224.0.0.255 */ #endif /* <asm/byteorder.h> contains the htonl type stuff.. */
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 22/30 perf script: Filter COMM/FORK/.. events by CPU
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
The --cpu option only filtered samples. Filter other perf events, such as COMM, FORK, SWITCH by the CPU too.
--- tools/perf/builtin-script.c | 71 ++++++++++++++++++++++++------------- 1 file changed, 47 insertions(+), 24 deletions(-)
tools/perf/builtin-script.c +47 -24
@@ -1933,6 +1933,13 @@ static int cleanup_scripting(void)return scripting_ops ? scripting_ops->stop_script () :0 ; } +static bool filter_cpu (struct perf_sample *sample) +{ +if (cpu_list) +return !test_bit (sample->cpu, cpu_bitmap); +return false; +} + static int process_sample_event(struct perf_tool *tool, union perf_event *event, struct perf_sample *sample,
@@ -1967,7 +1974,7 @@ static int process_sample_event(struct perf_tool *tool,if (al.filtered) goto out_put; -if (cpu_list && !test_bit (sample->cpu, cpu_bitmap)) +if (filter_cpu (sample)) goto out_put;if (scripting_ops)
@@ -2052,9 +2059,11 @@ static int process_comm_event(struct perf_tool *tool, sample->tid = event->comm.tid; sample->pid = event->comm.pid; } -perf_sample__fprintf_start (sample, thread, evsel, +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel,PERF_RECORD_COMM , stdout); -perf_event__fprintf (event, stdout); +perf_event__fprintf (event, stdout); + } ret =0 ; out:thread__put (thread);
@@ -2088,9 +2097,11 @@ static int process_namespaces_event(struct perf_tool *tool, sample->tid = event->namespaces.tid; sample->pid = event->namespaces.pid; } -perf_sample__fprintf_start (sample, thread, evsel, -PERF_RECORD_NAMESPACES , stdout); -perf_event__fprintf (event, stdout); +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_NAMESPACES , stdout); +perf_event__fprintf (event, stdout); + } ret =0 ; out:thread__put (thread);
@@ -2122,9 +2133,11 @@ static int process_fork_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } -perf_sample__fprintf_start (sample, thread, evsel, -PERF_RECORD_FORK , stdout); -perf_event__fprintf (event, stdout); +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_FORK , stdout); +perf_event__fprintf (event, stdout); + }thread__put (thread);return 0 ;
@@ -2152,9 +2165,11 @@ static int process_exit_event(struct perf_tool *tool, sample->tid = event->fork.tid; sample->pid = event->fork.pid; } -perf_sample__fprintf_start (sample, thread, evsel, -PERF_RECORD_EXIT , stdout); -perf_event__fprintf (event, stdout); +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_EXIT , stdout); +perf_event__fprintf (event, stdout); + }if (perf_event__process_exit (tool, event, sample, machine) <0 ) err =-1 ;
@@ -2188,9 +2203,11 @@ static int process_mmap_event(struct perf_tool *tool, sample->tid = event->mmap.tid; sample->pid = event->mmap.pid; } -perf_sample__fprintf_start (sample, thread, evsel, -PERF_RECORD_MMAP , stdout); -perf_event__fprintf (event, stdout); +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_MMAP , stdout); +perf_event__fprintf (event, stdout); + }thread__put (thread);return 0 ; }
@@ -2220,9 +2237,11 @@ static int process_mmap2_event(struct perf_tool *tool, sample->tid = event->mmap2.tid; sample->pid = event->mmap2.pid; } -perf_sample__fprintf_start (sample, thread, evsel, -PERF_RECORD_MMAP2 , stdout); -perf_event__fprintf (event, stdout); +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_MMAP2 , stdout); +perf_event__fprintf (event, stdout); + }thread__put (thread);return 0 ; }
@@ -2247,9 +2266,11 @@ static int process_switch_event(struct perf_tool *tool,return -1 ; } -perf_sample__fprintf_start (sample, thread, evsel, -PERF_RECORD_SWITCH , stdout); -perf_event__fprintf (event, stdout); +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_SWITCH , stdout); +perf_event__fprintf (event, stdout); + }thread__put (thread);return 0 ; }
@@ -2270,9 +2291,11 @@ process_lost_event(struct perf_tool *tool,if (thread ==NULL )return -1 ; -perf_sample__fprintf_start (sample, thread, evsel, -PERF_RECORD_LOST , stdout); -perf_event__fprintf (event, stdout); +if (!filter_cpu (sample)) { +perf_sample__fprintf_start (sample, thread, evsel, +PERF_RECORD_LOST , stdout); +perf_event__fprintf (event, stdout); + }thread__put (thread);return 0 ; }
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 23/30 perf report: Support time sort key
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add a time sort key to perf report to display samples for different time quantums separately. This allows easier analysis of workloads that change over time, and also will allow looking at the context of samples.
% perf record ...
% perf report --sort time,overhead,symbol --time-quantum 1ms --stdio
...
0.67% 277061.87300 [.] _dl_start
0.50% 277061.87300 [.] f1
0.50% 277061.87300 [.] f2
0.33% 277061.87300 [.] main
0.29% 277061.87300 [.] _dl_lookup_symbol_x
0.29% 277061.87300 [.] dl_main
0.29% 277061.87300 [.] do_lookup_x
0.17% 277061.87300 [.] _dl_debug_initialize
0.17% 277061.87300 [.] _dl_init_paths
0.08% 277061.87300 [.] check_match
0.04% 277061.87300 [.] _dl_count_modids
1.33% 277061.87400 [.] f1
1.33% 277061.87400 [.] f2
1.33% 277061.87400 [.] main
1.17% 277061.87500 [.] main
1.08% 277061.87500 [.] f1
1.08% 277061.87500 [.] f2
1.00% 277061.87600 [.] main
0.83% 277061.87600 [.] f1
0.83% 277061.87600 [.] f2
1.00% 277061.87700 [.] mainCommitter notes:
Rename 'time' argument to hist_time() to htime to overcome this in older distros:
cc1: warnings being treated as errors
util/hist.c: In function 'hist_time':
util/hist.c:251: error: declaration of 'time' shadows a global declaration /usr/include/time.h:186: error: shadowed declaration is here
--- tools/perf/Documentation/perf-report.txt | 2 ++ tools/perf/util/hist.c | 11 +++++++ tools/perf/util/hist.h | 1 + tools/perf/util/sort.c | 39 ++++++++++++++++++++++++ tools/perf/util/sort.h | 2 ++ 5 files changed, 55 insertions(+)
tools/perf/Documentation/perf-report.txt +2 -0
@@ -105,6 +105,8 @@ OPTIONS guest machine - sample: Number of sample - period: Raw number of event count of sample + - time: Separate the samples by time stamp with the resolution specified by + --time-quantum (default 100ms). Specify with overhead and before it. By default, comm, dso and symbol keys are used. (i.e. --sort comm,dso,symbol)
tools/perf/util/hist.c +11 -0
@@ -19,6 +19,7 @@#include <math.h> #include <inttypes.h> #include <sys/param.h> +#include <linux/time64.h> static bool hists__filter_entry_by_dso (struct hists *hists,struct hist_entry *he);
@@ -192,6 +193,7 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)hists__new_col_len (hists,HISTC_MEM_LVL ,21 +3 );hists__new_col_len (hists,HISTC_LOCAL_WEIGHT ,12 );hists__new_col_len (hists,HISTC_GLOBAL_WEIGHT ,12 ); +hists__new_col_len (hists,HISTC_TIME ,12 );if (h->srcline) { len =MAX (strlen (h->srcline),strlen (sort_srcline.se_header));
@@ -246,6 +248,14 @@ static void he_stat__add_cpumode_period(struct he_stat *he_stat, } } +static long hist_time (unsigned long htime) +{ +unsigned long time_quantum = symbol_conf.time_quantum; +if (time_quantum) +return (htime / time_quantum) * time_quantum; +return htime; +} +static void he_stat__add_period (struct he_stat *he_stat,u64 period,u64 weight) {
@@ -635,6 +645,7 @@ __hists__add_entry(struct hists *hists, .raw_data = sample->raw_data, .raw_size = sample->raw_size, .ops = ops, + .time =hist_time (sample->time), }, *he = hists__findnew_entry(hists, &entry, al, sample_self);if (!hists->has_callchains && he && he->callchain_size !=0 )
tools/perf/util/hist.h +1 -0
@@ -31,6 +31,7 @@ enum hist_filter {enum hist_column {HISTC_SYMBOL , +HISTC_TIME ,HISTC_DSO ,HISTC_THREAD ,HISTC_COMM ,
tools/perf/util/sort.c +39 -0
@@ -3,6 +3,7 @@#include <inttypes.h> #include <regex.h> #include <linux/mman.h> +#include <linux/time64.h> #include "sort.h" #include "hist.h" #include "comm.h"
@@ -15,6 +16,7 @@#include <traceevent/event-parse.h> #include "mem-events.h" #include "annotate.h" +#include "time-utils.h" #include <linux/kernel.h> regex_t parent_regex;
@@ -654,6 +656,42 @@ struct sort_entry sort_socket = { .se_width_idx = HISTC_SOCKET, }; +/* --sort time */ + +static int64_t +sort__time_cmp (struct hist_entry *left,struct hist_entry *right) +{ +return right->time - left->time; +} + +static int hist_entry__time_snprintf (struct hist_entry *he,char *bf, +size_t size,unsigned int width) +{ +unsigned long secs; +unsigned long long nsecs; +char he_time[32 ]; + + nsecs = he->time; + secs = nsecs /NSEC_PER_SEC ; + nsecs -= secs *NSEC_PER_SEC ; + +if (symbol_conf.nanosecs) +snprintf (he_time,sizeof he_time,"%5lu.%09llu: " , + secs, nsecs); +else +timestamp__scnprintf_usec (he->time, he_time, +sizeof (he_time)); + +return repsep_snprintf (bf, size,"%-.*s" , width, he_time); +} + +struct sort_entry sort_time = { + .se_header ="Time" , + .se_cmp = sort__time_cmp, + .se_snprintf = hist_entry__time_snprintf, + .se_width_idx =HISTC_TIME , +}; +/* --sort trace */ static char *get_trace_output (struct hist_entry *he)
@@ -1634,6 +1672,7 @@ static struct sort_dimension common_sort_dimensions[] = {DIM (SORT_DSO_SIZE ,"dso_size" , sort_dso_size),DIM (SORT_CGROUP_ID ,"cgroup_id" , sort_cgroup_id),DIM (SORT_SYM_IPC_NULL ,"ipc_null" , sort_sym_ipc_null), + DIM(SORT_TIME, "time", sort_time), };#undef DIM
tools/perf/util/sort.h +2 -0
@@ -135,6 +135,7 @@ struct hist_entry {char *srcfile;struct symbol *parent;struct branch_info *branch_info; +long time;struct hists *hists;struct mem_info *mem_info;void *raw_data;
@@ -231,6 +232,7 @@ enum sort_type {SORT_DSO_SIZE ,SORT_CGROUP_ID ,SORT_SYM_IPC_NULL , +SORT_TIME ,/* branch stack specific sort keys */ __SORT_BRANCH_STACK,
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 24/30 perf report: Support running scripts for current time range
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
When using the time sort key, add new context menus to run scripts for only the currently selected time range. Compute the correct range for the selection add pass it as the --time option to perf script.
--- tools/perf/ui/browsers/hists.c | 83 +++++++++++++++++++++++++++++----- 1 file changed, 72 insertions(+), 11 deletions(-)
tools/perf/ui/browsers/hists.c +72 -11
@@ -7,6 +7,7 @@#include <string.h> #include <linux/rbtree.h> #include <sys/ttydefaults.h> +#include <linux/time64.h> #include "../../util/callchain.h" #include "../../util/evsel.h"
@@ -30,6 +31,7 @@#include "srcline.h" #include "string2.h" #include "units.h" +#include "time-utils.h" #include "sane_ctype.h"
@@ -2338,6 +2340,7 @@ static int switch_data_file(void) }struct popup_action { +unsigned long time;struct thread *thread;struct map_symbol ms;int socket;
@@ -2527,36 +2530,64 @@ static int do_run_script(struct hist_browser *browser __maybe_unused, struct popup_action *act) { - char script_opt[64]; -memset (script_opt,0 ,sizeof (script_opt)); + char *script_opt; +int len; +int n =0 ; + + len =100 ; +if (act->thread) + len +=strlen (thread__comm_str (act->thread)); +else if (act->ms.sym) + len +=strlen (act->ms.sym->name); + script_opt =malloc (len); +if (!script_opt) +return -1 ; + script_opt[0 ] =0 ;if (act->thread) { -scnprintf (script_opt,sizeof (script_opt)," -c %s " , + n =scnprintf (script_opt, len," -c %s " ,thread__comm_str (act->thread)); }else if (act->ms.sym) { -scnprintf (script_opt,sizeof (script_opt)," -S %s " , + n =scnprintf (script_opt, len," -S %s " , act->ms.sym->name); } +if (act->time) { +char start[32 ], end[32 ]; +unsigned long starttime = act->time; +unsigned long endtime = act->time + symbol_conf.time_quantum; + +if (starttime == endtime) {/* Display 1ms as fallback */ + starttime -=1 *NSEC_PER_MSEC ; + endtime +=1 *NSEC_PER_MSEC ; + } +timestamp__scnprintf_usec (starttime, start,sizeof start); +timestamp__scnprintf_usec (endtime, end,sizeof end); + n +=snprintf (script_opt + n, len - n," --time %s,%s" , start, end); + } +script_browse (script_opt); +free (script_opt);return 0 ; }static int -add_script_opt (struct hist_browser *browser__maybe_unused , +add_script_opt_2 (struct hist_browser *browser__maybe_unused ,struct popup_action *act,char **optstr, -struct thread *thread,struct symbol *sym) +struct thread *thread,struct symbol *sym, +const char *tstr) { +if (thread) { -if (asprintf (optstr,"Run scripts for samples of thread [%s]" , -thread__comm_str (thread)) <0 ) +if (asprintf (optstr,"Run scripts for samples of thread [%s]%s" , +thread__comm_str (thread), tstr) <0 )return 0 ; }else if (sym) { -if (asprintf (optstr,"Run scripts for samples of symbol [%s]" , - sym->name) <0 ) +if (asprintf (optstr,"Run scripts for samples of symbol [%s]%s" , + sym->name, tstr) <0 )return 0 ; }else { -if (asprintf (optstr,"Run scripts for all samples" ) <0 ) +if (asprintf (optstr,"Run scripts for all samples%s" , tstr) <0 )return 0 ; }
@@ -2566,6 +2597,36 @@ add_script_opt(struct hist_browser *browser __maybe_unused,return 1 ; } +static int +add_script_opt (struct hist_browser *browser, +struct popup_action *act,char **optstr, +struct thread *thread,struct symbol *sym) +{ +int n, j; +struct hist_entry *he; + + n =add_script_opt_2 (browser, act, optstr, thread, sym,"" ); + + he =hist_browser__selected_entry (browser); +if (sort_order &&strstr (sort_order,"time" )) { +char tstr[128 ]; + + optstr++; + act++; + j =sprintf (tstr," in " ); + j +=timestamp__scnprintf_usec (he->time, tstr + j, +sizeof tstr - j); + j +=sprintf (tstr + j,"-" ); +timestamp__scnprintf_usec (he->time + symbol_conf.time_quantum, + tstr + j, +sizeof tstr - j); + n +=add_script_opt_2 (browser, act, optstr, thread, sym, + tstr); + act->time = he->time; + } +return n; +} +static int do_switch_data (struct hist_browser *browser__maybe_unused ,struct popup_action *act__maybe_unused )
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 25/30 perf report: Support builtin perf script in scripts menu
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
The scripts menu traditionally only showed custom perf scripts.
Allow to run standard perf script with useful default options too.
- Normal perf script
- perf script with assembler (needs xed installed)
- perf script with source code output (needs debuginfo)
- perf script with custom arguments
Then we automatically select the right options to display the information in the perf.data file.
For example with -b display branch contexts.
It's not easily possible to check for xed's existence in advance. perf script usually gives sensible error messages when it's not available.
--- tools/perf/ui/browsers/annotate.c | 2 +- tools/perf/ui/browsers/hists.c | 23 +++--- tools/perf/ui/browsers/scripts.c | 127 +++++++++++++++++++++++------- tools/perf/util/hist.h | 8 +- 4 files changed, 120 insertions(+), 40 deletions(-)
tools/perf/ui/browsers/annotate.c +1 -1
@@ -750,7 +750,7 @@ static int annotate_browser__run(struct annotate_browser *browser,continue ;case 'r' : { -script_browse (NULL ); +script_browse (NULL ,NULL );continue ; }case 'k' :
tools/perf/ui/browsers/hists.c +13 -10
@@ -2344,6 +2344,7 @@ struct popup_action {struct thread *thread;struct map_symbol ms;int socket; +struct perf_evsel *evsel;int (*fn)(struct hist_browser *browser,struct popup_action *act); };
@@ -2566,7 +2567,7 @@ do_run_script(struct hist_browser *browser __maybe_unused, n +=snprintf (script_opt + n, len - n," --time %s,%s" , start, end); } -script_browse (script_opt); +script_browse (script_opt, act->evsel);free (script_opt);return 0 ; }
@@ -2575,7 +2576,7 @@ static int add_script_opt_2(struct hist_browser *browser __maybe_unused, struct popup_action *act, char **optstr, struct thread *thread, struct symbol *sym, - const char *tstr) + struct perf_evsel *evsel, const char *tstr) { if (thread) {
@@ -2593,6 +2594,7 @@ add_script_opt_2(struct hist_browser *browser __maybe_unused, act->thread = thread; act->ms.sym = sym; + act->evsel = evsel; act->fn = do_run_script;return 1 ; }
@@ -2600,12 +2602,13 @@ add_script_opt_2(struct hist_browser *browser __maybe_unused,static int add_script_opt (struct hist_browser *browser,struct popup_action *act,char **optstr, -struct thread *thread,struct symbol *sym) +struct thread *thread,struct symbol *sym, +struct perf_evsel *evsel) {int n, j;struct hist_entry *he; - n =add_script_opt_2 (browser, act, optstr, thread, sym,"" ); + n =add_script_opt_2 (browser, act, optstr, thread, sym, evsel,"" ); he =hist_browser__selected_entry (browser);if (sort_order &&strstr (sort_order,"time" )) {
@@ -2618,10 +2621,9 @@ add_script_opt(struct hist_browser *browser, sizeof tstr - j); j +=sprintf (tstr + j,"-" );timestamp__scnprintf_usec (he->time + symbol_conf.time_quantum, - tstr + j, -sizeof tstr - j); + tstr + j,sizeof tstr - j); n +=add_script_opt_2 (browser, act, optstr, thread, sym, - tstr); + evsel, tstr); act->time = he->time; }return n;
@@ -3092,7 +3094,7 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, nr_options +=add_script_opt (browser, &actions[nr_options], &options[nr_options], - thread,NULL ); + thread,NULL , evsel); }/* * Note that browser->selection != NULL
@@ -3107,11 +3109,12 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events, nr_options +=add_script_opt (browser, &actions[nr_options], &options[nr_options], -NULL , browser->selection->sym); +NULL , browser->selection->sym, + evsel); } } nr_options +=add_script_opt (browser, &actions[nr_options], - &options[nr_options],NULL ,NULL ); + &options[nr_options],NULL ,NULL , evsel); nr_options +=add_switch_opt (browser, &actions[nr_options], &options[nr_options]); skip_scripting:
tools/perf/ui/browsers/scripts.c +100 -27
163 lines not on this page · raw message
tools/perf/util/hist.h +6 -2
@@ -436,6 +436,8 @@ struct annotation_options;#ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h" +void attr_to_script (char *buf,struct perf_event_attr *attr); +int map_symbol__tui_annotate (struct map_symbol *ms,struct perf_evsel *evsel,struct hist_browser_timer *hbt,struct annotation_options *annotation_opts);
@@ -450,7 +452,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,struct perf_env *env, bool warn_lost_event, struct annotation_options *annotation_options); -int script_browse (const char *script_opt); + +int script_browse (const char *script_opt,struct perf_evsel *evsel);#else static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
@@ -479,7 +482,8 @@ static inline int hist_entry__tui_annotate(struct hist_entry *he __maybe_unused,return 0 ; } -static inline int script_browse (const char *script_opt__maybe_unused ) +static inline int script_browse (const char *script_opt__maybe_unused , +struct perf_evsel *evsel__maybe_unused ) {return 0 ; }
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 26/30 perf report: Implement browsing of individual samples
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Now 'perf report' can show whole time periods with 'perf script', but the user still has to find individual samples of interest manually.
It would be expensive and complicated to search for the right samples in the whole perf file. Typically users only need to look at a small number of samples for useful analysis.
Also the full scripts tend to show samples of all CPUs and all threads mixed up, which can be very confusing on larger systems.
Add a new --samples option to save a small random number of samples per hist entry.
Use a reservoir sample technique to select a representatve number of samples.
Then allow browsing the samples using 'perf script' as part of the hist entry context menu. This automatically adds the right filters, so only the thread or cpu of the sample is displayed. Then we use less' search functionality to directly jump the to the time stamp of the selected sample.
It uses different menus for assembler and source display. Assembler needs xed installed and source needs debuginfo.
Currently it only supports as many samples as fit on the screen due to some limitations in the slang ui code.
--- tools/perf/Documentation/perf-config.txt | 6 ++ tools/perf/Documentation/perf-report.txt | 4 + tools/perf/builtin-report.c | 2 + tools/perf/ui/browsers/Build | 1 + tools/perf/ui/browsers/hists.c | 47 ++++++++++++ tools/perf/ui/browsers/res_sample.c | 94 ++++++++++++++++++++++++ tools/perf/ui/browsers/scripts.c | 2 +- tools/perf/util/hist.c | 39 ++++++++++ tools/perf/util/hist.h | 22 ++++++ tools/perf/util/sort.h | 8 ++ tools/perf/util/symbol.c | 1 + tools/perf/util/symbol_conf.h | 1 + 12 files changed, 226 insertions(+), 1 deletion(-) create mode 100644 tools/perf/ui/browsers/res_sample.c
tools/perf/Documentation/perf-config.txt +6 -0
@@ -584,6 +584,12 @@ llvm.*:: llvm.opts:: Options passed to llc. +samples.*:: + + samples.context:: + Define how many ns worth of time to show + around samples in perf report sample context browser. + SEE ALSO -------- linkperf:perf[1]
tools/perf/Documentation/perf-report.txt +4 -0
@@ -461,6 +461,10 @@ include::itrace.txt[] --socket-filter:: Only report the samples on the processor socket that match with this filter +--samples=N:: + Save N individual samples for each histogram entry to show context in perf + report tui browser. + --raw-trace:: When displaying traceevent output, do not use print fmt or plugins.
tools/perf/builtin-report.c +2 -0
@@ -1159,6 +1159,8 @@ int cmd_report(int argc, const char **argv)OPT_BOOLEAN (0 ,"demangle-kernel" , &symbol_conf.demangle_kernel,"Enable kernel symbol demangling" ),OPT_BOOLEAN (0 ,"mem-mode" , &report.mem_mode,"mem access profile" ), +OPT_INTEGER (0 ,"samples" , &symbol_conf.res_sample, +"Number of samples to save per histogram entry for individual browsing" ),OPT_CALLBACK (0 ,"percent-limit" , &report,"percent" ,"Don't show entries under that percent" , parse_percent_limit), OPT_CALLBACK(0, "percentage", NULL, "relative|absolute",
tools/perf/ui/browsers/Build +1 -0
@@ -3,6 +3,7 @@ perf-y += hists.o perf-y += map.o perf-y += scripts.o perf-y += header.o +perf-y += res_sample.o CFLAGS_annotate.o += -DENABLE_SLFUTURE_CONST CFLAGS_hists.o += -DENABLE_SLFUTURE_CONST
tools/perf/ui/browsers/hists.c +47 -0
77 lines not on this page · raw message
tools/perf/ui/browsers/res_sample.c new file +94 -0
94 lines not on this page · raw message
tools/perf/ui/browsers/scripts.c +1 -1
@@ -125,7 +125,7 @@ static int list_scripts(char *script_name, bool *custom,return ret; } -static void run_script (char *cmd) +void run_script (char *cmd) {pr_debug ("Running %s\n" , cmd);SLang_reset_tty ();
tools/perf/util/hist.c +39 -0
@@ -436,6 +436,13 @@ static int hist_entry__init(struct hist_entry *he, goto err_rawdata; } +if (symbol_conf.res_sample) { + he->res_samples =calloc (sizeof (struct res_sample ), + symbol_conf.res_sample); +if (!he->res_samples) + goto err_srcline; + } +INIT_LIST_HEAD (&he->pairs.node);thread__get (he->thread); he->hroot_in =RB_ROOT_CACHED ;
@@ -446,6 +453,9 @@ static int hist_entry__init(struct hist_entry *he,return 0 ; +err_srcline: +free (he->srcline); + err_rawdata:free (he->raw_data);
@@ -603,6 +613,32 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,return he; } +static unsigned random_max (unsigned high) +{ +unsigned thresh = -high % high; +for (;;) { +unsigned r =random (); +if (r >= thresh) +return r % high; + } +} + +static void hists__res_sample (struct hist_entry *he,struct perf_sample *sample) +{ +struct res_sample *r; +int j; + +if (he->num_res < symbol_conf.res_sample) { + j = he->num_res++; + }else { + j =random_max (symbol_conf.res_sample); + } + r = &he->res_samples[j]; + r->time = sample->time; + r->cpu = sample->cpu; + r->tid = sample->tid; +} +static struct hist_entry * __hists__add_entry(struct hists *hists, struct addr_location *al,
@@ -650,6 +686,8 @@ __hists__add_entry(struct hists *hists,if (!hists->has_callchains && he && he->callchain_size !=0 ) hists->has_callchains = true; +if (he && symbol_conf.res_sample) +hists__res_sample (he, sample);return he; }
@@ -1173,6 +1211,7 @@ void hist_entry__delete(struct hist_entry *he)mem_info__zput (he->mem_info); } +zfree (&he->res_samples);zfree (&he->stat_acc);free_srcline (he->srcline);if (he->srcfile && he->srcfile[0 ])
tools/perf/util/hist.h +22 -0
@@ -433,6 +433,13 @@ struct hist_browser_timer { };struct annotation_options ; +struct res_sample ; + +enum rstype { +A_NORMAL , +A_ASM , +A_SOURCE +};#ifdef HAVE_SLANG_SUPPORT #include "../ui/keysyms.h"
@@ -454,6 +461,11 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help, struct annotation_options *annotation_options);int script_browse (const char *script_opt,struct perf_evsel *evsel); + +void run_script (char *cmd); +int res_sample_browse (struct res_sample *res_samples,int num_res, +struct perf_evsel *evsel,enum rstype rstype); +void res_sample_init (void );#else static inline int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
@@ -488,6 +500,16 @@ static inline int script_browse(const char *script_opt __maybe_unused,return 0 ; } +static inline int res_sample_browse (struct res_sample *res_samples__maybe_unused , +int num_res__maybe_unused , +struct perf_evsel *evsel__maybe_unused , +enum rstype rstype__maybe_unused ) +{ +return 0 ; +} + +static inline void res_sample_init (void ) {} +#define K_LEFT -1000#define K_RIGHT -2000#define K_SWITCH_INPUT_DATA -3000
tools/perf/util/sort.h +8 -0
@@ -47,6 +47,12 @@ extern struct sort_entry sort_srcline;extern enum sort_type sort__first_dimension;extern const char default_mem_sort_order[]; +struct res_sample { +u64 time; +int cpu; +int tid; +}; +struct he_stat {u64 period;u64 period_sys;
@@ -140,6 +146,8 @@ struct hist_entry {struct mem_info *mem_info;void *raw_data;u32 raw_size; +int num_res; +struct res_sample *res_samples;void *trace_output;struct perf_hpp_list *hpp_list;struct hist_entry *parent_he;
tools/perf/util/symbol.c +1 -0
@@ -51,6 +51,7 @@ struct symbol_conf symbol_conf = { .symfs = "", .event_group = true, .inline_name = true, + .res_sample = 0, };static enum dso_binary_type binary_type_symtab[] = {
tools/perf/util/symbol_conf.h +1 -0
@@ -68,6 +68,7 @@ struct symbol_conf {struct intlist *pid_list, *tid_list;const char *symfs; +int res_sample; };extern struct symbol_conf symbol_conf;
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 27/30 perf tools: Add some new tips describing the new options
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
--- tools/perf/Documentation/tips.txt | 7 +++++++ 1 file changed, 7 insertions(+)
tools/perf/Documentation/tips.txt +7 -0
@@ -15,6 +15,7 @@ To see callchains in a more compact form: perf report -g folded Show individual samples with: perf script Limit to show entries above 5% only: perf report --percent-limit 5 Profiling branch (mis)predictions with: perf record -b / perf report +To show assembler sample contexts use perf record -b / perf script -F +brstackinsn --xed Treat branches as callchains: perf report --branch-history To count events in every 1000 msec: perf stat -I 1000 Print event counts in CSV format with: perf stat -x,
@@ -34,3 +35,9 @@ 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` To report cacheline events from previous recording: perf c2c report +To browse sample contexts use perf report --sample 10 and select in context menu +To separate samples by time use perf report --sort time,overhead,sym +To set sample time separation other than 100ms with --sort time use --time-quantum +Add -I to perf report to sample register values visible in perf report context. +To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context +To show context switches in perf report sample context add --switch-events to perf record.
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 28/30 perf script: Add array bound checking to list_scripts
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Don't overflow array when the scripts directory is too large, or the script file name is too long.
--- tools/perf/builtin-script.c | 8 ++++++-- tools/perf/builtin.h | 3 ++- tools/perf/ui/browsers/scripts.c | 3 ++- 3 files changed, 10 insertions(+), 4 deletions(-)
tools/perf/builtin-script.c +6 -2
@@ -2982,7 +2982,8 @@ static int check_ev_match(char *dir_name, char *scriptname,* will list all statically runnable scripts, select one, execute it and * show the output in a perf browser. */ -int find_scripts (char **scripts_array,char **scripts_path_array) +int find_scripts (char **scripts_array,char **scripts_path_array,int num, +int pathlen) {struct dirent *script_dirent, *lang_dirent;char scripts_path[MAXPATHLEN ], lang_path[MAXPATHLEN ];
@@ -3027,7 +3028,10 @@ int find_scripts(char **scripts_array, char **scripts_path_array)/* Skip those real time scripts: xxxtop.p[yl] */ if (strstr (script_dirent->d_name,"top." ))continue ; -sprintf (scripts_path_array[i],"%s/%s" , lang_path, +if (i >= num) +break ; +snprintf (scripts_path_array[i], pathlen,"%s/%s" , + lang_path, script_dirent->d_name); temp =strchr (script_dirent->d_name,'.' ); snprintf(scripts_array[i],
tools/perf/builtin.h +2 -1
@@ -40,5 +40,6 @@ int cmd_mem(int argc, const char **argv);int cmd_data (int argc,const char **argv);int cmd_ftrace (int argc,const char **argv); -int find_scripts (char **scripts_array,char **scripts_path_array); +int find_scripts (char **scripts_array,char **scripts_path_array,int num, +int pathlen);#endif
tools/perf/ui/browsers/scripts.c +2 -1
@@ -97,7 +97,8 @@ static int list_scripts(char *script_name, bool *custom, paths[i] = names[i] +SCRIPT_NAMELEN ; } - num =find_scripts (names + max_std, paths + max_std); + num =find_scripts (names + max_std, paths + max_std,SCRIPT_MAX_NO - max_std, +SCRIPT_FULLPATH_LEN );if (num <0 ) num =0 ; choice =ui__popup_menu (num + max_std, (char *const *)names);
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 29/30 perf ui browser: Fix ui popup argv browser for many entries
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Fix the argv ui browser code to correctly display more entries than fit on the screen without crashing. The problem was some type confusion with pointer types in the ->seek function. Do the argv arithmetic correctly with char ** pointers. Also add some asserts to find overruns and limit the display function correctly.
Then finally remove a workaround for this in the res sample browser.
Committer testing:
1) Resize the x terminal to have just some 5 lines
2) Use 'perf report --samples 1' to activate the sample browser options in the menu
3) Press ENTER, this will cause the crash:
# perf report --samples 1 perf: Segmentation fault -------- backtrace -------- perf[0x5a514a] /lib64/libc.so.6(+0x385bf)[0x7f27281b55bf] /lib64/libc.so.6(+0x161a67)[0x7f27282dea67] /lib64/libslang.so.2(SLsmg_write_wrapped_string+0x82)[0x7f272874a0b2] perf(ui_browser__argv_refresh+0x77)[0x5939a7] perf[0x5924cc] perf(ui_browser__run+0x39)[0x593449] perf(ui__popup_menu+0x83)[0x5a5263] perf[0x59f421] perf(perf_evlist__tui_browse_hists+0x3a0)[0x5a3780] perf(cmd_report+0x2746)[0x447136] perf[0x4a95fe] perf(main+0x61c)[0x42dc6c] /lib64/libc.so.6(__libc_start_main+0xf2)[0x7f27281a1412] perf(_start+0x2d)[0x42de9d] #
After applying this patch no crash takes place in such situation.
--- tools/perf/ui/browser.c | 10 +++++++--- tools/perf/ui/browsers/res_sample.c | 3 --- 2 files changed, 7 insertions(+), 6 deletions(-)
tools/perf/ui/browser.c +7 -3
@@ -611,14 +611,16 @@ void ui_browser__argv_seek(struct ui_browser *browser, off_t offset, int whence) browser->top = browser->entries;break ;case SEEK_CUR : - browser->top = browser->top + browser->top_idx + offset; + browser->top = (char **)browser->top + offset;break ;case SEEK_END : - browser->top = browser->top + browser->nr_entries -1 + offset; + browser->top = (char **)browser->entries + browser->nr_entries -1 + offset;break ;default :return ; } +assert ((char **)browser->top < (char **)browser->entries + browser->nr_entries); +assert ((char **)browser->top >= (char **)browser->entries); }unsigned int ui_browser__argv_refresh (struct ui_browser *browser)
@@ -630,7 +632,9 @@ unsigned int ui_browser__argv_refresh(struct ui_browser *browser) browser->top = browser->entries; pos = (char **)browser->top; -while (idx < browser->nr_entries) { +while (idx < browser->nr_entries && + row < (unsigned )SLtt_Screen_Rows -1 ) { +assert (pos < (char **)browser->entries + browser->nr_entries);if (!browser->filter || !browser->filter (browser, *pos)) {ui_browser__gotorc (browser, row,0 ); browser->write (browser, pos, row);
tools/perf/ui/browsers/res_sample.c +0 -3
@@ -36,9 +36,6 @@ int res_sample_browse(struct res_sample *res_samples, int num_res,struct res_sample *r;char extra_format[256 ]; -/* For now since ui__popup_menu doesn't like lists that don't fit */ - num_res =max (min (SLtt_Screen_Rows -4 , num_res),0 ); - names =calloc (num_res,sizeof (char *));if (!names)return -1 ;
Signature · 1 line
2.20.1
Arnaldo Carvalho de Melo
maintainerPATCH 30/30 perf tools report: Add custom scripts to script menu
In reply to Arnaldo Carvalho de MeloFrom: Andi Kleen <[email protected]>
Add a way to define custom scripts through ~/.perfconfig, which are then added to the scripts menu. The scripts get the same arguments as 'perf script', in particular -i, --cpu, --tid.
--- tools/perf/Documentation/perf-config.txt | 8 ++++++++ tools/perf/ui/browsers/scripts.c | 20 ++++++++++++++++++++ 2 files changed, 28 insertions(+)
tools/perf/Documentation/perf-config.txt +8 -0
@@ -590,6 +590,14 @@ samples.*:: Define how many ns worth of time to show around samples in perf report sample context browser. +scripts.*:: + + Any option defines a script that is added to the scripts menu + in the interactive perf browser and whose output is displayed. + The name of the option is the name, the value is a script command line. + The script gets the same options passed as a full perf script, + in particular -i perfdata file, --cpu, --tid + SEE ALSO -------- linkperf:perf[1]
tools/perf/ui/browsers/scripts.c +20 -0
@@ -6,6 +6,7 @@#include "../../util/symbol.h" #include "../browser.h" #include "../libslang.h" +#include "config.h" #define SCRIPT_NAMELEN 128#define SCRIPT_MAX_NO 64
@@ -53,6 +54,24 @@ static int add_script_option(const char *name, const char *opt,return 0 ; } +static int scripts_config (const char *var,const char *value,void *data) +{ +struct script_config *c = data; + +if (!strstarts (var,"scripts." )) +return -1 ; +if (c->index >=SCRIPT_MAX_NO ) +return -1 ; + c->names[c->index] =strdup (var +7 ); +if (!c->names[c->index]) +return -1 ; +if (asprintf (&c->paths[c->index],"%s %s" , value, + c->extra_format) <0 ) +return -1 ; + c->index++; +return 0 ; +} +/* * When success, will copy the full path of the selected script * into the buffer pointed by script_name, and return 0.
@@ -87,6 +106,7 @@ static int list_scripts(char *script_name, bool *custom, &scriptc);add_script_option ("Show individual samples with source" ,"-F +srcline,+srccode" , &scriptc); +perf_config (scripts_config, &scriptc); custom_perf = scriptc.index;add_script_option ("Show samples with custom perf script arguments" ,"" , &scriptc); i = scriptc.index;
Signature · 1 line
2.20.1