linux/tools/perf/perf.h

81 lines
1.9 KiB
C
Raw Normal View History

#ifndef _PERF_PERF_H
#define _PERF_PERF_H
#include <time.h>
#include <stdbool.h>
#include <linux/types.h>
#include <linux/perf_event.h>
extern bool test_attr__enabled;
void test_attr__init(void);
void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
int fd, int group_fd, unsigned long flags);
#define HAVE_ATTR_TEST
#include "perf-sys.h"
static inline unsigned long long rdclock(void)
{
struct timespec ts;
clock_gettime(CLOCK_MONOTONIC, &ts);
return ts.tv_sec * 1000000000ULL + ts.tv_nsec;
}
#define MAX_NR_CPUS 1024
extern const char *input_name;
extern bool perf_host, perf_guest;
perf tools: Make perf.data more self-descriptive (v8) The goal of this patch is to include more information about the host environment into the perf.data so it is more self-descriptive. Overtime, profiles are captured on various machines and it becomes hard to track what was recorded, on what machine and when. This patch provides a way to solve this by extending the perf.data file with basic information about the host machine. To add those extensions, we leverage the feature bits capabilities of the perf.data format. The change is backward compatible with existing perf.data files. We define the following useful new extensions: - HEADER_HOSTNAME: the hostname - HEADER_OSRELEASE: the kernel release number - HEADER_ARCH: the hw architecture - HEADER_CPUDESC: generic CPU description - HEADER_NRCPUS: number of online/avail cpus - HEADER_CMDLINE: perf command line - HEADER_VERSION: perf version - HEADER_TOPOLOGY: cpu topology - HEADER_EVENT_DESC: full event description (attrs) - HEADER_CPUID: easy-to-parse low level CPU identication The small granularity for the entries is to make it easier to extend without breaking backward compatiblity. Many entries are provided as ASCII strings. Perf report/script have been modified to print the basic information as easy-to-parse ASCII strings. Extended information about CPU and NUMA topology may be requested with the -I option. Thanks to David Ahern for reviewing and testing the many versions of this patch. $ perf report --stdio # ======== # captured on : Mon Sep 26 15:22:14 2011 # hostname : quad # os release : 3.1.0-rc4-tip # perf version : 3.1.0-rc4 # arch : x86_64 # nrcpus online : 4 # nrcpus avail : 4 # cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz # cpuid : GenuineIntel,6,15,11 # total memory : 8105360 kB # cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date # event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31, # HEADER_CPU_TOPOLOGY info available, use -I to display # HEADER_NUMA_TOPOLOGY info available, use -I to display # ======== # ... $ perf report --stdio -I # ======== # captured on : Mon Sep 26 15:22:14 2011 # hostname : quad # os release : 3.1.0-rc4-tip # perf version : 3.1.0-rc4 # arch : x86_64 # nrcpus online : 4 # nrcpus avail : 4 # cpudesc : Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz # cpuid : GenuineIntel,6,15,11 # total memory : 8105360 kB # cmdline : /home/eranian/perfmon/official/tip/build/tools/perf/perf record date # event : name = cycles, type = 0, config = 0x0, config1 = 0x0, config2 = 0x0, excl_usr = 0, excl_kern = 0, id = { 29, 30, 31, # sibling cores : 0-3 # sibling threads : 0 # sibling threads : 1 # sibling threads : 2 # sibling threads : 3 # node0 meminfo : total = 8320608 kB, free = 7571024 kB # node0 cpu list : 0-3 # ======== # ... Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Robert Richter <robert.richter@amd.com> Cc: Andi Kleen <ak@linux.intel.com> Link: http://lkml.kernel.org/r/20110930134040.GA5575@quad Signed-off-by: Stephane Eranian <eranian@google.com> [ committer notes: Use --show-info in the tools as was in the docs, rename perf_header_fprintf_info to perf_file_section__fprintf_info, fixup conflict with f69b64f7 "perf: Support setting the disassembler style" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2011-09-30 21:40:40 +08:00
extern const char perf_version_string[];
void pthread__unblock_sigwinch(void);
#include "util/target.h"
struct record_opts {
struct target target;
bool group;
bool inherit_stat;
bool no_buffering;
bool no_inherit;
bool no_inherit_set;
bool no_samples;
bool raw_samples;
bool sample_address;
bool sample_weight;
bool sample_time;
bool sample_time_set;
bool sample_cpu;
bool period;
bool running_time;
bool full_auxtrace;
bool auxtrace_snapshot_mode;
perf tools: Add PERF_RECORD_NAMESPACES to include namespaces related info Introduce a new option to record PERF_RECORD_NAMESPACES events emitted by the kernel when fork, clone, setns or unshare are invoked. And update perf-record documentation with the new option to record namespace events. Committer notes: Combined it with a later patch to allow printing it via 'perf report -D' and be able to test the feature introduced in this patch. Had to move here also perf_ns__name(), that was introduced in another later patch. Also used PRIu64 and PRIx64 to fix the build in some enfironments wrt: util/event.c:1129:39: error: format '%lx' expects argument of type 'long unsigned int', but argument 6 has type 'long long unsigned int' [-Werror=format=] ret += fprintf(fp, "%u/%s: %lu/0x%lx%s", idx ^ Testing it: # perf record --namespaces -a ^C[ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.083 MB perf.data (423 samples) ] # # perf report -D <SNIP> 3 2028902078892 0x115140 [0xa0]: PERF_RECORD_NAMESPACES 14783/14783 - nr_namespaces: 7 [0/net: 3/0xf0000081, 1/uts: 3/0xeffffffe, 2/ipc: 3/0xefffffff, 3/pid: 3/0xeffffffc, 4/user: 3/0xeffffffd, 5/mnt: 3/0xf0000000, 6/cgroup: 3/0xeffffffb] 0x1151e0 [0x30]: event: 9 . . ... raw event: size 48 bytes . 0000: 09 00 00 00 02 00 30 00 c4 71 82 68 0c 7f 00 00 ......0..q.h.... . 0010: a9 39 00 00 a9 39 00 00 94 28 fe 63 d8 01 00 00 .9...9...(.c.... . 0020: 03 00 00 00 00 00 00 00 ce c4 02 00 00 00 00 00 ................ <SNIP> NAMESPACES events: 1 <SNIP> # Signed-off-by: Hari Bathini <hbathini@linux.vnet.ibm.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Starovoitov <ast@fb.com> Cc: Ananth N Mavinakayanahalli <ananth@linux.vnet.ibm.com> Cc: Aravinda Prasad <aravinda@linux.vnet.ibm.com> Cc: Brendan Gregg <brendan.d.gregg@gmail.com> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Eric Biederman <ebiederm@xmission.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sargun Dhillon <sargun@sargun.me> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/148891930386.25309.18412039920746995488.stgit@hbathini.in.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-03-08 04:41:43 +08:00
bool record_namespaces;
bool record_switch_events;
perf record: Add --all-user/--all-kernel options Allow user to easily switch all events to user or kernel space with simple --all-user or --all-kernel options. This will be handy within perf mem/c2c wrappers to switch easily monitoring modes. Committer note: Testing it: # perf record --all-kernel --all-user -a sleep 2 Error: option `all-user' cannot be used with all-kernel Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] --all-user Configure all used events to run in user space. --all-kernel Configure all used events to run in kernel space. # perf record --all-user --all-kernel -a sleep 2 Error: option `all-kernel' cannot be used with all-user Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] --all-kernel Configure all used events to run in kernel space. --all-user Configure all used events to run in user space. # perf record --all-user -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.416 MB perf.data (162 samples) ] # perf report | grep '\[k\]' # perf record --all-kernel -a sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 1.423 MB perf.data (296 samples) ] # perf report | grep '\[\.\]' # Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1455525293-8671-2-git-send-email-jolsa@kernel.org [ Made those options to be mutually exclusive ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-02-15 16:34:31 +08:00
bool all_kernel;
bool all_user;
perf record: Add --tail-synthesize option When working with overwritable ring buffer there's a inconvenience problem: if perf dumps data after a long period after it starts, non-sample events may lost, which makes following 'perf report' unable to identify proc name and mmap layout. For example: # perf record -m 4 -e raw_syscalls:* -g --overwrite --switch-output \ dd if=/dev/zero of=/dev/null send SIGUSR2 after dd runs long enough. The resuling perf.data lost correct comm and mmap events: # perf script -i perf.data.2016061522374354 perf 24478 [004] 2581325.601789: raw_syscalls:sys_exit: NR 0 = 512 ^^^^ Should be 'dd' 27b2e8 syscall_slow_exit_work+0xfe2000e3 (/lib/modules/4.6.0-rc3+/build/vmlinux) 203cc7 do_syscall_64+0xfe200117 (/lib/modules/4.6.0-rc3+/build/vmlinux) b18d83 return_from_SYSCALL_64+0xfe200000 (/lib/modules/4.6.0-rc3+/build/vmlinux) 7f47c417edf0 [unknown] ([unknown]) ^^^^^^^^^^^^ Fail to unwind This patch provides a '--tail-synthesize' option, allows perf to collect system status when finalizing output file. In resuling output file, the non-sample events reflect system status when dumping data. After this patch: # perf record -m 4 -e raw_syscalls:* -g --overwrite --switch-output --tail-synthesize \ dd if=/dev/zero of=/dev/null # perf script -i perf.data.2016061600544998 dd 27364 [004] 2583244.994464: raw_syscalls:sys_enter: NR 1 (1, ... ^^ Correct comm 203a18 syscall_trace_enter_phase2+0xfe2001a8 ([kernel.kallsyms]) 203aa5 syscall_trace_enter+0xfe200055 ([kernel.kallsyms]) 203caa do_syscall_64+0xfe2000fa ([kernel.kallsyms]) b18d83 return_from_SYSCALL_64+0xfe200000 ([kernel.kallsyms]) d8e50 __GI___libc_write+0xffff01d9639f4010 (/tmp/oxygen_root-w00229757/lib64/libc-2.18.so) ^^^^^ Correct unwind This option doesn't aim to solve this problem completely. If a process terminates before SIGUSR2, we still lost its COMM and MMAP events. For example, we can't unwind correctly from the final perf.data we get from the previous example, because when perf collects the final output file (when we press C-c), 'dd' has been terminated so its '/proc/<pid>/mmap' becomes empty. However, this is a cheaper choice. To completely solve this problem we need to continously output non-sample events. To satisify the requirement of daemonization, we need to merge them periodically. It is possible but requires much more code and cycles. Automatically select --tail-synthesize when --overwrite is provided. Signed-off-by: Wang Nan <wangnan0@huawei.com> Cc: He Kuang <hekuang@huawei.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1468485287-33422-16-git-send-email-wangnan0@huawei.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-14 16:34:47 +08:00
bool tail_synthesize;
perf tools: Enable overwrite settings This patch allows following config terms and option: Globally setting events to overwrite; # perf record --overwrite ... Set specific events to be overwrite or no-overwrite. # perf record --event cycles/overwrite/ ... # perf record --event cycles/no-overwrite/ ... Add missing config terms and update the config term array size because the longest string length has changed. For overwritable events, it automatically selects attr.write_backward since perf requires it to be backward for reading. Test result: # perf record --overwrite -e syscalls:*enter_nanosleep* usleep 1 [ perf record: Woken up 2 times to write data ] [ perf record: Captured and wrote 0.011 MB perf.data (1 samples) ] # perf evlist -v syscalls:sys_enter_nanosleep: type: 2, size: 112, config: 0x134, { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|PERIOD|RAW, disabled: 1, inherit: 1, mmap: 1, comm: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, write_backward: 1 # Tip: use 'perf evlist --trace-fields' to show fields for tracepoint events Signed-off-by: Wang Nan <wangnan0@huawei.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Nilay Vaish <nilayvaish@gmail.com> Cc: Zefan Li <lizefan@huawei.com> Cc: pi3orama@163.com Link: http://lkml.kernel.org/r/1468485287-33422-14-git-send-email-wangnan0@huawei.com Signed-off-by: He Kuang <hekuang@huawei.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-07-14 16:34:45 +08:00
bool overwrite;
bool ignore_missing_thread;
unsigned int freq;
unsigned int mmap_pages;
unsigned int auxtrace_mmap_pages;
unsigned int user_freq;
u64 branch_stack;
perf record: Add ability to name registers to record This patch modifies the -I/--int-regs option to enablepassing the name of the registers to sample on interrupt. Registers can be specified by their symbolic names. For instance on x86, --intr-regs=ax,si. The motivation is to reduce the size of the perf.data file and the overhead of sampling by only collecting the registers useful to a specific analysis. For instance, for value profiling, sampling only the registers used to passed arguements to functions. With no parameter, the --intr-regs still records all possible registers based on the architecture. To name registers, it is necessary to use the long form of the option, i.e., --intr-regs: $ perf record --intr-regs=si,di,r8,r9 ..... To record any possible registers: $ perf record -I ..... $ perf report --intr-regs ... To display the register, one can use perf report -D To list the available registers: $ perf record --intr-regs=\? available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15 Signed-off-by: Stephane Eranian <eranian@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1441039273-16260-4-git-send-email-eranian@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-09-01 00:41:12 +08:00
u64 sample_intr_regs;
u64 default_interval;
u64 user_interval;
size_t auxtrace_snapshot_size;
const char *auxtrace_snapshot_opts;
bool sample_transaction;
unsigned initial_delay;
bool use_clockid;
clockid_t clockid;
unsigned int proc_map_timeout;
};
struct option;
extern const char * const *record_usage;
extern struct option *record_options;
#endif