OpenCloudOS-Kernel/tools/perf/util/record.h

94 lines
2.4 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _PERF_RECORD_H
#define _PERF_RECORD_H
#include <time.h>
#include <stdbool.h>
#include <linux/types.h>
#include <linux/stddef.h>
#include <linux/perf_event.h>
#include "util/target.h"
struct option;
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_phys_addr;
bool sample_data_page_size;
bool sample_code_page_size;
bool sample_weight;
bool sample_time;
bool sample_time_set;
bool sample_cpu;
bool period;
bool period_set;
bool running_time;
bool full_auxtrace;
bool auxtrace_snapshot_mode;
bool auxtrace_snapshot_on_exit;
bool auxtrace_sample_mode;
bool record_namespaces;
perf record: Add --all-cgroups option The --all-cgroups option is to enable cgroup profiling support. It tells kernel to record CGROUP events in the ring buffer so that perf report can identify task/cgroup association later. [root@seventh ~]# perf record --all-cgroups --namespaces /wb/cgtest [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.042 MB perf.data (558 samples) ] [root@seventh ~]# perf report --stdio -s cgroup_id,cgroup,pid # To display the perf.data header info, please use --header/--header-only options. # # # Total Lost Samples: 0 # # Samples: 558 of event 'cycles' # Event count (approx.): 458017341 # # Overhead cgroup id (dev/inode) Cgroup Pid:Command # ........ ..................... .......... ............... # 33.15% 4/0xeffffffb /sub 9615:looper0 32.83% 4/0xf00002f5 /sub/cgrp2 9620:looper2 32.79% 4/0xf00002f4 /sub/cgrp1 9619:looper1 0.35% 4/0xf00002f5 /sub/cgrp2 9618:cgtest 0.34% 4/0xf00002f4 /sub/cgrp1 9617:cgtest 0.32% 4/0xeffffffb / 9615:looper0 0.11% 4/0xeffffffb /sub 9617:cgtest 0.10% 4/0xeffffffb /sub 9618:cgtest # # (Tip: Sample related events with: perf record -e '{cycles,instructions}:S') # [root@seventh ~]# Signed-off-by: Namhyung Kim <namhyung@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lore.kernel.org/lkml/20200325124536.2800725-8-namhyung@kernel.org Link: http://lore.kernel.org/lkml/20200402015249.3800462-1-namhyung@kernel.org [ Extracted the HAVE_FILE_HANDLE from the followup patch ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-03-25 20:45:34 +08:00
bool record_cgroup;
bool record_switch_events;
bool record_switch_events_set;
bool all_kernel;
bool all_user;
bool kernel_callchains;
bool user_callchains;
bool tail_synthesize;
bool overwrite;
bool ignore_missing_thread;
bool strict_freq;
bool sample_id;
bool no_bpf_event;
perf record: Put a copy of kcore into the perf.data directory Add a new 'perf record' option '--kcore' which will put a copy of /proc/kcore, kallsyms and modules into a perf.data directory. Note, that without the --kcore option, output goes to a file as previously. The tools' -o and -i options work with either a file name or directory name. Example: $ sudo perf record --kcore uname $ sudo tree perf.data perf.data ├── kcore_dir │   ├── kallsyms │   ├── kcore │   └── modules └── data $ sudo perf script -v build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. Using CPUID GenuineIntel-6-8E-A Using perf.data/kcore_dir/kcore for kernel data Using perf.data/kcore_dir/kallsyms for symbols perf 19058 506778.423729: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423733: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423734: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423736: 117 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) perf 19058 506778.423738: 2092 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) perf 19058 506778.423740: 37380 cycles: ffffffffa2f121d0 perf_event_addr_filters_exec+0x0 (vmlinux) uname 19058 506778.423751: 582673 cycles: ffffffffa303a407 propagate_protected_usage+0x147 (vmlinux) uname 19058 506778.423892: 2241841 cycles: ffffffffa2cae0c9 unwind_next_frame.part.5+0x79 (vmlinux) uname 19058 506778.424430: 2457397 cycles: ffffffffa3019232 check_memory_region+0x52 (vmlinux) Committer testing: # rm -rf perf.data* # perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.024 MB perf.data (7 samples) ] # ls -l perf.data -rw-------. 1 root root 34772 Oct 21 11:08 perf.data # perf record --kcore uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.024 MB perf.data (7 samples) ] ls[root@quaco ~]# ls -lad perf.data* drwx------. 3 root root 4096 Oct 21 11:08 perf.data -rw-------. 1 root root 34772 Oct 21 11:08 perf.data.old # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1 # perf evlist -v -i perf.data/data cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1 # Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lore.kernel.org/lkml/20191004083121.12182-6-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-10-04 16:31:21 +08:00
bool kcore;
bool text_poke;
perf record: Add --buildid-mmap option to enable PERF_RECORD_MMAP2's build id Add --buildid-mmap option to enable build id in PERF_RECORD_MMAP2 events. It will only work if there's kernel support for that and it disables build id cache (implies --no-buildid). It's also possible to enable it permanently via config option in ~/.perfconfig file: [record] build-id=mmap Also added build_id bit in the verbose output for perf_event_attr: # perf record --buildid-mmap -vv ... perf_event_attr: type 1 size 120 ... build_id 1 Adding also missing text_poke bit. Committer testing: $ perf record -h build Usage: perf record [<options>] [<command>] or: perf record [<options>] -- <command> [<options>] -B, --no-buildid do not collect buildids in perf.data -N, --no-buildid-cache do not update the buildid cache --buildid-all Record build-id of all DSOs regardless of hits --buildid-mmap Record build-id in map events $ $ perf record --buildid-mmap sleep 1 Failed: no support to record build id in mmap events, update your kernel. $ After adding the needed kernel bits in a test kernel: $ perf record -vv --buildid-mmap sleep 1 |& grep -m1 build Enabling build id in mmap2 events. $ perf evlist -v cycles:u: size: 120, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, exclude_kernel: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, build_id: 1 $ Signed-off-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Ian Rogers <irogers@google.com> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexei Budankov <abudankov@huawei.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lore.kernel.org/lkml/20201214105457.543111-16-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-12-14 18:54:57 +08:00
bool build_id;
unsigned int freq;
unsigned int mmap_pages;
unsigned int auxtrace_mmap_pages;
unsigned int user_freq;
u64 branch_stack;
u64 sample_intr_regs;
u64 sample_user_regs;
u64 default_interval;
u64 user_interval;
size_t auxtrace_snapshot_size;
const char *auxtrace_snapshot_opts;
const char *auxtrace_sample_opts;
bool sample_transaction;
int initial_delay;
bool use_clockid;
clockid_t clockid;
u64 clockid_res_ns;
int nr_cblocks;
int affinity;
int mmap_flush;
unsigned int comp_level;
perf record: Add num-synthesize-threads option To control degree of parallelism of the synthesize_mmap() code which is scanning /proc/PID/task/PID/maps and can be time consuming. Mimic perf top way of handling the option. If not specified will default to 1 thread, i.e. default behavior before this option. On a desktop computer the processing of /proc/PID/task/PID/maps isn't slow enough to warrant parallel processing and the thread creation has some cost - hence the default of 1. On a loaded server with >100 cores it is possible to see synthesis times in the order of seconds and in this case having the option is desirable. As the processing is a synchronization point, it is legitimate to worry if Amdahl's law will apply to this patch. Profiling with this patch in place: https://lore.kernel.org/lkml/20200415054050.31645-4-irogers@google.com/ shows: ... - 32.59% __perf_event__synthesize_threads - 32.54% __event__synthesize_thread + 22.13% perf_event__synthesize_mmap_events + 6.68% perf_event__get_comm_ids.constprop.0 + 1.49% process_synthesized_event + 1.29% __GI___readdir64 + 0.60% __opendir ... That is the processing is 1.49% of execution time and there is plenty to make parallel. This is shown in the benchmark in this patch: https://lore.kernel.org/lkml/20200415054050.31645-2-irogers@google.com/ Computing performance of multi threaded perf event synthesis by synthesizing events on CPU 0: Number of synthesis threads: 1 Average synthesis took: 127729.000 usec (+- 3372.880 usec) Average num. events: 21548.600 (+- 0.306) Average time per event 5.927 usec Number of synthesis threads: 2 Average synthesis took: 88863.500 usec (+- 385.168 usec) Average num. events: 21552.800 (+- 0.327) Average time per event 4.123 usec Number of synthesis threads: 3 Average synthesis took: 83257.400 usec (+- 348.617 usec) Average num. events: 21553.200 (+- 0.327) Average time per event 3.863 usec Number of synthesis threads: 4 Average synthesis took: 75093.000 usec (+- 422.978 usec) Average num. events: 21554.200 (+- 0.200) Average time per event 3.484 usec Number of synthesis threads: 5 Average synthesis took: 64896.600 usec (+- 353.348 usec) Average num. events: 21558.000 (+- 0.000) Average time per event 3.010 usec Number of synthesis threads: 6 Average synthesis took: 59210.200 usec (+- 342.890 usec) Average num. events: 21560.000 (+- 0.000) Average time per event 2.746 usec Number of synthesis threads: 7 Average synthesis took: 54093.900 usec (+- 306.247 usec) Average num. events: 21562.000 (+- 0.000) Average time per event 2.509 usec Number of synthesis threads: 8 Average synthesis took: 48938.700 usec (+- 341.732 usec) Average num. events: 21564.000 (+- 0.000) Average time per event 2.269 usec Where average time per synthesized event goes from 5.927 usec with 1 thread to 2.269 usec with 8. This isn't a linear speed up as not all of synthesize code has been made parallel. If the synthesis time was about 10 seconds then using 8 threads may bring this down to less than 4. Signed-off-by: Stephane Eranian <eranian@google.com> Reviewed-by: Ian Rogers <irogers@google.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Alexey Budankov <alexey.budankov@linux.intel.com> Cc: Kan Liang <kan.liang@linux.intel.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Tony Jones <tonyj@suse.de> Cc: yuzhoujian <yuzhoujian@didichuxing.com> Link: http://lore.kernel.org/lkml/20200422155038.9380-1-irogers@google.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-04-22 23:50:38 +08:00
unsigned int nr_threads_synthesize;
int ctl_fd;
int ctl_fd_ack;
bool ctl_fd_close;
int synth;
};
extern const char * const *record_usage;
extern struct option *record_options;
int record__parse_freq(const struct option *opt, const char *str, int unset);
static inline bool record_opts__no_switch_events(const struct record_opts *opts)
{
return opts->record_switch_events_set && !opts->record_switch_events;
}
#endif // _PERF_RECORD_H