mirror of
git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2026-03-22 15:36:55 +08:00
bdd051e249
Currently -d/--data option controls both PERF_SAMPLE_ADDR bit and
perf_event_attr.mmap_data flag. Separate them using new --data-mmap
option to support recording only one of them.
For data-type profiling, data MMAP is unnecessary but it wastes a lot
of space in the ring buffer and data file.
Committer testing:
On an idle system:
root@x1:~# perf record -d -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 5.672 MB perf.data (1075 samples) ]
root@x1:~# ls -la perf.data
-rw-------. 1 root root 5982480 Dec 16 15:34 perf.data
root@x1:~# perf evlist -v
cpu_atom/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
cpu_core/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|ADDR|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
dummy:u: type: 1 (PERF_TYPE_SOFTWARE), size: 144, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|ADDR|CPU|IDENTIFIER|DATA_SRC, read_format: ID|LOST, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, build_id: 1
root@x1:~#
Now with just --data-mmap we will not save that much, as only DATA_SRC
will not be enabled in sample_type:
root@x1:~# perf record --data-mmap -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 5.576 MB perf.data (716 samples) ]
root@x1:~# ls -la perf.data
-rw-------. 1 root root 5880112 Dec 16 15:37 perf.data
root@x1:~# perf evlist -v
cpu_atom/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
cpu_core/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
dummy:u: type: 1 (PERF_TYPE_SOFTWARE), size: 144, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER, read_format: ID|LOST, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, mmap_data: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, build_id: 1
root@x1:~#
To complete, just with DATA_SRC, no mmap_data:
root@x1:~# perf record --sample-mem-info -a sleep 1
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 1.407 MB perf.data (1311 samples) ]
root@x1:~# ls -la perf.data
-rw-------. 1 root root 1509224 Dec 16 15:40 perf.data
root@x1:~# perf evlist -v
cpu_atom/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0xa00000000 (cpu_atom/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
cpu_core/cycles/P: type: 0 (PERF_TYPE_HARDWARE), size: 144, config: 0x400000000 (cpu_core/PERF_COUNT_HW_CPU_CYCLES/), { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|CPU|PERIOD|IDENTIFIER|DATA_SRC, read_format: ID|LOST, disabled: 1, freq: 1, precise_ip: 3, sample_id_all: 1
dummy:u: type: 1 (PERF_TYPE_SOFTWARE), size: 144, config: 0x9 (PERF_COUNT_SW_DUMMY), { sample_period, sample_freq }: 1, sample_type: IP|TID|TIME|CPU|IDENTIFIER|DATA_SRC, read_format: ID|LOST, exclude_kernel: 1, exclude_hv: 1, mmap: 1, comm: 1, task: 1, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1, build_id: 1
root@x1:~#
Reviewed-by: Ian Rogers <irogers@google.com>
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: James Clark <james.clark@linaro.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
99 lines
2.5 KiB
C
99 lines
2.5 KiB
C
/* 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 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 sample_identifier;
|
|
bool sample_data_src;
|
|
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;
|
|
bool record_cgroup;
|
|
bool record_switch_events;
|
|
bool record_switch_events_set;
|
|
bool record_data_mmap;
|
|
bool record_data_mmap_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;
|
|
bool kcore;
|
|
bool text_poke;
|
|
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;
|
|
bool use_clockid;
|
|
clockid_t clockid;
|
|
u64 clockid_res_ns;
|
|
int nr_cblocks;
|
|
int affinity;
|
|
int mmap_flush;
|
|
unsigned int comp_level;
|
|
unsigned int nr_threads_synthesize;
|
|
int ctl_fd;
|
|
int ctl_fd_ack;
|
|
bool ctl_fd_close;
|
|
int synth;
|
|
int threads_spec;
|
|
const char *threads_user_spec;
|
|
u64 off_cpu_thresh_ns;
|
|
};
|
|
|
|
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
|