forked from Minki/linux
4ea648aec0
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>
85 lines
1.9 KiB
C
85 lines
1.9 KiB
C
#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"
|
|
|
|
#ifndef NSEC_PER_SEC
|
|
# define NSEC_PER_SEC 1000000000ULL
|
|
#endif
|
|
#ifndef NSEC_PER_USEC
|
|
# define NSEC_PER_USEC 1000ULL
|
|
#endif
|
|
|
|
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;
|
|
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 period;
|
|
bool running_time;
|
|
bool full_auxtrace;
|
|
bool auxtrace_snapshot_mode;
|
|
bool record_switch_events;
|
|
bool all_kernel;
|
|
bool all_user;
|
|
bool tail_synthesize;
|
|
bool overwrite;
|
|
unsigned int freq;
|
|
unsigned int mmap_pages;
|
|
unsigned int auxtrace_mmap_pages;
|
|
unsigned int user_freq;
|
|
u64 branch_stack;
|
|
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
|