perf 是一个调查 Linux 中各种性能问题的有力工具。
# perf --help
usage: perf [--version] [--help] COMMAND [ARGS]
The most commonly used perf commands are:
annotate Read perf.data (created by perf record) and display annotated code
archive Create archive with object files with build-ids found in perf.data file
bench General framework for benchmark suites
buildid-cache Manage build-id cache.
buildid-list List the buildids in a perf.data file
diff Read two perf.data files and display the differential profile
evlist List the event names in a perf.data file
inject Filter to augment the events stream with additional information
kmem Tool to trace/measure kernel memory(slab) properties
kvm Tool to trace/measure kvm guest os
list List all symbolic event types
lock Analyze lock events
record Run a command and record its profile into perf.data
report Read perf.data (created by perf record) and display the profile
sched Tool to trace/measure scheduler properties (latencies)
script Read perf.data (created by perf record) and display trace output
stat Run a command and gather performance counter statistics
test Runs sanity tests.
timechart Tool to visualize total system behavior during a workload
top System profiling tool.
trace strace inspired tool
probe Define new dynamic tracepoints
annotate Read perf.data (created by perf record) and display annotated code
archive Create archive with object files with build-ids found in perf.data file
bench General framework for benchmark suites
buildid-cache Manage build-id cache.
buildid-list List the buildids in a perf.data file
diff Read two perf.data files and display the differential profile
evlist List the event names in a perf.data file
inject Filter to augment the events stream with additional information
kmem Tool to trace/measure kernel memory(slab) properties
kvm Tool to trace/measure kvm guest os
list List all symbolic event types
lock Analyze lock events
record Run a command and record its profile into perf.data
report Read perf.data (created by perf record) and display the profile
sched Tool to trace/measure scheduler properties (latencies)
script Read perf.data (created by perf record) and display trace output
stat Run a command and gather performance counter statistics
test Runs sanity tests.
timechart Tool to visualize total system behavior during a workload
top System profiling tool.
trace strace inspired tool
probe Define new dynamic tracepoints
See 'perf help COMMAND' for more information on a specific command.
perf 包含了:perf-stat (perf stat), perf-top (perf top), perf-record (perf record), perf-list (perf list)
perf list 主要是用于列出有哪些可用的event,可以供 perf top -e eventname 来分析。
perf top -e xxx
上面的 perf list [hw|sw...] 可以知道所有的 tracepoint events, 接下来我们就可以使用 perf top -e tracepoint-event 来专门获得指定的tracepoint的信息:
上面的 perf list [hw|sw...] 可以知道所有的 tracepoint events, 接下来我们就可以使用 perf top -e tracepoint-event 来专门获得指定的tracepoint的信息:
perf top常用选项有:
-e <event>:指明要分析的性能事件。
-p <pid>:Profile events on existing Process ID (comma sperated list). 仅分析目标进程及其创建的线程。
-k <path>:Path to vmlinux. Required for annotation functionality. 带符号表的内核映像所在的路径。
-K:不显示属于内核或模块的符号。
-U:不显示属于用户态程序的符号。
-d <n>:界面的刷新周期,默认为2s,因为perf top默认每2s从mmap的内存区域读取一次性能数据。
-g:得到函数的调用关系图。
# perf top -p `pidof mysqld`
Samples: 221 of event 'cycles', Event count (approx.): 10810377, UID: mysql
10.34% mysqld [.] my_strnncollsp_utf8
5.70% [kernel] [k] _spin_lock_irqsave
5.66% libc-2.12.so [.] __memset_sse2
5.55% [kernel] [k] remove_wait_queue
5.16% libc-2.12.so [.] __GI___strcmp_ssse3
4.36% [kernel] [k] __audit_syscall_exit
3.39% [kernel] [k] lookup_ioctx
3.28% [kernel] [k] find_next_bit
3.22% mysqld [.] lex_one_token(YYSTYPE*, THD*)
2.69% mysqld [.] Item::val_bool()
2.60% [kernel] [k] __do_softirq
2.53% mysqld [.] Protocol::send_result_set_row(List<Item>*)
2.52% [kernel] [k] local_bh_enable_ip
2.51% mysqld [.] my_strnncoll_binary
2.51% libc-2.12.so [.] memcpy
第一列:符号引发的性能事件的比例,默认指占用的cpu周期比例。
第二列:符号所在的DSO(Dynamic Shared Object),可以是应用程序、内核、动态链接库、模块。
第三列:DSO的类型。[.]表示此符号属于用户态的ELF文件,包括可执行文件与动态链接库)。[k]表述此符号属于内核或模块。
第四列:符号名。有些符号不能解析为函数名,只能用地址表示。