perf是否锁定配置文件用户空间互斥？

Question

摘要:perf lock配置文件pthread_mutex？

细节:

该工具perf有一个选项perf lock.手册页说:

You can analyze various lock behaviours and statistics with this perf lock command.
   'perf lock record <command>' records lock events
    between start and end <command>. And this command
    produces the file "perf.data" which contains tracing
    results of lock events.

    'perf lock trace' shows raw lock events.

    'perf lock report' reports statistical data.

但是当我试着跑步时,perf lock record我得到一个错误说:invalid or unsupported event: 'lock:lock_acquire'.我看了,似乎错误可能是因为我的内核没有编译CONFIG_LOCKDEP或CONFIG_LOCK_STAT.

我的问题是:是否perf lock报告与用户空间锁(如pthread_mutex)或仅内核锁相关的事件？我对分析主要在用户空间中运行的应用程序更感兴趣.我认为perf中的这个选项看起来很有意思,但是因为我没有编译(或获得)新内核就无法运行它,我有兴趣在尝试之前更好地了解它的作用.

Answer 1

摘要:perf锁定配置文件pthread_mutex？

摘要:否,因为在用户空间pthread_mutex中没有定义任何跟踪点.

根据源文件tools/perf/builtin-lock.c(http://lxr.free-electrons.com/source/tools/perf/builtin-lock.c#L939)cmd_lock调用 __cmd_record,它定义perf record(via -e TRACEPOINT_NAME)的几个跟踪点并将选项传递-R -m 1024 -c 1给perf report.定义的跟踪点列表lock_tracepoints:

842 static const struct perf_evsel_str_handler lock_tracepoints[] = {
843         { "lock:lock_acquire",   perf_evsel__process_lock_acquire,   }, /* CONFIG_LOCKDEP */
844         { "lock:lock_acquired",  perf_evsel__process_lock_acquired,  }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
845         { "lock:lock_contended", perf_evsel__process_lock_contended, }, /* CONFIG_LOCKDEP, CONFIG_LOCK_STAT */
846         { "lock:lock_release",   perf_evsel__process_lock_release,   }, /* CONFIG_LOCKDEP */
847 };

TRACE_EVENT(lock_acquire,..定义于 trace/events/lock.h.并且 trace_lock_acquire仅在kernel/locking/lockdep.c中定义(在debian代码库中重新检查:http://codesearch.debian.net/search？q = trace_lock_acquire ).根据以下内容,只有内核中缺少CONFIG_LOCKDEP kernel/locking/Makefile:( obj-$(CONFIG_LOCKDEP) += lockdep.o跟踪点是无条件定义的lockdep.c.

根据https://www.kernel.org/doc/Documentation/trace/tracepoints.txt,所有跟踪点都是仅内核的,因此perf lock不会分析用户空间锁.

您可以尝试LTTng中的跟踪点,LTTng是声明用户空间跟踪点的项目(http://lttng.org/ust).但是没有现成的锁定统计信息,只有跟踪点上的原始数据.您还应该使用tracef()宏定义跟踪点(重新编译pthreads/glibc,或者尝试在pthread周围创建自己的包装器).