linux - 为什么 perf stat 将 "stalled-cycles-backend"显示为 <不支持>？

Question

运行 perf stat ls 显示:

Performance counter stats for 'ls':

          1.388670 task-clock                #    0.067 CPUs utilized          
                 2 context-switches          #    0.001 M/sec                  
                 0 cpu-migrations            #    0.000 K/sec                  
               266 page-faults               #    0.192 M/sec                  
           3515391 cycles                    #    2.531 GHz                    
           2096636 stalled-cycles-frontend   #   59.64% frontend cycles idle   
   <not supported> stalled-cycles-backend  
           2927468 instructions              #    0.83  insns per cycle        
                                             #    0.72  stalled cycles per insn
            615636 branches                  #  443.328 M/sec                  
             22172 branch-misses             #    3.60% of all branches        

       0.020657192 seconds time elapsed

为什么 stalled-cycles-backend 显示为“不受支持”？我需要什么样的 CPU、硬件、内核或用户空间软件才能看到这个值？

目前在不同的 Intel Core i5 和 i7 系统(Ivy Bridge 类型)上用匹配的 perf 版本在 RHEL 和 Linux 3.12 for x86_64 上试过这个。它们都不支持stalled-cycles-backend。

更多信息:

$ perf list | grep stalled
  stalled-cycles-frontend OR idle-cycles-frontend    [Hardware event]
  stalled-cycles-frontend OR cpu/stalled-cycles-frontend/ [Kernel PMU event]

$ ls /sys/devices/cpu/events/
branch-instructions  bus-cycles    cache-references  instructions  mem-stores
branch-misses        cache-misses  cpu-cycles        mem-loads     stalled-cycles-frontend

$ cat /sys/bus/event_source/devices/cpu/events/stalled-cycles-frontend
event=0x0e,umask=0x01,inv,cmask=0x01

编辑:刚刚在 AMD Phenom II X6 1045T CPU 上尝试了这个，在 Ubuntu 12.04 和 Linux 3.2(32 位)下 - 这里它确实显示了 stalled-cycles-frontend 的值 和 stalled-cycles-backend。

Answer 1

看起来 perf 还没有更新以了解 Ivy Bridge 支持的所有性能监控事件。幸运的是，有一个通用的(尽管很麻烦)界面允许您访问性能监控事件的完整列表。当我快速查看列表时，我没有在列表中看到 stalled-cycles-backend，但也许我错过了，或者他们可能已经将它分解为可能使后端停止的所有不同事件.

我们从

开始

perf list --help

...显示以下注意

    1. Intel(R) 64 and IA-32 Architectures Software Developer's Manual
       Volume 3B: System Programming Guide
       http://www.intel.com/Assets/PDF/manual/253669.pdf

...用你最终到达的那个 URL 武装起来

http://www.intel.com/content/dam/www/public/us/en/documents/manuals/64-ia-32-architectures-software-developer-vol-3b-part-2-manual.pdf

...你想要第 19.3 节

19.3 PERFORMANCE MONITORING EVENTS FOR 3RD GENERATION INTEL® CORE™ PROCESSORS 3rd generation Intel® Core™ processors and Intel Xeon processor E3-1200 v2 product family are based on Intel microarchitecture code name Ivy Bridge. They support architectural performance-monitoring events listed in Table 19-1. Non-architectural performance-monitoring events in the processor core are listed in Table 19-5. The events in Table 19-5 apply to processors with CPUID signature of DisplayFamily_DisplayModel encoding with the following values: 06_3AH.

...因此对于架构事件，您需要表 19-1

19.1 ARCHITECTURAL PERFORMANCE-MONITORING EVENTS Architectural performance events are introduced in Intel Core Solo and Intel Core Duo processors. They are also supported on processors based on Intel Core microarchitecture. Table 19-1 lists pre-defined architectural performance events that can be configured using general-purpose performance counters and associated event-select registers.

**Table 19-1. Architectural Performance Events

...现在是棘手的部分，您将 UMask Value 作为高 2 位十六进制数字，Event Num 是 4 的低 2 位十六进制数字将提供给 perf stat 的十六进制数字硬件寄存器编号。

perf stat --help

   -e, --event=
       Select the PMU event. Selection can be a symbolic event name (use
       perf list to list all events) or a raw PMU event (eventsel+umask) in
       the form of rNNN where NNN is a hexadecimal event descriptor.

...它说 NNN 但你可以给它 NNNN。让我们验证它是否有效，让我们向 perf stat 请求缓存未命中，既可以是符号事件名称，也可以是表 19-1 中的十六进制数字。为简单起见，我们将调用 date 命令。

$ perf stat -e r412e -e cache-misses date

Fri Mar 28 09:28:52 CDT 2014

Performance counter stats for 'date':

          2292 r412e                                                       
          2292 cache-misses                                                

   0.003322663 seconds time elapsed

$ 

如您所见，两者都报告了相同的数字，到目前为止还不错。现在我们转到表 19-5 的非架构硬件寄存器，这里列出的太多了，但我会列出一些: