无法使用 linux perf 对硬件缓存事件进行采样

Question

由于某种原因，我无法采样 (perf record) 硬件缓存事件：

# perf record -e L1-dcache-stores -a -c 100 -- sleep 5
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.607 MB perf.data (~26517 samples) ]
# perf script

但我可以数一数（perf stat）：

# perf stat -e L1-dcache-stores -a -- sleep 5
  Performance counter stats for 'sleep 5':

     711,781 L1-dcache-stores                                            

     5.000842990 seconds time elapsed

我尝试了不同的 CPU、操作系统版本（和内核版本）、perf 版本，但结果是一样的。这是预期的行为吗？是什么原因？ perf 不能对此发出警告吗？

Answer 1

perf evlist -vvv 输出的三个 perf.data 不同，一个是缓存事件，第二个是软件事件，最后一个是硬件周期事件：

echo '2^234567 %2' | perf record -e L1-dcache-stores -c 100 -o cache bc
echo '2^234567 %2' | perf record -e cycles -c 100 -o cycles bc
echo '2^234567 %2' | perf record -e cs -c 100 -o cs bc

 perf evlist -vvv -i cache
L1-dcache-stores: sample_freq=100, type: 3, config: 256, size: 96, sample_type: IP|TID|TIME, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1
 perf evlist -vvv -i cycles
cycles: sample_freq=100, size: 96, sample_type: IP|TID|TIME, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1
 perf evlist -vvv -i cs
cs: sample_freq=100, type: 1, config: 3, size: 96, sample_type: IP|TID|TIME, disabled: 1, inherit: 1, mmap: 1, mmap2: 1, comm: 1, enable_on_exec: 1, sample_id_all: 1, exclude_guest: 1

有不同的类型，类型定义为

0028 enum perf_type_id {
0029     PERF_TYPE_HARDWARE          = 0,
0030     PERF_TYPE_SOFTWARE          = 1,
0031     PERF_TYPE_TRACEPOINT            = 2,
0032     PERF_TYPE_HW_CACHE          = 3,
0033     PERF_TYPE_RAW               = 4,
0034     PERF_TYPE_BREAKPOINT            = 5,
0035 
0036     PERF_TYPE_MAX,              /* non-ABI */
0037 };

Perf 脚本有一个 output 表，它定义了如何打印各种事件：http://lxr.free-electrons.com/source/tools/perf/builtin-script.c?v=3.16#L68

 68 /* default set to maintain compatibility with current format */
 69 static struct {
 70         bool user_set;
 71         bool wildcard_set;
 72         unsigned int print_ip_opts;
 73         u64 fields;
 74         u64 invalid_fields;
 75 } output[PERF_TYPE_MAX] = {
 76 
 77         [PERF_TYPE_HARDWARE] = {
 78                 .user_set = false,
 79 
 80                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 81                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 82                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 83                                   PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
 84 
 85                 .invalid_fields = PERF_OUTPUT_TRACE,
 86         },
 87 
 88         [PERF_TYPE_SOFTWARE] = {
 89                 .user_set = false,
 90 
 91                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
 92                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
 93                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
 94                                   PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
 95 
 96                 .invalid_fields = PERF_OUTPUT_TRACE,
 97         },
 98 
 99         [PERF_TYPE_TRACEPOINT] = {
100                 .user_set = false,
101 
102                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
103                                   PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
104                                   PERF_OUTPUT_EVNAME | PERF_OUTPUT_TRACE,
105         },
106 
107         [PERF_TYPE_RAW] = {
108                 .user_set = false,
109 
110                 .fields = PERF_OUTPUT_COMM | PERF_OUTPUT_TID |
111                               PERF_OUTPUT_CPU | PERF_OUTPUT_TIME |
112                               PERF_OUTPUT_EVNAME | PERF_OUTPUT_IP |
113                                   PERF_OUTPUT_SYM | PERF_OUTPUT_DSO,
114 
115                 .invalid_fields = PERF_OUTPUT_TRACE,
116         },
117 };
118 

因此，没有从类型为 3 - PERF_TYPE_HW_CACHE 的样本中打印任何字段的说明，并且perf script 不会打印它们。我们可以尝试在output数组中注册这个类型，甚至将补丁推送到内核。