File: linux-perf-events.h

package info (click to toggle)
simdjson 4.2.4-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 27,936 kB
  • sloc: cpp: 171,612; ansic: 19,122; sh: 1,126; python: 842; makefile: 47; ruby: 25; javascript: 13
file content (105 lines) | stat: -rw-r--r-- 2,806 bytes parent folder | download | duplicates (2)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
#pragma once
#ifdef __linux__

#include <asm/unistd.h>       // for __NR_perf_event_open
#include <linux/perf_event.h> // for perf event constants
#include <sys/ioctl.h>        // for ioctl
#include <unistd.h>           // for syscall

#include <cerrno>  // for errno
#include <cstring> // for memset
#include <stdexcept>

#include <iostream>
#include <vector>

template <int TYPE = PERF_TYPE_HARDWARE> class LinuxEvents {
  int fd;
  bool working;
  perf_event_attr attribs{};
  size_t num_events{};
  std::vector<uint64_t> temp_result_vec{};
  std::vector<uint64_t> ids{};

public:
  explicit LinuxEvents(std::vector<int> config_vec) : fd(0), working(true) {
    memset(&attribs, 0, sizeof(attribs));
    attribs.type = TYPE;
    attribs.size = sizeof(attribs);
    attribs.disabled = 1;
    attribs.exclude_kernel = 1;
    attribs.exclude_hv = 1;

    attribs.sample_period = 0;
    attribs.read_format = PERF_FORMAT_GROUP | PERF_FORMAT_ID;
    const int pid = 0;  // the current process
    const int cpu = -1; // all CPUs
    const unsigned long flags = 0;

    int group = -1; // no group
    num_events = config_vec.size();
    ids.resize(config_vec.size());
    uint32_t i = 0;
    for (auto config : config_vec) {
      attribs.config = config;
      int _fd = static_cast<int>(syscall(__NR_perf_event_open, &attribs, pid, cpu, group, flags));
      if (_fd == -1) {
        report_error("perf_event_open");
      }
      ioctl(_fd, PERF_EVENT_IOC_ID, &ids[i++]);
      if (group == -1) {
        group = _fd;
        fd = _fd;
      }
    }

    temp_result_vec.resize(num_events * 2 + 1);
  }

  ~LinuxEvents() { if (fd != -1) { close(fd); } }

  inline void start() {
    if (fd != -1) {
      if (ioctl(fd, PERF_EVENT_IOC_RESET, PERF_IOC_FLAG_GROUP) == -1) {
        report_error("ioctl(PERF_EVENT_IOC_RESET)");
      }

      if (ioctl(fd, PERF_EVENT_IOC_ENABLE, PERF_IOC_FLAG_GROUP) == -1) {
        report_error("ioctl(PERF_EVENT_IOC_ENABLE)");
      }
    }
  }

  inline void end(std::vector<unsigned long long> &results) {
    if (fd != -1) {
      if (ioctl(fd, PERF_EVENT_IOC_DISABLE, PERF_IOC_FLAG_GROUP) == -1) {
        report_error("ioctl(PERF_EVENT_IOC_DISABLE)");
      }

      if (read(fd, temp_result_vec.data(), temp_result_vec.size() * 8) == -1) {
        report_error("read");
      }
    }
    // our actual results are in slots 1,3,5, ... of this structure
    for (uint32_t i = 1; i < temp_result_vec.size(); i += 2) {
      results[i / 2] = temp_result_vec[i];
    }
    for (uint32_t i = 2; i < temp_result_vec.size(); i += 2) {
      if(ids[i/2-1] != temp_result_vec[i]) {
        report_error("event mismatch");
      }
    }


  }

  bool is_working() {
    return working;
  }

private:
  void report_error(const std::string &) {
    working = false;
  }
};
#endif