Benchmark C++ ifstream and mmap

After reading Which is fastest: read, fread, ifstream or mmap?, I try to benchmark C++ ifstream and mmap myself.

The test file is number.txt, and the size is 4GiB:

# ls -alt number.txt
-rw-r--r-- 1 root root 4294967296 Apr  2 13:51 number.txt

The test_ifstream.cpp is like this:

#include <chrono>
#include <fstream>
#include <iostream>
#include <string>
#include <vector>

const std::string FILE_NAME = "number.txt";
const std::string RESULT_FILE_NAME = "result.txt";

char chunk[1048576];

int main(void)
{
    std::ifstream ifs(FILE_NAME, std::ios_base::binary);
    if (!ifs) {
        std::cerr << "Error opeing " << FILE_NAME << std::endl;
        exit(1);
    }
    std::ofstream ofs(RESULT_FILE_NAME, std::ios_base::binary);
    if (!ofs) {
        std::cerr << "Error opeing " << RESULT_FILE_NAME << std::endl;
        exit(1);
    }

    std::vector<std::chrono::milliseconds> duration_vec(5);
    for (std::vector<std::chrono::milliseconds>::size_type i = 0; i < duration_vec.size(); i++) {
        unsigned long long res = 0;
        ifs.seekg(0);
        auto begin = std::chrono::system_clock::now();

        for (size_t j = 0; j < 4096; j++) {
            ifs.read(chunk, sizeof(chunk));
            for (size_t k = 0; k < sizeof(chunk); k++) {
                res += chunk[k];
            }
        }
        ofs << res;

        duration_vec[i] = std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now() - begin);
        std::cout<< duration_vec[i].count() << std::endl;
    }

    std::chrono::milliseconds total_time{0};
    for (auto const& v : duration_vec) {
        total_time += v;
    }
    std::cout << "Average exec time: " << total_time.count() / duration_vec.size() << std::endl;
    return 0;
}

The program reads 1MiB(1024 * 1024 = 1048576) every time (the total count is 4096). Use -O2 optimization:

# clang++ -O2 test_ifstream.cpp -o test_ifstream
# ./test_ifstream
57208
57085
57061
57105
57069
Average exec time: 57105

The average execution time is 57105 ms. From the htop output:

We can see test_ifstream occupies very little memory.

The following is test_mmap file:

#include <chrono>
#include <fstream>
#include <iostream>
#include <string>
#include <vector>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/mman.h>


const std::string FILE_NAME = "number.txt";
const std::string RESULT_FILE_NAME = "result.txt";

int main(void)
{
    int fd = ::open(FILE_NAME.c_str(), O_RDONLY);
    if (fd < 0) {
        std::cerr << "Error opeing " << FILE_NAME << std::endl;
        exit(1);
    }
    std::ofstream ofs(RESULT_FILE_NAME, std::ios_base::binary);
    if (!ofs) {
        std::cerr << "Error opeing " << RESULT_FILE_NAME << std::endl;
        exit(1);
    }

    auto file_size = lseek(fd, 0, SEEK_END);

    std::vector<std::chrono::milliseconds> duration_vec(5);
    for (std::vector<std::chrono::milliseconds>::size_type i = 0; i < duration_vec.size(); i++) {
        lseek(fd, 0, SEEK_SET);
        unsigned long long res = 0;
        auto begin = std::chrono::system_clock::now();

        char *chunk = reinterpret_cast<char*>(mmap(NULL, file_size, PROT_READ, MAP_FILE | MAP_SHARED, fd, 0));
        char *addr = chunk;

        for (size_t j = 0; j < file_size; j++) {
            res += *chunk++;
        }
        ofs << res;

        munmap(addr, file_size);

        duration_vec[i] = std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::system_clock::now() - begin);
        std::cout<< duration_vec[i].count() << std::endl;
    }

    std::chrono::milliseconds total_time{0};
    for (auto const& v : duration_vec) {
        total_time += v;
    }
    std::cout << "Average exec time: " << total_time.count() / duration_vec.size() << std::endl;

    ::close(fd);
    return 0;
}

Still use -O2 optimization:

# clang++ -O2 test_mmap.cpp -o test_mmap
# ./test_mmap
57241
57095
57038
57008
57175
Average read time: 57111

We can see the execution time of test_mmap is similar as test_ifstream, whereas test_mmap uses more memory: