Fast textfile reading in c++

Solution 1:

Updates: Be sure to check the (surprising) updates below the initial answer

Memory mapped files have served me well¹:

#include <boost/iostreams/device/mapped_file.hpp> // for mmap
#include <algorithm>  // for std::find
#include <iostream>   // for std::cout
#include <cstring>

int main()
{
    boost::iostreams::mapped_file mmap("input.txt", boost::iostreams::mapped_file::readonly);
    auto f = mmap.const_data();
    auto l = f + mmap.size();

    uintmax_t m_numLines = 0;
    while (f && f!=l)
        if ((f = static_cast<const char*>(memchr(f, '\n', l-f))))
            m_numLines++, f++;

    std::cout << "m_numLines = " << m_numLines << "\n";
}

This should be rather quick.

Update

In case it helps you test this approach, here's a version using mmap directly instead of using Boost: see it live on Coliru

#include <algorithm>
#include <iostream>
#include <cstring>

// for mmap:
#include <sys/mman.h>
#include <sys/stat.h>
#include <fcntl.h>

const char* map_file(const char* fname, size_t& length);

int main()
{
    size_t length;
    auto f = map_file("test.cpp", length);
    auto l = f + length;

    uintmax_t m_numLines = 0;
    while (f && f!=l)
        if ((f = static_cast<const char*>(memchr(f, '\n', l-f))))
            m_numLines++, f++;

    std::cout << "m_numLines = " << m_numLines << "\n";
}

void handle_error(const char* msg) {
    perror(msg); 
    exit(255);
}

const char* map_file(const char* fname, size_t& length)
{
    int fd = open(fname, O_RDONLY);
    if (fd == -1)
        handle_error("open");

    // obtain file size
    struct stat sb;
    if (fstat(fd, &sb) == -1)
        handle_error("fstat");

    length = sb.st_size;

    const char* addr = static_cast<const char*>(mmap(NULL, length, PROT_READ, MAP_PRIVATE, fd, 0u));
    if (addr == MAP_FAILED)
        handle_error("mmap");

    // TODO close fd at some point in time, call munmap(...)
    return addr;
}

Update

The last bit of performance I could squeeze out of this I found by looking at the source of GNU coreutils wc. To my surprise using the following (greatly simplified) code adapted from wc runs in about 84% of the time taken with the memory mapped file above:

static uintmax_t wc(char const *fname)
{
    static const auto BUFFER_SIZE = 16*1024;
    int fd = open(fname, O_RDONLY);
    if(fd == -1)
        handle_error("open");

    /* Advise the kernel of our access pattern.  */
    posix_fadvise(fd, 0, 0, 1);  // FDADVICE_SEQUENTIAL

    char buf[BUFFER_SIZE + 1];
    uintmax_t lines = 0;

    while(size_t bytes_read = read(fd, buf, BUFFER_SIZE))
    {
        if(bytes_read == (size_t)-1)
            handle_error("read failed");
        if (!bytes_read)
            break;

        for(char *p = buf; (p = (char*) memchr(p, '\n', (buf + bytes_read) - p)); ++p)
            ++lines;
    }

    return lines;
}

¹ see e.g. the benchmark here: How to parse space-separated floats in C++ quickly?

Solution 2:

4000 * 400,000 = 1.6 GB if you're hard drive isn't an SSD you're likely getting ~100 MB/s sequential read. That's 16 seconds just in I/O.

Since you don't elaborate on the specific code your using or how you need to parse these files (do you need to read it line by line, does the system have a lot of RAM could you read the whole file into a large RAM buffer and then parse it?) There's little you can do to speed up the process.

Memory mapped files won't offer any performance improvement when reading a file sequentially. Perhaps manually parsing large chunks for new lines rather than using "getline" would offer an improvement.

EDIT After doing some learning (thanks @sehe). Here's the memory mapped solution I would likely use.

#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/mman.h>
#include <sys/stat.h>
#include <errno.h>

int main() {
    char* fName = "big.txt";
    //
    struct stat sb;
    long cntr = 0;
    int fd, lineLen;
    char *data;
    char *line;
    // map the file
    fd = open(fName, O_RDONLY);
    fstat(fd, &sb);
    //// int pageSize;
    //// pageSize = getpagesize();
    //// data = mmap((caddr_t)0, pageSize, PROT_READ, MAP_PRIVATE, fd, pageSize);
    data = mmap((caddr_t)0, sb.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
    line = data;
    // get lines
    while(cntr < sb.st_size) {
        lineLen = 0;
        line = data;
        // find the next line
        while(*data != '\n' && cntr < sb.st_size) {
            data++;
            cntr++;
            lineLen++;
        }
        /***** PROCESS LINE *****/
        // ... processLine(line, lineLen);
    }
    return 0;
}

Solution 3:

Neil Kirk, unfortunately I can not reply to your comment (not enough reputation) but I did a performance test on ifstream an stringstream and the performance, reading a text file line by line, is exactly the same.

std::stringstream stream;
std::string line;
while(std::getline(stream, line)) {
}

This takes 1426ms on a 106MB file.

std::ifstream stream;
std::string line;
while(ifstream.good()) {
    getline(stream, line);
}

This takes 1433ms on the same file.

The following code is faster instead:

const int MAX_LENGTH = 524288;
char* line = new char[MAX_LENGTH];
while (iStream.getline(line, MAX_LENGTH) && strlen(line) > 0) {
}

This takes 884ms on the same file. It is just a little tricky since you have to set the maximum size of your buffer (i.e. maximum length for each line in the input file).