代码之家 › 专栏 › 技术社区 › valdo

文件映射与文件系统同步

shared-memory linux c

-1

valdo · 技术社区 · 8 年前

我有一个包含一些数据的文件,它也是内存映射的。这样我既有文件描述符又有指向映射页的指针。大多数数据只从映射中读取,但最终也会被修改。

这个数据结构是从不同的线程访问的,为了防止冲突,我同步了对它的访问(mutex和friends)。

WriteFile 在windows上, write

由于修改会更改文件大小,因此每次修改后都会重新初始化内存映射。也就是说,它是未映射的,然后再次映射(使用新大小)。

现在,这在windows上可以正常工作,但在linux(确切地说是android)上,映射的数据最终会暂时不一致(即在重试时数据是可以的)。似乎它没有反映新添加的数据。

sync , msync , syncfs

提前谢谢。

编辑:

这是一个伪代码,演示了我正在处理的场景。

struct CompressedGrid
{
    mutex m_Lock;
    int m_FileHandle;    
    void* m_pMappedMemory;

    Hdr* get_Hdr() { return /* the mapped memory with some offset*/; }

    void SaveGridCell(int idx, const Cell& cCompressed)
    {
        AutoLock scope(m_Lock);

        // Write to mapped memory
        get_Hdr()->m_pCellOffset[Idx] = /* current end of file */;

        // Append the data
        lseek64(m_FileHandle, 0, FILE_END);
        write(m_FileHandle, cCompressed.pPtr, cCompressed.nSize);

        // re-map
        munmap(...);
        m_pMappedMemory = mmap(...); // specify the new file size of course
    }

    bool DecodeGridCell(int idx, Cell& cRaw)
    {
        AutoLock scope(m_Lock);

        uint64_t nOffs = get_Hdr()->m_pCellOffset[Idx] = /* ;
        if (!nOffs)
            return false; // unavail

        const uint8_t* p = m_pMappedMemory + nOffs;

        cRaw.DecodeFrom(p); // This is where the problem appears!

        return true;
    }

1 回复 | 直到 8 年前

Nominal Animal 8 年前

使用 addr = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_NORESERVE, fd, offset)

如果文件大小更改,请使用 newaddr = mremap(addr, len, newlen, MREMAP_MAYMOVE) 更新映射以反映它。要扩展文件,请使用 ftruncate(fd, newlen)

你可以用 mprotect(addr, len, protflags) 更改映射中任何页上的保护(读/写)(两者必须在页边界上对齐)。您还可以通过 madvise()

当您更改映射时,使用 msync(partaddr, partlen, MS_SYNC | MS_INVALIDATE) 或 msync(partaddr, partlen, MS_ASYNC | MS_INVALIDATE) 以确保 partlen 来自的字符 partaddr 转发对其他映射和文件读取器可见。如果你使用 MS_SYNC ,仅当更新完成时才返回调用。这个 MS_ASYNC MS_INVALIDATE 不执行任何操作;但如果存在,则告诉内核确保这些更改也反映在这些更改中。

在2.6.19之后的Linux内核中, 异步 不执行任何操作,因为内核仍然正确地跟踪更改(不 msync() 是必要的,除了可能以前 munmap() ). 我不知道Android内核是否有改变这种行为的补丁;我想没有。为了在POSIXy系统中的可移植性,将它们保存在代码中仍然是一个好主意。

好吧,除非你真的用 ,内核将在它认为最好的时候进行更新。

因此,如果在继续之前需要对文件读取器可见一些更改,请使用 msync(areaptr, arealen, MS_SYNC | MS_INVALIDATE)

如果你不在乎确切的时刻,用 msync(areaptr, arealen, MS_ASYNC | MS_INVALIDATE) . 对于当前的Linux内核,这是一个禁止操作的操作,但是为了便于移植(如果性能需要的话,可能会被注释掉)和提醒开发人员(缺少)同步期望是一个好主意。

正如我对OP所评论的,我根本无法观察到Linux上的同步问题。(这并不意味着它不会在Android上发生,因为Android内核是 衍生产品 Linux内核,不完全相同。)

我相信 msync() 在Linux内核上根本不需要调用,因为2.6.19版本,只要映射使用标志 MAP_SHARED | MAP_NORESERVE ,并且未使用 O_DIRECT 旗帜。这种观点的原因是,在这种情况下,映射和文件访问应该使用完全相同的页面缓存页。

测试单c

#define  _POSIX_C_SOURCE  200809L
#define  _GNU_SOURCE
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <sys/wait.h>
#include <fcntl.h>
#include <signal.h>
#include <string.h>
#include <stdio.h>
#include <errno.h>

static inline int read_from(const int fd, void *const to, const size_t len, const off_t offset)
{
    char       *p = (char *)to;
    char *const q = (char *)to + len;
    ssize_t     n;

    if (lseek(fd, offset, SEEK_SET) != offset)
        return errno = EIO;

    while (p < q) {
        n = read(fd, p, (size_t)(q - p));
        if (n > 0)
            p += n;
        else
        if (n != -1)
            return errno = EIO;
        else
        if (errno != EINTR)
            return errno;
    }

    return 0;
}

static inline int write_to(const int fd, const void *const from, const size_t len, const off_t offset)
{
    const char *const q = (const char *)from + len;
    const char       *p = (const char *)from;
    ssize_t           n;

    if (lseek(fd, offset, SEEK_SET) != offset)
        return errno = EIO;

    while (p < q) {
        n = write(fd, p, (size_t)(q - p));
        if (n > 0)
            p += n;
        else
        if (n != -1)
            return errno = EIO;
        else
        if (errno != EINTR)
            return errno;
    }

    return 0;
}

int main(int argc, char *argv[])
{
    unsigned long  tests, n, merrs = 0, werrs = 0;
    size_t         page;
    long          *map, data[2];
    int            fd;
    char           dummy;

    if (argc != 3) {
        fprintf(stderr, "\n");
        fprintf(stderr, "Usage: %s FILENAME COUNT\n", argv[0]);
        fprintf(stderr, "\n");
        fprintf(stderr, "This program will test synchronization between a memory map\n");
        fprintf(stderr, "and reading/writing the underlying file, COUNT times.\n");
        fprintf(stderr, "\n");
        return EXIT_FAILURE;
    }

    if (sscanf(argv[2], " %lu %c", &tests, &dummy) != 1 || tests < 1) {
        fprintf(stderr, "%s: Invalid number of tests to run.\n", argv[2]);
        return EXIT_FAILURE;
    }

    /* Create the file. */
    page = sysconf(_SC_PAGESIZE);
    fd = open(argv[1], O_RDWR | O_CREAT | O_EXCL, 0644);
    if (fd == -1) {
        fprintf(stderr, "%s: Cannot create file: %s.\n", argv[1], strerror(errno));
        return EXIT_FAILURE;
    }
    if (ftruncate(fd, page) == -1) {
        fprintf(stderr, "%s: Cannot resize file: %s.\n", argv[1], strerror(errno));
        unlink(argv[1]);
        return EXIT_FAILURE;
    }

    /* Map it. */
    map = mmap(NULL, page, PROT_READ|PROT_WRITE, MAP_SHARED|MAP_NORESERVE, fd, 0);
    if (map == MAP_FAILED) {
        fprintf(stderr, "%s: Cannot map file: %s.\n", argv[1], strerror(errno));
        unlink(argv[1]);
        close(fd);
        return EXIT_FAILURE;
    }

    /* Test loop. */
    for (n = 0; n < tests; n++) {

        /* Update map. */
        map[0] = (long)(n + 1);
        map[1] = (long)(~n);

        /* msync(map, 2 * sizeof map[0], MAP_SYNC | MAP_INVALIDATE); */

        /* Check the file contents. */
        if (read_from(fd, data, sizeof data, 0)) {
            fprintf(stderr, "read_from() failed: %s.\n", strerror(errno));
            munmap(map, page);
            unlink(argv[1]);
            close(fd);
            return EXIT_FAILURE;
        }
        werrs += (data[0] != (long)(n + 1) || data[1] != (long)(~n));

        /* Update data. */
        data[0] = (long)(n * 386131);
        data[1] = (long)(n * -257);
        if (write_to(fd, data, sizeof data, 0)) {
            fprintf(stderr, "write_to() failed: %s.\n", strerror(errno));
            munmap(map, page);
            unlink(argv[1]);
            close(fd);
            return EXIT_FAILURE;
        }
        merrs += (map[0] != (long)(n * 386131) || map[1] != (long)(n * -257));
    }

    munmap(map, page);
    unlink(argv[1]);
    close(fd);

    if (!werrs && !merrs)
        printf("No errors detected.\n");
    else {
        if (!werrs)
            printf("Detected %lu times (%.3f%%) when file contents were incorrect.\n",
                   werrs, 100.0 * (double)werrs / (double)tests);
        if (!merrs)
            printf("Detected %lu times (%.3f%%) when mapping was incorrect.\n",
                   merrs, 100.0 * (double)merrs / (double)tests);
    }

    return EXIT_SUCCESS;
}

使用例如。

gcc -Wall -O2 test-single -o single
./single temp 1000000

要测试一百万次,当两个访问都在同一个进程中完成时,映射和文件内容是否保持同步。请注意 msync()

我机器上的测试速度大约是每秒55万次。请注意,每个测试都是双向的,所以包括读和写。我只是不能让它检测出任何错误。它的写作对错误也相当敏感。

第二个测试程序使用两个子进程和一个POSIX实时信号告诉另一个进程检查内容。 测试multi.c

#define  _POSIX_C_SOURCE  200809L
#define  _GNU_SOURCE
#include <stdlib.h>
#include <unistd.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <sys/mman.h>
#include <sys/wait.h>
#include <fcntl.h>
#include <signal.h>
#include <string.h>
#include <stdio.h>
#include <errno.h>

#define  NOTIFY_SIGNAL  (SIGRTMIN+0)

int mapper_process(const int fd, const size_t len)
{
    long       value = 1, count[2] = { 0, 0 };
    long      *data;
    siginfo_t  info;
    sigset_t   sigs;
    int        signum;

    if (fd == -1) {
        fprintf(stderr, "mapper_process(): Invalid file descriptor.\n");
        return EXIT_FAILURE;
    }

    data = mmap(NULL, len, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_NORESERVE, fd, 0);
    if (data == MAP_FAILED) {
        fprintf(stderr, "mapper_process(): Cannot map file.\n");
        return EXIT_FAILURE;
    }

    sigemptyset(&sigs);
    sigaddset(&sigs, NOTIFY_SIGNAL);
    sigaddset(&sigs, SIGINT);
    sigaddset(&sigs, SIGHUP);
    sigaddset(&sigs, SIGTERM);

    while (1) {
        /* Wait for the notification. */
        signum = sigwaitinfo(&sigs, &info);
        if (signum == -1) {
            if (errno == EINTR)
                continue;
            fprintf(stderr, "mapper_process(): sigwaitinfo() failed: %s.\n", strerror(errno));
            munmap(data, len);
            return EXIT_FAILURE;
        }
        if (signum != NOTIFY_SIGNAL)
            break;

        /* A notify signal was received. Check the write counter. */
        count[ (data[0] == value) ]++;

        /* Update. */
        data[0] = value++;
        data[1] = -(value++);

        /* Synchronize */
        /* msync(data, 2 * sizeof (data[0]), MS_SYNC | MS_INVALIDATE); */

        /* And let the writer know. */
        kill(info.si_pid, NOTIFY_SIGNAL);
    }

    /* Print statistics. */
    printf("mapper_process(): %lu errors out of %lu cycles (%.3f%%)\n",
           count[0], count[0] + count[1], 100.0 * (double)count[0] / (double)(count[0] + count[1]));
    fflush(stdout);

    munmap(data, len);
    return EXIT_SUCCESS;
}

static inline int read_from(const int fd, void *const to, const size_t len, const off_t offset)
{
    char       *p = (char *)to;
    char *const q = (char *)to + len;
    ssize_t     n;

    if (lseek(fd, offset, SEEK_SET) != offset)
        return errno = EIO;

    while (p < q) {
        n = read(fd, p, (size_t)(q - p));
        if (n > 0)
            p += n;
        else
        if (n != -1)
            return errno = EIO;
        else
        if (errno != EINTR)
            return errno;
    }

    return 0;
}

static inline int write_to(const int fd, const void *const from, const size_t len, const off_t offset)
{
    const char *const q = (const char *)from + len;
    const char       *p = (const char *)from;
    ssize_t           n;

    if (lseek(fd, offset, SEEK_SET) != offset)
        return errno = EIO;

    while (p < q) {
        n = write(fd, p, (size_t)(q - p));
        if (n > 0)
            p += n;
        else
        if (n != -1)
            return errno = EIO;
        else
        if (errno != EINTR)
            return errno;
    }

    return 0;
}

int writer_process(const int fd, const size_t len, const pid_t other)
{
    long       data[2] = { 0, 0 }, count[2] = { 0, 0 };
    long       value = 0;
    siginfo_t  info;
    sigset_t   sigs;
    int        signum;

    sigemptyset(&sigs);
    sigaddset(&sigs, NOTIFY_SIGNAL);
    sigaddset(&sigs, SIGINT);
    sigaddset(&sigs, SIGHUP);
    sigaddset(&sigs, SIGTERM);

    while (1) {

        /* Update. */
        data[0] = ++value;
        data[1] = -(value++);

        /* then write the data. */
        if (write_to(fd, data, sizeof data, 0)) {
            fprintf(stderr, "writer_process(): write_to() failed: %s.\n", strerror(errno));
            return EXIT_FAILURE;
        }

        /* Let the mapper know. */
        kill(other, NOTIFY_SIGNAL);

        /* Wait for the notification. */        
        signum = sigwaitinfo(&sigs, &info);
        if (signum == -1) {
            if (errno == EINTR)
                continue;
            fprintf(stderr, "writer_process(): sigwaitinfo() failed: %s.\n", strerror(errno));
            return EXIT_FAILURE;
        }
        if (signum != NOTIFY_SIGNAL || info.si_pid != other)
            break;

        /* Reread the file. */
        if (read_from(fd, data, sizeof data, 0)) {
            fprintf(stderr, "writer_process(): read_from() failed: %s.\n", strerror(errno));
            return EXIT_FAILURE;
        }

        /* Check the read counter. */
        count[ (data[1] == -value) ]++;
    }

    /* Print statistics. */
    printf("writer_process(): %lu errors out of %lu cycles (%.3f%%)\n",
           count[0], count[0] + count[1], 100.0 * (double)count[0] / (double)(count[0] + count[1]));
    fflush(stdout);

    return EXIT_SUCCESS;
}

int main(int argc, char *argv[])
{
    struct timespec  duration;
    double           seconds;
    pid_t            mapper, writer, p;
    size_t           page;
    siginfo_t        info;
    sigset_t         sigs;
    int              fd, status;
    char             dummy;

    if (argc != 3) {
        fprintf(stderr, "\n");
        fprintf(stderr, "Usage: %s FILENAME SECONDS\n", argv[0]);
        fprintf(stderr, "\n");
        fprintf(stderr, "This program will test synchronization between a memory map\n");
        fprintf(stderr, "and reading/writing the underlying file.\n");
        fprintf(stderr, "The test will run for the specified time, or indefinitely\n");
        fprintf(stderr, "if SECONDS is zero, but you can also interrupt it with\n");
        fprintf(stderr, "Ctrl+C (INT signal).\n");
        fprintf(stderr, "\n");
        return EXIT_FAILURE;
    }

    if (sscanf(argv[2], " %lf %c", &seconds, &dummy) != 1) {
        fprintf(stderr, "%s: Invalid number of seconds to run.\n", argv[2]);
        return EXIT_FAILURE;
    }
    if (seconds > 0) {
        duration.tv_sec = (time_t)seconds;
        duration.tv_nsec = (long)(1000000000 * (seconds - (double)(duration.tv_sec)));
    } else {
        duration.tv_sec = 0;
        duration.tv_nsec = 0;
    }

    /* Block INT, HUP, CHLD, and the notification signal. */
    sigemptyset(&sigs);
    sigaddset(&sigs, SIGINT);
    sigaddset(&sigs, SIGHUP);
    sigaddset(&sigs, SIGCHLD);
    sigaddset(&sigs, NOTIFY_SIGNAL);
    if (sigprocmask(SIG_BLOCK, &sigs, NULL) == -1) {
        fprintf(stderr, "Cannot block the necessary signals: %s.\n", strerror(errno));
        return EXIT_FAILURE;
    }

    /* Create the file. */
    page = sysconf(_SC_PAGESIZE);
    fd = open(argv[1], O_RDWR | O_CREAT | O_EXCL, 0644);
    if (fd == -1) {
        fprintf(stderr, "%s: Cannot create file: %s.\n", argv[1], strerror(errno));
        return EXIT_FAILURE;
    }
    if (ftruncate(fd, page) == -1) {
        fprintf(stderr, "%s: Cannot resize file: %s.\n", argv[1], strerror(errno));
        unlink(argv[1]);
        return EXIT_FAILURE;
    }
    close(fd);
    fd = -1;

    /* Ensure streams are flushed before forking. They should be, we're just paranoid here. */
    fflush(stdout);
    fflush(stderr);

    /* Fork the mapper child process. */
    mapper = fork();
    if (mapper == -1) {
        fprintf(stderr, "Cannot fork mapper child process: %s.\n", strerror(errno));
        unlink(argv[1]);
        return EXIT_FAILURE;
    }
    if (!mapper) {
        fd = open(argv[1], O_RDWR);
        if (fd == -1) {
            fprintf(stderr, "mapper_process(): %s: Cannot open file: %s.\n", argv[1], strerror(errno));
            return EXIT_FAILURE;
        }
        status = mapper_process(fd, page);
        close(fd);
        return status;
    }

    /* For the writer child process. (mapper contains the PID of the mapper process.) */
    writer = fork();
    if (writer == -1) {
        fprintf(stderr, "Cannot fork writer child process: %s.\n", strerror(errno));
        unlink(argv[1]);
        kill(mapper, SIGKILL);
        return EXIT_FAILURE;
    }
    if (!writer) {
        fd = open(argv[1], O_RDWR);
        if (fd == -1) {
            fprintf(stderr, "writer_process(): %s: Cannot open file: %s.\n", argv[1], strerror(errno));
            return EXIT_FAILURE;
        }
        status = writer_process(fd, page, mapper);
        close(fd);
        return status;
    }

    /* Wait for a signal. */
    if (duration.tv_sec || duration.tv_nsec)
        status = sigtimedwait(&sigs, &info, &duration);
    else
        status = sigwaitinfo(&sigs, &info);

    /* Whatever it was, we kill the child processes. */
    kill(mapper, SIGHUP);
    kill(writer, SIGHUP);
    do {
        p = waitpid(-1, NULL, 0);
    } while (p != -1 || errno == EINTR);

    /* Cleanup. */
    unlink(argv[1]);

    printf("Done.\n");                 
    return EXIT_SUCCESS;
}

注意,子进程单独打开临时文件。要编译和运行,请使用。

gcc -Wall -O2 test-multi.c -o multi
./multi temp 10

第二个参数是测试的持续时间,以秒为单位。(您可以使用SIGINT安全地中断测试( Ctrl键 + )或者叹气。)

在我的机器上,测试速度大约是每秒120000次测试这里还注释了调用,因为即使没有它,我也看不到任何错误/取消同步。(另外, msync(ptr, len, MS_SYNC) 和 msync(ptr, len, MS_SYNC | MS_INVALIDATE)

这个 MAP_NORESERVE