我对使用内存映射 IO 的前景感兴趣，最好
利用 boost::interprocess 中的设施进行跨平台
支持，将文件中的非连续系统页面大小 block 映射到
内存中的连续地址空间。

一个简化的具体场景:

我有许多“普通旧数据”结构，每个结构的长度都是固定的
(小于系统页面大小。)这些结构连接在一起
到一个(很长的)流中，带有结构的类型和位置
由在这些结构中处理它们的那些结构的值决定
溪流。我的目标是最大限度地减少延迟并最大限度地 boost 吞吐量
要求并发环境。

通过以 block 为单位进行内存映射，我可以非常有效地读取这些数据
至少两倍于系统页面大小......并建立一个新的
立即映射已读取超出范围的结构
倒数第二个系统页面边界。这允许交互的代码
使用简单的旧数据结构幸福地不知道这些
结构是内存映射的......并且，例如，可以比较两个
直接使用 memcmp() 的不同结构，无需关心
关于页面边界。

事情变得有趣的地方在于更新这些数据
流......当它们被(同时)读取时。我的策略
喜欢使用的灵感来自系统页面大小上的“写入时复制”
粒度……本质上是在写“覆盖页面”——允许一个
进程读取旧数据，而另一个进程读取更新数据。

在管理要使用的覆盖页面以及何时使用时，不一定
微不足道……这不是我主要关心的问题。我主要担心的是我可能
有一个跨越第 4 页和第 5 页的结构，然后更新一个
结构完全包含在第 5 页中...编写新页面
位置 6... 将第 5 页留在“垃圾收集”处
决定不再可达。这意味着，如果我映射页面
4 到位置 M，我需要将第 6 页映射到内存位置
M+page_size... 为了能够可靠地处理结构
使用现有(非内存映射感知)函数跨越页面边界。

我正在尝试制定最佳策略，但受到阻碍
我觉得文档不完整。本质上，我需要解耦
从内存映射到该地址的地址空间分配
空间。使用 mmap()，我知道我可以使用 MAP_FIXED - 如果我愿意
明确控制映射位置......但我不清楚我是如何
应该保留地址空间以安全地执行此操作。我可以映射吗
没有 MAP_FIXED 的两个页面的/dev/zero，然后使用 MAP_FIXED 两次来
将两个页面映射到显式 VM 地址的分配空间？如果
那么，我也应该调用 munmap() 三次吗？会不会泄露资源
和/或有任何其他不愉快的开销？为了让问题更
复杂，我想在 Windows 上有类似的行为......有什么办法
去做这个？如果我要妥协，是否有巧妙的解决方案
跨平台的野心？

——

感谢您的回答，马哈茂德...我已经阅读过，并认为我已经理解了该代码...我已经在 Linux 下编译了它，它的行为与您的建议相同。

我主要关注的是第 62 行 - 使用 MAP_FIXED。它对 mmap 做了一些假设，当我阅读我能找到的文档时，我一直无法确认。您将“更新”页面映射到与最初返回的 mmap() 相同的地址空间 - 我认为这是“正确的” - 即不是碰巧在 Linux 上工作的东西？我还需要假设它适用于文件映射和匿名映射的跨平台。

该示例肯定会让我前进......记录我最终需要的东西可能可以在 Linux 上使用 mmap() 实现 - 至少。我真正想要的是一个指向文档的指针，该文档表明 MAP_FIXED 行将像示例演示的那样工作......并且，理想情况下，从 Linux/Unix 特定的 mmap() 到独立于平台的转换 (Boost::interprocess ) 方法。

最佳答案

你的问题有点困惑。据我了解，此代码将满足您的需求:

#define PAGESIZE 4096

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

struct StoredObject
{
    int IntVal;
    char StrVal[25];
};

int main(int argc, char **argv)
{
    int fd = open("mmapfile", O_RDWR | O_CREAT | O_TRUNC, (mode_t) 0600);
    //Set the file to the size of our data (2 pages)
    lseek(fd, PAGESIZE*2 - 1, SEEK_SET);
    write(fd, "", 1); //The final byte

    unsigned char *mapPtr = (unsigned char *) mmap(0, PAGESIZE * 2, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);

    struct StoredObject controlObject;
    controlObject.IntVal = 12;
    strcpy(controlObject.StrVal, "Mary had a little lamb.\n");

    struct StoredObject *mary1;
    mary1 = (struct StoredObject *)(mapPtr + PAGESIZE - 4); //Will fall on the boundary between first and second page
    memcpy(mary1, &controlObject, sizeof(StoredObject));

    printf("%d, %s", mary1->IntVal, mary1->StrVal);
    //Should print "12, Mary had a little lamb.\n"

    struct StoredObject *john1;
    john1 = mary1 + 1; //Comes immediately after mary1 in memory; will start and end in the second page
    memcpy(john1, &controlObject, sizeof(StoredObject));

    john1->IntVal = 42;
    strcpy(john1->StrVal, "John had a little lamb.\n");

    printf("%d, %s", john1->IntVal, john1->StrVal);
    //Should print "12, Mary had a little lamb.\n"

    //Make sure the data's on the disk, as this is the initial, "read-only" data
    msync(mapPtr, PAGESIZE * 2, MS_SYNC);

    //This is the inital data set, now in memory, loaded across two pages
    //At this point, someone could be reading from there. We don't know or care.
    //We want to modify john1, but don't want to write over the existing data
    //Easy as pie.

    //This is the shadow map. COW-like optimization will take place: 
    //we'll map the entire address space from the shared source, then overlap with a new map to modify
    //This is mapped anywhere, letting the system decide what address we'll be using for the new data pointer
    unsigned char *mapPtr2 = (unsigned char *) mmap(0, PAGESIZE * 2, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0);

    //Map the second page on top of the first mapping; this is the one that we're modifying. It is *not* backed by disk
    unsigned char *temp = (unsigned char *) mmap(mapPtr2 + PAGESIZE, PAGESIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_FIXED | MAP_ANON, 0, 0);
    if (temp == MAP_FAILED)
    {
        printf("Fixed map failed. %s", strerror(errno));
    }
    assert(temp == mapPtr2 + PAGESIZE);

    //Make a copy of the old data that will later be changed
    memcpy(mapPtr2 + PAGESIZE, mapPtr + PAGESIZE, PAGESIZE);

    //The two address spaces should still be identical until this point
    assert(memcmp(mapPtr, mapPtr2, PAGESIZE * 2) == 0);

    //We can now make our changes to the second page as needed
    struct StoredObject *mary2 = (struct StoredObject *)(((unsigned char *)mary1 - mapPtr) + mapPtr2);
    struct StoredObject *john2 = (struct StoredObject *)(((unsigned char *)john1 - mapPtr) + mapPtr2);

    john2->IntVal = 52;
    strcpy(john2->StrVal, "Mike had a little lamb.\n");

    //Test that everything worked OK
    assert(memcmp(mary1, mary2, sizeof(struct StoredObject)) == 0);
    printf("%d, %s", john2->IntVal, john2->StrVal);
    //Should print "52, Mike had a little lamb.\n"

    //Now assume our garbage collection routine has detected that no one is using the original copy of the data
    munmap(mapPtr, PAGESIZE * 2);

    mapPtr = mapPtr2;

    //Now we're done with all our work and want to completely clean up
    munmap(mapPtr2, PAGESIZE * 2);

    close(fd);

    return 0;
}

 MAP_FIXED
              [...] If the memory
              region specified by addr and len overlaps pages of any existing
              mapping(s), then the overlapped part of the existing mapping(s) will be
              discarded. [...]

int main(int argc, char **argv)
{
    HANDLE hFile = CreateFile(L"mmapfile", GENERIC_READ | GENERIC_WRITE, FILE_SHARE_READ, NULL, CREATE_ALWAYS, FILE_ATTRIBUTE_NORMAL, NULL);
    //Set the file to the size of our data (2 pages)
    SetFilePointer(hFile, PAGESIZE*2 - 1, 0, FILE_BEGIN);
    DWORD bytesWritten = -1;
    WriteFile(hFile, "", 1, &bytesWritten, NULL);

    HANDLE hMap = CreateFileMapping(hFile, NULL, PAGE_READWRITE, 0, PAGESIZE * 2, NULL);
    unsigned char *mapPtr = (unsigned char *) MapViewOfFile(hMap, FILE_MAP_READ | FILE_MAP_WRITE, 0, 0, PAGESIZE * 2);

    struct StoredObject controlObject;
    controlObject.IntVal = 12;
    strcpy(controlObject.StrVal, "Mary had a little lamb.\n");

    struct StoredObject *mary1;
    mary1 = (struct StoredObject *)(mapPtr + PAGESIZE - 4); //Will fall on the boundary between first and second page
    memcpy(mary1, &controlObject, sizeof(StoredObject));

    printf("%d, %s", mary1->IntVal, mary1->StrVal);
    //Should print "12, Mary had a little lamb.\n"

    struct StoredObject *john1;
    john1 = mary1 + 1; //Comes immediately after mary1 in memory; will start and end in the second page
    memcpy(john1, &controlObject, sizeof(StoredObject));

    john1->IntVal = 42;
    strcpy(john1->StrVal, "John had a little lamb.\n");

    printf("%d, %s", john1->IntVal, john1->StrVal);
    //Should print "12, Mary had a little lamb.\n"

    //Make sure the data's on the disk, as this is the initial, "read-only" data
    //msync(mapPtr, PAGESIZE * 2, MS_SYNC);

    //This is the inital data set, now in memory, loaded across two pages
    //At this point, someone could be reading from there. We don't know or care.
    //We want to modify john1, but don't want to write over the existing data
    //Easy as pie.

    //This is the shadow map. COW-like optimization will take place: 
    //we'll map the entire address space from the shared source, then overlap with a new map to modify
    //This is mapped anywhere, letting the system decide what address we'll be using for the new data pointer
    unsigned char *reservedMem = (unsigned char *) VirtualAlloc(NULL, PAGESIZE * 2, MEM_RESERVE, PAGE_READWRITE);
    HANDLE hMap2 = CreateFileMapping(hFile, NULL, PAGE_READWRITE, 0, PAGESIZE, NULL);
    unsigned char *mapPtr2 = (unsigned char *) MapViewOfFileEx(hMap2, FILE_MAP_READ | FILE_MAP_WRITE, 0, 0, PAGESIZE, reservedMem);

    //Map the second page on top of the first mapping; this is the one that we're modifying. It is *not* backed by disk
    unsigned char *temp = (unsigned char *) MapViewOfFileEx(hMap2, FILE_MAP_READ | FILE_MAP_WRITE, 0, 0, PAGESIZE, reservedMem + PAGESIZE);
    if (temp == NULL)
    {
        printf("Fixed map failed. 0x%x\n", GetLastError());
        return -1;
    }
    assert(temp == mapPtr2 + PAGESIZE);

    //Make a copy of the old data that will later be changed
    memcpy(mapPtr2 + PAGESIZE, mapPtr + PAGESIZE, PAGESIZE);

    //The two address spaces should still be identical until this point
    assert(memcmp(mapPtr, mapPtr2, PAGESIZE * 2) == 0);

    //We can now make our changes to the second page as needed
    struct StoredObject *mary2 = (struct StoredObject *)(((unsigned char *)mary1 - mapPtr) + mapPtr2);
    struct StoredObject *john2 = (struct StoredObject *)(((unsigned char *)john1 - mapPtr) + mapPtr2);

    john2->IntVal = 52;
    strcpy(john2->StrVal, "Mike had a little lamb.\n");

    //Test that everything worked OK
    assert(memcmp(mary1, mary2, sizeof(struct StoredObject)) == 0);
    printf("%d, %s", john2->IntVal, john2->StrVal);
    //Should print "52, Mike had a little lamb.\n"

    //Now assume our garbage collection routine has detected that no one is using the original copy of the data
    //munmap(mapPtr, PAGESIZE * 2);

    mapPtr = mapPtr2;

    //Now we're done with all our work and want to completely clean up
    //munmap(mapPtr2, PAGESIZE * 2);

    //close(fd);

    return 0;
}

关于c++ - 将文件中的非连续 block 映射到连续的内存地址，我们在Stack Overflow上找到一个类似的问题： https://stackoverflow.com/questions/10454964/