Question

我对使用内存映射IO的前景感兴趣，最好是利用boost :: interprocess中的工具来实现跨平台支持，将文件中不连续的系统页面大小的块映射到内存中连续的地址空间。

简化的具体方案：

我有许多“普通旧数据”结构，每个都是固定长度的（小于系统页面大小。）这些结构是连接的进入一个（非常长的）流类型＆amp;结构的位置由那些在其中进行的结构的价值决定流。我的目标是最大限度地减少延迟并最大限度地提高吞吐量苛刻的并发环境。

我可以通过内存映射非常有效地读取这些数据系统页面大小至少两倍......并建立一个新的映射立即读取超出的结构倒数第二个系统页面边界。这允许交互的代码用普通的数据结构幸福地不知道这些结构是内存映射的...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。

事情变得有趣的是更新这些数据溪流......当他们被（同时）阅读时。我的策略喜欢使用的灵感来自系统页面大小的'Copy On Write' 粒度...基本上写'覆盖页' - 允许一个读取旧数据的过程，而另一个读取更新的数据。

管理要使用的覆盖页面，以及何时，不一定琐碎......这不是我主要担心的问题。我主要担心的是我可能有一个跨越第4和第5页的结构，然后更新一个结构完全包含在第5页...写入新页面位置6 ...当它是“垃圾收集”时，将第5页留下决定不再可达。这意味着，如果我映射页面 4进入位置M，我需要将第6页映射到内存位置 M + page_size ...以便能够可靠地处理结构使用现有（非内存映射感知）函数跨页边界。

我正在努力建立最好的策略，而且我受到了阻碍文件我觉得不完整。基本上，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 - 如果我愿意的话明确控制映射位置......但我不清楚我是怎么做的应该保留地址空间以便安全地执行此操作。我可以映射吗？ / dev / zero为没有MAP_FIXED的两个页面，然后使用MAP_FIXED两次将两个页面映射到显式VM地址的分配空间？如果所以，我应该三次打电话给munmap（）吗？它会泄漏资源吗？和/或有任何其他不愉快的开销？更进一步地解决这个问题复杂，我想在Windows上有类似的行为......有什么办法去做这个？如果我要妥协我的话，是否有完整的解决方案？跨平台的野心？

-

感谢您的回答，Mahmoud ......我已经读过了，并且认为我已经理解了代码......我已经在Linux下编译了它，它的行为与您的建议相符。

我主要关心的是第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' - 即不是恰好在Linux上运行的东西？我还需要假设它适用于文件映射和匿名映射的跨平台。

这个样本肯定让我前进......记录我最终需要的东西可能是在Linux上用mmap（）实现的 - 至少。我真正喜欢的是指向文档的指针，该文档显示MAP_FIXED行将作为示例演示...并且，理想情况下，从Linux / Unix特定mmap（）到独立平台的转换（Boost :: interprocess）方法。

Answer 1

你的问题有点令人困惑。根据我的理解，这段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;
}

我修改后的答案应该解决您的安全问题。仅在第二次MAP_FIXED电话上使用mmap（就像我上面的那样）。关于MAP_FIXED的一个很酷的事情是，它允许您覆盖现有的mmap地址部分。它将卸载您重叠的范围，并将其替换为新的映射内容：

 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. [...]

这样，你让操作系统负责为你找到数百兆的连续内存块（永远不要在你不确定的地址上调用MAP_FIXED不可用）。然后使用您将要修改的数据在现在映射的巨大空间的子部分上调用MAP_FIXED。多田。

在Windows上，这样的东西应该可行（我现在在Mac上，所以未经测试）：

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;
}

Answer 2

但我不清楚如何安全地保留地址空间

这会因操作系统的不同而有所不同，但是对mmap的msdn（我在msdn搜索中以“xp mmap”开头）进行了一些挖掘，表明微软拥有通常的VerboseAndHelpfullyCapitalizedNames来实现mmap的各种功能。文件和匿名映射器都可以处理与任何POSIX-2001系统相同的固定地址请求，即如果地址空间中的其他内容正在与内核通信，则可以对其进行排序。我不打算“安全地”触摸，没有“安全”的代码，你想要移植到未指定的平台。您将不得不构建自己的预映射匿名内存池，您可以在自己的控制下取消映射和分区。

Answer 3

我测试了来自@Mahmoud的windows代码，实际上我测试了以下类似的代码，但它不起作用（Linux代码可以正常工作。）如果取消注释VirtualFree，它将起作用。正如我在上面的评论中所提到的，在Windows上你可以使用VirtualAlloc保留地址空间，但是你不能将MapViewOfFileEx与已映射的地址一起使用，所以你需要首先使用VirtualFree。然后是一个竞争条件，其中另一个线程可以在你做之前获取内存地址，所以你必须在循环中做所有事情，例如尝试多达1000次，然后放弃。

package main

import (
    "fmt"
    "os"
    "syscall"
)

func main() {
    const size = 1024 * 1024

    file, err := os.Create("foo.dat")
    if err != nil {
        panic(err)
    }

    if err := file.Truncate(size); err != nil {
        panic(err)
    }

    const MEM_COMMIT = 0x1000

    addr, err := virtualAlloc(0, size, MEM_COMMIT, protReadWrite)
    if err != nil {
        panic(err)
    }

    fd, err := syscall.CreateFileMapping(
        syscall.Handle(file.Fd()),
        nil,
        uint32(protReadWrite),
        0,
        uint32(size),
        nil,
    )

    //if err := virtualFree(addr); err != nil {
    //  panic(err)
    //}

    base, err := mapViewOfFileEx(fd, syscall.FILE_MAP_READ|syscall.FILE_MAP_WRITE, 0, 0, size, addr)
    if base == 0 {
        panic("mapViewOfFileEx returned 0")
    }
    if err != nil {
        panic(err)
    }

    fmt.Println("success!")
}

type memProtect uint32

const (
    protReadOnly  memProtect = 0x02
    protReadWrite memProtect = 0x04
    protExecute   memProtect = 0x20
    protAll       memProtect = 0x40
)

var (
    modkernel32         = syscall.MustLoadDLL("kernel32.dll")
    procMapViewOfFileEx = modkernel32.MustFindProc("MapViewOfFileEx")
    procVirtualAlloc    = modkernel32.MustFindProc("VirtualAlloc")
    procVirtualFree     = modkernel32.MustFindProc("VirtualFree")
    procVirtualProtect  = modkernel32.MustFindProc("VirtualProtect")
)

func mapViewOfFileEx(handle syscall.Handle, prot memProtect, offsetHigh uint32, offsetLow uint32, length uintptr, target uintptr) (addr uintptr, err error) {
    r0, _, e1 := syscall.Syscall6(procMapViewOfFileEx.Addr(), 6, uintptr(handle), uintptr(prot), uintptr(offsetHigh), uintptr(offsetLow), length, target)
    addr = uintptr(r0)
    if addr == 0 {
        if e1 != 0 {
            err = error(e1)
        } else {
            err = syscall.EINVAL
        }
    }
    return addr, nil
}

func virtualAlloc(addr, size uintptr, allocType uint32, prot memProtect) (mem uintptr, err error) {
    r0, _, e1 := syscall.Syscall6(procVirtualAlloc.Addr(), 4, addr, size, uintptr(allocType), uintptr(prot), 0, 0)
    mem = uintptr(r0)
    if e1 != 0 {
        return 0, error(e1)
    }
    return mem, nil
}

func virtualFree(addr uintptr) error {
    const MEM_RELEASE = 0x8000
    _, _, e1 := syscall.Syscall(procVirtualFree.Addr(), 3, addr, 0, MEM_RELEASE)
    if e1 != 0 {
        return error(e1)
    }
    return nil
}

将非连续块从文件映射到连续的内存地址

3 个答案: