如何打开 TB 大小的 mmap

我需要打开一个巨大的内存映射。该文件为 1 TB。

然而，我得到了一个 errno: ENOMEM 12 Cannot allocate memory。我不明白是什么阻碍了我。请求RLIMIT_AS值中的结果：18446744073709551615。这就足够了。我的系统也是64位的所以并不是我的虚拟内存太小。ulimit -v是ulimited

我使用 python 创建了数据，np.lib.format.open_memmap因此它在物理上是可能的。我正在尝试用 C 语言阅读它。Python 阅读没问题，numpy.load('terabytearray.npy', mmap_mode='r')有效。

这是一个最小的例子。

像这样创建一个 numpy 数组：

import numpy as np

shape = (75000, 5000000)
filename = 'datafile.obj'

if __name__ == '__main__':
  arr = np.lib.format.open_memmap(filename, mode='w+', dtype=np.float32, shape=shape)

这样读：

#include <stdbool.h>
#include <assert.h>
#include <sys/mman.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <fcntl.h>
#include <stdint.h>
#include <unistd.h>

#include <sys/time.h>
#include <sys/resource.h>

#include <stdio.h>
#include <errno.h>

typedef enum {
  CNPY_LE, /* little endian (least significant byte to most significant byte) */
  CNPY_BE, /* big endian (most significant byte to least significant byte) */
  CNPY_NE, /* no / neutral endianness (each element is a single byte) */
  /* Host endianness is not supported because it is an incredibly bad idea to
     use it for storage. */
} cnpy_byte_order;

typedef enum {
  CNPY_B = 0, /* We want to use the values as index to the following arrays. */
  CNPY_I1,
  CNPY_I2,
  CNPY_I4,
  CNPY_I8,
  CNPY_U1,
  CNPY_U2,
  CNPY_U4,
  CNPY_U8,
  CNPY_F4,
  CNPY_F8,
  CNPY_C8,
  CNPY_C16,
} cnpy_dtype;

typedef enum {
  CNPY_C_ORDER,       /* C order (row major) */
  CNPY_FORTRAN_ORDER, /* Fortran order (column major) */
} cnpy_flat_order;

typedef enum {
  CNPY_SUCCESS,      /* success */
  CNPY_ERROR_FILE,   /* some error regarding handling of a file */
  CNPY_ERROR_MMAP,   /* some error regarding mmaping a file */
  CNPY_ERROR_FORMAT, /* file format error while reading some file */
} cnpy_status;

#define CNPY_MAX_DIM 4
typedef struct {
  cnpy_byte_order byte_order;
  cnpy_dtype dtype;
  cnpy_flat_order order;
  size_t n_dim;
  size_t dims[CNPY_MAX_DIM];
  char *raw_data;
  size_t data_begin;
  size_t raw_data_size;
} cnpy_array;

cnpy_status cnpy_open(const char * const fn, bool writable, cnpy_array *arr) {
  assert(arr != NULL);

  cnpy_array tmp_arr;

  /* open, mmap, and close the file */
  int fd = open(fn, writable? O_RDWR : O_RDONLY);
  if (fd == -1) {
    return CNPY_ERROR_FILE;
  }
  size_t raw_data_size = (size_t) lseek(fd, 0, SEEK_END);
  lseek(fd, 0, SEEK_SET);
  printf("%lu\n", raw_data_size);
  if (raw_data_size == 0) {
    close(fd); /* no point in checking for errors */
    return CNPY_ERROR_FORMAT;
  }
  if (raw_data_size == SIZE_MAX) {
    /* This is just because the author is too lazy to check for overflow on every pos+1 calculation. */
    close(fd);
    return CNPY_ERROR_FORMAT;
  }

  void *raw_data = mmap(
    NULL,
    raw_data_size,
    PROT_READ | PROT_WRITE,
    writable? MAP_SHARED : MAP_PRIVATE,
    fd,
    0 
  );

  if (raw_data == MAP_FAILED) {
    close(fd);
    return CNPY_ERROR_MMAP;
  }

  if (close(fd) != 0) {
    munmap(raw_data, raw_data_size);
    return CNPY_ERROR_FILE;
  }

  /* parse the file */
  // cnpy_status status = cnpy_parse(raw_data, raw_data_size, &tmp_arr); // library call ignore
  // if (status != CNPY_SUCCESS) {
  //   munmap(raw_data, raw_data_size);
  //   return status;
  // }
  // *arr = tmp_arr;

  return CNPY_SUCCESS;
}

int main(){

  cnpy_array arr = {};
  cnpy_status status = cnpy_open("datafile.obj", false, &arr);

  printf("status %i\n",(int) status);
  if(status != CNPY_SUCCESS){
    printf("failure\n");
    printf("errno %i\n", errno);
  }


    struct rlimit lim;
  printf("getrlimit RLIMIT_AS %s\n", (getrlimit(RLIMIT_AS, &lim) == 0 ? "success" : "failure") );
  printf("lim.rlim_cur %lu\n", lim.rlim_cur );
  printf("lim.rlim_max %lu\n", lim.rlim_max );
  printf("RLIM_INFINITY; %lu\n", RLIM_INFINITY );


  return 0;
}

编译

gcc -std=c11 -o mmap_testing main.c

我正在使用~quf/cnpy库，我包含了相关部分，以使其与 numpy 的东西一起工作。