voi*_*ter 13 c++ unix linux aio ext4
我正在编写一个使用Linux异步I/O系统调用的库,并且想知道为什么该io_submit函数在ext4文件系统上表现出较差的扩展.如果可能,我该怎么做io_submit才能阻止大IO请求大小?我已经做了以下(如描述这里):
O_DIRECT.为了观察内核花了多长时间io_submit,我运行了一个测试,在其中我用dd和创建了1 Gb测试文件/dev/urandom,并重复删除系统缓存(sync; echo 1 > /proc/sys/vm/drop_caches)并读取文件越来越大的部分.在每次迭代中,我打印io_submit了等待读取请求完成所花费的时间和所花费的时间.我在运行Arch Linux的x86-64系统上运行了以下实验,内核版本为3.11.该机器有一个SSD和一个Core i7 CPU.第一个图表绘制了读取的页数与等待io_submit完成所花费的时间.第二个图显示等待读取请求完成所花费的时间.时间以秒为单位.


为了比较,我创建了一个类似的测试,通过使用同步IO pread.结果如下:

似乎异步IO按预期工作,最大请求大小为20,000页.之后,io_submit阻止.这些观察结果导致以下问题:
io_submit不变?用于测试异步IO的代码如下所示.如果您认为它们是相关的,我可以添加其他源列表,但我尝试仅发布我认为可能相关的详细信息.
#include <cstddef>
#include <cstdint>
#include <cstring>
#include <chrono>
#include <iostream>
#include <memory>
#include <fcntl.h>
#include <stdio.h>
#include <time.h>
#include <unistd.h>
// For `__NR_*` system call definitions.
#include <sys/syscall.h>
#include <linux/aio_abi.h>
static int
io_setup(unsigned n, aio_context_t* c)
{
return syscall(__NR_io_setup, n, c);
}
static int
io_destroy(aio_context_t c)
{
return syscall(__NR_io_destroy, c);
}
static int
io_submit(aio_context_t c, long n, iocb** b)
{
return syscall(__NR_io_submit, c, n, b);
}
static int
io_getevents(aio_context_t c, long min, long max, io_event* e, timespec* t)
{
return syscall(__NR_io_getevents, c, min, max, e, t);
}
int main(int argc, char** argv)
{
using namespace std::chrono;
const auto n = 4096 * size_t(std::atoi(argv[1]));
// Initialize the file descriptor. If O_DIRECT is not used, the kernel
// will block on `io_submit` until the job finishes, because non-direct
// IO via the `aio` interface is not implemented (to my knowledge).
auto fd = ::open("dat/test.dat", O_RDONLY | O_DIRECT | O_NOATIME);
if (fd < 0) {
::perror("Error opening file");
return EXIT_FAILURE;
}
char* p;
auto r = ::posix_memalign((void**)&p, 512, n);
if (r != 0) {
std::cerr << "posix_memalign failed." << std::endl;
return EXIT_FAILURE;
}
auto del = [](char* p) { std::free(p); };
std::unique_ptr<char[], decltype(del)> buf{p, del};
// Initialize the IO context.
aio_context_t c{0};
r = io_setup(4, &c);
if (r < 0) {
::perror("Error invoking io_setup");
return EXIT_FAILURE;
}
// Setup I/O control block.
iocb b;
std::memset(&b, 0, sizeof(b));
b.aio_fildes = fd;
b.aio_lio_opcode = IOCB_CMD_PREAD;
// Command-specific options for `pread`.
b.aio_buf = (uint64_t)buf.get();
b.aio_offset = 0;
b.aio_nbytes = n;
iocb* bs[1] = {&b};
auto t1 = high_resolution_clock::now();
auto r = io_submit(c, 1, bs);
if (r != 1) {
if (r == -1) {
::perror("Error invoking io_submit");
}
else {
std::cerr << "Could not submit request." << std::endl;
}
return EXIT_FAILURE;
}
auto t2 = high_resolution_clock::now();
auto count = duration_cast<duration<double>>(t2 - t1).count();
// Print the wait time.
std::cout << count << " ";
io_event e[1];
t1 = high_resolution_clock::now();
r = io_getevents(c, 1, 1, e, NULL);
t2 = high_resolution_clock::now();
count = duration_cast<duration<double>>(t2 - t1).count();
// Print the read time.
std::cout << count << std::endl;
r = io_destroy(c);
if (r < 0) {
::perror("Error invoking io_destroy");
return EXIT_FAILURE;
}
}
Run Code Online (Sandbox Code Playgroud)