linux aio 实现概览

----------
kernel version : 2.6.32.60
----------

 

I.aio
Asynchronous I/O帮助用户程序提高CPU和IO设备的利用率和提高程序性能，特别是在高负载的IO操作下。比如各种代理服务器，数据库，流服务器等等。

AIO可以一次性发出大量的read/write调用并且通过通用块层的IO调度来获得更好的性能，用户程序也可以减少过多的同步负载，还可以在业务逻辑中更灵活的进行并发控制和负载均衡。另外相对于其他实现如用户多线程后台同步，Glibc等实现也减少了线程的负载和上下文切换。

 

AIO是横架于整个内核的接口，它把所有的IO包括(本地设备，网络，管道等)以统一的异步接口提供给用户程序，每个子系统都针对接口实现自己的异步方案，而同步IO(Synchronous IO)只是在内核内部的”AIO+Blocking”.

以read为例来看"同步IO在内核实现为AIO+Blocking"
fs/read_write.c

ssize_t do_sync_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos)
{
	struct iovec iov = { .iov_base = buf, .iov_len = len };
	struct kiocb kiocb;
	ssize_t ret;

	init_sync_kiocb(&kiocb, filp);
	kiocb.ki_pos = *ppos;
	kiocb.ki_left = len;

	for (;;) {
		ret = filp->f_op->aio_read(&kiocb, &iov, 1, kiocb.ki_pos);
		if (ret != -EIOCBRETRY)
			break;
		wait_on_retry_sync_kiocb(&kiocb);
	}

	if (-EIOCBQUEUED == ret)
		ret = wait_on_sync_kiocb(&kiocb);
	*ppos = kiocb.ki_pos;
	return ret;
}

EXPORT_SYMBOL(do_sync_read);

ssize_t vfs_read(struct file *file, char __user *buf, size_t count, loff_t *pos)
{
	ssize_t ret;

	if (!(file->f_mode & FMODE_READ))
		return -EBADF;
	if (!file->f_op || (!file->f_op->read && !file->f_op->aio_read))
		return -EINVAL;
	if (unlikely(!access_ok(VERIFY_WRITE, buf, count)))
		return -EFAULT;

	ret = rw_verify_area(READ, file, pos, count);
	if (ret >= 0) {
		count = ret;
		if (file->f_op->read)
			ret = file->f_op->read(file, buf, count, pos);
		else
			ret = do_sync_read(file, buf, count, pos);
		if (ret > 0) {
			fsnotify_access(file->f_path.dentry);
			add_rchar(current, ret);
		}
		inc_syscr(current);
	}

	return ret;
}

EXPORT_SYMBOL(vfs_read);

由以上代码可以看出，如果VFS提供同步read方法，则使用同步read方法；否则使用AIO+Blocking的do_sync_read

 

II.aio结构

aio的主要流程:
io_setup创建aio上下文
io_submit提交aio操作，并将aio上下文放入到work_queue中异步完成提交的aio操作
work_queue完成aio操作后将其入到事件回环缓存中，供io_getevents读取

 

III.io_setup
io_setup主要用于创建aio上下文:
  1.初始化kioctx结构
  2.分配Ring Buffer，用于存储完成AIO操作的事件

/* sys_io_setup:
 *	Create an aio_context capable of receiving at least nr_events.
 *	ctxp must not point to an aio_context that already exists, and
 *	must be initialized to 0 prior to the call.  On successful
 *	creation of the aio_context, *ctxp is filled in with the resulting 
 *	handle.  May fail with -EINVAL if *ctxp is not initialized,
 *	if the specified nr_events exceeds internal limits.  May fail 
 *	with -EAGAIN if the specified nr_events exceeds the user's limit 
 *	of available events.  May fail with -ENOMEM if insufficient kernel
 *	resources are available.  May fail with -EFAULT if an invalid
 *	pointer is passed for ctxp.  Will fail with -ENOSYS if not
 *	implemented.
 */
SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
{
	struct kioctx *ioctx = NULL;
	unsigned long ctx;
	long ret;

	ret = get_user(ctx, ctxp);
	if (unlikely(ret))
		goto out;

	ret = -EINVAL;
	if (unlikely(ctx || nr_events == 0)) {
		pr_debug("EINVAL: io_setup: ctx %lu nr_events %u\n",
		         ctx, nr_events);
		goto out;
	}

	ioctx = ioctx_alloc(nr_events);
	ret = PTR_ERR(ioctx);
	if (!IS_ERR(ioctx)) {
		ret = put_user(ioctx->user_id, ctxp);
		if (!ret)
			return 0;

		get_ioctx(ioctx); /* io_destroy() expects us to hold a ref */
		io_destroy(ioctx);
	}

out:
	return ret;
}

根据事件数创建aio上下文，并将user_id返回给用户空间，以后根据user_id使用该aio上下文

 

/* ioctx_alloc
 *	Allocates and initializes an ioctx.  Returns an ERR_PTR if it failed.
 */
static struct kioctx *ioctx_alloc(unsigned nr