云风的 BLOG

level-triggered(LT)，即水平触发模式
对于写缓冲，只要可写，就一直会触发EPOLLOUT事件

在linux上，我们经常在执行命令后，有太多的控制台输出，我们会习惯的按住回车键将屏幕上的输出推上去。

如果采用水平触发模式，程序启动后，通常也会打印些日志，这时习惯的将这些日志信息推上去，这时将接收到的客户端连接fd加入到epoll中，同时注册EPOLLOUT事件，并不会一直触发EPOLLOUT事件。

这个是什么原因？

应该是用得不对，导致问题吧。
API不应提供它够不着的安全，框架（如skynet）也不应提供它够不着的安全。用户应该规范自己的行为。

应该是用得不对，导致问题吧。
API不应提供它够不着的安全。

这是manual说法
Multithreaded applications

If a file descriptor being monitored by select() is closed in another thread, the result is unspecified. On some UNIX systems, select() unblocks and returns, with an indication that the file descriptor is ready (a subsequent I/O operation will likely fail with an error, unless another the file descriptor reopened between the time select() returned and the I/O operations was performed). On Linux (and some other systems), closing the file descriptor in another thread has no effect on select(). In summary, any application that relies on a particular behavior in this scenario must be considered buggy

对于这种情况，manual有讨论
For a discussion of what may happen if a file descriptor in an epoll instance being monitored by epoll_wait() is closed in another thread, see select(2).

close的时候，如果在epoll中，则先从epoll移除，然后再真实的close

@davidxu

这里的问题是，epoll 是 skynet 框架管理的，但 skynet 是个框架，并不阻止用框架的人通过第三方库调用 close 。

估计是close fd和处理事件的代码的生命周期没有同步控制。我常用libev, 到是在一个文件句柄被close掉后，epoll返回事件时，放在libev中的回调钩子只要不拿掉还时会被调用的。被调用时，读文件句柄应该会出错，错误号9. 这样就可以发现一些代码中的问题。

以前也碰到了楼主描述一模一样的问题, 但一直没有找到原因.
当时epoll不小心监听到了fd 0, 如果当前SecuryCRT不关闭,fd 0没有被close. CPU消耗正常. 但CRT关闭后, fd 0被close后,epoll就一直返回fd 0可读,第一次读已经被closed fd 0时,返回-1, 后续读操作全部返回为0

@codesun

引用计数是一个实现手段，本身并不是问题。问题是一旦一个 file descriptor 不在了，而 file description 还在，那么就没有任何方法从 epoll 中移除了，所以这是一个设计失误。

看看 illumos 的 man epoll :

While a best effort has been made to mimic the Linux semantics, there are some semantics that are too peculiar or ill-conceived to merit accommodation. In particular, the Linux epoll facility will -- by design
-- continue to generate events for closed file descriptors where/when the underlying file description remains open.

而 kqueue 的 man 是这样的：

Calling close() on a file descriptor will remove any kevents that reference the descriptor.

man 7 epoll

Q6 Will closing a file descriptor cause it to be removed from all epoll sets automatically?

A6 Yes, but be aware of the following point. A file descriptor is a reference to an open file description (see open(2)). Whenever a file descriptor is duplicated via dup(2), dup2(2), fcntl(2) F_DUPFD, or fork(2), a new file descriptor referring to the same open file description is created. An open file description continues to exist until all file descriptors referring to it have been closed. A file descriptor is removed from an epoll set only after all the file descriptors referring to the underlying open file description have been closed (or before if the file descriptor is explicitly removed using epoll_ctl(2) EPOLL_CTL_DEL). This means that even after a file descriptor that is part of an epoll set has been closed, events may be reported for that file descriptor if other file descriptors referring to the same underlying file description remain open

我觉得manual已经写得很清楚了，另外close的引用计数在Linux中难道不是很常见吗？epoll并非例外。

博客内容不错嘛，欢迎更多优秀内容
http://www.alipie.com/