Events: available bytes calculation via ioctl(FIONREAD). This makes it possible to avoid looping for a long time while working with a fast enough peer when data are added to the socket buffer faster than we are able to read and process them (ticket #1431). This is basically what we already do on FreeBSD with kqueue, where information about the number of bytes in the socket buffer is returned by the kevent() call. With other event methods rev->available is now set to -1 when the socket is ready for reading. Later in ngx_recv() and ngx_recv_chain(), if full buffer is received, real number of bytes in the socket buffer is retrieved using ioctl(FIONREAD). Reading more than this number of bytes ensures that even with edge-triggered event methods the event will be triggered again, so it is safe to stop processing of the socket and switch to other connections. Using ioctl(FIONREAD) only after reading a full buffer is an optimization. With this approach we only call ioctl(FIONREAD) when there are at least two recv()/readv() calls.

--- a/src/event/ngx_event.h
+++ b/src/event/ngx_event.h
@@ -91,21 +91,14 @@ struct ngx_event_s {
      *   write:      available space in buffer when event is ready
      *               or lowat when event is set with NGX_LOWAT_EVENT flag
      *
-     * epoll with EPOLLRDHUP:
-     *   accept:     1 if accept many, 0 otherwise
-     *   read:       1 if there can be data to read, 0 otherwise
-     *
      * iocp: TODO
      *
      * otherwise:
      *   accept:     1 if accept many, 0 otherwise
+     *   read:       bytes to read when event is ready, -1 if not known
      */
 
-#if (NGX_HAVE_KQUEUE) || (NGX_HAVE_IOCP)
     int              available;
-#else
-    unsigned         available:1;
-#endif
 
     ngx_event_handler_pt  handler;