Improved EPOLLRDHUP handling.

When it's known that the kernel supports EPOLLRDHUP, there is no need in
additional recv() call to get EOF or error when the flag is absent in the
event generated by the kernel.  A special runtime test is done at startup
to detect if EPOLLRDHUP is actually supported by the kernel because
epoll_ctl() silently ignores unknown flags.

With this knowledge it's now possible to drop the "ready" flag for partial
read.  Previously, the "ready" flag was kept until the recv() returned EOF
or error.  In particular, this change allows the lingering close heuristics
(which relies on the "ready" flag state) to actually work on Linux, and not
wait for more data in most cases.

The "available" flag is now used in the read event with the semantics similar
to the corresponding counter in kqueue.

2 files changed, 65 insertions, 0 deletions

diff --git a/src/os/unix/ngx_readv_chain.c b/src/os/unix/ngx_readv_chain.c
index d23508ea7..454cfdcad 100644
--- a/src/os/unix/ngx_readv_chain.c
+++ b/src/os/unix/ngx_readv_chain.c
@@ -53,6 +53,20 @@ ngx_readv_chain(ngx_connection_t *c, ngx_chain_t *chain, off_t limit)
 
 #endif
 
+#if (NGX_HAVE_EPOLLRDHUP)
+
+    if (ngx_event_flags & NGX_USE_EPOLL_EVENT) {
+        ngx_log_debug2(NGX_LOG_DEBUG_EVENT, c->log, 0,
+                       "readv: eof:%d, avail:%d",
+                       rev->pending_eof, rev->available);
+
+        if (!rev->available && !rev->pending_eof) {
+            return NGX_AGAIN;
+        }
+    }
+
+#endif
+
     prev = NULL;
     iov = NULL;
     size = 0;
@@ -151,6 +165,24 @@ ngx_readv_chain(ngx_connection_t *c, ngx_chain_t *chain, off_t limit)
 
 #endif
 
+#if (NGX_HAVE_EPOLLRDHUP)
+
+            if ((ngx_event_flags & NGX_USE_EPOLL_EVENT)
+                && ngx_use_epoll_rdhup)
+            {
+                if (n < size) {
+                    if (!rev->pending_eof) {
+                        rev->ready = 0;
+                    }
+
+                    rev->available = 0;
+                }
+
+                return n;
+            }
+
+#endif
+
             if (n < size && !(ngx_event_flags & NGX_USE_GREEDY_EVENT)) {
                 rev->ready = 0;
             }
diff --git a/src/os/unix/ngx_recv.c b/src/os/unix/ngx_recv.c
index 5013ae34c..c85fd453c 100644
--- a/src/os/unix/ngx_recv.c
+++ b/src/os/unix/ngx_recv.c
@@ -50,6 +50,21 @@ ngx_unix_recv(ngx_connection_t *c, u_char *buf, size_t size)
 
 #endif
 
+#if (NGX_HAVE_EPOLLRDHUP)
+
+    if (ngx_event_flags & NGX_USE_EPOLL_EVENT) {
+        ngx_log_debug2(NGX_LOG_DEBUG_EVENT, c->log, 0,
+                       "recv: eof:%d, avail:%d",
+                       rev->pending_eof, rev->available);
+
+        if (!rev->available && !rev->pending_eof) {
+            rev->ready = 0;
+            return NGX_AGAIN;
+        }
+    }
+
+#endif
+
     do {
         n = recv(c->fd, buf, size, 0);
 
@@ -101,6 +116,24 @@ ngx_unix_recv(ngx_connection_t *c, u_char *buf, size_t size)
 
 #endif
 
+#if (NGX_HAVE_EPOLLRDHUP)
+
+            if ((ngx_event_flags & NGX_USE_EPOLL_EVENT)
+                && ngx_use_epoll_rdhup)
+            {
+                if ((size_t) n < size) {
+                    if (!rev->pending_eof) {
+                        rev->ready = 0;
+                    }
+
+                    rev->available = 0;
+                }
+
+                return n;
+            }
+
+#endif
+
             if ((size_t) n < size
                 && !(ngx_event_flags & NGX_USE_GREEDY_EVENT))
             {