Libguestfs - Feb 2021 - [PATCH libnbd 0/2] Fix for connect(2) returning EAGAIN.

I don't believe there's really a good way to fix this, but we can at
least print a better error message.

Thanks: Xin Long and Lukas Doktor

Small, neutral refactoring to the CONNECT.START to make the subsequent
commit easier.
---
 generator/states-connect.c | 21 ++++++++++-----------
 1 file changed, 10 insertions(+), 11 deletions(-)

diff --git a/generator/states-connect.c b/generator/states-connect.c
index 392879d..03b34c7 100644
--- a/generator/states-connect.c
+++ b/generator/states-connect.c
@@ -47,11 +47,12 @@ disable_nagle (int sock)
 
 STATE_MACHINE {
  CONNECT.START:
-  int fd;
+  sa_family_t family;
+  int fd, r;
 
   assert (!h->sock);
-  fd = socket (h->connaddr.ss_family,
-               SOCK_STREAM|SOCK_NONBLOCK|SOCK_CLOEXEC, 0);
+  family = h->connaddr.ss_family;
+  fd = socket (family, SOCK_STREAM|SOCK_NONBLOCK|SOCK_CLOEXEC, 0);
   if (fd == -1) {
     SET_NEXT_STATE (%.DEAD);
     set_error (errno, "socket");
@@ -65,14 +66,12 @@ STATE_MACHINE {
 
   disable_nagle (fd);
 
-  if (connect (fd, (struct sockaddr *) &h->connaddr,
-               h->connaddrlen) == -1) {
-    if (errno != EINPROGRESS) {
-      SET_NEXT_STATE (%.DEAD);
-      set_error (errno, "connect");
-      return 0;
-    }
-  }
+  r = connect (fd, (struct sockaddr *) &h->connaddr, h->connaddrlen);
+  if (r == 0 || (r == -1 && errno == EINPROGRESS))
+    return 0;
+  assert (r == -1);
+  SET_NEXT_STATE (%.DEAD);
+  set_error (errno, "connect");
   return 0;
 
  CONNECT.CONNECTING:
-- 
2.29.0.rc2

The new error message is:

nbd_connect_unix: connect: server backlog overflowed, see
https://bugzilla.redhat.com/1925045: Resource temporarily unavailable

Fixes: https://bugzilla.redhat.com/1925045
---
 generator/states-connect.c | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

diff --git a/generator/states-connect.c b/generator/states-connect.c
index 03b34c7..98c26e5 100644
--- a/generator/states-connect.c
+++ b/generator/states-connect.c
@@ -70,6 +70,22 @@ STATE_MACHINE {
   if (r == 0 || (r == -1 && errno == EINPROGRESS))
     return 0;
   assert (r == -1);
+#ifdef __linux__
+  if (errno == EAGAIN && family == AF_UNIX) {
+    /* This can happen on Linux when connecting to a Unix domain
+     * socket, if the server's backlog is full.  Unfortunately there
+     * is nothing good we can do on the client side when this happens
+     * since any solution would involve sleeping or busy-waiting.  The
+     * only solution is on the server side, increasing the backlog.
+     * But at least improve the error message.
+     * https://bugzilla.redhat.com/1925045
+     */
+    SET_NEXT_STATE (%.DEAD);
+    set_error (errno, "connect: server backlog overflowed, "
+               "see https://bugzilla.redhat.com/1925045");
+    return 0;
+  }
+#endif
   SET_NEXT_STATE (%.DEAD);
   set_error (errno, "connect");
   return 0;
-- 
2.29.0.rc2