Don't permanently close UDP listeners on error

Also, don't inflate rbytes as we can only ever process one UDP packet at a
time.

Patch by pi3orama. Fixed by Dormando to use the correct state and actually
work.

I'm not fully convinced of the rbytes bit. We must ensure that a UDP packet
with multiple commands in it has all of its commands processed before we can
possibly call recvfrom again.

1 files changed, 5 insertions, 1 deletions

diff --git a/memcached.c b/memcached.c
index c82f5c5..e0bbf89 100644
--- a/memcached.c
+++ b/memcached.c
@@ -493,6 +493,10 @@ static void conn_cleanup(conn *c) {
         sasl_dispose(&c->sasl_conn);
         c->sasl_conn = NULL;
     }
+
+    if (IS_UDP(c->transport)) {
+        conn_set_state(c, conn_read);
+    }
 }
 
 /*
@@ -3264,7 +3268,7 @@ static enum try_read_result try_read_udp(conn *c) {
         res -= 8;
         memmove(c->rbuf, c->rbuf + 8, res);
 
-        c->rbytes += res;
+        c->rbytes = res;
         c->rcurr = c->rbuf;
         return READ_DATA_RECEIVED;
     }