diff options
-rw-r--r-- | python/pyspark/rdd.py | 18 |
1 files changed, 15 insertions, 3 deletions
diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index 1b64be23a6..cb20bc8b54 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -121,10 +121,22 @@ def _parse_memory(s): def _load_from_socket(port, serializer): - sock = socket.socket() - sock.settimeout(3) + sock = None + # Support for both IPv4 and IPv6. + # On most of IPv6-ready systems, IPv6 will take precedence. + for res in socket.getaddrinfo("localhost", port, socket.AF_UNSPEC, socket.SOCK_STREAM): + af, socktype, proto, canonname, sa = res + try: + sock = socket.socket(af, socktype, proto) + sock.settimeout(3) + sock.connect(sa) + except socket.error: + sock = None + continue + break + if not sock: + raise Exception("could not open socket") try: - sock.connect(("localhost", port)) rf = sock.makefile("rb", 65536) for item in serializer.load_stream(rf): yield item |