Github user jiangxb1987 commented on a diff in the pull request:
https://github.com/apache/spark/pull/22247#discussion_r213378931
--- Diff: python/pyspark/taskcontext.py ---
@@ -108,38 +108,12 @@ def _load_from_socket(port, auth_secret):
"""
Load data from a given socket, this is a blocking method thus only
return when the socket
connection has been closed.
-
- This is copied from context.py, while modified the message protocol.
"""
- 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
- sock = socket.socket(af, socktype, proto)
- try:
- # Do not allow timeout for socket reading operation.
- sock.settimeout(None)
- sock.connect(sa)
- except socket.error:
- sock.close()
- sock = None
- continue
- break
- if not sock:
- raise Exception("could not open socket")
-
- # We don't really need a socket file here, it's just for convenience
that we can reuse the
- # do_server_auth() function and data serialization methods.
- sockfile = sock.makefile("rwb", 65536)
-
+ (sockfile, sock) = local_connect_and_auth(port, auth_secret)
--- End diff --
We must set sock timeout to `None` to allow `barrier()` call blocking
forever.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
