diff --git a/python/pyspark/java_gateway.py b/python/pyspark/java_gateway.py index c7f7c1fe591b0..6f4f62f23bc4d 100644 --- a/python/pyspark/java_gateway.py +++ b/python/pyspark/java_gateway.py @@ -54,12 +54,19 @@ def preexec_func(): gateway_port = proc.stdout.readline() gateway_port = int(gateway_port) except ValueError: + # Grab the remaining lines of stdout (stdout, _) = proc.communicate() exit_code = proc.poll() error_msg = "Launching GatewayServer failed" - error_msg += " with exit code %d! " % exit_code if exit_code else "! " - error_msg += "(Warning: unexpected output detected.)\n\n" - error_msg += gateway_port + stdout + error_msg += " with exit code %d!\n" % exit_code if exit_code else "!\n" + error_msg += "Warning: Expected GatewayServer to output a port, but found " + if gateway_port == "" and stdout == "": + error_msg += "no output.\n" + else: + error_msg += "the following:\n\n" + error_msg += "--------------------------------------------------------------\n" + error_msg += gateway_port + stdout + error_msg += "--------------------------------------------------------------\n" raise Exception(error_msg) # Create a thread to echo output from the GatewayServer, which is required