aboutsummaryrefslogtreecommitdiff
path: root/python/pyspark/context.py
diff options
context:
space:
mode:
authorjyotiska <jyotiska123@gmail.com>2014-03-10 13:34:49 -0700
committerMatei Zaharia <matei@databricks.com>2014-03-10 13:34:49 -0700
commitf5518989b67a0941ca79368e73811895a5fa8669 (patch)
treeb62a0e4648e93f7c95e7fbec52a7bf62ed64a486 /python/pyspark/context.py
parente1e09e0ef6b18e034727403d81747d899b042219 (diff)
downloadspark-f5518989b67a0941ca79368e73811895a5fa8669.tar.gz
spark-f5518989b67a0941ca79368e73811895a5fa8669.tar.bz2
spark-f5518989b67a0941ca79368e73811895a5fa8669.zip
[SPARK-972] Added detailed callsite info for ValueError in context.py (resubmitted)
Author: jyotiska <jyotiska123@gmail.com> Closes #34 from jyotiska/pyspark_code and squashes the following commits: c9439be [jyotiska] replaced dict with namedtuple a6bf4cd [jyotiska] added callsite info for context.py
Diffstat (limited to 'python/pyspark/context.py')
-rw-r--r--python/pyspark/context.py16
1 files changed, 15 insertions, 1 deletions
diff --git a/python/pyspark/context.py b/python/pyspark/context.py
index c9f42d3aac..bf2454fd7e 100644
--- a/python/pyspark/context.py
+++ b/python/pyspark/context.py
@@ -20,6 +20,7 @@ import shutil
import sys
from threading import Lock
from tempfile import NamedTemporaryFile
+from collections import namedtuple
from pyspark import accumulators
from pyspark.accumulators import Accumulator
@@ -29,6 +30,7 @@ from pyspark.files import SparkFiles
from pyspark.java_gateway import launch_gateway
from pyspark.serializers import PickleSerializer, BatchedSerializer, UTF8Deserializer
from pyspark.storagelevel import StorageLevel
+from pyspark import rdd
from pyspark.rdd import RDD
from py4j.java_collections import ListConverter
@@ -83,6 +85,11 @@ class SparkContext(object):
...
ValueError:...
"""
+ if rdd._extract_concise_traceback() is not None:
+ self._callsite = rdd._extract_concise_traceback()
+ else:
+ tempNamedTuple = namedtuple("Callsite", "function file linenum")
+ self._callsite = tempNamedTuple(function=None, file=None, linenum=None)
SparkContext._ensure_initialized(self, gateway=gateway)
self.environment = environment or {}
@@ -169,7 +176,14 @@ class SparkContext(object):
if instance:
if SparkContext._active_spark_context and SparkContext._active_spark_context != instance:
- raise ValueError("Cannot run multiple SparkContexts at once")
+ currentMaster = SparkContext._active_spark_context.master
+ currentAppName = SparkContext._active_spark_context.appName
+ callsite = SparkContext._active_spark_context._callsite
+
+ # Raise error if there is already a running Spark context
+ raise ValueError("Cannot run multiple SparkContexts at once; existing SparkContext(app=%s, master=%s)" \
+ " created by %s at %s:%s " \
+ % (currentAppName, currentMaster, callsite.function, callsite.file, callsite.linenum))
else:
SparkContext._active_spark_context = instance