diff options
Diffstat (limited to 'python/pyspark/context.py')
| -rw-r--r-- | python/pyspark/context.py | 16 |
1 files changed, 12 insertions, 4 deletions
diff --git a/python/pyspark/context.py b/python/pyspark/context.py index a3dd1950a5..1b2e199c39 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -109,7 +109,7 @@ class SparkContext(object): ValueError:... """ self._callsite = first_spark_call() or CallSite(None, None, None) - SparkContext._ensure_initialized(self, gateway=gateway) + SparkContext._ensure_initialized(self, gateway=gateway, conf=conf) try: self._do_init(master, appName, sparkHome, pyFiles, environment, batchSize, serializer, conf, jsc, profiler_cls) @@ -121,7 +121,15 @@ class SparkContext(object): def _do_init(self, master, appName, sparkHome, pyFiles, environment, batchSize, serializer, conf, jsc, profiler_cls): self.environment = environment or {} - self._conf = conf or SparkConf(_jvm=self._jvm) + # java gateway must have been launched at this point. + if conf is not None and conf._jconf is not None: + # conf has been initialized in JVM properly, so use conf directly. This represent the + # scenario that JVM has been launched before SparkConf is created (e.g. SparkContext is + # created and then stopped, and we create a new SparkConf and new SparkContext again) + self._conf = conf + else: + self._conf = SparkConf(_jvm=SparkContext._jvm) + self._batchSize = batchSize # -1 represents an unlimited batch size self._unbatched_serializer = serializer if batchSize == 0: @@ -232,14 +240,14 @@ class SparkContext(object): return self._jvm.JavaSparkContext(jconf) @classmethod - def _ensure_initialized(cls, instance=None, gateway=None): + def _ensure_initialized(cls, instance=None, gateway=None, conf=None): """ Checks whether a SparkContext is initialized or not. Throws error if a SparkContext is already running. """ with SparkContext._lock: if not SparkContext._gateway: - SparkContext._gateway = gateway or launch_gateway() + SparkContext._gateway = gateway or launch_gateway(conf) SparkContext._jvm = SparkContext._gateway.jvm if instance: |