diff --git a/python/pyspark/context.py b/python/pyspark/context.py index 93faa2e3857ed200d276d8e69a747b3cd124ec8a..c9f42d3aacb5889eefbfd9365ce71785d108ad07 100644 --- a/python/pyspark/context.py +++ b/python/pyspark/context.py @@ -372,6 +372,37 @@ class SparkContext(object): return newStorageLevel(storageLevel.useDisk, storageLevel.useMemory, storageLevel.deserialized, storageLevel.replication) + def setJobGroup(self, groupId, description): + """ + Assigns a group ID to all the jobs started by this thread until the group ID is set to a + different value or cleared. + + Often, a unit of execution in an application consists of multiple Spark actions or jobs. + Application programmers can use this method to group all those jobs together and give a + group description. Once set, the Spark web UI will associate such jobs with this group. + """ + self._jsc.setJobGroup(groupId, description) + + def setLocalProperty(self, key, value): + """ + Set a local property that affects jobs submitted from this thread, such as the + Spark fair scheduler pool. + """ + self._jsc.setLocalProperty(key, value) + + def getLocalProperty(self, key): + """ + Get a local property set in this thread, or null if it is missing. See + L{setLocalProperty} + """ + return self._jsc.getLocalProperty(key) + + def sparkUser(self): + """ + Get SPARK_USER for user who is running SparkContext. + """ + return self._jsc.sc().sparkUser() + def _test(): import atexit import doctest diff --git a/python/pyspark/rdd.py b/python/pyspark/rdd.py index be23f87f5ed2d936fe79b22eb0f1cdc70d35d195..097a0a236b1451afe5e9d53b76a724d525def15c 100644 --- a/python/pyspark/rdd.py +++ b/python/pyspark/rdd.py @@ -95,6 +95,13 @@ class RDD(object): self.is_checkpointed = False self.ctx = ctx self._jrdd_deserializer = jrdd_deserializer + self._id = jrdd.id() + + def id(self): + """ + A unique ID for this RDD (within its SparkContext). + """ + return self._id def __repr__(self): return self._jrdd.toString()