Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SPARK-51055][SS][CONNECT] Streaming foreachBatch should call init logic inside a try #49757

Open
wants to merge 3 commits into
base: master
Choose a base branch
from
+19 −18
Open

[SPARK-51055][SS][CONNECT] Streaming foreachBatch should call init logic inside a try #49757

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
fe25067
done
WweiL Feb 1, 2025
7a29f87
retrigger
WweiL Feb 1, 2025
4280077
fmt
WweiL Feb 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
37 changes: 19 additions & 18 deletions python/pyspark/sql/connect/streaming/worker/foreach_batch_worker.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,26 +43,29 @@

def main(infile: IO, outfile: IO) -> None:
global spark
check_python_version(infile)

# Enable Spark Connect Mode
os.environ["SPARK_CONNECT_MODE_ENABLED"] = "1"
log_name = "Streaming ForeachBatch worker"

connect_url = os.environ["SPARK_CONNECT_LOCAL_URL"]
session_id = utf8_deserializer.loads(infile)
def init():
check_python_version(infile)

print(
"Streaming foreachBatch worker is starting with "
f"url {connect_url} and sessionId {session_id}."
)
# Enable Spark Connect Mode
os.environ["SPARK_CONNECT_MODE_ENABLED"] = "1"

# To attach to the existing SparkSession, we're setting the session_id in the URL.
connect_url = connect_url + ";session_id=" + session_id
spark_connect_session = SparkSession.builder.remote(connect_url).getOrCreate()
assert spark_connect_session.session_id == session_id
spark = spark_connect_session
connect_url = os.environ["SPARK_CONNECT_LOCAL_URL"]
session_id = utf8_deserializer.loads(infile)

log_name = "Streaming ForeachBatch worker"
print(f"{log_name} is starting with " f"url {connect_url} and sessionId {session_id}.")

# To attach to the existing SparkSession, we're setting the session_id in the URL.
connect_url = connect_url + ";session_id=" + session_id
spark_connect_session = SparkSession.builder.remote(connect_url).getOrCreate()
assert spark_connect_session.session_id == session_id
spark = spark_connect_session

func = worker.read_command(pickle_ser, infile)
write_int(0, outfile)
outfile.flush()

def process(df_id, batch_id): # type: ignore[no-untyped-def]
global spark
Expand All @@ -72,9 +75,7 @@ def process(df_id, batch_id): # type: ignore[no-untyped-def]
print(f"{log_name} Completed batch {batch_id} with DF id {df_id}")

try:
func = worker.read_command(pickle_ser, infile)
write_int(0, outfile)
outfile.flush()
init()

while True:
df_ref_id = utf8_deserializer.loads(infile)
Expand Down