HyukjinKwon commented on code in PR #54258:
URL: https://github.com/apache/spark/pull/54258#discussion_r2797584727
##########
python/pyspark/worker_util.py:
##########
@@ -155,39 +155,42 @@ def setup_spark_files(infile: IO) -> None:
def setup_broadcasts(infile: IO) -> None:
"""
Set up broadcasted variables.
+ {
+ "conn_info": int | str | None,
+ "auth_secret": str | None,
+ "broadcast_variables": [
+ {
+ "bid": int,
+ "path": str | None,
+ }
+ ]
+ }
"""
if not is_remote_only():
from pyspark.core.broadcast import Broadcast, _broadcastRegistry
- # fetch names and values of broadcast variables
- needs_broadcast_decryption_server = read_bool(infile)
- num_broadcast_variables = read_int(infile)
- if needs_broadcast_decryption_server:
+ data = json.loads(utf8_deserializer.loads(infile))
Review Comment:
How would we use this info for debugging? I feel like you can just log it
here instead of JSON ser/de
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
