Skip to content

feat: Support hdfs:// uris in to_remote_storage for Spark offline store #5635

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

Merged
HaoXuAI merged 3 commits into from
Sep 27, 2025
Merged

feat: Support hdfs:// uris in to_remote_storage for Spark offline store #5635

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
916788e
feat: support hdfs staging for Spark offline store
chimeyrock999 Sep 26, 2025
df17b70
fix: add safety check for _jvm and _jsc in _list_hdfs_files
chimeyrock999 Sep 26, 2025
837a123
Merge branch 'master' into feature/spark_hdfs_staging
HaoXuAI Sep 27, 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
28 changes: 26 additions & 2 deletions sdk/python/feast/infra/offline_stores/contrib/spark_offline_store/spark.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -497,10 +497,18 @@ def to_remote_storage(self) -> List[str]:
return aws_utils.list_s3_files(
self._config.offline_store.region, output_uri
)

elif self._config.offline_store.staging_location.startswith("hdfs://"):
output_uri = os.path.join(
self._config.offline_store.staging_location, str(uuid.uuid4())
)
sdf.write.parquet(output_uri)
spark_session = get_spark_session_or_start_new_with_repoconfig(
store_config=self._config.offline_store
)
return _list_hdfs_files(spark_session, output_uri)
else:
raise NotImplementedError(
"to_remote_storage is only implemented for file:// and s3:// uri schemes"
"to_remote_storage is only implemented for file://, s3:// and hdfs:// uri schemes"
)

else:
Expand Down Expand Up @@ -629,6 +637,22 @@ def _list_files_in_folder(folder):
return files


def _list_hdfs_files(spark_session: SparkSession, uri: str) -> List[str]:
jvm = spark_session._jvm
jsc = spark_session._jsc
if jvm is None or jsc is None:
raise RuntimeError("Spark JVM or JavaSparkContext is not available")
conf = jsc.hadoopConfiguration()
path = jvm.org.apache.hadoop.fs.Path(uri)
fs = jvm.org.apache.hadoop.fs.FileSystem.get(path.toUri(), conf)
statuses = fs.listStatus(path)
files = []
for f in statuses:
if f.isFile():
files.append(f.getPath().toString())
return files


def _cast_data_frame(
df_new: pyspark.sql.DataFrame, df_existing: pyspark.sql.DataFrame
) -> pyspark.sql.DataFrame:
Expand Down
Loading