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.

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

Implement disposition field in SQL backend #3455

Closed
Show file tree
Hide file tree
Changes from all commits
Commits
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
4 changes: 4 additions & 0 deletions src/databricks/labs/ucx/config.py
Original file line number Diff line number Diff line change
@@ -1,6 +1,7 @@
from dataclasses import dataclass

from databricks.sdk.core import Config
from databricks.sdk.service.sql import Disposition

__all__ = ["WorkspaceConfig"]

Expand Down Expand Up @@ -92,6 +93,9 @@ class WorkspaceConfig: # pylint: disable=too-many-instance-attributes
# Skip TACL migration during table migration
skip_tacl_migration: bool = False

# Select SQL query statement disposition, default to INLINE
query_statement_disposition: Disposition | None = None

def replace_inventory_variable(self, text: str) -> str:
return text.replace("$inventory", f"hive_metastore.{self.inventory_database}")

Expand Down
4 changes: 3 additions & 1 deletion src/databricks/labs/ucx/contexts/workspace_cli.py
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,9 @@ def workspace_client(self) -> WorkspaceClient:

@cached_property
def sql_backend(self) -> SqlBackend:
return StatementExecutionBackend(self.workspace_client, self.config.warehouse_id)
return StatementExecutionBackend(
self.workspace_client, self.config.warehouse_id, disposition=self.config.query_statement_disposition
)

@cached_property
def cluster_access(self) -> ClusterAccess:
Expand Down
8 changes: 8 additions & 0 deletions src/databricks/labs/ucx/install.py
Original file line number Diff line number Diff line change
Expand Up @@ -45,6 +45,7 @@
CreateWarehouseRequestWarehouseType,
EndpointInfoWarehouseType,
SpotInstancePolicy,
Disposition,
)
from databricks.sdk.useragent import with_extra

Expand Down Expand Up @@ -259,6 +260,12 @@ def _prompt_for_new_installation(self) -> WorkspaceConfig:
recon_tolerance_percent = int(
self.prompts.question("Reconciliation threshold, in percentage", default="5", valid_number=True)
)

query_statement_disposition = self.prompts.confirm(
"Do you want to use the `EXTERNAL_LINKS` disposition for query statements? (Only needed when exporting more than 25 MiB of data from workspaces with many resources)"
)
query_statement_disposition = Disposition.EXTERNAL_LINKS if query_statement_disposition else None

return WorkspaceConfig(
inventory_database=inventory_database,
ucx_catalog=ucx_catalog,
Expand All @@ -276,6 +283,7 @@ def _prompt_for_new_installation(self) -> WorkspaceConfig:
recon_tolerance_percent=recon_tolerance_percent,
upload_dependencies=upload_dependencies,
default_owner_group=default_owner_group,
query_statement_disposition=query_statement_disposition,
)

def _compare_remote_local_versions(self):
Expand Down
Loading