Skip to content

Bulk download of Databricks users and service principals. #12

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Bulk download of Databricks users and service principals. #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
9 changes: 8 additions & 1 deletion azure_dbr_scim_sync/cli.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,12 @@
help="verbose information about changes",
show_default=True)
@click.option('--debug', default=False, is_flag=True, help="more verbose, shows API calls", show_default=True)
@click.option(
'--bulk-download',
default=False,
is_flag=True,
help="bulk download of users and service principals from the Databricks account, better performance with a large number of users and service principals",
show_default=True)
@click.option(
'--dry-run-security-principals',
default=False,
Expand Down Expand Up @@ -72,7 +78,7 @@
help="include mail-enabled Entra groups in the sync")
def sync_cli(groups_json_file, verbose, debug, dry_run_security_principals, dry_run_members, worker_threads,
save_graph_response_json, query_graph_only, group_search_depth, full_sync,
graph_change_feed_grace_time, include_non_security_groups, include_mail_enabled_groups):
graph_change_feed_grace_time, include_non_security_groups, include_mail_enabled_groups, bulk_download):
install_logger()

logger = logging.getLogger('sync')
Expand Down Expand Up @@ -128,6 +134,7 @@ def sync_cli(groups_json_file, verbose, debug, dry_run_security_principals, dry_
groups=[x.to_sdk_group() for x in stuff_to_sync.groups.values()],
service_principals=[x.to_sdk_service_principal() for x in stuff_to_sync.service_principals.values()],
deep_sync_group_names=list(stuff_to_sync.deep_sync_group_names),
bulk_download=bulk_download,
dry_run_security_principals=dry_run_security_principals,
dry_run_members=dry_run_members,
worker_threads=worker_threads)
Expand Down
37 changes: 31 additions & 6 deletions azure_dbr_scim_sync/scim.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -126,17 +126,20 @@ def effecitve_change_count(self):
'user': {
'key_obj_field': 'user_name',
'key_api_field': 'userName',
'cache': user_cache
'cache': user_cache,
'objs_by_id': None
},
'group': {
'key_obj_field': 'display_name',
'key_api_field': 'displayName',
'cache': group_cache
'cache': group_cache,
'objs_by_id': None
},
'spn': {
'key_obj_field': 'application_id',
'key_api_field': 'applicationId',
'cache': spn_cache
'cache': spn_cache,
'objs_by_id': None
}
}

Expand All @@ -145,15 +148,19 @@ def _generic_get_by_human_name(mapper, sdk_module, search_name):
cache = mapper['cache']
key_obj_field = mapper['key_obj_field']
key_api_field = mapper['key_api_field']
objs_by_id = mapper['objs_by_id']

cached_id = cache[search_name]
obj = None

if cached_id:
# verify cache
try:
obj = sdk_module.get(cached_id)
if obj.__dict__[key_obj_field] == search_name:
if objs_by_id is not None:
obj = objs_by_id[cached_id]
else:
obj = sdk_module.get(cached_id)
if obj.__dict__[key_obj_field].casefold() == search_name.casefold():
# hit!
logger.debug(f"Cache hit: {search_name=}, {obj.id=}")
return obj
Expand Down Expand Up @@ -196,7 +203,6 @@ def _generic_create_or_update(mapper, desired: T, actual: T, compare_fields: Lis
ResultClass = MergeResult[T]
cache = mapper['cache']
key_obj_field = mapper['key_obj_field']
mapper['key_api_field']

desired = deepcopy(desired)
desired_dict = deepcopy(desired.as_dict())
Expand Down Expand Up @@ -453,10 +459,29 @@ def sync(*,
groups: Iterable[iam.Group],
service_principals: Iterable[iam.ServicePrincipal],
deep_sync_group_names: Iterable[str],
bulk_download=False,
dry_run_security_principals=False,
dry_run_members=False,
worker_threads: int = 10):

global _generic_type_map

if not bulk_download:
logger.info("Skipping bulk downloading of Databricks groups, users and service principals")
else:
# API does not include group members! Could only be used if dry_run_members is true.
logger.info("Skipping bulk downloading of Databricks groups...")
# _generic_type_map['group']['objs_by_id'] = {x.id : x for x in account_client.groups.list()}
# logger.info(f"Downloaded: groups={_generic_type_map['group']['objs_by_id']}")

logger.info("Bulk downloading of Databricks users...")
_generic_type_map['user']['objs_by_id'] = {x.id : x for x in account_client.users.list()}
logger.info(f"Downloaded: users={len(_generic_type_map['user']['objs_by_id'])}")

logger.info("Bulk downloading of Databricks service principals...")
_generic_type_map['spn']['objs_by_id'] = {x.id : x for x in account_client.service_principals.list()}
logger.info(f"Downloaded: service_principals={len(_generic_type_map['spn']['objs_by_id'])}")

logger.info("Starting creating or updating users, groups and service principals...")
result = ScimSyncObject(users=create_or_update_users(account_client,
users,
Expand Down