Change MinIO integration options in librarian to be more generic - to support a Garage integration (#594)

* Tweak object store parameters to be more generic for other S3-type store integration

* Update librarian to have region & SSL params

* Update MinIO migration tech spec
This commit is contained in:
cybermaggedon 2025-12-27 18:01:51 +00:00 committed by GitHub
parent 5304f96fe6
commit 25563bae3c
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 333 additions and 44 deletions

View file

@ -14,29 +14,32 @@ class BlobStore:
def __init__(
self,
minio_host, minio_access_key, minio_secret_key, bucket_name,
endpoint, access_key, secret_key, bucket_name,
use_ssl=False, region=None,
):
self.minio = Minio(
endpoint = minio_host,
access_key = minio_access_key,
secret_key = minio_secret_key,
secure = False,
self.client = Minio(
endpoint = endpoint,
access_key = access_key,
secret_key = secret_key,
secure = use_ssl,
region = region,
)
self.bucket_name = bucket_name
logger.info("Connected to MinIO")
protocol = "https" if use_ssl else "http"
logger.info(f"Connected to S3-compatible storage at {protocol}://{endpoint}")
self.ensure_bucket()
def ensure_bucket(self):
# Make the bucket if it doesn't exist.
found = self.minio.bucket_exists(bucket_name=self.bucket_name)
found = self.client.bucket_exists(bucket_name=self.bucket_name)
if not found:
self.minio.make_bucket(bucket_name=self.bucket_name)
self.client.make_bucket(bucket_name=self.bucket_name)
logger.info(f"Created bucket {self.bucket_name}")
else:
logger.debug(f"Bucket {self.bucket_name} already exists")
@ -44,7 +47,7 @@ class BlobStore:
async def add(self, object_id, blob, kind):
# FIXME: Loop retry
self.minio.put_object(
self.client.put_object(
bucket_name = self.bucket_name,
object_name = "doc/" + str(object_id),
length = len(blob),
@ -57,7 +60,7 @@ class BlobStore:
async def remove(self, object_id):
# FIXME: Loop retry
self.minio.remove_object(
self.client.remove_object(
bucket_name = self.bucket_name,
object_name = "doc/" + str(object_id),
)
@ -68,7 +71,7 @@ class BlobStore:
async def get(self, object_id):
# FIXME: Loop retry
resp = self.minio.get_object(
resp = self.client.get_object(
bucket_name = self.bucket_name,
object_name = "doc/" + str(object_id),
)

View file

@ -17,12 +17,14 @@ class Librarian:
def __init__(
self,
cassandra_host, cassandra_username, cassandra_password,
minio_host, minio_access_key, minio_secret_key,
object_store_endpoint, object_store_access_key, object_store_secret_key,
bucket_name, keyspace, load_document,
object_store_use_ssl=False, object_store_region=None,
):
self.blob_store = BlobStore(
minio_host, minio_access_key, minio_secret_key, bucket_name
object_store_endpoint, object_store_access_key, object_store_secret_key, bucket_name,
use_ssl=object_store_use_ssl, region=object_store_region,
)
self.table_store = LibraryTableStore(

View file

@ -41,9 +41,11 @@ default_collection_response_queue = collection_response_queue
default_config_request_queue = config_request_queue
default_config_response_queue = config_response_queue
default_minio_host = "minio:9000"
default_minio_access_key = "minioadmin"
default_minio_secret_key = "minioadmin"
default_object_store_endpoint = "ceph-rgw:7480"
default_object_store_access_key = "object-user"
default_object_store_secret_key = "object-password"
default_object_store_use_ssl = False
default_object_store_region = None
default_cassandra_host = "cassandra"
bucket_name = "library"
@ -80,14 +82,22 @@ class Processor(AsyncProcessor):
"config_response_queue", default_config_response_queue
)
minio_host = params.get("minio_host", default_minio_host)
minio_access_key = params.get(
"minio_access_key",
default_minio_access_key
object_store_endpoint = params.get("object_store_endpoint", default_object_store_endpoint)
object_store_access_key = params.get(
"object_store_access_key",
default_object_store_access_key
)
minio_secret_key = params.get(
"minio_secret_key",
default_minio_secret_key
object_store_secret_key = params.get(
"object_store_secret_key",
default_object_store_secret_key
)
object_store_use_ssl = params.get(
"object_store_use_ssl",
default_object_store_use_ssl
)
object_store_region = params.get(
"object_store_region",
default_object_store_region
)
cassandra_host = params.get("cassandra_host")
@ -113,8 +123,8 @@ class Processor(AsyncProcessor):
"librarian_response_queue": librarian_response_queue,
"collection_request_queue": collection_request_queue,
"collection_response_queue": collection_response_queue,
"minio_host": minio_host,
"minio_access_key": minio_access_key,
"object_store_endpoint": object_store_endpoint,
"object_store_access_key": object_store_access_key,
"cassandra_host": self.cassandra_host,
"cassandra_username": self.cassandra_username,
"cassandra_password": self.cassandra_password,
@ -208,12 +218,14 @@ class Processor(AsyncProcessor):
cassandra_host = self.cassandra_host,
cassandra_username = self.cassandra_username,
cassandra_password = self.cassandra_password,
minio_host = minio_host,
minio_access_key = minio_access_key,
minio_secret_key = minio_secret_key,
object_store_endpoint = object_store_endpoint,
object_store_access_key = object_store_access_key,
object_store_secret_key = object_store_secret_key,
bucket_name = bucket_name,
keyspace = keyspace,
load_document = self.load_document,
object_store_use_ssl = object_store_use_ssl,
object_store_region = object_store_region,
)
self.collection_manager = CollectionManager(
@ -494,23 +506,36 @@ class Processor(AsyncProcessor):
)
parser.add_argument(
'--minio-host',
default=default_minio_host,
help=f'Minio hostname (default: {default_minio_host})',
'--object-store-endpoint',
default=default_object_store_endpoint,
help=f'Object storage endpoint (default: {default_object_store_endpoint})',
)
parser.add_argument(
'--minio-access-key',
default='minioadmin',
help='Minio access key / username '
f'(default: {default_minio_access_key})',
'--object-store-access-key',
default=default_object_store_access_key,
help='Object storage access key / username '
f'(default: {default_object_store_access_key})',
)
parser.add_argument(
'--minio-secret-key',
default='minioadmin',
help='Minio secret key / password '
f'(default: {default_minio_access_key})',
'--object-store-secret-key',
default=default_object_store_secret_key,
help='Object storage secret key / password '
f'(default: {default_object_store_secret_key})',
)
parser.add_argument(
'--object-store-use-ssl',
action='store_true',
default=default_object_store_use_ssl,
help=f'Use SSL/TLS for object storage connection (default: {default_object_store_use_ssl})',
)
parser.add_argument(
'--object-store-region',
default=default_object_store_region,
help='Object storage region (optional)',
)
add_cassandra_args(parser)