sbcli-pre 25.3.8__tar.gz → 25.3.10__tar.gz

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 25.3.8
+Version: 25.3.10
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/sbcli_pre.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: sbcli-pre
-Version: 25.3.8
+Version: 25.3.10
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_cli/cli.py

@@ -515,6 +515,7 @@ class CLIWrapper(CLIWrapperBase):
     def init_cluster__get_logs(self, subparser):
         subcommand = self.add_sub_command(subparser, 'get-logs', 'Returns a cluster\'s status logs')
         subcommand.add_argument('cluster_id', help='Cluster id', type=str).completer = self._completer_get_cluster_list
+        argument = subcommand.add_argument('--limit', help='show last number of logs, default 50', type=int, default=50, dest='limit', required=False)
 
     def init_cluster__get_secret(self, subparser):
         subcommand = self.add_sub_command(subparser, 'get-secret', 'Gets a cluster\'s secret')
@@ -534,6 +535,8 @@ class CLIWrapper(CLIWrapperBase):
         subcommand.add_argument('cluster_id', help='Cluster id', type=str).completer = self._completer_get_cluster_list
         argument = subcommand.add_argument('--cp-only', help='Update the control plane only', type=bool, default=False, dest='mgmt_only', required=False)
         argument = subcommand.add_argument('--restart', help='Restart the management services', type=bool, default=False, dest='restart', required=False)
+        argument = subcommand.add_argument('--spdk-image', help='Restart the storage nodes using the provided image', type=str, dest='spdk_image', required=False)
+        argument = subcommand.add_argument('--mgmt-image', help='Restart the management services using the provided image', type=str, dest='mgmt_image', required=False)
 
     def init_cluster__graceful_shutdown(self, subparser):
         subcommand = self.add_sub_command(subparser, 'graceful-shutdown', 'Initiates a graceful shutdown of a cluster\'s storage nodes')
@@ -548,6 +551,7 @@ class CLIWrapper(CLIWrapperBase):
     def init_cluster__list_tasks(self, subparser):
         subcommand = self.add_sub_command(subparser, 'list-tasks', 'Lists tasks of a cluster')
         subcommand.add_argument('cluster_id', help='Cluster id', type=str).completer = self._completer_get_cluster_list
+        argument = subcommand.add_argument('--limit', help='show last number of tasks, default 50', type=int, default=50, dest='limit', required=False)
 
     def init_cluster__cancel_task(self, subparser):
         subcommand = self.add_sub_command(subparser, 'cancel-task', 'Cancels task by task id')

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_cli/clibase.py

@@ -311,8 +311,7 @@ class CLIWrapperBase:
             return False
 
     def cluster__get_logs(self, sub_command, args):
-        cluster_id = args.cluster_id
-        return cluster_ops.get_logs(cluster_id)
+        return cluster_ops.get_logs(**args.__dict__)
 
     def cluster__get_secret(self, sub_command, args):
         cluster_id = args.cluster_id
@@ -328,7 +327,7 @@ class CLIWrapperBase:
         return health_controller.check_cluster(cluster_id)
 
     def cluster__update(self, sub_command, args):
-        return cluster_ops.update_cluster(args.cluster_id, mgmt_only=args.mgmt_only, restart_cluster=args.restart)
+        return cluster_ops.update_cluster(**args.__dict__)
     
     def cluster__graceful_shutdown(self, sub_command, args):
         return cluster_ops.cluster_grace_shutdown(args.cluster_id)
@@ -337,7 +336,7 @@ class CLIWrapperBase:
         return cluster_ops.cluster_grace_startup(args.cluster_id, args.clear_data, args.spdk_image)
 
     def cluster__list_tasks(self, sub_command, args):
-        return tasks_controller.list_tasks(args.cluster_id)
+        return tasks_controller.list_tasks(**args.__dict__)
 
     def cluster__cancel_task(self, sub_command, args):
         return tasks_controller.cancel_task(args.task_id)

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_core/cluster_ops.py

@@ -1161,27 +1161,27 @@ def set_secret(cluster_id, secret):
     return "Done"
 
 
-def get_logs(cluster_id, is_json=False):
+def get_logs(cluster_id, is_json=False, limit=50, **kwargs):
     db_controller = DBController()
     cluster = db_controller.get_cluster_by_id(cluster_id)
     if not cluster:
         logger.error(f"Cluster not found {cluster_id}")
         return False
 
-    events = db_controller.get_events(cluster_id)
+    events = db_controller.get_events(cluster_id, limit=limit, reverse=True)
     out = []
+    events.reverse()
     for record in events:
-        logger.debug(record)
         Storage_ID = None
-        if 'storage_ID' in record.object_dict:
-            Storage_ID = record.object_dict['storage_ID']
+        if record.storage_id >= 0:
+            Storage_ID = record.storage_id
 
         elif 'cluster_device_order' in record.object_dict:
             Storage_ID = record.object_dict['cluster_device_order']
 
         vuid = None
-        if 'vuid' in record.object_dict:
-            vuid = record.object_dict['vuid']
+        if record.vuid > 0:
+            vuid = record.vuid
 
         msg =  record.message
         if record.event in ["device_status", "node_status"]:
@@ -1213,11 +1213,11 @@ def get_cluster(cl_id):
     return json.dumps(cluster.get_clean_dict(), indent=2, sort_keys=True)
 
 
-def update_cluster(cl_id, mgmt_only=False, restart_cluster=False):
+def update_cluster(cluster_id, mgmt_only=False, restart=False, spdk_image=None, mgmt_image=None, **kwargs):
     db_controller = DBController()
-    cluster = db_controller.get_cluster_by_id(cl_id)
+    cluster = db_controller.get_cluster_by_id(cluster_id)
     if not cluster:
-        logger.error(f"Cluster not found {cl_id}")
+        logger.error(f"Cluster not found {cluster_id}")
         return False
 
     try:
@@ -1230,34 +1230,56 @@ def update_cluster(cl_id, mgmt_only=False, restart_cluster=False):
 
     try:
         logger.info("Updating mgmt cluster")
-        cluster_docker = utils.get_docker_client(cl_id)
+        cluster_docker = utils.get_docker_client(cluster_id)
         logger.info(f"Pulling image {constants.SIMPLY_BLOCK_DOCKER_IMAGE}")
         cluster_docker.images.pull(constants.SIMPLY_BLOCK_DOCKER_IMAGE)
         image_without_tag = constants.SIMPLY_BLOCK_DOCKER_IMAGE.split(":")[0]
         image_without_tag = image_without_tag.split("/")[-1]
+        service_image = constants.SIMPLY_BLOCK_DOCKER_IMAGE
+        if mgmt_image:
+            service_image = mgmt_image
         for service in cluster_docker.services.list():
             if image_without_tag in service.attrs['Spec']['Labels']['com.docker.stack.image']:
                 logger.info(f"Updating service {service.name}")
-                service.update(image=constants.SIMPLY_BLOCK_DOCKER_IMAGE, force_update=True)
+                service.update(image=service_image, force_update=True)
         logger.info("Done updating mgmt cluster")
     except Exception as e:
-        print(e)
+        logger.exception(e)
+
+    if mgmt_only:
+        return True
+
+    logger.info("Updating spdk image on storage nodes")
+    for node in db_controller.get_storage_nodes_by_cluster_id(cluster_id):
+        if node.status in [StorageNode.STATUS_ONLINE, StorageNode.STATUS_SUSPENDED, StorageNode.STATUS_DOWN]:
+            try:
+                node_docker = docker.DockerClient(base_url=f"tcp://{node.mgmt_ip}:2375", version="auto", timeout=60 * 5)
+                img = constants.SIMPLY_BLOCK_SPDK_ULTRA_IMAGE
+                if spdk_image:
+                    img = spdk_image
+                logger.info(f"Pulling image {img}")
+                node_docker.images.pull(img)
+            except Exception as e:
+                logger.error(e)
+
+    if not restart:
+        return True
+
+    logger.info("Restarting cluster")
+    for node in db_controller.get_storage_nodes_by_cluster_id(cluster_id):
+        if node.status == StorageNode.STATUS_ONLINE:
+            logger.info(f"Suspending node: {node.get_id()}")
+            storage_node_ops.suspend_storage_node(node.get_id())
+            logger.info(f"Shutting down node: {node.get_id()}")
+            storage_node_ops.shutdown_storage_node(node.get_id(), force=True)
 
-    if not mgmt_only:
-        set_cluster_status(cl_id, Cluster.STATUS_SUSPENDED)
-        logger.info("updating storage nodes")
-        for node in db_controller.get_storage_nodes_by_cluster_id(cl_id):
-            if node.status in [StorageNode.STATUS_ONLINE, StorageNode.STATUS_SUSPENDED]:
-                try:
-                    storage_node_ops.start_storage_node_api_container(node.mgmt_ip)
-                except Exception as e:
-                    logger.error(e)
-
-        if restart_cluster:
-            logger.info("Restarting cluster")
-            ret = cluster_grace_shutdown(cl_id)
-            if ret:
-                cluster_grace_startup(cl_id)
+    for node in db_controller.get_storage_nodes_by_cluster_id(cluster_id):
+        if node.status == StorageNode.STATUS_OFFLINE:
+            if spdk_image:
+                logger.info(f"Restarting node: {node.get_id()} with SPDK image: {spdk_image}")
+            else:
+                logger.info(f"Restarting node: {node.get_id()}")
+            storage_node_ops.restart_storage_node(node.get_id(), force=True, spdk_image=spdk_image)
 
     logger.info("Done")
     return True

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_core/constants.py

@@ -114,7 +114,7 @@ INSTANCE_STORAGE_DATA = {
         'm6id.8xlarge': {'number_of_devices': 1, 'size_per_device_gb': 1900},
     }
 
-MAX_SNAP_COUNT = 15
+MAX_SNAP_COUNT = 100
 
 SPDK_PROXY_MULTI_THREADING_ENABLED=True
 SPDK_PROXY_TIMEOUT=60*5

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_core/controllers/tasks_controller.py

@@ -97,14 +97,15 @@ def add_node_to_auto_restart(node):
     return _add_task(JobSchedule.FN_NODE_RESTART, node.cluster_id, node.get_id(), "")
 
 
-def list_tasks(cluster_id, is_json=False):
+def list_tasks(cluster_id, is_json=False, limit=50, **kwargs):
     cluster = db_controller.get_cluster_by_id(cluster_id)
     if not cluster:
         logger.error("Cluster not found: %s", cluster_id)
         return False
 
     data = []
-    tasks = db_controller.get_job_tasks(cluster_id, reverse=False)
+    tasks = db_controller.get_job_tasks(cluster_id, reverse=True, limit=limit)
+    tasks.reverse()
     if tasks and is_json is True:
         for t in tasks:
             data.append(t.get_clean_dict())

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_core/db_controller.py

@@ -264,11 +264,11 @@ class DBController(metaclass=Singleton):
         stats = PortStat().read_from_db(self.kv_store, id="%s/%s" % (node_id, port_id), limit=limit, reverse=True)
         return stats
 
-    def get_events(self, event_id=" ") -> List[EventObj]:
-        return EventObj().read_from_db(self.kv_store, id=event_id)
+    def get_events(self, event_id=" ", limit=0, reverse=False) -> List[EventObj]:
+        return EventObj().read_from_db(self.kv_store, id=event_id, limit=limit, reverse=reverse)
 
-    def get_job_tasks(self, cluster_id, reverse=True) -> List[JobSchedule]:
-        return JobSchedule().read_from_db(self.kv_store, id=cluster_id, reverse=reverse)
+    def get_job_tasks(self, cluster_id, reverse=True, limit=0) -> List[JobSchedule]:
+        return JobSchedule().read_from_db(self.kv_store, id=cluster_id, reverse=reverse, limit=limit)
 
     def get_task_by_id(self, task_id) -> JobSchedule:
         for task in self.get_job_tasks(" "):

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_core/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-pre
-SIMPLY_BLOCK_VERSION=25.3.8
+SIMPLY_BLOCK_VERSION=25.3.10
 
 SIMPLY_BLOCK_DOCKER_IMAGE=public.ecr.aws/simply-block/simplyblock:R25.3-PRE-Hotfix
 SIMPLY_BLOCK_SPDK_ULTRA_IMAGE=public.ecr.aws/simply-block/ultra:R25.3-PRE-latest

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_core/services/storage_node_monitor.py

@@ -140,13 +140,19 @@ def update_cluster_status(cluster_id):
     elif current_cluster_status == Cluster.STATUS_SUSPENDED and next_current_status \
             in [Cluster.STATUS_ACTIVE, Cluster.STATUS_DEGRADED]:
         # needs activation
-        # check node statuss, check auto restart for nodes
+        # check node status, check auto restart for nodes
         can_activate = True
         for node in db_controller.get_storage_nodes_by_cluster_id(cluster_id):
-            if node.status not in [StorageNode.STATUS_ONLINE, StorageNode.STATUS_REMOVED]:
-                logger.error(f"can not activate cluster: node in not online {node.get_id()}: {node.status}")
+            if node.status in [StorageNode.STATUS_IN_SHUTDOWN, StorageNode.STATUS_IN_CREATION,
+                               StorageNode.STATUS_RESTARTING]:
+                logger.error(f"can not activate cluster: node is not in correct status {node.get_id()}: {node.status}")
                 can_activate = False
                 break
+
+            # if node.status not in [StorageNode.STATUS_ONLINE, StorageNode.STATUS_REMOVED]:
+            #     logger.error(f"can not activate cluster: node in not online {node.get_id()}: {node.status}")
+            #     can_activate = False
+            #     break
             if tasks_controller.get_active_node_restart_task(cluster_id, node.get_id()):
                 logger.error(f"can not activate cluster: restart tasks found")
                 can_activate = False

{sbcli-pre-25.3.8 → sbcli-pre-25.3.10}/simplyblock_core/storage_node_ops.py

@@ -2961,7 +2961,7 @@ def recreate_lvstore(snode):
         snode.rpc_username, snode.rpc_password)
 
     sec_node = db_controller.get_storage_node_by_id(snode.secondary_node_id)
-    sec_node_api = SNodeClient(sec_node.api_endpoint)
+    sec_node_api = SNodeClient(sec_node.api_endpoint, timeout=5, retry=5)
 
     lvol_list = []
     for lv in db_controller.get_lvols_by_node_id(snode.get_id()):