sbcli-dev 10.3.4__tar.gz → 10.4.0__tar.gz

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: sbcli-dev
-Version: 10.3.4
+Version: 10.4.0
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/sbcli_dev.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: sbcli-dev
-Version: 10.3.4
+Version: 10.4.0
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_cli/cli.py

@@ -279,8 +279,8 @@ class CLIWrapper:
         sub_command.add_argument("--prov-cap-crit", help='Capacity critical level in percent, default=190',
                                  type=int, required=False, dest="prov_cap_crit")
         sub_command.add_argument("--ifname", help='Management interface name, default: eth0')
-        sub_command.add_argument("--log-del-interval", help='graylog deletion interval, default: 2d',
-                                 dest='log_del_interval', default='2d')
+        sub_command.add_argument("--log-del-interval", help='graylog deletion interval, default: 3d',
+                                 dest='log_del_interval', default='3d')
         sub_command.add_argument("--metrics-retention-period", help='retention period for prometheus metrics, default: 7d',
                                  dest='metrics_retention_period', default='7d')
         sub_command.add_argument("--contact-point", help='the email or slack webhook url to be used for alerting',

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/constants.py

@@ -73,6 +73,7 @@ SIMPLY_BLOCK_CLI_NAME = get_from_env_var_file(
         "SIMPLY_BLOCK_COMMAND_NAME", "sbcli")
 TASK_EXEC_INTERVAL_SEC = 10
 TASK_EXEC_RETRY_COUNT = 8
+SIMPLY_BLOCK_SPDK_CORE_IMAGE = "simplyblock/spdk-core:v24.05.x-latest"
 
 
 SIMPLY_BLOCK_SPDK_ULTRA_IMAGE = "simplyblock/spdk:lvolstore-ha-snapshot-latest"

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/controllers/health_controller.py

@@ -396,6 +396,9 @@ def check_lvol_on_node(lvol_id, node_id):
         return False
 
     snode = db_controller.get_storage_node_by_id(node_id)
+    if not snode:
+        return False
+
     rpc_client = RPCClient(
         snode.mgmt_ip, snode.rpc_port,
         snode.rpc_username, snode.rpc_password, timeout=5, retry=1)
@@ -443,7 +446,7 @@ def check_lvol(lvol_id):
         passed = True
         for nodes_id in lvol.nodes:
             node = db_controller.get_storage_node_by_id(nodes_id)
-            if node.status == StorageNode.STATUS_ONLINE:
+            if node and node.status == StorageNode.STATUS_ONLINE:
                 ret = check_lvol_on_node(lvol_id, nodes_id)
                 if not ret:
                     passed = False

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/controllers/lvol_controller.py

@@ -175,6 +175,8 @@ def _get_next_3_nodes(cluster_id, lvol_size=0):
             continue
 
         if node.status == node.STATUS_ONLINE:
+            if node.hostname == "ip-10-245-16-169":
+                continue
             # Validate Eligible nodes for adding lvol
             # snode_api = SNodeClient(node.api_endpoint)
             # result, _ = snode_api.info()
@@ -319,6 +321,18 @@ def add_lvol_ha(name, size, host_id_or_name, ha_type, pool_id_or_name, use_comp,
     if cl.status not in [cl.STATUS_ACTIVE, cl.STATUS_DEGRADED]:
         return False, f"Cluster is not active, status: {cl.status}"
 
+    if uid:
+        for lvol in db_controller.get_lvols():
+            if lvol.get_id() == uid:
+                if pvc_name:
+                    lvol.pvc_name = pvc_name
+                if name:
+                    lvol.lvol_name = name
+                if namespace:
+                    lvol.namespace = namespace
+                lvol.write_to_db()
+                return uid, None
+
     if ha_type == "default":
         ha_type = cl.ha_type
 

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/distr_controller.py

@@ -140,6 +140,12 @@ def get_distr_cluster_map(snodes, target_node, distr_name=""):
         "map_prob": [d for k, d in map_prob.items()]
     }
     if cluster.enable_node_affinity:
+        if target_node.is_secondary_node and distr_name:
+            for index, snode in enumerate(snodes):
+                for bdev in snode.lvstore_stack:
+                    if bdev['type'] == "bdev_distr" and bdev['name'] == distr_name:
+                        local_node_index = index
+                        break
         cl_map['ppln1'] = local_node_index
     return cl_map
 
@@ -208,14 +214,25 @@ def send_cluster_map_to_node(node):
     db_controller = DBController()
     snodes = db_controller.get_storage_nodes_by_cluster_id(node.cluster_id)
     rpc_client = RPCClient(node.mgmt_ip, node.rpc_port, node.rpc_username, node.rpc_password, timeout=10)
-    cluster_map_data = get_distr_cluster_map(snodes, node)
-    cluster_map_data['UUID_node_target'] = node.get_id()
-    ret = rpc_client.distr_send_cluster_map(cluster_map_data)
-    if not ret:
-        logger.error("Failed to send cluster map")
-        logger.info(cluster_map_data)
-        return False
-    return True
+
+    if node.is_secondary_node:
+        for snode in db_controller.get_primary_storage_nodes_by_secondary_node_id(node.get_id()):
+            for bdev in snode.lvstore_stack:
+                if bdev['type'] == "bdev_distr":
+                    cluster_map_data = get_distr_cluster_map(snodes, node, bdev["name"])
+                    ret = rpc_client.distr_send_cluster_map(cluster_map_data)
+                    if not ret:
+                        logger.error("Failed to send cluster map")
+                        return False
+        return True
+    else:
+        cluster_map_data = get_distr_cluster_map(snodes, node)
+        ret = rpc_client.distr_send_cluster_map(cluster_map_data)
+        if not ret:
+            logger.error("Failed to send cluster map")
+            logger.info(cluster_map_data)
+            return False
+        return True
 
 
 def send_cluster_map_to_distr(node, distr_name):

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-dev
-SIMPLY_BLOCK_VERSION=10.3.4
+SIMPLY_BLOCK_VERSION=10.4.0
 
 SIMPLY_BLOCK_DOCKER_IMAGE=simplyblock/simplyblock:main
 DOCKER_USER=hamdysimplyblock

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/services/storage_node_monitor.py

@@ -62,7 +62,7 @@ def get_next_cluster_status(cluster_id):
             else:
                 node_offline_devices += 1
 
-        if node_offline_devices > 0 or node_online_devices == 0:
+        if node_offline_devices > 0 or (node_online_devices == 0 and node.status != StorageNode.STATUS_REMOVED):
             affected_nodes += 1
 
         online_devices += node_online_devices

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/services/tasks_runner_failed_migration.py

@@ -101,7 +101,12 @@ def task_runner(task):
 
         mig_info = task.function_params["migration"]
         res = rpc_client.distr_migration_status(**mig_info)
-        return utils.handle_task_result(task, res)
+        out = utils.handle_task_result(task, res)
+        dev_failed_task = tasks_controller.get_failed_device_mig_task(task.cluster_id, task.device_id)
+        if not dev_failed_task:
+            device_controller.device_set_failed_and_migrated(task.device_id)
+
+        return out
     else:
         task.retry += 1
         task.write_to_db(db_controller.kv_store)

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/storage_node_ops.py

@@ -2845,7 +2845,6 @@ def create_lvstore(snode, ndcs, npcs, distr_bs, distr_chunk_bs, page_size_in_blo
             distrib_vuid = utils.get_random_vuid()
 
         distrib_name = f"distrib_{distrib_vuid}"
-        lvs_name = f"LVS_{distrib_vuid}"
         lvstore_stack.extend(
             [
                 {
@@ -2904,18 +2903,16 @@ def create_lvstore(snode, ndcs, npcs, distr_bs, distr_chunk_bs, page_size_in_blo
         }
     )
 
-    ret, err = _create_bdev_stack(snode, lvstore_stack)
-    if err:
-        logger.error(f"Failed to create lvstore on node {snode.get_id()}")
-        logger.error(err)
-        return False
-
     snode.lvstore = lvs_name
     snode.lvstore_stack = lvstore_stack
     snode.raid = raid_device
     snode.write_to_db()
 
-    # time.sleep(1)
+    ret, err = _create_bdev_stack(snode, lvstore_stack)
+    if err:
+        logger.error(f"Failed to create lvstore on node {snode.get_id()}")
+        logger.error(err)
+        return False
 
     if snode.secondary_node_id:
         # creating lvstore on secondary

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_core/utils.py

@@ -664,6 +664,9 @@ def strfdelta(tdelta):
 
 def handle_task_result(task: JobSchedule, res: dict, allowed_error_codes = None):
     if res:
+        if not allowed_error_codes:
+            allowed_error_codes = [0]
+
         res_data = res[0]
         migration_status = res_data.get("status")
         error_code = res_data.get("error", -1)

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_web/blueprints/caching_node_ops.py

@@ -176,7 +176,7 @@ def spdk_process_start():
             node.remove(force=True)
             time.sleep(2)
 
-    spdk_image = constants.SIMPLY_BLOCK_SPDK_ULTRA_IMAGE
+    spdk_image = constants.SIMPLY_BLOCK_SPDK_CORE_IMAGE
 
     if 'spdk_image' in data and data['spdk_image']:
         spdk_image = data['spdk_image']
@@ -184,7 +184,7 @@ def spdk_process_start():
 
     container = node_docker.containers.run(
         spdk_image,
-        f"/root/scripts/run_spdk_tgt.sh {spdk_cpu_mask} {spdk_mem}",
+        f"/root/spdk/scripts/run_spdk_tgt.sh {spdk_cpu_mask} {spdk_mem}",
         name="spdk",
         detach=True,
         privileged=True,

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_web/blueprints/caching_node_ops_k8s.py

@@ -112,7 +112,7 @@ def spdk_process_start():
 
     spdk_mem_gega = int(spdk_mem / 1024)
 
-    spdk_image = constants.SIMPLY_BLOCK_SPDK_ULTRA_IMAGE
+    spdk_image = constants.SIMPLY_BLOCK_SPDK_CORE_IMAGE
 
     if 'spdk_image' in data and data['spdk_image']:
         spdk_image = data['spdk_image']

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_web/blueprints/node_api_caching_docker.py

@@ -64,14 +64,14 @@ def spdk_process_start():
             node.remove(force=True)
             time.sleep(2)
 
-    spdk_image = constants.SIMPLY_BLOCK_SPDK_ULTRA_IMAGE
+    spdk_image = constants.SIMPLY_BLOCK_SPDK_CORE_IMAGE
     if 'spdk_image' in data and data['spdk_image']:
         spdk_image = data['spdk_image']
         node_docker.images.pull(spdk_image)
 
     container = node_docker.containers.run(
         spdk_image,
-        f"/root/scripts/run_spdk_tgt.sh {spdk_cpu_mask} {spdk_mem}",
+        f"/root/spdk/scripts/run_spdk_tgt.sh {spdk_cpu_mask} {spdk_mem}",
         name="spdk",
         detach=True,
         privileged=True,

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_web/blueprints/node_api_caching_ks.py

@@ -63,7 +63,7 @@ def spdk_process_start():
     else:
         spdk_mem = 64096
 
-    spdk_image = constants.SIMPLY_BLOCK_SPDK_ULTRA_IMAGE
+    spdk_image = constants.SIMPLY_BLOCK_SPDK_CORE_IMAGE
     if 'spdk_image' in data and data['spdk_image']:
         spdk_image = data['spdk_image']
         # node_docker.images.pull(spdk_image)

{sbcli_dev-10.3.4 → sbcli_dev-10.4.0}/simplyblock_web/templates/caching_deploy_spdk.yaml.j2

@@ -55,7 +55,7 @@ spec:
       - name: spdk-container
         image: {{ SPDK_IMAGE }}
         imagePullPolicy: "Always"
-        command: ["/root/scripts/run_spdk_tgt.sh", "{{ SPDK_CPU_MASK }}", "{{ SPDK_MEM }}"]
+        command: ["/root/spdk/scripts/run_spdk_tgt.sh", "{{ SPDK_CPU_MASK }}", "{{ SPDK_MEM }}"]
         lifecycle:
           postStart:
             exec: