sbcli-dev 16.0.9__tar.gz → 16.2.0__tar.gz

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sbcli-dev
-Version: 16.0.9
+Version: 16.2.0
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/sbcli_dev.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: sbcli-dev
-Version: 16.0.9
+Version: 16.2.0
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/simplyblock_core/constants.py

@@ -128,6 +128,6 @@ QPAIR_COUNT=32
 NVME_TIMEOUT_US=20000000
 
 NVMF_MAX_SUBSYSTEMS=50000
-HA_JM_COUNT=2
+HA_JM_COUNT=3
 
 TEMP_CORES_FILE = "/etc/simplyblock/tmp_cores_config"

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/simplyblock_core/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-dev
-SIMPLY_BLOCK_VERSION=16.0.9
+SIMPLY_BLOCK_VERSION=16.2.0
 
 SIMPLY_BLOCK_DOCKER_IMAGE=public.ecr.aws/simply-block/simplyblock:main
 SIMPLY_BLOCK_SPDK_ULTRA_IMAGE=public.ecr.aws/simply-block/ultra:main-latest

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/simplyblock_core/rpc_client.py

@@ -285,7 +285,7 @@ class RPCClient:
             "lvs_name": name,
             "cluster_sz": cluster_sz,
             "clear_method": clear_method,
-            "num_md_pages_per_cluster_ratio": num_md_pages_per_cluster_ratio,
+            # "num_md_pages_per_cluster_ratio": num_md_pages_per_cluster_ratio,
         }
         return self._request("bdev_lvol_create_lvstore", params)
 

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/simplyblock_core/scripts/clean_local_storage_deploy.sh

@@ -6,9 +6,9 @@ sudo docker rm SNodeAPI --force
 sudo docker rm CachingNodeAPI --force
 sudo docker stack rm app
 sudo docker swarm leave --force
+sleep 2
+sudo service docker restart
 sudo docker container prune -f
-#sudo docker image prune -a -f
 sudo docker volume prune -a -f
-sudo service docker restart
-echo "Done"
 sudo rm -rf /etc/foundationdb/data/
+echo "Done"

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/simplyblock_core/services/storage_node_monitor.py

@@ -244,7 +244,7 @@ while True:
             if snode.status == StorageNode.STATUS_SCHEDULABLE and not ping_check and not node_api_check:
                 continue
 
-            spdk_process = False
+            spdk_process = True
             if node_api_check:
                 # 3- check spdk_process
                 spdk_process = health_controller._check_spdk_process_up(snode.mgmt_ip)
@@ -281,7 +281,7 @@ while True:
                             node_port_check = False
                             down_ports.append(data_nic.ip4_address)
 
-            is_node_online = ping_check and node_api_check and spdk_process and node_rpc_check and node_port_check
+            is_node_online = ping_check and spdk_process and node_rpc_check and node_port_check
             if is_node_online:
                 set_node_online(snode)
 
@@ -310,10 +310,13 @@ while True:
                             device_controller.device_set_unavailable(dev.get_id())
 
                 elif ping_check and node_api_check and (not spdk_process or not node_rpc_check):
+
+                    if cluster.status !=  Cluster.STATUS_IN_ACTIVATION:
+                        set_node_offline(snode)
+
                     # add node to auto restart
-                    if cluster.status in [Cluster.STATUS_ACTIVE, Cluster.STATUS_DEGRADED,
+                    if cluster.status in [Cluster.STATUS_ACTIVE, Cluster.STATUS_DEGRADED, Cluster.STATUS_UNREADY,
                                           Cluster.STATUS_SUSPENDED, Cluster.STATUS_READONLY]:
-                        set_node_offline(snode)
                         tasks_controller.add_node_to_auto_restart(snode)
                 elif not node_port_check:
                     if cluster.status in [Cluster.STATUS_ACTIVE, Cluster.STATUS_DEGRADED, Cluster.STATUS_READONLY]:

{sbcli_dev-16.0.9 → sbcli_dev-16.2.0}/simplyblock_core/storage_node_ops.py

@@ -1922,8 +1922,8 @@ def restart_storage_node(
     snode.lvstore_status = ""
     snode.write_to_db(db_controller.kv_store)
 
-    logger.info("Setting node status to Online")
-    set_node_status(node_id, StorageNode.STATUS_ONLINE, reconnect_on_online=False)
+    # logger.info("Setting node status to Online")
+    # set_node_status(node_id, StorageNode.STATUS_ONLINE, reconnect_on_online=False)
 
     # time.sleep(1)
     snode = db_controller.get_storage_node_by_id(snode.get_id())
@@ -1960,18 +1960,23 @@ def restart_storage_node(
             logger.error("Failed to recreate lvstore")
             snode.lvstore_status = "failed"
             snode.write_to_db()
+            return False
         else:
             snode.lvstore_status = "ready"
             snode.write_to_db()
 
-    if cluster.status in [Cluster.STATUS_ACTIVE, Cluster.STATUS_DEGRADED, Cluster.STATUS_READONLY]:
-        for dev in snode.nvme_devices:
-            if dev.status == NVMeDevice.STATUS_ONLINE:
-                logger.info(f"Starting migration task for device {dev.get_id()}")
-                tasks_controller.add_device_mig_task(dev.get_id())
+            logger.info("Setting node status to Online")
+            set_node_status(node_id, StorageNode.STATUS_ONLINE, reconnect_on_online=False)
+
+            if cluster.status in [Cluster.STATUS_ACTIVE, Cluster.STATUS_DEGRADED, Cluster.STATUS_READONLY]:
+                for dev in snode.nvme_devices:
+                    if dev.status == NVMeDevice.STATUS_ONLINE:
+                        logger.info(f"Starting migration task for device {dev.get_id()}")
+                        tasks_controller.add_device_mig_task(dev.get_id())
+            return True
 
     logger.info("Done")
-    return "Success"
+    return True
 
 
 def list_storage_nodes(is_json, cluster_id=None):
@@ -2881,12 +2886,12 @@ def recreate_lvstore_on_sec(snode):
         for lvol in lvol_list:
             logger.info("creating subsystem %s", lvol.nqn)
             rpc_client.subsystem_create(lvol.nqn, 'sbcli-cn', lvol.uuid, 1000)
-            for iface in snode.data_nics:
-                if iface.ip4_address:
-                    tr_type = iface.get_transport_type()
-                    logger.info("adding listener for %s on IP %s" % (lvol.nqn, iface.ip4_address))
-                    ret = rpc_client.listeners_create(
-                        lvol.nqn, tr_type, iface.ip4_address, lvol.subsys_port, "inaccessible")
+            # for iface in snode.data_nics:
+                # if iface.ip4_address:
+                #     tr_type = iface.get_transport_type()
+                #     logger.info("adding listener for %s on IP %s" % (lvol.nqn, iface.ip4_address))
+                #     ret = rpc_client.listeners_create(
+                #         lvol.nqn, tr_type, iface.ip4_address, lvol.subsys_port, "inaccessible")
 
         if node.status == StorageNode.STATUS_ONLINE:
             # for lvol in lvol_list:
@@ -2966,12 +2971,12 @@ def recreate_lvstore(snode):
     for lvol in lvol_list:
         logger.info("creating subsystem %s", lvol.nqn)
         rpc_client.subsystem_create(lvol.nqn, 'sbcli-cn', lvol.uuid, 1)
-        for iface in snode.data_nics:
-            if iface.ip4_address:
-                tr_type = iface.get_transport_type()
-                logger.info("adding listener for %s on IP %s" % (lvol.nqn, iface.ip4_address))
-                ret = rpc_client.listeners_create(
-                    lvol.nqn, tr_type, iface.ip4_address, lvol.subsys_port, "inaccessible")
+        # for iface in snode.data_nics:
+        #     if iface.ip4_address:
+        #         tr_type = iface.get_transport_type()
+        #         logger.info("adding listener for %s on IP %s" % (lvol.nqn, iface.ip4_address))
+        #         ret = rpc_client.listeners_create(
+        #             lvol.nqn, tr_type, iface.ip4_address, lvol.subsys_port, "inaccessible")
 
     if sec_node:
 
@@ -3050,8 +3055,8 @@ def add_lvol_thread(lvol, snode, lvol_ana_state="optimized"):
     for iface in snode.data_nics:
         if iface.ip4_address:
             logger.info("adding listener for %s on IP %s" % (lvol.nqn, iface.ip4_address))
-            ret = rpc_client.nvmf_subsystem_listener_set_ana_state(
-                lvol.nqn, iface.ip4_address, lvol.subsys_port, ana=lvol_ana_state)
+            ret = rpc_client.listeners_create(
+                lvol.nqn, iface.get_transport_type(), iface.ip4_address, lvol.subsys_port, ana_state=lvol_ana_state)
 
     lvol_obj = db_controller.get_lvol_by_id(lvol.get_id())
     lvol_obj.status = LVol.STATUS_ONLINE