sbcli-down 0.0.1__tar.gz → 0.0.5__tar.gz

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: sbcli-down
-Version: 0.0.1
+Version: 0.0.5
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/sbcli_down.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: sbcli-down
-Version: 0.0.1
+Version: 0.0.5
 Summary: CLI for managing SimplyBlock cluster
 Home-page: https://www.simplyblock.io/
 Author: Hamdy

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/setup.py

@@ -2,7 +2,7 @@ import os
 
 from setuptools import setup, find_packages
 
-from setuptools.command.install import install as _install
+from setuptools.command.install import install
 
 
 def _post_install():
@@ -19,12 +19,19 @@ def _post_install():
             _, out = getstatusoutput(f'source {path}')
 
 
-class install(_install):
+class CustomInstallCommand(install):
     def run(self):
-        _install.run(self)
         self.execute(_post_install, (), msg="Running post install task")
-
-
+        print("**"*50)
+        _post_install()
+        install.run(self)
+
+#
+# class CustomInstallCommand(install):
+#     """Customized setuptools install command - prints a friendly greeting."""
+#     def run(self):
+#         print "Hello, developer, how are you? :)"
+#         install.run(self)
 def get_env_var(name, default=None):
     if not name:
         return False
@@ -95,5 +102,8 @@ setup(
         '': ["/etc/simplyblock/requirements.txt"],
         '/etc/simplyblock': ["requirements.txt"]
     },
-    cmdclass={'install': install},
+    cmdclass={
+        'install': CustomInstallCommand,
+        # 'build': CustomInstallCommand
+    },
 )

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/simplyblock_core/controllers/health_controller.py

@@ -123,15 +123,6 @@ def _check_port_on_node(snode, port_id):
         logger.error(e)
     return True
 
-def port_check(host_ip, port):
-   s = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
-   s.settimeout(3)
-   try:
-      s.connect((host_ip, port))
-      return True
-   except:
-      return False
-
 
 def _check_node_ping(ip):
     res = utils.ping_host(ip)

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/simplyblock_core/env_var

@@ -1,5 +1,5 @@
 SIMPLY_BLOCK_COMMAND_NAME=sbcli-down
-SIMPLY_BLOCK_VERSION=0.0.1
+SIMPLY_BLOCK_VERSION=0.0.5
 
 SIMPLY_BLOCK_DOCKER_IMAGE=public.ecr.aws/simply-block/simplyblock:down
 DOCKER_USER=hamdysimplyblock

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/simplyblock_core/scripts/install_deps.sh

@@ -3,7 +3,7 @@
 sudo yum install -y yum-utils xorg-x11-xauth nvme-cli fio
 sudo yum-config-manager --add-repo https://download.docker.com/linux/centos/docker-ce.repo
 sudo yum install hostname pkg-config git wget python3-pip yum-utils docker-ce docker-ce-cli \
-  containerd.io docker-buildx-plugin docker-compose-plugin iptables -y
+  containerd.io docker-buildx-plugin docker-compose-plugin iptables pciutils -y
 
 sudo systemctl enable docker
 sudo systemctl start docker

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/simplyblock_core/services/health_check_service.py

@@ -58,16 +58,10 @@ while True:
         for snode in snodes:
             logger.info("Node: %s, status %s", snode.get_id(), snode.status)
 
-            if snode.status in [StorageNode.STATUS_RESTARTING, StorageNode.STATUS_IN_CREATION, StorageNode.STATUS_IN_SHUTDOWN]:
-                logger.info(f"Node status is: {snode.status}, skipping")
-                continue
-
-            if snode.status not in [StorageNode.STATUS_ONLINE, StorageNode.STATUS_UNREACHABLE, StorageNode.STATUS_SUSPENDED]:
+            if snode.status not in [StorageNode.STATUS_ONLINE, StorageNode.STATUS_UNREACHABLE,
+                                    StorageNode.STATUS_SUSPENDED, StorageNode.STATUS_DOWN]:
                 logger.info(f"Node status is: {snode.status}, skipping")
                 set_node_health_check(snode, False)
-                for dev in snode.nvme_devices:
-                    set_device_health_check(cluster_id, dev, False)
-                continue
 
             # 1- check node ping
             ping_check = health_controller._check_node_ping(snode.mgmt_ip)

{sbcli_down-0.0.1 → sbcli_down-0.0.5}/simplyblock_core/services/storage_node_monitor.py

@@ -131,15 +131,18 @@ def update_cluster_status(cluster_id):
         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}")
                 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
                 break
 
             if node.online_since:
                 diff = datetime.now(timezone.utc) - datetime.fromisoformat(node.online_since)
-                if diff.total_seconds() < 60:
+                if diff.total_seconds() < 30:
+                    logger.error(f"can not activate cluster: node is online less than 30 seconds: {node.get_id()}")
                     can_activate = False
                     break
 
@@ -183,9 +186,6 @@ def set_node_offline(node):
 def set_node_down(node):
     if node.status != StorageNode.STATUS_DOWN:
         storage_node_ops.set_node_status(node.get_id(), StorageNode.STATUS_DOWN)
-        for dev in node.nvme_devices:
-            if dev.status in [NVMeDevice.STATUS_ONLINE, NVMeDevice.STATUS_READONLY]:
-                device_controller.device_set_unavailable(dev.get_id())
 
 
 logger.info("Starting node monitor")
@@ -244,7 +244,7 @@ while True:
                     ports = [snode.lvol_subsys_port, 4420]
 
                 for port in ports:
-                    ret = health_controller.port_check(snode.mgmt_ip, port)
+                    ret = health_controller._check_port_on_node(snode, port)
                     logger.info(f"Check: node port {snode.mgmt_ip}, {port} ... {ret}")
                     node_port_check &= ret
 
@@ -276,7 +276,7 @@ while True:
                     if cluster.status in [Cluster.STATUS_ACTIVE, Cluster.STATUS_DEGRADED, Cluster.STATUS_SUSPENDED]:
                         set_node_offline(snode)
                         tasks_controller.add_node_to_auto_restart(snode)
-                elif node_port_check:
+                elif not node_port_check:
                     logger.info(f"Port check failed")
                     set_node_down(snode)
                 else: