Hotfix to main

simplyblock_cli/cli-reference.yaml

@@ -102,6 +102,14 @@ commands:
             required: false
             type: str
             default: ""
+          - name: "--nvme-names"
+            help: "Comma separated list of nvme namespace names like nvme0n1,nvme1n1..."
+            description: >
+              Comma separated list of nvme namespace names like nvme0n1,nvme1n1...
+            dest: nvme_names
+            required: false
+            type: str
+            default: ""
           - name: "--force"
             help: "Force format detected or passed nvme pci address to 4K and clean partitions"
             dest: force
@@ -150,6 +158,11 @@ commands:
             dest: partitions
             type: int
             default: 1
+          - name: "--format-4k"
+            help: "Force format nvme devices with 4K"
+            dest: format_4k
+            type: bool
+            action: store_true
           - name: "--jm-percent"
             help: "Number in percent to use for JM from each device"
             dest: jm_percent

simplyblock_cli/cli.py

@@ -96,6 +96,7 @@ def init_storage_node__configure(self, subparser):
         argument = subcommand.add_argument('--pci-blocked', help='Comma separated list of PCI addresses of Nvme devices to not use for storage devices', type=str, default='', dest='pci_blocked', required=False)
         argument = subcommand.add_argument('--device-model', help='NVMe SSD model string, example: --model PM1628, --device-model and --size-range must be set together', type=str, default='', dest='device_model', required=False)
         argument = subcommand.add_argument('--size-range', help='NVMe SSD device size range separated by -, can be X(m,g,t) or bytes as integer, example: --size-range 50G-1T or --size-range 1232345-67823987, --device-model and --size-range must be set together', type=str, default='', dest='size_range', required=False)
+        argument = subcommand.add_argument('--nvme-names', help='Comma separated list of nvme namespace names like nvme0n1,nvme1n1...', type=str, default='', dest='nvme_names', required=False)
         argument = subcommand.add_argument('--force', help='Force format detected or passed nvme pci address to 4K and clean partitions', dest='force', action='store_true')
 
     def init_storage_node__configure_upgrade(self, subparser):
@@ -114,6 +115,7 @@ def init_storage_node__add_node(self, subparser):
         subcommand.add_argument('node_addr', help='Address of storage node api to add, like <node-ip>:5000', type=str)
         subcommand.add_argument('ifname', help='Management interface name', type=str)
         argument = subcommand.add_argument('--journal-partition', help='1: auto-create small partitions for journal on nvme devices. 0: use a separate (the smallest) nvme device of the node for journal. The journal needs a maximum of 3 percent of total available raw disk space.', type=int, default=1, dest='partitions')
+        argument = subcommand.add_argument('--format-4k', help='Force format nvme devices with 4K', dest='format_4k', action='store_true')
         if self.developer_mode:
             argument = subcommand.add_argument('--jm-percent', help='Number in percent to use for JM from each device', type=int, default=3, dest='jm_percent')
         argument = subcommand.add_argument('--data-nics', help='Storage network interface names. currently one interface is supported.', type=str, dest='data_nics', nargs='+')

simplyblock_cli/clibase.py

@@ -103,12 +103,15 @@ def storage_node__configure(self, sub_command, args):
         max_prov = utils.parse_size(max_size, assume_unit='G')
         pci_allowed = []
         pci_blocked = []
+        nvme_names = []
         if args.pci_allowed:
             pci_allowed = [str(x) for x in args.pci_allowed.split(',')]
         if args.pci_blocked:
             pci_blocked = [str(x) for x in args.pci_blocked.split(',')]
         if (args.device_model and not args.size_range) or (not args.device_model and args.size_range):
             self.parser.error("device_model and size_range must be set together")
+        if args.nvme_names:
+            nvme_names = [str(x) for x in args.nvme_names.split(',')]
         use_pci_allowed = bool(args.pci_allowed)
         use_pci_blocked = bool(args.pci_blocked)
         use_model_range = bool(args.device_model and args.size_range)
@@ -122,7 +125,7 @@ def storage_node__configure(self, sub_command, args):
         return storage_ops.generate_automated_deployment_config(
             args.max_lvol, max_prov, sockets_to_use,args.nodes_per_socket,
             pci_allowed, pci_blocked, force=args.force, device_model=args.device_model,
-            size_range=args.size_range, cores_percentage=cores_percentage)
+            size_range=args.size_range, cores_percentage=cores_percentage, nvme_names=nvme_names)
 
     def storage_node__deploy_cleaner(self, sub_command, args):
         storage_ops.deploy_cleaner()
@@ -150,6 +153,7 @@ def storage_node__add_node(self, sub_command, args):
         enable_ha_jm = args.enable_ha_jm
         namespace = args.namespace
         ha_jm_count = args.ha_jm_count
+        format_4k = args.format_4k
         try:
             out = storage_ops.add_node(
                 cluster_id=cluster_id,
@@ -169,6 +173,7 @@ def storage_node__add_node(self, sub_command, args):
                 id_device_by_nqn=args.id_device_by_nqn,
                 partition_size=args.partition_size,
                 ha_jm_count=ha_jm_count,
+                format_4k=format_4k
             )
         except Exception as e:
             print(e)

simplyblock_core/constants.py

@@ -233,7 +233,9 @@ def get_config_var(name, default=None):
 
 # ports ranges
 RPC_PORT_RANGE_START = 8080
-LVOL_NVMF_PORT_START = 9100
 NODE_NVMF_PORT_START=9060
 NODE_HUBLVOL_PORT_START=9030
 FW_PORT_START = 50001
+# todo(hamdy): make it configurable: sfam-2586
+LVOL_NVMF_PORT_ENV = os.getenv("LVOL_NVMF_PORT_START", "")
+LVOL_NVMF_PORT_START = int(LVOL_NVMF_PORT_ENV) if LVOL_NVMF_PORT_ENV else 9100

simplyblock_core/controllers/lvol_controller.py

@@ -714,7 +714,7 @@ def add_lvol_on_node(lvol, snode, is_primary=True):
                         return False, f"Failed to create listener for {lvol.get_id()}"
 
     logger.info("Add BDev to subsystem")
-    ret = rpc_client.nvmf_subsystem_add_ns(lvol.nqn, lvol.top_bdev, lvol.uuid, lvol.guid,f"{lvol.vuid:016X}")
+    ret = rpc_client.nvmf_subsystem_add_ns(lvol.nqn, lvol.top_bdev, lvol.uuid, lvol.guid, lvol.ns_id)
     if not ret:
         return False, "Failed to add bdev to subsystem"
     lvol.ns_id = int(ret)
@@ -758,7 +758,7 @@ def recreate_lvol_on_node(lvol, snode, ha_inode_self=0, ana_state=None):
 
     # if namespace_found is False:
     logger.info("Add BDev to subsystem")
-    ret = rpc_client.nvmf_subsystem_add_ns(lvol.nqn, lvol.top_bdev, lvol.uuid, lvol.guid, f"{lvol.vuid:016X}")
+    ret = rpc_client.nvmf_subsystem_add_ns(lvol.nqn, lvol.top_bdev, lvol.uuid, lvol.guid, lvol.ns_id)
     # if not ret:
     #     return False, "Failed to add bdev to subsystem"
 

simplyblock_core/controllers/tasks_controller.py

@@ -322,7 +322,7 @@ def add_new_device_mig_task(device_id):
 
 def add_node_add_task(cluster_id, function_params):
     return _add_task(JobSchedule.FN_NODE_ADD, cluster_id, "", "",
-                     function_params=function_params, max_retry=11)
+                     function_params=function_params, max_retry=16)
 
 
 def get_active_node_tasks(cluster_id, node_id):

simplyblock_core/scripts/charts/Chart.yaml

@@ -25,6 +25,7 @@ dependencies:
   - name: prometheus
     version: "25.18.0"
     repository: "https://prometheus-community.github.io/helm-charts"
+    condition: monitoring.enabled
   - name: ingress-nginx
     version: 4.10.1
     repository: "https://kubernetes.github.io/ingress-nginx"

simplyblock_core/scripts/charts/templates/app_k8s.yaml

@@ -5,7 +5,7 @@ metadata:
   name: simplyblock-admin-control
   namespace: {{ .Release.Namespace }}
 spec:
-  replicas: 1
+  replicas: 2
   selector:
     matchLabels:
       app: simplyblock-admin-control
@@ -21,6 +21,13 @@ spec:
       serviceAccountName: simplyblock-sa
       hostNetwork: true
       dnsPolicy: ClusterFirstWithHostNet 
+      affinity:
+        podAntiAffinity:
+          requiredDuringSchedulingIgnoredDuringExecution:
+            - labelSelector:
+                matchLabels:
+                  app: simplyblock-admin-control
+              topologyKey: kubernetes.io/hostname
       containers:
       - name: simplyblock-control
         image: "{{ .Values.image.simplyblock.repository }}:{{ .Values.image.simplyblock.tag }}"

simplyblock_core/scripts/charts/templates/csi-hostpath-controller.yaml

@@ -0,0 +1,217 @@
+apiVersion: v1
+kind: ServiceAccount
+metadata:
+  name: csi-hostpathplugin-sa
+  namespace: {{ .Release.Namespace }}
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRole
+metadata:
+  name: csi-hostpathplugin
+rules:
+  - apiGroups: [""]
+    resources: ["persistentvolumes"]
+    verbs: ["get", "list", "watch", "create", "delete", "update", "patch"]
+  - apiGroups: [""]
+    resources: ["persistentvolumeclaims"]
+    verbs: ["get", "list", "watch", "update"]
+  - apiGroups: [""]
+    resources: ["persistentvolumeclaims/status"]
+    verbs: ["get", "update", "patch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["volumeattachments"]
+    verbs: ["get", "list", "watch", "update"]
+  - apiGroups: [""]
+    resources: ["nodes"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["csinodes"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["storageclasses"]
+    verbs: ["get", "list", "watch"]
+  - apiGroups: ["storage.k8s.io"]
+    resources: ["csistoragecapacities"]
+    verbs: ["get", "list", "watch", "create", "update", "delete"]
+  - apiGroups: [""]
+    resources: ["events"]
+    verbs: ["create", "patch", "update", "get", "list", "watch"]
+  - apiGroups: [""]
+    resources: ["pods"]
+    verbs: ["get", "list", "watch"]
+---
+apiVersion: rbac.authorization.k8s.io/v1
+kind: ClusterRoleBinding
+metadata:
+  name: csi-hostpathplugin
+roleRef:
+  apiGroup: rbac.authorization.k8s.io
+  kind: ClusterRole
+  name: csi-hostpathplugin
+subjects:
+  - kind: ServiceAccount
+    name: csi-hostpathplugin-sa
+    namespace: {{ .Release.Namespace }}
+---
+kind: StatefulSet
+apiVersion: apps/v1
+metadata:
+  name: csi-hostpathplugin
+  labels:
+    app.kubernetes.io/instance: hostpath.csi.k8s.io
+    app.kubernetes.io/part-of: csi-driver-host-path
+    app.kubernetes.io/name: csi-hostpathplugin
+    app.kubernetes.io/component: plugin
+spec:
+  serviceName: "csi-hostpathplugin"
+  # One replica only:
+  # Host path driver only works when everything runs
+  # on a single node.
+  replicas: 1
+  selector:
+    matchLabels:
+      app.kubernetes.io/instance: hostpath.csi.k8s.io
+      app.kubernetes.io/part-of: csi-driver-host-path
+      app.kubernetes.io/name: csi-hostpathplugin
+      app.kubernetes.io/component: plugin
+  template:
+    metadata:
+      labels:
+        app.kubernetes.io/instance: hostpath.csi.k8s.io
+        app.kubernetes.io/part-of: csi-driver-host-path
+        app.kubernetes.io/name: csi-hostpathplugin
+        app.kubernetes.io/component: plugin
+    spec:
+      serviceAccountName: csi-hostpathplugin-sa
+      containers:
+        - name: hostpath
+          image: registry.k8s.io/sig-storage/hostpathplugin:v1.17.0
+          args:
+            - "--drivername=hostpath.csi.k8s.io"
+            - "--v=5"
+            - "--endpoint=$(CSI_ENDPOINT)"
+            - "--nodeid=$(KUBE_NODE_NAME)"
+            # end hostpath args
+          env:
+            - name: CSI_ENDPOINT
+              value: unix:///csi/csi.sock
+            - name: KUBE_NODE_NAME
+              valueFrom:
+                fieldRef:
+                  apiVersion: v1
+                  fieldPath: spec.nodeName
+          securityContext:
+            privileged: true
+          ports:
+          - containerPort: 9898
+            name: healthz
+            protocol: TCP
+          livenessProbe:
+            failureThreshold: 5
+            httpGet:
+              path: /healthz
+              port: healthz
+            initialDelaySeconds: 10
+            timeoutSeconds: 3
+            periodSeconds: 2
+          volumeMounts:
+            - mountPath: /csi
+              name: socket-dir
+            - mountPath: /var/lib/kubelet/pods
+              mountPropagation: Bidirectional
+              name: mountpoint-dir
+            - mountPath: /var/lib/kubelet/plugins
+              mountPropagation: Bidirectional
+              name: plugins-dir
+            - mountPath: /csi-data-dir
+              name: csi-data-dir
+            - mountPath: /dev
+              name: dev-dir
+
+        - name: liveness-probe
+          volumeMounts:
+          - mountPath: /csi
+            name: socket-dir
+          image: registry.k8s.io/sig-storage/livenessprobe:v2.17.0
+          args:
+          - --csi-address=/csi/csi.sock
+          - --health-port=9898
+
+        - name: csi-provisioner
+          image: registry.k8s.io/sig-storage/csi-provisioner:v6.0.0
+          args:
+            - -v=5
+            - --csi-address=/csi/csi.sock
+            - --feature-gates=Topology=true
+            - --enable-capacity
+            - --capacity-ownerref-level=0 # pod is owner
+            - --node-deployment=true
+            - --strict-topology=true
+            - --immediate-topology=false
+            - --worker-threads=5
+          env:
+          - name: NODE_NAME
+            valueFrom:
+              fieldRef:
+                apiVersion: v1
+                fieldPath: spec.nodeName
+          - name: NAMESPACE
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.namespace
+          - name: POD_NAME
+            valueFrom:
+              fieldRef:
+                fieldPath: metadata.name
+            # end csi-provisioner args
+          securityContext:
+            # This is necessary only for systems with SELinux, where
+            # non-privileged sidecar containers cannot access unix domain socket
+            # created by privileged CSI driver container.
+            privileged: true
+          volumeMounts:
+            - mountPath: /csi
+              name: socket-dir
+
+        - name: csi-resizer
+          image: registry.k8s.io/sig-storage/csi-resizer:v2.0.0
+          args:
+            - -v=5
+            - -csi-address=/csi/csi.sock
+          securityContext:
+            # This is necessary only for systems with SELinux, where
+            # non-privileged sidecar containers cannot access unix domain socket
+            # created by privileged CSI driver container.
+            privileged: true
+          volumeMounts:
+            - mountPath: /csi
+              name: socket-dir
+
+      volumes:
+        - hostPath:
+            path: /var/lib/kubelet/plugins/csi-hostpath
+            type: DirectoryOrCreate
+          name: socket-dir
+        - hostPath:
+            path: /var/lib/kubelet/pods
+            type: DirectoryOrCreate
+          name: mountpoint-dir
+        - hostPath:
+            path: /var/lib/kubelet/plugins_registry
+            type: Directory
+          name: registration-dir
+        - hostPath:
+            path: /var/lib/kubelet/plugins
+            type: Directory
+          name: plugins-dir
+        - hostPath:
+            # 'path' is where PV data is persisted on host.
+            # using /tmp is also possible while the PVs will not available after plugin container recreation or host reboot
+            path: /var/lib/csi-hostpath-data/
+            type: DirectoryOrCreate
+          name: csi-data-dir
+        - hostPath:
+            path: /dev
+            type: Directory
+          name: dev-dir
+        # end csi volumes

simplyblock_core/scripts/charts/templates/csi-hostpath-driverinfo.yaml

@@ -17,8 +17,8 @@ spec:
   podInfoOnMount: true
   # No attacher needed.
   attachRequired: false
-  storageCapacity: false
-  # Kubernetes may use fsGroup to change permissions and ownership 
+  storageCapacity: true
+  # Kubernetes may use fsGroup to change permissions and ownership
   # of the volume to match user requested fsGroup in the pod's SecurityPolicy
   fsGroupPolicy: File