Feature branch sync - pub/q2_dev to pub/q2_upgrade

common/library/module_utils/input_validation/common_utils/config.py

@@ -130,7 +130,7 @@
     "intel_benchmarks": "2024.1.0",
     "ucx": "1.19.0",
     "openmpi": "5.0.8",
-    "csi_driver_powerscale": "v2.15.0",
+    "csi_driver_powerscale": "v2.16.0",
     "rocm": "6.3.1",
     "service_k8s": "1.35.1"
 }

common/library/module_utils/input_validation/schema/credential_rules.json

@@ -161,5 +161,17 @@
         "maxLength": 128,
         "pattern": "^.+$",
         "description": "Password for Dell OpenManage Enterprise (OME). Length must be between 1 and 128 characters."
+      },
+      "ufm_username": {
+        "minLength": 1,
+        "maxLength": 64,
+        "pattern": "^[^\\\\'\";]+$",
+        "description": "Username for NVIDIA UFM (Unified Fabric Manager). Must not contain backslashes (\\), single quotes ('), double quotes (\"), or semicolons (;). Length must be between 1 and 64 characters."
+      },
+      "ufm_password": {
+        "minLength": 1,
+        "maxLength": 128,
+        "pattern": "^.+$",
+        "description": "Password for NVIDIA UFM (Unified Fabric Manager). Length must be between 1 and 128 characters."
       }
   }

common/library/module_utils/input_validation/schema/telemetry_config.json

@@ -94,9 +94,37 @@
             }
           },
           "required": ["metrics_enabled", "collection_targets"]
+        },
+        "ufm": {
+          "type": "object",
+          "description": "NVIDIA UFM InfiniBand Fabric telemetry.",
+          "properties": {
+            "metrics_enabled": {
+              "type": "boolean",
+              "default": false,
+              "description": "Enable or disable UFM InfiniBand metrics collection."
+            },
+            "logs_enabled": {
+              "type": "boolean",
+              "default": false,
+              "description": "Enable or disable UFM syslog logs collection."
+            },
+            "collection_targets": {
+              "type": "array",
+              "items": {
+                "type": "string",
+                "enum": ["victoria_metrics", "victoria_logs"]
+              },
+              "minItems": 1,
+              "uniqueItems": true,
+              "default": ["victoria_metrics"],
+              "description": "UFM supports victoria_metrics (metrics) and victoria_logs (logs)."
+            }
+          },
+          "required": ["metrics_enabled", "collection_targets"]
         }
       },
-      "required": ["idrac", "ldms", "dcgm", "powerscale"]
+      "required": ["idrac", "ldms", "dcgm", "powerscale", "ufm"]
     },
     "telemetry_bridges": {
       "type": "object",
@@ -398,7 +426,54 @@
         }
       },
       "required": ["otel_collector_storage_size", "csm_observability_values_file_path"]
+    },
+    "ufm_configuration": {
+      "type": "object",
+      "description": "UFM telemetry detailed configurations.",
+      "properties": {
+        "ufm_endpoint": {
+          "type": "string",
+          "description": "UFM appliance IP address or hostname. Required when UFM telemetry is enabled (metrics_enabled or logs_enabled is true)."
+        },
+        "ufm_metrics_port": {
+          "type": "integer",
+          "minimum": 1,
+          "maximum": 65535,
+          "default": 9001,
+          "description": "UFM Prometheus exporter port."
+        },
+        "scrape_interval": {
+          "type": "string",
+          "pattern": "^[0-9]+[smh]$",
+          "default": "30s",
+          "description": "Prometheus scrape interval for UFM metrics."
+        },
+        "scrape_timeout": {
+          "type": "string",
+          "pattern": "^[0-9]+[smh]$",
+          "default": "15s",
+          "description": "Prometheus scrape timeout (must be <= scrape_interval)."
+        },
+        "tls_mode": {
+          "type": "string",
+          "enum": ["self_signed", "ca_signed"],
+          "default": "self_signed",
+          "description": "TLS mode for connecting to UFM Prometheus endpoint."
+        },
+        "ufm_ca_cert_path": {
+          "type": "string",
+          "default": "",
+          "description": "Path to CA certificate file for UFM TLS verification."
+        },
+        "auth_mode": {
+          "type": "string",
+          "enum": ["basic", "none"],
+          "default": "basic",
+          "description": "Authentication mode for UFM Prometheus endpoint."
+        }
+      },
+      "required": []
     }
   },
-  "required": ["telemetry_sources", "telemetry_bridges", "telemetry_sinks", "ldms_configurations", "powerscale_configurations"]
+  "required": ["telemetry_sources", "telemetry_bridges", "telemetry_sinks", "ldms_configurations", "powerscale_configurations", "ufm_configuration"]
 }

common/library/module_utils/input_validation/validation_flows/telemetry_validation.py

@@ -328,6 +328,7 @@ def validate_telemetry_config(
     idrac_source = telemetry_sources.get("idrac", {})
     ldms_source = telemetry_sources.get("ldms", {})
     powerscale_source = telemetry_sources.get("powerscale", {})
+    ufm_source = telemetry_sources.get("ufm", {})
 
     idrac_telemetry_support = idrac_source.get("metrics_enabled", False)
     idrac_collection_targets = idrac_source.get("collection_targets", [])
@@ -383,6 +384,17 @@ def validate_telemetry_config(
             list(invalid_powerscale_targets),
             f"Invalid collection targets for PowerScale. Only 'victoria_metrics' and 'victoria_logs' are supported. Found: {invalid_powerscale_targets}"
         ))
+
+    # UFM: supports victoria_metrics and victoria_logs
+    ufm_targets = set(ufm_source.get("collection_targets", []))
+    allowed_ufm_targets = {"victoria_metrics", "victoria_logs"}
+    invalid_ufm_targets = ufm_targets - allowed_ufm_targets
+    if invalid_ufm_targets:
+        errors.append(create_error_msg(
+            "telemetry_sources.ufm.collection_targets",
+            list(invalid_ufm_targets),
+            f"Invalid collection targets for UFM. Only 'victoria_metrics' and 'victoria_logs' are supported. Found: {invalid_ufm_targets}"
+        ))
 
     # =========================================================================
     # Validate service cluster and slurm cluster
@@ -784,4 +796,59 @@ def validate_telemetry_config(
         is_service_cluster_defined, config_paths, logger, errors
     )
 
+    # =========================================================================
+    # Validate UFM telemetry configuration
+    # =========================================================================
+    ufm_metrics_enabled = ufm_source.get("metrics_enabled", False)
+    ufm_logs_enabled = ufm_source.get("logs_enabled", False)
+    ufm_detailed_config = data.get("ufm_configuration", {})
+
+    if ufm_metrics_enabled or ufm_logs_enabled:
+        # Check required UFM endpoint
+        ufm_endpoint = ufm_detailed_config.get("ufm_endpoint", "")
+        if not ufm_endpoint or (isinstance(ufm_endpoint, str) and ufm_endpoint.strip() == ""):
+            errors.append(create_error_msg(
+                "ufm_configuration.ufm_endpoint",
+                ufm_endpoint,
+                "ufm_endpoint is required when UFM telemetry is enabled. Provide the UFM appliance IP address or hostname."
+            ))
+
+        # Validate UFM metrics port if metrics enabled
+        if ufm_metrics_enabled:
+            ufm_metrics_port = ufm_detailed_config.get("ufm_metrics_port", 9001)
+            if not isinstance(ufm_metrics_port, int) or ufm_metrics_port < 1 or ufm_metrics_port > 65535:
+                errors.append(create_error_msg(
+                    "ufm_configuration.ufm_metrics_port",
+                    ufm_metrics_port,
+                    "ufm_metrics_port must be an integer between 1 and 65535."
+                ))
+
+        # Validate TLS mode
+        tls_mode = ufm_detailed_config.get("tls_mode", "self_signed")
+        if tls_mode not in ["self_signed", "ca_signed"]:
+            errors.append(create_error_msg(
+                "ufm_configuration.tls_mode",
+                tls_mode,
+                "tls_mode must be 'self_signed' or 'ca_signed'."
+            ))
+
+        # Validate CA certificate path when tls_mode is ca_signed
+        if tls_mode == "ca_signed":
+            ca_cert_path = ufm_detailed_config.get("ufm_ca_cert_path", "")
+            if not ca_cert_path or (isinstance(ca_cert_path, str) and ca_cert_path.strip() == ""):
+                errors.append(create_error_msg(
+                    "ufm_configuration.ufm_ca_cert_path",
+                    ca_cert_path,
+                    "ufm_ca_cert_path is required when tls_mode is 'ca_signed'. Provide path to CA certificate file."
+                ))
+
+        # Validate auth mode
+        auth_mode = ufm_detailed_config.get("auth_mode", "basic")
+        if auth_mode not in ["basic", "none"]:
+            errors.append(create_error_msg(
+                "ufm_configuration.auth_mode",
+                auth_mode,
+                "auth_mode must be 'basic' or 'none'."
+            ))
+
     return errors

common/library/modules/fetch_telemetry_status.py

@@ -72,6 +72,13 @@ def main():
     if telemetry_sources.get("idrac", {}).get("metrics_enabled", False):
         telemetry_status_list.append("idrac_telemetry")
 
+    # Check UFM telemetry
+    ufm_config = telemetry_sources.get("ufm", {})
+    if ufm_config.get("metrics_enabled", False):
+        telemetry_status_list.append("ufm_telemetry")
+    if ufm_config.get("logs_enabled", False):
+        telemetry_status_list.append("ufm_logs")
+
     module.exit_json(
             changed=False,
             telemetry_status_list=telemetry_status_list

input/config/x86_64/rhel/10.0/csi_driver_powerscale.json

@@ -5,63 +5,63 @@
         "package": "csi-powerscale",
         "url": "https://github.com/dell/csi-powerscale.git",
         "type": "git",
-        "version": "v2.15.0" 
+        "version": "v2.16.0"
       },
       {
         "package": "external-snapshotter",
         "url": "https://github.com/kubernetes-csi/external-snapshotter.git",
         "type": "git",
-        "version": "v8.3.0"
+        "version": "v8.4.0"
       },
       {
         "package": "helm-charts",
         "url": "https://github.com/dell/helm-charts.git",
         "type": "git",
-        "version": "csi-isilon-2.15.0"
+        "version": "csi-isilon-2.16.0"
       },
       {
         "package": "quay.io/dell/container-storage-modules/csi-isilon",
-        "tag": "v2.15.0",
+        "tag": "v2.16.0",
         "type": "image"
       },
       {
         "package": "registry.k8s.io/sig-storage/csi-attacher",
-        "tag": "v4.9.0", 
+        "tag": "v4.10.0",
         "type": "image"
       },
       {
         "package": "registry.k8s.io/sig-storage/csi-provisioner",
-        "tag": "v5.3.0", 
+        "tag": "v6.1.0",
         "type": "image"
       },
       {
         "package": "registry.k8s.io/sig-storage/csi-snapshotter",
-        "tag": "v8.3.0",
+        "tag": "v8.4.0",
         "type": "image"
       },
       {
         "package": "registry.k8s.io/sig-storage/csi-resizer",
-        "tag": "v1.14.0",
+        "tag": "v2.0.0",
         "type": "image"
       },
       {
         "package": "registry.k8s.io/sig-storage/csi-node-driver-registrar",
-        "tag": "v2.14.0",
+        "tag": "v2.15.0",
         "type": "image"
       },
       {
         "package": "registry.k8s.io/sig-storage/csi-external-health-monitor-controller",
-        "tag": "v0.15.0",
+        "tag": "v0.16.0",
         "type": "image"
      },
      {
       "package": "quay.io/dell/container-storage-modules/dell-csi-replicator",
-      "tag": "v1.13.0",
+      "tag": "v1.14.0",
       "type": "image"
     },
      {
       "package": "quay.io/dell/container-storage-modules/podmon",
-      "tag": "v1.14.0",
+      "tag": "v1.15.0",
       "type": "image"
      },
       {
@@ -71,12 +71,12 @@
      },
     {
       "package": "quay.io/dell/container-storage-modules/csi-metadata-retriever",
-      "tag": "v1.12.0",
+      "tag": "v1.13.0",
       "type": "image"
     },
     {
       "package": "registry.k8s.io/sig-storage/snapshot-controller",
-      "tag": "v8.3.0",
+      "tag": "v8.4.0",
       "type": "image"
     },
     {

input/config/x86_64/rhel/10.0/service_k8s_v1.35.1.json

@@ -78,7 +78,7 @@
       { "package": "prettytable==3.14.0", "type": "pip_module" },
       { "package": "python3-3.12.9", "type": "rpm", "repo_name": "baseos" },
       { "package": "git", "type": "rpm", "repo_name": "appstream"},
-      { "package": "kubernetes==35.0.0", "type": "pip_module" },
+      { "package": "kubernetes==33.1.0", "type": "pip_module" },
       { "package": "PyMySQL==1.1.2", "type": "pip_module" }
 
     ]
@@ -106,7 +106,7 @@
       { "package": "prettytable==3.14.0", "type": "pip_module" },
       { "package": "python3-3.12.9", "type": "rpm", "repo_name": "baseos" },
       { "package": "git", "type": "rpm", "repo_name": "appstream"},
-      { "package": "kubernetes==35.0.0", "type": "pip_module" },
+      { "package": "kubernetes==33.1.0", "type": "pip_module" },
       { "package": "PyMySQL==1.1.2", "type": "pip_module" }
     ]
   },
@@ -118,4 +118,4 @@
       { "package": "quay.io/metallb/controller", "tag": "v0.15.3", "type": "image" } 
     ]
   }
-}
+}