Update example configs and add comments to the config schema (#28)

Resolves [Feature #25](#25)

source/cdk/cdk_slurm_stack.py

@@ -168,7 +168,7 @@ def get_config(self, context_var, default_path):
             from schema import SchemaError
             region = self.node.try_get_context('region')
             try:
-                config_parameters = check_schema(config_parameters, [region])
+                config_parameters = check_schema(config_parameters)
             except SchemaError:
                 logger.exception(f"Invalid config file: {config_file_path}")
                 exit(1)
@@ -378,7 +378,7 @@ def check_config(self):
         from config_schema import check_schema
         from schema import SchemaError
         try:
-            validated_config = check_schema(self.config, [self.config['Region']])
+            validated_config = check_schema(self.config)
         except SchemaError:
             logger.exception(f"Invalid config")
             exit(1)

source/resources/config/default_config.yml

@@ -2,12 +2,10 @@
 #====================================================================
 # Sample configuraton that creates a minimal Slurm cluster
 #
-# Shows all available configuration options
-# Note that CentOS 8 has been discontinued and support has been removed.
-# Uses arm64 architecture for SlurmCtl and SlurmDbd by default.
 # No SlurmDbd in this configuration.
 #
 # Defaults and valid configuration options are in source/config_schema.py.
+# Command line values override values in the config file.
 #====================================================================
 
 StackName: slurmminimal

source/resources/config/slurm_all_instance_types.yml

@@ -1,5 +1,10 @@
 ---
+#====================================================================
 # Create a minimal cluster with all instance types
+#
+# Defaults and valid configuration options are in source/config_schema.py.
+# Command line values override values in the config file.
+#====================================================================
 
 StackName: slurmalltypes
 
@@ -41,4 +46,4 @@ slurm:
 
   # Use defaults from schema
   SlurmCtl: {}
-  storage: {'efs': {}}
+  storage: {'zfs': {}}

source/resources/config/slurm_all_os.yml

@@ -1,6 +1,12 @@
 ---
+#====================================================================
 # Slurm cluster with all supported OS distributions and versions.
+#
 # Note that CentOS 8 has been discontinued and support has been removed.
+#
+# Defaults and valid configuration options are in source/config_schema.py.
+# Command line values override values in the config file.
+#====================================================================
 
 StackName: slurmallos
 
@@ -34,4 +40,4 @@ slurm:
 
   # Use defaults from schema
   SlurmCtl: {}
-  storage: {'efs': {}}
+  storage: {'zfs': {}}

source/resources/config/slurm_alma_linux.yml

@@ -1,5 +1,11 @@
 ---
+#====================================================================
 # Slurm cluster to test Alma Linux support
+#
+# Defaults and valid configuration options are in source/config_schema.py.
+# Command line values override values in the config file.
+#====================================================================
+
 
 StackName: slurmalma
 
@@ -26,4 +32,4 @@ slurm:
 
   # Use defaults from schema
   SlurmCtl: {}
-  storage: {'efs': {}}
+  storage: {'zfs': {}}

source/resources/config/slurm_eda.yml

@@ -1,26 +1,26 @@
 ---
+#====================================================================
 # Slurm cluster for EDA
+#
 # Redundant controllers and typical instances used by EDA.
 # Uses CentOS 7 and AlmaLinux 8 and both x86_64 and arm64 architectures.
+#
+# Defaults and valid configuration options are in source/config_schema.py.
+# Command line values override values in the config file.
+#====================================================================
 
 StackName: slurmeda
 
 slurm:
-  # High level configuration
-
-  SlurmVersion: "21.08.5"
-
   SlurmCtl:
     # For high availability configure multiple controllers
     NumberOfControllers: 2
 
   # The accounting database is required to enable fairshare scheduling
   # It is managed by the Slurm Database Daemon (slurmdbd) instance
-  # This instance can be created as part of the cluster or can use an existing instance.
   SlurmDbd: {}
 
-  # InstanceConfig:
-  # Configure the instances used by the cluster
+  # Configure typical EDA instance types
   # A partition will be created for each combination of Base OS, Architecture, and Spot
   InstanceConfig:
     UseSpot: true
@@ -33,34 +33,38 @@ slurm:
     Include:
       MaxSizeOnly: false
       InstanceFamilies:
-        - 'c5'                # Mixed depending on size
+        #- 'c5'                # Mixed depending on size
         #- 'c5a'               # AMD EPYC 7R32 3.3 GHz
         #- 'c5ad'              # AMD EPYC 7R32 3.3 GHz
-        #- 'c6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
+        - 'c6a'               # AMD EPYC 7R13 Processor     3.6 GHz
+        - 'c6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
         - 'c6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'c6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'f1'                # Intel Xeon E5-2686 v4 (Broadwell) 2.3 GHz
-        - 'm5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
+        #- 'm5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'm5d'               # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'm5a'               # AMD EPYC 7571 2.5 GHz
         #- 'm5ad'              # AMD EPYC 7571 2.5 GHz
-        #- 'm5zn'              # Intel Xeon Platinum 8252 4.5 GHz
-        #- 'm6a'               # AMD EPYC 7R13 Processor 3.6 GHz
-        #- 'm6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
+        - 'm5zn'              # Intel Xeon Platinum 8252 4.5 GHz
+        - 'm6a'               # AMD EPYC 7R13 Processor 3.6 GHz
+        - 'm6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
         - 'm6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'm6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'r5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'r5d'               # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'r5b'               # Intel Xeon Platinum 8259 (Cascade Lake) 3.1 GHz
         #- 'r5a'               # AMD EPYC 7571 2.5 GHz
         #- 'r5ad'              # AMD EPYC 7571 2.5 GHz
-        #- 'r6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz 1TB
-        #- 'r6g'               # AWS Graviton2 Processor 2.5 GHz
+        - 'r6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz 1TB
+        - 'r6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'r6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'x1'                # High Frequency Intel Xeon E7-8880 v3 (Haswell) 2.3 GHz 2TB
         #- 'x1e'               # High Frequency Intel Xeon E7-8880 v3 (Haswell) 2.3 GHz 4TB
-        #- 'x2gd'              # AWS Graviton2 Processor 2.5 GHz 1TB
-        #- 'z1d'               # Intel Xeon Platinum 8151 4.0 GHz
+        - 'x2gd'              # AWS Graviton2 Processor 2.5 GHz 1TB
+        - 'x2idn'             # Intel Xeon Scalable (Icelake) 3.5 GHz 2 TB
+        - 'x2iedn'            # Intel Xeon Scalable (Icelake) 3.5 GHz 4 TB
+        - 'x2iezn'            # Intel Xeon Platinum 8252 4.5 GHz 1.5 TB
+        - 'z1d'               # Intel Xeon Platinum 8151 4.0 GHz
         #- 'u-6tb1'            # Intel Xeon Scalable (Skylake) 6 TB
         #- 'u-9tb1'            # Intel Xeon Scalable (Skylake) 9 TB
         #- 'u-12tb1'           # Intel Xeon Scalable (Skylake) 12 TB
@@ -75,4 +79,4 @@ slurm:
         - '.*\.metal'
 
   # Use defaults from schema
-  storage: {'efs': {}}
+  storage: {'zfs': {}}

source/resources/config/slurm_eda_az1.yml

@@ -1,33 +1,38 @@
 ---
+#====================================================================
 # Federated Slurm cluster for EDA
 #
 # This is the first AZ that other AZs will reference.
 # Other federated clusters will share this cluster's SlurmDbd instance.
 # Redundant controllers and typical instances used by EDA.
 # Uses CentOS 7 and AlmaLinux 8 and both x86_64 and arm64 architectures.
+#
+# Defaults and valid configuration options are in source/config_schema.py.
+# Command line values override values in the config file.
+#====================================================================
 
 StackName: slurmedaaz1
 
-#SubnetId: subnet-xxxxxxxxxxxxxxxxx # PrivateSubnet1
+# Add your subnet id
+SubnetId: subnet-xxxxxxxxxxxxxxxxx # PrivateSubnet1
 
-slurm:
-  #MungeKeySsmParameter: "/slurm/munge_key"
+# This is optional, but highly recommended
+#ErrorSnsTopicArn: arn:aws:sns:{{region}}:{AccountId}:{TopicName}
 
+slurm:
   SlurmCtl:
     # For high availability configure multiple controllers
     NumberOfControllers: 2
 
   # The accounting database is required to enable fairshare scheduling
   # It is managed by the Slurm Database Daemon (slurmdbd) instance
-  # This instance can be created as part of the cluster or can use an existing instance.
   SlurmDbd: {}
 
   Federation:
     Name: slurmeda
     FederatedClusterStackNames: []
 
-  # InstanceConfig:
-  # Configure the instances used by the cluster
+  # Configure typical EDA instance types
   # A partition will be created for each combination of Base OS, Architecture, and Spot
   InstanceConfig:
     UseSpot: true
@@ -40,34 +45,38 @@ slurm:
     Include:
       MaxSizeOnly: false
       InstanceFamilies:
-        - 'c5'                # Mixed depending on size
+        #- 'c5'                # Mixed depending on size
         #- 'c5a'               # AMD EPYC 7R32 3.3 GHz
         #- 'c5ad'              # AMD EPYC 7R32 3.3 GHz
-        #- 'c6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
+        - 'c6a'               # AMD EPYC 7R13 Processor     3.6 GHz
+        - 'c6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
         - 'c6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'c6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'f1'                # Intel Xeon E5-2686 v4 (Broadwell) 2.3 GHz
-        - 'm5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
+        #- 'm5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'm5d'               # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'm5a'               # AMD EPYC 7571 2.5 GHz
         #- 'm5ad'              # AMD EPYC 7571 2.5 GHz
-        #- 'm5zn'              # Intel Xeon Platinum 8252 4.5 GHz
-        #- 'm6a'               # AMD EPYC 7R13 Processor 3.6 GHz
-        #- 'm6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
+        - 'm5zn'              # Intel Xeon Platinum 8252 4.5 GHz
+        - 'm6a'               # AMD EPYC 7R13 Processor 3.6 GHz
+        - 'm6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
         - 'm6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'm6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'r5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'r5d'               # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'r5b'               # Intel Xeon Platinum 8259 (Cascade Lake) 3.1 GHz
         #- 'r5a'               # AMD EPYC 7571 2.5 GHz
         #- 'r5ad'              # AMD EPYC 7571 2.5 GHz
-        #- 'r6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz 1TB
-        #- 'r6g'               # AWS Graviton2 Processor 2.5 GHz
+        - 'r6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz 1TB
+        - 'r6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'r6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'x1'                # High Frequency Intel Xeon E7-8880 v3 (Haswell) 2.3 GHz 2TB
         #- 'x1e'               # High Frequency Intel Xeon E7-8880 v3 (Haswell) 2.3 GHz 4TB
-        #- 'x2gd'              # AWS Graviton2 Processor 2.5 GHz 1TB
-        #- 'z1d'               # Intel Xeon Platinum 8151 4.0 GHz
+        - 'x2gd'              # AWS Graviton2 Processor 2.5 GHz 1TB
+        - 'x2idn'             # Intel Xeon Scalable (Icelake) 3.5 GHz 2 TB
+        - 'x2iedn'            # Intel Xeon Scalable (Icelake) 3.5 GHz 4 TB
+        - 'x2iezn'            # Intel Xeon Platinum 8252 4.5 GHz 1.5 TB
+        - 'z1d'               # Intel Xeon Platinum 8151 4.0 GHz
         #- 'u-6tb1'            # Intel Xeon Scalable (Skylake) 6 TB
         #- 'u-9tb1'            # Intel Xeon Scalable (Skylake) 9 TB
         #- 'u-12tb1'           # Intel Xeon Scalable (Skylake) 12 TB
@@ -82,4 +91,4 @@ slurm:
         - '.*\.metal'
 
   # Use defaults from schema
-  storage: {'efs': {}}
+  storage: {'zfs': {}}

source/resources/config/slurm_eda_az2.yml

@@ -1,28 +1,30 @@
 ---
+#====================================================================
 # Federated Slurm cluster for EDA
 #
 # This is the 2nd AZ that must be created after the 1st cluster.
 # Shares the SlurmDbd instance from the 1st AZ's cluster.
 # Redundant controllers and typical instances used by EDA.
 # Uses CentOS 7 and AlmaLinux 8 and both x86_64 and arm64 architectures.
+#
+# Defaults and valid configuration options are in source/config_schema.py.
+# Command line values override values in the config file.
+#====================================================================
 
 StackName: slurmedaaz2
 
-#SubnetId: subnet-xxxxxxxxxxxxxxxxx # PrivateSubnet2
+# Add your subnet id
+SubnetId: subnet-xxxxxxxxxxxxxxxxx # PrivateSubnet2
 
 # This is optional, but highly recommended
 #ErrorSnsTopicArn: arn:aws:sns:{{region}}:{AccountId}:{TopicName}
 
 slurm:
-  #MungeKeySsmParameter: "/slurm/munge_key"
-
   SlurmCtl:
     # For high availability configure multiple controllers
     NumberOfControllers: 2
 
-  # The accounting database is required to enable fairshare scheduling
-  # It is managed by the Slurm Database Daemon (slurmdbd) instance
-  # This instance can be created as part of the cluster or can use an existing instance.
+  # Re-use the SlurmDbd instance from slurmedaaz1
   ExistingSlurmDbd:
     StackName: slurmedaaz1
 
@@ -31,8 +33,7 @@ slurm:
     FederatedClusterStackNames:
       - slurmedaaz1
 
-  # InstanceConfig:
-  # Configure the instances used by the cluster
+  # Configure typical EDA instance types
   # A partition will be created for each combination of Base OS, Architecture, and Spot
   InstanceConfig:
     UseSpot: true
@@ -45,40 +46,43 @@ slurm:
     Include:
       MaxSizeOnly: false
       InstanceFamilies:
-        - 'c5'                # Mixed depending on size
-        #- 'c5a'               # AMD EPYC 7R32 3.3 GHz
+        #- 'c5'                # Mixed depending on size
+        - 'c5a'               # AMD EPYC 7R32 3.3 GHz
         #- 'c5ad'              # AMD EPYC 7R32 3.3 GHz
-        #- 'c6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
+        - 'c6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
         - 'c6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'c6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'f1'                # Intel Xeon E5-2686 v4 (Broadwell) 2.3 GHz
         - 'm5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'm5d'               # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
-        #- 'm5a'               # AMD EPYC 7571 2.5 GHz
+        - 'm5a'               # AMD EPYC 7571 2.5 GHz
         #- 'm5ad'              # AMD EPYC 7571 2.5 GHz
-        #- 'm5zn'              # Intel Xeon Platinum 8252 4.5 GHz
-        #- 'm6a'               # AMD EPYC 7R13 Processor 3.6 GHz
-        #- 'm6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
+        - 'm5zn'              # Intel Xeon Platinum 8252 4.5 GHz
+        - 'm6a'               # AMD EPYC 7R13 Processor 3.6 GHz
+        - 'm6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz
         - 'm6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'm6gd'              # AWS Graviton2 Processor 2.5 GHz
-        #- 'r5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
-        #- 'r5d'               # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
+        - 'r5'                # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
+        - 'r5d'               # Intel Xeon Platinum 8175 (Skylake) 3.1 GHz
         #- 'r5b'               # Intel Xeon Platinum 8259 (Cascade Lake) 3.1 GHz
-        #- 'r5a'               # AMD EPYC 7571 2.5 GHz
-        #- 'r5ad'              # AMD EPYC 7571 2.5 GHz
-        #- 'r6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz 1TB
-        #- 'r6g'               # AWS Graviton2 Processor 2.5 GHz
+        - 'r5a'               # AMD EPYC 7571 2.5 GHz
+        - 'r5ad'              # AMD EPYC 7571 2.5 GHz
+        - 'r6i'               # Intel Xeon 8375C (Ice Lake) 3.5 GHz 1TB
+        - 'r6g'               # AWS Graviton2 Processor 2.5 GHz
         #- 'r6gd'              # AWS Graviton2 Processor 2.5 GHz
         #- 'x1'                # High Frequency Intel Xeon E7-8880 v3 (Haswell) 2.3 GHz 2TB
         #- 'x1e'               # High Frequency Intel Xeon E7-8880 v3 (Haswell) 2.3 GHz 4TB
-        #- 'x2gd'              # AWS Graviton2 Processor 2.5 GHz 1TB
-        #- 'z1d'               # Intel Xeon Platinum 8151 4.0 GHz
+        - 'x2gd'              # AWS Graviton2 Processor 2.5 GHz 1TB
+        - 'x2idn'             # Intel Xeon Scalable (Icelake) 3.5 GHz 2 TB
+        - 'x2iedn'            # Intel Xeon Scalable (Icelake) 3.5 GHz 4 TB
+        - 'x2iezn'            # Intel Xeon Platinum 8252 4.5 GHz 1.5 TB
+        - 'z1d'               # Intel Xeon Platinum 8151 4.0 GHz
         #- 'u-6tb1'            # Intel Xeon Scalable (Skylake) 6 TB
         #- 'u-9tb1'            # Intel Xeon Scalable (Skylake) 9 TB
         #- 'u-12tb1'           # Intel Xeon Scalable (Skylake) 12 TB
-      InstanceTypes: []
+      InstanceTypes:
         #- 'c5\.(l|x|2|4|9|18).*'  # Intel Xeon Platinum 8124M 3.4 GHz
-        #- 'c5\.(12|24).*'         # Intel Xeon Platinum 8275L 3.6 GHz
+        - 'c5\.(12|24).*'         # Intel Xeon Platinum 8275L 3.6 GHz
         #- 'c5d\.(l|x|2|4|9|18).*' # Intel Xeon Platinum 8124M 3.4 GHz
         #- 'c5d\.(12|24).*'        # Intel Xeon Platinum 8275L 3.6 GHz
     Exclude:
@@ -87,4 +91,4 @@ slurm:
         - '.*\.metal'
 
   # Use defaults from schema
-  storage: {'efs': {}}
+  storage: {'zfs': {}}