Fix PR 4798 comments

- In each blueprint, add more explanations for each parameter
- Remove the debug partition and debug nodeset from the blurprint of slurm
- Add parameter descriptions for sycomp-scale-expansion

Author: gqiu-sycomp-com

community/examples/sycomp/README.md

@@ -66,10 +66,13 @@ Required parameter updates for each blueprint:
   - `security.ssh.public_key`: The file path to your SSH public key (e.g., `~/.ssh/id_rsa.pub`).
   - `security.customer_token.token`: Your Sycomp Customer Token. To get a customer token, contact Sycomp (`sycompstorage@sycomp.com`).
   - `name_prefix` (Optional): By default, `sycomp-scale-gcp` sets the value of `name_prefix` based on the `deployment_name`. Since `name_prefix` only accepts **alphanumeric** characters (letters and numbers), `sycomp-scale-gcp` automatically **removes any non-alphanumeric characters** (such as hyphens and underscores) before assigning the value. For example, a `deployment_name` of `sycomp-storage-1` would result in a `name_prefix` of `sycompstorage1`.
+  - **`scale_config`(Optional):**
+    - `scale_node_count`: The number of nodes in the Sycomp Storage cluster. Default is `3`.
+    - `scale_volumes`: Configuration for the data disks. Default is 4 disks of 250GiB each per storage node.
 
-- **(Optional) `scale_config` settings:**
-  - `scale_node_count`: The number of nodes in the Sycomp Storage cluster. Default is `3`.
-  - `scale_volumes`: Configuration for the data disks. Default is 4 disks of 250GiB each per storage node.
+- **`sycomp-scale-gcp` module settings:**
+  - `name_prefix`: Its value must be the same as the `name_prefix` of the cluster that is desired to be expanded.
+  - `add_scale_nodes`: The number of nodes to be added.
 
 ## Deployment
 

community/examples/sycomp/sycomp-storage-ece.yaml

@@ -52,14 +52,16 @@ deployment_groups:
         customer_token:
           token: ""              ## Set Your Customer Token
       ece:
-        use_ece: true
-        ece_node_per_rg: 7
-        ece_raid_code: "4+2p"
-        ece_block_size: "1m"
+        use_ece: true            ## Set deploy mode to ECE
+        ece_node_per_rg: 7       ## Set the number of nodes for each Recovery Group
+        ece_raid_code: "4+2p"    ## Set the raid code
+        ece_block_size: "1m"     ## Set block size
 
       scale_config:
-        scale_node_count: 7
+        scale_node_count: 7                   ## Number of storage nodes to deploy
+        scale_machine_type: "c3-standard-44"  ## Instance type of the storage nodes
         scale_volumes:
           data-storage:
-            count: 3
-            size_in_gb: 250
+            count: 3                          ## Number of disks to configure on each storage node
+            size_in_gb: 250                   ## Size of each disk
+            type: "hyperdisk-balanced"        ## Type of persistent disk to use

community/examples/sycomp/sycomp-storage-expansion.yaml

@@ -30,8 +30,8 @@ deployment_groups:
 - group: primary
   modules:
 
-  - id: sycomp-scale-gcp
+  - id: sycomp-scale-expansion
     source: "git::https://gitlab.com/sycomp/cluster-toolkit.git//sycomp-scale-expansion?ref=v1.0.0"
     settings:
       name_prefix: "<name_prefix_of_existing_cluster>" ## Its value must be the same as the name_prefix of the cluster that is desired to be expanded
-      add_scale_nodes: 1
+      add_scale_nodes: 1                               ## Number of storage nodes to add

community/examples/sycomp/sycomp-storage-slurm.yaml

@@ -47,56 +47,45 @@ deployment_groups:
     settings:
       security:
         ssh:
-          ssh_user_name: ""      ## Set user name to ssh mgmt node, for example: "sycompacct"
-          private_key: ""        ## Set private key file, for example: ~/.ssh/id_rsa
-          public_key: ""         ## Set public key file, for example: ~/.ssh/id_rsa.pub
+          ssh_user_name: ""                   ## Set user name to ssh mgmt node, for example: "sycompacct"
+          private_key: ""                     ## Set private key file, for example: ~/.ssh/id_rsa
+          public_key: ""                      ## Set public key file, for example: ~/.ssh/id_rsa.pub
         customer_token:
-          token: ""              ## Set Your Customer Token
+          token: ""                           ## Set Your Customer Token
       scale_config:
-        scale_node_count: 3
+        scale_node_count: 3                   ## Number of storage nodes to deploy
+        scale_machine_type: "c3-standard-44"  ## Instance type of the storage nodes
         scale_volumes:
           data-storage:
-            count: 4
-            size_in_gb: 250
+            count: 4                          ## Number of disks to configure on each storage node
+            size_in_gb: 250                   ## Size of each disk
+            type: "hyperdisk-balanced"        ## Type of persistent disk to use
+            provisioned_iops: 30000           ## Provisiioned IOPS per disk, required for Hyperdisk
+            provisioned_throughput: 500       ## Provisiioned Throughput in MiB/sec per disk, required for Hyperdisk
+
       ces_config:
-        enabled: true
-        create_dns: true
+        enabled: true                         ## A value of true enables NFS service
+        create_dns: true                      ## Create a round robin DNS entry that include all of the NFS Servers, one NFS server is created on each storage node.
       nfs_exports:
       - path: $(vars.nfs_dir)
         clients:
-        - no_root_squash: false
+        - no_root_squash: false               ## Disable no_root_squash in NFS
 
   ## Set up slurm cluster and configure NFS client
-  - id: debug_nodeset
+  - id: compute_nodeset
     source: community/modules/compute/schedmd-slurm-gcp-v6-nodeset
     use: [network1]
     settings:
       node_count_dynamic_max: 4
       machine_type: n2-standard-2
       allow_automatic_updates: false
 
-  - id: debug_partition
-    source: community/modules/compute/schedmd-slurm-gcp-v6-partition
-    use:
-    - debug_nodeset
-    settings:
-      partition_name: debug
-      exclusive: false  ## allows nodes to stay up after jobs are done
-      is_default: true
-
-  - id: compute_nodeset
-    source: community/modules/compute/schedmd-slurm-gcp-v6-nodeset
-    use: [network1]
-    settings:
-      node_count_dynamic_max: 20
-      bandwidth_tier: gvnic_enabled
-      allow_automatic_updates: false
-
   - id: compute_partition
     source: community/modules/compute/schedmd-slurm-gcp-v6-partition
     use:
     - compute_nodeset
     settings:
+      is_default: true
       partition_name: compute
 
   - id: slurm_login
@@ -110,7 +99,6 @@ deployment_groups:
     source: community/modules/scheduler/schedmd-slurm-gcp-v6-controller
     use:
     - network1
-    - debug_partition
     - compute_partition
     - slurm_login
     settings:

community/examples/sycomp/sycomp-storage.yaml

@@ -47,21 +47,21 @@ deployment_groups:
       name_prefix: "sycompstorage"
       security:
         ssh:
-          ssh_user_name: ""      ## Set user name to ssh mgmt node, for example: "sycompacct"
-          private_key: ""        ## Set private key file, for example: ~/.ssh/id_rsa
-          public_key: ""         ## Set public key file, for example: ~/.ssh/id_rsa.pub
+          ssh_user_name: ""                  ## Set user name to ssh mgmt node, for example: "sycompacct"
+          private_key: ""                    ## Set private key file, for example: ~/.ssh/id_rsa
+          public_key: ""                     ## Set public key file, for example: ~/.ssh/id_rsa.pub
         customer_token:
-          token: ""              ## Set Your Customer Token
+          token: ""                          ## Set Your Customer Token
       scale_config:
-        scale_node_count: 3
-        scale_machine_type: "c3-standard-44"
+        scale_node_count: 3                  ## Number of storage nodes to deploy
+        scale_machine_type: "c3-standard-44" ## Instance type of the storage nodes
         scale_volumes:
           data-storage:
-            count: 4
-            size_in_gb: 250
-            type: "hyperdisk-balanced"
-            provisioned_iops: 30000
-            provisioned_throughput: 500
+            count: 4                         ## Number of disks to configure on each storage node
+            size_in_gb: 250                  ## Size of each disk
+            type: "hyperdisk-balanced"       ## Type of persistent disk to use
+            provisioned_iops: 30000          ## Provisiioned IOPS per disk, required for Hyperdisk
+            provisioned_throughput: 500      ## Provisiioned Throughput in MiB/sec per disk, required for Hyperdisk
         afm_config:
-          afm_node_count: 1
-          afm_machine_type: "c3-standard-44"
+          afm_node_count: 1                  ## Number of AFM nodes to deploy
+          afm_machine_type: "c3-standard-44" ## Instance type of the AFM nodes