Change defaults so a cookiecutter environment is fully functional (#473)

* cookiecutter environment now has working defaults

* updated docs

* refactored ood demo user into cookiecutter

* updated docs

* changed secret name

* Doc changes

Co-authored-by: Steve Brasier <[email protected]>

* rename

* replaced testuser with demo_user

* selinux now defaults to disabled

* bump images

* updated readme

* moved files and removed redundant ood config

* environments now have grafana anonymous auth by default

* docs update

Co-authored-by: Steve Brasier <[email protected]>

---------

Co-authored-by: Steve Brasier <[email protected]>

Author: wtripp180901

.github/workflows/stackhpc.yml

@@ -99,9 +99,9 @@ jobs:
           . venv/bin/activate
           . environments/.stackhpc/activate
           ansible-playbook ansible/adhoc/generate-passwords.yml
-          echo vault_testuser_password: "$TESTUSER_PASSWORD" > $APPLIANCES_ENVIRONMENT_ROOT/inventory/group_vars/all/test_user.yml
+          echo vault_demo_user_password: "$DEMO_USER_PASSWORD" > $APPLIANCES_ENVIRONMENT_ROOT/inventory/group_vars/all/test_user.yml
         env:
-          TESTUSER_PASSWORD: ${{ secrets.TEST_USER_PASSWORD }}
+          DEMO_USER_PASSWORD: ${{ secrets.TEST_USER_PASSWORD }}
 
       - name: Provision nodes using fat image
         id: provision_servers
@@ -163,12 +163,12 @@ jobs:
             --spider \
             --server-response \
             --no-check-certificate \
-            --http-user=testuser \
-            --http-password=${TESTUSER_PASSWORD} https://${openondemand_servername} \
+            --http-user=demo_user \
+            --http-password=${DEMO_USER_PASSWORD} https://${openondemand_servername} \
             2>&1)
           (echo $statuscode | grep "200 OK") || (echo $statuscode  && exit 1)
         env:
-          TESTUSER_PASSWORD: ${{ secrets.TEST_USER_PASSWORD }}
+          DEMO_USER_PASSWORD: ${{ secrets.TEST_USER_PASSWORD }}
 
       # - name: Build environment-specific compute image
       #   id: packer_build

README.md

@@ -104,6 +104,7 @@ To deploy this infrastructure, ensure the venv and the environment are [activate
 
     export OS_CLOUD=openstack
     cd environments/$ENV/terraform/
+    tofu init
     tofu apply
 
 and follow the prompts. Note the OS_CLOUD environment variable assumes that OpenStack credentials are defined using a [clouds.yaml](https://docs.openstack.org/python-openstackclient/latest/configuration/index.html#clouds-yaml) file in a default location with the default cloud name of `openstack`.

ansible/roles/passwords/defaults/main.yml

@@ -10,6 +10,7 @@ slurm_appliance_secrets:
   vault_freeipa_admin_password: "{{ vault_freeipa_admin_password | default(lookup('password', '/dev/null')) }}"
   vault_k3s_token: "{{ vault_k3s_token | default(lookup('ansible.builtin.password', '/dev/null', length=64)) }}"
   vault_pulp_admin_password: "{{ vault_pulp_admin_password | default(lookup('password', '/dev/null', chars=['ascii_letters', 'digits'])) }}"
+  vault_demo_user_password: "{{ vault_demo_user_password | default(lookup('password', '/dev/null')) }}"
 
 secrets_openhpc_mungekey_default:
   content: "{{ lookup('pipe', 'dd if=/dev/urandom bs=1 count=1024 2>/dev/null | base64') }}"

ansible/roles/passwords/tasks/validate.yml

@@ -1,4 +1,4 @@
 - name: Assert secrets created
   assert:
-    that: (hostvars[inventory_hostname].keys() | select('contains', 'vault_') | length) > 1 # 1 as may have vault_testuser_password defined in dev
+    that: (hostvars[inventory_hostname].keys() | select('contains', 'vault_') | length) > 1 # 1 as may have vault_demo_user_password defined in dev
     fail_msg: "No inventory variables 'vault_*' found: Has ansible/adhoc/generate-passwords.yml been run?"

docs/openondemand.README.md renamed to docs/openondemand.md

@@ -30,11 +30,10 @@ The above functionality is configured by running the `ansible/portal.yml` playbo
 
 See the [ansible/roles/openondemand/README.md](../ansible/roles/openondemand/README.md) for more details on the variables described below.
 
-At minimum the following must be defined:
-- `openondemand_servername` - this must be defined for both `openondemand` and `grafana` hosts (when Grafana is enabled). It is suggested to place it groupvars for `all`.
-- `openondemand_auth` and any corresponding options.
-- `openondemand_desktop_partition` and `openondemand_jupyter_partition` if the corresponding inventory groups are defined.
-- `openondemand_host_regex` if `openondemand_desktop` or `openondemand_jupyter` inventory groups are defined and/or proxying Grafana via Open Ondemand is required.
+The following variables have been given default values to allow Open Ondemand to work in a newly created environment without additional configuration, but generally should be overridden in `environment/site/inventory/group_vars/all/` with site-specific values:
+- `openondemand_servername` - this must be defined for both `openondemand` and `grafana` hosts (when Grafana is enabled). Default is `ansible_host` (i.e. the IP address) of the first host in the `openondemand` group.
+- `openondemand_auth` and any corresponding options. Defaults to `basic_pam`.
+- `openondemand_desktop_partition` and `openondemand_jupyter_partition` if the corresponding inventory groups are defined. Defaults to the first compute group defined in the `compute` Terraform variable in `environments/$ENV/terraform`.
 
 It is also recommended to set:
 - `openondemand_dashboard_support_url`
@@ -45,3 +44,6 @@ If shared filesystems other than `$HOME` are available, add paths to `openondema
 The appliance automatically configures Open Ondemand to proxy Grafana and adds a link to it on the Open Ondemand dashboard. This means no external IP (or SSH proxying etc) is required to access Grafana (which by default is deployed on the control node). To allow users to authenticate to Grafana, the simplest option is to enable anonymous (View-only) login by setting `grafana_auth_anonymous` (see [environments/common/inventory/group_vars/all/grafana.yml](../environments/common/inventory/group_vars/all/grafana.yml)[^1]).
 
 [^1]: Note that if `openondemand_auth` is `basic_pam` and anonymous Grafana login is enabled, the appliance will (by default) configure Open Ondemand's Apache server to remove the Authorisation header from proxying of all `node/` addresses. This is done as otherwise Grafana tries to use this header to authenticate, which fails with the default configuration where only the admin Grafana user `grafana` is created. Note that the removal of this header in this configuration means it cannot be used to authenticate proxied interactive applications - however the appliance-deployed remote desktop and Jupyter Notebook server applications use other authentication methods. An alternative if using `basic_pam` is not to enable anonymous Grafana login and to create Grafana users matching the local users (e.g. in `environments/<env>/hooks/post.yml`).
+
+# Access
+By default the appliance authenticates against OOD with basic auth through PAM. When creating a new environment, a new user with username `demo_user` will be created. Its password is found under `vault_openondemand_default_user` in the appliance secrets store in `environments/{ENV}/inventory/group_vars/all/secrets.yml`. Other users can be defined by overriding the `basic_users_users` variable in your environment (templated into `environments/{ENV}/inventory/group_vars/all/basic_users.yml` by default).

docs/production.md

@@ -98,6 +98,10 @@ and referenced from the `site` and `production` environments, e.g.:
 
 - Configure Open OpenOndemand - see [specific documentation](openondemand.README.md).
 
+- Remove the `demo_user` user from `environments/$ENV/inventory/group_vars/all/basic_users.yml`
+
+- Consider whether having (read-only) access to Grafana without login is OK. If not, remove `grafana_auth_anonymous` in `environments/$ENV/inventory/group_vars/all/grafana.yml`
+
 - Modify `environments/site/terraform/nodes.tf` to provide fixed IPs for at least
   the control node, and (if not using FIPs) the login node(s):
 

environments/.caas/inventory/group_vars/all/selinux.yml

@@ -1,6 +1,6 @@
-test_user_password: "{{ lookup('env', 'TESTUSER_PASSWORD') | default(vault_testuser_password, true) }}" # CI uses env, debug can set vault_testuser_password
+test_demo_user_password: "{{ lookup('env', 'DEMO_USER_PASSWORD') | default(vault_demo_user_password, true) }}" # CI uses env, debug can set vault_demo_user_password
 
 basic_users_users:
-  - name: testuser # can't use rocky as $HOME isn't shared!
-    password: "{{ test_user_password | password_hash('sha512', 65534 | random(seed=inventory_hostname) | string) }}" # idempotent
+  - name: demo_user # can't use rocky as $HOME isn't shared!
+    password: "{{ test_demo_user_password | password_hash('sha512', 65534 | random(seed=inventory_hostname) | string) }}" # idempotent
     uid: 1005

environments/.stackhpc/inventory/group_vars/all/basic_users.yml

@@ -2,8 +2,8 @@
 
 # NB: Users defined this way have expired passwords
 freeipa_users:
-  - name: testuser # can't use rocky as $HOME isn't shared!
-    password: "{{ test_user_password }}"
+  - name: demo_user # can't use rocky as $HOME isn't shared!
+    password: "{{ test_demo_user_password }}"
     givenname: test
     sn: test
 

environments/.stackhpc/inventory/group_vars/all/freeipa.yml

@@ -1 +1,8 @@
-openondemand_servername: "{{ hostvars[ groups['openondemand'] | first].ansible_host }}" # Use a SOCKS proxy to acccess
+openondemand_auth: basic_pam
+openondemand_jupyter_partition: standard
+openondemand_desktop_partition: standard
+#openondemand_dashboard_support_url: 
+#openondemand_dashboard_docs_url:
+#openondemand_filesapp_paths:
+ondemand_package: ondemand-"{{ ondemand_package_version }}"
+ondemand_package_version: '3.1.10'

environments/.stackhpc/inventory/group_vars/grafana/overrides.yml renamed to environments/.stackhpc/inventory/group_vars/all/grafana.yml

@@ -5,7 +5,12 @@
 
 # NB: Variables prefixed ood_ are all from https://github.com/OSC/ood-ansible
 
-# openondemand_servername: '' # Must be defined when using openondemand
+openondemand_servername: "{{ hostvars[groups['openondemand'].0].ansible_host if groups['openondemand'] else '' }}"
+
+openondemand_auth: basic_pam
+
+openondemand_jupyter_partition: "{{ openhpc_slurm_partitions[0]['name'] }}"
+openondemand_desktop_partition: "{{ openhpc_slurm_partitions[0]['name'] }}"
 
 # Regex defining hosts which openondemand can proxy; the default regex is compute nodes (for apps) and grafana host,
 # e.g. if the group `compute` has hosts `compute-{0,1,2,..}` this will be '(compute-\d+)|(control)'.

environments/.stackhpc/inventory/group_vars/openhpc/overrides.yml renamed to environments/.stackhpc/inventory/group_vars/all/openhpc.yml

@@ -1,4 +1,4 @@
 ---
 
-selinux_state: permissive
+selinux_state: disabled
 selinux_policy: targeted

environments/.stackhpc/inventory/group_vars/all/openondemand.yml

@@ -36,8 +36,9 @@ login
 [block_devices:children]
 # Environment-specific so not defined here
 
-[basic_users]
+[basic_users:children]
 # Add `openhpc` group to add Slurm users via creation of users on each node.
+openhpc
 
 [openondemand:children]
 # Host to run Open Ondemand server on - subset of login
@@ -51,8 +52,9 @@ compute
 # Subset of compute to run a Jupyter Notebook servers on via Open Ondemand
 compute
 
-[etc_hosts]
+[etc_hosts:children]
 # Hosts to manage /etc/hosts e.g. if no internal DNS. See ansible/roles/etc_hosts/README.md
+cluster
 
 [cuda]
 # Hosts to install NVIDIA CUDA on - see ansible/roles/cuda/README.md

environments/.stackhpc/inventory/group_vars/openondemand/overrides.yml

@@ -0,0 +1,4 @@
+basic_users_users:
+  - name: demo_user
+    password: "{% raw %}{{ vault_demo_user_password | password_hash('sha512', 65534 | random(seed=inventory_hostname) | string) }}{% endraw %}" # idempotent
+    uid: 1005

environments/.stackhpc/inventory/group_vars/selinux/overrides.yml

@@ -0,0 +1 @@
+grafana_auth_anonymous: true

environments/common/inventory/group_vars/all/openondemand.yml

@@ -6,7 +6,7 @@ variable "cluster_name" {
 variable "cluster_domain_suffix" {
     type = string
     description = "Domain suffix for cluster"
-    default = "invalid"
+    default = "internal"
 }
 
 variable "cluster_net" {