Allow arbitrary hostnames

.travis.yml

@@ -1,20 +1,18 @@
 ---
 language: python
-python: "2.7"
 
 # Use the new container infrastructure
-sudo: false
-
-# Install ansible
-addons:
-  apt:
-    packages:
-    - python-pip
-
+sudo: required
+services:
+  - docker
+before_install:
+  - sudo apt-get -qq update
 install:
-  # Install ansible
-  - pip install ansible ansible-lint
-
+  - python3 -m pip install ansible
+  - python3 -m pip install ansible-lint
+  - python3 -m pip install molecule
+  - python3 -m pip install docker
+
   # Check ansible version
   - ansible --version
 
@@ -34,5 +32,8 @@ script:
   # Test the custom filters
   - ansible-playbook tests/filter.yml -i tests/inventory -i tests/inventory-mock-groups
 
+  # Run molecule tests
+  - molecule test
+
 notifications:
   webhooks: https://galaxy.ansible.com/api/v1/notifications/

.yamllint

@@ -0,0 +1,33 @@
+---
+# Based on ansible-lint config
+extends: default
+
+rules:
+  braces:
+    max-spaces-inside: 1
+    level: error
+  brackets:
+    max-spaces-inside: 1
+    level: error
+  colons:
+    max-spaces-after: -1
+    level: error
+  commas:
+    max-spaces-after: -1
+    level: error
+  comments: disable
+  comments-indentation: disable
+  document-start: disable
+  empty-lines:
+    max: 3
+    level: error
+  hyphens:
+    level: error
+  indentation: disable
+  key-duplicates: enable
+  line-length: disable
+  new-line-at-end-of-file: disable
+  new-lines:
+    type: unix
+  trailing-spaces: disable
+  truthy: disable

README.md

@@ -18,10 +18,9 @@ Role Variables
   Otherwise, `groups` can be omitted and the following attributes can be defined in the partition object:
   * `name`: The name of the nodes within this group.
   * `cluster_name`: Optional.  An override for the top-level definition `openhpc_cluster_name`.
-  * `num_nodes`: Nodes within the group are assumed to number `0:num_nodes-1`.
-  * `ram_mb`: Optional.  The physical RAM available in each server of this group ([slurm.conf](https://slurm.schedmd.com/slurm.conf.html) parameter `RealMemory`).
+  * `ram_mb`: Optional.  The physical RAM available in each server of this group ([slurm.conf](https://slurm.schedmd.com/slurm.conf.html) parameter `RealMemory`). This is set to the Slurm default of `1` if not defined.
 
-  For each group (if used) or partition there must be an ansible inventory group `{cluster_name}_{group_name}`. The compute nodes in this group must have hostnames in the form `{cluster_name}-{group_name}-{0..num_nodes-1}`. Note the inventory group uses "_" and the instances use "-".
+  For each group (if used) or partition there must be an ansible inventory group `<cluster_name>_<group_name>`. All nodes in this inventory group will be added to the group/partition. Nodes may have arbitrary hostnames but these should be lowercase to avoid a mismatch between inventory and actual hostname.
 
 * `default`: Optional.  A boolean flag for whether this partion is the default.  Valid settings are `YES` and `NO`.
 * `maxtime`: Optional.  A partition-specific time limit in hours, minutes and seconds ([slurm.conf](https://slurm.schedmd.com/slurm.conf.html) parameter `MaxTime`).  The default value is
@@ -82,16 +81,10 @@ To deploy, create a playbook which looks like this:
           openhpc_slurm_control_host: "{{ groups['cluster_control'] | first }}"
           openhpc_slurm_partitions:
             - name: "compute"
-              num_nodes: 8
           openhpc_cluster_name: openhpc
           openhpc_packages: []
     ...
 
-Note that the "compute" of the openhpc_slurm_partition name and the
-openhpc_cluster_name are used to generate the compute node in the
-slurm config of openhpc-compute-[0:7]. Your inventory entries
-for that partition must match that convention.
-
 To drain nodes, for example, before scaling down the cluster to 6 nodes:
 
     ---

filter_plugins/group_hosts.py

@@ -45,7 +45,7 @@ def _group_hosts(hosts):
             r.append(int(suffix))
         else:
             unmatchable.append(v)
-    return ['{}[{}]'.format(k, _group_numbers(v)) for k, v in results.iteritems()] + unmatchable
+    return ['{}[{}]'.format(k, _group_numbers(v)) for k, v in results.items()] + unmatchable
 
 def _group_numbers(numbers):
     units = []

molecule/README.md

@@ -0,0 +1,39 @@
+Molecule tests for the role.
+
+# Test Matrix
+
+Test options "flow down" through table unless changed.
+
+Test   | # Partitions | Groups in partitions?   | Other
+---    | ---          | ---                     | ---
+test1  | 1            | N                       | 2x compute node, sequential names (default test)
+test1b | 1            | N                       | 1x compute node
+test1c | 1            | N                       | 2x compute nodes, nonsequential names
+test2  | 2            | N                       | 4x compute node, sequential names
+test3  | 1            | Y                       | -
+
+# Local Installation & Running
+
+Local installation on a Centos7 machine looks like:
+
+    sudo yum install -y gcc python3-pip python3-devel openssl-devel python3-libselinux
+    sudo yum install -y docker-ce docker-ce-cli containerd.io
+    sudo yum install -y yum-utils
+    sudo yum-config-manager --add-repo https://download.docker.com/linux/centos/docker-ce.repo
+    sudo yum install -y docker-ce docker-ce-cli containerd.io
+    pip3 install -r molecule/requirements.txt --user
+
+    sudo systemctl start docker
+    sudo usermod -aG docker ${USER}
+    newgrp docker
+    docker run hello-world # test docker works without sudo
+
+    sudo yum install -y git
+    git clone git@github.com:stackhpc/ansible-role-openhpc.git
+    cd ansible-role-openhpc/
+
+Then to run all tests:
+
+    cd ansible-role-openhpc/
+    molecule test --all
+

molecule/default

@@ -0,0 +1 @@
+test1

molecule/requirements.txt

@@ -0,0 +1,4 @@
+pip
+setuptools
+molecule[lint]
+docker

molecule/test1/INSTALL.rst

@@ -0,0 +1,22 @@
+*******
+Docker driver installation guide
+*******
+
+Requirements
+============
+
+* Docker Engine
+
+Install
+=======
+
+Please refer to the `Virtual environment`_ documentation for installation best
+practices. If not using a virtual environment, please consider passing the
+widely recommended `'--user' flag`_ when invoking ``pip``.
+
+.. _Virtual environment: https://virtualenv.pypa.io/en/latest/
+.. _'--user' flag: https://packaging.python.org/tutorials/installing-packages/#installing-to-the-user-site
+
+.. code-block:: bash
+
+    $ python3 -m pip install 'molecule[docker]'

molecule/test1/converge.yml

@@ -0,0 +1,22 @@
+---
+- name: Converge
+  hosts: all
+  tasks:
+    - name: Install OpenHPC repository
+      yum:
+        name: "https://github.com/openhpc/ohpc/releases/download/v1.3.GA/ohpc-release-1.3-1.el7.x86_64.rpm"
+        state: present
+    - name: "Include ansible-role-openhpc"
+      include_role:
+        name: "ansible-role-openhpc/"
+      vars:
+        openhpc_enable:
+          control: "{{ inventory_hostname in groups['testohpc_login'] }}"
+          batch: "{{ inventory_hostname in groups['testohpc_compute'] }}"
+          runtime: true
+        openhpc_slurm_service_enabled: true
+        openhpc_slurm_control_host: "{{ groups['testohpc_login'] | first }}"
+        openhpc_slurm_partitions:
+          - name: "compute"
+        openhpc_cluster_name: testohpc
+

molecule/test1/molecule.yml

@@ -0,0 +1,48 @@
+---
+name: single partition, group is partition
+driver:
+  name: docker
+platforms:
+  - name: testohpc-login-0
+    image: docker.io/pycontribs/centos:7
+    pre_build_image: true
+    groups:
+      - testohpc_login
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    networks:
+      - name: net1
+  - name: testohpc-compute-0
+    image: docker.io/pycontribs/centos:7
+    pre_build_image: true
+    groups:
+      - testohpc_compute
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    networks:
+      - name: net1
+  - name: testohpc-compute-1
+    image: docker.io/pycontribs/centos:7
+    pre_build_image: true
+    groups:
+      - testohpc_compute
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    networks:
+      - name: net1
+provisioner:
+  name: ansible
+verifier:
+  name: ansible

molecule/test1/verify.yml

@@ -0,0 +1,12 @@
+---
+
+- name: Check slurm hostlist
+  hosts: testohpc_login
+  tasks:
+  - name: Get slurm partition info
+    command: sinfo -h
+    register: sinfo
+  - name: 
+    assert:                        # PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
+      that: "sinfo.stdout_lines == ['compute*     up 60-00:00:0      2   idle testohpc-compute-[0-1]']"
+      fail_msg: "FAILED - actual value: {{ sinfo.stdout_lines }}"

molecule/test1b/INSTALL.rst

@@ -0,0 +1,22 @@
+*******
+Docker driver installation guide
+*******
+
+Requirements
+============
+
+* Docker Engine
+
+Install
+=======
+
+Please refer to the `Virtual environment`_ documentation for installation best
+practices. If not using a virtual environment, please consider passing the
+widely recommended `'--user' flag`_ when invoking ``pip``.
+
+.. _Virtual environment: https://virtualenv.pypa.io/en/latest/
+.. _'--user' flag: https://packaging.python.org/tutorials/installing-packages/#installing-to-the-user-site
+
+.. code-block:: bash
+
+    $ python3 -m pip install 'molecule[docker]'

molecule/test1b/converge.yml

@@ -0,0 +1,22 @@
+---
+- name: Converge
+  hosts: all
+  tasks:
+    - name: Install OpenHPC repository
+      yum:
+        name: "https://github.com/openhpc/ohpc/releases/download/v1.3.GA/ohpc-release-1.3-1.el7.x86_64.rpm"
+        state: present
+    - name: "Include ansible-role-openhpc"
+      include_role:
+        name: "ansible-role-openhpc/"
+      vars:
+        openhpc_enable:
+          control: "{{ inventory_hostname in groups['testohpc_login'] }}"
+          batch: "{{ inventory_hostname in groups['testohpc_compute'] }}"
+          runtime: true
+        openhpc_slurm_service_enabled: true
+        openhpc_slurm_control_host: "{{ groups['testohpc_login'] | first }}"
+        openhpc_slurm_partitions:
+          - name: "compute"
+        openhpc_cluster_name: testohpc
+

molecule/test1b/molecule.yml

@@ -0,0 +1,37 @@
+---
+name: single partition, group is partition, single node
+dependency:
+  name: galaxy
+driver:
+  name: docker
+platforms:
+  - name: testohpc-login-0
+    image: docker.io/pycontribs/centos:7
+    pre_build_image: true
+    groups:
+      - testohpc_login
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    networks:
+      - name: net1
+  - name: testohpc-compute-0
+    image: docker.io/pycontribs/centos:7
+    pre_build_image: true
+    groups:
+      - testohpc_compute
+    command: /sbin/init
+    tmpfs:
+      - /run
+      - /tmp
+    volumes:
+      - /sys/fs/cgroup:/sys/fs/cgroup:ro
+    networks:
+      - name: net1
+provisioner:
+  name: ansible
+verifier:
+  name: ansible

molecule/test1b/verify.yml

@@ -0,0 +1,12 @@
+---
+
+- name: Check slurm hostlist
+  hosts: testohpc_login
+  tasks:
+  - name: Get slurm partition info
+    command: sinfo -h
+    register: sinfo
+  - name: 
+    assert:                        # PARTITION AVAIL  TIMELIMIT  NODES  STATE NODELIST
+      that: "sinfo.stdout_lines == ['compute*     up 60-00:00:0      1   idle testohpc-compute-0']"
+      fail_msg: "FAILED - actual value: {{ sinfo.stdout_lines }}"

molecule/test1c/INSTALL.rst

@@ -0,0 +1,22 @@
+*******
+Docker driver installation guide
+*******
+
+Requirements
+============
+
+* Docker Engine
+
+Install
+=======
+
+Please refer to the `Virtual environment`_ documentation for installation best
+practices. If not using a virtual environment, please consider passing the
+widely recommended `'--user' flag`_ when invoking ``pip``.
+
+.. _Virtual environment: https://virtualenv.pypa.io/en/latest/
+.. _'--user' flag: https://packaging.python.org/tutorials/installing-packages/#installing-to-the-user-site
+
+.. code-block:: bash
+
+    $ python3 -m pip install 'molecule[docker]'