ansible/base.yml

@@ -3,4 +3,5 @@
   hosts: default
   become: true
   roles:
+    - { name: 'fix_centos_repo', tags: 'fix_centos_repo' }
     - { name: 'install_packages', tags: 'install_packages' }

ansible/cheaha.yml

----
-- name: Setup node for use as a virtual cheaha node
-  hosts: default
-  become: true
-  roles:
-    - { name: 'cheaha.node', tags: 'cheaha.node' }
-    - { name: 'nfs_mounts', tags: 'nfs_mounts' }
-    - { name: 'ldap_config', tags: 'ldap_config' }
-    - { name: 'slurm_client', tags: 'slurm_client' }

ansible/cluster.yml

+---
+- name: Setup node for use as a virtual cheaha node
+  hosts: all
+  become: true
+  roles:
+    - { name: 'cheaha.node', tags: 'cheaha.node' }
+    - { name: 'nfs_mounts', tags: 'nfs_mounts', when: enable_nfs_mounts }
+    - { name: 'ldap_config', tags: 'ldap_config' }
+    - { name: 'slurm_client', tags: 'slurm_client', when: enable_slurm_client }
+    - { name: 'ssh_host_keys', tags: 'ssh_host_keys' }
+    - { name: 'ssh_proxy_config', tags: 'ssh_proxy_config', when: enable_ssh_proxy_config }
+    - { name: 'ssl_cert', tags: 'ssl_cert', when: enable_ssl_certs }
+    - { name: 'rsyslog_config', tags: 'rsyslog_config', when: enable_rsyslog_config }
+    - { name: 'rewrite_map', tags: 'rewrite_map', when: enable_rewrite_map }
+    - { name: 'fail2ban', tags: 'fail2ban', when: enable_fail2ban }
+    - { name: 'install_node_exporter', tags: 'install_node_exporter', when: enable_node_exporter }

ansible/gpu.yml

@@ -3,6 +3,7 @@
   hosts: default
   become: true
   roles:
+    - { name: 'fix_centos_repo', tags: 'fix_centos_repo' }
     - { name: 'install_packages', tags: 'install_packages' }
     - { name: 'cuda_driver', tags: 'cuda_driver' }
     - { name: 'pam_slurm_adopt', tags: 'pam_slurm_adopt' }

ansible/group_vars/all

@@ -4,9 +4,88 @@
   yum_repo_files: []
   pkg_list: []
   slurm_version: 18.08.9
-  
+  enable_slurm_client: false
+
 # NHC related
   nhc_download_url: "https://github.com/mej/nhc/releases/download/1.4.3/lbnl-nhc-1.4.3-1.el7.noarch.rpm"
   nhc_download_path: "/tmp"
   nhc_git_repo: "https://gitlab.rc.uab.edu/rc/nhc.git"
   nhc_git_repo_path: "/tmp/nhc"
+
+  root_ssh_key: ""
+
+# cheaha.node related
+  hostname_lookup_table:
+    - "10.141.255.254 master.cm.cluster master localmaster.cm.cluster localmaster ldapserver.cm.cluster ldapserver"
+  domain_search_list:
+    - openstack.internal
+    - cm.cluster
+  nameserver_list:
+    - 10.141.255.254
+
+# ldap_config related
+  ldap_cert_path: "/etc/openldap/certs"
+  ldap_uri: "ldap://ldapserver"
+
+# nfs_mounts related
+  enable_nfs_mounts: true
+  use_autofs: false
+  use_fstab: false
+  mount_points:
+    - { "src": "master:/gpfs4", "path": "/gpfs4", "opts": "ro,sync,hard", "mode": "0755" }
+    - { "src": "master:/gpfs5", "path": "/gpfs5", "opts": "ro,sync,hard", "mode": "0755" }
+  autofs_mounts:
+    - { "src": "master:/gpfs4/&", "path": "/gpfs4", "opts": "fstype=nfs,vers=3,_netdev,default", "mode": '0755', "mount_point": "/gpfs4", "map_name": "gpfs4", key: "*" }
+    - { "src": "master:/gpfs5/&", "path": "/gpfs5", "opts": "fstype=nfs,vers=3,_netdev,default", "mode": '0755', "mount_point": "/gpfs5", "map_name": "gpfs5", key: "*" }
+
+#SSH Host Keys
+  S3_ENDPOINT: ""
+  SSH_HOST_KEYS_S3_BUCKET: ""
+  SSH_HOST_KEYS_S3_OBJECT: ""
+
+# AWS credentials
+  LTS_ACCESS_KEY: ""
+  LTS_SECRET_KEY: ""
+
+# ssh proxy
+  enable_ssh_proxy_config: false
+  sshpiper_dest_dir: "/opt/sshpiper"
+
+# rsyslog
+  enable_rsyslog_config: true
+  rsyslog_target: "*.* @master:514"
+
+# ssl certs
+  enable_ssl_certs: false
+  ssl_cert_s3_bucket: ""
+  ssl_cert_key_location: "/etc/pki/tls/private"
+  ssl_cert_file_location: "/etc/pki/tls/certs"
+  ssl_cert_key: ""
+  ssl_cert_file: ""
+  ssl_cert_chain_file: ""
+  ssl_apache_config: ""
+  apache_service: "httpd"
+
+# rewrite map
+  enable_rewrite_map: false
+  target_groups:
+    - {"name": "gpfs4", "host": "login001", "default": True }
+    - {"name": "gpfs5", "host": "login002", "default": False }
+
+# account app
+  account_app_port: 8000
+
+# fail2ban
+  enable_fail2ban: false
+  maxretry: 1
+  findtime: 600
+  bantime: 1200
+  fail2ban_white_list: "127.0.0.1/8"
+
+# Node Exporter
+  enable_node_exporter: false
+  node_exporter_ver: "1.8.2"
+  node_exporter_filename: "node_exporter-{{ node_exporter_ver }}.linux-amd64"
+  node_exporter_user: node_exporter
+  node_exporter_group: node_exporter
+  node_exporter_port: 9100

ansible/group_vars/prod

+---
+  # cheaha.node related
+  hostname_lookup_table:
+    - "172.20.0.24 cheaha-master02.cm.cluster cheaha-master02"
+    - "172.20.0.22 cheaha-master01.cm.cluster cheaha-master01"
+    - "172.20.0.25 master.cm.cluster master localmaster.cm.cluster localmaster ldapserver.cm.cluster ldapserver"
+  domain_search_list:
+    - cm.cluster
+    - rc.uab.edu
+    - ib.cluster
+    - drac.cluster
+    - eth.cluster
+    - ib-hdr.cluster
+  nameserver_list:
+    - 172.20.0.25
+
+  bright_openldap_path: "/cm/local/apps/openldap"
+  ldap_cert_path: "{{bright_openldap_path}}/etc/certs"
+  ldap_uri: "ldaps://ldapserver"
+
+  # proxy_config
+  target_groups:
+    - {"name": "gpfs5", "host": "login002", "default": False, "authorized_keys":"/gpfs5/data/user/home/$DOWNSTREAM_USER/.ssh/authorized_keys", "private_key":"/gpfs5/data/user/home/$DOWNSTREAM_USER/.ssh/id_ecdsa"}
+    - {"name": "gpfs4", "host": "login001", "default": True, "authorized_keys":"/gpfs4/data/user/home/$DOWNSTREAM_USER/.ssh/authorized_keys", "private_key":"/gpfs4/data/user/home/$DOWNSTREAM_USER/.ssh/id_ecdsa"}

ansible/compute.yml → ansible/login.yml

@@ -3,9 +3,7 @@
   hosts: default
   become: true
   roles:
+    - { name: 'fix_centos_repo', tags: 'fix_centos_repo' }
     - { name: 'install_packages', tags: 'install_packages' }
-    - { name: 'pam_slurm_adopt', tags: 'pam_slurm_adopt' }
     - { name: 'install_nhc', tags: 'install_nhc'}
 
-- name: Setup node for use as a virtual cheaha node
-  ansible.builtin.import_playbook: cheaha.yml

ansible/ood.yml

@@ -3,8 +3,6 @@
   hosts: default
   become: true
   roles:
+    - { name: 'fix_centos_repo', tags: 'fix_centos_repo' }
     - { name: 'install_packages', tags: 'install_packages' }
     - { name: 'install_zsh', tags: 'install_zsh' }
-
-- name: Setup node for use as a virtual cheaha node
-  ansible.builtin.import_playbook: cheaha.yml

ansible/roles/cheaha.node/tasks/main.yml

@@ -4,15 +4,24 @@
     path: /etc/hosts
     line: "{{ item }}"
   loop:
-    - "172.20.0.24 cheaha-master02.cm.cluster cheaha-master02"
-    - "172.20.0.22 cheaha-master01.cm.cluster cheaha-master01"
-    - "172.20.0.25 master.cm.cluster master localmaster.cm.cluster localmaster ldapserver.cm.cluster ldapserver"
+    "{{ hostname_lookup_table }}"
 
 - name: Add proper DNS search to lookup other nodes on the cluster
   ansible.builtin.lineinfile:
     path: /etc/dhcp/dhclient.conf
     insertbefore: BOF
     line: 'append domain-name " cm.cluster rc.uab.edu ib.cluster drac.cluster eth.cluster ib-hdr.cluster";'
+    create: true
+    state: present
+
+- name: Template resolv.conf
+  ansible.builtin.template:
+    src: resolv.conf.j2
+    dest: /etc/resolv.conf
+    owner: root
+    group: root
+    mode: 0644
+    backup: true
 
 - name: Disable SELinux
   ansible.posix.selinux:
@@ -25,6 +34,7 @@
     owner: root
     group: root
     mode: 0644
+  when: "'cm.repo' in yum_repo_files"
 
 - name: Add ssh key for root access
   ansible.posix.authorized_key:
@@ -35,3 +45,7 @@
 - name: Set timezone to America/Chicago
   community.general.timezone:
     name: America/Chicago
+  retries: 3
+  delay: 3
+  register: result
+  until: not result.failed

ansible/roles/cheaha.node/templates/resolv.conf.j2

+search {{ domain_search_list | join(' ') }}
+{% for name_server in nameserver_list %}
+nameserver {{ name_server }}
+{% endfor %}

ansible/roles/fail2ban/tasks/main.yml

+---
+
+- name: Install fail2ban
+  ansible.builtin.package:
+    name: "{{ item }}"
+    state: present
+  loop:
+    - fail2ban
+    - fail2ban-firewalld
+
+- name: Configure fail2ban
+  ansible.builtin.template:
+    src: "{{ item.src }}"
+    dest: "{{ item.dest }}"
+    backup: true
+  loop:
+    - { src: 'jail.local.j2', dest: '/etc/fail2ban/jail.local' }
+    - { src: 'sshpiperd_filter.local.j2', dest: '/etc/fail2ban/filter.d/sshpiperd.local' }
+    - { src: 'sshpiperd_jail.local.j2', dest: '/etc/fail2ban/jail.d/sshpiperd.local' }
+
+- name: Activate the firewalld support for fail2ban
+  ansible.builtin.command:
+    cmd: mv /etc/fail2ban/jail.d/00-firewalld.conf /etc/fail2ban/jail.d/00-firewalld.local
+
+- name: Configure firewalld to allow ssh and sshpiper traffic
+  ansible.posix.firewalld:
+    port: "{{ item }}"
+    zone: public
+    state: enabled
+    permanent: true
+  loop:
+    - 2222/tcp
+    - 22/tcp
+
+- name: Enable and start firewalld
+  ansible.builtin.service:
+    name: firewalld
+    enabled: true
+    state: restarted
+
+- name: Enable and start fail2ban
+  ansible.builtin.service:
+    name: fail2ban
+    enabled: true
+    state: restarted
+

ansible/roles/fail2ban/templates/jail.local.j2

+[DEFAULT]
+banaction = firewalld
+bantime  = {{ bantime }}
+ignoreip = {{ fail2ban_white_list }}
+
+[sshd]
+enabled = true

ansible/roles/fail2ban/templates/sshpiperd_filter.local.j2

+# Refer to https://github.com/fail2ban/fail2ban/wiki/Developing-Regex-in-Fail2ban for developing regex using fail2ban
+#
+[INCLUDES]
+before = common.conf
+
+[DEFAULT]
+_daemon = sshpiperd
+__iso_datetime = "\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}(?:[+-]\d{2}:\d{2}|Z)"
+__pref = time=%(__iso_datetime)s level=(?:debug|error)
+
+[Definition]
+# Define the prefix regex for the log lines
+prefregex = ^<F-MLFID>%(__prefix_line)s%(__pref)s</F-MLFID>\s+<F-CONTENT>.+</F-CONTENT>$
+
+# Failregex to match the specific failure log lines (prefregex is automatically included)
+failregex = ^msg="connection from .*failtoban: ip <HOST> too auth many failures"$
+
+ignoreregex =
+
+mode = normal
+
+maxlines = 1

ansible/roles/fail2ban/templates/sshpiperd_jail.local.j2

+# This configuration will block the remote host after {{maxretry}} failed SSH login attempts.
+[sshpiperd]
+enabled  = true
+filter   = sshpiperd
+logpath  = /var/log/messages
+port     = 22
+maxretry = {{ maxretry }}
+backend  = auto
+findtime = {{ findtime }}

ansible/roles/fix_centos_repo/tasks/main.yaml

+---
+- name: Get CentOS repo files
+  shell: ls /etc/yum.repos.d/CentOS-*
+  register: repo_files
+
+- name: Remove mirrorlist from CentOS repo files
+  ansible.builtin.replace:
+    path: "{{ item }}"
+    regexp: '^mirrorlist'
+    replace: '#mirrorlist'
+    backup: yes
+  with_items: "{{ repo_files.stdout_lines }}"
+
+- name: Use vault baseurl to CentOS repo files
+  ansible.builtin.replace:
+    path: "{{ item }}"
+    regexp: '^#baseurl=http://mirror.centos.org'
+    replace: 'baseurl=http://vault.centos.org'
+    backup: yes
+  with_items: "{{ repo_files.stdout_lines }}"

ansible/roles/install_node_exporter/tasks/main.yaml

+---
+- name: Download node_exporter binary
+  ansible.builtin.get_url:
+    url: "https://github.com/prometheus/node_exporter/releases/download/v{{ node_exporter_ver }}/{{ node_exporter_filename }}.tar.gz"
+    dest: "/tmp/{{ node_exporter_filename }}.tar.gz"
+
+- name: Extract node_exporter
+  ansible.builtin.unarchive:
+    src: "/tmp/{{ node_exporter_filename }}.tar.gz"
+    dest: "/tmp"
+    remote_src: yes
+
+- name: Create system group for user account {{ node_exporter_group }}
+  ansible.builtin.group:
+    name: "{{ node_exporter_group }}"
+    system: true
+    state: present
+
+- name: Create system user account {{ node_exporter_user }}
+  ansible.builtin.user:
+    name: "{{ node_exporter_user }}"
+    comment: Prometheus node_exporter system account
+    group: "{{ node_exporter_group }}"
+    system: true
+    home: /var/lib/node_exporter
+    create_home: false
+    shell: /sbin/nologin
+    state: present
+
+- name: Copy node_exporter binary
+  ansible.builtin.copy:
+    src: "/tmp/{{ node_exporter_filename }}/node_exporter"
+    dest: /usr/local/bin/node_exporter
+    remote_src: yes
+    owner: root
+    group: root
+    mode: 0755
+
+- name: Copy systemd unit file
+  ansible.builtin.template:
+    src: node_exporter.service.j2
+    dest: /etc/systemd/system/node_exporter.service
+    owner: root
+    group: root
+    mode: '0644'
+
+- name: Clean up /tmp
+  ansible.builtin.file:
+    path: "/tmp/{{ item }}"
+    state: absent
+  loop:
+    - "{{ node_exporter_filename }}.tar.gz"
+    - "{{ node_exporter_filename }}"
+
+- name: Restart node_exporter service
+  ansible.builtin.systemd:
+    daemon_reload: yes
+    name: node_exporter
+    state: restarted
+    enabled: true
+
+- name: Collect facts about system services
+  ansible.builtin.service_facts:
+
+- name: Configure firewalld to allow prometheus
+  ansible.posix.firewalld:
+    port: "{{ node_exporter_port }}/tcp"
+    zone: public
+    state: enabled
+    permanent: true
+  when:
+    - "'firewalld.service' in ansible_facts.services"
+    - ansible_facts.services["firewalld.service"].state == "running"
+
+- name: Enable and start firewalld
+  ansible.builtin.service:
+    name: firewalld
+    enabled: true
+    state: restarted
+  when:
+    - "'firewalld.service' in ansible_facts.services"
+    - ansible_facts.services["firewalld.service"].state == "running"

ansible/roles/install_node_exporter/templates/node_exporter.service.j2

+[Unit]
+Description=Node Exporter
+After=network.target
+
+[Service]
+User={{ node_exporter_user }}
+Group={{ node_exporter_group }}
+Type=simple
+ExecStart=/usr/local/bin/node_exporter --web.listen-address=:{{ node_exporter_port }} --collector.filesystem.mount-points-exclude "^/(dev|proc|run/user/.+|run/credentials/.+|sys|var/lib/docker/.+)($|/)" --collector.filesystem.fs-types-exclude "^(autofs|binfmt_misc|bpf|cgroup|tmpfs|sunrpc|cgroup2?|configfs|debugfs|devpts|devtmpfs|fusectl|hugetlbfs|iso9660|mqueue|nsfs|overlay|proc|procfs|pstore|rpc_pipefs|securityfs|selinuxfs|squashfs|sysfs|tracefs)$"
+
+[Install]
+WantedBy=multi-user.target

ansible/roles/ldap_config/tasks/main.yml

@@ -25,7 +25,7 @@
 - name: Copy ldap cert(s) into place
   ansible.builtin.copy:
     src: "{{ item.src }}"
-    dest: "/cm/local/apps/openldap/etc/certs/{{ item.src }}"
+    dest: "{{ ldap_cert_path }}/{{ item.src }}"
     owner: ldap
     group: ldap
     mode: 0440
@@ -33,10 +33,11 @@
     - { src: ca.pem }
     - { src: ldap.key }
     - { src: ldap.pem }
+  when: ldap_uri | regex_search('^ldaps://')
 
 - name: Copy ldap config into place
-  ansible.builtin.copy:
-    src: nslcd.conf
+  ansible.builtin.template:
+    src: nslcd.conf.j2
     dest: /etc/nslcd.conf
     owner: root
     group: root
@@ -46,5 +47,6 @@
   ansible.builtin.service:
     name: "{{ item }}"
     enabled: yes
+    state: restarted
   loop:
     - nslcd

ansible/roles/ldap_config/templates/nslcd.conf.j2

+# This is the configuration file for the LDAP nameservice
+# switch library's nslcd daemon. It configures the mapping
+# between NSS names (see /etc/nsswitch.conf) and LDAP
+# information in the directory.
+# See the manual page nslcd.conf(5) for more information.
+
+# The user and group nslcd should run as.
+uid nslcd
+gid ldap
+
+# The uri pointing to the LDAP server to use for name lookups.
+# Multiple entries may be specified. The address that is used
+# here should be resolvable without using LDAP (obviously).
+#uri ldap://127.0.0.1/
+#uri ldaps://127.0.0.1/
+#uri ldapi://%2fvar%2frun%2fldapi_sock/
+# Note: %2f encodes the '/' used as directory separator
+uri {{ ldap_uri }}
+
+# The LDAP version to use (defaults to 3
+# if supported by client library)
+#ldap_version 3
+
+# The distinguished name of the search base.
+base dc=cm,dc=cluster
+
+# The distinguished name to bind to the server with.
+# Optional: default is to bind anonymously.
+#binddn cn=proxyuser,dc=example,dc=com
+
+# The credentials to bind with.
+# Optional: default is no credentials.
+# Note that if you set a bindpw you should check the permissions of this file.
+#bindpw secret
+
+# The distinguished name to perform password modifications by root by.
+#rootpwmoddn cn=admin,dc=example,dc=com
+
+# The default search scope.
+#scope sub
+#scope one
+#scope base
+
+# Customize certain database lookups.
+#base   group  ou=Groups,dc=example,dc=com
+#base   passwd ou=People,dc=example,dc=com
+#base   shadow ou=People,dc=example,dc=com
+#scope  group  onelevel
+#scope  hosts  sub
+
+# Bind/connect timelimit.
+#bind_timelimit 30
+
+# Search timelimit.
+#timelimit 30
+
+# Idle timelimit. nslcd will close connections if the
+# server has not been contacted for the number of seconds.
+idle_timelimit 240
+
+# Use StartTLS without verifying the server certificate.
+#ssl start_tls
+#tls_reqcert never
+
+{% if ldap_uri | regex_search('^ldaps://') %}
+ssl on
+tls_reqcert demand
+
+# CA certificates for server certificate verification
+#tls_cacertdir /etc/ssl/certs
+tls_cacertfile /cm/local/apps/openldap/etc/certs/ca.pem
+tls_cert /cm/local/apps/openldap/etc/certs/ldap.pem
+tls_key /cm/local/apps/openldap/etc/certs/ldap.key
+{% endif %}
+
+# Seed the PRNG if /dev/urandom is not provided
+#tls_randfile /var/run/egd-pool
+
+# SSL cipher suite
+# See man ciphers for syntax
+#tls_ciphers TLSv1
+
+# Client certificate and key
+# Use these, if your server requires client authentication.
+
+# Mappings for Services for UNIX 3.5
+#filter passwd (objectClass=User)
+#map    passwd uid              msSFU30Name
+#map    passwd userPassword     msSFU30Password
+#map    passwd homeDirectory    msSFU30HomeDirectory
+#map    passwd homeDirectory    msSFUHomeDirectory
+#filter shadow (objectClass=User)
+#map    shadow uid              msSFU30Name
+#map    shadow userPassword     msSFU30Password
+#filter group  (objectClass=Group)
+#map    group  member           msSFU30PosixMember
+
+# Mappings for Services for UNIX 2.0
+#filter passwd (objectClass=User)
+#map    passwd uid              msSFUName
+#map    passwd userPassword     msSFUPassword
+#map    passwd homeDirectory    msSFUHomeDirectory
+#map    passwd gecos            msSFUName
+#filter shadow (objectClass=User)
+#map    shadow uid              msSFUName
+#map    shadow userPassword     msSFUPassword
+#map    shadow shadowLastChange pwdLastSet
+#filter group  (objectClass=Group)
+#map    group  member           posixMember
+
+# Mappings for Active Directory
+#pagesize 1000
+#referrals off
+#idle_timelimit 800
+#filter passwd (&(objectClass=user)(!(objectClass=computer))(uidNumber=*)(unixHomeDirectory=*))
+#map    passwd uid              sAMAccountName
+#map    passwd homeDirectory    unixHomeDirectory
+#map    passwd gecos            displayName
+#filter shadow (&(objectClass=user)(!(objectClass=computer))(uidNumber=*)(unixHomeDirectory=*))
+#map    shadow uid              sAMAccountName
+#map    shadow shadowLastChange pwdLastSet
+#filter group  (objectClass=group)
+
+# Alternative mappings for Active Directory
+# (replace the SIDs in the objectSid mappings with the value for your domain)
+#pagesize 1000
+#referrals off
+#idle_timelimit 800
+#filter passwd (&(objectClass=user)(objectClass=person)(!(objectClass=computer)))
+#map    passwd uid           cn
+#map    passwd uidNumber     objectSid:S-1-5-21-3623811015-3361044348-30300820
+#map    passwd gidNumber     objectSid:S-1-5-21-3623811015-3361044348-30300820
+#map    passwd homeDirectory "/home/$cn"
+#map    passwd gecos         displayName
+#map    passwd loginShell    "/bin/bash"
+#filter group (|(objectClass=group)(objectClass=person))
+#map    group gidNumber      objectSid:S-1-5-21-3623811015-3361044348-30300820
+
+# Mappings for AIX SecureWay
+#filter passwd (objectClass=aixAccount)
+#map    passwd uid              userName
+#map    passwd userPassword     passwordChar
+#map    passwd uidNumber        uid
+#map    passwd gidNumber        gid
+#filter group  (objectClass=aixAccessGroup)
+#map    group  cn               groupName
+#map    group  gidNumber        gid
+# This comment prevents repeated auto-migration of settings.