Skip to content
Snippets Groups Projects
Commit 7d5bf803 authored by Simon Michnowicz's avatar Simon Michnowicz
Browse files

Merge branch 'master' of...

Merge branch 'master' of gitlab.erc.monash.edu.au:hpc-team/ansible_cluster_in_a_box into fixSemaphoreCount


Former-commit-id: 8ad9fee0
parents cd717c44 aeb47f5d
No related branches found
No related tags found
No related merge requests found
# Place this file in your /etc/yum.repos.d/ directory
[epel]
name=Extra Packages for Enterprise Linux 7 - $basearch
baseurl=https://consistency0/epel/$releasever/$basearch/
enabled=0
gpgcheck=0
sslverify=false
......@@ -35,13 +35,14 @@
with_items:
- monashhpc_base.repo
- monashhpc_others.repo
- epel.repo
- name: get enabled repos
#shell: yum repolist | grep -v "repo id" | grep -v "Loaded plugins" | head -n -1 | cut -f 1 -d '/' | sed -s 's/\!//'
shell: yum repolist all | grep enabled | cut -f 1 -d '/' | sed -s 's/\!//'
register: repolist
check_mode: no
args:
args:
warn: False
- name: disable unwanted repos
......
- name: Add ec2-user to systems group locally
user:
name: ec2-user
groups: systems
append: yes
become: true
become_user: root
......@@ -13,6 +13,7 @@
- libX11-common
- libX11-devel
- libX11
- libglvnd-devel
- xorg-x11-server-common
- xorg-x11-util-macros
- xorg-x11-server-utils
......
#%PAM-1.0
# This file is auto-generated.
# User changes will be destroyed the next time authconfig is run.
auth required pam_env.so
auth required pam_faildelay.so delay=2000000
auth sufficient pam_unix.so nullok try_first_pass
auth requisite pam_succeed_if.so uid >= 500 quiet
auth sufficient pam_sss.so use_first_pass
auth required pam_deny.so
account required pam_unix.so broken_shadow
account sufficient pam_localuser.so
account sufficient pam_succeed_if.so uid < 500 quiet
account [default=bad success=ok user_unknown=ignore] pam_sss.so
account required pam_permit.so
password requisite pam_cracklib.so try_first_pass retry=3
password sufficient pam_unix.so md5 shadow nullok try_first_pass use_authtok
password requisite pam_pwquality.so try_first_pass local_users_only retry=3 authtok_type=
password sufficient pam_unix.so sha512 shadow nullok try_first_pass use_authtok
password sufficient pam_sss.so use_authtok
password required pam_deny.so
......@@ -21,4 +24,4 @@ session optional pam_keyinit.so revoke
session required pam_limits.so
session [success=1 default=ignore] pam_succeed_if.so service in crond quiet use_uid
session required pam_unix.so
session optional pam_sss.so
session optional pam_sss.so
\ No newline at end of file
......@@ -53,7 +53,7 @@
set_fact:
install_now: true
reboot_now: true
when: driver_version is failed or not desired_driver_version.stdout in driver_version.stdout
when: driver_version | failed or not desired_driver_version.stdout in driver_version.stdout
- name: debug - print out value of install_now
debug: var=install_now
......@@ -65,7 +65,7 @@
when: install_now
- name: install drivers
shell: ./mlnxofedinstall -q --add-kernel-support --force
shell: ./mlnxofedinstall -q --add-kernel-support --force --skip-repo
args:
#more changes
chdir: "/tmp/{{ MELLANOX_DRIVER_SRC }}"
......@@ -87,9 +87,9 @@
register: reload_service
- name: enable roce_mode setting
service: name=roce_mode state=started enabled=True
service: name=roce_mode state=started enabled=yes
become: true
ignore_errors: yes
#
# A REBOOT IS NEEDED AFTER SUCCESSFUL INSTALL
#
......
---
#note. do not add '.tgz' to driver src. done in playbook
#MELLANOX_DRIVER_SRC: "{% if ansible_os_family == 'RedHat' %}MLNX_OFED_LINUX-3.1-1.0.3-rhel7.1-x86_64-ext{% elif ansible_os_family == 'Debian' %}MLNX_OFED_LINUX-3.1-1.0.3-ubuntu14.04-x86_64{% endif %}"
#MELLANOX_DRIVER_SRC: "{% if ansible_os_family == 'RedHat' %}MLNX_OFED_LINUX-3.1-1.0.3-rhel7.2-x86_64-ext{% elif ansible_os_family == 'Debian' %}MLNX_OFED_LINUX-3.1-1.0.3-ubuntu14.04-x86_64{% endif %}"
#MELLANOX_DRIVER_SRC: "{% if ansible_os_family == 'RedHat' %}MLNX_OFED_LINUX-3.4-1.0.0.0-rhel7.2-x86_64{% elif ansible_os_family == 'Debian' %}MLNX_OFED_LINUX-3.1-1.0.3-ubuntu14.04-x86_64{% endif %}"
# MELLANOX_DRIVER_SRC: "{% if ansible_os_family == 'RedHat' %}MLNX_OFED_LINUX-4.2-1.2.0.0-rhel7.4-x86_64{% elif ansible_os_family == 'Debian' %}MLNX_OFED_LINUX-3.1-1.0.3-ubuntu14.04-x86_64{% endif %}"
MELLANOX_DRIVER_SRC: "{% if ansible_os_family == 'RedHat' %}MLNX_OFED_LINUX-4.4-1.0.0.0-rhel7.4-x86_64{% elif ansible_os_family == 'Debian' %}MLNX_OFED_LINUX-3.1-1.0.3-ubuntu14.04-x86_64{% endif %}"
#MELLANOX_DRIVER_SRC: "{% if ansible_os_family == 'RedHat' %}MLNX_OFED_LINUX-4.4-1.0.0.0-rhel7.4-x86_64{% elif ansible_os_family == 'Debian' %}MLNX_OFED_LINUX-3.1-1.0.3-ubuntu14.04-x86_64{% endif %}"
MELLANOX_DRIVER_SRC: "{% if ansible_os_family == 'RedHat' %}MLNX_OFED_LINUX-4.5-1.0.1.0-rhel7.6-x86_64{% elif ansible_os_family == 'Debian' %}MLNX_OFED_LINUX-3.1-1.0.3-ubuntu14.04-x86_64{% endif %}"
......@@ -22,6 +22,7 @@ COMMIT
:INPUT ACCEPT [0:0]
:FORWARD ACCEPT [0:0]
:OUTPUT ACCEPT [0:0]
-A INPUT -s {{ PRIVATE_NETWORK_CIDR }} -j ACCEPT
-A INPUT -m state --state RELATED,ESTABLISHED -j ACCEPT
-A INPUT -p icmp -j ACCEPT
-A INPUT -i lo -j ACCEPT
......
---
slurm_use_vpn: False
slurmctlddebug: {level: 9, log: '/var/log/slurm/slurmctld.log'}
slurmddebug: {level: 9, log: '/var/log/slurm/slurmd.log'}
slurmschedlog: {level: 9, log: '/var/log/slurm/slurmsched.log'}
slurmdbdlog: {level: 9, log: '/var/log/slurm/slurmdbd.log'}
slurmddebug: {level: 5, log: '/var/log/slurm/slurmd.log'}
slurmctlddebug: {level: 5, log: '/mnt/slurm-logs/slurmctld.log'}
slurmdbdlog: {level: 5, log: '/mnt/slurm-logs/slurmdbd.log'}
slurmfairshare: {def: false, val: 10000}
slurmdatadir: "/var/spool/slurm"
slurmselecttype: "select/linear"
......
---
- name: make sure slurmctld and slurmdb log dir exists
file: dest=/mnt/slurm-logs state=directory owner=root group=root mode=755
sudo: true
- name: make sure slurm conf dir exists
file: dest={{ slurm_dir }}/etc state=directory
sudo: true
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment