Skip to content
GitLab
Explore
Sign in
Primary navigation
Search or go to…
Project
H
HPCasCode
Manage
Activity
Members
Labels
Plan
Issues
Issue boards
Milestones
Wiki
Code
Merge requests
Repository
Branches
Commits
Tags
Repository graph
Compare revisions
Deploy
Releases
Model registry
Operate
Environments
Monitor
Incidents
Analyze
Value stream analytics
Contributor analytics
Repository analytics
Model experiments
Help
Help
Support
GitLab documentation
Compare GitLab plans
Community forum
Contribute to GitLab
Provide feedback
Keyboard shortcuts
?
Snippets
Groups
Projects
Show more breadcrumbs
hpc-team
HPCasCode
Commits
aa77f62b
Commit
aa77f62b
authored
9 years ago
by
Chris Hines
Browse files
Options
Downloads
Patches
Plain Diff
fix up mellanox drivers and lustre-client for CentOS7
parent
7cdae5a0
No related branches found
Branches containing commit
No related tags found
1 merge request
!1
Master
Changes
2
Hide whitespace changes
Inline
Side-by-side
Showing
2 changed files
roles/lustre-client/tasks/main.yml
+16
-12
16 additions, 12 deletions
roles/lustre-client/tasks/main.yml
roles/mellanox_drivers/tasks/main.yml
+46
-11
46 additions, 11 deletions
roles/mellanox_drivers/tasks/main.yml
with
62 additions
and
23 deletions
roles/lustre-client/tasks/main.yml
+
16
−
12
View file @
aa77f62b
---
-
include_vars
:
"
{{
ansible_distribution
}}_{{
ansible_distirubtion_major_version
}}.yaml"
lustre_pkgs
:
-
lustre-client-modules-2.7.0-3.10.0_229.14.1.el7.x86_64.x86_64.rpm
-
lustre-client-2.7.0-3.10.0_229.14.1.el7.x86_64.x86_64.rpm
-
include_vars
:
"
{{
ansible_distribution
}}_{{
ansible_distribution_major_version
}}.yaml"
-
name
:
copy rpms
copy
:
dest=/tmp/ src={{ item }}
copy
:
dest=/tmp/ src=
lustre-install/
{{ item }}
with_items
:
{{
lustre_pkgs
}}
"
{{
lustre_pkgs
}}"
#- name: install rpms
# yum: name="/tmp/{{ item }}"
# sudo: true
# with_items: "{{ lustre_pkgs }}"
-
name
:
install rpms
yum
:
name=/tmp/lustre-client-modules-2.7.0-3.10.0_229.14.1.el7.x86_64.x86_64.rpm
sudo
:
true
-
name
:
install rpms
yum
:
name=
/tmp/
{{ item }}
yum
:
name=/tmp/
lustre-client-2.7.0-3.10.0_229.14.1.el7.x86_64.x86_64.rpm
sudo
:
true
with_tiems
:
{{
lustre_pkgs
}}
-
name
:
"
Mount
lustre
filesystems"
mount
:
name="{{ item.mntpt }}" src=
"{{ item.servers }}"/"{{ item.src }}" state="mounted" fstype="lustre" opts="_netdev,flock
0 0
"
mount
:
name="{{ item.mntpt }}" src="{{ item.servers }}"/"{{ item.src }}" state="mounted" fstype="lustre" opts="_netdev,flock"
sudo
:
true
with_
t
iems
:
{{
mntlist
}}
with_i
t
ems
:
"
{{
mntlist
}}
"
This diff is collapsed.
Click to expand it.
roles/mellanox_drivers/tasks/main.yml
+
46
−
11
View file @
aa77f62b
---
-
name
:
yum install dependencies
yum
:
name=perl,pciutils,gtk2,atk,cairo,gcc-gfortran,libxml2-python,tcsh,libnl,lsof,tcl,tk
sudo
:
true
ignore_errors
:
true
-
name
:
yum update to upgrade kernel
shell
:
"
yum
update
-y"
sudo
:
true
when
:
ansible_os_family=="RedHat" and ansible_distribution_major_version == "7"
#
# A REBOOT IS NEEDED AFTER a KERNEL UPDATE
#
-
name
:
restart machine
command
:
shutdown -r now "Ansible updates triggered"
async
:
0
shell
:
sleep 5; sudo
shutdown -r now "Ansible updates triggered"
async
:
2
poll
:
0
ignore_errors
:
true
sudo
:
true
-
name
:
waiting for server to come back
local_action
:
wait_for host={{ inventory_hostname }}
state=started
#local_action: wait_for host={{ ansible_host }} state=started port=22 delay=10 search_regex=OpenSSH
local_action
:
wait_for host={{ ansible_ssh_host }} state=started port=22 delay=10 search_regex=OpenSSH
sudo
:
false
-
name
:
waiting for server to come back number
2
local_action
:
wait_for host={{ ansible_ssh_host }} state=started port=22 delay=10 search_regex=OpenSSH
sudo
:
false
-
name
:
test for existing installation of drivers
...
...
@@ -17,25 +36,41 @@
ignore_errors
:
true
-
name
:
copy driver source
unarchive
:
copy=yes src=MLNX_OFED_LINUX-3.1-1.0.3-rhel7.1-x86_64-ext.tgz dest=/tmp
/MLNX_OFED_LINUX-3.1-1.0.3-rhel7.1-x86_64-ext
unarchive
:
copy=yes src=
files/
MLNX_OFED_LINUX-3.1-1.0.3-rhel7.1-x86_64-ext.tgz dest=/tmp
sudo
:
true
when
:
drivers_installed|failed and ansible_os_family=="RedHat" and ansible_distribution_major_version == "7"
-
name
:
install drivers
command
:
./mlnxofedinstall -q
shell
:
./mlnxofedinstall -q
args
:
path
:
/tmp/MLNX_OFED_LINUX-3.1-1.0.3-rhel7.1-x86_64-ext
chdir
:
/tmp/MLNX_OFED_LINUX-3.1-1.0.3-rhel7.1-x86_64-ext
sudo
:
true
when
:
drivers_installed
failed and ansible_distribution_major_version == "7"
when
:
drivers_installed
|
failed and ansible_distribution_major_version == "7"
#
# A REBOOT IS NEEDED AFTER SUCCESSFUL INSTALL
#
-
name
:
restart machine
command
:
sleep 5; sudo shutdown -r now "Ansible updates triggered"
async
:
2
poll
:
0
ignore_errors
:
true
sudo
:
true
-
name
:
waiting for server to come back
local_action
:
wait_for host={{ ansible_ssh_host }} state=started port=22 delay=10 search_regex=OpenSSH
sudo
:
false
-
name
:
waiting for server to come back
2
local_action
:
wait_for host={{ ansible_ssh_host }} state=started port=22 delay=10 search_regex=OpenSSH
sudo
:
false
-
name
:
get IP address
command
:
./scripts/map_ib_ip.pl {{ inventory_hostname }}
local_action
:
true
local_action
:
command ./scripts/map_ib_ip.pl {{ inventory_hostname }}
register
:
ip_address
-
name
:
template IP address
template
:
dest=/etc/sysconfig/network-scripts/ifcfg-ens6 s
ou
rc
e
=ifcfg-ens6.j2 owner=root group=root
template
:
dest=/etc/sysconfig/network-scripts/ifcfg-ens6 src=ifcfg-ens6.j2 owner=root group=root
sudo
:
true
when
:
ansible_distribution_major_version == "7"
...
...
This diff is collapsed.
Click to expand it.
Preview
0%
Loading
Try again
or
attach a new file
.
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Save comment
Cancel
Please
register
or
sign in
to comment