Skip to content

Commit d38cf10

Browse files
authored
Merge pull request #3841 from VrindaMarwah/pub/ib_support
Installation of DOCA-OFED with Static IP Assignment
2 parents 6f17b12 + 2a86f1c commit d38cf10

15 files changed

+184
-11
lines changed

discovery/roles/configure_ochami/templates/cloud_init/ci-group-login_compiler_node_aarch64.yaml.j2

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,12 @@
2929
content: |
3030
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
3131

32+
- path: /usr/local/bin/configure-ib-network.sh
33+
owner: root:root
34+
permissions: '{{ file_mode_755 }}'
35+
content: |
36+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
37+
3238
- path: /usr/local/bin/set-ssh.sh
3339
permissions: '0755'
3440
content: |
@@ -180,19 +186,24 @@
180186
{{ lookup('template', 'templates/slurm/check_slurm_controller_status.sh.j2') | indent(12) }}
181187

182188
runcmd:
183-
- bash /usr/local/bin/doca-install.sh
184189
- /usr/local/bin/set-ssh.sh
185190
- /usr/local/bin/install_cuda_toolkit.sh
186191

187-
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /var/log/track
192+
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /var/log/track /var/lib/packages
188193
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/log/slurm /var/log/slurm nfs defaults,_netdev 0 0" >> /etc/fstab
189194
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
190195
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/slurm/epilog.d /etc/slurm/epilog.d nfs defaults,_netdev 0 0" >> /etc/fstab
191196
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
192197
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/munge /etc/munge nfs defaults,_netdev 0 0" >> /etc/fstab
193198
- echo "{{ trackfile_nfs_path }} /var/log/track nfs defaults,_netdev 0 0" >> /etc/fstab
199+
- echo "{{ cloud_init_nfs_path }}/cert /cert nfs defaults,_netdev 0 0" >> /etc/fstab
200+
- echo "{{ cloud_init_nfs_path }}/packages /var/lib/packages nfs defaults,_netdev 0 0" >> /etc/fstab
194201
- chmod {{ file_mode }} /etc/fstab
195202
- mount -a
203+
- cp /cert/pulp_webserver.crt /etc/pki/ca-trust/source/anchors && update-ca-trust
204+
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
205+
- bash /usr/local/bin/doca-install.sh
206+
- bash /usr/local/bin/configure-ib-network.sh
196207
- yes | cp /etc/slurm/epilog.d/slurmd.service /usr/lib/systemd/system/
197208
- /usr/local/bin/check_slurm_controller_status.sh
198209
- chown -R {{ slurm_user }}:{{ slurm_user }} /var/log/slurm

discovery/roles/configure_ochami/templates/cloud_init/ci-group-login_compiler_node_x86_64.yaml.j2

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -29,6 +29,12 @@
2929
content: |
3030
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
3131

32+
- path: /usr/local/bin/configure-ib-network.sh
33+
owner: root:root
34+
permissions: '{{ file_mode_755 }}'
35+
content: |
36+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
37+
3238
- path: /usr/local/bin/set-ssh.sh
3339
permissions: '0755'
3440
content: |
@@ -182,20 +188,25 @@
182188
{{ lookup('template', 'templates/slurm/check_slurm_controller_status.sh.j2') | indent(12) }}
183189

184190
runcmd:
185-
- bash /usr/local/bin/doca-install.sh
186191
- /usr/local/bin/set-ssh.sh
187192
- /usr/local/bin/install_cuda_toolkit.sh
188193

189-
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /cert /var/log/track
194+
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /cert /var/log/track /var/lib/packages
190195
- echo "{{ cloud_init_nfs_path }}/cert /cert nfs defaults,_netdev 0 0" >> /etc/fstab
191196
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/log/slurm /var/log/slurm nfs defaults,_netdev 0 0" >> /etc/fstab
192197
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
193198
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/slurm/epilog.d /etc/slurm/epilog.d nfs defaults,_netdev 0 0" >> /etc/fstab
194199
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
195200
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/munge /etc/munge nfs defaults,_netdev 0 0" >> /etc/fstab
196201
- echo "{{ trackfile_nfs_path }} /var/log/track nfs defaults,_netdev 0 0" >> /etc/fstab
202+
- echo "{{ cloud_init_nfs_path }}/cert /cert nfs defaults,_netdev 0 0" >> /etc/fstab
203+
- echo "{{ cloud_init_nfs_path }}/packages /var/lib/packages nfs defaults,_netdev 0 0" >> /etc/fstab
197204
- chmod {{ file_mode }} /etc/fstab
198205
- mount -a
206+
- cp /cert/pulp_webserver.crt /etc/pki/ca-trust/source/anchors && update-ca-trust
207+
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
208+
- bash /usr/local/bin/doca-install.sh
209+
- bash /usr/local/bin/configure-ib-network.sh
199210
- yes | cp /etc/slurm/epilog.d/slurmd.service /usr/lib/systemd/system/
200211
- /usr/local/bin/check_slurm_controller_status.sh
201212
- chown -R {{ slurm_user }}:{{ slurm_user }} /var/log/slurm

discovery/roles/configure_ochami/templates/cloud_init/ci-group-login_node_aarch64.yaml.j2

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,12 @@
3131
content: |
3232
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
3333

34+
- path: /usr/local/bin/configure-ib-network.sh
35+
owner: root:root
36+
permissions: '{{ file_mode_755 }}'
37+
content: |
38+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
39+
3440
- path: /usr/local/bin/set-ssh.sh
3541
permissions: '{{ file_mode_755 }}'
3642
content: |
@@ -103,18 +109,23 @@
103109
{{ lookup('template', 'templates/slurm/check_slurm_controller_status.sh.j2') | indent(12) }}
104110

105111
runcmd:
106-
- bash /usr/local/bin/doca-install.sh
107112
- /usr/local/bin/set-ssh.sh
108113

109-
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /var/log/track
114+
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /var/log/track /var/lib/packages
110115
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/log/slurm /var/log/slurm nfs defaults,_netdev 0 0" >> /etc/fstab
111116
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
112117
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/slurm/epilog.d /etc/slurm/epilog.d nfs defaults,_netdev 0 0" >> /etc/fstab
113118
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
114119
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/munge /etc/munge nfs defaults,_netdev 0 0" >> /etc/fstab
115120
- echo "{{ trackfile_nfs_path }} /var/log/track nfs defaults,_netdev 0 0" >> /etc/fstab
121+
- echo "{{ cloud_init_nfs_path }}/cert /cert nfs defaults,_netdev 0 0" >> /etc/fstab
122+
- echo "{{ cloud_init_nfs_path }}/packages /var/lib/packages nfs defaults,_netdev 0 0" >> /etc/fstab
116123
- chmod {{ file_mode }} /etc/fstab
117124
- mount -a
125+
- cp /cert/pulp_webserver.crt /etc/pki/ca-trust/source/anchors && update-ca-trust
126+
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
127+
- bash /usr/local/bin/doca-install.sh
128+
- bash /usr/local/bin/configure-ib-network.sh
118129
- yes | cp /etc/slurm/epilog.d/slurmd.service /usr/lib/systemd/system/
119130
- /usr/local/bin/check_slurm_controller_status.sh
120131
- chown -R {{ slurm_user }}:{{ slurm_user }} /var/log/slurm

discovery/roles/configure_ochami/templates/cloud_init/ci-group-login_node_x86_64.yaml.j2

Lines changed: 13 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,12 @@
3131
content: |
3232
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
3333

34+
- path: /usr/local/bin/configure-ib-network.sh
35+
owner: root:root
36+
permissions: '{{ file_mode_755 }}'
37+
content: |
38+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
39+
3440
- path: /usr/local/bin/set-ssh.sh
3541
permissions: '{{ file_mode_755 }}'
3642
content: |
@@ -102,19 +108,24 @@
102108
{{ lookup('template', 'templates/slurm/check_slurm_controller_status.sh.j2') | indent(12) }}
103109

104110
runcmd:
105-
- bash /usr/local/bin/doca-install.sh
106111
- /usr/local/bin/set-ssh.sh
107112

108-
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /cert /var/log/track
113+
- mkdir -p /var/log/slurm /var/run/slurm /var/spool /var/lib/slurm /etc/slurm/epilog.d /etc/munge /cert /var/log/track /var/lib/packages
109114
- echo "{{ cloud_init_nfs_path }}/cert /cert nfs defaults,_netdev 0 0" >> /etc/fstab
110115
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/log/slurm /var/log/slurm nfs defaults,_netdev 0 0" >> /etc/fstab
111116
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
112117
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/slurm/epilog.d /etc/slurm/epilog.d nfs defaults,_netdev 0 0" >> /etc/fstab
113118
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/var/spool /var/spool nfs defaults,_netdev 0 0" >> /etc/fstab
114119
- echo "{{ cloud_init_nfs_path }}/$(hostname -s)/etc/munge /etc/munge nfs defaults,_netdev 0 0" >> /etc/fstab
115120
- echo "{{ trackfile_nfs_path }} /var/log/track nfs defaults,_netdev 0 0" >> /etc/fstab
121+
- echo "{{ cloud_init_nfs_path }}/cert /cert nfs defaults,_netdev 0 0" >> /etc/fstab
122+
- echo "{{ cloud_init_nfs_path }}/packages /var/lib/packages nfs defaults,_netdev 0 0" >> /etc/fstab
116123
- chmod {{ file_mode }} /etc/fstab
117124
- mount -a
125+
- cp /cert/pulp_webserver.crt /etc/pki/ca-trust/source/anchors && update-ca-trust
126+
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
127+
- bash /usr/local/bin/doca-install.sh
128+
- bash /usr/local/bin/configure-ib-network.sh
118129
- yes | cp /etc/slurm/epilog.d/slurmd.service /usr/lib/systemd/system/
119130
- /usr/local/bin/check_slurm_controller_status.sh
120131
- chown -R {{ slurm_user }}:{{ slurm_user }} /var/log/slurm

discovery/roles/configure_ochami/templates/cloud_init/ci-group-service_kube_control_plane_first_x86_64.yaml.j2

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -26,6 +26,12 @@
2626
content: |
2727
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
2828

29+
- path: /usr/local/bin/configure-ib-network.sh
30+
owner: root:root
31+
permissions: '{{ file_mode_755 }}'
32+
content: |
33+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
34+
2935
- path: /usr/local/bin/set-ssh.sh
3036
permissions: '0755'
3137
content: |
@@ -402,6 +408,7 @@
402408
- update-ca-trust extract
403409
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
404410
- bash /usr/local/bin/doca-install.sh
411+
- bash /usr/local/bin/configure-ib-network.sh
405412
- systemctl start crio.service
406413
- systemctl enable crio.service
407414
- sudo systemctl enable --now kubelet

discovery/roles/configure_ochami/templates/cloud_init/ci-group-service_kube_control_plane_x86_64.yaml.j2

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -26,6 +26,12 @@
2626
content: |
2727
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
2828

29+
- path: /usr/local/bin/configure-ib-network.sh
30+
owner: root:root
31+
permissions: '{{ file_mode_755 }}'
32+
content: |
33+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
34+
2935
- path: /usr/local/bin/set-ssh.sh
3036
permissions: '0755'
3137
content: |
@@ -310,6 +316,7 @@
310316
- update-ca-trust extract
311317
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
312318
- bash /usr/local/bin/doca-install.sh
319+
- bash /usr/local/bin/configure-ib-network.sh
313320
- systemctl start crio.service
314321
- systemctl enable crio.service
315322
- sudo systemctl enable --now kubelet

discovery/roles/configure_ochami/templates/cloud_init/ci-group-service_kube_node_x86_64.yaml.j2

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -26,6 +26,12 @@
2626
content: |
2727
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
2828

29+
- path: /usr/local/bin/configure-ib-network.sh
30+
owner: root:root
31+
permissions: '{{ file_mode_755 }}'
32+
content: |
33+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
34+
2935
- path: /usr/local/bin/set-ssh.sh
3036
permissions: '0755'
3137
content: |
@@ -213,6 +219,7 @@
213219
- update-ca-trust extract
214220
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
215221
- bash /usr/local/bin/doca-install.sh
222+
- bash /usr/local/bin/configure-ib-network.sh
216223
- systemctl start crio.service
217224
- systemctl enable crio.service
218225
- sudo systemctl enable --now kubelet

discovery/roles/configure_ochami/templates/cloud_init/ci-group-slurm_control_node_x86_64.yaml.j2

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,12 @@
3131
content: |
3232
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
3333

34+
- path: /usr/local/bin/configure-ib-network.sh
35+
owner: root:root
36+
permissions: '{{ file_mode_755 }}'
37+
content: |
38+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
39+
3440
- path: /usr/local/bin/set-ssh.sh
3541
permissions: '{{ file_mode_755 }}'
3642
content: |
@@ -268,6 +274,7 @@
268274
- cp /cert/pulp_webserver.crt /etc/pki/ca-trust/source/anchors && update-ca-trust
269275
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
270276
- bash /usr/local/bin/doca-install.sh
277+
- bash /usr/local/bin/configure-ib-network.sh
271278

272279
- chown -R {{ slurm_user }}:{{ slurm_user }} {{ home_dir }}
273280
- chmod {{ file_mode_755 }} {{ home_dir }}

discovery/roles/configure_ochami/templates/cloud_init/ci-group-slurm_node_aarch64.yaml.j2

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -31,6 +31,12 @@
3131
content: |
3232
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
3333

34+
- path: /usr/local/bin/configure-ib-network.sh
35+
owner: root:root
36+
permissions: '{{ file_mode_755 }}'
37+
content: |
38+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
39+
3440
- path: /usr/local/bin/set-ssh.sh
3541
permissions: '{{ file_mode_755 }}'
3642
content: |
@@ -390,6 +396,7 @@
390396
- cp /cert/pulp_webserver.crt /etc/pki/ca-trust/source/anchors && update-ca-trust
391397
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
392398
- bash /usr/local/bin/doca-install.sh
399+
- bash /usr/local/bin/configure-ib-network.sh
393400
- /usr/local/bin/configure_slurmd_setup.sh
394401
- /usr/local/bin/configure_munge_and_pam.sh
395402

discovery/roles/configure_ochami/templates/cloud_init/ci-group-slurm_node_x86_64.yaml.j2

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -32,6 +32,12 @@
3232
content: |
3333
{{ lookup('template', 'templates/doca-ofed/doca-install.sh.j2') | indent(12) }}
3434

35+
- path: /usr/local/bin/configure-ib-network.sh
36+
owner: root:root
37+
permissions: '{{ file_mode_755 }}'
38+
content: |
39+
{{ lookup('template', 'templates/doca-ofed/configure-ib-network.sh.j2') | indent(12) }}
40+
3541
- path: /usr/local/bin/set-ssh.sh
3642
permissions: '{{ file_mode_755 }}'
3743
content: |
@@ -394,6 +400,7 @@
394400
- sed -i 's/^gpgcheck=1/gpgcheck=0/' /etc/dnf/dnf.conf
395401

396402
- bash /usr/local/bin/doca-install.sh
403+
- bash /usr/local/bin/configure-ib-network.sh
397404
- /usr/local/bin/configure_slurmd_setup.sh
398405
- /usr/local/bin/configure_munge_and_pam.sh
399406

0 commit comments

Comments
 (0)