From 77d984eb94477f5e170c30318e0d3064d1c953e4 Mon Sep 17 00:00:00 2001
From: Dan Williams <dcbw@redhat.com>
Date: Fri, 3 Mar 2017 11:09:56 -0600
Subject: node/sdn: make /var/lib/cni persistent to ensure IPAM allocations
 stick around across node restart

With the move to a CNI plugin, docker no longer handles IPAM, but CNI does through
openshift-sdn's usage of the 'host-local' CNI IPAM plugin.  That plugin stores
IPAM allocations under /var/lib/cni/.

If the node container gets restarted, without presreving /var/lib/cni, the IPs
currently allocated to running pods get lost and on restart, openshift-sdn
may allocate those IPs to new pods causing duplicate allocations.

This never happened with docker because it has its own persistent IPAM store that
does not get removed when docker restarts.  Also because (historically) when docker
restarted, all the containers died and the IP allocations were released by the
daemon.

Fix this by ensuring that IPAM allocations (which are tied to the life of the pod,
*not* the life of the openshift-node process) persist even if the openshift-node
process restarts.

Fixes: https://bugzilla.redhat.com/show_bug.cgi?id=1427789
---
 roles/openshift_node/templates/openshift.docker.node.service         | 2 +-
 roles/openshift_node_upgrade/templates/openshift.docker.node.service | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'roles')

diff --git a/roles/openshift_node/templates/openshift.docker.node.service b/roles/openshift_node/templates/openshift.docker.node.service
index e33d5d497..6ec88f85e 100644
--- a/roles/openshift_node/templates/openshift.docker.node.service
+++ b/roles/openshift_node/templates/openshift.docker.node.service
@@ -15,7 +15,7 @@ After={{ openshift.common.service_type }}-node-dep.service
 EnvironmentFile=/etc/sysconfig/{{ openshift.common.service_type }}-node
 EnvironmentFile=/etc/sysconfig/{{ openshift.common.service_type }}-node-dep
 ExecStartPre=-/usr/bin/docker rm -f {{ openshift.common.service_type }}-node
-ExecStart=/usr/bin/docker run --name {{ openshift.common.service_type }}-node --rm --privileged --net=host --pid=host --env-file=/etc/sysconfig/{{ openshift.common.service_type }}-node -v /:/rootfs:ro -e CONFIG_FILE=${CONFIG_FILE} -e OPTIONS=${OPTIONS} -e HOST=/rootfs -e HOST_ETC=/host-etc -v {{ openshift.common.data_dir }}:{{ openshift.common.data_dir }}{{ ':rslave' if openshift.docker.gte_1_10 | default(False) | bool else '' }} -v {{ openshift.common.config_base }}/node:{{ openshift.common.config_base }}/node {% if openshift_cloudprovider_kind | default('') != '' -%} -v {{ openshift.common.config_base }}/cloudprovider:{{ openshift.common.config_base}}/cloudprovider {% endif -%} -v /etc/localtime:/etc/localtime:ro -v /etc/machine-id:/etc/machine-id:ro -v /run:/run -v /sys:/sys:rw -v /sys/fs/cgroup:/sys/fs/cgroup:rw -v /usr/bin/docker:/usr/bin/docker:ro -v /var/lib/docker:/var/lib/docker -v /lib/modules:/lib/modules -v /etc/origin/openvswitch:/etc/openvswitch -v /etc/origin/sdn:/etc/openshift-sdn -v /etc/systemd/system:/host-etc/systemd/system -v /var/log:/var/log -v /dev:/dev $DOCKER_ADDTL_BIND_MOUNTS {{ openshift.node.node_image }}:${IMAGE_VERSION}
+ExecStart=/usr/bin/docker run --name {{ openshift.common.service_type }}-node --rm --privileged --net=host --pid=host --env-file=/etc/sysconfig/{{ openshift.common.service_type }}-node -v /:/rootfs:ro -e CONFIG_FILE=${CONFIG_FILE} -e OPTIONS=${OPTIONS} -e HOST=/rootfs -e HOST_ETC=/host-etc -v {{ openshift.common.data_dir }}:{{ openshift.common.data_dir }}{{ ':rslave' if openshift.docker.gte_1_10 | default(False) | bool else '' }} -v {{ openshift.common.config_base }}/node:{{ openshift.common.config_base }}/node {% if openshift_cloudprovider_kind | default('') != '' -%} -v {{ openshift.common.config_base }}/cloudprovider:{{ openshift.common.config_base}}/cloudprovider {% endif -%} -v /etc/localtime:/etc/localtime:ro -v /etc/machine-id:/etc/machine-id:ro -v /run:/run -v /sys:/sys:rw -v /sys/fs/cgroup:/sys/fs/cgroup:rw -v /usr/bin/docker:/usr/bin/docker:ro -v /var/lib/docker:/var/lib/docker -v /lib/modules:/lib/modules -v /etc/origin/openvswitch:/etc/openvswitch -v /etc/origin/sdn:/etc/openshift-sdn -v /var/lib/cni:/var/lib/cni -v /etc/systemd/system:/host-etc/systemd/system -v /var/log:/var/log -v /dev:/dev $DOCKER_ADDTL_BIND_MOUNTS {{ openshift.node.node_image }}:${IMAGE_VERSION}
 ExecStartPost=/usr/bin/sleep 10
 ExecStop=/usr/bin/docker stop {{ openshift.common.service_type }}-node
 SyslogIdentifier={{ openshift.common.service_type }}-node
diff --git a/roles/openshift_node_upgrade/templates/openshift.docker.node.service b/roles/openshift_node_upgrade/templates/openshift.docker.node.service
index e33d5d497..6ec88f85e 100644
--- a/roles/openshift_node_upgrade/templates/openshift.docker.node.service
+++ b/roles/openshift_node_upgrade/templates/openshift.docker.node.service
@@ -15,7 +15,7 @@ After={{ openshift.common.service_type }}-node-dep.service
 EnvironmentFile=/etc/sysconfig/{{ openshift.common.service_type }}-node
 EnvironmentFile=/etc/sysconfig/{{ openshift.common.service_type }}-node-dep
 ExecStartPre=-/usr/bin/docker rm -f {{ openshift.common.service_type }}-node
-ExecStart=/usr/bin/docker run --name {{ openshift.common.service_type }}-node --rm --privileged --net=host --pid=host --env-file=/etc/sysconfig/{{ openshift.common.service_type }}-node -v /:/rootfs:ro -e CONFIG_FILE=${CONFIG_FILE} -e OPTIONS=${OPTIONS} -e HOST=/rootfs -e HOST_ETC=/host-etc -v {{ openshift.common.data_dir }}:{{ openshift.common.data_dir }}{{ ':rslave' if openshift.docker.gte_1_10 | default(False) | bool else '' }} -v {{ openshift.common.config_base }}/node:{{ openshift.common.config_base }}/node {% if openshift_cloudprovider_kind | default('') != '' -%} -v {{ openshift.common.config_base }}/cloudprovider:{{ openshift.common.config_base}}/cloudprovider {% endif -%} -v /etc/localtime:/etc/localtime:ro -v /etc/machine-id:/etc/machine-id:ro -v /run:/run -v /sys:/sys:rw -v /sys/fs/cgroup:/sys/fs/cgroup:rw -v /usr/bin/docker:/usr/bin/docker:ro -v /var/lib/docker:/var/lib/docker -v /lib/modules:/lib/modules -v /etc/origin/openvswitch:/etc/openvswitch -v /etc/origin/sdn:/etc/openshift-sdn -v /etc/systemd/system:/host-etc/systemd/system -v /var/log:/var/log -v /dev:/dev $DOCKER_ADDTL_BIND_MOUNTS {{ openshift.node.node_image }}:${IMAGE_VERSION}
+ExecStart=/usr/bin/docker run --name {{ openshift.common.service_type }}-node --rm --privileged --net=host --pid=host --env-file=/etc/sysconfig/{{ openshift.common.service_type }}-node -v /:/rootfs:ro -e CONFIG_FILE=${CONFIG_FILE} -e OPTIONS=${OPTIONS} -e HOST=/rootfs -e HOST_ETC=/host-etc -v {{ openshift.common.data_dir }}:{{ openshift.common.data_dir }}{{ ':rslave' if openshift.docker.gte_1_10 | default(False) | bool else '' }} -v {{ openshift.common.config_base }}/node:{{ openshift.common.config_base }}/node {% if openshift_cloudprovider_kind | default('') != '' -%} -v {{ openshift.common.config_base }}/cloudprovider:{{ openshift.common.config_base}}/cloudprovider {% endif -%} -v /etc/localtime:/etc/localtime:ro -v /etc/machine-id:/etc/machine-id:ro -v /run:/run -v /sys:/sys:rw -v /sys/fs/cgroup:/sys/fs/cgroup:rw -v /usr/bin/docker:/usr/bin/docker:ro -v /var/lib/docker:/var/lib/docker -v /lib/modules:/lib/modules -v /etc/origin/openvswitch:/etc/openvswitch -v /etc/origin/sdn:/etc/openshift-sdn -v /var/lib/cni:/var/lib/cni -v /etc/systemd/system:/host-etc/systemd/system -v /var/log:/var/log -v /dev:/dev $DOCKER_ADDTL_BIND_MOUNTS {{ openshift.node.node_image }}:${IMAGE_VERSION}
 ExecStartPost=/usr/bin/sleep 10
 ExecStop=/usr/bin/docker stop {{ openshift.common.service_type }}-node
 SyslogIdentifier={{ openshift.common.service_type }}-node
-- 
cgit v1.2.3