20680: Only do a rolling update when there is multiple controllers

[arvados.git] / tools / salt-install / installer.sh

diff --git a/tools/salt-install/installer.sh b/tools/salt-install/installer.sh
index b042d1a835938dc18190da240000afe61c04b0a0..fe04047431b42091d290ee05f0f49262275f1765 100755 (executable)
--- a/tools/salt-install/installer.sh
+++ b/tools/salt-install/installer.sh
@@ -35,6 +35,11 @@ declare DOMAIN
 # This will be populated by loadconfig()
 declare -A NODES
 
+# A bash associative array listing each role and mapping to the nodes
+# that should be provisioned with this role.
+# This will be populated by loadconfig()
+declare -A ROLE2NODES
+
 # The ssh user we'll use
 # This will be populated by loadconfig()
 declare DEPLOY_USER
@@ -47,6 +52,11 @@ declare GITTARGET
 # This will be populated by loadconfig()
 declare USE_SSH_JUMPHOST
 
+# The temp file that will get used to disable envvar forwarding to avoid locale
+# issues in Debian distros.
+# This will be populated by loadconfig()
+declare SSH_CONFFILE
+
 checktools() {
     local MISSING=''
     for a in git ip ; do
@@ -101,10 +111,13 @@ sync() {
 deploynode() {
     local NODE=$1
     local ROLES=$2
+    local BRANCH=$3
 
     # Deploy a node.  This runs the provision script on the node, with
     # the appropriate roles.
 
+    sync $NODE $BRANCH
+
     if [[ -z "$ROLES" ]] ; then
                echo "No roles specified for $NODE, will deploy all roles"
     else
@@ -121,26 +134,31 @@ deploynode() {
                fi
                $SUDO ./provision.sh --config ${CONFIG_FILE} ${ROLES} 2>&1 | tee $logfile
     else
-           $SSH $DEPLOY_USER@$NODE "cd ${GITTARGET} && git log -n1 HEAD && sudo ./provision.sh --config ${CONFIG_FILE} ${ROLES}" 2>&1 | tee $logfile
+           $SSH $DEPLOY_USER@$NODE "cd ${GITTARGET} && git log -n1 HEAD && DISABLED_CONTROLLER=\"$DISABLED_CONTROLLER\" sudo --preserve-env=DISABLED_CONTROLLER ./provision.sh --config ${CONFIG_FILE} ${ROLES}" 2>&1 | tee $logfile
            cleanup $NODE
     fi
 }
 
 loadconfig() {
-    if [[ -s ${CONFIG_FILE} && -s ${CONFIG_FILE}.secrets ]]; then
+    if ! [[ -s ${CONFIG_FILE} && -s ${CONFIG_FILE}.secrets ]]; then
                echo "Must be run from initialized setup dir, maybe you need to 'initialize' first?"
     fi
-    source ${CONFIG_FILE}.secrets
-    source ${CONFIG_FILE}
+    source common.sh
     GITTARGET=arvados-deploy-config-${CLUSTER}
+
+       # Set up SSH so that it doesn't forward any environment variable. This is to avoid
+       # getting "setlocale" errors on the first run, depending on the distro being used
+       # to run the installer (like Debian).
+       SSH_CONFFILE=$(mktemp)
+       echo "Include config SendEnv -*" > ${SSH_CONFFILE}
 }
 
 ssh_cmd() {
        local NODE=$1
        if [ -z "${USE_SSH_JUMPHOST}" -o "${NODE}" == "${USE_SSH_JUMPHOST}" -o "${NODE}" == "localhost" ]; then
-               echo "ssh"
+               echo "ssh -F ${SSH_CONFFILE}"
        else
-               echo "ssh -J ${DEPLOY_USER}@${USE_SSH_JUMPHOST}"
+               echo "ssh -F ${SSH_CONFFILE} -J ${DEPLOY_USER}@${USE_SSH_JUMPHOST}"
        fi
 }
 
@@ -276,43 +294,73 @@ case "$subcmd" in
            git commit -m"prepare for deploy"
        fi
 
+       # Used for rolling updates to disable individual nodes at the
+       # load balancer.
+       export DISABLED_CONTROLLER=""
        if [[ -z "$NODE" ]]; then
            for NODE in "${!NODES[@]}"
            do
-               # First, push the git repo to each node.  This also
-               # confirms that we have git and can log into each
-               # node.
-               sync $NODE $BRANCH
+               # First, just confirm we can ssh to each node.
+               `ssh_cmd "$NODE"` $DEPLOY_USER@$NODE true
            done
 
            for NODE in "${!NODES[@]}"
            do
                # Do 'database' role first,
                if [[ "${NODES[$NODE]}" =~ database ]] ; then
-                   deploynode $NODE "${NODES[$NODE]}"
+                   deploynode $NODE "${NODES[$NODE]}" $BRANCH
                    unset NODES[$NODE]
                fi
            done
 
-           for NODE in "${!NODES[@]}"
-           do
-               # then  'api' or 'controller' roles
-               if [[ "${NODES[$NODE]}" =~ (api|controller) ]] ; then
-                   deploynode $NODE "${NODES[$NODE]}"
-                   unset NODES[$NODE]
-               fi
-           done
+           BALANCER=${ROLE2NODES['balancer']:-}
+
+           # Check if there are multiple controllers, they'll be comma-separated
+           # in ROLE2NODES
+           if [[ ${ROLE2NODES['controller']} =~ , ]] ;
+           then
+               # If we have multiple controllers then there must be
+               # load balancer. We want to do a rolling update, take
+               # down each node at the load balancer before updating
+               # it.
+
+               for NODE in "${!NODES[@]}"
+               do
+                   if [[ "${NODES[$NODE]}" =~ controller ]] ; then
+                       export DISABLED_CONTROLLER=$NODE
+
+                       # Update balancer that the node is disabled
+                       deploynode $BALANCER "${NODES[$BALANCER]}" $BRANCH
+
+                       # Now update the node itself
+                       deploynode $NODE "${NODES[$NODE]}" $BRANCH
+                       unset NODES[$NODE]
+                   fi
+               done
+           else
+               # Only one controller
+               NODE=${ROLE2NODES['controller']}
+               deploynode $NODE "${NODES[$NODE]}" $BRANCH
+               unset NODES[$NODE]
+           fi
+
+           if [[ -n "$BALANCER" ]] ; then
+               # Deploy balancer. In the rolling update case, this
+               # will re-enable all the controllers at the balancer.
+               export DISABLED_CONTROLLER=""
+               deploynode $BALANCER "${NODES[$BALANCER]}" $BRANCH
+               unset NODES[$BALANCER]
+           fi
 
            for NODE in "${!NODES[@]}"
            do
                # Everything else (we removed the nodes that we
                # already deployed from the list)
-               deploynode $NODE "${NODES[$NODE]}"
+               deploynode $NODE "${NODES[$NODE]}" $BRANCH
            done
        else
            # Just deploy the node that was supplied on the command line.
-           sync $NODE $BRANCH
-           deploynode $NODE "${NODES[$NODE]}"
+           deploynode $NODE "${NODES[$NODE]}" $BRANCH
        fi
 
        set +x