Merge "Wait for compute service to check in"

functions

@@ -407,6 +407,26 @@ EOF
     return $rval
 }
 
+function wait_for_compute {
+    local timeout=$1
+    local rval=0
+    time_start "wait_for_service"
+    timeout $timeout bash -x <<EOF || rval=$?
+        ID=""
+        while [[ "\$ID" == "" ]]; do
+            sleep 1
+            ID=\$(openstack --os-cloud devstack-admin --os-region "$REGION_NAME" compute service list --host `hostname` --service nova-compute -c ID -f value)
+        done
+EOF
+    time_stop "wait_for_service"
+    # Figure out what's happening on platforms where this doesn't work
+    if [[ "$rval" != 0 ]]; then
+        echo "Didn't find service registered by hostname after $timeout seconds"
+        openstack --os-cloud devstack-admin --os-region "$REGION_NAME" compute service list
+    fi
+    return $rval
+}
+
 
 # ping check
 # Uses globals ``ENABLED_SERVICES``, ``TOP_DIR``, ``MULTI_HOST``, ``PRIVATE_NETWORK``

lib/nova

@@ -955,6 +955,28 @@ function start_nova_conductor {
     done
 }
 
+function is_nova_ready {
+    # NOTE(sdague): with cells v2 all the compute services must be up
+    # and checked into the database before discover_hosts is run. This
+    # happens in all in one installs by accident, because > 30 seconds
+    # happen between here and the script ending. However, in multinode
+    # tests this can very often not be the case. So ensure that the
+    # compute is up before we move on.
+    if is_service_enabled n-cell; then
+        # cells v1 can't complete the check below because it munges
+        # hostnames with cell information (grumble grumble).
+        return
+    fi
+    # TODO(sdague): honestly, this probably should be a plug point for
+    # an external system.
+    if [[ "$VIRT_DRIVER" == 'xenserver' ]]; then
+        # xenserver encodes information in the hostname of the compute
+        # because of the dom0/domU split. Just ignore for now.
+        return
+    fi
+    wait_for_compute 60
+}
+
 function start_nova {
     # this catches the cells v1 case early
     _set_singleconductor

stack.sh

@@ -1431,6 +1431,13 @@ fi
 # Sanity checks
 # =============
 
+# Check that computes are all ready
+#
+# TODO(sdague): there should be some generic phase here.
+if is_service_enabled n-cpu; then
+    is_nova_ready
+fi
+
 # Check the status of running services
 service_check