Bring in baremetal support

- ci/deploy.sh: fail if default scenario file is missing;
- start by copying reclass/classes/cluster/virtual-mcp-ocata-ovs as
  classes/cluster/baremetal-mcp-ocata-ovs;
- add new state (maas) that will handle MaaS configuration;
- Split PXE network in two for baremetal:
  * rename old "pxe" virtual network to "mcpcontrol", make it
    non-configurable and identical for baremetal/virtual deploys;
  * new "pxebr" bridge is dedicated for MaaS fabric network, which
    comes with its own DHCP, TFTP etc.;
- Drop hardcoded PXE gateway & static IP for MaaS node, since
  "mcpcontrol" remains a NAT-ed virtual network, with its own DHCP;
- Keep internet access available on first interfaces for cfg01/mas01;
- Align MaaS IP addrs (all x.y.z.3), add public IP for easy debug
  via MaaS dashboard;
- Add static IP in new network segment (192.168.11.3/24) on MaaS
  node's PXE interface;
- Set MaaS PXE interface MTU 1500 (weird network errors with jumbo);
- MaaS node: Add NAT iptables traffic forward from "mcpcontrol" to
  "pxebr" interfaces;
- MaaS: Add harcoded lf-pod2 machine info (fixed identation in v6);
- Switch our targeted scenario to HA;
  * scenario: s/os-nosdn-nofeature-noha/os-nosdn-nofeature-ha/
- maas region: Use mcp.rsa.pub from ~ubuntu/.ssh/authorized_keys;
- add route for 192.168.11.0/24 via mas01 on cfg01;
- fix race condition on kvm nodes network setup:
  * add "noifupdown" support in salt formula for linux.network;
  * keep primary eth/br-mgmt unconfigured till reboot;

TODO:
- Read all this info from PDF (Pod Descriptor File) later;
- investigate leftover references to eno2, eth3;
- add public network interfaces config, IPs;
- improve wait conditions for MaaS commision/deploy;
- report upstream breakage in system.single;

Change-Id: Ie8dd584b140991d2bd992acdfe47f5644bf51409
Signed-off-by: Michael Polenchuk <mpolenchuk@mirantis.com>
Signed-off-by: Guillermo Herrero <Guillermo.Herrero@enea.com>
Signed-off-by: Charalampos Kominos <Charalampos.Kominos@enea.com>
Signed-off-by: Alexandru Avadanii <Alexandru.Avadanii@enea.com>

2 files changed, 68 insertions, 0 deletions

diff --git a/mcp/config/states/maas b/mcp/config/states/maas
new file mode 100755
index 000000000..8b599105d
--- /dev/null
+++ b/mcp/config/states/maas
@@ -0,0 +1,56 @@
+#!/bin/bash
+function wait_for() {
+  local cmdstr=$@
+  local total_attempts=360
+  local sleep_time=10
+  local attempt=1
+  echo "[NOTE] Waiting for cmd to return success: ${cmdstr}"
+  while ((attempt <= total_attempts)); do
+    eval "${cmdstr}" && break || true
+    echo -n '.'; sleep "${sleep_time}"
+    ((attempt+=1))
+  done
+}
+
+# MaaS rack/region controller, node commissioning
+salt -C 'mas01*' cmd.run "add-apt-repository ppa:maas/stable"
+
+salt -C 'mas01*' state.apply linux,salt,openssh,ntp
+salt -C 'mas01*' state.apply linux.network.interface
+salt -C 'mas01*' state.apply maas.pxe_nat
+salt -C 'mas01*' state.apply maas.cluster
+salt -C 'cfg01*' cmd.run \
+  "route add -net 192.168.11.0/24 gw ${MAAS_IP:-192.168.10.3}"
+
+wait_for "salt -C 'mas01*' state.apply maas.region"
+
+salt -C 'mas01*' state.apply maas.machines
+# TODO: relax cond, as this is not re-entrant (e.g. nodes already deployed)
+wait_for "salt 'mas01*' --out yaml state.apply maas.machines.status | " \
+         "fgrep -q 'Ready: 5'"
+
+# MaaS node deployment
+salt -C 'mas01*' state.apply maas.machines.deploy
+wait_for "salt 'mas01*' --out yaml state.apply maas.machines.status | " \
+         "fgrep -q 'Deployed: 5'"
+
+salt -C 'mas01*' pillar.item\
+  maas:region:admin:username \
+  maas:region:admin:password
+
+# KVM, compute node prereqs (libvirt first), VCP deployment
+salt -C '* and not cfg01* and not mas01*' saltutil.sync_all
+salt -C '* and not cfg01* and not mas01*' state.apply linux,ntp
+
+salt -C 'kvm*' state.sls libvirt
+
+salt -C '* and not cfg01* and not mas01*' system.reboot
+wait_for "! salt '*' test.ping | fgrep -q 'Not connected'"
+
+salt -C '* and not cfg01* and not mas01*' state.apply salt
+
+salt -C 'kvm*' state.sls salt.control
+
+salt -C '* and not cfg01* and not mas01*' saltutil.sync_all
+salt -C '* and not cfg01* and not mas01*' state.apply salt
+salt -C '* and not cfg01* and not mas01*' state.apply linux,ntp
diff --git a/mcp/config/states/openstack_ha b/mcp/config/states/openstack_ha
new file mode 100755
index 000000000..293273594
--- /dev/null
+++ b/mcp/config/states/openstack_ha
@@ -0,0 +1,12 @@
+salt -I 'keepalived:cluster' state.sls keepalived -b 1
+
+salt -I 'rabbitmq:server' state.sls rabbitmq # maybe twice
+salt -I 'rabbitmq:server' cmd.run "rabbitmqctl cluster_status"
+
+salt -I 'glusterfs:server' state.sls glusterfs.server.service
+salt -I 'glusterfs:server' state.sls glusterfs.server.setup -b 1
+salt -I 'glusterfs:server' cmd.run "gluster peer status; gluster volume status" -b 1
+
+salt -I 'galera:master' state.sls galera
+salt -I 'galera:slave' state.sls galera
+salt -I 'galera:master' mysql.status | grep -A1 wsrep_cluster_size