[pve-devel] [PATCH v2 ha-manager 1/2] tests: simulate stale maintainance node caused by simultaneous cluster shutdown

Fiona Ebner f.ebner at proxmox.com
Mon Jun 12 17:27:10 CEST 2023


In the test log, it can be seen that the service will unexpectedly be
migrated back. This is caused by the service's maintainance node
property being set by the initial shutdown, but never cleared, because
that currently happens only when the service is started on a different
node. The next commit will address the issue.

Signed-off-by: Fiona Ebner <f.ebner at proxmox.com>
---

Changes in v2:
    * Rebase on current master.
    * Split out introducing the test into a dedicated patch.

 src/test/test-stale-maintenance-node/cmdlist  |  6 ++
 .../datacenter.cfg                            |  5 +
 .../hardware_status                           |  5 +
 .../test-stale-maintenance-node/log.expect    | 92 +++++++++++++++++++
 .../manager_status                            |  1 +
 .../service_config                            |  3 +
 6 files changed, 112 insertions(+)
 create mode 100644 src/test/test-stale-maintenance-node/cmdlist
 create mode 100644 src/test/test-stale-maintenance-node/datacenter.cfg
 create mode 100644 src/test/test-stale-maintenance-node/hardware_status
 create mode 100644 src/test/test-stale-maintenance-node/log.expect
 create mode 100644 src/test/test-stale-maintenance-node/manager_status
 create mode 100644 src/test/test-stale-maintenance-node/service_config

diff --git a/src/test/test-stale-maintenance-node/cmdlist b/src/test/test-stale-maintenance-node/cmdlist
new file mode 100644
index 0000000..8e4ed64
--- /dev/null
+++ b/src/test/test-stale-maintenance-node/cmdlist
@@ -0,0 +1,6 @@
+[
+    [ "power node1 on", "power node2 on", "power node3 on"],
+    [ "shutdown node1", "shutdown node2", "shutdown node3"],
+    [ "power node1 on", "power node2 on", "power node3 on"],
+    [ "service vm:103 migrate node3" ]
+]
diff --git a/src/test/test-stale-maintenance-node/datacenter.cfg b/src/test/test-stale-maintenance-node/datacenter.cfg
new file mode 100644
index 0000000..de0bf81
--- /dev/null
+++ b/src/test/test-stale-maintenance-node/datacenter.cfg
@@ -0,0 +1,5 @@
+{
+    "ha": {
+        "shutdown_policy": "migrate"
+    }
+}
diff --git a/src/test/test-stale-maintenance-node/hardware_status b/src/test/test-stale-maintenance-node/hardware_status
new file mode 100644
index 0000000..451beb1
--- /dev/null
+++ b/src/test/test-stale-maintenance-node/hardware_status
@@ -0,0 +1,5 @@
+{
+  "node1": { "power": "off", "network": "off" },
+  "node2": { "power": "off", "network": "off" },
+  "node3": { "power": "off", "network": "off" }
+}
diff --git a/src/test/test-stale-maintenance-node/log.expect b/src/test/test-stale-maintenance-node/log.expect
new file mode 100644
index 0000000..ac944ca
--- /dev/null
+++ b/src/test/test-stale-maintenance-node/log.expect
@@ -0,0 +1,92 @@
+info      0     hardware: starting simulation
+info     20      cmdlist: execute power node1 on
+info     20    node1/crm: status change startup => wait_for_quorum
+info     20    node1/lrm: status change startup => wait_for_agent_lock
+info     20      cmdlist: execute power node2 on
+info     20    node2/crm: status change startup => wait_for_quorum
+info     20    node2/lrm: status change startup => wait_for_agent_lock
+info     20      cmdlist: execute power node3 on
+info     20    node3/crm: status change startup => wait_for_quorum
+info     20    node3/lrm: status change startup => wait_for_agent_lock
+info     20    node1/crm: got lock 'ha_manager_lock'
+info     20    node1/crm: status change wait_for_quorum => master
+info     20    node1/crm: node 'node1': state changed from 'unknown' => 'online'
+info     20    node1/crm: node 'node2': state changed from 'unknown' => 'online'
+info     20    node1/crm: node 'node3': state changed from 'unknown' => 'online'
+info     20    node1/crm: adding new service 'vm:103' on node 'node1'
+info     20    node1/crm: service 'vm:103': state changed from 'request_start' to 'started'  (node = node1)
+info     21    node1/lrm: got lock 'ha_agent_node1_lock'
+info     21    node1/lrm: status change wait_for_agent_lock => active
+info     21    node1/lrm: starting service vm:103
+info     21    node1/lrm: service status vm:103 started
+info     22    node2/crm: status change wait_for_quorum => slave
+info     24    node3/crm: status change wait_for_quorum => slave
+info    120      cmdlist: execute shutdown node1
+info    120    node1/lrm: got shutdown request with shutdown policy 'migrate'
+info    120    node1/lrm: shutdown LRM, doing maintenance, removing this node from active list
+info    120      cmdlist: execute shutdown node2
+info    120    node2/lrm: got shutdown request with shutdown policy 'migrate'
+info    120    node2/lrm: shutdown LRM, doing maintenance, removing this node from active list
+info    120      cmdlist: execute shutdown node3
+info    120    node3/lrm: got shutdown request with shutdown policy 'migrate'
+info    120    node3/lrm: shutdown LRM, doing maintenance, removing this node from active list
+info    120    node1/crm: node 'node1': state changed from 'online' => 'maintenance'
+info    120    node1/crm: node 'node2': state changed from 'online' => 'maintenance'
+info    120    node1/crm: node 'node3': state changed from 'online' => 'maintenance'
+info    121    node1/lrm: status change active => maintenance
+info    124    node2/lrm: exit (loop end)
+info    124     shutdown: execute crm node2 stop
+info    123    node2/crm: server received shutdown request
+info    126    node3/lrm: exit (loop end)
+info    126     shutdown: execute crm node3 stop
+info    125    node3/crm: server received shutdown request
+info    143    node2/crm: exit (loop end)
+info    143     shutdown: execute power node2 off
+info    144    node3/crm: exit (loop end)
+info    144     shutdown: execute power node3 off
+info    160    node1/crm: status change master => lost_manager_lock
+info    160    node1/crm: status change lost_manager_lock => wait_for_quorum
+info    161    node1/lrm: status change maintenance => lost_agent_lock
+err     161    node1/lrm: get shutdown request in state 'lost_agent_lock' - detected 1 running services
+err     181    node1/lrm: get shutdown request in state 'lost_agent_lock' - detected 1 running services
+err     201    node1/lrm: get shutdown request in state 'lost_agent_lock' - detected 1 running services
+info    202     watchdog: execute power node1 off
+info    201    node1/crm: killed by poweroff
+info    202    node1/lrm: killed by poweroff
+info    202     hardware: server 'node1' stopped by poweroff (watchdog)
+info    220      cmdlist: execute power node1 on
+info    220    node1/crm: status change startup => wait_for_quorum
+info    220    node1/lrm: status change startup => wait_for_agent_lock
+info    220      cmdlist: execute power node2 on
+info    220    node2/crm: status change startup => wait_for_quorum
+info    220    node2/lrm: status change startup => wait_for_agent_lock
+info    220      cmdlist: execute power node3 on
+info    220    node3/crm: status change startup => wait_for_quorum
+info    220    node3/lrm: status change startup => wait_for_agent_lock
+info    220    node1/crm: status change wait_for_quorum => master
+info    221    node1/lrm: status change wait_for_agent_lock => active
+info    221    node1/lrm: starting service vm:103
+info    221    node1/lrm: service status vm:103 started
+info    222    node2/crm: status change wait_for_quorum => slave
+info    224    node3/crm: status change wait_for_quorum => slave
+info    240    node1/crm: node 'node1': state changed from 'maintenance' => 'online'
+info    240    node1/crm: node 'node2': state changed from 'maintenance' => 'online'
+info    240    node1/crm: node 'node3': state changed from 'maintenance' => 'online'
+info    320      cmdlist: execute service vm:103 migrate node3
+info    320    node1/crm: got crm command: migrate vm:103 node3
+info    320    node1/crm: migrate service 'vm:103' to node 'node3'
+info    320    node1/crm: service 'vm:103': state changed from 'started' to 'migrate'  (node = node1, target = node3)
+info    321    node1/lrm: service vm:103 - start migrate to node 'node3'
+info    321    node1/lrm: service vm:103 - end migrate to node 'node3'
+info    340    node1/crm: service 'vm:103': state changed from 'migrate' to 'started'  (node = node3)
+info    340    node1/crm: moving service 'vm:103' back to 'node1', node came back from maintenance.
+info    340    node1/crm: migrate service 'vm:103' to node 'node1' (running)
+info    340    node1/crm: service 'vm:103': state changed from 'started' to 'migrate'  (node = node3, target = node1)
+info    345    node3/lrm: got lock 'ha_agent_node3_lock'
+info    345    node3/lrm: status change wait_for_agent_lock => active
+info    345    node3/lrm: service vm:103 - start migrate to node 'node1'
+info    345    node3/lrm: service vm:103 - end migrate to node 'node1'
+info    360    node1/crm: service 'vm:103': state changed from 'migrate' to 'started'  (node = node1)
+info    361    node1/lrm: starting service vm:103
+info    361    node1/lrm: service status vm:103 started
+info    920     hardware: exit simulation - done
diff --git a/src/test/test-stale-maintenance-node/manager_status b/src/test/test-stale-maintenance-node/manager_status
new file mode 100644
index 0000000..0967ef4
--- /dev/null
+++ b/src/test/test-stale-maintenance-node/manager_status
@@ -0,0 +1 @@
+{}
diff --git a/src/test/test-stale-maintenance-node/service_config b/src/test/test-stale-maintenance-node/service_config
new file mode 100644
index 0000000..cfed86f
--- /dev/null
+++ b/src/test/test-stale-maintenance-node/service_config
@@ -0,0 +1,3 @@
+{
+    "vm:103": { "node": "node1", "state": "enabled" }
+}
-- 
2.39.2






More information about the pve-devel mailing list