Dev: behave: add functional tests for pre-migration checks (jsc#PED-8252)

Author: nicholasyang2022

.github/workflows/crmsh-ci.yml

@@ -415,6 +415,21 @@ jobs:
         token: ${{ secrets.CODECOV_TOKEN }}
         flags: integration
 
+  functional_test_migration:
+    runs-on: ubuntu-24.04
+    timeout-minutes: 40
+    steps:
+    - uses: actions/checkout@v4
+    - name: functional test for migration
+      run:  |
+        echo '{ "exec-opts": ["native.cgroupdriver=systemd"] }' | sudo tee /etc/docker/daemon.json
+        sudo systemctl restart docker.service
+        $CONTAINER_SCRIPT `$GET_INDEX_OF migration` && $CONTAINER_SCRIPT -d && $CONTAINER_SCRIPT -u `$GET_INDEX_OF migration`
+    - uses: codecov/codecov-action@v4
+      with:
+        token: ${{ secrets.CODECOV_TOKEN }}
+        flags: integration
+
   original_regression_test:
     runs-on: ubuntu-24.04
     timeout-minutes: 40

codecov.yml

@@ -8,7 +8,7 @@ coverage:
         threshold: 0.35%
 codecov:
   notify:
-    after_n_builds: 28
+    after_n_builds: 29
 comment:
-  after_n_builds: 28
+  after_n_builds: 29
   layout: "condensed_header, flags, files, condensed_footer"

data-manifest

@@ -83,6 +83,7 @@ test/features/environment.py
 test/features/geo_setup.feature
 test/features/gfs2.feature
 test/features/healthcheck.feature
+test/features/migration.feature
 test/features/ocfs2.feature
 test/features/qdevice_options.feature
 test/features/qdevice_setup_remove.feature

test/features/migration.feature

@@ -0,0 +1,102 @@
+# vim: sw=2 sts=2
+Feature: migration
+
+  Test migration and pre-migration checks
+  Need nodes: hanode1 hanode2
+
+  Scenario: Run pre-migration checks when cluster services are running.
+    Given   Cluster service is "stopped" on "hanode1"
+    And     Cluster service is "stopped" on "hanode2"
+    And     Run "crm cluster init -y -N hanode2" OK on "hanode1"
+    When    Try "crm cluster health sles16" on "hanode1"
+    Then    Expected return code is "1"
+    And     Expected "[FAIL] Cluster services are running" in stdout
+
+  Scenario: Run pre-migration checks with cluster services stopped.
+    When    Run "crm cluster stop --all" on "hanode1"
+    And     Run "crm cluster stop --all" on "hanode2"
+    And     Try "crm cluster health sles16" on "hanode1"
+    Then    Expected return code is "0"
+
+  Scenario: Should run fixes.
+    When    Try "crm cluster health sles16 --fix" on "hanode1"
+    Then    Expected return code is "0"
+
+  Scenario: run pre-migration checks against corosync.conf generated in crmsh-4.6
+    When    Run "rm -f /etc/corosync/corosync.conf" on "hanode1"
+    And     Write multi lines to file "/etc/corosync/corosync.conf" on "hanode1"
+      """
+      # Please read the corosync.conf.5 manual page
+      totem {
+              version: 2
+              cluster_name: hacluster
+              clear_node_high_bit: yes
+              interface {
+                      ringnumber: 0
+                      mcastport: 5405
+                      ttl: 1
+              }
+
+              transport: udpu
+              crypto_hash: sha1
+              crypto_cipher: aes256
+              token: 5000
+              join: 60
+              max_messages: 20
+              token_retransmits_before_loss_const: 10
+      }
+
+      logging {
+              fileline: off
+              to_stderr: no
+              to_logfile: yes
+              logfile: /var/log/cluster/corosync.log
+              to_syslog: yes
+              debug: off
+              timestamp: on
+              logger_subsys {
+                      subsys: QUORUM
+                      debug: off
+              }
+
+      }
+
+      quorum {
+
+              # Enable and configure quorum subsystem (default: off)
+              # see also corosync.conf.5 and votequorum.5
+              provider: corosync_votequorum
+              expected_votes: 2
+              two_node: 1
+      }
+
+      nodelist {
+        node {
+                ring0_addr: @hanode1.ip.0
+                name: hanode1
+                nodeid: 1
+        }
+
+        node {
+                ring0_addr: @hanode2.ip.0
+                name: hanode2
+                nodeid: 2
+        }
+
+      }
+      """
+    And Run "crm cluster copy /etc/corosync/corosync.conf" on "hanode1"
+    And Try "crm cluster health sles16" on "hanode1"
+    Then    Expected return code is "0"
+    And     Expect stdout contains snippets ["[PASS] This cluster is good to migrate to SLES 16.", "[INFO] Please run \"crm cluster health sles16 --fix\" on on any one of above nodes.", "[WARN] Corosync transport \"udpu\" will be deprecated in corosync 3. Please use knet.", "----- localhost -----", "----- hanode2 -----"].
+
+  Scenario: Run fixes against corosync.conf generated in crmsh-4.6
+    When    Try "crm cluster health sles16 --fix" on "hanode1"
+    Then    Expected return code is "0"
+
+  Scenario: Run pre-migration checks when some of the nodes are offline.
+    When    Run "systemctl stop sshd" on "hanode2"
+    And     Try "crm cluster health sles16" on "hanode1"
+    Then    Expected return code is "1"
+    And     Expect stdout contains snippets ["Cannot create SSH connection to", "----- localhost -----", "----- hanode2 -----"].
+

test/features/steps/step_implementation.py

@@ -1,3 +1,4 @@
+import ast
 import re
 import time
 import os
@@ -18,8 +19,8 @@
 
 
 def _parse_str(text):
-    return text[1:-1].encode('utf-8').decode('unicode_escape')
-_parse_str.pattern='".*"'
+    return ast.literal_eval(text)
+_parse_str.pattern='"([^"]|\\")*?"'
 
 
 behave.use_step_matcher("cfparse")
@@ -170,6 +171,13 @@ def step_impl(context, msg):
     context.stderr = None
 
 
+@then('Expect stdout contains snippets [{snippets:str+}].')
+def step_impl(context, snippets):
+    for snippet in snippets:
+        assert_in(snippet, context.stdout)
+    context.stdout = None
+
+
 @then('Expected regex "{reg_str}" in stdout')
 def step_impl(context, reg_str):
     res = re.search(reg_str, context.stdout)

test/run-functional-tests

@@ -228,8 +228,6 @@ deploy_ha_node() {
 
 
 create_node() {
-	info "Loading container image $CONTAINER_IMAGE..."
-
         echo 16777216 > /proc/sys/net/core/rmem_max
         echo 16777216 > /proc/sys/net/core/wmem_max
         info "Create ha specific container networks..."