Merge pull request #1362 from cschwede/fix-cix-1318

Fix possible race condition in swift_migration check

Author: openshift-merge-bot[bot]

docs_user/modules/proc_migrating-object-storage-data-to-rhoso-nodes.adoc

@@ -98,6 +98,10 @@ ssh commands for your existing nodes that store the {object_storage} data:
 $ oc extract --confirm cm/swift-ring-files
 $ $CONTROLLER1_SSH "tar -C /var/lib/config-data/puppet-generated/swift/etc/swift/ -xzf -" < swiftrings.tar.gz
 $ $CONTROLLER1_SSH "systemctl restart tripleo_swift_*"
+$ $CONTROLLER2_SSH "tar -C /var/lib/config-data/puppet-generated/swift/etc/swift/ -xzf -" < swiftrings.tar.gz
+$ $CONTROLLER2_SSH "systemctl restart tripleo_swift_*"
+$ $CONTROLLER3_SSH "tar -C /var/lib/config-data/puppet-generated/swift/etc/swift/ -xzf -" < swiftrings.tar.gz
+$ $CONTROLLER3_SSH "systemctl restart tripleo_swift_*"
 ----
 
 . Track the replication progress by using the `swift-dispersion-report` tool:

tests/roles/swift_migration/tasks/main.yaml

@@ -57,7 +57,7 @@
   ansible.builtin.shell: |
     {{ shell_header }}
     CONTROLLER1_SSH="{{ controller1_ssh }}"
-    $CONTROLLER1_SSH "timeout 900s bash -c 'while \$(find /srv/node/ -type f -name \"*.db\" -o -name \"*.data\" | grep -q \".\"); do sleep 5; done'"
+    $CONTROLLER1_SSH "timeout 900s bash -c 'while \$(find /srv/node/ -ignore_readdir_race -type f -name \"*.db\" -o -name \"*.data\" | grep -q \".\"); do sleep 5; done'"
 
 - name: remove standalone node from rings
   ansible.builtin.shell: |

tests/roles/swift_migration/tasks/rebalance_and_wait.yaml

@@ -6,14 +6,23 @@
     swift-ring-tool forced_rebalance
     swift-ring-tool push'
 
-- name: push rings to standalone and restart swift services
+- name: push rings to controller nodes and restart swift services
   ansible.builtin.shell: |
     {{ shell_header }}
     {{ oc_header }}
     CONTROLLER1_SSH="{{ controller1_ssh }}"
+    CONTROLLER2_SSH="{{ controller2_ssh }}"
+    CONTROLLER3_SSH="{{ controller3_ssh }}"
+
     oc extract --confirm cm/swift-ring-files
-    $CONTROLLER1_SSH "tar -C /var/lib/config-data/puppet-generated/swift/etc/swift/ -xzf -" < swiftrings.tar.gz
-    $CONTROLLER1_SSH "systemctl restart tripleo_swift_*"
+
+    for i in {1..3}; do
+        SSH_CMD="CONTROLLER${i}_SSH"
+        if [ ! -z "${!SSH_CMD}" ]; then
+            ${!SSH_CMD} "tar -C /var/lib/config-data/puppet-generated/swift/etc/swift/ -xzf -" < swiftrings.tar.gz
+            ${!SSH_CMD} "systemctl restart tripleo_swift_*"
+        fi
+    done
 
 - name: wait until all replicas are 100% available after rebalance
   ansible.builtin.shell: |