Merge pull request #899 from stackhpc/zed-yoga-merge

zed: yoga merge

Author: markgoddard

etc/kayobe/ansible/reset-bls-entries.yml

@@ -0,0 +1,39 @@
+---
+# Custom playbook to reset Boot Loader Specification (BLS) entries to resolve
+# an issue with GRUB defaulting to an old kernel. This is adapted from a Bash
+# script in diskimage-builder:
+# https://opendev.org/openstack/diskimage-builder/src/branch/master/diskimage_builder/elements/rhel/post-install.d/03-reset-bls-entries
+
+- name: Reset BLS entries
+  hosts: overcloud
+  become: true
+  tags:
+    - reset-bls-entries
+  tasks:
+    - name: Get machine ID
+      command: cat /etc/machine-id
+      register: machine_id
+      check_mode: false
+
+    - name: Find entries with wrong machine ID
+      ansible.builtin.find:
+        paths: /boot/loader/entries
+        patterns: "*.conf"
+      register: bls_entries
+      check_mode: false
+
+    # We set force to false to avoid replacing an existing BLS entry with the
+    # correct machine ID.
+    - name: Rename entries with wrong machine ID
+      copy:
+        src: "/boot/loader/entries/{{ item }}"
+        dest: "/boot/loader/entries/{{ item | ansible.builtin.regex_replace('^[a-f0-9]*', machine_id.stdout) }}"
+        force: false
+        remote_src: true
+      with_items: "{{ bls_entries.files | map(attribute='path') | reject('search', machine_id.stdout) | map('basename') }}"
+
+    - name: Remove entries with wrong machine ID
+      file:
+        path: "/boot/loader/entries/{{ item }}"
+        state: absent
+      with_items: "{{ bls_entries.files | map(attribute='path') | reject('search', machine_id.stdout) | map('basename') }}"

etc/kayobe/environments/ci-aio/automated-setup.sh

@@ -7,6 +7,7 @@ cat << EOF | sudo tee -a /etc/hosts
 EOF
 
 if sudo vgdisplay | grep -q lvm2; then
+   sudo pvresize $(sudo pvs --noheadings | head -n 1 | awk '{print $1}')
    sudo lvextend -L 4G /dev/rootvg/lv_home -r || true
    sudo lvextend -L 4G /dev/rootvg/lv_tmp -r || true
 fi

etc/kayobe/kolla/config/prometheus/cadvisor.rules

@@ -33,15 +33,6 @@ groups:
       summary: "Container Volume usage (instance {{ $labels.instance }})"
       description: "Container Volume usage is above 80%"
 
-  - alert: ContainerVolumeIoUsage
-    expr: (sum(container_fs_io_current{name!=""}) BY (instance, name) * 100) > 80
-    for: 5m
-    labels:
-      severity: warning
-    annotations:
-      summary: "Container Volume IO usage (instance {{ $labels.instance }})"
-      description: "Container Volume IO usage is above 80%"
-
   - alert: ContainerHighThrottleRate
     expr: rate(container_cpu_cfs_throttled_seconds_total[3m]) > 1
     for: 1m

releasenotes/notes/removes-bogus-ContainerVolumeUsage-alert-c973b61f598d85e5.yaml

@@ -0,0 +1,5 @@
+---
+fixes:
+  - |
+    Removes bogus ContainerVolumeUsage alert. This rule wasn't correctly measuring
+    container volume IO and could cause spurious alerts.

releasenotes/notes/reset-bls-entries-b2bded62c5887937.yaml

@@ -0,0 +1,7 @@
+---
+fixes:
+  - |
+    Add a new ``reset-bls-entries.yml`` custom playbook which will rename
+    existing Boot Loader Specification (BLS) entries using the current machine
+    ID for each host. This should fix an issue with Grub not selecting the most
+    recent kernel during boot.