Add in-place upgrades & rollbacks with charm-refresh (#866)

Uses `charm-refresh` Python package: https://github.com/canonical/charm-refresh

Only supports refreshing to/from postgresql charm code with refresh v3

Author: carlcsaposs-canonical

.github/workflows/approve_renovate_pr.yaml

@@ -10,6 +10,6 @@ on:
 jobs:
   approve-pr:
     name: Approve Renovate pull request
-    uses: canonical/data-platform-workflows/.github/workflows/approve_renovate_pr.yaml@v31.0.1
+    uses: canonical/data-platform-workflows/.github/workflows/approve_renovate_pr.yaml@v32.0.0
     permissions:
       pull-requests: write  # Needed to approve PR

.github/workflows/check_pr.yaml

@@ -16,4 +16,4 @@ on:
 jobs:
   check-pr:
     name: Check pull request
-    uses: canonical/data-platform-workflows/.github/workflows/check_charm_pr.yaml@v31.0.1
+    uses: canonical/data-platform-workflows/.github/workflows/check_charm_pr.yaml@v32.0.0

.github/workflows/ci.yaml

@@ -27,7 +27,7 @@ on:
 jobs:
   lint:
     name: Lint
-    uses: canonical/data-platform-workflows/.github/workflows/lint.yaml@v31.0.1
+    uses: canonical/data-platform-workflows/.github/workflows/lint.yaml@v32.0.0
 
   unit-test:
     name: Unit test charm
@@ -49,7 +49,7 @@ jobs:
 
   build:
     name: Build charm
-    uses: canonical/data-platform-workflows/.github/workflows/build_charm.yaml@v31.0.1
+    uses: canonical/data-platform-workflows/.github/workflows/build_charm.yaml@v32.0.0
 
   integration-test:
     name: Integration test charm

.github/workflows/promote.yaml

@@ -25,7 +25,7 @@ on:
 jobs:
   promote:
     name: Promote charm
-    uses: canonical/data-platform-workflows/.github/workflows/_promote_charm.yaml@v31.0.1
+    uses: canonical/data-platform-workflows/.github/workflows/_promote_charm.yaml@v32.0.0
     with:
       track: '16'
       from-risk: ${{ inputs.from-risk }}

.github/workflows/release.yaml

@@ -1,6 +1,6 @@
 # Copyright 2023 Canonical Ltd.
 # See LICENSE file for licensing details.
-name: Release to Charmhub
+name: Release to Charmhub edge
 
 on:
   push:
@@ -16,8 +16,18 @@ on:
       - '.github/workflows/sync_docs.yaml'
 
 jobs:
+  tag:
+    name: Create charm refresh compatibility version git tag
+    uses: canonical/data-platform-workflows/.github/workflows/[email protected]
+    with:
+      track: '16'
+    permissions:
+      contents: write  # Needed to create git tag
+
   ci-tests:
     name: Tests
+    needs:
+      - tag
     uses: ./.github/workflows/ci.yaml
     secrets: inherit
     permissions:
@@ -26,10 +36,11 @@ jobs:
   release:
     name: Release charm
     needs:
+      - tag
       - ci-tests
-    uses: canonical/data-platform-workflows/.github/workflows/release_charm.yaml@v31.0.1
+    uses: canonical/data-platform-workflows/.github/workflows/release_charm_edge.yaml@v32.0.0
     with:
-      channel: ${{ github.ref_name }}
+      track: ${{ needs.tag.outputs.track }}
       artifact-prefix: ${{ needs.ci-tests.outputs.artifact-prefix }}
     secrets:
       charmhub-token: ${{ secrets.CHARMHUB_TOKEN }}

.github/workflows/sync_docs.yaml

@@ -10,7 +10,7 @@ on:
 jobs:
   sync-docs:
     name: Sync docs from Discourse
-    uses: canonical/data-platform-workflows/.github/workflows/sync_docs.yaml@v31.0.1
+    uses: canonical/data-platform-workflows/.github/workflows/sync_docs.yaml@v32.0.0
     with:
       reviewers: a-velasco,izmalk
     permissions:

actions.yaml

@@ -22,8 +22,61 @@ get-primary:
   description: Get the unit which is the primary/leader in the replication.
 list-backups:
   description: Lists backups in s3 storage.
-pre-upgrade-check:
-  description: Run necessary pre-upgrade checks and preparations before executing a charm refresh.
+pre-refresh-check:
+  description: Check if charm is ready to refresh
+  additionalProperties: false
+force-refresh-start:
+  description: |
+    Potential of data loss and downtime
+    
+    Force refresh of first unit
+    
+    Must run with at least one of the parameters `=false`
+  params:
+    check-compatibility:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime
+        
+        If `false`, force refresh if new version of PostgreSQL and/or charm is not compatible with previous version
+    run-pre-refresh-checks:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime
+        
+        If `false`, force refresh if app is unhealthy or not ready to refresh (and unit status shows "Pre-refresh check failed")
+    check-workload-container:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime during and after refresh
+        
+        If `false`, allow refresh to PostgreSQL container version that has not been validated to work with the charm revision
+  additionalProperties: false
+resume-refresh:
+  description: |
+    Refresh next unit(s) (after you have manually verified that refreshed units are healthy)
+    
+    If the `pause_after_unit_refresh` config is set to `all`, this action will refresh the next unit.
+    
+    If `pause_after_unit_refresh` is set to `first`, this action will refresh all remaining units.
+    Exception: if automatic health checks fail after a unit has refreshed, the refresh will pause.
+    
+    If `pause_after_unit_refresh` is set to `none`, this action will have no effect unless it is called with `check-health-of-refreshed-units` as `false`.
+  params:
+    check-health-of-refreshed-units:
+      type: boolean
+      default: true
+      description: |
+        Potential of data loss and downtime
+        
+        If `false`, force refresh (of next unit) if 1 or more refreshed units are unhealthy
+        
+        Warning: if first unit to refresh is unhealthy, consider running `force-refresh-start` action on that unit instead of using this parameter.
+        If first unit to refresh is unhealthy because compatibility checks, pre-refresh checks, or workload container checks are failing, this parameter is more destructive than the `force-refresh-start` action.
+  additionalProperties: false
 promote-to-primary:
   description: Promotes the cluster of choice to a primary cluster. Must be ran against the leader unit when promoting a cluster
    or against the unit to be promoted within the cluster.

charmcraft.yaml

@@ -84,8 +84,21 @@ parts:
   files:
     plugin: dump
     source: .
+    after:
+      - poetry-deps  # Ensure poetry is installed
+    build-packages:
+      - git
+    override-build: |
+      # Set `charm_version` in refresh_versions.toml from git tag
+      python3 -m venv refresh-version-venv
+      source refresh-version-venv/bin/activate
+      poetry install --only build-refresh-version
+      write-charm-version
+
+      craftctl default
     stage:
       - LICENSE
+      - refresh_versions.toml
       - scripts
       - templates
   libpq:

config.yaml

@@ -383,6 +383,12 @@ options:
       Allowed values are: from 0 to 1.80E+308.
     type: float
     default: 0.1
+  pause_after_unit_refresh:
+    description: |
+      Wait for manual confirmation to resume refresh after these units refresh
+      Allowed values: "all", "first", "none"
+    type: string
+    default: first
   plugin_address_standardizer_data_us_enable:
     default: false
     type: boolean