feat(ci): add static IPs and improve node deployment workflows (ZcashFoundation#8891)

gustavovalverde · web-flow · commit 39017c06d223 · 2025-02-13T15:51:04.000Z
This change enhances the GCP deployment workflows with several improvements: - Add static IP address support for long-running nodes - Implement dynamic network selection matrix - Add manual deployment trigger support - Update GCP configuration syntax for better compatibility - Remove redundant deploy-instance job - Improve environment labeling and log file handling The static IP addresses will help maintain stable network connectivity for long-running nodes, particularly important for testnet peer discovery. Fixes ZcashFoundation#8763
diff --git a/.github/workflows/cd-deploy-nodes-gcp.yml b/.github/workflows/cd-deploy-nodes-gcp.yml
@@ -226,13 +226,34 @@ jobs:
   # Runs:
   # - on every push to the `main` branch
   # - on every release, when it's published
+  # - on workflow_dispatch for manual deployments
+  
+  # Determine which networks to deploy based on the trigger
+  
+  
+  
+  :
+    runs-on: ubuntu-latest
+    outputs:
+      networks: ${{ steps.set-networks.outputs.matrix }}
+    steps:
+      - id: set-networks
+        run: |
+          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
+            # Manually triggered deployment: output a valid JSON array with the single chosen network.
+            echo "matrix=[\"${{ inputs.network }}\"]" >> $GITHUB_OUTPUT
+          else
+            echo 'matrix=["Mainnet","Testnet"]' >> $GITHUB_OUTPUT
+          fi
+
   deploy-nodes:
     strategy:
       matrix:
-        network: [Mainnet, Testnet]
+        network: ${{ fromJSON(needs.set-matrix.outputs.networks) }}
     name: Deploy ${{ matrix.network }} nodes
     needs:
       [
+        set-matrix,
         build,
         versioning,
         test-configuration-file,
@@ -247,7 +268,7 @@ jobs:
     permissions:
       contents: "read"
       id-token: "write"
-    if: ${{ !cancelled() && !failure() && ((github.event_name == 'push' && github.ref_name == 'main') || github.event_name == 'release') }}
+    if: ${{ !cancelled() && !failure() && ((github.event_name == 'push' && github.ref_name == 'main') || github.event_name == 'release' || github.event_name == 'workflow_dispatch') }}
 
     steps:
       - uses: actions/checkout@v4.2.2
@@ -264,7 +285,7 @@ jobs:
       # Labels in GCP are required to be in lowercase, but the blockchain network
       # uses sentence case, so we need to downcase the network.
       #
-      # Passes the lowercase network to subsequent steps using $NETWORK env variable.
+      # Passes lowercase network to subsequent steps using $NETWORK env variable.
       - name: Downcase network name for labels
         run: |
           NETWORK_CAPS="${{ matrix.network }}"
@@ -281,13 +302,26 @@ jobs:
       - name: Set up Cloud SDK
         uses: google-github-actions/setup-gcloud@v2.1.4
 
+      - name: Get static IP address for long-running nodes
+        # Now runs when triggered by a release or a manual workflow_dispatch event.
+        if: ${{ github.event_name == 'release' || github.event_name == 'workflow_dispatch' }}
+        run: |
+          set -e  # Exit immediately if a command exits with a non-zero status.
+          # Attempt to retrieve the static IP address for the network.
+          echo "IP_ADDRESS=$(gcloud compute addresses describe zebra-${NETWORK} --region ${{ vars.GCP_REGION }} --format='value(address)')" >> "$GITHUB_ENV"
+
       - name: Create instance template for ${{ matrix.network }}
         run: |
           if [ "${{ github.event_name }}" == "release" ]; then
             DISK_NAME="zebrad-cache-${NETWORK}"
           else
             DISK_NAME="zebrad-cache-${{ env.GITHUB_HEAD_REF_SLUG_URL || env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}-${NETWORK}"
           fi
+          if [ -n "${{ env.IP_ADDRESS }}" ]; then
+            IP_FLAG="--address=${{ env.IP_ADDRESS }}"
+          else
+            IP_FLAG=""
+          fi
           DISK_PARAMS="name=${DISK_NAME},device-name=${DISK_NAME},size=400GB,type=pd-balanced"
           if [ -n "${{ env.CACHED_DISK_NAME }}" ]; then
             DISK_PARAMS+=",image=${{ env.CACHED_DISK_NAME }}"
@@ -297,13 +331,22 @@ jobs:
             echo "No cached disk found for ${{ matrix.network }} in main branch"
             exit 1
           fi
+
+          # Set log file based on input or default
+          if [ "${{ github.event_name }}" == "workflow_dispatch" ]; then
+            LOG_FILE="${{ inputs.log_file }}"
+          else
+            LOG_FILE="${{ vars.CD_LOG_FILE }}"
+          fi
+
           gcloud compute instance-templates create-with-container zebrad-${{ needs.versioning.outputs.major_version || env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}-${NETWORK} \
           --machine-type ${{ vars.GCP_SMALL_MACHINE }} \
           --boot-disk-size=10GB \
           --boot-disk-type=pd-standard \
           --image-project=cos-cloud \
           --image-family=cos-stable \
-          --network-interface=subnet=${{ vars.GCP_SUBNETWORK }} \
+          --subnet=${{ vars.GCP_SUBNETWORK }} \
+          ${IP_FLAG} \
           --create-disk="${DISK_PARAMS}" \
           --container-mount-disk=mount-path='/home/zebra/.cache/zebra',name=${DISK_NAME},mode=rw \
           --container-stdin \
@@ -313,7 +356,7 @@ jobs:
           --service-account ${{ vars.GCP_DEPLOYMENTS_SA }} \
           --scopes cloud-platform \
           --metadata google-logging-enabled=true,google-logging-use-fluentbit=true,google-monitoring-enabled=true \
-          --labels=app=zebrad,environment=staging,network=${NETWORK},github_ref=${{ env.GITHUB_REF_SLUG_URL }} \
+          --labels=app=zebrad,environment=${{ github.event_name == 'workflow_dispatch' && 'qa' || 'staging' }},network=${NETWORK},github_ref=${{ env.GITHUB_REF_SLUG_URL }} \
           --tags zebrad
 
       # Check if our destination instance group exists already
@@ -344,95 +387,11 @@ jobs:
           --version template="zebrad-${{ needs.versioning.outputs.major_version || env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}-${NETWORK}" \
           --region "${{ vars.GCP_REGION }}"
 
-  # This jobs handles the deployment of a single node (1) in the configured GCP zone
-  # when an instance is required to test a specific commit
-  #
-  # Runs:
-  # - on request, using workflow_dispatch with regenerate-disks
-  #
-  # Note: this instances are not automatically replaced or deleted
-  deploy-instance:
-    name: Deploy single ${{ inputs.network }} instance
-    needs: [build, test-configuration-file, test-zebra-conf-path, get-disk-name]
-    runs-on: ubuntu-latest
-    timeout-minutes: 30
-    env:
-      CACHED_DISK_NAME: ${{ needs.get-disk-name.outputs.cached_disk_name }}
-    permissions:
-      contents: "read"
-      id-token: "write"
-    # Run even if we don't need a cached disk, but only when triggered by a workflow_dispatch
-    if: ${{ !failure() && github.event_name == 'workflow_dispatch' }}
-
-    steps:
-      - uses: actions/checkout@v4.2.2
-        with:
-          persist-credentials: false
-
-      - name: Inject slug/short variables
-        uses: rlespinasse/github-slug-action@v5
-        with:
-          short-length: 7
-
-      # Makes the Zcash network name lowercase.
-      #
-      # Labels in GCP are required to be in lowercase, but the blockchain network
-      # uses sentence case, so we need to downcase the network.
-      #
-      # Passes the lowercase network to subsequent steps using $NETWORK env variable.
-      - name: Downcase network name for labels
-        run: |
-          NETWORK_CAPS="${{ inputs.network }}"
-          echo "NETWORK=${NETWORK_CAPS,,}" >> "$GITHUB_ENV"
-
-      # Setup gcloud CLI
-      - name: Authenticate to Google Cloud
-        id: auth
-        uses: google-github-actions/auth@v2.1.8
-        with:
-          workload_identity_provider: "${{ vars.GCP_WIF }}"
-          service_account: "${{ vars.GCP_DEPLOYMENTS_SA }}"
-
-      - name: Set up Cloud SDK
-        uses: google-github-actions/setup-gcloud@v2.1.4
-
-      # Create instance template from container image
-      - name: Manual deploy of a single ${{ inputs.network }} instance running zebrad
-        run: |
-          DISK_NAME="zebrad-cache-${{ env.GITHUB_HEAD_REF_SLUG_URL || env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}-${NETWORK}"
-          DISK_PARAMS="name=${DISK_NAME},device-name=${DISK_NAME},size=400GB,type=pd-balanced"
-          if [ -n "${{ env.CACHED_DISK_NAME }}" ]; then
-            DISK_PARAMS+=",image=${{ env.CACHED_DISK_NAME }}"
-          elif [ ${{ !inputs.need_cached_disk && github.event_name == 'workflow_dispatch' }} ]; then
-           echo "No cached disk required"
-          else
-            echo "No cached disk found for ${{ matrix.network }} in main branch"
-            exit 1
-          fi
-          gcloud compute instances create-with-container "zebrad-${{ env.GITHUB_REF_SLUG_URL }}-${{ env.GITHUB_SHA_SHORT }}-${NETWORK}" \
-          --machine-type ${{ vars.GCP_SMALL_MACHINE }} \
-          --boot-disk-size=10GB \
-          --boot-disk-type=pd-standard \
-          --image-project=cos-cloud \
-          --image-family=cos-stable \
-          --network-interface=subnet=${{ vars.GCP_SUBNETWORK }} \
-          --create-disk="${DISK_PARAMS}" \
-          --container-mount-disk=mount-path='/home/zebra/.cache/zebra',name=${DISK_NAME},mode=rw \
-          --container-stdin \
-          --container-tty \
-          --container-image ${{ vars.GAR_BASE }}/zebrad@${{ needs.build.outputs.image_digest }} \
-          --container-env "NETWORK=${{ inputs.network }},LOG_FILE=${{ inputs.log_file }},SENTRY_DSN=${{ vars.SENTRY_DSN }}" \
-          --service-account ${{ vars.GCP_DEPLOYMENTS_SA }} \
-          --scopes cloud-platform \
-          --metadata google-logging-enabled=true,google-monitoring-enabled=true \
-          --labels=app=zebrad,environment=qa,network=${NETWORK},github_ref=${{ env.GITHUB_REF_SLUG_URL }} \
-          --tags zebrad \
-          --zone ${{ vars.GCP_ZONE }}
-
   failure-issue:
     name: Open or update issues for release failures
     # When a new job is added to this workflow, add it to this list.
-    needs: [versioning, build, deploy-nodes, deploy-instance]
+    needs: [ versioning, build, deploy-nodes ]
+
     # Only open tickets for failed or cancelled jobs that are not coming from PRs.
     # (PR statuses are already reported in the PR jobs list, and checked by GitHub's Merge Queue.)
     if: (failure() && github.event.pull_request == null) || (cancelled() && github.event.pull_request == null)
diff --git a/.github/workflows/manual-zcashd-deploy.yml b/.github/workflows/manual-zcashd-deploy.yml
@@ -73,7 +73,7 @@ jobs:
           --container-image electriccoinco/zcashd \
           --container-env ZCASHD_NETWORK="${{ inputs.network }}" \
           --machine-type ${{ vars.GCP_SMALL_MACHINE }} \
-          --network-interface=subnet=${{ vars.GCP_SUBNETWORK }} \
+          --subnet=${{ vars.GCP_SUBNETWORK }} \
           --service-account ${{ vars.GCP_DEPLOYMENTS_SA }} \
           --scopes cloud-platform \
           --labels=app=zcashd,environment=prod,network=${NETWORK},github_ref=${{ env.GITHUB_REF_SLUG_URL }} \
