feat(ci): add shadow-docker-build workflow for OS-49 Phase 3 (#964)

Signed-off-by: Jonas Toelke <jtoelke@nvidia.com>
2026-10-16 05:20:22 +08:00 · 2026-04-24 12:33:25 -07:00
parent 25c827d271
commit d331ed5117
1 changed files with 89 additions and 0 deletions
@@ -0,0 +1,89 @@
+name: Shadow — Docker Build (local driver + GHA cache)
+
+# OS-49 Phase 3 / PR 3 — non-blocking shadow of docker-build.yml.
+#
+# Exercises buildx's local (docker-container) driver plus GHA-cache
+# (type=gha, scoped per component+arch) so Docker builds no longer depend on
+# the in-cluster BuildKit pods. Per-arch matrix on nv-gha-runners; each job
+# builds a single platform natively (no QEMU). No multi-arch manifest
+# merging — that folds into the real cut-over in Phase 6.
+#
+# Plan, decision thresholds, and results: OS-127 Linear issue. Dispatch
+# manually 4–5 times after merge to collect cold + warm numbers.
+
+on:
+  push:
+    branches: [main]
+  workflow_dispatch:
+
+permissions:
+  contents: read
+  packages: read
+
+env:
+  MISE_GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+
+jobs:
+  shadow-build:
+    name: shadow ${{ matrix.component }} (${{ matrix.arch }})
+    strategy:
+      fail-fast: false
+      matrix:
+        component: [gateway, supervisor, cluster]
+        arch: [amd64, arm64]
+        include:
+          - arch: amd64
+            runner: linux-amd64-cpu8
+          - arch: arm64
+            runner: linux-arm64-cpu8
+    runs-on: ${{ matrix.runner }}
+    container:
+      image: ghcr.io/nvidia/openshell/ci:latest
+      credentials:
+        username: ${{ github.actor }}
+        password: ${{ secrets.GITHUB_TOKEN }}
+      options: --privileged
+      volumes:
+        - /var/run/docker.sock:/var/run/docker.sock
+    timeout-minutes: 45
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Mark workspace safe for git
+        run: git config --global --add safe.directory "$GITHUB_WORKSPACE"
+
+      - name: Install tools
+        run: mise install
+
+      - name: Set up buildx (local driver)
+        uses: ./.github/actions/setup-buildx
+        with:
+          driver: local
+
+      - name: Package Helm chart (cluster only)
+        if: matrix.component == 'cluster'
+        run: |
+          mkdir -p deploy/docker/.build/charts
+          helm package deploy/helm/openshell -d deploy/docker/.build/charts/
+
+      - name: Build ${{ matrix.component }} (${{ matrix.arch }})
+        # Matches docker-build.yml's default EXTRA_CARGO_FEATURES so CI image
+        # content is comparable. No --push: the shadow measures build/cache
+        # mechanics, not publish behavior. Multi-arch manifests are Phase 6.
+        run: |
+          docker buildx build \
+            --builder openshell \
+            --platform linux/${{ matrix.arch }} \
+            --cache-from type=gha,scope=${{ matrix.component }}-${{ matrix.arch }} \
+            --cache-to   type=gha,mode=max,scope=${{ matrix.component }}-${{ matrix.arch }} \
+            --build-arg EXTRA_CARGO_FEATURES=openshell-core/dev-settings \
+            --load \
+            --file deploy/docker/Dockerfile.images \
+            --target ${{ matrix.component }} \
+            .
+
+      - name: buildx du
+        if: always()
+        run: docker buildx du --builder openshell || true