Create a must-gather for the operator

.chloggen/3149-add-must-gather.yaml

@@ -0,0 +1,25 @@
+# One of 'breaking', 'deprecation', 'new_component', 'enhancement', 'bug_fix'
+change_type: enhancement
+
+# The name of the component, or a single word describing the area of concern, (e.g. collector, target allocator, auto-instrumentation, opamp, github action)
+component: auto-instrumentation, collector
+
+# A brief description of the change. Surround your text with quotes ("") if it needs to start with a backtick (`).
+note: "Add a must gather utility to help troubleshoot"
+
+# One or more tracking issues related to the change
+issues: [3149]
+
+# (Optional) One or more lines of additional information to render under the primary note.
+# These lines will be padded with 2 spaces and then inserted directly into the document.
+# Use pipe (|) for multiline entries.
+subtext: |
+  The new utility is available as part of a new container image.
+
+  To use the image in a running OpenShift cluster, you need to run the following command:
+
+  ```sh
+  oc adm must-gather --image=ghcr.io/open-telemetry/opentelemetry-operator/must-gather -- /usr/bin/must-gather --operator-namespace opentelemetry-operator-system
+  ```
+
+  See the [README](https://github.com/open-telemetry/opentelemetry-operator/blob/main/cmd/gather/README.md) for more details.

.github/workflows/publish-must-gather.yaml

@@ -0,0 +1,86 @@
+name: "Publish must-gather image"
+
+on:
+  push:
+    branches: [ main ]
+    tags: [ 'v*' ]
+
+  workflow_dispatch:
+
+env:
+  PLATFORMS: linux/amd64,linux/arm64,linux/s390x,linux/ppc64le
+
+jobs:
+  publish:
+    name: Publish must-gather container image
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-go@v5
+        with:
+          go-version: '~1.22.4'
+
+      - name: Unshallow
+        run: git fetch --prune --unshallow
+
+      - name: Build the binary for each supported architecture
+        run: |
+          for platform in $(echo $PLATFORMS | tr "," "\n"); do
+            arch=${platform#*/}
+            echo "Building must-gather for $arch"
+            make must-gather ARCH=$arch
+          done
+
+      - name: Docker meta
+        id: docker_meta
+        uses: docker/metadata-action@v5
+        with:
+          images: |
+            ghcr.io/open-telemetry/opentelemetry-operator/must-gather
+          tags: |
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{raw}}
+            type=ref,event=branch
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v3
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Cache Docker layers
+        uses: actions/cache@v4
+        with:
+          path: /tmp/.buildx-cache
+          key: ${{ runner.os }}-buildx-${{ github.sha }}
+          restore-keys: |
+            ${{ runner.os }}-buildx-
+
+      - name: Log into Docker.io
+        uses: docker/login-action@v3
+        if: ${{ github.event_name == 'push' }}
+        with:
+          username: ${{ secrets.DOCKER_USERNAME }}
+          password: ${{ secrets.DOCKER_PASSWORD }}
+
+      - name: Login to GitHub Package Registry
+        uses: docker/login-action@v3
+        if: ${{ github.event_name == 'push' }}
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Build and push must-gather image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./cmd/gather/Dockerfile
+          platforms: ${{ env.PLATFORMS }}
+          push: ${{ github.event_name != 'pull_request' }}
+          tags: ${{ steps.docker_meta.outputs.tags }}
+          labels: ${{ steps.docker_meta.outputs.labels }}
+          cache-from: type=local,src=/tmp/.buildx-cache
+          cache-to: type=local,dest=/tmp/.buildx-cache

Makefile

@@ -38,6 +38,8 @@ OPERATOROPAMPBRIDGE_IMG ?= ${IMG_PREFIX}/${OPERATOROPAMPBRIDGE_IMG_REPO}:$(addpr
 BRIDGETESTSERVER_IMG_REPO ?= e2e-test-app-bridge-server
 BRIDGETESTSERVER_IMG ?= ${IMG_PREFIX}/${BRIDGETESTSERVER_IMG_REPO}:ve2e
 
+MUSTGATHER_IMG ?= ${IMG_PREFIX}/must-gather
+
 # Get the currently used golang install path (in GOPATH/bin, unless GOBIN is set)
 ifeq (,$(shell go env GOBIN))
 GOBIN=$(shell go env GOPATH)/bin
@@ -143,6 +145,10 @@ ci: generate fmt vet test ensure-generate-is-noop
 manager: generate
 	CGO_ENABLED=0 GOOS=$(GOOS) GOARCH=$(ARCH) go build -o bin/manager_${ARCH} -ldflags "${COMMON_LDFLAGS} ${OPERATOR_LDFLAGS}" main.go
 
+.PHONY: must-gather
+must-gather:
+	CGO_ENABLED=0 GOOS=$(GOOS) GOARCH=$(ARCH) go build -o bin/must-gather_${ARCH} -ldflags "${COMMON_LDFLAGS}" ./cmd/gather/main.go
+
 # Build target allocator binary
 .PHONY: targetallocator
 targetallocator:
@@ -362,6 +368,15 @@ container-bridge-test-server: GOOS = linux
 container-bridge-test-server:
 	docker build --load -t ${BRIDGETESTSERVER_IMG} tests/test-e2e-apps/bridge-server
 
+.PHONY: container-must-gather
+container-must-gather: GOOS = linux
+container-must-gather: must-gather
+	docker build -f cmd/gather/Dockerfile --load -t ${MUSTGATHER_IMG} .
+
+.PHONY: container-must-gather-push
+container-must-gather-push:
+	docker push ${MUSTGATHER_IMG}
+
 .PHONY: start-kind
 start-kind: kind
 ifeq (true,$(START_KIND_CLUSTER))
@@ -388,7 +403,6 @@ else
 	$(MAKE) container-push
 endif
 
-
 .PHONY: load-image-target-allocator
 load-image-target-allocator: container-target-allocator kind
 ifeq (true,$(START_KIND_CLUSTER))

cmd/gather/Dockerfile

@@ -0,0 +1,16 @@
+FROM registry.access.redhat.com/ubi9-minimal:9.2
+
+RUN INSTALL_PKGS=" \
+  rsync \
+  tar \
+  " && \
+  microdnf install -y $INSTALL_PKGS && \
+  microdnf clean all
+WORKDIR /
+
+ARG TARGETARCH
+COPY bin/must-gather_${TARGETARCH} /usr/bin/must-gather
+
+USER 65532:65532
+
+ENTRYPOINT ["/usr/bin/must-gather"]

cmd/gather/README.md

@@ -0,0 +1,36 @@
+# OpenTelemetry Operator Must-Gather
+
+The OpenTelemetry Operator `must-gather` tool is designed to collect comprehensive information about OpenTelemetry components within an OpenShift cluster. This utility extends the functionality of [OpenShift must-gather](https://github.com/openshift/must-gather) by specifically targeting and retrieving data related to the OpenTelemetry Operator, helping in diagnostics and troubleshooting.
+
+Note that you can use this utility too to gather information about the objects deployed by the OpenTelemetry Operator if you don't use OpenShift.
+
+## What is a Must-Gather?
+
+The `must-gather` tool is a utility that collects logs, cluster information, and resource configurations related to a specific operator or application in an OpenShift cluster. It helps cluster administrators and developers diagnose issues by providing a snapshot of the cluster's state related to the targeted component. More information [in the official documentation](https://docs.openshift.com/container-platform/4.16/support/gathering-cluster-data.html).
+
+## Usage
+
+First, you will need to build and push the image:
+```sh
+make container-must-gather container-must-gather-push
+```
+
+To run the must-gather tool for the OpenTelemetry Operator, use one of the following commands, depending on how you want to source the image and the namespace where the operator is deployed.
+
+### Using the image from the Operator deployment
+
+This is the recommended way to do it if you are not using OpenShift.
+
+If you want to use the image in a running cluster, you need to run the following command:
+
+```sh
+oc adm must-gather --image=ghcr.io/open-telemetry/opentelemetry-operator/must-gather -- /usr/bin/must-gather --operator-namespace opentelemetry-operator-system
+```
+
+### Using it as a CLI
+
+You only need to build and run:
+```sh
+make must-gather
+./bin/must-gather_$(go env GOARCH) --help
+```