Move header offset calculation to private values

The interface creation on macOS seems to be asynchronus why the tun.create methode somethimes failes becasue the interface is not ready yet. To work around this issue we introduce a retry on tun.create

.github/ISSUE_TEMPLATE/bug-issue-report.md

@@ -31,9 +31,14 @@ Please specify whether you use NetBird Cloud or self-host NetBird's control plan
 
 `netbird version`
 
-**NetBird status -d output:**
+**NetBird status -dA output:**
 
-If applicable, add the `netbird status -d' command output.
+If applicable, add the `netbird status -dA' command output.
+
+**Do you face any (non-mobile) client issues?**
+
+Please provide the file created by `netbird debug for 1m -AS`.
+We advise reviewing the anonymized files for any remaining PII.
 
 **Screenshots**
 

.github/workflows/golang-test-darwin.yml

@@ -1,4 +1,4 @@
-name: Test Code Linux
+name: Test Code Darwin
 
 on:
   push:
@@ -11,27 +11,29 @@ concurrency:
   cancel-in-progress: true
 
 jobs:
-  test_client_on_docker:
-    runs-on: ubuntu-20.04
+  test:
+    strategy:
+      matrix:
+        store: ['sqlite']
+    runs-on: macos-latest
     steps:
       - name: Install Go
         uses: actions/setup-go@v4
         with:
           go-version: "1.21.x"
+      - name: Checkout code
+        uses: actions/checkout@v3
 
       - name: Cache Go modules
         uses: actions/cache@v3
         with:
           path: ~/go/pkg/mod
-          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
+          key: macos-go-${{ hashFiles('**/go.sum') }}
           restore-keys: |
-            ${{ runner.os }}-go-
+            macos-go-
 
-      - name: Checkout code
-        uses: actions/checkout@v3
-
-      - name: Install dependencies
-        run: sudo apt update && sudo apt install -y -q libgtk-3-dev libayatana-appindicator3-dev libgl1-mesa-dev xorg-dev gcc-multilib libpcap-dev
+      - name: Install libpcap
+        run: brew install libpcap
 
       - name: Install modules
         run: go mod tidy
@@ -39,5 +41,5 @@ jobs:
       - name: check git status
         run: git --no-pager diff --exit-code
 
-      - name: Run test
-        run: go test ./client/internal/routemanager -run TestGetBestrouteFromStatuses
+      - name: Test
+        run: NETBIRD_STORE_ENGINE=${{ matrix.store }} go test -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' -timeout 5m -p 1 ./...

.github/workflows/golang-test-freebsd.yml

@@ -0,0 +1,46 @@
+
+name: Test Code FreeBSD
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+      - name: Test in FreeBSD
+        id: test
+        uses: vmactions/freebsd-vm@v1
+        with:
+          usesh: true
+          copyback: false
+          release: "14.1"
+          prepare: |
+            pkg install -y go
+
+          # -x - to print all executed commands
+          # -e - to faile on first error
+          run: |
+            set -e -x
+            time go build -o netbird client/main.go
+            # check all component except management, since we do not support management server on freebsd
+            time go test -timeout 1m -failfast ./base62/...
+            # NOTE: without -p1 `client/internal/dns` will fail becasue of `listen udp4 :33100: bind: address already in use`
+            time go test -timeout 8m -failfast -p 1 ./client/...
+            time go test -timeout 1m -failfast ./dns/...
+            time go test -timeout 1m -failfast ./encryption/...
+            time go test -timeout 1m -failfast ./formatter/...
+            time go test -timeout 1m -failfast ./iface/...
+            time go test -timeout 1m -failfast ./route/...
+            time go test -timeout 1m -failfast ./sharedsock/...
+            time go test -timeout 1m -failfast ./signal/...
+            time go test -timeout 1m -failfast ./util/...
+            time go test -timeout 1m -failfast ./version/...

.github/workflows/golang-test-linux.yml

@@ -0,0 +1,127 @@
+name: Test Code Linux
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    strategy:
+      matrix:
+        arch: [ '386','amd64' ]
+        store: [ 'sqlite', 'postgres']
+    runs-on: ubuntu-latest
+    steps:
+      - name: Install Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21.x"
+
+
+      - name: Cache Go modules
+        uses: actions/cache@v3
+        with:
+          path: ~/go/pkg/mod
+          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
+          restore-keys: |
+            ${{ runner.os }}-go-
+
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Install dependencies
+        run: sudo apt update && sudo apt install -y -q libgtk-3-dev libayatana-appindicator3-dev libgl1-mesa-dev xorg-dev gcc-multilib libpcap-dev
+
+      - name: Install 32-bit libpcap
+        if: matrix.arch == '386'
+        run: sudo dpkg --add-architecture i386 && sudo apt update && sudo apt-get install -y libpcap0.8-dev:i386
+
+      - name: Install modules
+        run: go mod tidy
+
+      - name: check git status
+        run: git --no-pager diff --exit-code
+
+      - name: Test
+        run: CGO_ENABLED=1 GOARCH=${{ matrix.arch }} NETBIRD_STORE_ENGINE=${{ matrix.store }} go test -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' -timeout 5m -p 1 ./...
+
+  test_client_on_docker:
+    runs-on: ubuntu-20.04
+    steps:
+      - name: Install Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21.x"
+
+      - name: Cache Go modules
+        uses: actions/cache@v3
+        with:
+          path: ~/go/pkg/mod
+          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
+          restore-keys: |
+            ${{ runner.os }}-go-
+
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Install dependencies
+        run: sudo apt update && sudo apt install -y -q libgtk-3-dev libayatana-appindicator3-dev libgl1-mesa-dev xorg-dev gcc-multilib libpcap-dev
+
+      - name: Install modules
+        run: go mod tidy
+
+      - name: check git status
+        run: git --no-pager diff --exit-code
+
+      - name: Generate Iface Test bin
+        run: CGO_ENABLED=0 go test -c -o iface-testing.bin ./iface/
+
+      - name: Generate Shared Sock Test bin
+        run: CGO_ENABLED=0 go test -c -o sharedsock-testing.bin ./sharedsock
+
+      - name: Generate RouteManager Test bin
+        run: CGO_ENABLED=0 go test -c -o routemanager-testing.bin  ./client/internal/routemanager
+
+      - name: Generate SystemOps Test bin
+        run: CGO_ENABLED=1 go test -c -o systemops-testing.bin -tags netgo -ldflags '-w -extldflags "-static -ldbus-1 -lpcap"' ./client/internal/routemanager/systemops
+
+      - name: Generate nftables Manager Test bin
+        run: CGO_ENABLED=0 go test -c -o nftablesmanager-testing.bin ./client/firewall/nftables/...
+
+      - name: Generate Engine Test bin
+        run: CGO_ENABLED=1 go test -c -o engine-testing.bin ./client/internal
+
+      - name: Generate Peer Test bin
+        run: CGO_ENABLED=0 go test -c -o peer-testing.bin ./client/internal/peer/...
+
+      - run: chmod +x *testing.bin
+
+      - name: Run Shared Sock tests in docker
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/sharedsock --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/sharedsock-testing.bin -test.timeout 5m -test.parallel 1
+
+      - name: Run Iface tests in docker
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/iface --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/iface-testing.bin -test.timeout 5m -test.parallel 1
+
+      - name: Run RouteManager tests in docker
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/client/internal/routemanager --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/routemanager-testing.bin  -test.timeout 5m -test.parallel 1
+
+      - name: Run SystemOps tests in docker
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/client/internal/routemanager/systemops --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/systemops-testing.bin  -test.timeout 5m -test.parallel 1
+
+      - name: Run nftables Manager tests in docker
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/client/firewall --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/nftablesmanager-testing.bin  -test.timeout 5m -test.parallel 1
+
+      - name: Run Engine tests in docker with file store
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/client/internal -e NETBIRD_STORE_ENGINE="jsonfile" --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/engine-testing.bin  -test.timeout 5m -test.parallel 1
+
+      - name: Run Engine tests in docker with sqlite store
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/client/internal -e NETBIRD_STORE_ENGINE="sqlite" --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/engine-testing.bin  -test.timeout 5m -test.parallel 1
+
+      - name: Run Peer tests in docker
+        run: docker run -t --cap-add=NET_ADMIN --privileged --rm -v $PWD:/ci -w /ci/client/internal/peer  --entrypoint /busybox/sh gcr.io/distroless/base:debug -c /ci/peer-testing.bin  -test.timeout 5m -test.parallel 1

.github/workflows/golang-test-windows.yml

@@ -0,0 +1,52 @@
+name: Test Code Windows
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+env:
+  downloadPath: '${{ github.workspace }}\temp'
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    runs-on: windows-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: Install Go
+        uses: actions/setup-go@v4
+        id: go
+        with:
+          go-version: "1.21.x"
+
+      - name: Download wintun
+        uses: carlosperate/download-file-action@v2
+        id: download-wintun
+        with:
+          file-url: https://pkgs.netbird.io/wintun/wintun-0.14.1.zip
+          file-name: wintun.zip
+          location: ${{ env.downloadPath }}
+          sha256: '07c256185d6ee3652e09fa55c0b673e2624b565e02c4b9091c79ca7d2f24ef51'
+
+      - name: Decompressing wintun files
+        run: tar -zvxf "${{ steps.download-wintun.outputs.file-path }}" -C ${{ env.downloadPath }}
+
+      - run: mv ${{ env.downloadPath }}/wintun/bin/amd64/wintun.dll 'C:\Windows\System32\'
+
+      - run: choco install -y sysinternals --ignore-checksums
+      - run: choco install -y mingw
+
+      - run: PsExec64 -s -w ${{ github.workspace }} C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe env -w GOMODCACHE=C:\Users\runneradmin\go\pkg\mod
+      - run: PsExec64 -s -w ${{ github.workspace }} C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe env -w GOCACHE=C:\Users\runneradmin\AppData\Local\go-build
+
+      - name: test
+        run: PsExec64 -s -w ${{ github.workspace }} cmd.exe /c "C:\hostedtoolcache\windows\go\${{ steps.go.outputs.go-version }}\x64\bin\go.exe test -timeout 10m -p 1 ./... > test-out.txt 2>&1"
+      - name: test output
+        if: ${{ always() }}
+        run: Get-Content test-out.txt

.github/workflows/golangci-lint.yml

@@ -0,0 +1,52 @@
+name: golangci-lint
+on: [pull_request]
+
+permissions:
+  contents: read
+  pull-requests: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  codespell:
+    name: codespell
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+      - name: codespell
+        uses: codespell-project/actions-codespell@v2
+        with:
+          ignore_words_list: erro,clienta,hastable,
+          skip: go.mod,go.sum
+          only_warn: 1
+  golangci:
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [macos-latest, windows-latest, ubuntu-latest]
+    name: lint
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 15
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+      - name: Check for duplicate constants
+        if: matrix.os == 'ubuntu-latest'
+        run: |
+          ! awk '/const \(/,/)/{print $0}' management/server/activity/codes.go | grep -o '= [0-9]*' | sort | uniq -d | grep .
+      - name: Install Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21.x"
+          cache: false
+      - name: Install dependencies
+        if: matrix.os == 'ubuntu-latest'
+        run: sudo apt update && sudo apt install -y -q libgtk-3-dev libayatana-appindicator3-dev libgl1-mesa-dev xorg-dev libpcap-dev
+      - name: golangci-lint
+        uses: golangci/golangci-lint-action@v3
+        with:
+          version: latest
+          args: --timeout=12m

.github/workflows/install-script-test.yml

@@ -0,0 +1,36 @@
+name: Test installation
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - "release_files/install.sh"
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+jobs:
+  test-install-script:
+    strategy:
+      max-parallel: 2
+      matrix:
+        os: [ubuntu-latest, macos-latest]
+        skip_ui_mode: [true, false]
+        install_binary: [true, false]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: run install script
+        env:
+          SKIP_UI_APP: ${{ matrix.skip_ui_mode }}
+          USE_BIN_INSTALL: ${{ matrix.install_binary }}
+          GITHUB_TOKEN: ${{ secrets.RO_API_CALLER_TOKEN }}
+        run: |
+          [ "$SKIP_UI_APP" == "false" ] && export XDG_CURRENT_DESKTOP="none"
+          cat release_files/install.sh | sh -x
+
+      - name: check cli binary
+        run: command -v netbird

.github/workflows/mobile-build-validation.yml

@@ -0,0 +1,65 @@
+name: Mobile build validation
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  android_build:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+      - name: Install Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21.x"
+      - name: Setup Android SDK
+        uses: android-actions/setup-android@v3
+        with:
+          cmdline-tools-version: 8512546
+      - name: Setup Java
+        uses: actions/setup-java@v3
+        with:
+          java-version: "11"
+          distribution: "adopt"
+      - name: NDK Cache
+        id: ndk-cache
+        uses: actions/cache@v3
+        with:
+          path: /usr/local/lib/android/sdk/ndk
+          key: ndk-cache-23.1.7779620
+      - name: Setup NDK
+        run: /usr/local/lib/android/sdk/cmdline-tools/7.0/bin/sdkmanager --install "ndk;23.1.7779620"
+      - name: install gomobile
+        run: go install golang.org/x/mobile/cmd/gomobile@v0.0.0-20240404231514-09dbf07665ed
+      - name: gomobile init
+        run: gomobile init
+      - name: build android netbird lib
+        run: PATH=$PATH:$(go env GOPATH) gomobile bind -o $GITHUB_WORKSPACE/netbird.aar -javapkg=io.netbird.gomobile -ldflags="-X golang.zx2c4.com/wireguard/ipc.socketDirectory=/data/data/io.netbird.client/cache/wireguard -X github.com/netbirdio/netbird/version.version=buildtest"  $GITHUB_WORKSPACE/client/android
+        env:
+          CGO_ENABLED: 0
+          ANDROID_NDK_HOME: /usr/local/lib/android/sdk/ndk/23.1.7779620
+  ios_build:
+    runs-on: macos-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v3
+      - name: Install Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21.x"
+      - name: install gomobile
+        run: go install golang.org/x/mobile/cmd/gomobile@v0.0.0-20240404231514-09dbf07665ed
+      - name: gomobile init
+        run: gomobile init
+      - name: build iOS netbird lib
+        run: PATH=$PATH:$(go env GOPATH) gomobile bind -target=ios -bundleid=io.netbird.framework -ldflags="-X github.com/netbirdio/netbird/version.version=buildtest" -o ./NetBirdSDK.xcframework ./client/ios/NetBirdSDK
+        env:
+          CGO_ENABLED: 0

.github/workflows/release.yml

@@ -0,0 +1,246 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - 'v*'
+    branches:
+      - main
+  pull_request:
+
+
+env:
+  SIGN_PIPE_VER: "v0.0.14"
+  GORELEASER_VER: "v1.14.1"
+  PRODUCT_NAME: "NetBird"
+  COPYRIGHT: "Wiretrustee UG (haftungsbeschreankt)"
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    env:
+      flags: ""
+    steps:
+      - name: Parse semver string
+        id: semver_parser
+        uses: booxmedialtd/ws-action-parse-semver@v1
+        with:
+          input_string: ${{ (startsWith(github.ref, 'refs/tags/v') && github.ref) || 'refs/tags/v0.0.0' }}
+          version_extractor_regex: '\/v(.*)$'
+
+      - if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
+        run: echo "flags=--snapshot" >> $GITHUB_ENV
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # It is required for GoReleaser to work properly
+      -
+        name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21"
+          cache: false
+      -
+        name: Cache Go modules
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/go/pkg/mod
+            ~/.cache/go-build
+          key: ${{ runner.os }}-go-releaser-${{ hashFiles('**/go.sum') }}
+          restore-keys: |
+            ${{ runner.os }}-go-releaser-
+      -
+        name: Install modules
+        run: go mod tidy
+      -
+        name: check git status
+        run: git --no-pager diff --exit-code
+      -
+        name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+      -
+        name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+      -
+        name: Login to Docker hub
+        if: github.event_name != 'pull_request'
+        uses: docker/login-action@v1
+        with:
+          username: netbirdio
+          password: ${{ secrets.DOCKER_TOKEN }}
+      - name: Install OS build dependencies
+        run: sudo apt update && sudo apt install -y -q gcc-arm-linux-gnueabihf gcc-aarch64-linux-gnu
+
+      - name: Install goversioninfo
+        run: go install github.com/josephspurrier/goversioninfo/cmd/goversioninfo@233067e
+      - name: Generate windows syso amd64
+        run: goversioninfo  -icon client/ui/netbird.ico -manifest client/manifest.xml -product-name ${{ env.PRODUCT_NAME }} -copyright "${{ env.COPYRIGHT }}" -ver-major ${{ steps.semver_parser.outputs.major }} -ver-minor ${{ steps.semver_parser.outputs.minor }} -ver-patch ${{ steps.semver_parser.outputs.patch }} -ver-build 0 -file-version ${{ steps.semver_parser.outputs.fullversion }}.0 -product-version ${{ steps.semver_parser.outputs.fullversion }}.0 -o client/resources_windows_amd64.syso
+      - name: Run GoReleaser
+        uses: goreleaser/goreleaser-action@v4
+        with:
+          version: ${{ env.GORELEASER_VER }}
+          args: release --rm-dist ${{ env.flags }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          HOMEBREW_TAP_GITHUB_TOKEN: ${{ secrets.HOMEBREW_TAP_GITHUB_TOKEN }}
+          UPLOAD_DEBIAN_SECRET: ${{ secrets.PKG_UPLOAD_SECRET }}
+          UPLOAD_YUM_SECRET: ${{ secrets.PKG_UPLOAD_SECRET }}
+      -
+        name: upload non tags for debug purposes
+        uses: actions/upload-artifact@v3
+        with:
+          name: release
+          path: dist/
+          retention-days: 3
+      -
+        name: upload linux packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: linux-packages
+          path: dist/netbird_linux**
+          retention-days: 3
+      -
+        name: upload windows packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: windows-packages
+          path: dist/netbird_windows**
+          retention-days: 3
+      -
+        name: upload macos packages
+        uses: actions/upload-artifact@v3
+        with:
+          name: macos-packages
+          path: dist/netbird_darwin**
+          retention-days: 3
+
+  release_ui:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Parse semver string
+        id: semver_parser
+        uses: booxmedialtd/ws-action-parse-semver@v1
+        with:
+          input_string: ${{ (startsWith(github.ref, 'refs/tags/v') && github.ref) || 'refs/tags/v0.0.0' }}
+          version_extractor_regex: '\/v(.*)$'
+
+      - if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
+        run: echo "flags=--snapshot" >> $GITHUB_ENV
+      - name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # It is required for GoReleaser to work properly
+
+      - name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21"
+          cache: false
+      - name: Cache Go modules
+        uses: actions/cache@v3
+        with:
+          path: | 
+            ~/go/pkg/mod
+            ~/.cache/go-build
+          key: ${{ runner.os }}-ui-go-releaser-${{ hashFiles('**/go.sum') }}
+          restore-keys: |
+            ${{ runner.os }}-ui-go-releaser-
+
+      - name: Install modules
+        run: go mod tidy
+
+      - name: check git status
+        run: git --no-pager diff --exit-code
+
+      - name: Install dependencies
+        run: sudo apt update && sudo apt install -y -q libappindicator3-dev gir1.2-appindicator3-0.1 libxxf86vm-dev gcc-mingw-w64-x86-64
+      - name: Install goversioninfo
+        run: go install github.com/josephspurrier/goversioninfo/cmd/goversioninfo@233067e
+      - name: Generate windows syso amd64
+        run: goversioninfo -64 -icon client/ui/netbird.ico -manifest client/ui/manifest.xml -product-name ${{ env.PRODUCT_NAME }}-"UI" -copyright "${{ env.COPYRIGHT }}" -ver-major ${{ steps.semver_parser.outputs.major }} -ver-minor ${{ steps.semver_parser.outputs.minor }} -ver-patch ${{ steps.semver_parser.outputs.patch }} -ver-build 0 -file-version ${{ steps.semver_parser.outputs.fullversion }}.0 -product-version ${{ steps.semver_parser.outputs.fullversion }}.0 -o client/ui/resources_windows_amd64.syso
+
+      - name: Run GoReleaser
+        uses: goreleaser/goreleaser-action@v4
+        with:
+          version: ${{ env.GORELEASER_VER }}
+          args: release --config .goreleaser_ui.yaml --rm-dist ${{ env.flags }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          HOMEBREW_TAP_GITHUB_TOKEN: ${{ secrets.HOMEBREW_TAP_GITHUB_TOKEN }}
+          UPLOAD_DEBIAN_SECRET: ${{ secrets.PKG_UPLOAD_SECRET }}
+          UPLOAD_YUM_SECRET: ${{ secrets.PKG_UPLOAD_SECRET }}
+      - name: upload non tags for debug purposes
+        uses: actions/upload-artifact@v3
+        with:
+          name: release-ui
+          path: dist/
+          retention-days: 3
+
+  release_ui_darwin:
+    runs-on: macos-latest
+    steps:
+      - if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
+        run: echo "flags=--snapshot" >> $GITHUB_ENV
+      -
+        name: Checkout
+        uses: actions/checkout@v3
+        with:
+          fetch-depth: 0 # It is required for GoReleaser to work properly
+      -
+        name: Set up Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21"
+          cache: false
+      -
+        name: Cache Go modules
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/go/pkg/mod
+            ~/.cache/go-build
+          key: ${{ runner.os }}-ui-go-releaser-darwin-${{ hashFiles('**/go.sum') }}
+          restore-keys: |
+            ${{ runner.os }}-ui-go-releaser-darwin-
+      -
+        name: Install modules
+        run: go mod tidy
+      - 
+        name: check git status
+        run: git --no-pager diff --exit-code
+      -
+        name: Run GoReleaser
+        id: goreleaser
+        uses: goreleaser/goreleaser-action@v4
+        with:
+          version: ${{ env.GORELEASER_VER }}
+          args: release --config .goreleaser_ui_darwin.yaml --rm-dist ${{ env.flags }}
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+      -
+        name: upload non tags for debug purposes
+        uses: actions/upload-artifact@v3
+        with:
+          name: release-ui-darwin
+          path: dist/
+          retention-days: 3
+
+  trigger_signer:
+    runs-on: ubuntu-latest
+    needs: [release,release_ui,release_ui_darwin]
+    if: startsWith(github.ref, 'refs/tags/')
+    steps:
+      - name: Trigger binaries sign pipelines
+        uses: benc-uk/workflow-dispatch@v1
+        with:
+          workflow: Sign bin and installer
+          repo: netbirdio/sign-pipelines
+          ref: ${{ env.SIGN_PIPE_VER }}
+          token: ${{ secrets.SIGN_GITHUB_TOKEN }}
+          inputs: '{ "tag": "${{ github.ref }}" }'

.github/workflows/sync-main.yml

@@ -0,0 +1,22 @@
+name: sync main
+
+on:
+  push:
+    branches:
+      - main
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  trigger_sync_main:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger main branch sync
+        uses: benc-uk/workflow-dispatch@v1
+        with:
+          workflow: sync-main.yml
+          repo: ${{ secrets.UPSTREAM_REPO }}
+          token: ${{ secrets.NC_GITHUB_TOKEN }}
+          inputs: '{ "sha": "${{ github.sha }}" }'

.github/workflows/sync-tag.yml

@@ -0,0 +1,23 @@
+name: sync tag
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  trigger_sync_tag:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Trigger release tag sync
+        uses: benc-uk/workflow-dispatch@v1
+        with:
+          workflow: sync-tag.yml
+          ref: main
+          repo: ${{ secrets.UPSTREAM_REPO }}
+          token: ${{ secrets.NC_GITHUB_TOKEN }}
+          inputs: '{ "tag": "${{ github.ref_name }}" }'

.github/workflows/test-infrastructure-files.yml

@@ -0,0 +1,293 @@
+name: Test Infrastructure files
+
+on:
+  push:
+    branches:
+      - main
+  pull_request:
+    paths:
+      - 'infrastructure_files/**'
+      - '.github/workflows/test-infrastructure-files.yml'
+      - 'management/cmd/**'
+      - 'signal/cmd/**'
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  test-docker-compose:
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        store: [ 'sqlite', 'postgres' ]
+    services:
+      postgres:
+        image: ${{ (matrix.store == 'postgres') && 'postgres' || '' }}
+        env:
+          POSTGRES_USER: netbird
+          POSTGRES_PASSWORD: postgres
+          POSTGRES_DB: netbird
+        options: >-
+          --health-cmd pg_isready
+          --health-interval 10s
+          --health-timeout 5s
+        ports:
+          - 5432:5432
+    steps:
+      - name: Set Database Connection String
+        run: |
+          if [ "${{ matrix.store }}" == "postgres" ]; then
+            echo "NETBIRD_STORE_ENGINE_POSTGRES_DSN=host=$(hostname -I | awk '{print $1}') user=netbird password=postgres dbname=netbird port=5432" >> $GITHUB_ENV
+          else
+            echo "NETBIRD_STORE_ENGINE_POSTGRES_DSN==" >> $GITHUB_ENV
+          fi
+
+      - name: Install jq
+        run: sudo apt-get install -y jq
+
+      - name: Install curl
+        run: sudo apt-get install -y curl
+
+      - name: Install Go
+        uses: actions/setup-go@v4
+        with:
+          go-version: "1.21.x"
+
+      - name: Cache Go modules
+        uses: actions/cache@v3
+        with:
+          path: ~/go/pkg/mod
+          key: ${{ runner.os }}-go-${{ hashFiles('**/go.sum') }}
+          restore-keys: |
+            ${{ runner.os }}-go-
+
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: cp setup.env
+        run: cp infrastructure_files/tests/setup.env infrastructure_files/
+
+      - name: run configure
+        working-directory: infrastructure_files
+        run: bash -x configure.sh
+        env:
+          CI_NETBIRD_DOMAIN: localhost
+          CI_NETBIRD_AUTH_CLIENT_ID: testing.client.id
+          CI_NETBIRD_AUTH_CLIENT_SECRET: testing.client.secret
+          CI_NETBIRD_AUTH_AUDIENCE: testing.ci
+          CI_NETBIRD_AUTH_OIDC_CONFIGURATION_ENDPOINT: https://example.eu.auth0.com/.well-known/openid-configuration
+          CI_NETBIRD_USE_AUTH0: true
+          CI_NETBIRD_MGMT_IDP: "none"
+          CI_NETBIRD_IDP_MGMT_CLIENT_ID: testing.client.id
+          CI_NETBIRD_IDP_MGMT_CLIENT_SECRET: testing.client.secret
+          CI_NETBIRD_AUTH_SUPPORTED_SCOPES: "openid profile email offline_access api email_verified"
+          CI_NETBIRD_STORE_CONFIG_ENGINE: ${{ matrix.store }}
+          NETBIRD_STORE_ENGINE_POSTGRES_DSN: ${{ env.NETBIRD_STORE_ENGINE_POSTGRES_DSN }}
+          CI_NETBIRD_MGMT_IDP_SIGNKEY_REFRESH: false
+
+      - name: check values
+        working-directory: infrastructure_files/artifacts
+        env:
+          CI_NETBIRD_DOMAIN: localhost
+          CI_NETBIRD_AUTH_CLIENT_ID: testing.client.id
+          CI_NETBIRD_AUTH_CLIENT_SECRET: testing.client.secret
+          CI_NETBIRD_AUTH_AUDIENCE: testing.ci
+          CI_NETBIRD_AUTH_OIDC_CONFIGURATION_ENDPOINT: https://example.eu.auth0.com/.well-known/openid-configuration
+          CI_NETBIRD_USE_AUTH0: true
+          CI_NETBIRD_AUTH_SUPPORTED_SCOPES: "openid profile email offline_access api email_verified"
+          CI_NETBIRD_AUTH_AUTHORITY: https://example.eu.auth0.com/
+          CI_NETBIRD_AUTH_JWT_CERTS: https://example.eu.auth0.com/.well-known/jwks.json
+          CI_NETBIRD_AUTH_TOKEN_ENDPOINT: https://example.eu.auth0.com/oauth/token
+          CI_NETBIRD_AUTH_DEVICE_AUTH_ENDPOINT: https://example.eu.auth0.com/oauth/device/code
+          CI_NETBIRD_AUTH_PKCE_AUTHORIZATION_ENDPOINT: https://example.eu.auth0.com/authorize
+          CI_NETBIRD_AUTH_REDIRECT_URI: "/peers"
+          CI_NETBIRD_TOKEN_SOURCE: "idToken"
+          CI_NETBIRD_AUTH_USER_ID_CLAIM: "email"
+          CI_NETBIRD_AUTH_DEVICE_AUTH_AUDIENCE: "super"
+          CI_NETBIRD_AUTH_DEVICE_AUTH_SCOPE: "openid email"
+          CI_NETBIRD_MGMT_IDP: "none"
+          CI_NETBIRD_IDP_MGMT_CLIENT_ID: testing.client.id
+          CI_NETBIRD_IDP_MGMT_CLIENT_SECRET: testing.client.secret
+          CI_NETBIRD_SIGNAL_PORT: 12345
+          CI_NETBIRD_STORE_CONFIG_ENGINE: ${{ matrix.store }}
+          NETBIRD_STORE_ENGINE_POSTGRES_DSN: '${{ env.NETBIRD_STORE_ENGINE_POSTGRES_DSN }}$'
+          CI_NETBIRD_MGMT_IDP_SIGNKEY_REFRESH: false
+          CI_NETBIRD_TURN_EXTERNAL_IP: "1.2.3.4"
+
+        run: |
+          set -x
+          grep AUTH_CLIENT_ID docker-compose.yml | grep $CI_NETBIRD_AUTH_CLIENT_ID
+          grep AUTH_CLIENT_SECRET docker-compose.yml | grep $CI_NETBIRD_AUTH_CLIENT_SECRET
+          grep AUTH_AUTHORITY docker-compose.yml | grep $CI_NETBIRD_AUTH_AUTHORITY
+          grep AUTH_AUDIENCE docker-compose.yml | grep $CI_NETBIRD_AUTH_AUDIENCE
+          grep AUTH_SUPPORTED_SCOPES docker-compose.yml | grep "$CI_NETBIRD_AUTH_SUPPORTED_SCOPES"
+          grep USE_AUTH0 docker-compose.yml | grep $CI_NETBIRD_USE_AUTH0
+          grep NETBIRD_MGMT_API_ENDPOINT docker-compose.yml | grep "$CI_NETBIRD_DOMAIN:33073"
+          grep AUTH_REDIRECT_URI docker-compose.yml | grep $CI_NETBIRD_AUTH_REDIRECT_URI
+          grep AUTH_SILENT_REDIRECT_URI docker-compose.yml | egrep 'AUTH_SILENT_REDIRECT_URI=$'
+          grep $CI_NETBIRD_SIGNAL_PORT docker-compose.yml | grep ':80'
+          grep LETSENCRYPT_DOMAIN docker-compose.yml | egrep 'LETSENCRYPT_DOMAIN=$'
+          grep NETBIRD_TOKEN_SOURCE docker-compose.yml | grep $CI_NETBIRD_TOKEN_SOURCE
+          grep AuthUserIDClaim management.json | grep $CI_NETBIRD_AUTH_USER_ID_CLAIM
+          grep -A 3 DeviceAuthorizationFlow management.json | grep -A 1 ProviderConfig | grep Audience | grep $CI_NETBIRD_AUTH_DEVICE_AUTH_AUDIENCE
+          grep -A 3 DeviceAuthorizationFlow management.json | grep -A 1 ProviderConfig | grep Audience | grep $CI_NETBIRD_AUTH_DEVICE_AUTH_AUDIENCE
+          grep Engine management.json  | grep "$CI_NETBIRD_STORE_CONFIG_ENGINE"
+          grep IdpSignKeyRefreshEnabled management.json | grep "$CI_NETBIRD_MGMT_IDP_SIGNKEY_REFRESH"
+          grep UseIDToken management.json | grep false
+          grep -A 1 IdpManagerConfig management.json | grep ManagerType | grep $CI_NETBIRD_MGMT_IDP
+          grep -A 3 IdpManagerConfig management.json | grep -A 1 ClientConfig | grep Issuer | grep $CI_NETBIRD_AUTH_AUTHORITY
+          grep -A 4 IdpManagerConfig management.json | grep -A 2 ClientConfig | grep TokenEndpoint | grep $CI_NETBIRD_AUTH_TOKEN_ENDPOINT
+          grep -A 5 IdpManagerConfig management.json | grep -A 3 ClientConfig | grep ClientID | grep $CI_NETBIRD_IDP_MGMT_CLIENT_ID
+          grep -A 6 IdpManagerConfig management.json | grep -A 4 ClientConfig | grep ClientSecret | grep $CI_NETBIRD_IDP_MGMT_CLIENT_SECRET
+          grep -A 7 IdpManagerConfig management.json | grep -A 5 ClientConfig | grep GrantType | grep client_credentials
+          grep -A 10 PKCEAuthorizationFlow management.json | grep -A 10 ProviderConfig | grep Audience | grep $CI_NETBIRD_AUTH_AUDIENCE
+          grep -A 10 PKCEAuthorizationFlow management.json | grep -A 10 ProviderConfig | grep ClientID | grep $CI_NETBIRD_AUTH_CLIENT_ID
+          grep -A 10 PKCEAuthorizationFlow management.json | grep -A 10 ProviderConfig | grep ClientSecret | grep $CI_NETBIRD_AUTH_CLIENT_SECRET
+          grep -A 10 PKCEAuthorizationFlow management.json | grep -A 10 ProviderConfig | grep AuthorizationEndpoint | grep $CI_NETBIRD_AUTH_PKCE_AUTHORIZATION_ENDPOINT
+          grep -A 10 PKCEAuthorizationFlow management.json | grep -A 10 ProviderConfig | grep TokenEndpoint | grep $CI_NETBIRD_AUTH_TOKEN_ENDPOINT
+          grep -A 10 PKCEAuthorizationFlow management.json | grep -A 10 ProviderConfig | grep Scope | grep "$CI_NETBIRD_AUTH_SUPPORTED_SCOPES"
+          grep -A 10 PKCEAuthorizationFlow management.json | grep -A 10 ProviderConfig | grep -A 3 RedirectURLs | grep "http://localhost:53000"
+          grep "external-ip" turnserver.conf | grep $CI_NETBIRD_TURN_EXTERNAL_IP
+          grep NETBIRD_STORE_ENGINE_POSTGRES_DSN docker-compose.yml | egrep "$NETBIRD_STORE_ENGINE_POSTGRES_DSN"
+          # check relay values
+          grep "NB_EXPOSED_ADDRESS=$CI_NETBIRD_DOMAIN:33445" docker-compose.yml
+          grep "NB_LISTEN_ADDRESS=:33445" docker-compose.yml
+          grep '33445:33445' docker-compose.yml
+          grep -A 10 'relay:' docker-compose.yml | egrep 'NB_AUTH_SECRET=.+$'
+          grep -A 7 Relay management.json | grep "rel://$CI_NETBIRD_DOMAIN:33445"
+          grep -A 7 Relay management.json | egrep '"Secret": ".+"'
+
+      - name: Install modules
+        run: go mod tidy
+
+      - name: check git status
+        run: git --no-pager diff --exit-code
+
+      - name: Build management binary
+        working-directory: management
+        run: CGO_ENABLED=1 go build -o netbird-mgmt main.go
+
+      - name: Build management docker image
+        working-directory: management
+        run: |
+          docker build -t netbirdio/management:latest .
+
+      - name: Build signal binary
+        working-directory: signal
+        run: CGO_ENABLED=0 go build -o netbird-signal main.go
+
+      - name: Build signal docker image
+        working-directory: signal
+        run: |
+          docker build -t netbirdio/signal:latest .
+
+      - name: Build relay binary
+        working-directory: relay
+        run: CGO_ENABLED=0 go build -o netbird-relay main.go
+
+      - name: Build relay docker image
+        working-directory: relay
+        run: |
+          docker build -t netbirdio/relay:latest .
+
+      - name: run docker compose up
+        working-directory: infrastructure_files/artifacts
+        run: |
+          docker compose up -d
+          sleep 5
+          docker compose ps
+          docker compose logs --tail=20
+
+      - name: test running containers
+        run: |
+          count=$(docker compose ps --format json | jq '. | select(.Name | contains("artifacts")) | .State' | grep -c running)
+          test $count -eq 5 || docker compose logs
+        working-directory: infrastructure_files/artifacts
+
+      - name: test geolocation databases
+        working-directory: infrastructure_files/artifacts
+        run: |
+          sleep 30
+          docker compose exec management ls -l /var/lib/netbird/ | grep -i GeoLite2-City_[0-9]*.mmdb
+          docker compose exec management ls -l /var/lib/netbird/ | grep -i geonames_[0-9]*.db
+
+  test-getting-started-script:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Install jq
+        run: sudo apt-get install -y jq
+
+      - name: Checkout code
+        uses: actions/checkout@v3
+
+      - name: handle insisting image   # remove after release
+        run: docker pull netbirdio/relay:latest || docker pull netbirdio/signal:latest && docker tag netbirdio/signal:latest netbirdio/relay:latest
+
+      - name: run script with Zitadel PostgreSQL
+        run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh
+
+      - name: test Caddy file gen postgres
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen postgres
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen postgres
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen postgres
+        run: |
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen postgres
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen postgres
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen postgres
+        run: test -f relay.env
+
+      - name: test zdb.env file gen postgres
+        run: test -f zdb.env
+
+      - name: Postgres run cleanup
+        run: |
+          docker compose down --volumes --rmi all
+          rm -rf docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json zdb.env
+
+      - name: handle insisting image  gen CockroachDB # remove after release
+        run: docker pull netbirdio/relay:latest || docker pull netbirdio/signal:latest && docker tag netbirdio/signal:latest netbirdio/relay:latest
+
+      - name: run script with Zitadel CockroachDB
+        run: bash -x infrastructure_files/getting-started-with-zitadel.sh
+        env:
+          NETBIRD_DOMAIN: use-ip
+          ZITADEL_DATABASE: cockroach
+
+      - name: test Caddy file gen CockroachDB
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen CockroachDB
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen CockroachDB
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen CockroachDB
+        run: |
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen CockroachDB
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen CockroachDB
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen CockroachDB
+        run: test -f relay.env

.github/workflows/update-docs.yml

@@ -0,0 +1,22 @@
+name: update docs
+
+on:
+  push:
+    tags:
+      - 'v*'
+    paths:
+      - 'management/server/http/api/openapi.yml'
+
+jobs:
+  trigger_docs_api_update:
+    runs-on: ubuntu-latest
+    if: startsWith(github.ref, 'refs/tags/')
+    steps:
+      - name: Trigger API pages generation
+        uses: benc-uk/workflow-dispatch@v1
+        with:
+          workflow: generate api pages
+          repo: netbirdio/docs
+          ref: "refs/heads/main"
+          token: ${{ secrets.SIGN_GITHUB_TOKEN }}
+          inputs: '{ "tag": "${{ github.ref }}" }'

.gitignore

@@ -29,4 +29,3 @@ infrastructure_files/setup.env
 infrastructure_files/setup-*.env
 .vscode
 .DS_Store
-GeoLite2-City*

.goreleaser.yaml

@@ -80,6 +80,20 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: '{{ .CommitTimestamp }}'
 
+  - id: netbird-relay
+    dir: relay
+    env: [CGO_ENABLED=0]
+    binary: netbird-relay
+    goos:
+      - linux
+    goarch:
+      - amd64
+      - arm64
+      - arm
+    ldflags:
+      - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
+    mod_timestamp: '{{ .CommitTimestamp }}'
+
 archives:
   - builds:
       - netbird
@@ -161,6 +175,52 @@ dockers:
       - "--label=org.opencontainers.image.revision={{.FullCommit}}"
       - "--label=org.opencontainers.image.version={{.Version}}"
       - "--label=maintainer=dev@netbird.io"
+  - image_templates:
+      - netbirdio/relay:{{ .Version }}-amd64
+    ids:
+      - netbird-relay
+    goarch: amd64
+    use: buildx
+    dockerfile: relay/Dockerfile
+    build_flag_templates:
+      - "--platform=linux/amd64"
+      - "--label=org.opencontainers.image.created={{.Date}}"
+      - "--label=org.opencontainers.image.title={{.ProjectName}}"
+      - "--label=org.opencontainers.image.version={{.Version}}"
+      - "--label=org.opencontainers.image.revision={{.FullCommit}}"
+      - "--label=org.opencontainers.image.version={{.Version}}"
+      - "--label=maintainer=dev@netbird.io"
+  - image_templates:
+      - netbirdio/relay:{{ .Version }}-arm64v8
+    ids:
+      - netbird-relay
+    goarch: arm64
+    use: buildx
+    dockerfile: relay/Dockerfile
+    build_flag_templates:
+      - "--platform=linux/arm64"
+      - "--label=org.opencontainers.image.created={{.Date}}"
+      - "--label=org.opencontainers.image.title={{.ProjectName}}"
+      - "--label=org.opencontainers.image.version={{.Version}}"
+      - "--label=org.opencontainers.image.revision={{.FullCommit}}"
+      - "--label=org.opencontainers.image.version={{.Version}}"
+      - "--label=maintainer=dev@netbird.io"
+  - image_templates:
+      - netbirdio/relay:{{ .Version }}-arm
+    ids:
+      - netbird-relay
+    goarch: arm
+    goarm: 6
+    use: buildx
+    dockerfile: relay/Dockerfile
+    build_flag_templates:
+      - "--platform=linux/arm"
+      - "--label=org.opencontainers.image.created={{.Date}}"
+      - "--label=org.opencontainers.image.title={{.ProjectName}}"
+      - "--label=org.opencontainers.image.version={{.Version}}"
+      - "--label=org.opencontainers.image.revision={{.FullCommit}}"
+      - "--label=org.opencontainers.image.version={{.Version}}"
+      - "--label=maintainer=dev@netbird.io"
   - image_templates:
       - netbirdio/signal:{{ .Version }}-amd64
     ids:
@@ -313,6 +373,18 @@ docker_manifests:
       - netbirdio/netbird:{{ .Version }}-arm
       - netbirdio/netbird:{{ .Version }}-amd64
 
+  - name_template: netbirdio/relay:{{ .Version }}
+    image_templates:
+      - netbirdio/relay:{{ .Version }}-arm64v8
+      - netbirdio/relay:{{ .Version }}-arm
+      - netbirdio/relay:{{ .Version }}-amd64
+
+  - name_template: netbirdio/relay:latest
+    image_templates:
+      - netbirdio/relay:{{ .Version }}-arm64v8
+      - netbirdio/relay:{{ .Version }}-arm
+      - netbirdio/relay:{{ .Version }}-amd64
+
   - name_template: netbirdio/signal:{{ .Version }}
     image_templates:
       - netbirdio/signal:{{ .Version }}-arm64v8
@@ -386,4 +458,4 @@ checksum:
 release:
   extra_files:
     - glob: ./infrastructure_files/getting-started-with-zitadel.sh
-    - glob: ./release_files/install.sh
+    - glob: ./release_files/install.sh

.goreleaser_ui.yaml

@@ -11,8 +11,6 @@ builds:
       - amd64
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
-    tags:
-      - legacy_appindicator
     mod_timestamp: '{{ .CommitTimestamp }}'
 
   - id: netbird-ui-windows

README.md

@@ -17,7 +17,7 @@
        <img src="https://img.shields.io/badge/license-BSD--3-blue" />
      </a> 
     <br>
-    <a href="https://join.slack.com/t/netbirdio/shared_invite/zt-vrahf41g-ik1v7fV8du6t0RwxSrJ96A">
+    <a href="https://join.slack.com/t/netbirdio/shared_invite/zt-2p5zwhm4g-8fHollzrQa5y4PZF5AEpvQ">
         <img src="https://img.shields.io/badge/slack-@netbird-red.svg?logo=slack"/>
      </a>    
   </p>
@@ -30,7 +30,7 @@
   <br/>
   See <a href="https://netbird.io/docs/">Documentation</a>
   <br/>
-   Join our <a href="https://join.slack.com/t/netbirdio/shared_invite/zt-vrahf41g-ik1v7fV8du6t0RwxSrJ96A">Slack channel</a>
+   Join our <a href="https://join.slack.com/t/netbirdio/shared_invite/zt-2p5zwhm4g-8fHollzrQa5y4PZF5AEpvQ">Slack channel</a>
   <br/>
  
 </strong>

client/Dockerfile

@@ -1,4 +1,4 @@
-FROM alpine:3.19
+FROM alpine:3.20
 RUN apk add --no-cache ca-certificates iptables ip6tables
 ENV NB_FOREGROUND_MODE=true
 ENTRYPOINT [ "/usr/local/bin/netbird","up"]

client/android/login.go

@@ -84,7 +84,7 @@ func (a *Auth) SaveConfigIfSSOSupported(listener SSOListener) {
 func (a *Auth) saveConfigIfSSOSupported() (bool, error) {
 	supportsSSO := true
 	err := a.withBackOff(a.ctx, func() (err error) {
-		_, err = internal.GetPKCEAuthorizationFlowInfo(a.ctx, a.config.PrivateKey, a.config.ManagementURL)
+		_, err = internal.GetPKCEAuthorizationFlowInfo(a.ctx, a.config.PrivateKey, a.config.ManagementURL, nil)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
 			_, err = internal.GetDeviceAuthorizationFlowInfo(a.ctx, a.config.PrivateKey, a.config.ManagementURL)
 			s, ok := gstatus.FromError(err)

client/cmd/down.go

@@ -42,6 +42,8 @@ var downCmd = &cobra.Command{
 			log.Errorf("call service down method: %v", err)
 			return err
 		}
+
+		cmd.Println("Disconnected")
 		return nil
 	},
 }

client/cmd/login.go

@@ -39,6 +39,11 @@ var loginCmd = &cobra.Command{
 			ctx = context.WithValue(ctx, system.DeviceNameCtxKey, hostName)
 		}
 
+		providedSetupKey, err := getSetupKey()
+		if err != nil {
+			return err
+		}
+
 		// workaround to run without service
 		if logFile == "console" {
 			err = handleRebrand(cmd)
@@ -62,7 +67,7 @@ var loginCmd = &cobra.Command{
 
 			config, _ = internal.UpdateOldManagementURL(ctx, config, configPath)
 
-			err = foregroundLogin(ctx, cmd, config, setupKey)
+			err = foregroundLogin(ctx, cmd, config, providedSetupKey)
 			if err != nil {
 				return fmt.Errorf("foreground login failed: %v", err)
 			}
@@ -81,7 +86,7 @@ var loginCmd = &cobra.Command{
 		client := proto.NewDaemonServiceClient(conn)
 
 		loginRequest := proto.LoginRequest{
-			SetupKey:             setupKey,
+			SetupKey:             providedSetupKey,
 			ManagementUrl:        managementURL,
 			IsLinuxDesktopClient: isLinuxRunningDesktop(),
 			Hostname:             hostName,

client/cmd/root.go

@@ -56,6 +56,7 @@ var (
 	managementURL           string
 	adminURL                string
 	setupKey                string
+	setupKeyPath            string
 	hostName                string
 	preSharedKey            string
 	natExternalIPs          []string
@@ -128,6 +129,8 @@ func init() {
 	rootCmd.PersistentFlags().StringVarP(&logLevel, "log-level", "l", "info", "sets Netbird log level")
 	rootCmd.PersistentFlags().StringVar(&logFile, "log-file", defaultLogFile, "sets Netbird log path. If console is specified the log will be output to stdout. If syslog is specified the log will be sent to syslog daemon.")
 	rootCmd.PersistentFlags().StringVarP(&setupKey, "setup-key", "k", "", "Setup key obtained from the Management Service Dashboard (used to register peer)")
+	rootCmd.PersistentFlags().StringVar(&setupKeyPath, "setup-key-file", "", "The path to a setup key obtained from the Management Service Dashboard (used to register peer) This is ignored if the setup-key flag is provided.")
+	rootCmd.MarkFlagsMutuallyExclusive("setup-key", "setup-key-file")
 	rootCmd.PersistentFlags().StringVar(&preSharedKey, preSharedKeyFlag, "", "Sets Wireguard PreSharedKey property. If set, then only peers that have the same key can communicate.")
 	rootCmd.PersistentFlags().StringVarP(&hostName, "hostname", "n", "", "Sets a custom hostname for the device")
 	rootCmd.PersistentFlags().BoolVarP(&anonymizeFlag, "anonymize", "A", false, "anonymize IP addresses and non-netbird.io domains in logs and status output")
@@ -253,6 +256,21 @@ var CLIBackOffSettings = &backoff.ExponentialBackOff{
 	Clock:               backoff.SystemClock,
 }
 
+func getSetupKey() (string, error) {
+	if setupKeyPath != "" && setupKey == "" {
+		return getSetupKeyFromFile(setupKeyPath)
+	}
+	return setupKey, nil
+}
+
+func getSetupKeyFromFile(setupKeyPath string) (string, error) {
+	data, err := os.ReadFile(setupKeyPath)
+	if err != nil {
+		return "", fmt.Errorf("failed to read setup key file: %v", err)
+	}
+	return strings.TrimSpace(string(data)), nil
+}
+
 func handleRebrand(cmd *cobra.Command) error {
 	var err error
 	if logFile == defaultLogFile {

client/cmd/root_test.go

@@ -4,6 +4,10 @@ import (
 	"fmt"
 	"io"
 	"testing"
+
+	"github.com/spf13/cobra"
+
+	"github.com/netbirdio/netbird/iface"
 )
 
 func TestInitCommands(t *testing.T) {
@@ -34,3 +38,44 @@ func TestInitCommands(t *testing.T) {
 		})
 	}
 }
+
+func TestSetFlagsFromEnvVars(t *testing.T) {
+	var cmd = &cobra.Command{
+		Use:          "netbird",
+		Long:         "test",
+		SilenceUsage: true,
+		Run: func(cmd *cobra.Command, args []string) {
+			SetFlagsFromEnvVars(cmd)
+		},
+	}
+
+	cmd.PersistentFlags().StringSliceVar(&natExternalIPs, externalIPMapFlag, nil,
+		`comma separated list of external IPs to map to the Wireguard interface`)
+	cmd.PersistentFlags().StringVar(&interfaceName, interfaceNameFlag, iface.WgInterfaceDefault, "Wireguard interface name")
+	cmd.PersistentFlags().BoolVar(&rosenpassEnabled, enableRosenpassFlag, false, "Enable Rosenpass feature Rosenpass.")
+	cmd.PersistentFlags().Uint16Var(&wireguardPort, wireguardPortFlag, iface.DefaultWgPort, "Wireguard interface listening port")
+
+	t.Setenv("NB_EXTERNAL_IP_MAP", "abc,dec")
+	t.Setenv("NB_INTERFACE_NAME", "test-name")
+	t.Setenv("NB_ENABLE_ROSENPASS", "true")
+	t.Setenv("NB_WIREGUARD_PORT", "10000")
+	err := cmd.Execute()
+	if err != nil {
+		t.Fatalf("expected no error while running netbird command, got %v", err)
+	}
+	if len(natExternalIPs) != 2 {
+		t.Errorf("expected 2 external ips, got %d", len(natExternalIPs))
+	}
+	if natExternalIPs[0] != "abc" || natExternalIPs[1] != "dec" {
+		t.Errorf("expected abc,dec, got %s,%s", natExternalIPs[0], natExternalIPs[1])
+	}
+	if interfaceName != "test-name" {
+		t.Errorf("expected test-name, got %s", interfaceName)
+	}
+	if !rosenpassEnabled {
+		t.Errorf("expected rosenpassEnabled to be true, got false")
+	}
+	if wireguardPort != 10000 {
+		t.Errorf("expected wireguardPort to be 10000, got %d", wireguardPort)
+	}
+}

client/cmd/service.go

@@ -2,18 +2,21 @@ package cmd
 
 import (
 	"context"
+
 	"github.com/kardianos/service"
 	log "github.com/sirupsen/logrus"
 	"github.com/spf13/cobra"
 	"google.golang.org/grpc"
 
 	"github.com/netbirdio/netbird/client/internal"
+	"github.com/netbirdio/netbird/client/server"
 )
 
 type program struct {
-	ctx    context.Context
-	cancel context.CancelFunc
-	serv   *grpc.Server
+	ctx            context.Context
+	cancel         context.CancelFunc
+	serv           *grpc.Server
+	serverInstance *server.Server
 }
 
 func newProgram(ctx context.Context, cancel context.CancelFunc) *program {

client/cmd/service_controller.go

@@ -61,6 +61,8 @@ func (p *program) Start(svc service.Service) error {
 		}
 		proto.RegisterDaemonServiceServer(p.serv, serverInstance)
 
+		p.serverInstance = serverInstance
+
 		log.Printf("started daemon server: %v", split[1])
 		if err := p.serv.Serve(listen); err != nil {
 			log.Errorf("failed to serve daemon requests: %v", err)
@@ -70,6 +72,14 @@ func (p *program) Start(svc service.Service) error {
 }
 
 func (p *program) Stop(srv service.Service) error {
+	if p.serverInstance != nil {
+		in := new(proto.DownRequest)
+		_, err := p.serverInstance.Down(p.ctx, in)
+		if err != nil {
+			log.Errorf("failed to stop daemon: %v", err)
+		}
+	}
+
 	p.cancel()
 
 	if p.serv != nil {

client/cmd/testutil_test.go

@@ -11,6 +11,7 @@ import (
 	"go.opentelemetry.io/otel"
 
 	"github.com/netbirdio/netbird/management/server/activity"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 
 	"github.com/netbirdio/netbird/util"
 
@@ -71,6 +72,7 @@ func startSignal(t *testing.T) (*grpc.Server, net.Listener) {
 
 func startManagement(t *testing.T, config *mgmt.Config) (*grpc.Server, net.Listener) {
 	t.Helper()
+
 	lis, err := net.Listen("tcp", ":0")
 	if err != nil {
 		t.Fatal(err)
@@ -88,16 +90,17 @@ func startManagement(t *testing.T, config *mgmt.Config) (*grpc.Server, net.Liste
 		return nil, nil
 	}
 	iv, _ := integrations.NewIntegratedValidator(context.Background(), eventStore)
-	accountManager, err := mgmt.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, iv)
+
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	require.NoError(t, err)
+
+	accountManager, err := mgmt.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, iv, metrics)
 	if err != nil {
 		t.Fatal(err)
 	}
 
-	rc := &mgmt.RelayConfig{
-		Address: "localhost:0",
-	}
-	turnManager := mgmt.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, rc)
-	mgmtServer, err := mgmt.NewServer(context.Background(), config, accountManager, peersUpdateManager, turnManager, nil, nil)
+	secretsManager := mgmt.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, config.Relay)
+	mgmtServer, err := mgmt.NewServer(context.Background(), config, accountManager, peersUpdateManager, secretsManager, nil, nil)
 	if err != nil {
 		t.Fatal(err)
 	}

client/cmd/up.go

@@ -147,6 +147,11 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command) error {
 		ic.DNSRouteInterval = &dnsRouteInterval
 	}
 
+	providedSetupKey, err := getSetupKey()
+	if err != nil {
+		return err
+	}
+
 	config, err := internal.UpdateOrCreateConfig(ic)
 	if err != nil {
 		return fmt.Errorf("get config file: %v", err)
@@ -154,7 +159,7 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command) error {
 
 	config, _ = internal.UpdateOldManagementURL(ctx, config, configPath)
 
-	err = foregroundLogin(ctx, cmd, config, setupKey)
+	err = foregroundLogin(ctx, cmd, config, providedSetupKey)
 	if err != nil {
 		return fmt.Errorf("foreground login failed: %v", err)
 	}
@@ -202,8 +207,13 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command) error {
 		return nil
 	}
 
+	providedSetupKey, err := getSetupKey()
+	if err != nil {
+		return err
+	}
+
 	loginRequest := proto.LoginRequest{
-		SetupKey:             setupKey,
+		SetupKey:             providedSetupKey,
 		ManagementUrl:        managementURL,
 		AdminURL:             adminURL,
 		NatExternalIPs:       natExternalIPs,

client/cmd/up_daemon_test.go

@@ -2,6 +2,7 @@ package cmd
 
 import (
 	"context"
+	"os"
 	"testing"
 	"time"
 
@@ -40,6 +41,36 @@ func TestUpDaemon(t *testing.T) {
 		return
 	}
 
+	// Test the setup-key-file flag.
+	tempFile, err := os.CreateTemp("", "setup-key")
+	if err != nil {
+		t.Errorf("could not create temp file, got error %v", err)
+		return
+	}
+	defer os.Remove(tempFile.Name())
+	if _, err := tempFile.Write([]byte("A2C8E62B-38F5-4553-B31E-DD66C696CEBB")); err != nil {
+		t.Errorf("could not write to temp file, got error %v", err)
+		return
+	}
+	if err := tempFile.Close(); err != nil {
+		t.Errorf("unable to close file, got error %v", err)
+	}
+	rootCmd.SetArgs([]string{
+		"login",
+		"--daemon-addr", "tcp://" + cliAddr,
+		"--setup-key-file", tempFile.Name(),
+		"--log-file", "",
+	})
+	if err := rootCmd.Execute(); err != nil {
+		t.Errorf("expected no error while running up command, got %v", err)
+		return
+	}
+	time.Sleep(time.Second * 3)
+	if status, err := state.Status(); err != nil && status != internal.StatusIdle {
+		t.Errorf("wrong status after login: %s, %v", internal.StatusIdle, err)
+		return
+	}
+
 	rootCmd.SetArgs([]string{
 		"up",
 		"--daemon-addr", "tcp://" + cliAddr,

client/internal/auth/device_flow.go

@@ -3,6 +3,7 @@ package auth
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
@@ -180,7 +181,7 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 					continue
 				}
 
-				return TokenInfo{}, fmt.Errorf(tokenResponse.ErrorDescription)
+				return TokenInfo{}, errors.New(tokenResponse.ErrorDescription)
 			}
 
 			tokenInfo := TokenInfo{

client/internal/auth/oauth.go

@@ -86,7 +86,7 @@ func NewOAuthFlow(ctx context.Context, config *internal.Config, isLinuxDesktopCl
 
 // authenticateWithPKCEFlow initializes the Proof Key for Code Exchange flow auth flow
 func authenticateWithPKCEFlow(ctx context.Context, config *internal.Config) (OAuthFlow, error) {
-	pkceFlowInfo, err := internal.GetPKCEAuthorizationFlowInfo(ctx, config.PrivateKey, config.ManagementURL)
+	pkceFlowInfo, err := internal.GetPKCEAuthorizationFlowInfo(ctx, config.PrivateKey, config.ManagementURL, config.ClientCertKeyPair)
 	if err != nil {
 		return nil, fmt.Errorf("getting pkce authorization flow info failed with error: %v", err)
 	}

client/internal/auth/pkce_flow.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"crypto/sha256"
 	"crypto/subtle"
+	"crypto/tls"
 	"encoding/base64"
 	"errors"
 	"fmt"
@@ -143,6 +144,18 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, _ AuthFlowInfo) (
 func (p *PKCEAuthorizationFlow) startServer(server *http.Server, tokenChan chan<- *oauth2.Token, errChan chan<- error) {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/", func(w http.ResponseWriter, req *http.Request) {
+		cert := p.providerConfig.ClientCertPair
+		if cert != nil {
+			tr := &http.Transport{
+				TLSClientConfig: &tls.Config{
+					Certificates: []tls.Certificate{*cert},
+				},
+			}
+			sslClient := &http.Client{Transport: tr}
+			ctx := context.WithValue(req.Context(), oauth2.HTTPClient, sslClient)
+			req = req.WithContext(ctx)
+		}
+
 		token, err := p.handleRequest(req)
 		if err != nil {
 			renderPKCEFlowTmpl(w, err)

client/internal/config.go

@@ -2,6 +2,7 @@ package internal
 
 import (
 	"context"
+	"crypto/tls"
 	"fmt"
 	"net/url"
 	"os"
@@ -57,6 +58,8 @@ type ConfigInput struct {
 	DisableAutoConnect  *bool
 	ExtraIFaceBlackList []string
 	DNSRouteInterval    *time.Duration
+	ClientCertPath      string
+	ClientCertKeyPath   string
 }
 
 // Config Configuration type
@@ -102,6 +105,13 @@ type Config struct {
 
 	// DNSRouteInterval is the interval in which the DNS routes are updated
 	DNSRouteInterval time.Duration
+	//Path to a certificate used for mTLS authentication
+	ClientCertPath string
+
+	//Path to corresponding private key of ClientCertPath
+	ClientCertKeyPath string
+
+	ClientCertKeyPair *tls.Certificate `json:"-"`
 }
 
 // ReadConfig read config file and return with Config. If it is not exists create a new with default values
@@ -385,6 +395,26 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) {
 
 	}
 
+	if input.ClientCertKeyPath != "" {
+		config.ClientCertKeyPath = input.ClientCertKeyPath
+		updated = true
+	}
+
+	if input.ClientCertPath != "" {
+		config.ClientCertPath = input.ClientCertPath
+		updated = true
+	}
+
+	if config.ClientCertPath != "" && config.ClientCertKeyPath != "" {
+		cert, err := tls.LoadX509KeyPair(config.ClientCertPath, config.ClientCertKeyPath)
+		if err != nil {
+			log.Error("Failed to load mTLS cert/key pair: ", err)
+		} else {
+			config.ClientCertKeyPair = &cert
+			log.Info("Loaded client mTLS cert/key pair")
+		}
+	}
+
 	return updated, nil
 }
 

client/internal/connect.go

@@ -57,17 +57,15 @@ func NewConnectClient(
 
 // Run with main logic.
 func (c *ConnectClient) Run() error {
-	return c.run(MobileDependency{}, nil, nil, nil, nil)
+	return c.run(MobileDependency{}, nil, nil)
 }
 
 // RunWithProbes runs the client's main logic with probes attached
 func (c *ConnectClient) RunWithProbes(
-	mgmProbe *Probe,
-	signalProbe *Probe,
-	relayProbe *Probe,
-	wgProbe *Probe,
+	probes *ProbeHolder,
+	runningChan chan error,
 ) error {
-	return c.run(MobileDependency{}, mgmProbe, signalProbe, relayProbe, wgProbe)
+	return c.run(MobileDependency{}, probes, runningChan)
 }
 
 // RunOnAndroid with main logic on mobile system
@@ -86,7 +84,7 @@ func (c *ConnectClient) RunOnAndroid(
 		HostDNSAddresses:      dnsAddresses,
 		DnsReadyListener:      dnsReadyListener,
 	}
-	return c.run(mobileDependency, nil, nil, nil, nil)
+	return c.run(mobileDependency, nil, nil)
 }
 
 func (c *ConnectClient) RunOniOS(
@@ -102,15 +100,13 @@ func (c *ConnectClient) RunOniOS(
 		NetworkChangeListener: networkChangeListener,
 		DnsManager:            dnsManager,
 	}
-	return c.run(mobileDependency, nil, nil, nil, nil)
+	return c.run(mobileDependency, nil, nil)
 }
 
 func (c *ConnectClient) run(
 	mobileDependency MobileDependency,
-	mgmProbe *Probe,
-	signalProbe *Probe,
-	relayProbe *Probe,
-	wgProbe *Probe,
+	probes *ProbeHolder,
+	runningChan chan error,
 ) error {
 	defer func() {
 		if r := recover(); r != nil {
@@ -198,6 +194,7 @@ func (c *ConnectClient) run(
 			log.Debug(err)
 			if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 				state.Set(StatusNeedsLogin)
+				_ = c.Stop()
 				return backoff.Permanent(wrapErr(err)) // unrecoverable error
 			}
 			return wrapErr(err)
@@ -242,13 +239,16 @@ func (c *ConnectClient) run(
 
 		c.statusRecorder.MarkSignalConnected()
 
-		relayURL, token := parseRelayInfo(loginResp)
-		relayManager := relayClient.NewManager(engineCtx, relayURL, myPrivateKey.PublicKey().String())
-		if relayURL != "" {
+		relayURLs, token := parseRelayInfo(loginResp)
+		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String())
+		if len(relayURLs) > 0 {
 			if token != nil {
-				relayManager.UpdateToken(token)
+				if err := relayManager.UpdateToken(token); err != nil {
+					log.Errorf("failed to update token: %s", err)
+					return wrapErr(err)
+				}
 			}
-			log.Infof("connecting to the Relay service %s", relayURL)
+			log.Infof("connecting to the Relay service(s): %s", strings.Join(relayURLs, ", "))
 			if err = relayManager.Serve(); err != nil {
 				log.Error(err)
 				return wrapErr(err)
@@ -267,7 +267,8 @@ func (c *ConnectClient) run(
 		checks := loginResp.GetChecks()
 
 		c.engineMutex.Lock()
-		c.engine = NewEngineWithProbes(engineCtx, cancel, signalClient, mgmClient, relayManager, engineConfig, mobileDependency, c.statusRecorder, mgmProbe, signalProbe, relayProbe, wgProbe, checks)
+		c.engine = NewEngineWithProbes(engineCtx, cancel, signalClient, mgmClient, relayManager, engineConfig, mobileDependency, c.statusRecorder, probes, checks)
+
 		c.engineMutex.Unlock()
 
 		if err := c.engine.Start(); err != nil {
@@ -278,17 +279,16 @@ func (c *ConnectClient) run(
 		log.Infof("Netbird engine started, the IP is: %s", peerConfig.GetAddress())
 		state.Set(StatusConnected)
 
+		if runningChan != nil {
+			runningChan <- nil
+			close(runningChan)
+		}
+
 		<-engineCtx.Done()
 		c.statusRecorder.ClientTeardown()
 
 		backOff.Reset()
 
-		err = c.engine.Stop()
-		if err != nil {
-			log.Errorf("failed stopping engine %v", err)
-			return wrapErr(err)
-		}
-
 		log.Info("stopped NetBird client")
 
 		if _, err := state.Status(); errors.Is(err, ErrResetConnection) {
@@ -304,32 +304,31 @@ func (c *ConnectClient) run(
 		log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 			state.Set(StatusNeedsLogin)
+			_ = c.Stop()
 		}
 		return err
 	}
 	return nil
 }
 
-func parseRelayInfo(resp *mgmProto.LoginResponse) (string, *hmac.Token) {
-	msg := resp.GetWiretrusteeConfig().GetRelay()
-	if msg == nil {
-		return "", nil
-	}
-
-	var url string
-	if msg.GetUrls() != nil && len(msg.GetUrls()) > 0 {
-		url = msg.GetUrls()[0]
+func parseRelayInfo(loginResp *mgmProto.LoginResponse) ([]string, *hmac.Token) {
+	relayCfg := loginResp.GetWiretrusteeConfig().GetRelay()
+	if relayCfg == nil {
+		return nil, nil
 	}
 
 	token := &hmac.Token{
-		Payload:   msg.GetTokenPayload(),
-		Signature: msg.GetTokenSignature(),
+		Payload:   relayCfg.GetTokenPayload(),
+		Signature: relayCfg.GetTokenSignature(),
 	}
 
-	return url, token
+	return relayCfg.GetUrls(), token
 }
 
 func (c *ConnectClient) Engine() *Engine {
+	if c == nil {
+		return nil
+	}
 	var e *Engine
 	c.engineMutex.Lock()
 	e = c.engine
@@ -337,6 +336,19 @@ func (c *ConnectClient) Engine() *Engine {
 	return e
 }
 
+func (c *ConnectClient) Stop() error {
+	if c == nil {
+		return nil
+	}
+	c.engineMutex.Lock()
+	defer c.engineMutex.Unlock()
+
+	if c.engine == nil {
+		return nil
+	}
+	return c.engine.Stop()
+}
+
 func (c *ConnectClient) isContextCancelled() bool {
 	select {
 	case <-c.ctx.Done():
@@ -436,19 +448,43 @@ func statusRecorderToSignalConnStateNotifier(statusRecorder *peer.Status) signal
 	return notifier
 }
 
-func freePort(start int) (int, error) {
+// freePort attempts to determine if the provided port is available, if not it will ask the system for a free port.
+func freePort(initPort int) (int, error) {
 	addr := net.UDPAddr{}
-	if start == 0 {
-		start = iface.DefaultWgPort
+	if initPort == 0 {
+		initPort = iface.DefaultWgPort
 	}
-	for x := start; x <= 65535; x++ {
-		addr.Port = x
-		conn, err := net.ListenUDP("udp", &addr)
-		if err != nil {
-			continue
-		}
-		conn.Close()
-		return x, nil
+
+	addr.Port = initPort
+
+	conn, err := net.ListenUDP("udp", &addr)
+	if err == nil {
+		closeConnWithLog(conn)
+		return initPort, nil
+	}
+
+	// if the port is already in use, ask the system for a free port
+	addr.Port = 0
+	conn, err = net.ListenUDP("udp", &addr)
+	if err != nil {
+		return 0, fmt.Errorf("unable to get a free port: %v", err)
+	}
+
+	udpAddr, ok := conn.LocalAddr().(*net.UDPAddr)
+	if !ok {
+		return 0, errors.New("wrong address type when getting a free port")
+	}
+	closeConnWithLog(conn)
+	return udpAddr.Port, nil
+}
+
+func closeConnWithLog(conn *net.UDPConn) {
+	startClosing := time.Now()
+	err := conn.Close()
+	if err != nil {
+		log.Warnf("closing probe port %d failed: %v. NetBird will still attempt to use this port for connection.", conn.LocalAddr().(*net.UDPAddr).Port, err)
+	}
+	if time.Since(startClosing) > time.Second {
+		log.Warnf("closing the testing port %d took %s. Usually it is safe to ignore, but continuous warnings may indicate a problem.", conn.LocalAddr().(*net.UDPAddr).Port, time.Since(startClosing))
 	}
-	return 0, errors.New("no free ports")
 }

client/internal/connect_test.go

@@ -7,51 +7,55 @@ import (
 
 func Test_freePort(t *testing.T) {
 	tests := []struct {
-		name    string
-		port    int
-		want    int
-		wantErr bool
+		name        string
+		port        int
+		want        int
+		shouldMatch bool
 	}{
 		{
-			name:    "available",
-			port:    51820,
-			want:    51820,
-			wantErr: false,
+			name:        "not provided, fallback to default",
+			port:        0,
+			want:        51820,
+			shouldMatch: true,
 		},
 		{
-			name:    "notavailable",
-			port:    51830,
-			want:    51831,
-			wantErr: false,
+			name:        "provided and available",
+			port:        51821,
+			want:        51821,
+			shouldMatch: true,
 		},
 		{
-			name:    "noports",
-			port:    65535,
-			want:    0,
-			wantErr: true,
+			name:        "provided and not available",
+			port:        51830,
+			want:        51830,
+			shouldMatch: false,
 		},
 	}
+	c1, err := net.ListenUDP("udp", &net.UDPAddr{Port: 51830})
+	if err != nil {
+		t.Errorf("freePort error = %v", err)
+	}
+	defer func(c1 *net.UDPConn) {
+		_ = c1.Close()
+	}(c1)
+
 	for _, tt := range tests {
 
-		c1, err := net.ListenUDP("udp", &net.UDPAddr{Port: 51830})
-		if err != nil {
-			t.Errorf("freePort error = %v", err)
-		}
-		c2, err := net.ListenUDP("udp", &net.UDPAddr{Port: 65535})
-		if err != nil {
-			t.Errorf("freePort error = %v", err)
-		}
 		t.Run(tt.name, func(t *testing.T) {
 			got, err := freePort(tt.port)
-			if (err != nil) != tt.wantErr {
-				t.Errorf("freePort() error = %v, wantErr %v", err, tt.wantErr)
-				return
+
+			if err != nil {
+				t.Errorf("got an error while getting free port: %v", err)
 			}
-			if got != tt.want {
-				t.Errorf("freePort() = %v, want %v", got, tt.want)
+
+			if tt.shouldMatch && got != tt.want {
+				t.Errorf("got a different port %v, want %v", got, tt.want)
+			}
+
+			if !tt.shouldMatch && got == tt.want {
+				t.Errorf("got the same port %v, want a different port", tt.want)
 			}
 		})
-		c1.Close()
-		c2.Close()
+
 	}
 }

client/internal/engine.go

@@ -128,7 +128,7 @@ type Engine struct {
 	STUNs []*stun.URI
 	// TURNs is a list of STUN servers used by ICE
 	TURNs    []*stun.URI
-	StunTurn atomic.Value
+	stunTurn atomic.Value
 
 	// clientRoutes is the most recent list of clientRoutes received from the Management Service
 	clientRoutes   route.HAMap
@@ -161,10 +161,7 @@ type Engine struct {
 
 	dnsServer dns.Server
 
-	mgmProbe    *Probe
-	signalProbe *Probe
-	relayProbe  *Probe
-	wgProbe     *Probe
+	probes *ProbeHolder
 
 	// checks are the client-applied posture checks that need to be evaluated on the client
 	checks []*mgmProto.Checks
@@ -200,9 +197,6 @@ func NewEngine(
 		mobileDep,
 		statusRecorder,
 		nil,
-		nil,
-		nil,
-		nil,
 		checks,
 	)
 }
@@ -217,10 +211,7 @@ func NewEngineWithProbes(
 	config *EngineConfig,
 	mobileDep MobileDependency,
 	statusRecorder *peer.Status,
-	mgmProbe *Probe,
-	signalProbe *Probe,
-	relayProbe *Probe,
-	wgProbe *Probe,
+	probes *ProbeHolder,
 	checks []*mgmProto.Checks,
 ) *Engine {
 	return &Engine{
@@ -239,22 +230,20 @@ func NewEngineWithProbes(
 		networkSerial:  0,
 		sshServerFunc:  nbssh.DefaultSSHServer,
 		statusRecorder: statusRecorder,
-		mgmProbe:       mgmProbe,
-		signalProbe:    signalProbe,
-		relayProbe:     relayProbe,
-		wgProbe:        wgProbe,
+		probes:         probes,
 		checks:         checks,
 	}
 }
 
 func (e *Engine) Stop() error {
+	if e == nil {
+		// this seems to be a very odd case but there was the possibility if the netbird down command comes before the engine is fully started
+		log.Debugf("tried stopping engine that is nil")
+		return nil
+	}
 	e.syncMsgMux.Lock()
 	defer e.syncMsgMux.Unlock()
 
-	if e.cancel != nil {
-		e.cancel()
-	}
-
 	// stopping network monitor first to avoid starting the engine again
 	if e.networkMonitor != nil {
 		e.networkMonitor.Stop()
@@ -263,13 +252,17 @@ func (e *Engine) Stop() error {
 
 	err := e.removeAllPeers()
 	if err != nil {
-		return err
+		return fmt.Errorf("failed to remove all peers: %s", err)
 	}
 
 	e.clientRoutesMu.Lock()
 	e.clientRoutes = nil
 	e.clientRoutesMu.Unlock()
 
+	if e.cancel != nil {
+		e.cancel()
+	}
+
 	// very ugly but we want to remove peers from the WireGuard interface first before removing interface.
 	// Removing peers happens in the conn.Close() asynchronously
 	time.Sleep(500 * time.Millisecond)
@@ -325,7 +318,7 @@ func (e *Engine) Start() error {
 	}
 	e.dnsServer = dnsServer
 
-	e.routeManager = routemanager.NewManager(e.ctx, e.config.WgPrivateKey.PublicKey().String(), e.config.DNSRouteInterval, e.wgInterface, e.statusRecorder, initialRoutes)
+	e.routeManager = routemanager.NewManager(e.ctx, e.config.WgPrivateKey.PublicKey().String(), e.config.DNSRouteInterval, e.wgInterface, e.statusRecorder, e.relayManager, initialRoutes)
 	beforePeerHook, afterPeerHook, err := e.routeManager.Init()
 	if err != nil {
 		log.Errorf("Failed to initialize route manager: %s", err)
@@ -487,18 +480,18 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		wCfg := update.GetWiretrusteeConfig()
 		err := e.updateTURNs(wCfg.GetTurns())
 		if err != nil {
-			return err
+			return fmt.Errorf("update TURNs: %w", err)
 		}
 
 		err = e.updateSTUNs(wCfg.GetStuns())
 		if err != nil {
-			return err
+			return fmt.Errorf("update STUNs: %w", err)
 		}
 
 		var stunTurn []*stun.URI
 		stunTurn = append(stunTurn, e.STUNs...)
 		stunTurn = append(stunTurn, e.TURNs...)
-		e.StunTurn.Store(stunTurn)
+		e.stunTurn.Store(stunTurn)
 
 		relayMsg := wCfg.GetRelay()
 		if relayMsg != nil {
@@ -506,7 +499,10 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 				Payload:   relayMsg.GetTokenPayload(),
 				Signature: relayMsg.GetTokenSignature(),
 			}
-			e.relayManager.UpdateToken(c)
+			if err := e.relayManager.UpdateToken(c); err != nil {
+				log.Errorf("failed to update relay token: %v", err)
+				return fmt.Errorf("update relay token: %w", err)
+			}
 		}
 
 		// todo update relay address in the relay manager
@@ -952,7 +948,7 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs string) (*peer.Conn, e
 		RosenpassPubKey: e.getRosenpassPubKey(),
 		RosenpassAddr:   e.getRosenpassAddr(),
 		ICEConfig: peer.ICEConfig{
-			StunTurn:             e.StunTurn,
+			StunTurn:             &e.stunTurn,
 			InterfaceBlackList:   e.config.IFaceBlackList,
 			DisableIPv6Discovery: e.config.DisableIPv6Discovery,
 			UDPMux:               e.udpMux.UDPMuxDefault,
@@ -1295,24 +1291,27 @@ func (e *Engine) getRosenpassAddr() string {
 }
 
 func (e *Engine) receiveProbeEvents() {
-	if e.signalProbe != nil {
-		go e.signalProbe.Receive(e.ctx, func() bool {
+	if e.probes == nil {
+		return
+	}
+	if e.probes.SignalProbe != nil {
+		go e.probes.SignalProbe.Receive(e.ctx, func() bool {
 			healthy := e.signal.IsHealthy()
 			log.Debugf("received signal probe request, healthy: %t", healthy)
 			return healthy
 		})
 	}
 
-	if e.mgmProbe != nil {
-		go e.mgmProbe.Receive(e.ctx, func() bool {
+	if e.probes.MgmProbe != nil {
+		go e.probes.MgmProbe.Receive(e.ctx, func() bool {
 			healthy := e.mgmClient.IsHealthy()
 			log.Debugf("received management probe request, healthy: %t", healthy)
 			return healthy
 		})
 	}
 
-	if e.relayProbe != nil {
-		go e.relayProbe.Receive(e.ctx, func() bool {
+	if e.probes.RelayProbe != nil {
+		go e.probes.RelayProbe.Receive(e.ctx, func() bool {
 			healthy := true
 
 			results := append(e.probeSTUNs(), e.probeTURNs()...)
@@ -1331,8 +1330,8 @@ func (e *Engine) receiveProbeEvents() {
 		})
 	}
 
-	if e.wgProbe != nil {
-		go e.wgProbe.Receive(e.ctx, func() bool {
+	if e.probes.WgProbe != nil {
+		go e.probes.WgProbe.Receive(e.ctx, func() bool {
 			log.Debug("received wg probe request")
 
 			for _, peer := range e.peerConns {
@@ -1428,20 +1427,3 @@ func isChecksEqual(checks []*mgmProto.Checks, oChecks []*mgmProto.Checks) bool {
 		return slices.Equal(checks.Files, oChecks.Files)
 	})
 }
-
-func (e *Engine) IsWGIfaceUp() bool {
-	if e == nil || e.wgInterface == nil {
-		return false
-	}
-	iface, err := net.InterfaceByName(e.wgInterface.Name())
-	if err != nil {
-		log.Debugf("failed to get interface by name %s: %v", e.wgInterface.Name(), err)
-		return false
-	}
-
-	if iface.Flags&net.FlagUp != 0 {
-		return true
-	}
-
-	return false
-}

client/internal/engine_test.go

@@ -13,6 +13,7 @@ import (
 	"testing"
 	"time"
 
+	"github.com/google/uuid"
 	"github.com/pion/transport/v3/stdnet"
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
@@ -36,6 +37,7 @@ import (
 	mgmtProto "github.com/netbirdio/netbird/management/proto"
 	"github.com/netbirdio/netbird/management/server"
 	"github.com/netbirdio/netbird/management/server/activity"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 	relayClient "github.com/netbirdio/netbird/relay/client"
 	"github.com/netbirdio/netbird/route"
 	signal "github.com/netbirdio/netbird/signal/client"
@@ -79,7 +81,7 @@ func TestEngine_SSH(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
 
-	relayMgr := relayClient.NewManager(ctx, "", key.PublicKey().String())
+	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String())
 	engine := NewEngine(
 		ctx, cancel,
 		&signal.MockClient{},
@@ -224,7 +226,7 @@ func TestEngine_UpdateNetworkMap(t *testing.T) {
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
 
-	relayMgr := relayClient.NewManager(ctx, "", key.PublicKey().String())
+	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String())
 	engine := NewEngine(
 		ctx, cancel,
 		&signal.MockClient{},
@@ -246,7 +248,7 @@ func TestEngine_UpdateNetworkMap(t *testing.T) {
 		},
 	}
 	engine.wgInterface = wgIface
-	engine.routeManager = routemanager.NewManager(ctx, key.PublicKey().String(), time.Minute, engine.wgInterface, engine.statusRecorder, nil)
+	engine.routeManager = routemanager.NewManager(ctx, key.PublicKey().String(), time.Minute, engine.wgInterface, engine.statusRecorder, relayMgr, nil)
 	engine.dnsServer = &dns.MockServer{
 		UpdateDNSServerFunc: func(serial uint64, update nbdns.Config) error { return nil },
 	}
@@ -428,7 +430,7 @@ func TestEngine_Sync(t *testing.T) {
 		}
 		return nil
 	}
-	relayMgr := relayClient.NewManager(ctx, "", key.PublicKey().String())
+	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String())
 	engine := NewEngine(ctx, cancel, &signal.MockClient{}, &mgmt.MockClient{SyncFunc: syncFunc}, relayMgr, &EngineConfig{
 		WgIfaceName:  "utun103",
 		WgAddr:       "100.64.0.1/24",
@@ -588,7 +590,7 @@ func TestEngine_UpdateNetworkMapWithRoutes(t *testing.T) {
 			wgIfaceName := fmt.Sprintf("utun%d", 104+n)
 			wgAddr := fmt.Sprintf("100.66.%d.1/24", n)
 
-			relayMgr := relayClient.NewManager(ctx, "", key.PublicKey().String())
+			relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String())
 			engine := NewEngine(ctx, cancel, &signal.MockClient{}, &mgmt.MockClient{}, relayMgr, &EngineConfig{
 				WgIfaceName:  wgIfaceName,
 				WgAddr:       wgAddr,
@@ -759,7 +761,7 @@ func TestEngine_UpdateNetworkMapWithDNSUpdate(t *testing.T) {
 			wgIfaceName := fmt.Sprintf("utun%d", 104+n)
 			wgAddr := fmt.Sprintf("100.66.%d.1/24", n)
 
-			relayMgr := relayClient.NewManager(ctx, "", key.PublicKey().String())
+			relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String())
 			engine := NewEngine(ctx, cancel, &signal.MockClient{}, &mgmt.MockClient{}, relayMgr, &EngineConfig{
 				WgIfaceName:  wgIfaceName,
 				WgAddr:       wgAddr,
@@ -871,6 +873,8 @@ func TestEngine_MultiplePeers(t *testing.T) {
 			engine.dnsServer = &dns.MockServer{}
 			mu.Lock()
 			defer mu.Unlock()
+			guid := fmt.Sprintf("{%s}", uuid.New().String())
+			iface.CustomWindowsGUIDString = strings.ToLower(guid)
 			err = engine.Start()
 			if err != nil {
 				t.Errorf("unable to start engine for peer %d with error %v", j, err)
@@ -1036,7 +1040,7 @@ func createEngine(ctx context.Context, cancel context.CancelFunc, setupKey strin
 		WgPort:       wgPort,
 	}
 
-	relayMgr := relayClient.NewManager(ctx, "", key.PublicKey().String())
+	relayMgr := relayClient.NewManager(ctx, nil, key.PublicKey().String())
 	e, err := NewEngine(ctx, cancel, signalClient, mgmtClient, relayMgr, conf, MobileDependency{}, peer.NewRecorder("https://mgm"), nil), nil
 	e.ctx = ctx
 	return e, err
@@ -1071,6 +1075,11 @@ func startManagement(t *testing.T, dataDir string) (*grpc.Server, string, error)
 	config := &server.Config{
 		Stuns:      []*server.Host{},
 		TURNConfig: &server.TURNConfig{},
+		Relay: &server.Relay{
+			Addresses:      []string{"127.0.0.1:1234"},
+			CredentialsTTL: util.Duration{Duration: time.Hour},
+			Secret:         "222222222222222222",
+		},
 		Signal: &server.Host{
 			Proto: "http",
 			URI:   "localhost:10000",
@@ -1097,15 +1106,17 @@ func startManagement(t *testing.T, dataDir string) (*grpc.Server, string, error)
 		return nil, "", err
 	}
 	ia, _ := integrations.NewIntegratedValidator(context.Background(), eventStore)
-	accountManager, err := server.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, ia)
+
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	require.NoError(t, err)
+
+	accountManager, err := server.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, ia, metrics)
 	if err != nil {
 		return nil, "", err
 	}
-	rc := &server.RelayConfig{
-		Address: "127.0.0.1:1234",
-	}
-	turnManager := server.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, rc)
-	mgmtServer, err := server.NewServer(context.Background(), config, accountManager, peersUpdateManager, turnManager, nil, nil)
+
+	secretsManager := server.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, config.Relay)
+	mgmtServer, err := server.NewServer(context.Background(), config, accountManager, peersUpdateManager, secretsManager, nil, nil)
 	if err != nil {
 		return nil, "", err
 	}

client/internal/networkmonitor/monitor_bsd.go

@@ -65,7 +65,7 @@ func checkChange(ctx context.Context, nexthopv4, nexthopv6 systemops.Nexthop, ca
 					continue
 				}
 
-				if !route.Dst.Addr().IsUnspecified() {
+				if route.Dst.Bits() != 0 {
 					continue
 				}
 

client/internal/networkmonitor/monitor_generic.go

@@ -59,7 +59,7 @@ func (nw *NetworkMonitor) Start(ctx context.Context, callback func()) (err error
 	// recover in case sys ops panic
 	defer func() {
 		if r := recover(); r != nil {
-			err = fmt.Errorf("panic occurred: %v, stack trace: %s", r, string(debug.Stack()))
+			err = fmt.Errorf("panic occurred: %v, stack trace: %s", r, debug.Stack())
 		}
 	}()
 

client/internal/networkmonitor/monitor_windows.go

@@ -3,252 +3,73 @@ package networkmonitor
 import (
 	"context"
 	"fmt"
-	"net"
-	"net/netip"
 	"strings"
-	"time"
 
 	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/client/internal/routemanager/systemops"
 )
 
-const (
-	unreachable = 0
-	incomplete  = 1
-	probe       = 2
-	delay       = 3
-	stale       = 4
-	reachable   = 5
-	permanent   = 6
-	tbd         = 7
-)
-
-const interval = 10 * time.Second
-
 func checkChange(ctx context.Context, nexthopv4, nexthopv6 systemops.Nexthop, callback func()) error {
-	var neighborv4, neighborv6 *systemops.Neighbor
-	{
-		initialNeighbors, err := getNeighbors()
-		if err != nil {
-			return fmt.Errorf("get neighbors: %w", err)
-		}
-
-		neighborv4 = assignNeighbor(nexthopv4, initialNeighbors)
-		neighborv6 = assignNeighbor(nexthopv6, initialNeighbors)
+	routeMonitor, err := systemops.NewRouteMonitor(ctx)
+	if err != nil {
+		return fmt.Errorf("failed to create route monitor: %w", err)
 	}
-	log.Debugf("Network monitor: initial IPv4 neighbor: %v, IPv6 neighbor: %v", neighborv4, neighborv6)
-
-	ticker := time.NewTicker(interval)
-	defer ticker.Stop()
+	defer func() {
+		if err := routeMonitor.Stop(); err != nil {
+			log.Errorf("Network monitor: failed to stop route monitor: %v", err)
+		}
+	}()
 
 	for {
 		select {
 		case <-ctx.Done():
 			return ErrStopped
-		case <-ticker.C:
-			if changed(nexthopv4, neighborv4, nexthopv6, neighborv6) {
-				go callback()
-				return nil
+		case route := <-routeMonitor.RouteUpdates():
+			if route.Destination.Bits() != 0 {
+				continue
+			}
+
+			if routeChanged(route, nexthopv4, nexthopv6, callback) {
+				break
 			}
 		}
 	}
 }
 
-func assignNeighbor(nexthop systemops.Nexthop, initialNeighbors map[netip.Addr]systemops.Neighbor) *systemops.Neighbor {
-	if n, ok := initialNeighbors[nexthop.IP]; ok &&
-		n.State != unreachable &&
-		n.State != incomplete &&
-		n.State != tbd {
-		return &n
-	}
-	return nil
-}
-
-func changed(
-	nexthopv4 systemops.Nexthop,
-	neighborv4 *systemops.Neighbor,
-	nexthopv6 systemops.Nexthop,
-	neighborv6 *systemops.Neighbor,
-) bool {
-	neighbors, err := getNeighbors()
-	if err != nil {
-		log.Errorf("network monitor: error fetching current neighbors: %v", err)
-		return false
-	}
-	if neighborChanged(nexthopv4, neighborv4, neighbors) || neighborChanged(nexthopv6, neighborv6, neighbors) {
-		return true
-	}
-
-	routes, err := getRoutes()
-	if err != nil {
-		log.Errorf("network monitor: error fetching current routes: %v", err)
-		return false
-	}
-
-	if routeChanged(nexthopv4, nexthopv4.Intf, routes) || routeChanged(nexthopv6, nexthopv6.Intf, routes) {
-		return true
-	}
-
-	return false
-}
-
-// routeChanged checks if the default routes still point to our nexthop/interface
-func routeChanged(nexthop systemops.Nexthop, intf *net.Interface, routes []systemops.Route) bool {
-	if !nexthop.IP.IsValid() {
-		return false
-	}
-
-	if isSoftInterface(nexthop.Intf.Name) {
-		log.Tracef("network monitor: ignoring default route change for soft interface %s", nexthop.Intf.Name)
-		return false
-	}
-
-	unspec := getUnspecifiedPrefix(nexthop.IP)
-	defaultRoutes, foundMatchingRoute := processRoutes(nexthop, intf, routes, unspec)
-
-	log.Tracef("network monitor: all default routes:\n%s", strings.Join(defaultRoutes, "\n"))
-
-	if !foundMatchingRoute {
-		logRouteChange(nexthop.IP, intf)
-		return true
-	}
-
-	return false
-}
-
-func getUnspecifiedPrefix(ip netip.Addr) netip.Prefix {
-	if ip.Is6() {
-		return netip.PrefixFrom(netip.IPv6Unspecified(), 0)
-	}
-	return netip.PrefixFrom(netip.IPv4Unspecified(), 0)
-}
-
-func processRoutes(nexthop systemops.Nexthop, nexthopIntf *net.Interface, routes []systemops.Route, unspec netip.Prefix) ([]string, bool) {
-	var defaultRoutes []string
-	foundMatchingRoute := false
-
-	for _, r := range routes {
-		if r.Destination == unspec {
-			routeInfo := formatRouteInfo(r)
-			defaultRoutes = append(defaultRoutes, routeInfo)
-
-			if r.Nexthop == nexthop.IP && compareIntf(r.Interface, nexthopIntf) == 0 {
-				foundMatchingRoute = true
-				log.Debugf("network monitor: found matching default route: %s", routeInfo)
-			}
+func routeChanged(route systemops.RouteUpdate, nexthopv4, nexthopv6 systemops.Nexthop, callback func()) bool {
+	intf := "<nil>"
+	if route.Interface != nil {
+		intf = route.Interface.Name
+		if isSoftInterface(intf) {
+			log.Debugf("Network monitor: ignoring default route change for soft interface %s", intf)
+			return false
 		}
 	}
 
-	return defaultRoutes, foundMatchingRoute
-}
-
-func formatRouteInfo(r systemops.Route) string {
-	newIntf := "<nil>"
-	if r.Interface != nil {
-		newIntf = r.Interface.Name
-	}
-	return fmt.Sprintf("Nexthop: %s, Interface: %s", r.Nexthop, newIntf)
-}
-
-func logRouteChange(ip netip.Addr, intf *net.Interface) {
-	oldIntf := "<nil>"
-	if intf != nil {
-		oldIntf = intf.Name
-	}
-	log.Infof("network monitor: default route for %s (%s) is gone or changed", ip, oldIntf)
-}
-
-func neighborChanged(nexthop systemops.Nexthop, neighbor *systemops.Neighbor, neighbors map[netip.Addr]systemops.Neighbor) bool {
-	if neighbor == nil {
-		return false
-	}
-
-	// TODO: consider non-local nexthops, e.g. on point-to-point interfaces
-	if n, ok := neighbors[nexthop.IP]; ok {
-		if n.State == unreachable || n.State == incomplete {
-			log.Infof("network monitor: neighbor %s (%s) is not reachable: %s", neighbor.IPAddress, neighbor.LinkLayerAddress, stateFromInt(n.State))
-			return true
-		} else if n.InterfaceIndex != neighbor.InterfaceIndex {
-			log.Infof(
-				"network monitor: neighbor %s (%s) changed interface from '%s' (%d) to '%s' (%d): %s",
-				neighbor.IPAddress,
-				neighbor.LinkLayerAddress,
-				neighbor.InterfaceAlias,
-				neighbor.InterfaceIndex,
-				n.InterfaceAlias,
-				n.InterfaceIndex,
-				stateFromInt(n.State),
-			)
+	switch route.Type {
+	case systemops.RouteModified:
+		// TODO: get routing table to figure out if our route is affected for modified routes
+		log.Infof("Network monitor: default route changed: via %s, interface %s", route.NextHop, intf)
+		go callback()
+		return true
+	case systemops.RouteAdded:
+		if route.NextHop.Is4() && route.NextHop != nexthopv4.IP || route.NextHop.Is6() && route.NextHop != nexthopv6.IP {
+			log.Infof("Network monitor: default route added: via %s, interface %s", route.NextHop, intf)
+			go callback()
+			return true
+		}
+	case systemops.RouteDeleted:
+		if nexthopv4.Intf != nil && route.NextHop == nexthopv4.IP || nexthopv6.Intf != nil && route.NextHop == nexthopv6.IP {
+			log.Infof("Network monitor: default route removed: via %s, interface %s", route.NextHop, intf)
+			go callback()
 			return true
 		}
-	} else {
-		log.Infof("network monitor: neighbor %s (%s) is gone", neighbor.IPAddress, neighbor.LinkLayerAddress)
-		return true
 	}
 
 	return false
 }
 
-func getNeighbors() (map[netip.Addr]systemops.Neighbor, error) {
-	entries, err := systemops.GetNeighbors()
-	if err != nil {
-		return nil, fmt.Errorf("get neighbors: %w", err)
-	}
-
-	neighbours := make(map[netip.Addr]systemops.Neighbor, len(entries))
-	for _, entry := range entries {
-		neighbours[entry.IPAddress] = entry
-	}
-
-	return neighbours, nil
-}
-
-func getRoutes() ([]systemops.Route, error) {
-	entries, err := systemops.GetRoutes()
-	if err != nil {
-		return nil, fmt.Errorf("get routes: %w", err)
-	}
-
-	return entries, nil
-}
-
-func stateFromInt(state uint8) string {
-	switch state {
-	case unreachable:
-		return "unreachable"
-	case incomplete:
-		return "incomplete"
-	case probe:
-		return "probe"
-	case delay:
-		return "delay"
-	case stale:
-		return "stale"
-	case reachable:
-		return "reachable"
-	case permanent:
-		return "permanent"
-	case tbd:
-		return "tbd"
-	default:
-		return "unknown"
-	}
-}
-
-func compareIntf(a, b *net.Interface) int {
-	switch {
-	case a == nil && b == nil:
-		return 0
-	case a == nil:
-		return -1
-	case b == nil:
-		return 1
-	default:
-		return a.Index - b.Index
-	}
-}
-
 func isSoftInterface(name string) bool {
 	return strings.Contains(strings.ToLower(name), "isatap") || strings.Contains(strings.ToLower(name), "teredo")
 }

client/internal/peer/conn.go

@@ -147,7 +147,7 @@ func NewConn(engineCtx context.Context, config ConnConfig, statusRecorder *Statu
 		OnStatusChanged: conn.onWorkerICEStateDisconnected,
 	}
 
-	conn.workerRelay = NewWorkerRelay(ctx, connLog, config, relayManager, rFns)
+	conn.workerRelay = NewWorkerRelay(connLog, config, relayManager, rFns)
 
 	relayIsSupportedLocally := conn.workerRelay.RelayIsSupportedLocally()
 	conn.workerICE, err = NewWorkerICE(ctx, connLog, config, signaler, iFaceDiscover, statusRecorder, relayIsSupportedLocally, wFns)
@@ -204,7 +204,6 @@ func (conn *Conn) startHandshakeAndReconnect() {
 	} else {
 		conn.reconnectLoopForOnDisconnectedEvent()
 	}
-
 }
 
 // Close closes this peer Conn issuing a close event to the Conn closeCh
@@ -212,13 +211,18 @@ func (conn *Conn) Close() {
 	conn.mu.Lock()
 	defer conn.mu.Unlock()
 
+	conn.log.Infof("close peer connection")
 	conn.ctxCancel()
 
 	if !conn.opened {
-		log.Debugf("ignore close connection to peer")
+		conn.log.Debugf("ignore close connection to peer")
 		return
 	}
 
+	conn.workerRelay.DisableWgWatcher()
+	conn.workerRelay.CloseConn()
+	conn.workerICE.Close()
+
 	if conn.wgProxyRelay != nil {
 		err := conn.wgProxyRelay.CloseConn()
 		if err != nil {
@@ -320,11 +324,11 @@ func (conn *Conn) reconnectLoopWithRetry() {
 
 			if conn.workerRelay.IsRelayConnectionSupportedWithPeer() {
 				if conn.statusRelay == StatusDisconnected || conn.statusICE == StatusDisconnected {
-					conn.log.Tracef("ticker timedout, relay state: %s, ice state: %s", conn.statusRelay, conn.statusICE)
+					conn.log.Tracef("connectivity guard timedout, relay state: %s, ice state: %s", conn.statusRelay, conn.statusICE)
 				}
 			} else {
 				if conn.statusICE == StatusDisconnected {
-					conn.log.Tracef("ticker timedout, ice state: %s", conn.statusICE)
+					conn.log.Tracef("connectivity guard timedout, ice state: %s", conn.statusICE)
 				}
 			}
 
@@ -352,6 +356,7 @@ func (conn *Conn) reconnectLoopWithRetry() {
 			ticker.Stop()
 			ticker = conn.prepareExponentTicker()
 		case <-conn.ctx.Done():
+			conn.log.Debugf("context is done, stop reconnect loop")
 			return
 		}
 	}
@@ -392,6 +397,7 @@ func (conn *Conn) reconnectLoopForOnDisconnectedEvent() {
 			}
 			conn.log.Debugf("ICE state changed, try to send new offer")
 		case <-conn.ctx.Done():
+			conn.log.Debugf("context is done, stop reconnect loop")
 			return
 		}
 
@@ -438,7 +444,9 @@ func (conn *Conn) iCEConnectionIsReady(priority ConnPriority, iceConnInfo ICECon
 		}
 	}
 
-	err = conn.config.WgConfig.WgInterface.UpdatePeer(conn.config.WgConfig.RemoteKey, conn.config.WgConfig.AllowedIps, defaultWgKeepAlive, endpointUdpAddr, conn.config.WgConfig.PreSharedKey)
+	conn.workerRelay.DisableWgWatcher()
+
+	err = conn.configureWGEndpoint(endpointUdpAddr)
 	if err != nil {
 		if wgProxy != nil {
 			if err := wgProxy.CloseConn(); err != nil {
@@ -467,6 +475,10 @@ func (conn *Conn) onWorkerICEStateDisconnected(newState ConnStatus) {
 	conn.mu.Lock()
 	defer conn.mu.Unlock()
 
+	if conn.ctx.Err() != nil {
+		return
+	}
+
 	conn.log.Tracef("ICE connection state changed to %s", newState)
 
 	// switch back to relay connection
@@ -476,6 +488,8 @@ func (conn *Conn) onWorkerICEStateDisconnected(newState ConnStatus) {
 		if err != nil {
 			conn.log.Errorf("failed to switch to relay conn: %v", err)
 		}
+		conn.workerRelay.EnableWgWatcher(conn.ctx)
+		conn.currentConnPriority = connPriorityRelay
 	}
 
 	changed := conn.statusICE != newState && newState != StatusConnecting
@@ -546,6 +560,7 @@ func (conn *Conn) relayConnectionIsReady(rci RelayConnInfo) {
 		return
 	}
 	wgConfigWorkaround()
+	conn.workerRelay.EnableWgWatcher(conn.ctx)
 
 	if conn.wgProxyRelay != nil {
 		if err := conn.wgProxyRelay.CloseConn(); err != nil {
@@ -563,6 +578,10 @@ func (conn *Conn) onWorkerRelayStateDisconnected() {
 	conn.mu.Lock()
 	defer conn.mu.Unlock()
 
+	if conn.ctx.Err() != nil {
+		return
+	}
+
 	if conn.wgProxyRelay != nil {
 		log.Debugf("relayed connection is closed, clean up WireGuard config")
 		err := conn.config.WgConfig.WgInterface.RemovePeer(conn.config.WgConfig.RemoteKey)

client/internal/peer/handshaker.go

@@ -79,7 +79,8 @@ func (h *Handshaker) Listen() {
 		h.log.Debugf("wait for remote offer confirmation")
 		remoteOfferAnswer, err := h.waitForRemoteOfferConfirmation()
 		if err != nil {
-			if _, ok := err.(*ConnectionClosedError); ok {
+			var connectionClosedError *ConnectionClosedError
+			if errors.As(err, &connectionClosedError) {
 				h.log.Tracef("stop handshaker")
 				return
 			}

client/internal/peer/status.go

@@ -3,6 +3,7 @@ package peer
 import (
 	"errors"
 	"net/netip"
+	"slices"
 	"sync"
 	"time"
 
@@ -651,29 +652,35 @@ func (d *Status) GetSignalState() SignalState {
 	}
 }
 
+// GetRelayStates returns the stun/turn/permanent relay states
 func (d *Status) GetRelayStates() []relay.ProbeResult {
 	if d.relayMgr == nil {
 		return d.relayStates
 	}
 
 	// extend the list of stun, turn servers with relay address
-	relaysState := make([]relay.ProbeResult, len(d.relayStates), len(d.relayStates)+1)
-	copy(relaysState, d.relayStates)
+	relayStates := slices.Clone(d.relayStates)
 
-	relayState := relay.ProbeResult{}
+	var relayState relay.ProbeResult
 
 	// if the server connection is not established then we will use the general address
 	// in case of connection we will use the instance specific address
 	instanceAddr, err := d.relayMgr.RelayInstanceAddress()
 	if err != nil {
-		relayState.URI = d.relayMgr.ServerURL()
+		// TODO add their status
+		if errors.Is(err, relayClient.ErrRelayClientNotConnected) {
+			for _, r := range d.relayMgr.ServerURLs() {
+				relayStates = append(relayStates, relay.ProbeResult{
+					URI: r,
+				})
+			}
+			return relayStates
+		}
 		relayState.Err = err
-	} else {
-		relayState.URI = instanceAddr
 	}
 
-	relaysState = append(relaysState, relayState)
-	return relaysState
+	relayState.URI = instanceAddr
+	return append(relayStates, relayState)
 }
 
 func (d *Status) GetDNSStates() []NSGroupState {

client/internal/peer/worker_ice.go

@@ -38,7 +38,7 @@ var (
 
 type ICEConfig struct {
 	// StunTurn is a list of STUN and TURN URLs
-	StunTurn atomic.Value // []*stun.URI
+	StunTurn *atomic.Value // []*stun.URI
 
 	// InterfaceBlackList is a list of machine interfaces that should be filtered out by ICE Candidate gathering
 	// (e.g. if eth0 is in the list, host candidate of this interface won't be used)
@@ -218,6 +218,20 @@ func (w *WorkerICE) GetLocalUserCredentials() (frag string, pwd string) {
 	return w.localUfrag, w.localPwd
 }
 
+func (w *WorkerICE) Close() {
+	w.muxAgent.Lock()
+	defer w.muxAgent.Unlock()
+
+	if w.agent == nil {
+		return
+	}
+
+	err := w.agent.Close()
+	if err != nil {
+		w.log.Warnf("failed to close ICE agent: %s", err)
+	}
+}
+
 func (w *WorkerICE) reCreateAgent(agentCancel context.CancelFunc, relaySupport []ice.CandidateType) (*ice.Agent, error) {
 	transportNet, err := w.newStdNet()
 	if err != nil {
@@ -453,5 +467,4 @@ func generateICECredentials() (string, string, error) {
 		return "", "", err
 	}
 	return ufrag, pwd, nil
-
 }

client/internal/peer/worker_relay.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"net"
+	"sync"
 	"sync/atomic"
 	"time"
 
@@ -14,7 +15,7 @@ import (
 
 var (
 	wgHandshakePeriod   = 2 * time.Minute
-	wgHandshakeOvertime = 30000 * time.Millisecond
+	wgHandshakeOvertime = 30 * time.Second
 )
 
 type RelayConnInfo struct {
@@ -29,23 +30,26 @@ type WorkerRelayCallbacks struct {
 }
 
 type WorkerRelay struct {
-	parentCtx    context.Context
 	log          *log.Entry
 	config       ConnConfig
 	relayManager relayClient.ManagerService
-	conn         WorkerRelayCallbacks
+	callBacks    WorkerRelayCallbacks
+
+	relayedConn      net.Conn
+	relayLock        sync.Mutex
+	ctxWgWatch       context.Context
+	ctxCancelWgWatch context.CancelFunc
+	ctxLock          sync.Mutex
 
-	ctxCancel                  context.CancelFunc
 	relaySupportedOnRemotePeer atomic.Bool
 }
 
-func NewWorkerRelay(ctx context.Context, log *log.Entry, config ConnConfig, relayManager relayClient.ManagerService, callbacks WorkerRelayCallbacks) *WorkerRelay {
+func NewWorkerRelay(log *log.Entry, config ConnConfig, relayManager relayClient.ManagerService, callbacks WorkerRelayCallbacks) *WorkerRelay {
 	r := &WorkerRelay{
-		parentCtx:    ctx,
 		log:          log,
 		config:       config,
 		relayManager: relayManager,
-		conn:         callbacks,
+		callBacks:    callbacks,
 	}
 	return r
 }
@@ -69,7 +73,6 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 
 	relayedConn, err := w.relayManager.OpenConn(srv, w.config.Key)
 	if err != nil {
-		// todo handle all type errors
 		if errors.Is(err, relayClient.ErrConnAlreadyExists) {
 			w.log.Infof("do not need to reopen relay connection")
 			return
@@ -77,28 +80,54 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 		w.log.Errorf("failed to open connection via Relay: %s", err)
 		return
 	}
+	w.relayLock.Lock()
+	w.relayedConn = relayedConn
+	w.relayLock.Unlock()
 
-	ctx, ctxCancel := context.WithCancel(w.parentCtx)
-	w.ctxCancel = ctxCancel
-
-	err = w.relayManager.AddCloseListener(srv, w.disconnected)
+	err = w.relayManager.AddCloseListener(srv, w.onRelayMGDisconnected)
 	if err != nil {
 		log.Errorf("failed to add close listener: %s", err)
 		_ = relayedConn.Close()
-		ctxCancel()
 		return
 	}
 
-	go w.wgStateCheck(ctx, relayedConn)
-
 	w.log.Debugf("peer conn opened via Relay: %s", srv)
-	go w.conn.OnConnReady(RelayConnInfo{
+	go w.callBacks.OnConnReady(RelayConnInfo{
 		relayedConn:     relayedConn,
 		rosenpassPubKey: remoteOfferAnswer.RosenpassPubKey,
 		rosenpassAddr:   remoteOfferAnswer.RosenpassAddr,
 	})
 }
 
+func (w *WorkerRelay) EnableWgWatcher(ctx context.Context) {
+	w.log.Debugf("enable WireGuard watcher")
+	w.ctxLock.Lock()
+	defer w.ctxLock.Unlock()
+
+	if w.ctxWgWatch != nil && w.ctxWgWatch.Err() == nil {
+		return
+	}
+
+	ctx, ctxCancel := context.WithCancel(ctx)
+	go w.wgStateCheck(ctx)
+	w.ctxWgWatch = ctx
+	w.ctxCancelWgWatch = ctxCancel
+
+}
+
+func (w *WorkerRelay) DisableWgWatcher() {
+	w.ctxLock.Lock()
+	defer w.ctxLock.Unlock()
+
+	if w.ctxCancelWgWatch == nil {
+		return
+	}
+
+	w.log.Debugf("disable WireGuard watcher")
+
+	w.ctxCancelWgWatch()
+}
+
 func (w *WorkerRelay) RelayInstanceAddress() (string, error) {
 	return w.relayManager.RelayInstanceAddress()
 }
@@ -115,10 +144,24 @@ func (w *WorkerRelay) RelayIsSupportedLocally() bool {
 	return w.relayManager.HasRelayAddress()
 }
 
+func (w *WorkerRelay) CloseConn() {
+	w.relayLock.Lock()
+	defer w.relayLock.Unlock()
+	if w.relayedConn == nil {
+		return
+	}
+
+	err := w.relayedConn.Close()
+	if err != nil {
+		w.log.Warnf("failed to close relay connection: %v", err)
+	}
+}
+
 // wgStateCheck help to check the state of the wireguard handshake and relay connection
-func (w *WorkerRelay) wgStateCheck(ctx context.Context, conn net.Conn) {
+func (w *WorkerRelay) wgStateCheck(ctx context.Context) {
 	timer := time.NewTimer(wgHandshakeOvertime)
 	defer timer.Stop()
+	expected := wgHandshakeOvertime
 	for {
 		select {
 		case <-timer.C:
@@ -129,15 +172,19 @@ func (w *WorkerRelay) wgStateCheck(ctx context.Context, conn net.Conn) {
 			}
 			w.log.Tracef("last handshake: %v", lastHandshake)
 
-			if time.Since(lastHandshake) > wgHandshakePeriod {
+			if time.Since(lastHandshake) > expected {
 				w.log.Infof("Wireguard handshake timed out, closing relay connection")
-				_ = conn.Close()
-				w.conn.OnDisconnected()
+				w.relayLock.Lock()
+				_ = w.relayedConn.Close()
+				w.relayLock.Unlock()
+				w.callBacks.OnDisconnected()
 				return
 			}
-			resetTime := time.Until(lastHandshake.Add(wgHandshakeOvertime + wgHandshakePeriod))
+			resetTime := time.Until(lastHandshake.Add(wgHandshakePeriod + wgHandshakeOvertime))
 			timer.Reset(resetTime)
+			expected = wgHandshakePeriod
 		case <-ctx.Done():
+			w.log.Debugf("WireGuard watcher stopped")
 			return
 		}
 	}
@@ -165,9 +212,12 @@ func (w *WorkerRelay) wgState() (time.Time, error) {
 	return wgState.LastHandshake, nil
 }
 
-func (w *WorkerRelay) disconnected() {
-	if w.ctxCancel != nil {
-		w.ctxCancel()
+func (w *WorkerRelay) onRelayMGDisconnected() {
+	w.ctxLock.Lock()
+	defer w.ctxLock.Unlock()
+
+	if w.ctxCancelWgWatch != nil {
+		w.ctxCancelWgWatch()
 	}
-	w.conn.OnDisconnected()
+	go w.callBacks.OnDisconnected()
 }

client/internal/pkce_auth.go

@@ -2,6 +2,7 @@ package internal
 
 import (
 	"context"
+	"crypto/tls"
 	"fmt"
 	"net/url"
 
@@ -36,10 +37,12 @@ type PKCEAuthProviderConfig struct {
 	RedirectURLs []string
 	// UseIDToken indicates if the id token should be used for authentication
 	UseIDToken bool
+	//ClientCertPair is used for mTLS authentication to the IDP
+	ClientCertPair *tls.Certificate
 }
 
 // GetPKCEAuthorizationFlowInfo initialize a PKCEAuthorizationFlow instance and return with it
-func GetPKCEAuthorizationFlowInfo(ctx context.Context, privateKey string, mgmURL *url.URL) (PKCEAuthorizationFlow, error) {
+func GetPKCEAuthorizationFlowInfo(ctx context.Context, privateKey string, mgmURL *url.URL, clientCert *tls.Certificate) (PKCEAuthorizationFlow, error) {
 	// validate our peer's Wireguard PRIVATE key
 	myPrivateKey, err := wgtypes.ParseKey(privateKey)
 	if err != nil {
@@ -93,6 +96,7 @@ func GetPKCEAuthorizationFlowInfo(ctx context.Context, privateKey string, mgmURL
 			Scope:                 protoPKCEAuthorizationFlow.GetProviderConfig().GetScope(),
 			RedirectURLs:          protoPKCEAuthorizationFlow.GetProviderConfig().GetRedirectURLs(),
 			UseIDToken:            protoPKCEAuthorizationFlow.GetProviderConfig().GetUseIDToken(),
+			ClientCertPair:        clientCert,
 		},
 	}
 

client/internal/probe.go

@@ -2,6 +2,13 @@ package internal
 
 import "context"
 
+type ProbeHolder struct {
+	MgmProbe    *Probe
+	SignalProbe *Probe
+	RelayProbe  *Probe
+	WgProbe     *Probe
+}
+
 // Probe allows to run on-demand callbacks from different code locations.
 // Pass the probe to a receiving and a sending end. The receiving end starts listening
 // to requests with Receive and executes a callback when the sending end requests it

client/internal/routemanager/client.go

@@ -95,8 +95,8 @@ func (c *clientNetwork) getRouterPeerStatuses() map[route.ID]routerPeerStatus {
 // * Connected peers: Only routes with connected peers are considered.
 // * Metric: Routes with lower metrics (better) are prioritized.
 // * Non-relayed: Routes without relays are preferred.
-// * Direct connections: Routes with direct peer connections are favored.
 // * Latency: Routes with lower latency are prioritized.
+// * we compare the current score + 10ms to the chosen score to avoid flapping between routes
 // * Stability: In case of equal scores, the currently active route (if any) is maintained.
 //
 // It returns the ID of the selected optimal route.
@@ -136,13 +136,11 @@ func (c *clientNetwork) getBestRouteFromStatuses(routePeerStatuses map[route.ID]
 		}
 
 		if tempScore > chosenScore || (tempScore == chosenScore && chosen == "") {
-			log.Infof("tempScore(%f) > chosenScore(%f) || (tempScore(%f) == chosenScore(%f) && chosen == \"\"(%s): chosen: %s", tempScore, chosenScore, tempScore, chosenScore, chosen, r.ID)
 			chosen = r.ID
 			chosenScore = tempScore
 		}
 
 		if chosen == "" && currID == "" {
-			log.Infof("chosen == \"\" && currID == \"\" , chosen: %s", r.ID)
 			chosen = r.ID
 			chosenScore = tempScore
 		}
@@ -161,7 +159,6 @@ func (c *clientNetwork) getBestRouteFromStatuses(routePeerStatuses map[route.ID]
 
 		log.Warnf("The network [%v] has not been assigned a routing peer as no peers from the list %s are currently connected", c.handler, peers)
 	case chosen != currID:
-		log.Infof("chosen != currID, chosen: %s", chosen)
 		// we compare the current score + 10ms to the chosen score to avoid flapping between routes
 		if currScore != 0 && currScore+0.01 > chosenScore {
 			log.Debugf("Keeping current routing peer because the score difference with latency is less than 0.01(10ms), current: %f, new: %f", currScore, chosenScore)

client/internal/routemanager/client_test.go

@@ -3,8 +3,7 @@ package routemanager
 import (
 	"net/netip"
 	"testing"
-
-	log "github.com/sirupsen/logrus"
+	"time"
 
 	"github.com/netbirdio/netbird/client/internal/routemanager/static"
 	"github.com/netbirdio/netbird/route"
@@ -20,7 +19,79 @@ func TestGetBestrouteFromStatuses(t *testing.T) {
 		existingRoutes  map[route.ID]*route.Route
 	}{
 		{
-			name: "multiple connected peers with one direct",
+			name: "one route",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					relayed:   false,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+			},
+			currentRoute:    "",
+			expectedRouteID: "route1",
+		},
+		{
+			name: "one connected routes with relayed and direct",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					relayed:   true,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+			},
+			currentRoute:    "",
+			expectedRouteID: "route1",
+		},
+		{
+			name: "one connected routes with relayed and no direct",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					relayed:   true,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+			},
+			currentRoute:    "",
+			expectedRouteID: "route1",
+		},
+		{
+			name: "no connected peers",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: false,
+					relayed:   false,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+			},
+			currentRoute:    "",
+			expectedRouteID: "",
+		},
+		{
+			name: "multiple connected peers with different metrics",
 			statuses: map[route.ID]routerPeerStatus{
 				"route1": {
 					connected: true,
@@ -31,6 +102,33 @@ func TestGetBestrouteFromStatuses(t *testing.T) {
 					relayed:   false,
 				},
 			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: 9000,
+					Peer:   "peer1",
+				},
+				"route2": {
+					ID:     "route2",
+					Metric: route.MaxMetric,
+					Peer:   "peer2",
+				},
+			},
+			currentRoute:    "",
+			expectedRouteID: "route1",
+		},
+		{
+			name: "multiple connected peers with one relayed",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					relayed:   false,
+				},
+				"route2": {
+					connected: true,
+					relayed:   true,
+				},
+			},
 			existingRoutes: map[route.ID]*route.Route{
 				"route1": {
 					ID:     "route1",
@@ -46,31 +144,169 @@ func TestGetBestrouteFromStatuses(t *testing.T) {
 			currentRoute:    "",
 			expectedRouteID: "route1",
 		},
+		{
+			name: "multiple connected peers with different latencies",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					latency:   300 * time.Millisecond,
+				},
+				"route2": {
+					connected: true,
+					latency:   10 * time.Millisecond,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+				"route2": {
+					ID:     "route2",
+					Metric: route.MaxMetric,
+					Peer:   "peer2",
+				},
+			},
+			currentRoute:    "",
+			expectedRouteID: "route2",
+		},
+		{
+			name: "should ignore routes with latency 0",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					latency:   0 * time.Millisecond,
+				},
+				"route2": {
+					connected: true,
+					latency:   10 * time.Millisecond,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+				"route2": {
+					ID:     "route2",
+					Metric: route.MaxMetric,
+					Peer:   "peer2",
+				},
+			},
+			currentRoute:    "",
+			expectedRouteID: "route2",
+		},
+		{
+			name: "current route with similar score and similar but slightly worse latency should not change",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					relayed:   false,
+					latency:   15 * time.Millisecond,
+				},
+				"route2": {
+					connected: true,
+					relayed:   false,
+					latency:   10 * time.Millisecond,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+				"route2": {
+					ID:     "route2",
+					Metric: route.MaxMetric,
+					Peer:   "peer2",
+				},
+			},
+			currentRoute:    "route1",
+			expectedRouteID: "route1",
+		},
+		{
+			name: "current route with bad score should be changed to route with better score",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					relayed:   false,
+					latency:   200 * time.Millisecond,
+				},
+				"route2": {
+					connected: true,
+					relayed:   false,
+					latency:   10 * time.Millisecond,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+				"route2": {
+					ID:     "route2",
+					Metric: route.MaxMetric,
+					Peer:   "peer2",
+				},
+			},
+			currentRoute:    "route1",
+			expectedRouteID: "route2",
+		},
+		{
+			name: "current chosen route doesn't exist anymore",
+			statuses: map[route.ID]routerPeerStatus{
+				"route1": {
+					connected: true,
+					relayed:   false,
+					latency:   20 * time.Millisecond,
+				},
+				"route2": {
+					connected: true,
+					relayed:   false,
+					latency:   10 * time.Millisecond,
+				},
+			},
+			existingRoutes: map[route.ID]*route.Route{
+				"route1": {
+					ID:     "route1",
+					Metric: route.MaxMetric,
+					Peer:   "peer1",
+				},
+				"route2": {
+					ID:     "route2",
+					Metric: route.MaxMetric,
+					Peer:   "peer2",
+				},
+			},
+			currentRoute:    "routeDoesntExistAnymore",
+			expectedRouteID: "route2",
+		},
 	}
 
-	for i := 0; i < 10; i++ {
-		log.Infof("Test iteration %d", i)
-		for _, tc := range testCases {
-			t.Run(tc.name, func(t *testing.T) {
-				currentRoute := &route.Route{
-					ID: "routeDoesntExistAnymore",
-				}
-				if tc.currentRoute != "" {
-					currentRoute = tc.existingRoutes[tc.currentRoute]
-				}
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			currentRoute := &route.Route{
+				ID: "routeDoesntExistAnymore",
+			}
+			if tc.currentRoute != "" {
+				currentRoute = tc.existingRoutes[tc.currentRoute]
+			}
 
-				// create new clientNetwork
-				client := &clientNetwork{
-					handler:       static.NewRoute(&route.Route{Network: netip.MustParsePrefix("192.168.0.0/24")}, nil, nil),
-					routes:        tc.existingRoutes,
-					currentChosen: currentRoute,
-				}
+			// create new clientNetwork
+			client := &clientNetwork{
+				handler:       static.NewRoute(&route.Route{Network: netip.MustParsePrefix("192.168.0.0/24")}, nil, nil),
+				routes:        tc.existingRoutes,
+				currentChosen: currentRoute,
+			}
 
-				chosenRoute := client.getBestRouteFromStatuses(tc.statuses)
-				if chosenRoute != tc.expectedRouteID {
-					t.Errorf("expected routeID %s, got %s", tc.expectedRouteID, chosenRoute)
-				}
-			})
-		}
+			chosenRoute := client.getBestRouteFromStatuses(tc.statuses)
+			if chosenRoute != tc.expectedRouteID {
+				t.Errorf("expected routeID %s, got %s", tc.expectedRouteID, chosenRoute)
+			}
+		})
 	}
 }

client/internal/routemanager/manager.go

@@ -22,6 +22,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/routemanager/vars"
 	"github.com/netbirdio/netbird/client/internal/routeselector"
 	"github.com/netbirdio/netbird/iface"
+	relayClient "github.com/netbirdio/netbird/relay/client"
 	"github.com/netbirdio/netbird/route"
 	nbnet "github.com/netbirdio/netbird/util/net"
 	"github.com/netbirdio/netbird/version"
@@ -49,6 +50,7 @@ type DefaultManager struct {
 	serverRouter         serverRouter
 	sysOps               *systemops.SysOps
 	statusRecorder       *peer.Status
+	relayMgr             *relayClient.Manager
 	wgInterface          iface.IWGIface
 	pubKey               string
 	notifier             *notifier.Notifier
@@ -63,6 +65,7 @@ func NewManager(
 	dnsRouteInterval time.Duration,
 	wgInterface iface.IWGIface,
 	statusRecorder *peer.Status,
+	relayMgr *relayClient.Manager,
 	initialRoutes []*route.Route,
 ) *DefaultManager {
 	mCTX, cancel := context.WithCancel(ctx)
@@ -74,6 +77,7 @@ func NewManager(
 		stop:             cancel,
 		dnsRouteInterval: dnsRouteInterval,
 		clientNetworks:   make(map[route.HAUniqueID]*clientNetwork),
+		relayMgr:         relayMgr,
 		routeSelector:    routeselector.NewRouteSelector(),
 		sysOps:           sysOps,
 		statusRecorder:   statusRecorder,
@@ -124,9 +128,12 @@ func (m *DefaultManager) Init() (nbnet.AddHookFunc, nbnet.RemoveHookFunc, error)
 		log.Warnf("Failed cleaning up routing: %v", err)
 	}
 
-	mgmtAddress := m.statusRecorder.GetManagementState().URL
-	signalAddress := m.statusRecorder.GetSignalState().URL
-	ips := resolveURLsToIPs([]string{mgmtAddress, signalAddress})
+	initialAddresses := []string{m.statusRecorder.GetManagementState().URL, m.statusRecorder.GetSignalState().URL}
+	if m.relayMgr != nil {
+		initialAddresses = append(initialAddresses, m.relayMgr.ServerURLs()...)
+	}
+
+	ips := resolveURLsToIPs(initialAddresses)
 
 	beforePeerHook, afterPeerHook, err := m.sysOps.SetupRouting(ips)
 	if err != nil {

client/internal/routemanager/manager_test.go

@@ -416,7 +416,7 @@ func TestManagerUpdateRoutes(t *testing.T) {
 
 			statusRecorder := peer.NewRecorder("https://mgm")
 			ctx := context.TODO()
-			routeManager := NewManager(ctx, localPeerKey, 0, wgInterface, statusRecorder, nil)
+			routeManager := NewManager(ctx, localPeerKey, 0, wgInterface, statusRecorder, nil, nil)
 
 			_, _, err = routeManager.Init()
 

client/internal/routemanager/sysctl/sysctl_linux.go

@@ -1,4 +1,5 @@
-// go:build !android
+//go:build !android
+
 package sysctl
 
 import (

client/internal/routemanager/systemops/systemops_windows.go

@@ -3,6 +3,8 @@
 package systemops
 
 import (
+	"context"
+	"encoding/binary"
 	"fmt"
 	"net"
 	"net/netip"
@@ -11,15 +13,43 @@ import (
 	"strconv"
 	"strings"
 	"sync"
+	"syscall"
 	"time"
+	"unsafe"
 
 	log "github.com/sirupsen/logrus"
 	"github.com/yusufpapurcu/wmi"
+	"golang.org/x/sys/windows"
 
 	"github.com/netbirdio/netbird/client/firewall/uspfilter"
 	nbnet "github.com/netbirdio/netbird/util/net"
 )
 
+type RouteUpdateType int
+
+// RouteUpdate represents a change in the routing table.
+// The interface field contains the index only.
+type RouteUpdate struct {
+	Type        RouteUpdateType
+	Destination netip.Prefix
+	NextHop     netip.Addr
+	Interface   *net.Interface
+}
+
+// RouteMonitor provides a way to monitor changes in the routing table.
+type RouteMonitor struct {
+	updates chan RouteUpdate
+	handle  windows.Handle
+	done    chan struct{}
+}
+
+// Route represents a single routing table entry.
+type Route struct {
+	Destination netip.Prefix
+	Nexthop     netip.Addr
+	Interface   *net.Interface
+}
+
 type MSFT_NetRoute struct {
 	DestinationPrefix string
 	NextHop           string
@@ -28,33 +58,77 @@ type MSFT_NetRoute struct {
 	AddressFamily     uint16
 }
 
-type Route struct {
-	Destination netip.Prefix
-	Nexthop     netip.Addr
-	Interface   *net.Interface
+// MIB_IPFORWARD_ROW2 is defined in https://learn.microsoft.com/en-us/windows/win32/api/netioapi/ns-netioapi-mib_ipforward_row2
+type MIB_IPFORWARD_ROW2 struct {
+	InterfaceLuid        uint64
+	InterfaceIndex       uint32
+	DestinationPrefix    IP_ADDRESS_PREFIX
+	NextHop              SOCKADDR_INET_NEXTHOP
+	SitePrefixLength     uint8
+	ValidLifetime        uint32
+	PreferredLifetime    uint32
+	Metric               uint32
+	Protocol             uint32
+	Loopback             uint8
+	AutoconfigureAddress uint8
+	Publish              uint8
+	Immortal             uint8
+	Age                  uint32
+	Origin               uint32
 }
 
-type MSFT_NetNeighbor struct {
-	IPAddress        string
-	LinkLayerAddress string
-	State            uint8
-	AddressFamily    uint16
-	InterfaceIndex   uint32
-	InterfaceAlias   string
+// IP_ADDRESS_PREFIX is defined in https://learn.microsoft.com/en-us/windows/win32/api/netioapi/ns-netioapi-ip_address_prefix
+type IP_ADDRESS_PREFIX struct {
+	Prefix       SOCKADDR_INET
+	PrefixLength uint8
 }
 
-type Neighbor struct {
-	IPAddress        netip.Addr
-	LinkLayerAddress string
-	State            uint8
-	AddressFamily    uint16
-	InterfaceIndex   uint32
-	InterfaceAlias   string
+// SOCKADDR_INET is defined in https://learn.microsoft.com/en-us/windows/win32/api/ws2ipdef/ns-ws2ipdef-sockaddr_inet
+// It represents the union of IPv4 and IPv6 socket addresses
+type SOCKADDR_INET struct {
+	sin6_family int16
+	// nolint:unused
+	sin6_port uint16
+	// 4 bytes ipv4 or 4 bytes flowinfo + 16 bytes ipv6 + 4 bytes scope_id
+	data [24]byte
 }
 
-var prefixList []netip.Prefix
-var lastUpdate time.Time
-var mux = sync.Mutex{}
+// SOCKADDR_INET_NEXTHOP is the same as SOCKADDR_INET but offset by 2 bytes
+type SOCKADDR_INET_NEXTHOP struct {
+	// nolint:unused
+	pad         [2]byte
+	sin6_family int16
+	// nolint:unused
+	sin6_port uint16
+	// 4 bytes ipv4 or 4 bytes flowinfo + 16 bytes ipv6 + 4 bytes scope_id
+	data [24]byte
+}
+
+// MIB_NOTIFICATION_TYPE is defined in https://learn.microsoft.com/en-us/windows/win32/api/netioapi/ne-netioapi-mib_notification_type
+type MIB_NOTIFICATION_TYPE int32
+
+var (
+	modiphlpapi                = windows.NewLazyDLL("iphlpapi.dll")
+	procNotifyRouteChange2     = modiphlpapi.NewProc("NotifyRouteChange2")
+	procCancelMibChangeNotify2 = modiphlpapi.NewProc("CancelMibChangeNotify2")
+
+	prefixList []netip.Prefix
+	lastUpdate time.Time
+	mux        sync.Mutex
+)
+
+const (
+	MibParemeterModification MIB_NOTIFICATION_TYPE = iota
+	MibAddInstance
+	MibDeleteInstance
+	MibInitialNotification
+)
+
+const (
+	RouteModified RouteUpdateType = iota
+	RouteAdded
+	RouteDeleted
+)
 
 func (r *SysOps) SetupRouting(initAddresses []net.IP) (nbnet.AddHookFunc, nbnet.RemoveHookFunc, error) {
 	return r.setupRefCounter(initAddresses)
@@ -94,6 +168,155 @@ func (r *SysOps) removeFromRouteTable(prefix netip.Prefix, nexthop Nexthop) erro
 	return nil
 }
 
+// NewRouteMonitor creates and starts a new RouteMonitor.
+// It returns a pointer to the RouteMonitor and an error if the monitor couldn't be started.
+func NewRouteMonitor(ctx context.Context) (*RouteMonitor, error) {
+	rm := &RouteMonitor{
+		updates: make(chan RouteUpdate, 5),
+		done:    make(chan struct{}),
+	}
+
+	if err := rm.start(ctx); err != nil {
+		return nil, err
+	}
+
+	return rm, nil
+}
+
+func (rm *RouteMonitor) start(ctx context.Context) error {
+	if ctx.Err() != nil {
+		return ctx.Err()
+	}
+
+	callbackPtr := windows.NewCallback(func(callerContext uintptr, row *MIB_IPFORWARD_ROW2, notificationType MIB_NOTIFICATION_TYPE) uintptr {
+		if ctx.Err() != nil {
+			return 0
+		}
+
+		update, err := rm.parseUpdate(row, notificationType)
+		if err != nil {
+			log.Errorf("Failed to parse route update: %v", err)
+			return 0
+		}
+
+		select {
+		case <-rm.done:
+			return 0
+		case rm.updates <- update:
+		default:
+			log.Warn("Route update channel is full, dropping update")
+		}
+		return 0
+	})
+
+	var handle windows.Handle
+	if err := notifyRouteChange2(windows.AF_UNSPEC, callbackPtr, 0, false, &handle); err != nil {
+		return fmt.Errorf("NotifyRouteChange2 failed: %w", err)
+	}
+
+	rm.handle = handle
+
+	return nil
+}
+
+func (rm *RouteMonitor) parseUpdate(row *MIB_IPFORWARD_ROW2, notificationType MIB_NOTIFICATION_TYPE) (RouteUpdate, error) {
+	// destination prefix, next hop, interface index, interface luid are guaranteed to be there
+	// GetIpForwardEntry2 is not needed
+
+	var update RouteUpdate
+
+	idx := int(row.InterfaceIndex)
+	if idx != 0 {
+		intf, err := net.InterfaceByIndex(idx)
+		if err != nil {
+			return update, fmt.Errorf("get interface name: %w", err)
+		}
+
+		update.Interface = intf
+	}
+
+	log.Tracef("Received route update with destination %v, next hop %v, interface %v", row.DestinationPrefix, row.NextHop, update.Interface)
+	dest := parseIPPrefix(row.DestinationPrefix, idx)
+	if !dest.Addr().IsValid() {
+		return RouteUpdate{}, fmt.Errorf("invalid destination: %v", row)
+	}
+
+	nexthop := parseIPNexthop(row.NextHop, idx)
+	if !nexthop.IsValid() {
+		return RouteUpdate{}, fmt.Errorf("invalid next hop %v", row)
+	}
+
+	updateType := RouteModified
+	switch notificationType {
+	case MibParemeterModification:
+		updateType = RouteModified
+	case MibAddInstance:
+		updateType = RouteAdded
+	case MibDeleteInstance:
+		updateType = RouteDeleted
+	}
+
+	update.Type = updateType
+	update.Destination = dest
+	update.NextHop = nexthop
+
+	return update, nil
+}
+
+// Stop stops the RouteMonitor.
+func (rm *RouteMonitor) Stop() error {
+	if rm.handle != 0 {
+		if err := cancelMibChangeNotify2(rm.handle); err != nil {
+			return fmt.Errorf("CancelMibChangeNotify2 failed: %w", err)
+		}
+		rm.handle = 0
+	}
+	close(rm.done)
+	close(rm.updates)
+	return nil
+}
+
+// RouteUpdates returns a channel that receives RouteUpdate messages.
+func (rm *RouteMonitor) RouteUpdates() <-chan RouteUpdate {
+	return rm.updates
+}
+
+func notifyRouteChange2(family uint32, callback uintptr, callerContext uintptr, initialNotification bool, handle *windows.Handle) error {
+	var initNotif uint32
+	if initialNotification {
+		initNotif = 1
+	}
+
+	r1, _, e1 := syscall.SyscallN(
+		procNotifyRouteChange2.Addr(),
+		uintptr(family),
+		callback,
+		callerContext,
+		uintptr(initNotif),
+		uintptr(unsafe.Pointer(handle)),
+	)
+	if r1 != 0 {
+		if e1 != 0 {
+			return e1
+		}
+		return syscall.EINVAL
+	}
+	return nil
+}
+
+func cancelMibChangeNotify2(handle windows.Handle) error {
+	r1, _, e1 := syscall.SyscallN(procCancelMibChangeNotify2.Addr(), uintptr(handle))
+	if r1 != 0 {
+		if e1 != 0 {
+			return e1
+		}
+		return syscall.EINVAL
+	}
+	return nil
+}
+
+// GetRoutesFromTable returns the current routing table from with prefixes only.
+// It ccaches the result for 2 seconds to avoid blocking the caller.
 func GetRoutesFromTable() ([]netip.Prefix, error) {
 	mux.Lock()
 	defer mux.Unlock()
@@ -117,6 +340,7 @@ func GetRoutesFromTable() ([]netip.Prefix, error) {
 	return prefixList, nil
 }
 
+// GetRoutes retrieves the current routing table using WMI.
 func GetRoutes() ([]Route, error) {
 	var entries []MSFT_NetRoute
 
@@ -146,8 +370,8 @@ func GetRoutes() ([]Route, error) {
 				Name:  entry.InterfaceAlias,
 			}
 
-			if nexthop.Is6() && (nexthop.IsLinkLocalUnicast() || nexthop.IsLinkLocalMulticast()) {
-				nexthop = nexthop.WithZone(strconv.Itoa(int(entry.InterfaceIndex)))
+			if nexthop.Is6() {
+				nexthop = addZone(nexthop, int(entry.InterfaceIndex))
 			}
 		}
 
@@ -161,33 +385,6 @@ func GetRoutes() ([]Route, error) {
 	return routes, nil
 }
 
-func GetNeighbors() ([]Neighbor, error) {
-	var entries []MSFT_NetNeighbor
-	query := `SELECT IPAddress, LinkLayerAddress, State, AddressFamily, InterfaceIndex, InterfaceAlias FROM MSFT_NetNeighbor`
-	if err := wmi.QueryNamespace(query, &entries, `ROOT\StandardCimv2`); err != nil {
-		return nil, fmt.Errorf("failed to query MSFT_NetNeighbor: %w", err)
-	}
-
-	var neighbors []Neighbor
-	for _, entry := range entries {
-		addr, err := netip.ParseAddr(entry.IPAddress)
-		if err != nil {
-			log.Warnf("Unable to parse neighbor IP address %s: %v", entry.IPAddress, err)
-			continue
-		}
-		neighbors = append(neighbors, Neighbor{
-			IPAddress:        addr,
-			LinkLayerAddress: entry.LinkLayerAddress,
-			State:            entry.State,
-			AddressFamily:    entry.AddressFamily,
-			InterfaceIndex:   entry.InterfaceIndex,
-			InterfaceAlias:   entry.InterfaceAlias,
-		})
-	}
-
-	return neighbors, nil
-}
-
 func addRouteCmd(prefix netip.Prefix, nexthop Nexthop) error {
 	args := []string{"add", prefix.String()}
 
@@ -220,3 +417,54 @@ func addRouteCmd(prefix netip.Prefix, nexthop Nexthop) error {
 func isCacheDisabled() bool {
 	return os.Getenv("NB_DISABLE_ROUTE_CACHE") == "true"
 }
+
+func parseIPPrefix(prefix IP_ADDRESS_PREFIX, idx int) netip.Prefix {
+	ip := parseIP(prefix.Prefix, idx)
+	return netip.PrefixFrom(ip, int(prefix.PrefixLength))
+}
+
+func parseIP(addr SOCKADDR_INET, idx int) netip.Addr {
+	return parseIPGeneric(addr.sin6_family, addr.data, idx)
+}
+
+func parseIPNexthop(addr SOCKADDR_INET_NEXTHOP, idx int) netip.Addr {
+	return parseIPGeneric(addr.sin6_family, addr.data, idx)
+}
+
+func parseIPGeneric(family int16, data [24]byte, interfaceIndex int) netip.Addr {
+	switch family {
+	case windows.AF_INET:
+		ipv4 := binary.BigEndian.Uint32(data[:4])
+		return netip.AddrFrom4([4]byte{
+			byte(ipv4 >> 24),
+			byte(ipv4 >> 16),
+			byte(ipv4 >> 8),
+			byte(ipv4),
+		})
+
+	case windows.AF_INET6:
+		// The IPv6 address is stored after the 4-byte flowinfo field
+		var ipv6 [16]byte
+		copy(ipv6[:], data[4:20])
+		ip := netip.AddrFrom16(ipv6)
+
+		// Check if there's a non-zero scope_id
+		scopeID := binary.BigEndian.Uint32(data[20:24])
+		if scopeID != 0 {
+			ip = ip.WithZone(strconv.FormatUint(uint64(scopeID), 10))
+		} else if interfaceIndex != 0 {
+			ip = addZone(ip, interfaceIndex)
+		}
+
+		return ip
+	}
+
+	return netip.IPv4Unspecified()
+}
+
+func addZone(ip netip.Addr, interfaceIndex int) netip.Addr {
+	if ip.IsLinkLocalUnicast() || ip.IsLinkLocalMulticast() {
+		ip = ip.WithZone(strconv.Itoa(interfaceIndex))
+	}
+	return ip
+}

client/ios/NetBirdSDK/client.go

@@ -270,7 +270,14 @@ func (c *Client) GetRoutesSelectionDetails() (*RoutesSelectionDetails, error) {
 	}
 
 	routesMap := engine.GetClientRoutesWithNetID()
-	routeSelector := engine.GetRouteManager().GetRouteSelector()
+	routeManager := engine.GetRouteManager()
+	if routeManager == nil {
+		return nil, fmt.Errorf("could not get route manager")
+	}
+	routeSelector := routeManager.GetRouteSelector()
+	if routeSelector == nil {
+		return nil, fmt.Errorf("could not get route selector")
+	}
 
 	var routes []*selectRoute
 	for id, rt := range routesMap {

client/ios/NetBirdSDK/login.go

@@ -74,7 +74,7 @@ func (a *Auth) SaveConfigIfSSOSupported() (bool, error) {
 	err := a.withBackOff(a.ctx, func() (err error) {
 		_, err = internal.GetDeviceAuthorizationFlowInfo(a.ctx, a.config.PrivateKey, a.config.ManagementURL)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
-			_, err = internal.GetPKCEAuthorizationFlowInfo(a.ctx, a.config.PrivateKey, a.config.ManagementURL)
+			_, err = internal.GetPKCEAuthorizationFlowInfo(a.ctx, a.config.PrivateKey, a.config.ManagementURL, nil)
 			if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
 				supportsSSO = false
 				err = nil

client/server/server.go

@@ -12,7 +12,6 @@ import (
 
 	"github.com/cenkalti/backoff/v4"
 	"golang.org/x/exp/maps"
-
 	"google.golang.org/protobuf/types/known/durationpb"
 
 	log "github.com/sirupsen/logrus"
@@ -143,10 +142,12 @@ func (s *Server) Start() error {
 		s.sessionWatcher.SetOnExpireListener(s.onSessionExpire)
 	}
 
-	if !config.DisableAutoConnect {
-		go s.connectWithRetryRuns(ctx, config, s.statusRecorder, s.mgmProbe, s.signalProbe, s.relayProbe, s.wgProbe)
+	if config.DisableAutoConnect {
+		return nil
 	}
 
+	go s.connectWithRetryRuns(ctx, config, s.statusRecorder, nil)
+
 	return nil
 }
 
@@ -154,7 +155,7 @@ func (s *Server) Start() error {
 // mechanism to keep the client connected even when the connection is lost.
 // we cancel retry if the client receive a stop or down command, or if disable auto connect is configured.
 func (s *Server) connectWithRetryRuns(ctx context.Context, config *internal.Config, statusRecorder *peer.Status,
-	mgmProbe *internal.Probe, signalProbe *internal.Probe, relayProbe *internal.Probe, wgProbe *internal.Probe,
+	runningChan chan error,
 ) {
 	backOff := getConnectWithBackoff(ctx)
 	retryStarted := false
@@ -185,7 +186,15 @@ func (s *Server) connectWithRetryRuns(ctx context.Context, config *internal.Conf
 	runOperation := func() error {
 		log.Tracef("running client connection")
 		s.connectClient = internal.NewConnectClient(ctx, config, statusRecorder)
-		err := s.connectClient.RunWithProbes(mgmProbe, signalProbe, relayProbe, wgProbe)
+
+		probes := internal.ProbeHolder{
+			MgmProbe:    s.mgmProbe,
+			SignalProbe: s.signalProbe,
+			RelayProbe:  s.relayProbe,
+			WgProbe:     s.wgProbe,
+		}
+
+		err := s.connectClient.RunWithProbes(&probes, runningChan)
 		if err != nil {
 			log.Debugf("run client connection exited with error: %v. Will retry in the background", err)
 		}
@@ -576,9 +585,22 @@ func (s *Server) Up(callerCtx context.Context, _ *proto.UpRequest) (*proto.UpRes
 	s.statusRecorder.UpdateManagementAddress(s.config.ManagementURL.String())
 	s.statusRecorder.UpdateRosenpass(s.config.RosenpassEnabled, s.config.RosenpassPermissive)
 
-	go s.connectWithRetryRuns(ctx, s.config, s.statusRecorder, s.mgmProbe, s.signalProbe, s.relayProbe, s.wgProbe)
+	runningChan := make(chan error)
+	go s.connectWithRetryRuns(ctx, s.config, s.statusRecorder, runningChan)
 
-	return &proto.UpResponse{}, nil
+	for {
+		select {
+		case err := <-runningChan:
+			if err != nil {
+				log.Debugf("waiting for engine to become ready failed: %s", err)
+			} else {
+				return &proto.UpResponse{}, nil
+			}
+		case <-callerCtx.Done():
+			log.Debug("context done, stopping the wait for engine to become ready")
+			return nil, callerCtx.Err()
+		}
+	}
 }
 
 // Down engine work in the daemon.
@@ -590,28 +612,19 @@ func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownRes
 		return nil, fmt.Errorf("service is not up")
 	}
 	s.actCancel()
+
+	err := s.connectClient.Stop()
+	if err != nil {
+		log.Errorf("failed to shut down properly: %v", err)
+		return nil, err
+	}
+
 	state := internal.CtxGetState(s.rootCtx)
 	state.Set(internal.StatusIdle)
 
-	maxWaitTime := 5 * time.Second
-	timeout := time.After(maxWaitTime)
+	log.Infof("service is down")
 
-	engine := s.connectClient.Engine()
-
-	for {
-		if !engine.IsWGIfaceUp() {
-			return &proto.DownResponse{}, nil
-		}
-
-		select {
-		case <-ctx.Done():
-			return &proto.DownResponse{}, nil
-		case <-timeout:
-			return nil, fmt.Errorf("failed to shut down properly")
-		default:
-			time.Sleep(100 * time.Millisecond)
-		}
-	}
+	return &proto.DownResponse{}, nil
 }
 
 // Status returns the daemon status

client/server/server_test.go

@@ -6,10 +6,11 @@ import (
 	"testing"
 	"time"
 
-	"github.com/netbirdio/management-integrations/integrations"
 	"github.com/stretchr/testify/require"
 	"go.opentelemetry.io/otel"
 
+	"github.com/netbirdio/management-integrations/integrations"
+
 	log "github.com/sirupsen/logrus"
 	"google.golang.org/grpc"
 	"google.golang.org/grpc/keepalive"
@@ -19,6 +20,7 @@ import (
 	mgmtProto "github.com/netbirdio/netbird/management/proto"
 	"github.com/netbirdio/netbird/management/server"
 	"github.com/netbirdio/netbird/management/server/activity"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 	"github.com/netbirdio/netbird/signal/proto"
 	signalServer "github.com/netbirdio/netbird/signal/server"
 )
@@ -72,7 +74,7 @@ func TestConnectWithRetryRuns(t *testing.T) {
 	t.Setenv(maxRetryTimeVar, "5s")
 	t.Setenv(retryMultiplierVar, "1")
 
-	s.connectWithRetryRuns(ctx, config, s.statusRecorder, s.mgmProbe, s.signalProbe, s.relayProbe, s.wgProbe)
+	s.connectWithRetryRuns(ctx, config, s.statusRecorder, nil)
 	if counter < 3 {
 		t.Fatalf("expected counter > 2, got %d", counter)
 	}
@@ -120,15 +122,17 @@ func startManagement(t *testing.T, signalAddr string, counter *int) (*grpc.Serve
 		return nil, "", err
 	}
 	ia, _ := integrations.NewIntegratedValidator(context.Background(), eventStore)
-	accountManager, err := server.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, ia)
+
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	require.NoError(t, err)
+
+	accountManager, err := server.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, ia, metrics)
 	if err != nil {
 		return nil, "", err
 	}
-	rc := &server.RelayConfig{
-		Address: "localhost:0",
-	}
-	turnManager := server.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, rc)
-	mgmtServer, err := server.NewServer(context.Background(), config, accountManager, peersUpdateManager, turnManager, nil, nil)
+
+	secretsManager := server.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, config.Relay)
+	mgmtServer, err := server.NewServer(context.Background(), config, accountManager, peersUpdateManager, secretsManager, nil, nil)
 	if err != nil {
 		return nil, "", err
 	}

client/ssh/server.go

@@ -118,9 +118,9 @@ func (srv *DefaultServer) publicKeyHandler(ctx ssh.Context, key ssh.PublicKey) b
 
 func prepareUserEnv(user *user.User, shell string) []string {
 	return []string{
-		fmt.Sprintf("SHELL=" + shell),
-		fmt.Sprintf("USER=" + user.Username),
-		fmt.Sprintf("HOME=" + user.HomeDir),
+		fmt.Sprint("SHELL=" + shell),
+		fmt.Sprint("USER=" + user.Username),
+		fmt.Sprint("HOME=" + user.HomeDir),
 	}
 }
 

client/testdata/management.json

@@ -20,6 +20,13 @@
     "Secret": "c29tZV9wYXNzd29yZA==",
     "TimeBasedCredentials": true
   },
+  "Relay": {
+    "Addresses": [
+      "localhost:0"
+    ],
+    "CredentialsTTL": "1h",
+    "Secret": "b29tZV9wYXNzd29yZA=="
+  },
   "Signal": {
     "Proto": "http",
     "URI": "signal.wiretrustee.com:10000",
@@ -34,4 +41,4 @@
     "AuthAudience": "<PASTE YOUR AUTH0 AUDIENCE HERE>",
     "AuthKeysLocation": "<PASTE YOUR AUTH0 PUBLIC JWT KEYS LOCATION HERE>"
   }
-}
+}

client/ui/client_ui.go

@@ -22,8 +22,8 @@ import (
 	"fyne.io/fyne/v2/app"
 	"fyne.io/fyne/v2/dialog"
 	"fyne.io/fyne/v2/widget"
+	"fyne.io/systray"
 	"github.com/cenkalti/backoff/v4"
-	"github.com/getlantern/systray"
 	log "github.com/sirupsen/logrus"
 	"github.com/skratchdot/open-golang/open"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"

encryption/route53.go

@@ -3,7 +3,9 @@ package encryption
 import (
 	"context"
 	"crypto/tls"
+	"fmt"
 	"os"
+	"strings"
 
 	"github.com/caddyserver/certmagic"
 	"github.com/libdns/route53"
@@ -23,12 +25,21 @@ type Route53TLS struct {
 }
 
 func (r *Route53TLS) GetCertificate() (*tls.Config, error) {
+	if len(r.Domains) == 0 {
+		return nil, fmt.Errorf("no domains provided")
+	}
+
 	certmagic.Default.Logger = logger()
 	certmagic.Default.Storage = &certmagic.FileStorage{Path: r.DataDir}
 	certmagic.DefaultACME.Agreed = true
-	certmagic.DefaultACME.Email = r.Email
+	if r.Email != "" {
+		certmagic.DefaultACME.Email = r.Email
+	} else {
+		certmagic.DefaultACME.Email = emailFromDomain(r.Domains[0])
+	}
+
 	if r.CA == "" {
-		certmagic.DefaultACME.CA = certmagic.LetsEncryptStagingCA
+		certmagic.DefaultACME.CA = certmagic.LetsEncryptProductionCA
 	} else {
 		certmagic.DefaultACME.CA = r.CA
 	}
@@ -52,6 +63,21 @@ func (r *Route53TLS) GetCertificate() (*tls.Config, error) {
 	return tlsConfig, nil
 }
 
+func emailFromDomain(domain string) string {
+	if domain == "" {
+		return ""
+	}
+
+	parts := strings.Split(domain, ".")
+	if len(parts) < 2 {
+		return ""
+	}
+	if parts[0] == "" {
+		return ""
+	}
+	return fmt.Sprintf("admin@%s.%s", parts[len(parts)-2], parts[len(parts)-1])
+}
+
 func logger() *zap.Logger {
 	return zap.New(zapcore.NewCore(
 		zapcore.NewConsoleEncoder(zap.NewProductionEncoderConfig()),

encryption/route53_test.go

@@ -60,3 +60,25 @@ func TestRoute53TLSConfig(t *testing.T) {
 		t.Errorf("Unexpected response: %s", body)
 	}
 }
+
+func Test_emailFromDomain(t *testing.T) {
+	tests := []struct {
+		input string
+		want  string
+	}{
+		{"example.com", "admin@example.com"},
+		{"x.example.com", "admin@example.com"},
+		{"x.x.example.com", "admin@example.com"},
+		{"*.example.com", "admin@example.com"},
+		{"example", ""},
+		{"", ""},
+		{".com", ""},
+	}
+	for _, tt := range tests {
+		t.Run("domain test", func(t *testing.T) {
+			if got := emailFromDomain(tt.input); got != tt.want {
+				t.Errorf("emailFromDomain() = %v, want %v", got, tt.want)
+			}
+		})
+	}
+}

go.mod

@@ -10,7 +10,7 @@ require (
 	github.com/golang/protobuf v1.5.4
 	github.com/google/uuid v1.6.0
 	github.com/gorilla/mux v1.8.0
-	github.com/kardianos/service v1.2.1-0.20210728001519-a323c3813bc7
+	github.com/kardianos/service v1.2.3-0.20240613133416-becf2eb62b83
 	github.com/onsi/ginkgo v1.16.5
 	github.com/onsi/gomega v1.27.6
 	github.com/pion/ice/v3 v3.0.2
@@ -30,7 +30,8 @@ require (
 )
 
 require (
-	fyne.io/fyne/v2 v2.1.4
+	fyne.io/fyne/v2 v2.5.0
+	fyne.io/systray v1.11.0
 	github.com/TheJumpCloud/jcapi-go v3.0.0+incompatible
 	github.com/c-robinson/iplib v1.0.3
 	github.com/caddyserver/certmagic v0.21.3
@@ -39,7 +40,6 @@ require (
 	github.com/creack/pty v1.1.18
 	github.com/eko/gocache/v3 v3.1.1
 	github.com/fsnotify/fsnotify v1.7.0
-	github.com/getlantern/systray v1.2.1
 	github.com/gliderlabs/ssh v0.3.4
 	github.com/godbus/dbus/v5 v5.1.0
 	github.com/golang/mock v1.6.0
@@ -60,6 +60,7 @@ require (
 	github.com/mitchellh/hashstructure/v2 v2.0.2
 	github.com/nadoo/ipset v0.5.0
 	github.com/netbirdio/management-integrations/integrations v0.0.0-20240703085513-32605f7ffd8e
+	github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20240820130728-bc0683599080
 	github.com/okta/okta-sdk-golang/v2 v2.18.0
 	github.com/oschwald/maxminddb-golang v1.12.0
 	github.com/patrickmn/go-cache v2.1.0+incompatible
@@ -87,7 +88,7 @@ require (
 	go.uber.org/zap v1.27.0
 	goauthentik.io/api/v3 v3.2023051.3
 	golang.org/x/exp v0.0.0-20240506185415-9bf2ced13842
-	golang.org/x/mobile v0.0.0-20190719004257-d2bd2a29d028
+	golang.org/x/mobile v0.0.0-20231127183840-76ac6878050a
 	golang.org/x/net v0.26.0
 	golang.org/x/oauth2 v0.19.0
 	golang.org/x/sync v0.7.0
@@ -106,7 +107,7 @@ require (
 	cloud.google.com/go/compute/metadata v0.3.0 // indirect
 	dario.cat/mergo v1.0.0 // indirect
 	github.com/Azure/go-ansiterm v0.0.0-20230124172434-306776ec8161 // indirect
-	github.com/BurntSushi/toml v1.3.2 // indirect
+	github.com/BurntSushi/toml v1.4.0 // indirect
 	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/Microsoft/hcsshim v0.12.3 // indirect
 	github.com/XiaoMi/pegasus-go-client v0.0.0-20210427083443-f3b6b08bc4c2 // indirect
@@ -136,31 +137,29 @@ require (
 	github.com/dgraph-io/ristretto v0.1.1 // indirect
 	github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f // indirect
 	github.com/distribution/reference v0.6.0 // indirect
-	github.com/docker/docker v26.1.4+incompatible // indirect
+	github.com/docker/docker v26.1.5+incompatible // indirect
 	github.com/docker/go-connections v0.5.0 // indirect
 	github.com/docker/go-units v0.5.0 // indirect
 	github.com/felixge/httpsnoop v1.0.4 // indirect
-	github.com/fredbi/uri v0.0.0-20181227131451-3dcfdacbaaf3 // indirect
-	github.com/getlantern/context v0.0.0-20190109183933-c447772a6520 // indirect
-	github.com/getlantern/errors v0.0.0-20190325191628-abdb3e3e36f7 // indirect
-	github.com/getlantern/golog v0.0.0-20190830074920-4ef2e798c2d7 // indirect
-	github.com/getlantern/hex v0.0.0-20190417191902-c6586a6fe0b7 // indirect
-	github.com/getlantern/hidden v0.0.0-20190325191715-f02dbb02be55 // indirect
-	github.com/getlantern/ops v0.0.0-20190325191751-d70cb0d6f85f // indirect
-	github.com/go-gl/gl v0.0.0-20210813123233-e4099ee2221f // indirect
-	github.com/go-gl/glfw/v3.3/glfw v0.0.0-20211024062804-40e447a793be // indirect
+	github.com/fredbi/uri v1.1.0 // indirect
+	github.com/fyne-io/gl-js v0.0.0-20220119005834-d2da28d9ccfe // indirect
+	github.com/fyne-io/glfw-js v0.0.0-20240101223322-6e1efdc71b7a // indirect
+	github.com/fyne-io/image v0.0.0-20220602074514-4956b0afb3d2 // indirect
+	github.com/go-gl/gl v0.0.0-20211210172815-726fda9656d6 // indirect
+	github.com/go-gl/glfw/v3.3/glfw v0.0.0-20240506104042-037f3cc74f2a // indirect
 	github.com/go-logr/logr v1.4.1 // indirect
 	github.com/go-logr/stdr v1.2.2 // indirect
 	github.com/go-ole/go-ole v1.3.0 // indirect
 	github.com/go-redis/redis/v8 v8.11.5 // indirect
-	github.com/go-stack/stack v1.8.0 // indirect
+	github.com/go-text/render v0.1.0 // indirect
+	github.com/go-text/typesetting v0.1.0 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
-	github.com/goki/freetype v0.0.0-20181231101311-fa8a33aabaff // indirect
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/google/btree v1.0.1 // indirect
 	github.com/google/s2a-go v0.1.7 // indirect
 	github.com/googleapis/enterprise-certificate-proxy v0.3.2 // indirect
 	github.com/googleapis/gax-go/v2 v2.12.3 // indirect
+	github.com/gopherjs/gopherjs v1.17.2 // indirect
 	github.com/hashicorp/errwrap v1.1.0 // indirect
 	github.com/hashicorp/go-uuid v1.0.3 // indirect
 	github.com/inconshreveable/mousetrap v1.1.0 // indirect
@@ -168,10 +167,12 @@ require (
 	github.com/jackc/pgservicefile v0.0.0-20221227161230-091c0ba34f0a // indirect
 	github.com/jackc/pgx/v5 v5.5.5 // indirect
 	github.com/jackc/puddle/v2 v2.2.1 // indirect
+	github.com/jeandeaual/go-locale v0.0.0-20240223122105-ce5225dcaa49 // indirect
 	github.com/jinzhu/inflection v1.0.0 // indirect
 	github.com/jinzhu/now v1.1.5 // indirect
 	github.com/jmespath/go-jmespath v0.4.0 // indirect
 	github.com/josharian/native v1.1.0 // indirect
+	github.com/jsummers/gobmp v0.0.0-20151104160322-e2ba15ffa76e // indirect
 	github.com/kelseyhightower/envconfig v1.4.0 // indirect
 	github.com/klauspost/compress v1.17.8 // indirect
 	github.com/klauspost/cpuid/v2 v2.2.7 // indirect
@@ -186,11 +187,11 @@ require (
 	github.com/moby/sys/user v0.1.0 // indirect
 	github.com/moby/term v0.5.0 // indirect
 	github.com/morikuni/aec v1.0.0 // indirect
+	github.com/nicksnyder/go-i18n/v2 v2.4.0 // indirect
 	github.com/nxadm/tail v1.4.8 // indirect
 	github.com/onsi/ginkgo/v2 v2.9.5 // indirect
 	github.com/opencontainers/go-digest v1.0.0 // indirect
 	github.com/opencontainers/image-spec v1.1.0 // indirect
-	github.com/oxtoacart/bpool v0.0.0-20190530202638-03653db5a59c // indirect
 	github.com/pegasus-kv/thrift v0.13.0 // indirect
 	github.com/pion/dtls/v2 v2.2.10 // indirect
 	github.com/pion/mdns v0.0.12 // indirect
@@ -201,14 +202,15 @@ require (
 	github.com/prometheus/client_model v0.6.1 // indirect
 	github.com/prometheus/common v0.53.0 // indirect
 	github.com/prometheus/procfs v0.15.0 // indirect
+	github.com/rymdport/portal v0.2.2 // indirect
 	github.com/shoenig/go-m1cpu v0.1.6 // indirect
 	github.com/spf13/cast v1.5.0 // indirect
-	github.com/srwiley/oksvg v0.0.0-20200311192757-870daf9aa564 // indirect
-	github.com/srwiley/rasterx v0.0.0-20200120212402-85cb7272f5e9 // indirect
+	github.com/srwiley/oksvg v0.0.0-20221011165216-be6e8873101c // indirect
+	github.com/srwiley/rasterx v0.0.0-20220730225603-2ab79fcdd4ef // indirect
 	github.com/tklauser/go-sysconf v0.3.14 // indirect
 	github.com/tklauser/numcpus v0.8.0 // indirect
 	github.com/vishvananda/netns v0.0.4 // indirect
-	github.com/yuin/goldmark v1.4.13 // indirect
+	github.com/yuin/goldmark v1.7.1 // indirect
 	github.com/zeebo/blake3 v0.2.3 // indirect
 	go.opencensus.io v0.24.0 // indirect
 	go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.51.0 // indirect
@@ -230,7 +232,7 @@ require (
 	k8s.io/apimachinery v0.26.2 // indirect
 )
 
-replace github.com/kardianos/service => github.com/netbirdio/service v0.0.0-20230215170314-b923b89432b0
+replace github.com/kardianos/service => github.com/netbirdio/service v0.0.0-20240904111318-17777758453a
 
 replace github.com/getlantern/systray => github.com/netbirdio/systray v0.0.0-20231030152038-ef1ed2a27949
 

iface/iface.go

@@ -124,7 +124,23 @@ func (w *WGIface) RemoveAllowedIP(peerKey string, allowedIP string) error {
 func (w *WGIface) Close() error {
 	w.mu.Lock()
 	defer w.mu.Unlock()
-	return w.tun.Close()
+
+	err := w.tun.Close()
+	if err != nil {
+		return fmt.Errorf("failed to close wireguard interface %s: %w", w.Name(), err)
+	}
+
+	err = w.waitUntilRemoved()
+	if err != nil {
+		log.Warnf("failed to remove WireGuard interface %s: %v", w.Name(), err)
+		err = w.Destroy()
+		if err != nil {
+			return fmt.Errorf("failed to remove WireGuard interface %s: %w", w.Name(), err)
+		}
+		log.Infof("interface %s successfully removed", w.Name())
+	}
+
+	return nil
 }
 
 // SetFilter sets packet filters for the userspace implementation
@@ -163,3 +179,30 @@ func (w *WGIface) GetDevice() *DeviceWrapper {
 func (w *WGIface) GetStats(peerKey string) (WGStats, error) {
 	return w.configurer.getStats(peerKey)
 }
+
+func (w *WGIface) waitUntilRemoved() error {
+	maxWaitTime := 5 * time.Second
+	timeout := time.NewTimer(maxWaitTime)
+	defer timeout.Stop()
+
+	for {
+		iface, err := net.InterfaceByName(w.Name())
+		if err != nil {
+			if _, ok := err.(*net.OpError); ok {
+				log.Infof("interface %s has been removed", w.Name())
+				return nil
+			}
+			log.Debugf("failed to get interface by name %s: %v", w.Name(), err)
+		} else if iface == nil {
+			log.Infof("interface %s has been removed", w.Name())
+			return nil
+		}
+
+		select {
+		case <-timeout.C:
+			return fmt.Errorf("timeout when waiting for interface %s to be removed", w.Name())
+		default:
+			time.Sleep(100 * time.Millisecond)
+		}
+	}
+}

iface/iface_create.go

@@ -1,4 +1,4 @@
-//go:build !android
+//go:build (!android && !darwin) || ios
 
 package iface
 

iface/iface_darwin.go

@@ -4,7 +4,9 @@ package iface
 
 import (
 	"fmt"
+	"time"
 
+	"github.com/cenkalti/backoff/v4"
 	"github.com/pion/transport/v3"
 
 	"github.com/netbirdio/netbird/iface/bind"
@@ -36,3 +38,29 @@ func NewWGIFace(iFaceName string, address string, wgPort int, wgPrivKey string,
 func (w *WGIface) CreateOnAndroid([]string, string, []string) error {
 	return fmt.Errorf("this function has not implemented on this platform")
 }
+
+// Create creates a new Wireguard interface, sets a given IP and brings it up.
+// Will reuse an existing one.
+// this function is different on Android
+func (w *WGIface) Create() error {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+
+	backOff := &backoff.ExponentialBackOff{
+		InitialInterval: 20 * time.Millisecond,
+		MaxElapsedTime:  500 * time.Millisecond,
+		Stop:            backoff.Stop,
+		Clock:           backoff.SystemClock,
+	}
+
+	operation := func() error {
+		cfgr, err := w.tun.Create()
+		if err != nil {
+			return err
+		}
+		w.configurer = cfgr
+		return nil
+	}
+
+	return backoff.Retry(operation, backOff)
+}

iface/iface_destroy_bsd.go

@@ -0,0 +1,17 @@
+//go:build darwin || dragonfly || freebsd || netbsd || openbsd
+
+package iface
+
+import (
+	"fmt"
+	"os/exec"
+)
+
+func (w *WGIface) Destroy() error {
+	out, err := exec.Command("ifconfig", w.Name(), "destroy").CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("failed to remove interface %s: %w - %s", w.Name(), err, out)
+	}
+
+	return nil
+}

iface/iface_destroy_linux.go

@@ -0,0 +1,22 @@
+//go:build linux && !android
+
+package iface
+
+import (
+	"fmt"
+
+	"github.com/vishvananda/netlink"
+)
+
+func (w *WGIface) Destroy() error {
+	link, err := netlink.LinkByName(w.Name())
+	if err != nil {
+		return fmt.Errorf("failed to get link by name %s: %w", w.Name(), err)
+	}
+
+	if err := netlink.LinkDel(link); err != nil {
+		return fmt.Errorf("failed to delete link %s: %w", w.Name(), err)
+	}
+
+	return nil
+}

iface/iface_destroy_mobile.go

@@ -0,0 +1,9 @@
+//go:build android || (ios && !darwin)
+
+package iface
+
+import "errors"
+
+func (w *WGIface) Destroy() error {
+	return errors.New("not supported on mobile")
+}

iface/iface_destroy_windows.go

@@ -0,0 +1,32 @@
+//go:build windows
+
+package iface
+
+import (
+	"fmt"
+	"os/exec"
+
+	log "github.com/sirupsen/logrus"
+)
+
+func (w *WGIface) Destroy() error {
+	netshCmd := GetSystem32Command("netsh")
+	out, err := exec.Command(netshCmd, "interface", "set", "interface", w.Name(), "admin=disable").CombinedOutput()
+	if err != nil {
+		return fmt.Errorf("failed to remove interface %s: %w - %s", w.Name(), err, out)
+	}
+	return nil
+}
+
+// GetSystem32Command checks if a command can be found in the system path and returns it. In case it can't find it
+// in the path it will return the full path of a command assuming C:\windows\system32 as the base path.
+func GetSystem32Command(command string) string {
+	_, err := exec.LookPath(command)
+	if err == nil {
+		return command
+	}
+
+	log.Tracef("Command %s not found in PATH, using C:\\windows\\system32\\%s.exe path", command, command)
+
+	return "C:\\windows\\system32\\" + command + ".exe"
+}

iface/iface_test.go

@@ -4,9 +4,11 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"strings"
 	"testing"
 	"time"
 
+	"github.com/google/uuid"
 	"github.com/pion/transport/v3/stdnet"
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
@@ -174,6 +176,72 @@ func Test_Close(t *testing.T) {
 	}
 }
 
+func TestRecreation(t *testing.T) {
+	for i := 0; i < 100; i++ {
+		t.Run(fmt.Sprintf("down-%d", i), func(t *testing.T) {
+			ifaceName := fmt.Sprintf("utun%d", WgIntNumber+2)
+			wgIP := "10.99.99.2/32"
+			wgPort := 33100
+			newNet, err := stdnet.NewNet()
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			iface, err := NewWGIFace(ifaceName, wgIP, wgPort, key, DefaultMTU, newNet, nil, nil)
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			for {
+				_, err = net.InterfaceByName(ifaceName)
+				if err != nil {
+					t.Logf("interface %s not found: err: %s", ifaceName, err)
+					break
+				}
+				t.Logf("interface %s found", ifaceName)
+			}
+
+			err = iface.Create()
+			if err != nil {
+				t.Fatal(err)
+			}
+			wg, err := wgctrl.New()
+			if err != nil {
+				t.Fatal(err)
+			}
+			defer func() {
+				err = wg.Close()
+				if err != nil {
+					t.Error(err)
+				}
+			}()
+
+			_, err = iface.Up()
+			if err != nil {
+				t.Fatal(err)
+			}
+
+			for {
+				_, err = net.InterfaceByName(ifaceName)
+				if err == nil {
+					t.Logf("interface %s found", ifaceName)
+
+					break
+				}
+				t.Logf("interface %s not found: err: %s", ifaceName, err)
+
+			}
+
+			start := time.Now()
+			err = iface.Close()
+			t.Logf("down time: %s", time.Since(start))
+			if err != nil {
+				t.Fatal(err)
+			}
+		})
+	}
+}
+
 func Test_ConfigureInterface(t *testing.T) {
 	ifaceName := fmt.Sprintf("utun%d", WgIntNumber+3)
 	wgIP := "10.99.99.5/30"
@@ -345,6 +413,9 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
+	guid := fmt.Sprintf("{%s}", uuid.New().String())
+	CustomWindowsGUIDString = strings.ToLower(guid)
+
 	iface1, err := NewWGIFace(peer1ifaceName, peer1wgIP, peer1wgPort, peer1Key.String(), DefaultMTU, newNet, nil, nil)
 	if err != nil {
 		t.Fatal(err)
@@ -364,6 +435,9 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
+	guid = fmt.Sprintf("{%s}", uuid.New().String())
+	CustomWindowsGUIDString = strings.ToLower(guid)
+
 	newNet, err = stdnet.NewNet()
 	if err != nil {
 		t.Fatal(err)

iface/tun.go

@@ -7,6 +7,9 @@ import (
 	"github.com/netbirdio/netbird/iface/bind"
 )
 
+// CustomWindowsGUIDString is a custom GUID string for the interface
+var CustomWindowsGUIDString string
+
 type wgTunDevice interface {
 	Create() (wgConfigurer, error)
 	Up() (*bind.UniversalUDPMuxDefault, error)

iface/tun_darwin.go

@@ -3,6 +3,7 @@
 package iface
 
 import (
+	"fmt"
 	"os/exec"
 
 	"github.com/pion/transport/v3"
@@ -41,7 +42,7 @@ func newTunDevice(name string, address WGAddress, port int, key string, mtu int,
 func (t *tunDevice) Create() (wgConfigurer, error) {
 	tunDevice, err := tun.CreateTUN(t.name, t.mtu)
 	if err != nil {
-		return nil, err
+		return nil, fmt.Errorf("error creating tun device: %s", err)
 	}
 	t.wrapper = newDeviceWrapper(tunDevice)
 
@@ -55,7 +56,7 @@ func (t *tunDevice) Create() (wgConfigurer, error) {
 	err = t.assignAddr()
 	if err != nil {
 		t.device.Close()
-		return nil, err
+		return nil, fmt.Errorf("error assigning ip: %s", err)
 	}
 
 	t.configurer = newWGUSPConfigurer(t.device, t.name)
@@ -63,7 +64,7 @@ func (t *tunDevice) Create() (wgConfigurer, error) {
 	if err != nil {
 		t.device.Close()
 		t.configurer.close()
-		return nil, err
+		return nil, fmt.Errorf("error configuring interface: %s", err)
 	}
 	return t.configurer, nil
 }

iface/tun_kernel_unix.go

@@ -70,7 +70,7 @@ func (t *tunKernelDevice) Create() (wgConfigurer, error) {
 	configurer := newWGConfigurer(t.name)
 
 	if err := configurer.configureInterface(t.key, t.wgPort); err != nil {
-		return nil, err
+		return nil, fmt.Errorf("error configuring interface: %s", err)
 	}
 
 	return configurer, nil

iface/tun_netstack.go

@@ -47,7 +47,7 @@ func (t *tunNetstackDevice) Create() (wgConfigurer, error) {
 	t.nsTun = netstack.NewNetStackTun(t.listenAddress, t.address.IP.String(), t.mtu)
 	tunIface, err := t.nsTun.Create()
 	if err != nil {
-		return nil, err
+		return nil, fmt.Errorf("error creating tun device: %s", err)
 	}
 	t.wrapper = newDeviceWrapper(tunIface)
 
@@ -61,7 +61,7 @@ func (t *tunNetstackDevice) Create() (wgConfigurer, error) {
 	err = t.configurer.configureInterface(t.key, t.port)
 	if err != nil {
 		_ = tunIface.Close()
-		return nil, err
+		return nil, fmt.Errorf("error configuring interface: %s", err)
 	}
 
 	log.Debugf("device has been created: %s", t.name)

iface/tun_usp_unix.go

@@ -48,8 +48,8 @@ func (t *tunUSPDevice) Create() (wgConfigurer, error) {
 	log.Info("create tun interface")
 	tunIface, err := tun.CreateTUN(t.name, t.mtu)
 	if err != nil {
-		log.Debugf("failed to create tun unterface (%s, %d): %s", t.name, t.mtu, err)
-		return nil, err
+		log.Debugf("failed to create tun interface (%s, %d): %s", t.name, t.mtu, err)
+		return nil, fmt.Errorf("error creating tun device: %s", err)
 	}
 	t.wrapper = newDeviceWrapper(tunIface)
 
@@ -63,7 +63,7 @@ func (t *tunUSPDevice) Create() (wgConfigurer, error) {
 	err = t.assignAddr()
 	if err != nil {
 		t.device.Close()
-		return nil, err
+		return nil, fmt.Errorf("error assigning ip: %s", err)
 	}
 
 	t.configurer = newWGUSPConfigurer(t.device, t.name)
@@ -71,7 +71,7 @@ func (t *tunUSPDevice) Create() (wgConfigurer, error) {
 	if err != nil {
 		t.device.Close()
 		t.configurer.close()
-		return nil, err
+		return nil, fmt.Errorf("error configuring interface: %s", err)
 	}
 	return t.configurer, nil
 }

iface/tun_windows.go

@@ -14,6 +14,8 @@ import (
 	"github.com/netbirdio/netbird/iface/bind"
 )
 
+const defaultWindowsGUIDSTring = "{f2f29e61-d91f-4d76-8151-119b20c4bdeb}"
+
 type tunDevice struct {
 	name    string
 	address WGAddress
@@ -40,12 +42,25 @@ func newTunDevice(name string, address WGAddress, port int, key string, mtu int,
 	}
 }
 
+func getGUID() (windows.GUID, error) {
+	guidString := defaultWindowsGUIDSTring
+	if CustomWindowsGUIDString != "" {
+		guidString = CustomWindowsGUIDString
+	}
+	return windows.GUIDFromString(guidString)
+}
+
 func (t *tunDevice) Create() (wgConfigurer, error) {
-	log.Info("create tun interface")
-	tunDevice, err := tun.CreateTUN(t.name, t.mtu)
+	guid, err := getGUID()
 	if err != nil {
+		log.Errorf("failed to get GUID: %s", err)
 		return nil, err
 	}
+	log.Info("create tun interface")
+	tunDevice, err := tun.CreateTUNWithRequestedGUID(t.name, &guid, t.mtu)
+	if err != nil {
+		return nil, fmt.Errorf("error creating tun device: %s", err)
+	}
 	t.nativeTunDevice = tunDevice.(*tun.NativeTun)
 	t.wrapper = newDeviceWrapper(tunDevice)
 
@@ -74,7 +89,7 @@ func (t *tunDevice) Create() (wgConfigurer, error) {
 	err = t.assignAddr()
 	if err != nil {
 		t.device.Close()
-		return nil, err
+		return nil, fmt.Errorf("error assigning ip: %s", err)
 	}
 
 	t.configurer = newWGUSPConfigurer(t.device, t.name)
@@ -82,7 +97,7 @@ func (t *tunDevice) Create() (wgConfigurer, error) {
 	if err != nil {
 		t.device.Close()
 		t.configurer.close()
-		return nil, err
+		return nil, fmt.Errorf("error configuring interface: %s", err)
 	}
 	return t.configurer, nil
 }

infrastructure_files/base.setup.env

@@ -20,6 +20,12 @@ NETBIRD_MGMT_IDP_SIGNKEY_REFRESH=${NETBIRD_MGMT_IDP_SIGNKEY_REFRESH:-false}
 NETBIRD_SIGNAL_PROTOCOL="http"
 NETBIRD_SIGNAL_PORT=${NETBIRD_SIGNAL_PORT:-10000}
 
+# Relay
+NETBIRD_RELAY_DOMAIN=${NETBIRD_RELAY_DOMAIN:-$NETBIRD_DOMAIN}
+NETBIRD_RELAY_PORT=${NETBIRD_RELAY_PORT:-33080}
+# Relay auth secret
+NETBIRD_RELAY_AUTH_SECRET=
+
 # Turn
 TURN_DOMAIN=${NETBIRD_TURN_DOMAIN:-$NETBIRD_DOMAIN}
 
@@ -69,7 +75,7 @@ NETBIRD_DASHBOARD_TAG=${NETBIRD_DASHBOARD_TAG:-"latest"}
 NETBIRD_SIGNAL_TAG=${NETBIRD_SIGNAL_TAG:-"latest"}
 NETBIRD_MANAGEMENT_TAG=${NETBIRD_MANAGEMENT_TAG:-"latest"}
 COTURN_TAG=${COTURN_TAG:-"latest"}
-
+NETBIRD_RELAY_TAG=${NETBIRD_RELAY_TAG:-"latest"}
 
 # exports
 export NETBIRD_DOMAIN
@@ -123,3 +129,7 @@ export NETBIRD_SIGNAL_TAG
 export NETBIRD_MANAGEMENT_TAG
 export COTURN_TAG
 export NETBIRD_TURN_EXTERNAL_IP
+export NETBIRD_RELAY_DOMAIN
+export NETBIRD_RELAY_PORT
+export NETBIRD_RELAY_AUTH_SECRET
+export NETBIRD_RELAY_TAG

infrastructure_files/configure.sh

@@ -41,6 +41,18 @@ if [[ "x-$NETBIRD_DOMAIN" == "x-" ]]; then
   exit 1
 fi
 
+# Check if PostgreSQL is set as the store engine
+if [[ "$NETBIRD_STORE_CONFIG_ENGINE" == "postgres" ]]; then
+  # Exit if 'NETBIRD_STORE_ENGINE_POSTGRES_DSN' is not set
+  if [[ -z "$NETBIRD_STORE_ENGINE_POSTGRES_DSN" ]]; then
+    echo "Warning: NETBIRD_STORE_CONFIG_ENGINE=postgres but NETBIRD_STORE_ENGINE_POSTGRES_DSN is not set."
+    echo "Please add the following line to your setup.env file:"
+    echo 'NETBIRD_STORE_ENGINE_POSTGRES_DSN="host=<PG_HOST> user=<PG_USER> password=<PG_PASSWORD> dbname=<PG_DB_NAME> port=<PG_PORT>"'
+    exit 1
+  fi
+  export NETBIRD_STORE_ENGINE_POSTGRES_DSN
+fi
+
 # local development or tests
 if [[ $NETBIRD_DOMAIN == "localhost" || $NETBIRD_DOMAIN == "127.0.0.1" ]]; then
   export NETBIRD_MGMT_SINGLE_ACCOUNT_MODE_DOMAIN="netbird.selfhosted"
@@ -77,6 +89,11 @@ fi
 
 export TURN_EXTERNAL_IP_CONFIG
 
+# if not provided, we generate a relay auth secret
+if [[ "x-$NETBIRD_RELAY_AUTH_SECRET" == "x-" ]]; then
+  export NETBIRD_RELAY_AUTH_SECRET=$(openssl rand -base64 32 | sed 's/=//g')
+fi
+
 artifacts_path="./artifacts"
 mkdir -p $artifacts_path
 

infrastructure_files/docker-compose.yml.tmpl

@@ -49,6 +49,23 @@ services:
       options:
         max-size: "500m"
         max-file: "2"
+  # Relay
+  relay:
+    image: netbirdio/relay:$NETBIRD_RELAY_TAG
+    restart: unless-stopped
+    environment:
+    - NB_LOG_LEVEL=info
+    - NB_LISTEN_ADDRESS=:$NETBIRD_RELAY_PORT
+    - NB_EXPOSED_ADDRESS=$NETBIRD_RELAY_DOMAIN:$NETBIRD_RELAY_PORT
+    # todo: change to a secure secret
+    - NB_AUTH_SECRET=$NETBIRD_RELAY_AUTH_SECRET
+    ports:
+      - $NETBIRD_RELAY_PORT:$NETBIRD_RELAY_PORT
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
 
   # Management
   management:
@@ -77,6 +94,9 @@ services:
       options:
         max-size: "500m"
         max-file: "2"
+    environment:
+      - NETBIRD_STORE_ENGINE_POSTGRES_DSN=$NETBIRD_STORE_ENGINE_POSTGRES_DSN
+      
   # Coturn
   coturn:
     image: coturn/coturn:$COTURN_TAG

infrastructure_files/docker-compose.yml.tmpl.traefik

@@ -81,7 +81,9 @@ services:
     - traefik.http.routers.netbird-management.service=netbird-management
     - traefik.http.services.netbird-management.loadbalancer.server.port=443
     - traefik.http.services.netbird-management.loadbalancer.server.scheme=h2c
-
+    environment:
+      - NETBIRD_STORE_ENGINE_POSTGRES_DSN=$NETBIRD_STORE_ENGINE_POSTGRES_DSN
+      
   # Coturn
   coturn:
     image: coturn/coturn:$COTURN_TAG

infrastructure_files/download-geolite2.sh

@@ -1,109 +0,0 @@
-#!/bin/bash
-
-# to install sha256sum on mac: brew install coreutils
-if ! command -v sha256sum &> /dev/null
-then
-    echo "sha256sum is not installed or not in PATH, please install with your package manager. e.g. sudo apt install sha256sum" > /dev/stderr
-    exit 1
-fi
-
-if ! command -v sqlite3 &> /dev/null
-then
-    echo "sqlite3 is not installed or not in PATH, please install with your package manager. e.g. sudo apt install sqlite3" > /dev/stderr
-    exit 1
-fi
-
-if ! command -v unzip &> /dev/null
-then
-    echo "unzip is not installed or not in PATH, please install with your package manager. e.g. sudo apt install unzip" > /dev/stderr
-    exit 1
-fi
-
-download_geolite_mmdb() {
-  DATABASE_URL="https://pkgs.netbird.io/geolocation-dbs/GeoLite2-City/download?suffix=tar.gz"
-  SIGNATURE_URL="https://pkgs.netbird.io/geolocation-dbs/GeoLite2-City/download?suffix=tar.gz.sha256"
-  # Download the database and signature files
-  echo "Downloading mmdb signature file..."
-  SIGNATURE_FILE=$(curl -s  -L -O -J "$SIGNATURE_URL" -w "%{filename_effective}")
-  echo "Downloading mmdb database file..."
-  DATABASE_FILE=$(curl -s  -L -O -J "$DATABASE_URL" -w "%{filename_effective}")
-
-  # Verify the signature
-  echo "Verifying signature..."
-  if sha256sum -c --status "$SIGNATURE_FILE"; then
-      echo "Signature is valid."
-  else
-      echo "Signature is invalid. Aborting."
-      exit 1
-  fi
-
-  # Unpack the database file
-  EXTRACTION_DIR=$(basename "$DATABASE_FILE" .tar.gz)
-  echo "Unpacking $DATABASE_FILE..."
-  mkdir -p "$EXTRACTION_DIR"
-  tar -xzvf "$DATABASE_FILE" > /dev/null 2>&1
-
-  MMDB_FILE="GeoLite2-City.mmdb"
-  cp "$EXTRACTION_DIR"/"$MMDB_FILE" $MMDB_FILE
-
-  # Remove downloaded files
-  rm -r "$EXTRACTION_DIR"
-  rm "$DATABASE_FILE" "$SIGNATURE_FILE"
-
-  # Done. Print next steps
-  echo ""
-  echo "Process completed successfully."
-  echo "Now you can place $MMDB_FILE to 'datadir' of management service."
-  echo -e "Example:\n\tdocker compose cp $MMDB_FILE management:/var/lib/netbird/"
-}
-
-
-download_geolite_csv_and_create_sqlite_db() {
-  DATABASE_URL="https://pkgs.netbird.io/geolocation-dbs/GeoLite2-City-CSV/download?suffix=zip"
-  SIGNATURE_URL="https://pkgs.netbird.io/geolocation-dbs/GeoLite2-City-CSV/download?suffix=zip.sha256"
-
-
-  # Download the database file
-  echo "Downloading csv signature file..."
-  SIGNATURE_FILE=$(curl -s  -L -O -J "$SIGNATURE_URL" -w "%{filename_effective}")
-  echo "Downloading csv database file..."
-  DATABASE_FILE=$(curl -s  -L -O -J "$DATABASE_URL" -w "%{filename_effective}")
-
-  # Verify the signature
-  echo "Verifying signature..."
-  if sha256sum -c --status "$SIGNATURE_FILE"; then
-      echo "Signature is valid."
-  else
-      echo "Signature is invalid. Aborting."
-      exit 1
-  fi
-
-  # Unpack the database file
-  EXTRACTION_DIR=$(basename "$DATABASE_FILE" .zip)
-  DB_NAME="geonames.db"
-
-  echo "Unpacking $DATABASE_FILE..."
-  unzip "$DATABASE_FILE" > /dev/null 2>&1
-
-# Create SQLite database and import data from CSV
-sqlite3 "$DB_NAME" <<EOF
-.mode csv
-.import "$EXTRACTION_DIR/GeoLite2-City-Locations-en.csv" geonames
-EOF
-
-
-  # Remove downloaded and extracted files
-  rm -r -r "$EXTRACTION_DIR"
-  rm  "$DATABASE_FILE" "$SIGNATURE_FILE"
-  echo ""
-  echo "SQLite database '$DB_NAME' created successfully."
-  echo "Now you can place $DB_NAME to 'datadir' of management service."
-  echo -e "Example:\n\tdocker compose cp $DB_NAME management:/var/lib/netbird/"
-}
-
-download_geolite_mmdb
-echo -e "\n\n"
-download_geolite_csv_and_create_sqlite_db
-echo -e "\n\n"
-echo "After copying the database files to the management service. You can restart the management service with:"
-echo -e "Example:\n\tdocker compose restart management"

infrastructure_files/getting-started-with-zitadel.sh

@@ -103,13 +103,25 @@ wait_api() {
     INSTANCE_URL=$1
     PAT=$2
     set +e
+    counter=1
     while true; do
-      curl -s --fail -o /dev/null "$INSTANCE_URL/auth/v1/users/me" -H "Authorization: Bearer $PAT"
+      FLAGS="-s"
+      if [[ $counter -eq 45 ]]; then
+        FLAGS="-v"
+        echo ""
+      fi
+
+      curl $FLAGS --fail --connect-timeout 1 -o /dev/null "$INSTANCE_URL/auth/v1/users/me" -H "Authorization: Bearer $PAT"
       if [[ $? -eq 0 ]]; then
         break
       fi
+      if [[ $counter -eq 45 ]]; then
+        echo ""
+        echo "Unable to connect to Zitadel for more than 45s, please check the output above, your firewall rules and the caddy container logs to confirm if there are any issues provisioning TLS certificates"
+      fi
       echo -n " ."
       sleep 1
+      counter=$((counter + 1))
     done
     echo " done"
     set -e
@@ -424,8 +436,10 @@ initEnvironment() {
   ZITADEL_MASTERKEY="$(openssl rand -base64 32 | head -c 32)"
   NETBIRD_PORT=80
   NETBIRD_HTTP_PROTOCOL="http"
+  NETBIRD_RELAY_PROTO="rel"
   TURN_USER="self"
   TURN_PASSWORD=$(openssl rand -base64 32 | sed 's/=//g')
+  NETBIRD_RELAY_AUTH_SECRET=$(openssl rand -base64 32 | sed 's/=//g')
   TURN_MIN_PORT=49152
   TURN_MAX_PORT=65535
   TURN_EXTERNAL_IP_CONFIG=$(get_turn_external_ip)
@@ -442,6 +456,7 @@ initEnvironment() {
     NETBIRD_PORT=443
     CADDY_SECURE_DOMAIN=", $NETBIRD_DOMAIN:$NETBIRD_PORT"
     NETBIRD_HTTP_PROTOCOL="https"
+    NETBIRD_RELAY_PROTO="rels"
   fi
 
   if [[ "$OSTYPE" == "darwin"* ]]; then
@@ -458,7 +473,7 @@ initEnvironment() {
     echo "Generated files already exist, if you want to reinitialize the environment, please remove them first."
     echo "You can use the following commands:"
     echo "  $DOCKER_COMPOSE_COMMAND down --volumes # to remove all containers and volumes"
-    echo "  rm -f docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json"
+    echo "  rm -f docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json relay.env"
     echo "Be aware that this will remove all data from the database, and you will have to reconfigure the dashboard."
     exit 1
   fi
@@ -484,6 +499,7 @@ initEnvironment() {
   echo "" > dashboard.env
   echo "" > turnserver.conf
   echo "" > management.json
+  echo "" > relay.env
 
   mkdir -p machinekey
   chmod 777 machinekey
@@ -498,6 +514,7 @@ initEnvironment() {
   renderTurnServerConf > turnserver.conf
   renderManagementJson > management.json
   renderDashboardEnv > dashboard.env
+  renderRelayEnv > relay.env
 
   echo -e "\nStarting NetBird services\n"
   $DOCKER_COMPOSE_COMMAND up -d
@@ -541,7 +558,7 @@ renderCaddyfile() {
 
         # clickjacking protection
         # https://cheatsheetseries.owasp.org/cheatsheets/HTTP_Headers_Cheat_Sheet.html#x-frame-options
-        X-Frame-Options "DENY"
+        X-Frame-Options "SAMEORIGIN"
 
         # xss protection
         # https://cheatsheetseries.owasp.org/cheatsheets/HTTP_Headers_Cheat_Sheet.html#x-xss-protection
@@ -559,6 +576,8 @@ renderCaddyfile() {
 
 :80${CADDY_SECURE_DOMAIN} {
     import security_headers
+    # relay
+    reverse_proxy /relay* relay:80
     # Signal
     reverse_proxy /signalexchange.SignalExchange/* h2c://signal:10000
     # Management
@@ -629,6 +648,11 @@ renderManagementJson() {
         ],
         "TimeBasedCredentials": false
     },
+    "Relay": {
+        "Addresses": ["$NETBIRD_RELAY_PROTO://$NETBIRD_DOMAIN:$NETBIRD_PORT"],
+        "CredentialsTTL": "24h",
+        "Secret": "$NETBIRD_RELAY_AUTH_SECRET"
+    },
     "Signal": {
         "Proto": "$NETBIRD_HTTP_PROTOCOL",
         "URI": "$NETBIRD_DOMAIN:$NETBIRD_PORT"
@@ -744,6 +768,15 @@ POSTGRES_PASSWORD=$POSTGRES_ROOT_PASSWORD
 EOF
 }
 
+renderRelayEnv() {
+  cat <<EOF
+NB_LOG_LEVEL=info
+NB_LISTEN_ADDRESS=:80
+NB_EXPOSED_ADDRESS=$NETBIRD_RELAY_PROTO://$NETBIRD_DOMAIN:$NETBIRD_PORT
+NB_AUTH_SECRET=$NETBIRD_RELAY_AUTH_SECRET
+EOF
+}
+
 renderDockerCompose() {
   cat <<EOF
 version: "3.4"
@@ -782,6 +815,18 @@ services:
       options:
         max-size: "500m"
         max-file: "2"
+  # Relay
+  relay:
+    image: netbirdio/relay:latest
+    restart: unless-stopped
+    networks: [netbird]
+    env_file:
+      - ./relay.env
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
   # Management
   management:
     image: netbirdio/management:latest

infrastructure_files/management.json.tmpl

@@ -20,6 +20,11 @@
         "Secret": "secret",
         "TimeBasedCredentials": false
     },
+    "Relay": {
+        "Addresses": ["rel://$NETBIRD_RELAY_DOMAIN:$NETBIRD_RELAY_PORT"],
+        "CredentialsTTL": "24h",
+        "Secret": "$NETBIRD_RELAY_AUTH_SECRET"
+    },
     "Signal": {
         "Proto": "$NETBIRD_SIGNAL_PROTOCOL",
         "URI": "$NETBIRD_DOMAIN:$NETBIRD_SIGNAL_PORT",

infrastructure_files/setup.env.example

@@ -7,6 +7,7 @@ NETBIRD_DASHBOARD_TAG=""
 NETBIRD_SIGNAL_TAG=""
 NETBIRD_MANAGEMENT_TAG=""
 COTURN_TAG=""
+NETBIRD_RELAY_TAG=""
 
 # Dashboard domain. e.g. app.mydomain.com
 NETBIRD_DOMAIN=""
@@ -91,3 +92,14 @@ NETBIRD_LETSENCRYPT_EMAIL=""
 NETBIRD_DISABLE_ANONYMOUS_METRICS=false
 # DNS DOMAIN configures the domain name used for peer resolution. By default it is netbird.selfhosted
 NETBIRD_MGMT_DNS_DOMAIN=netbird.selfhosted
+
+# -------------------------------------------
+# Relay settings
+# -------------------------------------------
+# Relay server domain. e.g. relay.mydomain.com
+# if not specified it will assume NETBIRD_DOMAIN
+NETBIRD_RELAY_DOMAIN=""
+
+# Relay server connection port. If none is supplied
+# it will default to 33080
+NETBIRD_RELAY_PORT=""

infrastructure_files/tests/setup.env

@@ -25,4 +25,5 @@ NETBIRD_IDP_MGMT_CLIENT_SECRET=$CI_NETBIRD_IDP_MGMT_CLIENT_SECRET
 NETBIRD_SIGNAL_PORT=12345
 NETBIRD_STORE_CONFIG_ENGINE=$CI_NETBIRD_STORE_CONFIG_ENGINE
 NETBIRD_MGMT_IDP_SIGNKEY_REFRESH=$CI_NETBIRD_MGMT_IDP_SIGNKEY_REFRESH
-NETBIRD_TURN_EXTERNAL_IP=1.2.3.4
+NETBIRD_TURN_EXTERNAL_IP=1.2.3.4
+NETBIRD_RELAY_PORT=33445

management/client/client_test.go

@@ -9,7 +9,10 @@ import (
 	"testing"
 	"time"
 
+	"github.com/stretchr/testify/require"
+
 	"github.com/netbirdio/netbird/management/server/activity"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 
 	"github.com/netbirdio/netbird/client/system"
 
@@ -71,15 +74,17 @@ func startManagement(t *testing.T) (*grpc.Server, net.Listener) {
 	peersUpdateManager := mgmt.NewPeersUpdateManager(nil)
 	eventStore := &activity.InMemoryEventStore{}
 	ia, _ := integrations.NewIntegratedValidator(context.Background(), eventStore)
-	accountManager, err := mgmt.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, ia)
+
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	require.NoError(t, err)
+
+	accountManager, err := mgmt.BuildManager(context.Background(), store, peersUpdateManager, nil, "", "netbird.selfhosted", eventStore, nil, false, ia, metrics)
 	if err != nil {
 		t.Fatal(err)
 	}
-	rc := &mgmt.RelayConfig{
-		Address: "localhost:0",
-	}
-	turnManager := mgmt.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, rc)
-	mgmtServer, err := mgmt.NewServer(context.Background(), config, accountManager, peersUpdateManager, turnManager, nil, nil)
+
+	secretsManager := mgmt.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, config.Relay)
+	mgmtServer, err := mgmt.NewServer(context.Background(), config, accountManager, peersUpdateManager, secretsManager, nil, nil)
 	if err != nil {
 		t.Fatal(err)
 	}

management/client/grpc.go

@@ -2,6 +2,7 @@ package client
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"io"
 	"sync"
@@ -267,7 +268,7 @@ func (c *GrpcClient) receiveEvents(stream proto.ManagementService_SyncClient, se
 // GetServerPublicKey returns server's WireGuard public key (used later for encrypting messages sent to the server)
 func (c *GrpcClient) GetServerPublicKey() (*wgtypes.Key, error) {
 	if !c.ready() {
-		return nil, fmt.Errorf(errMsgNoMgmtConnection)
+		return nil, errors.New(errMsgNoMgmtConnection)
 	}
 
 	mgmCtx, cancel := context.WithTimeout(c.ctx, 5*time.Second)
@@ -314,7 +315,7 @@ func (c *GrpcClient) IsHealthy() bool {
 
 func (c *GrpcClient) login(serverKey wgtypes.Key, req *proto.LoginRequest) (*proto.LoginResponse, error) {
 	if !c.ready() {
-		return nil, fmt.Errorf(errMsgNoMgmtConnection)
+		return nil, errors.New(errMsgNoMgmtConnection)
 	}
 
 	loginReq, err := encryption.EncryptMessage(serverKey, c.key, req)
@@ -452,7 +453,7 @@ func (c *GrpcClient) GetPKCEAuthorizationFlow(serverKey wgtypes.Key) (*proto.PKC
 // It should be used if there is changes on peer posture check after initial sync.
 func (c *GrpcClient) SyncMeta(sysInfo *system.Info) error {
 	if !c.ready() {
-		return fmt.Errorf(errMsgNoMgmtConnection)
+		return errors.New(errMsgNoMgmtConnection)
 	}
 
 	serverPubKey, err := c.GetServerPublicKey()

management/cmd/management.go

@@ -123,6 +123,8 @@ var (
 			return nil
 		},
 		RunE: func(cmd *cobra.Command, args []string) error {
+			flag.Parse()
+
 			ctx, cancel := context.WithCancel(cmd.Context())
 			defer cancel()
 			//nolint
@@ -178,11 +180,11 @@ var (
 				}
 			}
 
-			geo, err := geolocation.NewGeolocation(ctx, config.Datadir)
+			geo, err := geolocation.NewGeolocation(ctx, config.Datadir, !disableGeoliteUpdate)
 			if err != nil {
-				log.WithContext(ctx).Warnf("could not initialize geo location service: %v, we proceed without geo support", err)
+				log.WithContext(ctx).Warnf("could not initialize geolocation service. proceeding without geolocation support: %v", err)
 			} else {
-				log.WithContext(ctx).Infof("geo location service has been initialized from %s", config.Datadir)
+				log.WithContext(ctx).Infof("geolocation service has been initialized from %s", config.Datadir)
 			}
 
 			integratedPeerValidator, err := integrations.NewIntegratedValidator(ctx, eventStore)
@@ -190,12 +192,12 @@ var (
 				return fmt.Errorf("failed to initialize integrated peer validator: %v", err)
 			}
 			accountManager, err := server.BuildManager(ctx, store, peersUpdateManager, idpManager, mgmtSingleAccModeDomain,
-				dnsDomain, eventStore, geo, userDeleteFromIDPEnabled, integratedPeerValidator)
+				dnsDomain, eventStore, geo, userDeleteFromIDPEnabled, integratedPeerValidator, appMetrics)
 			if err != nil {
 				return fmt.Errorf("failed to build default manager: %v", err)
 			}
 
-			turnRelayTokenManager := server.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, config.RelayConfig)
+			secretsManager := server.NewTimeBasedAuthSecretsManager(peersUpdateManager, config.TURNConfig, config.Relay)
 
 			trustedPeers := config.ReverseProxy.TrustedPeers
 			defaultTrustedPeers := []netip.Prefix{netip.MustParsePrefix("0.0.0.0/0"), netip.MustParsePrefix("::/0")}
@@ -271,7 +273,7 @@ var (
 			ephemeralManager.LoadInitialPeers(ctx)
 
 			gRPCAPIHandler := grpc.NewServer(gRPCOpts...)
-			srv, err := server.NewServer(ctx, config, accountManager, peersUpdateManager, turnRelayTokenManager, appMetrics, ephemeralManager)
+			srv, err := server.NewServer(ctx, config, accountManager, peersUpdateManager, secretsManager, appMetrics, ephemeralManager)
 			if err != nil {
 				return fmt.Errorf("failed creating gRPC API handler: %v", err)
 			}
@@ -538,8 +540,8 @@ func loadMgmtConfig(ctx context.Context, mgmtConfigPath string) (*server.Config,
 		}
 	}
 
-	if loadedConfig.RelayConfig != nil {
-		log.Infof("Relay address: %v", loadedConfig.RelayConfig.Address)
+	if loadedConfig.Relay != nil {
+		log.Infof("Relay addresses: %v", loadedConfig.Relay.Addresses)
 	}
 
 	return loadedConfig, err

management/cmd/management_test.go

@@ -7,15 +7,20 @@ import (
 )
 
 const (
-	exampleConfig = `{	
-		"RelayConfig": {
-		   "Address": "rels://relay.stage.npeer.io"
-		},
-		"HttpConfig": {
-			"AuthAudience": "https://stageapp/",
-			"AuthIssuer": "https://something.eu.auth0.com/",
-			"OIDCConfigEndpoint": "https://something.eu.auth0.com/.well-known/openid-configuration"
-		}
+	exampleConfig = `{
+	  "Relay": {
+		"Addresses": [
+		  "rel://192.168.100.1:8085",
+		  "rel://192.168.100.1:8086"
+		],
+		"CredentialsTTL": "12h0m0s",
+		"Secret": "8f7e9d6c5b4a3f2e1d0c9b8a7f6e5d4c3b2a1f0e9d8c7b6a5f4e3d2c1b0a9f8"
+	  },
+	  "HttpConfig": {
+		"AuthAudience": "https://stageapp/",
+		"AuthIssuer": "https://something.eu.auth0.com/",
+		"OIDCConfigEndpoint": "https://something.eu.auth0.com/.well-known/openid-configuration"
+	  }
 	}`
 )
 
@@ -29,10 +34,10 @@ func Test_loadMgmtConfig(t *testing.T) {
 	if err != nil {
 		t.Fatalf("failed to load management config: %s", err)
 	}
-	if cfg.RelayConfig == nil {
+	if cfg.Relay == nil {
 		t.Fatalf("config is nil")
 	}
-	if cfg.RelayConfig.Address == "" {
+	if len(cfg.Relay.Addresses) == 0 {
 		t.Fatalf("relay address is empty")
 	}
 }

management/cmd/root.go

@@ -24,6 +24,7 @@ var (
 	logFile                  string
 	disableMetrics           bool
 	disableSingleAccMode     bool
+	disableGeoliteUpdate     bool
 	idpSignKeyRefreshEnabled bool
 	userDeleteFromIDPEnabled bool
 
@@ -65,6 +66,7 @@ func init() {
 	mgmtCmd.Flags().StringVar(&dnsDomain, "dns-domain", defaultSingleAccModeDomain, fmt.Sprintf("Domain used for peer resolution. This is appended to the peer's name, e.g. pi-server. %s. Max length is 192 characters to allow appending to a peer name with up to 63 characters.", defaultSingleAccModeDomain))
 	mgmtCmd.Flags().BoolVar(&idpSignKeyRefreshEnabled, idpSignKeyRefreshEnabledFlagName, false, "Enable cache headers evaluation to determine signing key rotation period. This will refresh the signing key upon expiry.")
 	mgmtCmd.Flags().BoolVar(&userDeleteFromIDPEnabled, "user-delete-from-idp", false, "Allows to delete user from IDP when user is deleted from account")
+	mgmtCmd.Flags().BoolVar(&disableGeoliteUpdate, "disable-geolite-update", true, "disables automatic updates to the Geolite2 geolocation databases")
 	rootCmd.MarkFlagRequired("config") //nolint
 
 	rootCmd.PersistentFlags().StringVar(&logLevel, "log-level", "info", "")

management/server/account.go

@@ -18,6 +18,8 @@ import (
 
 	"github.com/eko/gocache/v3/cache"
 	cacheStore "github.com/eko/gocache/v3/store"
+	"github.com/hashicorp/go-multierror"
+	"github.com/miekg/dns"
 	gocache "github.com/patrickmn/go-cache"
 	"github.com/rs/xid"
 	log "github.com/sirupsen/logrus"
@@ -37,6 +39,7 @@ import (
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
 	"github.com/netbirdio/netbird/management/server/posture"
 	"github.com/netbirdio/netbird/management/server/status"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 	"github.com/netbirdio/netbird/route"
 )
 
@@ -65,6 +68,7 @@ type AccountManager interface {
 	SaveSetupKey(ctx context.Context, accountID string, key *SetupKey, userID string) (*SetupKey, error)
 	CreateUser(ctx context.Context, accountID, initiatorUserID string, key *UserInfo) (*UserInfo, error)
 	DeleteUser(ctx context.Context, accountID, initiatorUserID string, targetUserID string) error
+	DeleteRegularUsers(ctx context.Context, accountID, initiatorUserID string, targetUserIDs []string) error
 	InviteUser(ctx context.Context, accountID string, initiatorUserID string, targetUserID string) error
 	ListSetupKeys(ctx context.Context, accountID, userID string) ([]*SetupKey, error)
 	SaveUser(ctx context.Context, accountID, initiatorUserID string, update *User) (*UserInfo, error)
@@ -98,6 +102,7 @@ type AccountManager interface {
 	SaveGroup(ctx context.Context, accountID, userID string, group *nbgroup.Group) error
 	SaveGroups(ctx context.Context, accountID, userID string, newGroups []*nbgroup.Group) error
 	DeleteGroup(ctx context.Context, accountId, userId, groupID string) error
+	DeleteGroups(ctx context.Context, accountId, userId string, groupIDs []string) error
 	ListGroups(ctx context.Context, accountId string) ([]*nbgroup.Group, error)
 	GroupAddPeer(ctx context.Context, accountId, groupID, peerID string) error
 	GroupDeletePeer(ctx context.Context, accountId, groupID, peerID string) error
@@ -156,6 +161,8 @@ type DefaultAccountManager struct {
 	eventStore           activity.Store
 	geo                  *geolocation.Geolocation
 
+	requestBuffer *AccountRequestBuffer
+
 	// singleAccountMode indicates whether the instance has a single account.
 	// If true, then every new user will end up under the same account.
 	// This value will be set to false if management service has more than one account.
@@ -170,6 +177,8 @@ type DefaultAccountManager struct {
 	userDeleteFromIDPEnabled bool
 
 	integratedPeerValidator integrated_validator.IntegratedValidator
+
+	metrics telemetry.AppMetrics
 }
 
 // Settings represents Account settings structure that can be modified via API and Dashboard
@@ -401,8 +410,16 @@ func (a *Account) GetGroup(groupID string) *nbgroup.Group {
 	return a.Groups[groupID]
 }
 
-// GetPeerNetworkMap returns a group by ID if exists, nil otherwise
-func (a *Account) GetPeerNetworkMap(ctx context.Context, peerID, dnsDomain string, validatedPeersMap map[string]struct{}) *NetworkMap {
+// GetPeerNetworkMap returns the networkmap for the given peer ID.
+func (a *Account) GetPeerNetworkMap(
+	ctx context.Context,
+	peerID string,
+	peersCustomZone nbdns.CustomZone,
+	validatedPeersMap map[string]struct{},
+	metrics *telemetry.AccountManagerMetrics,
+) *NetworkMap {
+	start := time.Now()
+
 	peer := a.Peers[peerID]
 	if peer == nil {
 		return &NetworkMap{
@@ -438,7 +455,7 @@ func (a *Account) GetPeerNetworkMap(ctx context.Context, peerID, dnsDomain strin
 
 	if dnsManagementStatus {
 		var zones []nbdns.CustomZone
-		peersCustomZone := getPeersCustomZone(ctx, a, dnsDomain)
+
 		if peersCustomZone.Domain != "" {
 			zones = append(zones, peersCustomZone)
 		}
@@ -446,7 +463,7 @@ func (a *Account) GetPeerNetworkMap(ctx context.Context, peerID, dnsDomain strin
 		dnsUpdate.NameServerGroups = getPeerNSGroups(a, peerID)
 	}
 
-	return &NetworkMap{
+	nm := &NetworkMap{
 		Peers:         peersToConnect,
 		Network:       a.Network.Copy(),
 		Routes:        routesUpdate,
@@ -454,6 +471,66 @@ func (a *Account) GetPeerNetworkMap(ctx context.Context, peerID, dnsDomain strin
 		OfflinePeers:  expiredPeers,
 		FirewallRules: firewallRules,
 	}
+
+	if metrics != nil {
+		objectCount := int64(len(peersToConnect) + len(expiredPeers) + len(routesUpdate) + len(firewallRules))
+		metrics.CountNetworkMapObjects(objectCount)
+		metrics.CountGetPeerNetworkMapDuration(time.Since(start))
+
+		if objectCount > 5000 {
+			log.WithContext(ctx).Tracef("account: %s has a total resource count of %d objects, "+
+				"peers to connect: %d, expired peers: %d, routes: %d, firewall rules: %d",
+				a.Id, objectCount, len(peersToConnect), len(expiredPeers), len(routesUpdate), len(firewallRules))
+		}
+	}
+
+	return nm
+}
+
+func (a *Account) GetPeersCustomZone(ctx context.Context, dnsDomain string) nbdns.CustomZone {
+	var merr *multierror.Error
+
+	if dnsDomain == "" {
+		log.WithContext(ctx).Error("no dns domain is set, returning empty zone")
+		return nbdns.CustomZone{}
+	}
+
+	customZone := nbdns.CustomZone{
+		Domain:  dns.Fqdn(dnsDomain),
+		Records: make([]nbdns.SimpleRecord, 0, len(a.Peers)),
+	}
+
+	domainSuffix := "." + dnsDomain
+
+	var sb strings.Builder
+	for _, peer := range a.Peers {
+		if peer.DNSLabel == "" {
+			merr = multierror.Append(merr, fmt.Errorf("peer %s has an empty DNS label", peer.Name))
+			continue
+		}
+
+		sb.Grow(len(peer.DNSLabel) + len(domainSuffix))
+		sb.WriteString(peer.DNSLabel)
+		sb.WriteString(domainSuffix)
+
+		customZone.Records = append(customZone.Records, nbdns.SimpleRecord{
+			Name:  sb.String(),
+			Type:  int(dns.TypeA),
+			Class: nbdns.DefaultClass,
+			TTL:   defaultTTL,
+			RData: peer.IP.String(),
+		})
+
+		sb.Reset()
+	}
+
+	go func() {
+		if merr != nil {
+			log.WithContext(ctx).Errorf("error generating custom zone for account %s: %v", a.Id, merr)
+		}
+	}()
+
+	return customZone
 }
 
 // GetExpiredPeers returns peers that have been expired
@@ -853,7 +930,7 @@ func (a *Account) UserGroupsAddToPeers(userID string, groups ...string) {
 func (a *Account) UserGroupsRemoveFromPeers(userID string, groups ...string) {
 	for _, gid := range groups {
 		group, ok := a.Groups[gid]
-		if !ok {
+		if !ok || group.Name == "All" {
 			continue
 		}
 		update := make([]string, 0, len(group.Peers))
@@ -871,10 +948,18 @@ func (a *Account) UserGroupsRemoveFromPeers(userID string, groups ...string) {
 }
 
 // BuildManager creates a new DefaultAccountManager with a provided Store
-func BuildManager(ctx context.Context, store Store, peersUpdateManager *PeersUpdateManager, idpManager idp.Manager,
-	singleAccountModeDomain string, dnsDomain string, eventStore activity.Store, geo *geolocation.Geolocation,
+func BuildManager(
+	ctx context.Context,
+	store Store,
+	peersUpdateManager *PeersUpdateManager,
+	idpManager idp.Manager,
+	singleAccountModeDomain string,
+	dnsDomain string,
+	eventStore activity.Store,
+	geo *geolocation.Geolocation,
 	userDeleteFromIDPEnabled bool,
 	integratedPeerValidator integrated_validator.IntegratedValidator,
+	metrics telemetry.AppMetrics,
 ) (*DefaultAccountManager, error) {
 	am := &DefaultAccountManager{
 		Store:                    store,
@@ -889,6 +974,8 @@ func BuildManager(ctx context.Context, store Store, peersUpdateManager *PeersUpd
 		peerLoginExpiry:          NewDefaultScheduler(),
 		userDeleteFromIDPEnabled: userDeleteFromIDPEnabled,
 		integratedPeerValidator:  integratedPeerValidator,
+		metrics:                  metrics,
+		requestBuffer:            NewAccountRequestBuffer(ctx, store),
 	}
 	allAccounts := store.GetAllAccounts(ctx)
 	// enable single account mode only if configured by user and number of existing accounts is not grater than 1
@@ -1994,6 +2081,28 @@ func (am *DefaultAccountManager) GetAccountIDForPeerKey(ctx context.Context, pee
 	return am.Store.GetAccountIDByPeerPubKey(ctx, peerKey)
 }
 
+func (am *DefaultAccountManager) handleUserPeer(ctx context.Context, peer *nbpeer.Peer, settings *Settings) (bool, error) {
+	user, err := am.Store.GetUserByUserID(ctx, peer.UserID)
+	if err != nil {
+		return false, err
+	}
+
+	err = checkIfPeerOwnerIsBlocked(peer, user)
+	if err != nil {
+		return false, err
+	}
+
+	if peerLoginExpired(ctx, peer, settings) {
+		err = am.handleExpiredPeer(ctx, user, peer)
+		if err != nil {
+			return false, err
+		}
+		return true, nil
+	}
+
+	return false, nil
+}
+
 // addAllGroup to account object if it doesn't exist
 func addAllGroup(account *Account) error {
 	if len(account.Groups) == 0 {

management/server/account_request_buffer.go

@@ -0,0 +1,108 @@
+package server
+
+import (
+	"context"
+	"os"
+	"sync"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// AccountRequest holds the result channel to return the requested account.
+type AccountRequest struct {
+	AccountID  string
+	ResultChan chan *AccountResult
+}
+
+// AccountResult holds the account data or an error.
+type AccountResult struct {
+	Account *Account
+	Err     error
+}
+
+type AccountRequestBuffer struct {
+	store               Store
+	getAccountRequests  map[string][]*AccountRequest
+	mu                  sync.Mutex
+	getAccountRequestCh chan *AccountRequest
+	bufferInterval      time.Duration
+}
+
+func NewAccountRequestBuffer(ctx context.Context, store Store) *AccountRequestBuffer {
+	bufferIntervalStr := os.Getenv("NB_GET_ACCOUNT_BUFFER_INTERVAL")
+	bufferInterval, err := time.ParseDuration(bufferIntervalStr)
+	if err != nil {
+		if bufferIntervalStr != "" {
+			log.WithContext(ctx).Warnf("failed to parse account request buffer interval: %s", err)
+		}
+		bufferInterval = 100 * time.Millisecond
+	}
+
+	log.WithContext(ctx).Infof("set account request buffer interval to %s", bufferInterval)
+
+	ac := AccountRequestBuffer{
+		store:               store,
+		getAccountRequests:  make(map[string][]*AccountRequest),
+		getAccountRequestCh: make(chan *AccountRequest),
+		bufferInterval:      bufferInterval,
+	}
+
+	go ac.processGetAccountRequests(ctx)
+
+	return &ac
+}
+func (ac *AccountRequestBuffer) GetAccountWithBackpressure(ctx context.Context, accountID string) (*Account, error) {
+	req := &AccountRequest{
+		AccountID:  accountID,
+		ResultChan: make(chan *AccountResult, 1),
+	}
+
+	log.WithContext(ctx).Tracef("requesting account %s with backpressure", accountID)
+	startTime := time.Now()
+	ac.getAccountRequestCh <- req
+
+	result := <-req.ResultChan
+	log.WithContext(ctx).Tracef("got account with backpressure after %s", time.Since(startTime))
+	return result.Account, result.Err
+}
+
+func (ac *AccountRequestBuffer) processGetAccountBatch(ctx context.Context, accountID string) {
+	ac.mu.Lock()
+	requests := ac.getAccountRequests[accountID]
+	delete(ac.getAccountRequests, accountID)
+	ac.mu.Unlock()
+
+	if len(requests) == 0 {
+		return
+	}
+
+	startTime := time.Now()
+	account, err := ac.store.GetAccount(ctx, accountID)
+	log.WithContext(ctx).Tracef("getting account %s in batch took %s", accountID, time.Since(startTime))
+	result := &AccountResult{Account: account, Err: err}
+
+	for _, req := range requests {
+		req.ResultChan <- result
+		close(req.ResultChan)
+	}
+}
+
+func (ac *AccountRequestBuffer) processGetAccountRequests(ctx context.Context) {
+	for {
+		select {
+		case req := <-ac.getAccountRequestCh:
+			ac.mu.Lock()
+			ac.getAccountRequests[req.AccountID] = append(ac.getAccountRequests[req.AccountID], req)
+			if len(ac.getAccountRequests[req.AccountID]) == 1 {
+				go func(ctx context.Context, accountID string) {
+					time.Sleep(ac.bufferInterval)
+					ac.processGetAccountBatch(ctx, accountID)
+				}(ctx, req.AccountID)
+			}
+			ac.mu.Unlock()
+		case <-ctx.Done():
+			return
+		}
+	}
+}

management/server/account_test.go

@@ -24,6 +24,7 @@ import (
 	"github.com/netbirdio/netbird/management/server/jwtclaims"
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
 	"github.com/netbirdio/netbird/management/server/posture"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 	"github.com/netbirdio/netbird/route"
 )
 
@@ -410,7 +411,8 @@ func TestAccount_GetPeerNetworkMap(t *testing.T) {
 			validatedPeers[p] = struct{}{}
 		}
 
-		networkMap := account.GetPeerNetworkMap(context.Background(), testCase.peerID, "netbird.io", validatedPeers)
+		customZone := account.GetPeersCustomZone(context.Background(), "netbird.io")
+		networkMap := account.GetPeerNetworkMap(context.Background(), testCase.peerID, customZone, validatedPeers, nil)
 		assert.Len(t, networkMap.Peers, len(testCase.expectedPeers))
 		assert.Len(t, networkMap.OfflinePeers, len(testCase.expectedOfflinePeers))
 	}
@@ -2293,7 +2295,13 @@ func TestAccount_UserGroupsRemoveFromPeers(t *testing.T) {
 	})
 }
 
-func createManager(t *testing.T) (*DefaultAccountManager, error) {
+type TB interface {
+	Cleanup(func())
+	Helper()
+	TempDir() string
+}
+
+func createManager(t TB) (*DefaultAccountManager, error) {
 	t.Helper()
 
 	store, err := createStore(t)
@@ -2302,7 +2310,12 @@ func createManager(t *testing.T) (*DefaultAccountManager, error) {
 	}
 	eventStore := &activity.InMemoryEventStore{}
 
-	manager, err := BuildManager(context.Background(), store, NewPeersUpdateManager(nil), nil, "", "netbird.cloud", eventStore, nil, false, MocIntegratedValidator{})
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	if err != nil {
+		return nil, err
+	}
+
+	manager, err := BuildManager(context.Background(), store, NewPeersUpdateManager(nil), nil, "", "netbird.cloud", eventStore, nil, false, MocIntegratedValidator{}, metrics)
 	if err != nil {
 		return nil, err
 	}
@@ -2310,7 +2323,7 @@ func createManager(t *testing.T) (*DefaultAccountManager, error) {
 	return manager, nil
 }
 
-func createStore(t *testing.T) (Store, error) {
+func createStore(t TB) (Store, error) {
 	t.Helper()
 	dataDir := t.TempDir()
 	store, cleanUp, err := NewTestStoreFromJson(context.Background(), dataDir)

management/server/config.go

@@ -32,10 +32,10 @@ const (
 
 // Config of the Management service
 type Config struct {
-	Stuns       []*Host
-	TURNConfig  *TURNConfig
-	RelayConfig *RelayConfig
-	Signal      *Host
+	Stuns      []*Host
+	TURNConfig *TURNConfig
+	Relay      *Relay
+	Signal     *Host
 
 	Datadir                string
 	DataStoreEncryptionKey string
@@ -76,8 +76,10 @@ type TURNConfig struct {
 	Turns                []*Host
 }
 
-type RelayConfig struct {
-	Address string
+type Relay struct {
+	Addresses      []string
+	CredentialsTTL util.Duration
+	Secret         string
 }
 
 // HttpServerConfig is a config of the HTTP Management service server

management/server/dns.go

@@ -4,8 +4,8 @@ import (
 	"context"
 	"fmt"
 	"strconv"
+	"sync"
 
-	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
 
 	nbdns "github.com/netbirdio/netbird/dns"
@@ -17,6 +17,50 @@ import (
 
 const defaultTTL = 300
 
+// DNSConfigCache is a thread-safe cache for DNS configuration components
+type DNSConfigCache struct {
+	CustomZones      sync.Map
+	NameServerGroups sync.Map
+}
+
+// GetCustomZone retrieves a cached custom zone
+func (c *DNSConfigCache) GetCustomZone(key string) (*proto.CustomZone, bool) {
+	if c == nil {
+		return nil, false
+	}
+	if value, ok := c.CustomZones.Load(key); ok {
+		return value.(*proto.CustomZone), true
+	}
+	return nil, false
+}
+
+// SetCustomZone stores a custom zone in the cache
+func (c *DNSConfigCache) SetCustomZone(key string, value *proto.CustomZone) {
+	if c == nil {
+		return
+	}
+	c.CustomZones.Store(key, value)
+}
+
+// GetNameServerGroup retrieves a cached name server group
+func (c *DNSConfigCache) GetNameServerGroup(key string) (*proto.NameServerGroup, bool) {
+	if c == nil {
+		return nil, false
+	}
+	if value, ok := c.NameServerGroups.Load(key); ok {
+		return value.(*proto.NameServerGroup), true
+	}
+	return nil, false
+}
+
+// SetNameServerGroup stores a name server group in the cache
+func (c *DNSConfigCache) SetNameServerGroup(key string, value *proto.NameServerGroup) {
+	if c == nil {
+		return
+	}
+	c.NameServerGroups.Store(key, value)
+}
+
 type lookupMap map[string]struct{}
 
 // DNSSettings defines dns settings at the account level
@@ -113,69 +157,73 @@ func (am *DefaultAccountManager) SaveDNSSettings(ctx context.Context, accountID
 	return nil
 }
 
-func toProtocolDNSConfig(update nbdns.Config) *proto.DNSConfig {
-	protoUpdate := &proto.DNSConfig{ServiceEnable: update.ServiceEnable}
+// toProtocolDNSConfig converts nbdns.Config to proto.DNSConfig using the cache
+func toProtocolDNSConfig(update nbdns.Config, cache *DNSConfigCache) *proto.DNSConfig {
+	protoUpdate := &proto.DNSConfig{
+		ServiceEnable:    update.ServiceEnable,
+		CustomZones:      make([]*proto.CustomZone, 0, len(update.CustomZones)),
+		NameServerGroups: make([]*proto.NameServerGroup, 0, len(update.NameServerGroups)),
+	}
 
 	for _, zone := range update.CustomZones {
-		protoZone := &proto.CustomZone{Domain: zone.Domain}
-		for _, record := range zone.Records {
-			protoZone.Records = append(protoZone.Records, &proto.SimpleRecord{
-				Name:  record.Name,
-				Type:  int64(record.Type),
-				Class: record.Class,
-				TTL:   int64(record.TTL),
-				RData: record.RData,
-			})
+		cacheKey := zone.Domain
+		if cachedZone, exists := cache.GetCustomZone(cacheKey); exists {
+			protoUpdate.CustomZones = append(protoUpdate.CustomZones, cachedZone)
+		} else {
+			protoZone := convertToProtoCustomZone(zone)
+			cache.SetCustomZone(cacheKey, protoZone)
+			protoUpdate.CustomZones = append(protoUpdate.CustomZones, protoZone)
 		}
-		protoUpdate.CustomZones = append(protoUpdate.CustomZones, protoZone)
 	}
 
 	for _, nsGroup := range update.NameServerGroups {
-		protoGroup := &proto.NameServerGroup{
-			Primary:              nsGroup.Primary,
-			Domains:              nsGroup.Domains,
-			SearchDomainsEnabled: nsGroup.SearchDomainsEnabled,
+		cacheKey := nsGroup.ID
+		if cachedGroup, exists := cache.GetNameServerGroup(cacheKey); exists {
+			protoUpdate.NameServerGroups = append(protoUpdate.NameServerGroups, cachedGroup)
+		} else {
+			protoGroup := convertToProtoNameServerGroup(nsGroup)
+			cache.SetNameServerGroup(cacheKey, protoGroup)
+			protoUpdate.NameServerGroups = append(protoUpdate.NameServerGroups, protoGroup)
 		}
-		for _, ns := range nsGroup.NameServers {
-			protoNS := &proto.NameServer{
-				IP:     ns.IP.String(),
-				Port:   int64(ns.Port),
-				NSType: int64(ns.NSType),
-			}
-			protoGroup.NameServers = append(protoGroup.NameServers, protoNS)
-		}
-		protoUpdate.NameServerGroups = append(protoUpdate.NameServerGroups, protoGroup)
 	}
 
 	return protoUpdate
 }
 
-func getPeersCustomZone(ctx context.Context, account *Account, dnsDomain string) nbdns.CustomZone {
-	if dnsDomain == "" {
-		log.WithContext(ctx).Errorf("no dns domain is set, returning empty zone")
-		return nbdns.CustomZone{}
+// Helper function to convert nbdns.CustomZone to proto.CustomZone
+func convertToProtoCustomZone(zone nbdns.CustomZone) *proto.CustomZone {
+	protoZone := &proto.CustomZone{
+		Domain:  zone.Domain,
+		Records: make([]*proto.SimpleRecord, 0, len(zone.Records)),
 	}
-
-	customZone := nbdns.CustomZone{
-		Domain: dns.Fqdn(dnsDomain),
-	}
-
-	for _, peer := range account.Peers {
-		if peer.DNSLabel == "" {
-			log.WithContext(ctx).Errorf("found a peer with empty dns label. It was probably caused by a invalid character in its name. Peer Name: %s", peer.Name)
-			continue
-		}
-
-		customZone.Records = append(customZone.Records, nbdns.SimpleRecord{
-			Name:  dns.Fqdn(peer.DNSLabel + "." + dnsDomain),
-			Type:  int(dns.TypeA),
-			Class: nbdns.DefaultClass,
-			TTL:   defaultTTL,
-			RData: peer.IP.String(),
+	for _, record := range zone.Records {
+		protoZone.Records = append(protoZone.Records, &proto.SimpleRecord{
+			Name:  record.Name,
+			Type:  int64(record.Type),
+			Class: record.Class,
+			TTL:   int64(record.TTL),
+			RData: record.RData,
 		})
 	}
+	return protoZone
+}
 
-	return customZone
+// Helper function to convert nbdns.NameServerGroup to proto.NameServerGroup
+func convertToProtoNameServerGroup(nsGroup *nbdns.NameServerGroup) *proto.NameServerGroup {
+	protoGroup := &proto.NameServerGroup{
+		Primary:              nsGroup.Primary,
+		Domains:              nsGroup.Domains,
+		SearchDomainsEnabled: nsGroup.SearchDomainsEnabled,
+		NameServers:          make([]*proto.NameServer, 0, len(nsGroup.NameServers)),
+	}
+	for _, ns := range nsGroup.NameServers {
+		protoGroup.NameServers = append(protoGroup.NameServers, &proto.NameServer{
+			IP:     ns.IP.String(),
+			Port:   int64(ns.Port),
+			NSType: int64(ns.NSType),
+		})
+	}
+	return protoGroup
 }
 
 func getPeerNSGroups(account *Account, peerID string) []*nbdns.NameServerGroup {

management/server/dns_test.go

@@ -2,9 +2,14 @@ package server
 
 import (
 	"context"
+	"fmt"
 	"net/netip"
+	"reflect"
 	"testing"
 
+	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/management/server/telemetry"
+
 	"github.com/stretchr/testify/require"
 
 	"github.com/netbirdio/netbird/dns"
@@ -195,7 +200,11 @@ func createDNSManager(t *testing.T) (*DefaultAccountManager, error) {
 		return nil, err
 	}
 	eventStore := &activity.InMemoryEventStore{}
-	return BuildManager(context.Background(), store, NewPeersUpdateManager(nil), nil, "", "netbird.test", eventStore, nil, false, MocIntegratedValidator{})
+
+	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
+	require.NoError(t, err)
+
+	return BuildManager(context.Background(), store, NewPeersUpdateManager(nil), nil, "", "netbird.test", eventStore, nil, false, MocIntegratedValidator{}, metrics)
 }
 
 func createDNSStore(t *testing.T) (Store, error) {
@@ -320,3 +329,150 @@ func initTestDNSAccount(t *testing.T, am *DefaultAccountManager) (*Account, erro
 
 	return am.Store.GetAccount(context.Background(), account.Id)
 }
+
+func generateTestData(size int) nbdns.Config {
+	config := nbdns.Config{
+		ServiceEnable:    true,
+		CustomZones:      make([]nbdns.CustomZone, size),
+		NameServerGroups: make([]*nbdns.NameServerGroup, size),
+	}
+
+	for i := 0; i < size; i++ {
+		config.CustomZones[i] = nbdns.CustomZone{
+			Domain: fmt.Sprintf("domain%d.com", i),
+			Records: []nbdns.SimpleRecord{
+				{
+					Name:  fmt.Sprintf("record%d", i),
+					Type:  1,
+					Class: "IN",
+					TTL:   3600,
+					RData: "192.168.1.1",
+				},
+			},
+		}
+
+		config.NameServerGroups[i] = &nbdns.NameServerGroup{
+			ID:                   fmt.Sprintf("group%d", i),
+			Primary:              i == 0,
+			Domains:              []string{fmt.Sprintf("domain%d.com", i)},
+			SearchDomainsEnabled: true,
+			NameServers: []nbdns.NameServer{
+				{
+					IP:     netip.MustParseAddr("8.8.8.8"),
+					Port:   53,
+					NSType: 1,
+				},
+			},
+		}
+	}
+
+	return config
+}
+
+func BenchmarkToProtocolDNSConfig(b *testing.B) {
+	sizes := []int{10, 100, 1000}
+
+	for _, size := range sizes {
+		testData := generateTestData(size)
+
+		b.Run(fmt.Sprintf("WithCache-Size%d", size), func(b *testing.B) {
+			cache := &DNSConfigCache{}
+
+			b.ResetTimer()
+			for i := 0; i < b.N; i++ {
+				toProtocolDNSConfig(testData, cache)
+			}
+		})
+
+		b.Run(fmt.Sprintf("WithoutCache-Size%d", size), func(b *testing.B) {
+			b.ResetTimer()
+			for i := 0; i < b.N; i++ {
+				cache := &DNSConfigCache{}
+				toProtocolDNSConfig(testData, cache)
+			}
+		})
+	}
+}
+
+func TestToProtocolDNSConfigWithCache(t *testing.T) {
+	var cache DNSConfigCache
+
+	// Create two different configs
+	config1 := nbdns.Config{
+		ServiceEnable: true,
+		CustomZones: []nbdns.CustomZone{
+			{
+				Domain: "example.com",
+				Records: []nbdns.SimpleRecord{
+					{Name: "www", Type: 1, Class: "IN", TTL: 300, RData: "192.168.1.1"},
+				},
+			},
+		},
+		NameServerGroups: []*nbdns.NameServerGroup{
+			{
+				ID:   "group1",
+				Name: "Group 1",
+				NameServers: []nbdns.NameServer{
+					{IP: netip.MustParseAddr("8.8.8.8"), Port: 53},
+				},
+			},
+		},
+	}
+
+	config2 := nbdns.Config{
+		ServiceEnable: true,
+		CustomZones: []nbdns.CustomZone{
+			{
+				Domain: "example.org",
+				Records: []nbdns.SimpleRecord{
+					{Name: "mail", Type: 1, Class: "IN", TTL: 300, RData: "192.168.1.2"},
+				},
+			},
+		},
+		NameServerGroups: []*nbdns.NameServerGroup{
+			{
+				ID:   "group2",
+				Name: "Group 2",
+				NameServers: []nbdns.NameServer{
+					{IP: netip.MustParseAddr("8.8.4.4"), Port: 53},
+				},
+			},
+		},
+	}
+
+	// First run with config1
+	result1 := toProtocolDNSConfig(config1, &cache)
+
+	// Second run with config2
+	result2 := toProtocolDNSConfig(config2, &cache)
+
+	// Third run with config1 again
+	result3 := toProtocolDNSConfig(config1, &cache)
+
+	// Verify that result1 and result3 are identical
+	if !reflect.DeepEqual(result1, result3) {
+		t.Errorf("Results are not identical when run with the same input. Expected %v, got %v", result1, result3)
+	}
+
+	// Verify that result2 is different from result1 and result3
+	if reflect.DeepEqual(result1, result2) || reflect.DeepEqual(result2, result3) {
+		t.Errorf("Results should be different for different inputs")
+	}
+
+	// Verify that the cache contains elements from both configs
+	if _, exists := cache.GetCustomZone("example.com"); !exists {
+		t.Errorf("Cache should contain custom zone for example.com")
+	}
+
+	if _, exists := cache.GetCustomZone("example.org"); !exists {
+		t.Errorf("Cache should contain custom zone for example.org")
+	}
+
+	if _, exists := cache.GetNameServerGroup("group1"); !exists {
+		t.Errorf("Cache should contain name server group 'group1'")
+	}
+
+	if _, exists := cache.GetNameServerGroup("group2"); !exists {
+		t.Errorf("Cache should contain name server group 'group2'")
+	}
+}