feat(hole-punch): add hole-punch interoperability test suite

.github/actions/run-interop-hole-punch-test/action.yml

@@ -0,0 +1,155 @@
+name: "libp2p hole-punch interop test"
+description: "Run the libp2p hole-punch interoperability test suite"
+inputs:
+  test-filter:
+    description: "Filter which tests to run out of the created matrix"
+    required: false
+    default: ""
+  test-ignore:
+    description: "Exclude tests from the created matrix that include this string in their name"
+    required: false
+    default: ""
+  extra-versions:
+    description: "Space-separated paths to JSON files describing additional images"
+    required: false
+    default: ""
+  s3-cache-bucket:
+    description: "Which S3 bucket to use for container layer caching"
+    required: false
+    default: ""
+  s3-access-key-id:
+    description: "S3 Access key id for the cache"
+    required: false
+    default: ""
+  s3-secret-access-key:
+    description: "S3 secret key id for the cache"
+    required: false
+    default: ""
+  aws-region:
+    description: "Which AWS region to use"
+    required: false
+    default: "us-east-1"
+  worker-count:
+    description: "How many workers to use for the test"
+    required: false
+    default: "2"
+runs:
+  using: "composite"
+  steps:
+    - name: Configure AWS credentials for S3 build cache
+      if: inputs.s3-access-key-id != '' && inputs.s3-secret-access-key != ''
+      run: |
+        echo "PUSH_CACHE=true" >> $GITHUB_ENV
+      shell: bash
+
+    # This depends on where this file is within this repository. This walks up
+    # from here to the hole-punch-interop folder
+    - run: |
+        WORK_DIR=$(realpath "$GITHUB_ACTION_PATH/../../../hole-punch-interop")
+        echo "WORK_DIR=$WORK_DIR" >> $GITHUB_OUTPUT
+      shell: bash
+      id: find-workdir
+
+    - uses: actions/setup-node@v3
+      with:
+        node-version: 18
+
+    # Existence of /etc/buildkit/buildkitd.toml indicates that this is a
+    # self-hosted runner. If so, we need to pass the config to the buildx
+    # action. The config enables docker.io proxy which is required to
+    # work around docker hub rate limiting.
+    - run: |
+        if test -f /etc/buildkit/buildkitd.toml; then
+          echo "config=/etc/buildkit/buildkitd.toml" >> $GITHUB_OUTPUT
+        fi
+      shell: bash
+      id: buildkit
+
+    - name: Install more recent docker-compose version # https://stackoverflow.com/questions/54331949/having-networking-issues-with-docker-compose
+      shell: bash
+      run: |
+        mkdir -p $HOME/.docker/cli-plugins
+        wget -q -O- https://github.com/docker/compose/releases/download/v2.21.0/docker-compose-linux-x86_64 > $HOME/.docker/cli-plugins/docker-compose
+        chmod +x $HOME/.docker/cli-plugins/docker-compose
+        docker compose version
+
+    - name: Set up Docker Buildx
+      id: buildx
+      uses: docker/setup-buildx-action@v2
+      with:
+        config: ${{ steps.buildkit.outputs.config }}
+
+    - name: Install deps
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      run: npm ci
+      shell: bash
+
+    - name: Load cache and build
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      run: npm run cache -- load
+      shell: bash
+
+    - name: Assert Git tree is clean.
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      shell: bash
+      run: |
+        if [[ -n "$(git status --porcelain)" ]]; then
+          echo "Git tree is dirty. This means that building an impl generated something that should probably be .gitignore'd"
+          git status
+          exit 1
+        fi
+
+    - name: Push the image cache
+      if: env.PUSH_CACHE == 'true'
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      env:
+        AWS_BUCKET: ${{ inputs.s3-cache-bucket }}
+        AWS_REGION: ${{ inputs.aws-region }}
+        AWS_ACCESS_KEY_ID: ${{ inputs.s3-access-key-id }}
+        AWS_SECRET_ACCESS_KEY: ${{ inputs.s3-secret-access-key }}
+      run: npm run cache -- push
+      shell: bash
+
+    - name: Run the test
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      env:
+        WORKER_COUNT: ${{ inputs.worker-count }}
+        EXTRA_VERSION: ${{ inputs.extra-versions }}
+        NAME_FILTER: ${{ inputs.test-filter }}
+        NAME_IGNORE: ${{ inputs.test-ignore }}
+      run: npm run test -- --extra-version=$EXTRA_VERSION --name-filter=$NAME_FILTER --name-ignore=$NAME_IGNORE
+      shell: bash
+
+    - name: Print the results
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      run: cat results.csv
+      shell: bash
+
+    - name: Render results
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      run: npm run renderResults > ./dashboard.md
+      shell: bash
+
+    - name: Show Dashboard Output
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      run: cat ./dashboard.md >> $GITHUB_STEP_SUMMARY
+      shell: bash
+
+    - name: Exit with Error
+      working-directory: ${{ steps.find-workdir.outputs.WORK_DIR }}
+      run: |
+        if grep -q ":red_circle:" ./dashboard.md; then
+          exit 1
+        else
+          exit 0
+        fi
+      shell: bash
+
+    - uses: actions/upload-artifact@v3
+      if: ${{ always() }}
+      with:
+        name: test-plans-output
+        path: |
+          ${{ steps.find-workdir.outputs.WORK_DIR }}/results.csv
+          ${{ steps.find-workdir.outputs.WORK_DIR }}/dashboard.md
+          ${{ steps.find-workdir.outputs.WORK_DIR }}/runs

.github/workflows/hole-punch-interop.yml

@@ -0,0 +1,24 @@
+on:
+  workflow_dispatch:
+  pull_request:
+    paths:
+      - 'hole-punch-interop/**'
+  push:
+    branches:
+      - "master"
+    paths:
+      - 'hole-punch-interop/**'
+
+name: libp2p holepunching interop test
+
+jobs:
+  run-hole-punch-interop:
+    runs-on: ['self-hosted', 'linux', 'x64', '4xlarge'] # https://github.com/pl-strflt/tf-aws-gh-runner/blob/main/runners.tf
+    steps:
+      - uses: actions/checkout@v3
+      - uses: ./.github/actions/run-interop-hole-punch-test
+        with:
+          s3-cache-bucket: libp2p-by-tf-aws-bootstrap
+          s3-access-key-id: ${{ vars.S3_AWS_ACCESS_KEY_ID }}
+          s3-secret-access-key: ${{ secrets.S3_AWS_SECRET_ACCESS_KEY }}
+          worker-count: 16

hole-punch-interop/.gitignore

@@ -0,0 +1,7 @@
+# For now, not committing image.json files
+image.json
+
+results.csv
+runs/
+
+node_modules/

hole-punch-interop/Makefile

@@ -0,0 +1,19 @@
+RUST_SUBDIRS := $(wildcard impl/rust/*/.)
+GO_SUBDIRS := $(wildcard impl/go/*/.)
+
+all: rust-relay router $(RUST_SUBDIRS) $(GO_SUBDIRS)
+rust-relay:
+	$(MAKE) -C rust-relay
+router:
+	$(MAKE) -C router
+$(RUST_SUBDIRS):
+	$(MAKE) -C $@
+$(GO_SUBDIRS):
+	$(MAKE) -C $@
+clean:
+	$(MAKE) -C rust-relay clean
+	$(MAKE) -C router clean
+	$(MAKE) -C $(RUST_SUBDIRS) clean
+	$(MAKE) -C $(GO_SUBDIRS) clean
+
+.PHONY: rust-relay router all $(RUST_SUBDIRS) $(GO_SUBDIRS)

hole-punch-interop/README.md

@@ -0,0 +1,84 @@
+# Hole punch tests
+
+## How to run locally
+
+1. `npm install`
+2. `make`
+3. `npm run test`
+
+## Client configuration
+
+| env variable | possible values |
+|--------------|-----------------|
+| MODE         | listen \| dial  |
+| TRANSPORT    | tcp \| quic     |
+
+- For TCP, the client MUST use noise + yamux to upgrade the connection.
+- The relayed connection MUST use noise + yamux.
+
+## Test flow
+
+1. The relay starts and pushes its address to the following redis keys:
+   - `RELAY_TCP_ADDRESS` for the TCP test
+   - `RELAY_QUIC_ADDRESS` for the QUIC test
+1. Upon start-up, clients connect to a redis server at `redis:6379` and block until this redis key comes available.
+   They then dial the relay on the provided address.
+1. The relay supports identify.
+   Implementations SHOULD use that to figure out their external address next.
+1. Once connected to the relay, a client in `MODE=listen` should listen on the relay and make a reservation.
+   Once the reservation is made, it pushes its `PeerId` to the redis key `LISTEN_CLIENT_PEER_ID`.
+1. A client in `MODE=dial` blocks on the availability of `LISTEN_CLIENT_PEER_ID`.
+   Once available, it dials `<relay_addr>/p2p-circuit/<listen-client-peer-id>`.
+1. Upon a successful hole-punch, the peer in `MODE=dial` measures the RTT across the newly established connection.
+1. The RTT MUST be printed to stdout in the following format:
+   ```json
+   { "rtt_to_holepunched_peer_millis": 12 }
+   ```
+1. Once printed, the dialer MUST exit with `0`.
+
+## Requirements for implementations
+
+- Docker containers MUST have a binary called `hole-punch-client` in their $PATH
+- MUST have `dig`, `curl`, `jq` and `tcpdump` installed
+- Listener MUST NOT early-exit but wait to be killed by test runner
+- Logs MUST go to stderr, RTT json MUST go to stdout
+- Dialer and lister both MUST use 0RTT negotiation for protocols
+- Implementations SHOULD disable timeouts on the redis client, i.e. use `0`
+- Implementations SHOULD exit early with a non-zero exit code if anything goes wrong
+- Implementations MUST set `TCP_NODELAY` for the TCP transport
+- Implements MUST make sure connections are being kept alive
+
+## Design notes
+
+The design of this test runner is heavily influenced by [multidim-interop](../multidim-interop) but differs in several ways.
+
+All files related to test runs will be written to the [./runs](./runs) directory.
+This includes the `docker-compose.yml` files of each individual run as well as logs and `tcpdump`'s for the dialer and listener.
+
+The docker-compose file uses 6 containers in total:
+
+- 1 redis container for orchestrating the test
+- 1 [relay](./rust-relay)
+- 1 hole-punch client in `MODE=dial`
+- 1 hole-punch client in `MODE=listen`
+- 2 [routers](./router): 1 per client
+
+The networks are allocated by docker-compose.
+We dynamically fetch the IPs and subnets as part of a startup script to set the correct IP routes.  
+
+In total, we have three networks:
+
+1. `lan_dialer`
+2. `lan_listener`
+3. `internet`
+
+The two LANs host a router and a client each whereas the relay is connected (without a router) to the `internet` network.
+On startup of the clients, we add an `ip route` that redirects all traffic to the corresponding `router` container.
+The router container masquerades all traffic upon forwarding, see the [README](./router/README.md) for details.
+
+## Running a single test
+
+1. Build all containers using `make`
+1. Generate all test definitions using `npm run test -- --no-run`
+1. Pick the desired test from the [runs](./runs) directory
+1. Execute it using `docker compose up`