Handle restarts for services in fixturenet-optimism stack (#282)

* Check existing L1 contracts deployment

* Rename volume used for generated L2 config

* Check for existing L2 geth data directory

* Cross check existing L2 config against L1 deployment config

* Verify sequencer key in existing L2 geth data directory

* Add instructions to troubleshoot corrupt L2 geth dir

* Separate out instructions to run L2 with external L1

* Update docs

Former-commit-id: 9ffa9bb5a9

app/data/compose/docker-compose-fixturenet-optimism.yml

@@ -14,6 +14,7 @@ services:
       "./wait-for-it.sh -h $${L1_HOST} -p $${L1_PORT} -s -t 60 -- ./run.sh"
     volumes:
       - ../config/wait-for-it.sh:/app/packages/contracts-bedrock/wait-for-it.sh
+      - ../container-build/cerc-optimism-contracts/hardhat-tasks/verify-contract-deployment.ts:/app/packages/contracts-bedrock/tasks/verify-contract-deployment.ts
       - ../container-build/cerc-optimism-contracts/hardhat-tasks/rekey-json.ts:/app/packages/contracts-bedrock/tasks/rekey-json.ts
       - ../container-build/cerc-optimism-contracts/hardhat-tasks/send-balance.ts:/app/packages/contracts-bedrock/tasks/send-balance.ts
       - ../config/fixturenet-optimism/optimism-contracts/update-config.js:/app/packages/contracts-bedrock/update-config.js
@@ -24,7 +25,7 @@ services:
     extra_hosts:
     - "host.docker.internal:host-gateway"
 
-  # Generates the config files required for L2 (outputs to volume op_node_data)
+  # Generates the config files required for L2 (outputs to volume l2_config)
   op-node-l2-config-gen:
     image: cerc/optimism-op-node:local
     depends_on:
@@ -35,12 +36,12 @@ services:
     volumes:
       - ../config/fixturenet-optimism/generate-l2-config.sh:/app/generate-l2-config.sh
       - l1_deployment:/contracts-bedrock:ro
-      - op_node_data:/app
+      - l2_config:/app
     command: ["sh", "/app/generate-l2-config.sh"]
     extra_hosts:
     - "host.docker.internal:host-gateway"
 
-  # Initializes and runs the L2 execution client
+  # Initializes and runs the L2 execution client  (outputs to volume l2_geth_data)
   op-geth:
     image: cerc/optimism-l2geth:local
     depends_on:
@@ -48,8 +49,9 @@ services:
         condition: service_started
     volumes:
       - ../config/fixturenet-optimism/run-op-geth.sh:/run-op-geth.sh
-      - op_node_data:/op-node:ro
+      - l2_config:/op-node:ro
       - l2_accounts:/l2-accounts:ro
+      - l2_geth_data:/datadir
     entrypoint: "sh"
     command: "/run-op-geth.sh"
     ports:
@@ -71,7 +73,7 @@ services:
     image: cerc/optimism-op-node:local
     volumes:
       - ../config/fixturenet-optimism/run-op-node.sh:/app/run-op-node.sh
-      - op_node_data:/op-node-data:ro
+      - l2_config:/op-node-data:ro
       - l2_accounts:/l2-accounts:ro
     command: ["sh", "/app/run-op-node.sh"]
     ports:
@@ -110,4 +112,5 @@ volumes:
   fixturenet_geth_accounts:
   l1_deployment:
   l2_accounts:
-  op_node_data:
+  l2_config:
+  l2_geth_data:

app/data/config/fixturenet-optimism/generate-l2-config.sh

@@ -4,6 +4,27 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
   set -x
 fi
 
+# Check existing config if it exists
+if [ -f /app/jwt.txt ] && [ -f /app/rollup.json ]; then
+  echo "Found existing L2 config, cross-checking with L1 deployment config"
+
+  SOURCE_L1_CONF=$(cat /contracts-bedrock/deploy-config/getting-started.json)
+  EXP_L1_BLOCKHASH=$(echo "$SOURCE_L1_CONF" | jq -r '.l1StartingBlockTag')
+  EXP_BATCHER=$(echo "$SOURCE_L1_CONF" | jq -r '.batchSenderAddress')
+
+  GEN_L2_CONF=$(cat /app/rollup.json)
+  GEN_L1_BLOCKHASH=$(echo "$GEN_L2_CONF" | jq -r '.genesis.l1.hash')
+  GEN_BATCHER=$(echo "$GEN_L2_CONF" | jq -r '.genesis.system_config.batcherAddr')
+
+  if [ "$EXP_L1_BLOCKHASH" = "$GEN_L1_BLOCKHASH" ] && [ "$EXP_BATCHER" = "$GEN_BATCHER" ]; then
+    echo "Config cross-checked, exiting"
+    exit 0
+  fi
+
+  echo "Existing L2 config doesn't match the L1 deployment config, please clear L2 config volume before starting"
+  exit 1
+fi
+
 op-node genesis l2 \
   --deploy-config /contracts-bedrock/deploy-config/getting-started.json \
   --deployment-dir /contracts-bedrock/deployments/getting-started/ \

app/data/config/fixturenet-optimism/optimism-contracts/run.sh

@@ -4,22 +4,43 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
   set -x
 fi
 
-# TODO Support restarts; fixturenet-eth-geth currently starts fresh on a restart
-# Exit if a deployment already exists (on restarts)
-# if [ -d "deployments/getting-started" ]; then
-#     echo "Deployment directory deployments/getting-started already exists, exiting"
-#     exit 0
-# fi
-
 echo "Using L1 RPC endpoint ${L1_RPC}"
 
-# Append tasks/index.ts file
+IMPORT_1="import './verify-contract-deployment'"
-echo "import './rekey-json'" >> tasks/index.ts
+IMPORT_2="import './rekey-json'"
-echo "import './send-balance'" >> tasks/index.ts
+IMPORT_3="import './send-balance'"
+
+# Append mounted tasks to tasks/index.ts file if not present
+if ! grep -Fxq "$IMPORT_1" tasks/index.ts; then
+  echo "$IMPORT_1" >> tasks/index.ts
+  echo "$IMPORT_2" >> tasks/index.ts
+  echo "$IMPORT_3" >> tasks/index.ts
+fi
 
 # Update the chainId in the hardhat config
 sed -i "/getting-started/ {n; s/.*chainId.*/      chainId: $L1_CHAIN_ID,/}" hardhat.config.ts
 
+# Exit if a deployment already exists (on restarts)
+# Note: fixturenet-eth-geth currently starts fresh on a restart
+if [ -d "deployments/getting-started" ]; then
+  echo "Deployment directory deployments/getting-started found, checking SystemDictator deployment"
+
+  # Read JSON file into variable
+  SYSTEM_DICTATOR_DETAILS=$(cat deployments/getting-started/SystemDictator.json)
+
+  # Parse JSON into variables
+  SYSTEM_DICTATOR_ADDRESS=$(echo "$SYSTEM_DICTATOR_DETAILS" | jq -r '.address')
+  SYSTEM_DICTATOR_TXHASH=$(echo "$SYSTEM_DICTATOR_DETAILS" | jq -r '.transactionHash')
+
+  if yarn hardhat verify-contract-deployment --contract "${SYSTEM_DICTATOR_ADDRESS}" --transaction-hash "${SYSTEM_DICTATOR_TXHASH}"; then
+    echo "Deployment verfication successful, exiting"
+    exit 0
+  else
+    echo "Deployment verfication failed, please clear L1 deployment volume before starting"
+    exit 1
+  fi
+fi
+
 # Generate the L2 account addresses
 yarn hardhat rekey-json --output /l2-accounts/keys.json
 

app/data/config/fixturenet-optimism/run-op-geth.sh

@@ -4,16 +4,30 @@ if [ -n "$CERC_SCRIPT_DEBUG" ]; then
   set -x
 fi
 
-mkdir datadir
-
-echo "pwd" > datadir/password
-
 # TODO: Add in container build or use other tool
-echo "installing jq"
+echo "Installing jq"
 apk update && apk add jq
 
-# Get SEQUENCER KEY from keys.json
+# Get SEQUENCER key from keys.json
 SEQUENCER_KEY=$(jq -r '.Sequencer.privateKey' /l2-accounts/keys.json | tr -d '"')
+
+# Initialize op-geth if datadir/geth not found
+if [ -f /op-node/jwt.txt ] && [ -d datadir/geth ]; then
+  echo "Found existing datadir, checking block signer key"
+
+  BLOCK_SIGNER_KEY=$(cat datadir/block-signer-key)
+
+  if [ "$SEQUENCER_KEY" = "$BLOCK_SIGNER_KEY" ]; then
+    echo "Sequencer and block signer keys match, skipping initialization"
+  else
+    echo "Sequencer and block signer keys don't match, please clear L2 geth data volume before starting"
+    exit 1
+  fi
+else
+  echo "Initializing op-geth"
+
+  mkdir -p datadir
+  echo "pwd" > datadir/password
   echo $SEQUENCER_KEY > datadir/block-signer-key
 
   geth account import --datadir=datadir --password=datadir/password datadir/block-signer-key
@@ -24,14 +38,16 @@ do
     sleep 5
   done
 
-echo "Config files created by op-node, proceeding with script..."
+  echo "Config files created by op-node, proceeding with the initialization..."
 
-cp /op-node/genesis.json ./
+  geth init --datadir=datadir /op-node/genesis.json
-geth init --datadir=datadir genesis.json
+  echo "Node Initialized"
+fi
 
 SEQUENCER_ADDRESS=$(jq -r '.Sequencer.address' /l2-accounts/keys.json | tr -d '"')
 echo "SEQUENCER_ADDRESS: ${SEQUENCER_ADDRESS}"
-cp /op-node/jwt.txt ./
+
+# Run op-geth
 geth \
   --datadir ./datadir \
   --http \
@@ -52,7 +68,7 @@ geth \
   --authrpc.vhosts="*" \
   --authrpc.addr=0.0.0.0 \
   --authrpc.port=8551 \
-  --authrpc.jwtsecret=./jwt.txt \
+  --authrpc.jwtsecret=/op-node/jwt.txt \
   --rollup.disabletxpoolgossip=true \
   --password=./datadir/password \
   --allow-insecure-unlock \

app/data/container-build/cerc-optimism-contracts/hardhat-tasks/verify-contract-deployment.ts

@@ -0,0 +1,30 @@
+import { task } from 'hardhat/config'
+import '@nomiclabs/hardhat-ethers'
+
+task(
+  'verify-contract-deployment',
+  'Verifies the given contract deployment transaction'
+)
+  .addParam('contract', 'Address of the contract deployed')
+  .addParam('transactionHash', 'Hash of the deployment transaction')
+  .setAction(async ({ contract, transactionHash }, { ethers }) => {
+    const provider = new ethers.providers.JsonRpcProvider(
+      `${process.env.L1_RPC}`
+    )
+
+    // Get the deployment tx receipt
+    const receipt = await provider.getTransactionReceipt(transactionHash)
+    if (
+      receipt &&
+      receipt.contractAddress &&
+      receipt.contractAddress === contract
+    ) {
+      console.log(
+        `Deployment for contract ${contract} in transaction ${transactionHash} verified`
+      )
+      process.exit(0)
+    } else {
+      console.log(`Contract ${contract} deployment verification failed`)
+      process.exit(1)
+    }
+  })

app/data/stacks/fixturenet-optimism/L2-ONLY.md

@@ -0,0 +1,87 @@
+# fixturenet-optimism
+
+Instructions to setup and deploy L2 fixturenet using [Optimism](https://stack.optimism.io)
+
+## Setup
+
+Prerequisite: An L1 Ethereum RPC endpoint
+
+Clone required repositories:
+
+```bash
+laconic-so --stack fixturenet-optimism setup-repositories --exclude cerc-io/go-ethereum
+```
+
+Checkout to the required versions and branches in repos:
+
+```bash
+# Optimism
+cd ~/cerc/optimism
+git checkout @eth-optimism/sdk@0.0.0-20230329025055
+```
+
+Build the container images:
+
+```bash
+laconic-so --stack fixturenet-optimism build-containers --include cerc/foundry,cerc/optimism-contracts,cerc/optimism-op-node,cerc/optimism-l2geth,cerc/optimism-op-batcher
+```
+
+This should create the required docker images in the local image registry:
+* `cerc/foundry`
+* `cerc/optimism-contracts`
+* `cerc/optimism-l2geth`
+* `cerc/optimism-op-batcher`
+* `cerc/optimism-op-node`
+
+## Deploy
+
+Update the [l1-params.env](../../config/fixturenet-optimism/l1-params.env) file with L1 endpoint (`L1_RPC`, `L1_HOST` and `L1_PORT`) and other params
+
+* NOTE:
+  * Stack Orchestrator needs to be run in [`dev`](/docs/CONTRIBUTING.md#install-developer-mode) mode to be able to edit the env file
+  * If L1 is running on the host machine, use `host.docker.internal` as the hostname to access the host port
+
+Deploy the stack:
+
+```bash
+laconic-so --stack fixturenet-optimism deploy up --include fixturenet-optimism
+```
+
+The `fixturenet-optimism-contracts` service may take a while (`~15 mins`) to complete running as it:
+1. waits for the 'Merge' to happen on L1
+2. waits for a finalized block to exist on L1 (so that it can be taken as a starting block for roll ups)
+3. deploys the L1 contracts
+
+To list down and monitor the running containers:
+
+```bash
+laconic-so --stack fixturenet-optimism deploy ps
+
+# With status
+docker ps
+
+# Check logs for a container
+docker logs -f <CONTAINER_ID>
+```
+
+## Clean up
+
+Stop all services running in the background:
+
+```bash
+laconic-so --stack fixturenet-optimism deploy down --include fixturenet-optimism
+```
+
+Clear volumes created by this stack:
+
+```bash
+# List all relevant volumes
+docker volume ls -q --filter name=laconic*
+
+# Remove all the listed volumes
+docker volume rm $(docker volume ls -q --filter name=laconic*)
+```
+
+## Troubleshooting
+
+See [Troubleshooting](./README.md#troubleshooting)

app/data/stacks/fixturenet-optimism/README.md

@@ -2,15 +2,14 @@
 
 Instructions to setup and deploy an end-to-end L1+L2 stack with [fixturenet-eth](../fixturenet-eth/) (L1) and [Optimism](https://stack.optimism.io) (L2)
 
+We support running just the L2 part of stack, given an external L1 endpoint. Follow [L2-ONLY](./L2-ONLY.md) for the same.
+
 ## Setup
 
 Clone required repositories:
 
 ```bash
 laconic-so --stack fixturenet-optimism setup-repositories
-
-# Exclude cerc-io/go-ethereum repository if running L1 separately
-laconic-so --stack fixturenet-optimism setup-repositories --exclude cerc-io/go-ethereum
 ```
 
 Checkout to the required versions and branches in repos:
@@ -25,9 +24,6 @@ Build the container images:
 
 ```bash
 laconic-so --stack fixturenet-optimism build-containers
-
-# Only build containers required for L2 if running L1 separately
-laconic-so --stack fixturenet-optimism build-containers --include cerc/foundry,cerc/optimism-contracts,cerc/optimism-op-node,cerc/optimism-l2geth,cerc/optimism-op-batcher
 ```
 
 This should create the required docker images in the local image registry:
@@ -43,19 +39,10 @@ This should create the required docker images in the local image registry:
 
 ## Deploy
 
-(Optional) Update the [l1-params.env](../../config/fixturenet-optimism/l1-params.env) file with L1 endpoint (`L1_RPC`, `L1_HOST` and `L1_PORT`) and other params if running L1 separately
-
-* NOTE:
-  * Stack Orchestrator needs to be run in [`dev`](/docs/CONTRIBUTING.md#install-developer-mode) mode to be able to edit the env file
-  * If L1 is running on the host machine, use `host.docker.internal` as the hostname to access the host port
-
 Deploy the stack:
 
 ```bash
 laconic-so --stack fixturenet-optimism deploy up
-
-# Only start fixturenet-optimism pod (L2) if running L1 separately
-laconic-so --stack fixturenet-optimism deploy up --include fixturenet-optimism
 ```
 
 The `fixturenet-optimism-contracts` service may take a while (`~15 mins`) to complete running as it:
@@ -81,9 +68,6 @@ Stop all services running in the background:
 
 ```bash
 laconic-so --stack fixturenet-optimism deploy down
-
-# If only ran fixturenet-optimism pod (L2)
-laconic-so --stack fixturenet-optimism deploy down --include fixturenet-optimism
 ```
 
 Clear volumes created by this stack:
@@ -96,9 +80,39 @@ docker volume ls -q --filter name=laconic*
 docker volume rm $(docker volume ls -q --filter name=laconic*)
 ```
 
+## Troubleshooting
+
+* If `op-geth` service aborts or is restarted, the following error might occur in the `op-node` service:
+
+  ```bash
+  WARN [02-16|21:22:02.868] Derivation process temporary error       attempts=14 err="stage 0 failed resetting: temp: failed to find the L2 Heads to start from: failed to fetch L2 block by hash 0x0000000000000000000000000000000000000000000000000000000000000000: failed to determine block-hash of hash 0x0000000000000000000000000000000000000000000000000000000000000000, could not get payload: not found"
+  ```
+
+* This means that the data directory that `op-geth` is using is corrupted and needs to be reinitialized; the containers `op-geth`, `op-node` and `op-batcher` need to be started afresh:
+  * Stop and remove the concerned containers:
+
+    ```bash
+    # List the containers
+    docker ps -f "name=op-geth|op-node|op-batcher"
+
+    # Force stop and remove the listed containers
+    docker rm -f $(docker ps -qf "name=op-geth|op-node|op-batcher")
+    ```
+
+  * Remove the concerned volume:
+
+    ```bash
+    # List the volume
+    docker volume ls -q --filter name=l2_geth_data
+
+    # Remove the listed volume
+    docker volume rm $(docker volume ls -q --filter name=l2_geth_data)
+    ```
+
+  * Reuse the deployment command used in [Deploy](#deploy) to restart the stopped containers
+
 ## Known Issues
 
-* Currently not supported:
+* `fixturenet-eth` currently starts fresh on a restart
-  * Stopping and restarting the stack from where it left off; currently starts fresh on a restart
+* Resource requirements (memory + time) for building the `cerc/foundry` image are on the higher side
-* Resource requirements (memory + time) for building `cerc/foundry` image are on the higher side
   * `cerc/optimism-contracts` image is currently based on `cerc/foundry` (Optimism requires foundry installation)