Merge pull request #2 from ritual-net/dev

Major release 1.0.0

Author: arshan-ritual

.github/workflows/pr.yaml

@@ -18,6 +18,12 @@ jobs:
       with:
         extra_args: --all-files --show-diff-on-failure
 
+    - name: Run Format (AWS)
+      run: cd procure/aws && terraform fmt -check
+
+    - name: Run Format (GCP)
+      run: cd procure/gcp && terraform fmt -check
+
     - name: Setup TFLint
       uses: terraform-linters/setup-tflint@v3
       with:

CHANGELOG.md

@@ -0,0 +1,30 @@
+# Changelog
+
+All notable changes to this project will be documented in this file.
+
+- ##### The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
+- ##### This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+
+## [1.0.0] - UNRELEASED
+
+### Added
+- Support for multi-region, multi-zone deployments in GCP.
+- Support for multi-zone deployments in AWS. Since multi-region deployments require
+separate provider blocks, we don't allow multiple regions to avoid increased repo complexity.
+- Support for GPUs on GCP (via the terraform `accelerator` block) and AWS. Includes driver installation script
+and a gpu-specific `docker-compose.yaml` file to expose GPUs to the node container for diagnostics.
+- Terraform formatter in pipeline and README.
+
+### Changed
+- Format of node specification in `.tfvars`. Nodes are now specified via a map (see `variables.tf`) where keys correspond to node IDs.
+- Format of router specification in `.tfvars`. Router is now specified via a map (see `variables.tf`).
+- Naming conventions for configuration `.json` files. One file per deployed node, names (without `.json` postfix) matching the node IDs (keys of `nodes` from `variables.tf`), are now the only requirements.
+
+### Fixed
+- All created resources are now parametrized by cluster name, so no conflicts arise from successive deployments within the same project.
+- Omissions in Makefile.
+
+## [0.1.0] - 2024-01-18
+
+### Added
+- Initial release of Infernet Deploy.

README.md

@@ -7,13 +7,14 @@ Deploy a cluster of heterogenous [Infernet](https://github.com/ritual-net/infern
 1. [Install Terraform](https://developer.hashicorp.com/terraform/install)
 2. **Configure nodes**: A node configuration file **for each** node being deployed.
     - See [example configuration](configs/0.json.example).
-    - They must be named `0.json`, `1.json`, etc...
-        - Misnamed files are ignored.
+    - They must have **unique** names
+        - A straightforward approach would be `0.json`, `1.json`, etc...
     - They must be placed under the top-level `configs/` directory.
+    - Number and name of `.json` files must match the number and name of *keys* in the `nodes` variable in `terraform.tfvars`.
+        - See [terraform.tfvars.example](./procure/aws/terraform.tfvars.example).
+        - Each key should correspond to the name of a `.json` file, *excluding* the `.json` postfix.
     - Each node *strictly* requires its own configuration `.json` file, even if those are identical.
-    - Number of `.json` files must match the `node_count` variable in `terraform.tfvars`.
-        - Extra files are ignored.
-    - For instructions on configuring nodes, refer to the [Infernet Node](https://github.com/ritual-net/infernet-node).
+    - For instructions on configuring individual nodes, refer to the [Infernet Node](https://github.com/ritual-net/infernet-node).
 
 #### Infernet Router:
 The Infernet Router REST server is configured automatically by Terraform. However, if you plan to use it, you need to understand its implications:
@@ -106,6 +107,17 @@ tflint --init
 tflint --recursive
 ```
 
+### Using Terraform Format
+```bash
+# Format AWS files
+cd procure/aws
+terraform fmt
+
+# Format GCP files
+cd procure/gcp
+terraform fmt
+```
+
 ## License
 
 [BSD 3-clause Clear](./LICENSE)

configs/0.json.example

@@ -6,19 +6,24 @@
   "chain": {
     "enabled": true,
     "rpc_url": "http://127.0.0.1:8545",
-    "coordinator_address": "0x...",
     "trail_head_blocks": 4,
     "wallet": {
       "max_gas_limit": 100000,
-      "private_key": "12345s"
+      "private_key": "12345s",
+      "payment_address": "0x...",
+      "allowed_sim_errors": []
+    },
+    "snapshot_sync": {
+      "sleep": 1.5,
+      "batch_size": 200
     }
   },
   "docker": {
     "username": "username",
     "password": "password"
   },
   "redis": {
-    "host": "localhost",
+    "host": "redis",
     "port": 6379
   },
   "forward_stats": true,
@@ -40,7 +45,12 @@
         "KEY1": "VALUE1",
         "KEY2": "VALUE2"
       },
-      "gpu": true
+      "gpu": false,
+      "accepted_payments": {
+        "0x0000000000000000000000000000000000000000": 1000000000000000000,
+        "0x59F2f1fCfE2474fD5F0b9BA1E73ca90b143Eb8d0": 1000000000000000000
+      },
+      "generates_proofs": true
     },
     {
       "id": "container-2",
@@ -58,7 +68,13 @@
       "env": {
         "KEY3": "VALUE3",
         "KEY4": "VALUE4"
-      }
+      },
+      "gpu": true,
+      "accepted_payments": {
+        "0x0000000000000000000000000000000000000000": 1000000000000000000,
+        "0x59F2f1fCfE2474fD5F0b9BA1E73ca90b143Eb8d0": 1000000000000000000
+      },
+      "generates_proofs": false
     }
   ]
 }

deploy/docker-compose-gpu.yaml

@@ -0,0 +1,62 @@
+version: '3'
+
+services:
+  node:
+    image: ritualnetwork/infernet-node:latest-gpu
+    ports:
+      - "0.0.0.0:4000:4000"
+    volumes:
+      - ./config.json:/app/config.json
+      - node-logs:/logs
+      - /var/run/docker.sock:/var/run/docker.sock
+    tty: true
+    networks:
+      - network
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: all
+            capabilities: [gpu]
+    depends_on:
+      - redis
+    restart:
+      on-failure
+    extra_hosts:
+      - "host.docker.internal:host-gateway"
+    stop_grace_period: 1m
+
+  redis:
+    image: redis:latest
+    expose:
+      - "6379"
+    networks:
+      - network
+    volumes:
+      - ./redis.conf:/usr/local/etc/redis/redis.conf
+      - redis-data:/data
+    restart:
+      on-failure
+
+  fluentbit:
+    image: fluent/fluent-bit:latest
+    expose:
+      - "24224"
+    environment:
+      - FLUENTBIT_CONFIG_PATH=/fluent-bit/etc/fluent-bit.conf
+    volumes:
+      - ./fluent-bit.conf:/fluent-bit/etc/fluent-bit.conf
+      - /var/log:/var/log:ro
+    networks:
+      - network
+    restart:
+      on-failure
+
+networks:
+  network:
+
+
+volumes:
+  node-logs:
+  redis-data:

deploy/docker-compose.yaml

@@ -2,29 +2,28 @@ version: '3'
 
 services:
   node:
-    image: ritualnetwork/infernet-node:0.1.0
+    image: ritualnetwork/infernet-node:latest
     ports:
       - "0.0.0.0:4000:4000"
     volumes:
-      - type: bind
-        source: ./config.json
-        target: /app/config.json
+      - ./config.json:/app/config.json
       - node-logs:/logs
       - /var/run/docker.sock:/var/run/docker.sock
+    tty: true
     networks:
       - network
-    restart:
-      on-failure
     depends_on:
       - redis
+    restart:
+      on-failure
     extra_hosts:
       - "host.docker.internal:host-gateway"
     stop_grace_period: 1m
 
   redis:
     image: redis:latest
-    ports:
-      - "6379:6379"
+    expose:
+      - "6379"
     networks:
       - network
     volumes:
@@ -35,8 +34,8 @@ services:
 
   fluentbit:
     image: fluent/fluent-bit:latest
-    ports:
-      - "24224:24224"
+    expose:
+      - "24224"
     environment:
       - FLUENTBIT_CONFIG_PATH=/fluent-bit/etc/fluent-bit.conf
     volumes:

procure/Makefile

@@ -1,3 +1,5 @@
+SHELL := /bin/bash
+
 # Define the Terraform command
 TERRAFORM_CMD := terraform
 
@@ -21,6 +23,9 @@ init: check-provider
 
 # Define the plan target
 plan: check-provider
+	@echo "Preparing deployment files..."
+	@chmod +x prepare_files.sh
+	@./prepare_files.sh
 	@echo "Generating Terraform plan..."
 	$(TERRAFORM_CMD) -chdir=$(provider) plan
 
@@ -33,7 +38,6 @@ apply: check-provider
 	@$(TERRAFORM_CMD) -chdir=$(provider) apply
 
 # Define the destroy target
-destroy:
-	@[[ "$(provider)" == "aws" || "$(provider)" == "gcp" ]] || (echo "Usage: 'make destroy provider={aws, gcp}'" && exit 1)
+destroy: check-provider
 	@echo "Destroying Terraform resources..."
 	@$(TERRAFORM_CMD) -chdir=$(provider) destroy

procure/aws/main.tf

@@ -16,5 +16,5 @@ terraform {
 provider "aws" {
   access_key = var.access_key_id
   secret_key = var.secret_access_key
-  region = var.region
+  region     = var.region
 }

procure/aws/metadata.tf

@@ -1,22 +1,24 @@
 # Config files as secrets
 resource "aws_ssm_parameter" "config_file" {
-  count = var.node_count
+  for_each = var.nodes
 
-  name  = "config_${count.index}"
+  name  = "${each.key}.json"
   type  = "SecureString"
-  value = filebase64("${path.module}/../../configs/${count.index}.json")
+  value = filebase64("${path.module}/../../configs/${each.key}.json")
 }
 
 # Deployment files
 resource "aws_ssm_parameter" "deploy_tar" {
-  name  = "deploy_tar"
+  for_each = var.nodes
+
+  name  = "deploy-tar-${each.key}"
   type  = "SecureString"
-  value = filebase64("${path.module}/../deploy.tar.gz")
+  value = each.value.has_gpu ? filebase64("${path.module}/../deploy-gpu.tar.gz") : filebase64("${path.module}/../deploy.tar.gz")
 }
 
 # Node IPs
 resource "aws_ssm_parameter" "node_ips" {
-  name  = "node_ips"
+  name  = "node-ips-${var.name}"
   type  = "String"
-  value = join("\n", [for ip in aws_eip.static_ip[*].public_ip : "${ip}:4000"])
+  value = join("\n", [for key, _ in aws_instance.nodes : "${aws_eip.static_ip[key].public_ip}:4000"])
 }