Merge pull request #138 from planetary-social/groups_relay

Playbook for groups_relay

inventories/groups_relay/README.md

@@ -0,0 +1,3 @@
+# groups_relay Inventory
+
+Hosts running our Nip 29 relay.  Meant to be used with the `groups_relay` role.

inventories/groups_relay/inventory.yml

@@ -0,0 +1,19 @@
+---
+groups_relay:
+  hosts:
+    communities.nos.social:
+      groups_relay_image_tag: stable
+    communities2.nos.social:
+      groups_relay_image_tag: latest
+  vars:
+    admin_username: admin
+    ansible_user: '{{ admin_username }}'
+    homedir: /home/{{ admin_username }}
+    cert_email: [email protected]
+    domain: '{{ inventory_hostname }}'
+    groups_relay_image: ghcr.io/verse-pbc/groups_relay
+    groups_relay_health_endpoint: https://{{ inventory_hostname }}/health
+prod:
+  hosts:
+    communities.nos.social:
+    communities2.nos.social:

new-server-vars.yml

@@ -219,3 +219,25 @@
 # inv:  relay
 # inv_groups:
 # - relay
+
+#-----------------------------
+# Groups Relay example
+# ansible-playbook -i inventories/groups_relay/inventory.yml playbooks/new-do-droplet.yml -e '@new-server-vars.yml'
+#-----------------------------
+domain: communities2.nos.social
+do_droplet_size: s-1vcpu-1gb
+do_droplet_image: ubuntu-22-04-x64
+do_droplet_region: NYC3
+do_droplet_project: Nos
+do_droplet_tags:
+- prod
+gh_user_keys_to_add:
+- mplorentz
+- dcadenas
+- nbenmoody
+inv: groups_relay
+inv_groups:
+- groups_relay
+- prod
+additional_roles:
+- groups_relay

playbooks/groups_relay.yml

@@ -0,0 +1,8 @@
+- name: Install new server for groups_relay
+  hosts: groups_relay:&prod
+  vars:
+    ansible_user: admin
+    domain: "{{ inventory_hostname }}"
+  roles:
+    - groups_relay
+

roles/groups_relay/README.md

@@ -0,0 +1,31 @@
+# groups_relay role
+
+This role sets up a Nostr groups relay server using strfry as the backend relay. It's designed to handle NIP-29 group messages.
+
+## Architecture
+
+The role deploys two main services:
+1. `groups_relay` - A specialized relay that handles NIP-29 group messages
+2. `strfry` - A lightweight Nostr relay that serves as the backend storage
+
+## Variables
+
+| Variable                     | Example                                    | Purpose                                    |
+|-----------------------------|--------------------------------------------|--------------------------------------------|
+| domain                      | communities.nos.social                      | The FQDN of the service                    |
+| cert_email                  | [email protected]                        | The email used for LetsEncrypt certificate |
+| groups_relay_image          | ghcr.io/verse-pbc/groups_relay             | The Docker image name                      |
+| groups_relay_image_tag      | stable                                     | The Docker image tag                       |
+| groups_relay_health_endpoint| https://{{ inventory_hostname }}/health    | Health check endpoint                      |
+
+## Dependencies
+
+The role depends on:
+- common
+- digital-ocean
+- docker
+- traefik
+
+## Network Configuration
+
+The service exposes the groups relay on port 8080 through Traefik, while strfry runs internally and is not exposed to the internet. All traffic is routed through the `proxy` network managed by Traefik.

roles/groups_relay/files/settings.yml

@@ -0,0 +1,8 @@
+# Default relay configuration
+relay:
+  # Relay secret key (hex format)
+  # This is a test key, replace with your own in settings.local.yml
+  relay_secret_key: "6b911fd37cdf5c81d4c0adb1ab7fa822ed253ab0ad9aa18d77257c88b29b718e"
+  local_addr: "0.0.0.0:8080"
+  auth_url: "ws://localhost:8080"
+  relay_url: "ws://localhost:8080"

roles/groups_relay/files/strfry.conf

@@ -0,0 +1,144 @@
+##
+## Default strfry config
+##
+
+# Directory that contains the strfry LMDB database (restart required)
+db = "/strfry/data"
+
+dbParams {
+    # Maximum number of threads/processes that can simultaneously have LMDB transactions open (restart required)
+    maxreaders = 256
+
+    # Size of mmap() to use when loading LMDB (default is 10TB, does *not* correspond to disk-space used) (restart required)
+    mapsize = 10995116277760
+
+    # Disables read-ahead when accessing the LMDB mapping. Reduces IO activity when DB size is larger than RAM. (restart required)
+    noReadAhead = false
+}
+
+events {
+    # Maximum size of normalised JSON, in bytes
+    maxEventSize = 65536
+
+    # Events newer than this will be rejected
+    rejectEventsNewerThanSeconds = 900
+
+    # Events older than this will be rejected
+    rejectEventsOlderThanSeconds = 94608000
+
+    # Ephemeral events older than this will be rejected
+    rejectEphemeralEventsOlderThanSeconds = 60
+
+    # Ephemeral events will be deleted from the DB when older than this
+    ephemeralEventsLifetimeSeconds = 300
+
+    # Maximum number of tags allowed
+    maxNumTags = 2000
+
+    # Maximum size for tag values, in bytes
+    maxTagValSize = 1024
+}
+
+relay {
+    # Interface to listen on. Use 0.0.0.0 to listen on all interfaces (restart required)
+    bind = "0.0.0.0"
+
+    # Port to open for the nostr websocket protocol (restart required)
+    port = 7777
+
+    # Set OS-limit on maximum number of open files/sockets (if 0, don't attempt to set) (restart required)
+    nofiles = 1000000
+
+    # HTTP header that contains the client's real IP, before reverse proxying (ie x-real-ip) (MUST be all lower-case)
+    realIpHeader = ""
+
+    info {
+        # NIP-11: Name of this server. Short/descriptive (< 30 characters)
+        name = "strfry default"
+
+        # NIP-11: Detailed information about relay, free-form
+        description = "This is a strfry instance."
+
+        # NIP-11: Administrative nostr pubkey, for contact purposes
+        pubkey = ""
+
+        # NIP-11: Alternative administrative contact (email, website, etc)
+        contact = ""
+
+        # NIP-11: URL pointing to an image to be used as an icon for the relay
+        icon = ""
+
+        # List of supported lists as JSON array, or empty string to use default. Example: "[1,2]"
+        nips = ""
+    }
+
+    # Maximum accepted incoming websocket frame size (should be larger than max event) (restart required)
+    maxWebsocketPayloadSize = 131072
+
+    # Websocket-level PING message frequency (should be less than any reverse proxy idle timeouts) (restart required)
+    autoPingSeconds = 55
+
+    # If TCP keep-alive should be enabled (detect dropped connections to upstream reverse proxy)
+    enableTcpKeepalive = false
+
+    # How much uninterrupted CPU time a REQ query should get during its DB scan
+    queryTimesliceBudgetMicroseconds = 10000
+
+    # Maximum records that can be returned per filter
+    maxFilterLimit = 500
+
+    # Maximum number of subscriptions (concurrent REQs) a connection can have open at any time
+    maxSubsPerConnection = 20
+
+    writePolicy {
+        # If non-empty, path to an executable script that implements the writePolicy plugin logic
+        plugin = ""
+    }
+
+    compression {
+        # Use permessage-deflate compression if supported by client. Reduces bandwidth, but slight increase in CPU (restart required)
+        enabled = true
+
+        # Maintain a sliding window buffer for each connection. Improves compression, but uses more memory (restart required)
+        slidingWindow = true
+    }
+
+    logging {
+        # Dump all incoming messages
+        dumpInAll = false
+
+        # Dump all incoming EVENT messages
+        dumpInEvents = false
+
+        # Dump all incoming REQ/CLOSE messages
+        dumpInReqs = false
+
+        # Log performance metrics for initial REQ database scans
+        dbScanPerf = false
+
+        # Log reason for invalid event rejection? Can be disabled to silence excessive logging
+        invalidEvents = true
+    }
+
+    numThreads {
+        # Ingester threads: route incoming requests, validate events/sigs (restart required)
+        ingester = 3
+
+        # reqWorker threads: Handle initial DB scan for events (restart required)
+        reqWorker = 3
+
+        # reqMonitor threads: Handle filtering of new events (restart required)
+        reqMonitor = 3
+
+        # negentropy threads: Handle negentropy protocol messages (restart required)
+        negentropy = 2
+    }
+
+    negentropy {
+        # Support negentropy protocol messages
+        enabled = true
+
+        # Maximum records that sync will process before returning an error
+        maxSyncEvents = 1000000
+    }
+}

roles/groups_relay/meta/main.yml

@@ -0,0 +1,6 @@
+---
+dependencies:
+  - role: common
+  - role: digital-ocean
+  - role: docker
+  - role: traefik

roles/groups_relay/tasks/main.yml

@@ -0,0 +1,86 @@
+---
+- name: Set groups_relay dir
+  ansible.builtin.set_fact:
+    groups_relay_dir: "{{ homedir }}/services/groups_relay"
+
+- name: Ensure services/groups_relay exists
+  ansible.builtin.file:
+    path: "{{ groups_relay_dir }}"
+    state: directory
+    mode: '0755'
+
+- name: Copy necessary template files to groups_relay dir
+  ansible.builtin.template:
+    src: "docker-compose.yml.tpl"
+    dest: "{{ groups_relay_dir }}/docker-compose.yml"
+    mode: 0644
+
+- name: UFW - Allow http/https/strfry connections
+  become: true
+  community.general.ufw:
+    rule: allow
+    port: "{{ item }}"
+    proto: tcp
+  loop:
+    - "80"
+    - "443"
+    - "7777"
+
+- name: Ensure cert directory exist
+  ansible.builtin.file:
+    path: "{{ groups_relay_dir }}/certs"
+    state: directory
+    mode: '0755'
+
+- name: Ensure config directory exist
+  ansible.builtin.file:
+    path: "{{ groups_relay_dir }}/config"
+    state: directory
+    mode: '0755'
+
+- name: Copy settings.production.yml to config dir
+  ansible.builtin.template:
+    src: settings.production.yml.tpl
+    dest: "{{ groups_relay_dir }}/config/settings.production.yml"
+    mode: '0644'
+
+- name: Copy strfry.conf to config dir
+  ansible.builtin.copy:
+    src: strfry.conf
+    dest: "{{ groups_relay_dir }}/config/strfry.conf"
+    mode: '0644'
+
+- name: Copy settings.yml to config dir
+  ansible.builtin.copy:
+    src: settings.yml
+    dest: "{{ groups_relay_dir }}/config/settings.yml"
+    mode: '0644'
+
+- name: ensure docker is running
+  ansible.builtin.service:
+    name: docker
+    state: started
+
+- name: Start up docker services
+  ansible.builtin.shell: "docker compose down && docker compose up -d"
+  args:
+    chdir: "{{ groups_relay_dir }}"
+  register: service_started
+  retries: 5
+  until: service_started is success
+
+- name: Setup the image updater
+  ansible.builtin.include_role:
+    name: image-update-service
+  vars:
+    service_name: groups_relay
+    service_image: "{{ groups_relay_image }}"
+    service_image_tag: "{{ groups_relay_image_tag }}"
+    frequency: 3m
+    working_dir: "{{ groups_relay_dir }}"
+
+- name: Setup the health check
+  ansible.builtin.include_role:
+    name: health-check
+  vars:
+    health_endpoint: "{{ groups_relay_health_endpoint }}"

roles/groups_relay/templates/docker-compose.yml.tpl

@@ -0,0 +1,29 @@
+services:
+  groups_relay:
+    container_name: groups_relay
+    image: "{{ groups_relay_image }}:{{ groups_relay_image_tag }}"
+    platform: linux/amd64
+    volumes:
+      - ./config:/app/config:ro
+      - db-data:/db/data
+    environment:
+      RUST_LOG: info
+      RUST_BACKTRACE: 1
+      NIP29__ENVIRONMENT: production
+    ports:
+      - "8080:8080"
+    labels:
+      - "traefik.enable=true"
+      - "traefik.http.routers.groups_relay.rule=Host(`{{ domain }}`)"
+      - "traefik.http.routers.groups_relay.entrypoints=websecure"
+      - "traefik.http.services.groups_relay.loadbalancer.server.port=8080"
+    restart: always
+    networks:
+      - proxy
+
+volumes:
+  db-data:
+
+networks:
+  proxy:
+    external: true

roles/groups_relay/templates/settings.production.yml.tpl

@@ -0,0 +1,3 @@
+relay:
+  auth_url: "wss://{{ inventory_hostname }}"
+  db_path: "/db/data"