Create new VMs with Ubuntu 24.04

AGENTS.md

@@ -0,0 +1,41 @@
+# AGENTS.md
+
+Welcome, AI Agent! This file contains essential context and rules for interacting with the Kosmos Chef repository. Read this carefully before planning or executing any changes.
+
+## 🏢 Project Overview
+This repository contains the infrastructure automation code used by Kosmos to provision and configure bare metal servers (KVM hosts) and Ubuntu virtual machines (KVM guests). 
+
+We use **Chef Infra**, managed locally via **Knife Zero** (agentless Chef), and **Berkshelf** for dependency management.
+
+## 📂 Directory Structure & Rules
+
+* **`site-cookbooks/`**: 🟢 **EDITABLE.** This directory contains all custom, internal cookbooks written specifically for Kosmos services (e.g., `kosmos-postgresql`, `kosmos_gitea`, `kosmos-mastodon`). *Active development happens here.*
+* **`cookbooks/`**: 🔴 **DO NOT EDIT.** This directory contains third-party/community cookbooks that are vendored. These are managed by Berkshelf. Modifying them directly will result in lost changes.
+* **`roles/`**: 🟢 **EDITABLE.** Contains Chef roles written in Ruby (e.g., `base.rb`, `kvm_guest.rb`, `postgresql_primary.rb`). These define run-lists and role-specific default attributes for servers.
+* **`environments/`**: Contains Chef environment definitions (like `production.rb`).
+* **`data_bags/`**: Contains data bag configurations, often encrypted. Be cautious and do not expose secrets. (Note: Agents should not manage data bag secrets directly unless provided the `.chef/encrypted_data_bag_secret`).
+* **`nodes/`**: Contains JSON state files for bootstrapped nodes. *Agents typically do not edit these directly unless cleaning up a deleted node.*
+* **`Berksfile`**: Defines community cookbook dependencies.
+* **`Vagrantfile` / `.kitchen/`**: Used for local virtualization and integration testing.
+
+## 🛠️ Tooling & Workflows
+
+1. **Dependency Management (Berkshelf)**
+   If a new community cookbook is required:
+   - Add it to the `Berksfile` at the root.
+   - Instruct the user to run `berks install` and `berks vendor cookbooks/ --delete` (or run it via the `bash` tool if permitted).
+
+2. **Provisioning (Knife Zero)**
+   - Bootstrapping and converging nodes is done using `knife zero`. 
+   - *Example:* `knife zero converge name:server-name.kosmos.org`
+
+3. **Code Style & Conventions**
+   - Chef recipes, resources, and roles are written in **Ruby**. 
+   - Follow standard Chef and Ruby (RuboCop) idioms. Look at neighboring files in `site-cookbooks/` or `roles/` to match formatting and naming conventions.
+
+## 🚨 Core Directives for AI Agents
+
+1. **Infrastructure as Code**: Manual server configurations are highly discouraged. All changes must be codified in a cookbook or role.
+2. **Test Safety Nets**: Look for `.kitchen.yml` within specific `site-cookbooks/<name>` to understand if local integration tests are available.
+3. **No Assumptions**: Do not assume standard test commands. Check `README.md` and repository config files first.
+4. **Secret Handling**: Avoid hardcoding passwords or API keys in recipes or roles. Assume sensitive information is managed via Chef `data_bags`.

roles/postgresql_replica_logical.rb

@@ -1,7 +0,0 @@
-name "postgresql_replica_logical"
-
-run_list %w(
-  kosmos_postgresql::hostsfile
-  kosmos_postgresql::replica_logical
-  kosmos_postgresql::firewall
-)

site-cookbooks/kosmos-base/recipes/default.rb

@@ -26,9 +26,9 @@
 
 include_recipe 'apt'
 include_recipe 'timezone_iii'
-include_recipe 'ntp'
 include_recipe 'kosmos-base::journald_conf'
 include_recipe 'kosmos-base::systemd_emails'
+include_recipe "ntp" if node["platform"] == "ubuntu" && node["platform_version"].to_f < 24.04
 
 node.override["apt"]["unattended_upgrades"]["enable"] = true
 node.override["apt"]["unattended_upgrades"]["mail_only_on_error"] = false

site-cookbooks/kosmos_kvm/attributes/default.rb

@@ -1,9 +1,9 @@
-release = "20260320"
-img_filename = "ubuntu-22.04-server-cloudimg-amd64-disk-kvm"
+release = "20260321"
+img_filename = "ubuntu-24.04-server-cloudimg-amd64"
 
 node.default["kosmos_kvm"]["host"]["qemu_base_image"] = {
-  "url" => "https://cloud-images.ubuntu.com/releases/jammy/release-#{release}/#{img_filename}.img",
-  "checksum" => "f7173eb7137b4f0ebeaea8fffe68ecdab1e3c787bde1fd8dfdf27103554332b3",
+  "url" => "https://cloud-images.ubuntu.com/releases/noble/release-#{release}/#{img_filename}.img",
+  "checksum" => "5c3ddb00f60bc455dac0862fabe9d8bacec46c33ac1751143c5c3683404b110d",
   "path" => "/var/lib/libvirt/images/base/#{img_filename}-#{release}.qcow2"
 }
 

site-cookbooks/kosmos_kvm/templates/create_vm.erb

@@ -70,7 +70,7 @@ virt-install \
   --vcpus "$CPUS" \
   --cpu host \
   --arch x86_64 \
-  --osinfo detect=on,name=ubuntujammy \
+  --osinfo detect=on,name=ubuntu24.04 \
   --hvm \
   --virt-type kvm \
   --disk "$IMAGE_PATH" \

site-cookbooks/kosmos_postgresql/attributes/default.rb

@@ -1,8 +1,3 @@
-node.default['kosmos_postgresql']['postgresql_version'] = "14"
-
 # This is set to false by default, and set to true in the server resource
 # for replicas.
 node.default['kosmos_postgresql']['ready_to_set_up_replica'] = false
-
-# Address space from which clients are allowed to connect
-node.default['kosmos_postgresql']['access_addr'] = "10.1.1.0/24"

site-cookbooks/kosmos_postgresql/files/create_publications.sh

@@ -1,34 +0,0 @@
-#!/bin/bash
-set -e
-
-echo "== Creating publication in each database =="
-
-for db in $(psql -Atqc "SELECT datname FROM pg_database WHERE datallowconn AND datname NOT IN ('template0','template1')"); do
-  echo "Processing DB: $db"
-
-  # Create publication (idempotent)
-  psql -d "$db" -v ON_ERROR_STOP=1 <<SQL
-DO \$\$
-BEGIN
-  IF NOT EXISTS (
-    SELECT 1 FROM pg_publication WHERE pubname = 'migrate_pub'
-  ) THEN
-    CREATE PUBLICATION migrate_pub FOR ALL TABLES;
-  END IF;
-END
-\$\$;
-SQL
-
-  # Create logical replication slot (idempotent-ish)
-  SLOT="migrate_slot_${db}"
-
-  if ! psql -d "$db" -Atqc "SELECT 1 FROM pg_replication_slots WHERE slot_name = '$SLOT'" | grep -q 1; then
-    echo "  Creating slot: $SLOT"
-    psql -d "$db" -c "SELECT pg_create_logical_replication_slot('$SLOT', 'pgoutput');"
-  else
-    echo "  Slot already exists: $SLOT"
-  fi
-
-done
-
-echo "== Done =="

site-cookbooks/kosmos_postgresql/files/drop_publications.sh

@@ -1,33 +0,0 @@
-set -e
-
-echo "== Dropping subscriptions slots and publications on PRIMARY =="
-
-for db in $(psql -Atqc "SELECT datname FROM pg_database WHERE datallowconn AND datname NOT IN ('template0','template1')"); do
-  echo "Processing DB: $db"
-
-  SLOT="migrate_slot_${db}"
-
-  # Drop slot if exists
-  if psql -d "$db" -Atqc "SELECT 1 FROM pg_replication_slots WHERE slot_name = '$SLOT'" | grep -q 1; then
-    echo "  Dropping slot: $SLOT"
-    psql -d "$db" -c "SELECT pg_drop_replication_slot('$SLOT');"
-  else
-    echo "  Slot not found: $SLOT"
-  fi
-
-  # Drop publication if exists
-  psql -d "$db" -v ON_ERROR_STOP=1 <<SQL
-DO \$\$
-BEGIN
-  IF EXISTS (
-    SELECT 1 FROM pg_publication WHERE pubname = 'migrate_pub'
-  ) THEN
-    DROP PUBLICATION migrate_pub;
-  END IF;
-END
-\$\$;
-SQL
-
-done
-
-echo "== Done =="

site-cookbooks/kosmos_postgresql/files/drop_subscriptions.sh

@@ -1,28 +0,0 @@
-set -e
-
-echo "== Dropping subscriptions on PG14 =="
-
-for db in $(psql -Atqc "SELECT datname FROM pg_database WHERE datallowconn AND datname NOT IN ('template0,'template1'')"); do
-  echo "Processing DB: $db"
-
-  SUB="migrate_sub_${db}"
-
-  # Disable first (important)
-  psql -d "$db" -c "ALTER SUBSCRIPTION $SUB DISABLE;" 2>/dev/null || true
-
-  # Drop subscription if exists
-  psql -d "$db" -v ON_ERROR_STOP=1 <<SQL
-DO \$\$
-BEGIN
-  IF EXISTS (
-    SELECT 1 FROM pg_subscription WHERE subname = '$SUB'
-  ) THEN
-    DROP SUBSCRIPTION $SUB;
-  END IF;
-END
-\$\$;
-SQL
-
-done
-
-echo "== Done =="

site-cookbooks/kosmos_postgresql/files/dump_all_databases.sh

@@ -1,9 +0,0 @@
-#!/bin/bash
-cd /tmp && \
-(pg_dumpall --globals-only > globals.sql) && \
-psql -Atqc "SELECT datname FROM pg_database WHERE datallowconn AND datname NOT IN (''template0'')" | \
-xargs -I{} -P4 sh -c "
-  pg_dump -Fd -j 4 -d \"{}\" -f dump_{} &&
-  tar -cf - dump_{} | zstd -19 -T0 > dump_{}.tar.zst &&
-  rm -rf dump_{}
-"

site-cookbooks/kosmos_postgresql/files/list_publications.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-for db in $(psql -Atqc "SELECT datname FROM pg_database WHERE datallowconn"); do
-  echo "DB: $db"
-  psql -d "$db" -Atqc "SELECT pubname FROM pg_publication;"
-done

site-cookbooks/kosmos_postgresql/files/list_replication_slots.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-psql -c "
-SELECT slot_name,
-pg_size_pretty(pg_wal_lsn_diff(pg_current_wal_lsn(), restart_lsn))
-FROM pg_replication_slots;"

site-cookbooks/kosmos_postgresql/files/list_subscriptions.sh

@@ -1,5 +0,0 @@
-#!/bin/bash
-for db in $(psql -Atqc "SELECT datname FROM pg_database WHERE datallowconn AND datname NOT IN ('template0','template1')"); do
-  echo "==== DB: $db ===="
-  psql -d "$db" -c "SELECT * FROM pg_stat_subscription;"
-done

site-cookbooks/kosmos_postgresql/files/restore_all_databases.sh

@@ -1,8 +0,0 @@
-#!/bin/bash
-cd /tmp
-for f in dump_*.tar.zst; do
-  db=$(echo $f | sed "s/dump_\(.*\)\.tar\.zst/\1/")
-  echo "Restoring $db"
-  zstd -d "$f" -c | tar -xf -
-  pg_restore -j 4 -d "$db" dump_$db
-done

site-cookbooks/kosmos_postgresql/libraries/helpers.rb

@@ -36,16 +36,10 @@ class Chef
       end
     end
 
-    def postgresql_version
-      node['kosmos_postgresql']['postgresql_version']
-    end
+    def postgresql_service_name
+      postgresql_version = "12"
 
-    def postgresql_service
       "postgresql@#{postgresql_version}-main"
     end
-
-    def postgresql_data_dir
-      "/var/lib/postgresql/#{postgresql_version}/main"
-    end
   end
 end

site-cookbooks/kosmos_postgresql/recipes/primary.rb

@@ -3,41 +3,31 @@
 # Recipe:: primary
 #
 
+postgresql_version = "12"
+postgresql_service = "postgresql@#{postgresql_version}-main"
+
+service postgresql_service do
+  supports restart: true, status: true, reload: true
+end
+
 postgresql_custom_server postgresql_version do
   role "primary"
 end
 
-cookbook_file "/usr/local/bin/pg_dump_all_databases" do
-  source "dump_all_databases.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
+postgresql_access "zerotier members" do
+  access_type "host"
+  access_db "all"
+  access_user "all"
+  access_addr "10.1.1.0/24"
+  access_method "md5"
+  notifies :reload, "service[#{postgresql_service}]", :immediately
 end
 
-cookbook_file "/usr/local/bin/pg_create_replication_publications" do
-  source "create_publications.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
-end
-
-cookbook_file "/usr/local/bin/pg_drop_replication_publications" do
-  source "drop_publications.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
-end
-
-cookbook_file "/usr/local/bin/pg_list_replication_publications" do
-  source "list_publications.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
-end
-
-cookbook_file "/usr/local/bin/pg_list_replication_slots" do
-  source "list_replication_slots.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
+postgresql_access "zerotier members replication" do
+  access_type "host"
+  access_db "replication"
+  access_user "replication"
+  access_addr "10.1.1.0/24"
+  access_method "md5"
+  notifies :reload, "service[#{postgresql_service}]", :immediately
 end

site-cookbooks/kosmos_postgresql/recipes/replica.rb

@@ -3,32 +3,54 @@
 # Recipe:: replica
 #
 
-service postgresql_service do
-  supports restart: true, status: true, reload: true
-end
+postgresql_version = "12"
+postgresql_service = "postgresql@#{postgresql_version}-main"
 
 postgresql_custom_server postgresql_version do
   role "replica"
 end
 
+service postgresql_service do
+  supports restart: true, status: true, reload: true
+end
+
 postgresql_data_bag_item = data_bag_item('credentials', 'postgresql')
 
 primary = postgresql_primary
 
-if primary.nil?
-  Chef::Log.warn("No PostgreSQL primary node found. Skipping replication setup.")
-  return
-end
+unless primary.nil?
+  # TODO
+  postgresql_data_dir = "/var/lib/postgresql/#{postgresql_version}/main"
 
-execute "set up replication" do
-  command <<-EOF
+  # FIXME get zerotier IP
+  execute "set up replication" do
+    command <<-EOF
 systemctl stop #{postgresql_service}
 mv #{postgresql_data_dir} #{postgresql_data_dir}.old
 pg_basebackup -h pg.kosmos.local -U replication -D #{postgresql_data_dir} -R
 chown -R postgres:postgres #{postgresql_data_dir}
 systemctl start #{postgresql_service}
-  EOF
-  environment 'PGPASSWORD' => postgresql_data_bag_item['replication_password']
-  sensitive true
-  not_if { ::File.exist? "#{postgresql_data_dir}/standby.signal" }
+    EOF
+    environment 'PGPASSWORD' => postgresql_data_bag_item['replication_password']
+    sensitive true
+    not_if { ::File.exist? "#{postgresql_data_dir}/standby.signal" }
+  end
+
+  postgresql_access "zerotier members" do
+    access_type "host"
+    access_db "all"
+    access_user "all"
+    access_addr "10.1.1.0/24"
+    access_method "md5"
+    notifies :reload, "service[#{postgresql_service}]", :immediately
+  end
+
+  postgresql_access "zerotier members replication" do
+    access_type "host"
+    access_db "replication"
+    access_user "replication"
+    access_addr "10.1.1.0/24"
+    access_method "md5"
+    notifies :reload, "service[#{postgresql_service}]", :immediately
+  end
 end

site-cookbooks/kosmos_postgresql/recipes/replica_logical.rb

@@ -1,50 +0,0 @@
-#
-# Cookbook:: kosmos_postgresql
-# Recipe:: replica_logical
-#
-
-service postgresql_service do
-  supports restart: true, status: true, reload: true
-end
-
-postgresql_custom_server postgresql_version do
-  role "replica_logical"
-end
-
-postgresql_data_bag_item = data_bag_item('credentials', 'postgresql')
-
-primary = postgresql_primary
-
-if primary.nil?
-  Chef::Log.warn("No PostgreSQL primary node found. Skipping replication setup.")
-  return
-end
-
-template "/usr/local/bin/pg_create_replication_subscriptions" do
-  source "create_subscriptions.sh.erb"
-  user "postgres"
-  group "postgres"
-  mode "0740"
-  sensitive true
-end
-
-cookbook_file "/usr/local/bin/pg_drop_replication_subscriptions" do
-  source "drop_subscriptions.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
-end
-
-cookbook_file "/usr/local/bin/pg_list_replication_subscriptions" do
-  source "list_subscriptions.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
-end
-
-cookbook_file "/usr/local/bin/pg_restore_all_databases" do
-  source "restore_all_databases.sh"
-  user "postgres"
-  group "postgres"
-  mode "0744"
-end

site-cookbooks/kosmos_postgresql/resources/server.rb

@@ -56,9 +56,7 @@ action :create do
     timezone: "UTC", # default is GMT
     listen_addresses: "0.0.0.0",
     promote_trigger_file: "#{postgresql_data_dir}/failover.trigger",
-    wal_level: "logical",
-    wal_keep_size: 4096, # 256 segments, 16MB each
-    max_replication_slots: 16
+    wal_keep_segments: 256
   }
 
   postgresql_server_conf "main" do
@@ -72,24 +70,6 @@ action :create do
     replication true
     password postgresql_credentials['replication_password']
   end
-
-  postgresql_access "all members" do
-    access_type "host"
-    access_db "all"
-    access_user "all"
-    access_addr node['kosmos_postgresql']['access_addr']
-    access_method "md5"
-    notifies :reload, "service[#{postgresql_service}]", :immediately
-  end
-
-  postgresql_access "replication members" do
-    access_type "host"
-    access_db "replication"
-    access_user "replication"
-    access_addr node['kosmos_postgresql']['access_addr']
-    access_method "md5"
-    notifies :reload, "service[#{postgresql_service}]", :immediately
-  end
 end
 
 action_class do

site-cookbooks/kosmos_postgresql/templates/create_subscriptions.sh.erb

@@ -1,33 +0,0 @@
-set -e
-
-echo "== Creating subscriptions for all databases =="
-
-for db in $(psql -Atqc "SELECT datname FROM pg_database WHERE datallowconn AND datname NOT IN ('template0','template1')"); do
-  echo "Processing DB: $db"
-
-  SLOT="migrate_slot_${db}"
-  SUB="migrate_sub_${db}"
-
-  psql -d "$db" -v ON_ERROR_STOP=1 <<SQL
-DO \$\$
-BEGIN
-  IF NOT EXISTS (
-    SELECT 1 FROM pg_subscription WHERE subname = '$SUB'
-  ) THEN
-    CREATE SUBSCRIPTION $SUB
-    CONNECTION 'host=<%= @pg_host %> port=<%= @pg_port %> dbname=$db user=<%= @pg_user %> password=<%= @pg_pass %>'
-    PUBLICATION migrate_pub
-    WITH (
-      slot_name = '$SLOT',
-      create_slot = false,
-      copy_data = false,
-      enabled = true
-    );
-  END IF;
-END
-\$\$;
-SQL
-
-done
-
-echo "== Done =="