./configure -c pgsql     # Use postgres kernel
./deploy.yml             # Set up everything with pigsty

pg-meta:
  hosts:
    10.10.10.10: { pg_seq: 1, pg_role: primary }
  vars:
    pg_cluster: pg-meta
    pg_users:
      - { name: dbuser_meta ,password: DBUser.Meta   ,pgbouncer: true ,roles: [dbrole_admin   ] ,comment: pigsty admin user }
      - { name: dbuser_view ,password: DBUser.Viewer ,pgbouncer: true ,roles: [dbrole_readonly] ,comment: read-only viewer  }
    pg_databases:
      - { name: meta, baseline: cmdb.sql ,comment: pigsty meta database ,schemas: [pigsty] ,extensions: [ vector ]}
    pg_hba_rules:
      - { user: dbuser_view , db: all ,addr: infra ,auth: pwd ,title: 'allow grafana dashboard access cmdb from infra nodes' }
    node_crontab: [ '00 01 * * * postgres /pg/bin/pg-backup full' ] # Full backup at 1 AM daily
    pg_packages: [ pgsql-main, pgsql-common ]   # pg kernel and common utilities
    #pg_extensions: [ pg18-time ,pg18-gis ,pg18-rag ,pg18-fts ,pg18-olap ,pg18-feat ,pg18-lang ,pg18-type ,pg18-util ,pg18-func ,pg18-admin ,pg18-stat ,pg18-sec ,pg18-fdw ,pg18-sim ,pg18-etl]

./configure -c pgsql            # Default is postgresql 18, no need to specify explicitly
./configure -c pgsql -v 17      # Use postgresql 17
./configure -c pgsql -v 16      # Use postgresql 16
./configure -c pgsql -v 15      # Use postgresql 15
./configure -c pgsql -v 14      # Use postgresql 14
./configure -c pgsql -v 13      # Use postgresql 13

./pgsql-rm.yml # -l pg-meta

 curl -fsSL https://repo.pigsty.io/get | bash
./bootstrap          # environment check, install dependencies
./configure -c supa  # Important: please modify passwords and other key information in the configuration file!
./deploy.yml         # install Pigsty, deploy PGSQL and MINIO!

./supabase.yml       # install Docker and deploy stateless Supabase components!

# launch supabase stateless part with docker compose:
# ./supabase.yml
supabase:
  hosts:
    10.10.10.10: { supa_seq: 1 }  # instance id
  vars:
    supa_cluster: supa            # cluster name
    docker_enabled: true          # enable docker

    # use these to pull docker images via proxy and mirror registries
    #docker_registry_mirrors: ['https://docker.xxxxx.io']
    #proxy_env:   # add [OPTIONAL] proxy env to /etc/docker/daemon.json configuration file
    #  no_proxy: "localhost,127.0.0.1,10.0.0.0/8,192.168.0.0/16,*.pigsty,*.aliyun.com,mirrors.*,*.myqcloud.com,*.tsinghua.edu.cn"
    #  #all_proxy: http://user:pass@host:port

    # these configuration entries will OVERWRITE or APPEND to /opt/supabase/.env file (src template: app/supabase/.env)
    # check https://github.com/pgsty/pigsty/blob/main/app/supabase/.env for default values
    supa_config:

      # IMPORTANT: CHANGE JWT_SECRET AND REGENERATE CREDENTIAL ACCORDING!!!!!!!!!!!
      # https://supabase.com/docs/guides/self-hosting/docker#securing-your-services
      jwt_secret: your-super-secret-jwt-token-with-at-least-32-characters-long
      anon_key: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyAgCiAgICAicm9sZSI6ICJhbm9uIiwKICAgICJpc3MiOiAic3VwYWJhc2UtZGVtbyIsCiAgICAiaWF0IjogMTY0MTc2OTIwMCwKICAgICJleHAiOiAxNzk5NTM1NjAwCn0.dc_X5iR_VP_qT0zsiyj_I_OZ2T9FtRU2BBNWN8Bu4GE
      service_role_key: eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyAgCiAgICAicm9sZSI6ICJzZXJ2aWNlX3JvbGUiLAogICAgImlzcyI6ICJzdXBhYmFzZS1kZW1vIiwKICAgICJpYXQiOiAxNjQxNzY5MjAwLAogICAgImV4cCI6IDE3OTk1MzU2MDAKfQ.DaYlNEoUrrEn2Ig7tqibS-PHK5vgusbcbo7X36XVt4Q
      dashboard_username: supabase
      dashboard_password: pigsty

      # postgres connection string (use the correct ip and port)
      postgres_host: 10.10.10.10
      postgres_port: 5436             # access via the 'default' service, which always route to the primary postgres
      postgres_db: postgres
      postgres_password: DBUser.Supa  # password for supabase_admin and multiple supabase users

      # expose supabase via domain name
      site_url: http://supa.pigsty
      api_external_url: http://supa.pigsty
      supabase_public_url: http://supa.pigsty

      # if using s3/minio as file storage
      s3_bucket: supa
      s3_endpoint: https://sss.pigsty:9000
      s3_access_key: supabase
      s3_secret_key: S3User.Supabase
      s3_force_path_style: true
      s3_protocol: https
      s3_region: stub
      minio_domain_ip: 10.10.10.10  # sss.pigsty domain name will resolve to this ip statically

      # if using SMTP (optional)
      #smtp_admin_email: [email protected]
      #smtp_host: supabase-mail
      #smtp_port: 2500
      #smtp_user: fake_mail_user
      #smtp_pass: fake_mail_password
      #smtp_sender_name: fake_sender
      #enable_anonymous_users: false

curl -fsSL https://repo.pigsty.io/get | bash; cd ~/pigsty;
./configure -c pgtde     # Use percona postgres kernel
./deploy.yml             # Set up everything with pigsty

pg-meta:
  hosts:
    10.10.10.10: { pg_seq: 1, pg_role: primary }
  vars:
    pg_cluster: pg-meta
    pg_users:
      - { name: dbuser_meta ,password: DBUser.Meta   ,pgbouncer: true ,roles: [dbrole_admin   ] ,comment: pgsql admin user }
      - { name: dbuser_view ,password: DBUser.Viewer ,pgbouncer: true ,roles: [dbrole_readonly] ,comment: read-only viewer  }
    pg_databases:
      - name: meta
        baseline: cmdb.sql
        comment: pigsty tde database
        schemas: [pigsty]
        extensions: [ vector, postgis, pg_tde ,pgaudit, { name: pg_stat_monitor, schema: monitor } ]
    pg_hba_rules:
      - { user: dbuser_view , db: all ,addr: infra ,auth: pwd ,title: 'allow grafana dashboard access cmdb from infra nodes' }
    node_crontab: [ '00 01 * * * postgres /pg/bin/pg-backup full' ] # Full backup at 1 AM daily

    # Percona PostgreSQL TDE specific settings
    pg_packages: [ percona-main, pgsql-common ]  # Install percona postgres packages
    pg_libs: 'pg_tde, pgaudit, pg_stat_statements, pg_stat_monitor, auto_explain'

curl -fsSL https://repo.pigsty.io/get | bash; cd ~/pigsty;
./configure -c mysql    # Use MySQL (openHalo) configuration template
./deploy.yml            # Install, for production deployment please modify passwords in pigsty.yml first

pg-meta:
  hosts:
    10.10.10.10: { pg_seq: 1, pg_role: primary }
  vars:
    pg_cluster: pg-meta
    pg_users:
      - {name: dbuser_meta ,password: DBUser.Meta   ,pgbouncer: true ,roles: [dbrole_admin]    ,comment: pigsty admin user }
      - {name: dbuser_view ,password: DBUser.Viewer ,pgbouncer: true ,roles: [dbrole_readonly] ,comment: read-only viewer for meta database }
    pg_databases:
      - {name: postgres, extensions: [aux_mysql]} # mysql compatible database
      - {name: meta ,baseline: cmdb.sql ,comment: pigsty meta database ,schemas: [pigsty]}
    pg_hba_rules:
      - {user: dbuser_view , db: all ,addr: infra ,auth: pwd ,title: 'allow grafana dashboard access cmdb from infra nodes'}
    node_crontab: [ '00 01 * * * postgres /pg/bin/pg-backup full' ] # Full backup at 1 AM daily

    # OpenHalo specific settings
    pg_mode: mysql                    # HaloDB's MySQL compatibility mode
    pg_version: 14                    # Current HaloDB compatible PG major version 14
    pg_packages: [ openhalodb, pgsql-common ]  # Install openhalodb instead of postgresql kernel

mysql -h 127.0.0.1 -u dbuser_dba

curl -fsSL https://repo.pigsty.io/get | bash; cd ~/pigsty;
./configure -c oriole    # Use OrioleDB configuration template
./deploy.yml             # Install Pigsty with OrioleDB

pg-meta:
  hosts:
    10.10.10.10: { pg_seq: 1, pg_role: primary }
  vars:
    pg_cluster: pg-meta
    pg_users:
      - {name: dbuser_meta ,password: DBUser.Meta   ,pgbouncer: true ,roles: [dbrole_admin]    ,comment: pigsty admin user }
      - {name: dbuser_view ,password: DBUser.Viewer ,pgbouncer: true ,roles: [dbrole_readonly] ,comment: read-only viewer for meta database }
    pg_databases:
      - {name: meta ,baseline: cmdb.sql ,comment: pigsty meta database ,schemas: [pigsty], extensions: [orioledb]}
    pg_hba_rules:
      - {user: dbuser_view , db: all ,addr: infra ,auth: pwd ,title: 'allow grafana dashboard access cmdb from infra nodes'}
    node_crontab: [ '00 01 * * * postgres /pg/bin/pg-backup full' ] # Full backup at 1 AM daily

    # OrioleDB specific settings
    pg_mode: oriole                                         # oriole compatibility mode
    pg_packages: [ orioledb, pgsql-common ]                 # Install OrioleDB kernel
    pg_libs: 'orioledb, pg_stat_statements, auto_explain'   # Load OrioleDB extension

pgbench -is 100 meta
pgbench -nv -P1 -c10 -S -T1000 meta
pgbench -nv -P1 -c50 -S -T1000 meta
pgbench -nv -P1 -c10    -T1000 meta
pgbench -nv -P1 -c50    -T1000 meta

-- Create OrioleDB tables
CREATE TABLE pgbench_accounts_o (LIKE pgbench_accounts INCLUDING ALL) USING orioledb;
CREATE TABLE pgbench_branches_o (LIKE pgbench_branches INCLUDING ALL) USING orioledb;
CREATE TABLE pgbench_history_o (LIKE pgbench_history INCLUDING ALL) USING orioledb;
CREATE TABLE pgbench_tellers_o (LIKE pgbench_tellers INCLUDING ALL) USING orioledb;

-- Copy data from regular tables to OrioleDB tables
INSERT INTO pgbench_accounts_o SELECT * FROM pgbench_accounts;
INSERT INTO pgbench_branches_o SELECT * FROM pgbench_branches;
INSERT INTO pgbench_history_o SELECT  * FROM pgbench_history;
INSERT INTO pgbench_tellers_o SELECT * FROM pgbench_tellers;

-- Drop original tables and rename OrioleDB tables
DROP TABLE pgbench_accounts, pgbench_branches, pgbench_history, pgbench_tellers;
ALTER TABLE pgbench_accounts_o RENAME TO pgbench_accounts;
ALTER TABLE pgbench_branches_o RENAME TO pgbench_branches;
ALTER TABLE pgbench_history_o RENAME TO pgbench_history;
ALTER TABLE pgbench_tellers_o RENAME TO pgbench_tellers;

./pgsql.yml -t pg_extension -e '{"pg_extensions":["citus"]}'

all:
  children:
    pg-citus0: # citus shard 0
      hosts: { 10.10.10.10: { pg_seq: 1, pg_role: primary } }
      vars: { pg_cluster: pg-citus0 , pg_group: 0 }
    pg-citus1: # citus shard 1
      hosts: { 10.10.10.11: { pg_seq: 1, pg_role: primary } }
      vars: { pg_cluster: pg-citus1 , pg_group: 1 }
    pg-citus2: # citus shard 2
      hosts: { 10.10.10.12: { pg_seq: 1, pg_role: primary } }
      vars: { pg_cluster: pg-citus2 , pg_group: 2 }
    pg-citus3: # citus shard 3
      hosts:
        10.10.10.13: { pg_seq: 1, pg_role: primary }
        10.10.10.14: { pg_seq: 2, pg_role: replica }
      vars: { pg_cluster: pg-citus3 , pg_group: 3 }
  vars:                               # Global parameters for all Citus clusters
    pg_mode: citus                    # pgsql cluster mode must be set to: citus
    pg_shard: pg-citus                # citus horizontal shard name: pg-citus
    pg_primary_db: meta               # citus database name: meta
    pg_dbsu_password: DBUser.Postgres # If using dbsu, you need to configure a password for it
    pg_users: [ { name: dbuser_meta ,password: DBUser.Meta ,pgbouncer: true ,roles: [ dbrole_admin ] } ]
    pg_databases: [ { name: meta ,extensions: [ { name: citus }, { name: postgis }, { name: timescaledb } ] } ]
    pg_hba_rules:
      - { user: 'all' ,db: all  ,addr: 127.0.0.1/32 ,auth: ssl ,title: 'all user ssl access from localhost' }
      - { user: 'all' ,db: all  ,addr: intra        ,auth: ssl ,title: 'all user ssl access from intranet'  }

#==========================================================#
# pg-citus: 10 node citus cluster (5 x primary-replica pair)
#==========================================================#
pg-citus: # citus group
  hosts:
    10.10.10.50: { pg_group: 0, pg_cluster: pg-citus0 ,pg_vip_address: 10.10.10.60/24 ,pg_seq: 0, pg_role: primary }
    10.10.10.51: { pg_group: 0, pg_cluster: pg-citus0 ,pg_vip_address: 10.10.10.60/24 ,pg_seq: 1, pg_role: replica }
    10.10.10.52: { pg_group: 1, pg_cluster: pg-citus1 ,pg_vip_address: 10.10.10.61/24 ,pg_seq: 0, pg_role: primary }
    10.10.10.53: { pg_group: 1, pg_cluster: pg-citus1 ,pg_vip_address: 10.10.10.61/24 ,pg_seq: 1, pg_role: replica }
    10.10.10.54: { pg_group: 2, pg_cluster: pg-citus2 ,pg_vip_address: 10.10.10.62/24 ,pg_seq: 0, pg_role: primary }
    10.10.10.55: { pg_group: 2, pg_cluster: pg-citus2 ,pg_vip_address: 10.10.10.62/24 ,pg_seq: 1, pg_role: replica }
    10.10.10.56: { pg_group: 3, pg_cluster: pg-citus3 ,pg_vip_address: 10.10.10.63/24 ,pg_seq: 0, pg_role: primary }
    10.10.10.57: { pg_group: 3, pg_cluster: pg-citus3 ,pg_vip_address: 10.10.10.63/24 ,pg_seq: 1, pg_role: replica }
    10.10.10.58: { pg_group: 4, pg_cluster: pg-citus4 ,pg_vip_address: 10.10.10.64/24 ,pg_seq: 0, pg_role: primary }
    10.10.10.59: { pg_group: 4, pg_cluster: pg-citus4 ,pg_vip_address: 10.10.10.64/24 ,pg_seq: 1, pg_role: replica }
  vars:
    pg_mode: citus                    # pgsql cluster mode: citus
    pg_shard: pg-citus                # citus shard name: pg-citus
    pg_primary_db: test               # primary database used by citus
    pg_dbsu_password: DBUser.Postgres # all dbsu password access for citus cluster
    pg_vip_enabled: true
    pg_vip_interface: eth1
    pg_extensions: [ 'citus postgis timescaledb pgvector' ]
    pg_libs: 'citus, timescaledb, pg_stat_statements, auto_explain' # citus will be added by patroni automatically
    pg_users: [ { name: test ,password: test ,pgbouncer: true ,roles: [ dbrole_admin ] } ]
    pg_databases: [ { name: test ,owner: test ,extensions: [ { name: citus }, { name: postgis } ] } ]
    pg_hba_rules:
      - { user: 'all' ,db: all  ,addr: 10.10.10.0/24 ,auth: trust ,title: 'trust citus cluster members'        }
      - { user: 'all' ,db: all  ,addr: 127.0.0.1/32  ,auth: ssl   ,title: 'all user ssl access from localhost' }
      - { user: 'all' ,db: all  ,addr: intra         ,auth: ssl   ,title: 'all user ssl access from intranet'  }

pgbench -i postgres://test:test@pg-citus0/test
pgbench -nv -P1 -T1000 -c 2 postgres://test:test@pg-citus0/test

psql -h pg-citus0 -d test -c "SELECT create_distributed_table('pgbench_accounts', 'aid'); SELECT truncate_local_data_after_distributing_table('public.pgbench_accounts');"
psql -h pg-citus0 -d test -c "SELECT create_reference_table('pgbench_branches')         ; SELECT truncate_local_data_after_distributing_table('public.pgbench_branches');"
psql -h pg-citus0 -d test -c "SELECT create_reference_table('pgbench_history')          ; SELECT truncate_local_data_after_distributing_table('public.pgbench_history');"
psql -h pg-citus0 -d test -c "SELECT create_reference_table('pgbench_tellers')          ; SELECT truncate_local_data_after_distributing_table('public.pgbench_tellers');"

psql -h pg-citus1 -d test -c '\dt+'

vagrant@meta-1:~$ psql -h pg-citus3 -d test -c 'explain select * from pgbench_accounts'
                                               QUERY PLAN
---------------------------------------------------------------------------------------------------------
 Custom Scan (Citus Adaptive)  (cost=0.00..0.00 rows=100000 width=352)
   Task Count: 32
   Tasks Shown: One of 32
   ->  Task
         Node: host=10.10.10.52 port=5432 dbname=test
         ->  Seq Scan on pgbench_accounts_102008 pgbench_accounts  (cost=0.00..81.66 rows=3066 width=97)
(6 rows)

pgbench -nv -P1 -T1000 -c 2 postgres://test:test@pg-citus1/test
pgbench -nv -P1 -T1000 -c 2 postgres://test:test@pg-citus2/test
pgbench -nv -P1 -T1000 -c 2 postgres://test:test@pg-citus3/test
pgbench -nv -P1 -T1000 -c 2 postgres://test:test@pg-citus4/test

test=# select * from  pg_dist_node;
 nodeid | groupid |  nodename   | nodeport | noderack | hasmetadata | isactive | noderole | nodecluster | metadatasynced | shouldhaveshards
--------+---------+-------------+----------+----------+-------------+----------+----------+-------------+----------------+------------------
      1 |       0 | 10.10.10.51 |     5432 | default  | t           | t        | primary  | default     | t              | f
      2 |       2 | 10.10.10.54 |     5432 | default  | t           | t        | primary  | default     | t              | t
      5 |       1 | 10.10.10.52 |     5432 | default  | t           | t        | primary  | default     | t              | t
      3 |       4 | 10.10.10.58 |     5432 | default  | t           | t        | primary  | default     | t              | t
      4 |       3 | 10.10.10.56 |     5432 | default  | t           | t        | primary  | default     | t              | t

./node.yml -t node_install -e '{"node_repo_modules":"local,mssql","node_packages":["wiltondb"]}'

#----------------------------------#
# PGSQL & MSSQL (Babelfish & Wilton)
#----------------------------------#
# PG Installation
node_repo_modules: local,node,mssql # add mssql and os upstream repos
pg_mode: mssql                      # Microsoft SQL Server Compatible Mode
pg_libs: 'babelfishpg_tds, pg_stat_statements, auto_explain' # add timescaledb to shared_preload_libraries
pg_version: 15                      # The current WiltonDB major version is 15
pg_packages:
  - wiltondb                        # install forked version of postgresql with babelfishpg support
  - patroni pgbouncer pgbackrest pg_exporter pgbadger vip-manager
pg_extensions: []                   # do not install any vanilla postgresql extensions

# PG Provision
pg_default_hba_rules:               # overwrite default HBA rules for babelfish cluster
- {user: '${dbsu}'    ,db: all         ,addr: local     ,auth: ident ,title: 'dbsu access via local os user ident'  }
- {user: '${dbsu}'    ,db: replication ,addr: local     ,auth: ident ,title: 'dbsu replication from local os ident' }
- {user: '${repl}'    ,db: replication ,addr: localhost ,auth: pwd   ,title: 'replicator replication from localhost'}
- {user: '${repl}'    ,db: replication ,addr: intra     ,auth: pwd   ,title: 'replicator replication from intranet' }
- {user: '${repl}'    ,db: postgres    ,addr: intra     ,auth: pwd   ,title: 'replicator postgres db from intranet' }
- {user: '${monitor}' ,db: all         ,addr: localhost ,auth: pwd   ,title: 'monitor from localhost with password' }
- {user: '${monitor}' ,db: all         ,addr: infra     ,auth: pwd   ,title: 'monitor from infra host with password'}
- {user: '${admin}'   ,db: all         ,addr: infra     ,auth: ssl   ,title: 'admin @ infra nodes with pwd & ssl'   }
- {user: '${admin}'   ,db: all         ,addr: world     ,auth: ssl   ,title: 'admin @ everywhere with ssl & pwd'    }
- {user: dbuser_mssql ,db: mssql       ,addr: intra     ,auth: md5   ,title: 'allow mssql dbsu intranet access'     } # <--- use md5 auth method for mssql user
- {user: '+dbrole_readonly',db: all    ,addr: localhost ,auth: pwd   ,title: 'pgbouncer read/write via local socket'}
- {user: '+dbrole_readonly',db: all    ,addr: intra     ,auth: pwd   ,title: 'read/write biz user via password'     }
- {user: '+dbrole_offline' ,db: all    ,addr: intra     ,auth: pwd   ,title: 'allow etl offline tasks from intranet'}
pg_default_services:                # route primary & replica service to mssql port 1433
- { name: primary ,port: 5433 ,dest: 1433  ,check: /primary   ,selector: "[]" }
- { name: replica ,port: 5434 ,dest: 1433  ,check: /read-only ,selector: "[]" , backup: "[? pg_role == `primary` || pg_role == `offline` ]" }
- { name: default ,port: 5436 ,dest: postgres ,check: /primary   ,selector: "[]" }
- { name: offline ,port: 5438 ,dest: postgres ,check: /replica   ,selector: "[? pg_role == `offline` || pg_offline_query ]" , backup: "[? pg_role == `replica` && !pg_offline_query]"}

#----------------------------------#
# pgsql (singleton on current node)
#----------------------------------#
# this is an example single-node postgres cluster with postgis & timescaledb installed, with one biz database & two biz users
pg-meta:
  hosts:
    10.10.10.10: { pg_seq: 1, pg_role: primary } # <---- primary instance with read-write capability
  vars:
    pg_cluster: pg-test
    pg_users:                           # create MSSQL superuser
      - {name: dbuser_mssql ,password: DBUser.MSSQL ,superuser: true, pgbouncer: true ,roles: [dbrole_admin], comment: superuser & owner for babelfish  }
    pg_primary_db: mssql                # use `mssql` as the primary sql server database
    pg_databases:
      - name: mssql
        baseline: mssql.sql             # init babelfish database & user
        extensions:
          - { name: uuid-ossp          }
          - { name: babelfishpg_common }
          - { name: babelfishpg_tsql   }
          - { name: babelfishpg_tds    }
          - { name: babelfishpg_money  }
          - { name: pg_hint_plan       }
          - { name: system_stats       }
          - { name: tds_fdw            }
        owner: dbuser_mssql
        parameters: { 'babelfishpg_tsql.migration_mode' : 'multi-db' }
        comment: babelfish cluster, a MSSQL compatible pg cluster

curl -LO https://github.com/microsoft/go-sqlcmd/releases/download/v1.4.0/sqlcmd-v1.4.0-linux-amd64.tar.bz2
tar xjvf sqlcmd-v1.4.0-linux-amd64.tar.bz2
sudo mv sqlcmd* /usr/bin/

$ sqlcmd -S 10.10.10.10,1433 -U dbuser_mssql -P DBUser.MSSQL
1> select @@version
2> go
version
----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
Babelfish for PostgreSQL with SQL Server Compatibility - 12.0.2000.8
Oct 22 2023 17:48:32
Copyright (c) Amazon Web Services
PostgreSQL 15.4 (EL 1:15.4.wiltondb3.3_2-2.el8) on x86_64-redhat-linux-gnu (Babelfish 3.3.0)

(1 row affected)

# Access port 5433 on any cluster member, pointing to port 1433 MSSQL port on the primary
sqlcmd -S 10.10.10.11,5433 -U dbuser_mssql -P DBUser.MSSQL

# Access port 5434 on any cluster member, pointing to port 1433 MSSQL port on any readable replica
sqlcmd -S 10.10.10.11,5434 -U dbuser_mssql -P DBUser.MSSQL

./node.yml -t node_repo -e '{"node_repo_modules":"local,node,pgsql,ivory"}'

#----------------------------------#
# Ivory SQL Configuration
#----------------------------------#
node_repo_modules: local,node,pgsql,ivory  # add ivorysql upstream repo
pg_mode: ivory                    # IvorySQL Oracle Compatible Mode
pg_packages: [ 'ivorysql patroni pgbouncer pgbackrest pg_exporter pgbadger vip-manager' ]
pg_libs: 'liboracle_parser, pg_stat_statements, auto_explain'
pg_extensions: [ ]                # do not install any vanilla postgresql extensions

node_repo_modules: local,node,pgsql

#----------------------------------#
# PGSQL & PolarDB
#----------------------------------#
pg_version: 15
pg_packages: [ 'polardb patroni pgbouncer pgbackrest pg_exporter pgbadger vip-manager' ]
pg_extensions: [ ]                # do not install any vanilla postgresql extensions
pg_mode: polar                    # PolarDB Compatible Mode
pg_default_roles:                 # default roles and users in postgres cluster
  - { name: dbrole_readonly  ,login: false ,comment: role for global read-only access     }
  - { name: dbrole_offline   ,login: false ,comment: role for restricted read-only access }
  - { name: dbrole_readwrite ,login: false ,roles: [dbrole_readonly] ,comment: role for global read-write access }
  - { name: dbrole_admin     ,login: false ,roles: [pg_monitor, dbrole_readwrite] ,comment: role for object creation }
  - { name: postgres     ,superuser: true  ,comment: system superuser }
  - { name: replicator   ,superuser: true  ,replication: true ,roles: [pg_monitor, dbrole_readonly] ,comment: system replicator } # <- superuser is required for replication
  - { name: dbuser_dba   ,superuser: true  ,roles: [dbrole_admin]  ,pgbouncer: true ,pool_mode: session, pool_connlimit: 16 ,comment: pgsql admin user }
  - { name: dbuser_monitor ,roles: [pg_monitor] ,pgbouncer: true ,parameters: {log_min_duration_statement: 1000 } ,pool_mode: session ,pool_connlimit: 8 ,comment: pgsql monitor user }

pg-meta:
  hosts: { 10.10.10.10: { pg_seq: 1, pg_role: primary } }
  vars:
    pg_cluster: pg-meta
    pg_users:
      - {name: dbuser_meta     ,password: DBUser.Meta     ,pgbouncer: true ,roles: [dbrole_admin]    ,comment: pigsty admin user }
      - {name: dbuser_view     ,password: DBUser.Viewer   ,pgbouncer: true ,roles: [dbrole_readonly] ,comment: read-only viewer for meta database }
    pg_databases:
      - { name: meta ,baseline: cmdb.sql ,comment: pigsty meta database ,schemas: [pigsty] ,extensions: [{name: postgis, schema: public}, {name: timescaledb}]}
    pg_hba_rules:
      - {user: dbuser_view , db: all ,addr: infra ,auth: pwd ,title: 'allow grafana dashboard access cmdb from infra nodes'}
    pg_libs: 'pgml, pg_stat_statements, auto_explain'
    pg_extensions: [ 'pgml_15 pgvector_15 wal2json_15 repack_15' ]  # ubuntu
    #pg_extensions: [ 'postgresql-pgml-15 postgresql-15-pgvector postgresql-15-wal2json postgresql-15-repack' ]  # ubuntu

ansible pg-meta -m package -b -a 'name=pgml_15'
# ansible el8,el9 -m package -b -a 'name=pgml_15'           # EL 8/9
# ansible u22 -m package -b -a 'name=postgresql-pgml-15'    # Ubuntu 22.04 jammy

# Ubuntu 22.04 (python3.10), need to install pip and venv using apt
sudo apt install -y python3 python3-pip python3-venv

# EL 8/9, can upgrade the default pip and virtualenv
sudo yum install -y python3.11 python3.11-pip       # install latest python3.11
python3.11 -m pip install --upgrade pip virtualenv  # use python3.11 on EL8 / EL9

su - postgres;                          # create virtual environment as database superuser
mkdir -p /data/pgml; cd /data/pgml;     # create virtual environment directory
python3    -m venv /data/pgml           # create virtual environment directory (Ubuntu 22.04)
source /data/pgml/bin/activate          # activate virtual environment

# write Python dependencies and install with pip
cat > /data/pgml/requirments.txt <<EOF
accelerate==0.22.0
auto-gptq==0.4.2
bitsandbytes==0.41.1
catboost==1.2
ctransformers==0.2.27
datasets==2.14.5
deepspeed==0.10.3
huggingface-hub==0.17.1
InstructorEmbedding==1.0.1
lightgbm==4.1.0
orjson==3.9.7
pandas==2.1.0
rich==13.5.2
rouge==1.0.1
sacrebleu==2.3.1
sacremoses==0.0.53
scikit-learn==1.3.0
sentencepiece==0.1.99
sentence-transformers==2.2.2
tokenizers==0.13.3
torch==2.0.1
torchaudio==2.0.2
torchvision==0.15.2
tqdm==4.66.1
transformers==4.33.1
xgboost==2.0.0
langchain==0.0.287
einops==0.6.1
pynvml==11.5.0
EOF

# install dependencies using pip in the virtual environment
python3 -m pip install -r /data/pgml/requirments.txt
python3 -m pip install xformers==0.0.21 --no-dependencies

# additionally, 3 Python packages need to be installed globally using sudo!
sudo python3 -m pip install xgboost lightgbm scikit-learn

shared_preload_libraries: pgml, timescaledb, pg_stat_statements, auto_explain
pgml.venv: '/data/pgml'

CREATE EXTENSION vector;        -- also recommend installing pgvector!
CREATE EXTENSION pgml;          -- create PostgresML in the current database
SELECT pgml.version();          -- print PostgresML version information

# create extension pgml;
INFO:  Python version: 3.11.2 (main, Oct  5 2023, 16:06:03) [GCC 8.5.0 20210514 (Red Hat 8.5.0-18)]
INFO:  Scikit-learn 1.3.0, XGBoost 2.0.0, LightGBM 4.1.0, NumPy 1.26.1
CREATE EXTENSION

# SELECT pgml.version(); -- print PostgresML version information
 version
---------
 2.7.8

# EL 7 Only (Greenplum6)
./node.yml -t node_install  -e '{"node_repo_modules":"pgsql","node_packages":["open-source-greenplum-db-6"]}'

# EL 8 Only (Greenplum7)
./node.yml -t node_install  -e '{"node_repo_modules":"pgsql","node_packages":["open-source-greenplum-db-7"]}'

#================================================================#
#                        GPSQL Clusters                          #
#================================================================#

#----------------------------------#
# cluster: mx-mdw (gp master)
#----------------------------------#
mx-mdw:
  hosts:
    10.10.10.10: { pg_seq: 1, pg_role: primary , nodename: mx-mdw-1 }
  vars:
    gp_role: master          # this cluster is used as greenplum master
    pg_shard: mx             # pgsql sharding name & gpsql deployment name
    pg_cluster: mx-mdw       # this master cluster name is mx-mdw
    pg_databases:
      - { name: matrixmgr , extensions: [ { name: matrixdbts } ] }
      - { name: meta }
    pg_users:
      - { name: meta , password: DBUser.Meta , pgbouncer: true }
      - { name: dbuser_monitor , password: DBUser.Monitor , roles: [ dbrole_readonly ], superuser: true }

    pgbouncer_enabled: true                # enable pgbouncer for greenplum master
    pgbouncer_exporter_enabled: false      # enable pgbouncer_exporter for greenplum master
    pg_exporter_params: 'host=127.0.0.1&sslmode=disable'  # use 127.0.0.1 as local monitor host

#----------------------------------#
# cluster: mx-sdw (gp master)
#----------------------------------#
mx-sdw:
  hosts:
    10.10.10.11:
      nodename: mx-sdw-1        # greenplum segment node
      pg_instances:             # greenplum segment instances
        6000: { pg_cluster: mx-seg1, pg_seq: 1, pg_role: primary , pg_exporter_port: 9633 }
        6001: { pg_cluster: mx-seg2, pg_seq: 2, pg_role: replica , pg_exporter_port: 9634 }
    10.10.10.12:
      nodename: mx-sdw-2
      pg_instances:
        6000: { pg_cluster: mx-seg2, pg_seq: 1, pg_role: primary , pg_exporter_port: 9633  }
        6001: { pg_cluster: mx-seg3, pg_seq: 2, pg_role: replica , pg_exporter_port: 9634  }
    10.10.10.13:
      nodename: mx-sdw-3
      pg_instances:
        6000: { pg_cluster: mx-seg3, pg_seq: 1, pg_role: primary , pg_exporter_port: 9633 }
        6001: { pg_cluster: mx-seg1, pg_seq: 2, pg_role: replica , pg_exporter_port: 9634 }
  vars:
    gp_role: segment               # these are nodes for gp segments
    pg_shard: mx                   # pgsql sharding name & gpsql deployment name
    pg_cluster: mx-sdw             # these segment clusters name is mx-sdw
    pg_preflight_skip: true        # skip preflight check (since pg_seq & pg_role & pg_cluster not exists)
    pg_exporter_config: pg_exporter_basic.yml                             # use basic config to avoid segment server crash
    pg_exporter_params: 'options=-c%20gp_role%3Dutility&sslmode=disable'  # use gp_role = utility to connect to segments

# EL 7 Only (Greenplum6)
./node.yml -t node_install  -e '{"node_repo_modules":"pgsql","node_packages":["cloudberrydb"]}'

# EL 8 Only (Greenplum7)
./node.yml -t node_install  -e '{"node_repo_modules":"pgsql","node_packages":["cloudberrydb"]}'