Replication Setup

Author: SimoneGiusso

.gitignore

@@ -0,0 +1 @@
+/Physical Replication/README.md

Physical Replication/Postgres_Replica.png

@@ -0,0 +1,72 @@
+-- 1. CHECKING IF SETUP IS WORKING
+
+-- Primary Server should have a walsender process
+SELECT *
+FROM pg_catalog.pg_stat_activity 
+WHERE backend_type = 'walsender'
+
+-- Standby Server should have a walreceiver process
+SELECT *
+FROM pg_catalog.pg_stat_activity 
+WHERE backend_type = 'walreceiver'
+
+-- Finally the standby server should contain the same data of the primary server
+SELECT *
+FROM authors
+
+-- 2. STREAMING REPLICATION IN ACTION
+
+-- movies table doesn't exist on standby server
+SELECT *
+FROM movies
+
+-- Create movies table with foreign key on primary server and insert some rows
+CREATE TABLE movies (
+    movie_id SERIAL PRIMARY KEY,
+    title VARCHAR(255) NOT NULL,
+    release_year INT,
+    director VARCHAR(255),
+    genre VARCHAR(100),
+    author_id INT,
+    FOREIGN KEY (author_id) REFERENCES authors(author_id)
+);
+INSERT INTO movies (title, release_year, director, genre, author_id) VALUES
+    ('The Shawshank Redemption', 1994, 'Frank Darabont', 'Drama', 1),
+    ('The Godfather', 1972, 'Francis Ford Coppola', 'Crime', 2),
+    ('The Dark Knight', 2008, 'Christopher Nolan', 'Action', 3);
+
+-- Data should have been replicated on the standby server
+SELECT *
+FROM movies
+
+-- 3. READONLY STANDBY AND WRITING QUERIES
+
+-- Although only read queries can be performed on standby, write queries can still run on the standby as result of replication
+-- Open a transaction in standby server
+BEGIN;
+SELECT * FROM movies;
+
+-- Add new column on movies table in primary server
+ALTER TABLE movies ADD COLUMN rating int;
+
+-- Open a new connection to the standby. The following query won't run because the ALTER TABLE statement queued, which has priority, is blocked by the opened transaction.
+SELECT * FROM movies;
+
+-- Unblock the recently opened connection by running END; on standby
+-- If you don't do it a mechanism provided by postgresql, and active by default, will forcibly cancel the standby query that conflict with to-be-applied WAL records. The delay, before the query get cancelled, can be controlled via the max_standby_streaming_delay parameter (30s by default).
+-- This error will be then showed to the client in the stanby:
+
+-- SQL Error [40001]: FATAL: terminating connection due to conflict with recovery
+--  Detail: User was holding a relation lock for too long.
+--  Hint: In a moment you should be able to reconnect to the database and repeat your command.
+
+-- The problem doesn't happen if the opened transaction is on the primary, since the statement are sent after commit
+
+-- Primary server connection 1
+BEGIN;
+SELECT * FROM movies;
+
+-- Primary server connection 2
+ALTER TABLE movies ADD COLUMN budget float;
+
+-- At this point SELECT * FROM movies; on primary server will wait. However it will run on the standby.

Physical Replication/demo.sql

@@ -0,0 +1,40 @@
+networks:
+  default:
+    name: internal-network
+
+services:
+  masterdb:
+    image: postgres:15.6-alpine
+    container_name: primary-server
+    ports:
+      - 5432:5432
+    environment:
+      POSTGRES_USER: admin
+      POSTGRES_PASSWORD: psw
+    volumes:
+      - ./primary_config/init.sql:/docker-entrypoint-initdb.d/init.sql
+      - ./primary_config/pg_hba.conf:/etc/pg_hba.conf
+      - ./primary_config/postgresql.conf:/etc/postgresql.conf
+    command: postgres -c config_file=/etc/postgresql.conf
+
+  readonlydb:
+    image: postgres:15.6-alpine
+    container_name: hot-standby
+    ports:
+      - 5430:5432
+    environment:
+      POSTGRES_USER: admin
+      POSTGRES_PASSWORD: psw
+      PGUSER: replica_role
+      PGPASSWORD: replica_password
+    user: postgres
+    command: |
+      bash -c "
+      echo 'Waiting for primary...'
+      sleep 3s
+      pg_basebackup --pgdata=/var/lib/postgresql/data --write-recovery-conf --host=masterdb --port=5432
+      chmod 0700 /var/lib/postgresql/data
+      postgres
+      "
+    depends_on:
+      - masterdb

Physical Replication/docker-compose.yml

@@ -0,0 +1,18 @@
+-- Roles used by the stand by server for replication
+CREATE ROLE replica_role WITH LOGIN REPLICATION PASSWORD 'replica_password';
+
+\c postgres; 
+
+-- Create authors table
+CREATE TABLE authors (
+    author_id SERIAL PRIMARY KEY,
+    author_name VARCHAR(255) NOT NULL,
+    nationality VARCHAR(100),
+    birth_year INT
+);
+
+-- Insert rows into authors table
+INSERT INTO authors (author_name, nationality, birth_year) VALUES
+    ('Stephen King', 'American', 1947),
+    ('Mario Puzo', 'American', 1920),
+    ('Christopher Nolan', 'British', 1970);

Physical Replication/primary_config/init.sql

@@ -0,0 +1,102 @@
+# PostgreSQL Client Authentication Configuration File
+# ===================================================
+#
+# Refer to the "Client Authentication" section in the PostgreSQL
+# documentation for a complete description of this file.  A short
+# synopsis follows.
+#
+# This file controls: which hosts are allowed to connect, how clients
+# are authenticated, which PostgreSQL user names they can use, which
+# databases they can access.  Records take one of these forms:
+#
+# local         DATABASE  USER  METHOD  [OPTIONS]
+# host          DATABASE  USER  ADDRESS  METHOD  [OPTIONS]
+# hostssl       DATABASE  USER  ADDRESS  METHOD  [OPTIONS]
+# hostnossl     DATABASE  USER  ADDRESS  METHOD  [OPTIONS]
+# hostgssenc    DATABASE  USER  ADDRESS  METHOD  [OPTIONS]
+# hostnogssenc  DATABASE  USER  ADDRESS  METHOD  [OPTIONS]
+#
+# (The uppercase items must be replaced by actual values.)
+#
+# The first field is the connection type:
+# - "local" is a Unix-domain socket
+# - "host" is a TCP/IP socket (encrypted or not)
+# - "hostssl" is a TCP/IP socket that is SSL-encrypted
+# - "hostnossl" is a TCP/IP socket that is not SSL-encrypted
+# - "hostgssenc" is a TCP/IP socket that is GSSAPI-encrypted
+# - "hostnogssenc" is a TCP/IP socket that is not GSSAPI-encrypted
+#
+# DATABASE can be "all", "sameuser", "samerole", "replication", a
+# database name, or a comma-separated list thereof. The "all"
+# keyword does not match "replication". Access to replication
+# must be enabled in a separate record (see example below).
+#
+# USER can be "all", a user name, a group name prefixed with "+", or a
+# comma-separated list thereof.  In both the DATABASE and USER fields
+# you can also write a file name prefixed with "@" to include names
+# from a separate file.
+#
+# ADDRESS specifies the set of hosts the record matches.  It can be a
+# host name, or it is made up of an IP address and a CIDR mask that is
+# an integer (between 0 and 32 (IPv4) or 128 (IPv6) inclusive) that
+# specifies the number of significant bits in the mask.  A host name
+# that starts with a dot (.) matches a suffix of the actual host name.
+# Alternatively, you can write an IP address and netmask in separate
+# columns to specify the set of hosts.  Instead of a CIDR-address, you
+# can write "samehost" to match any of the server's own IP addresses,
+# or "samenet" to match any address in any subnet that the server is
+# directly connected to.
+#
+# METHOD can be "trust", "reject", "md5", "password", "scram-sha-256",
+# "gss", "sspi", "ident", "peer", "pam", "ldap", "radius" or "cert".
+# Note that "password" sends passwords in clear text; "md5" or
+# "scram-sha-256" are preferred since they send encrypted passwords.
+#
+# OPTIONS are a set of options for the authentication in the format
+# NAME=VALUE.  The available options depend on the different
+# authentication methods -- refer to the "Client Authentication"
+# section in the documentation for a list of which options are
+# available for which authentication methods.
+#
+# Database and user names containing spaces, commas, quotes and other
+# special characters must be quoted.  Quoting one of the keywords
+# "all", "sameuser", "samerole" or "replication" makes the name lose
+# its special character, and just match a database or username with
+# that name.
+#
+# This file is read on server startup and when the server receives a
+# SIGHUP signal.  If you edit the file on a running system, you have to
+# SIGHUP the server for the changes to take effect, run "pg_ctl reload",
+# or execute "SELECT pg_reload_conf()".
+#
+# Put your actual configuration here
+# ----------------------------------
+#
+# If you want to allow non-local connections, you need to add more
+# "host" records.  In that case you will also need to make PostgreSQL
+# listen on a non-local interface via the listen_addresses
+# configuration parameter, or via the -i or -h command line switches.
+
+# CAUTION: Configuring the system for local "trust" authentication
+# allows any local user to connect as any PostgreSQL user, including
+# the database superuser.  If you do not trust all your local users,
+# use another authentication method.
+
+
+# TYPE  DATABASE        USER            ADDRESS                         METHOD
+
+# "local" is for Unix domain socket connections only
+local   all             all                                             trust
+# IPv4 local connections:
+host    all             all             127.0.0.1/32                    trust
+# IPv6 local connections:
+host    all             all             ::1/128                         trust
+# Allow replication connections from localhost, by a user with the
+# replication privilege.
+local   replication     all                                             trust
+host    replication     all             127.0.0.1/32                    trust
+host    replication     all             ::1/128                         trust
+
+host    all             all             all scram-sha-256
+
+host    replication     replica_role    hot-standby.internal-network    trust