Tag Archives: pg_hba.conf

PostgreSQL

PostgreSQL DBA Step by Step Learning

#	PostgreSQL DBA Topics
1	How to Install PostgreSQL ON Linux?
2	How to Install PostgreSQL on Linux 7 using source code?
3	How to START/STOP PostgreSQL ON Linux?
4	How to Create Database in PostgreSQL?
5	PostgreSQL User Management
6	PostgreSQL pg_hba.conf Guide
7	PostgreSQL Change Data Directory
8	Understanding WAL Files in PostgreSQL – For Oracle DBAs
9	Change PostgreSQL WAL Directory Path (pg_wal)
10	Enable Archive Mode in PostgreSQL 17
11	How to Disable ARCHIVELOG Mode
12	PostgreSQL Tablespace Management
13	PostgreSQL pg_dump and pg_restore Guide
14	PostgreSQL Backup and Restore Using pg_dumpall and psql
15	pg_basebackup – Backup, Restore, and Recovery
16	Backup & Restore PostgreSQL DB Cluster to Another Host (No Archive Mode)
17	Backup & Restore PostgreSQL DB Cluster on Same Host
18	Restore PostgreSQL to New Host using pg_basebackup + WAL Archives
19	PostgreSQL PITR – Point in Time Recovery
20	Configure Streaming Replication in PostgreSQL
21	Manual Failover in PostgreSQL Streaming Replication
22	Convert Asynchronous Replication to Synchronous Replication

Thank you,
Rajasekhar Amudala
Email: br8dba@gmail.com
Linkedin: https://www.linkedin.com/in/rajasekhar-amudala/

pg_basebackup

PostgreSQLBackup PostgreSQL Database, base backup, compressed backup, How to Backup Postgresql, pg_basebackup, pg_basebackup examples, pg_basebackup gzip, pg_basebackup restore, pg_basebackup tar, pg_hba.conf, pg_wal, physical backup, PITR, point in time recovery, postgres disaster recovery, postgres replication, postgresql 17 backup, PostgreSQL archive, PostgreSQL Backup, PostgreSQL recovery, PostgreSQL Restore, recovery.signal, replication role, tar backup

pg_basebackup – Backup, Restore, and Recovery

What is pg_basebackup?

pg_basebackup is a utility provided by PostgreSQL to take a physical base backup of the entire database cluster.

Common Use Cases:

Setting up standby servers for streaming replication
Creating physical backups for disaster recovery
Performing Point-In-Time Recovery (PITR)
Performing Incremental Backups (PostgreSQL v17 feature)

It connects to a running PostgreSQL server and copies all necessary data files and WAL segments, producing a consistent and restorable backup.

———- Backup ———-

Pre-requisites parameter and config:

1. User : Requires a user with replication role or superuser privileges

CREATE ROLE repl_user WITH REPLICATION LOGIN ENCRYPTED PASSWORD 'replpass';

2. postgresql.conf

wal_level=replica (Mandatory)
max_wal_senders >=1 (Mandatory)
archive_mode=on (Optional if Database in NO Archivelog mode)
archive_command = ‘cp %p /pgArch/pgsql17/arch/%f’ (Optional if Database in NO Archivelog mode)

3. pg_hba.conf

# TYPE  DATABASE        USER            ADDRESS             METHOD
# Local connections for replication (for pg_basebackup run locally)
local   replication     all                                 trust

# or you can use peer (if same OS user postgres is used)
# local   replication     all                                 peer

# Remote connections for replication (for pg_basebackup run remotely)
host    replication     repl_user       192.168.2.22/32     scram-sha-256

How pg_basebackup Works Internally:

Feature	`pg_basebackup` Supports?
Backup of data directory	Yes
Include enough WALs to make backup consistent	Yes
Backup of WAL archives (even with archive mode=on & archive_command configured)	No
Works without `archive_mode`	Yes

Performs a physical file-level backup by copying the full data directory
Uses PostgreSQL’s streaming replication protocol
Requires a user with replication role or superuser privileges
Can be used while the server is running (online backup)
Ensures a transactionally consistent snapshot of the database
Even with archive_mode=on and archive_command configured, pg_basebackup does not back up WAL archive logs from the archive location. It only includes enough live WAL files to make the backup consistent, streamed from pg_wal/.
pg_basebackup does not include all files from the pg_wal directory in the backup.
Instead, it selectively includes only the WAL files required to make the base backup consistent at the point in time the backup was taken.

What It Includes:

All essential data files of the cluster
Necessary WAL (Write-Ahead Log) segments for recovery
Custom tablespaces, replication slots, and large objects

WAL Handling Options:

Default: WAL files included after backup (-X fetch)
Streaming: WAL files streamed live during backup (-X stream)

How to take Backup using pg_basebackup ?

Want symlinks preserved → use (both -Fp & –waldir)-Fp --waldir=/pgWal/pgsql17/wal
Want single tar archive → use -Ft, but recreate symlinks after restore, for pg_wal
The –waldir option in pg_basebackup is supported only when using the plain format (-Fp), not with the tar format (-Ft).

-- Do not use -R here since it's not a replica (No standby).

Typically Backup using: Plain format, Tar format & Tar format (gzip)

1. Take backup in Plain format
nohup pg_basebackup -U postgres -D /pgBackups/pgsql17/demo_restore -Fp -Xs -P -v > pg_basebackup_demo_restore.log 2>&1 &

2. Take backup in Tar format
nohup pg_basebackup -U postgres -D /pgBackups/pgsql17/demo_tar_backup -Ft -Xs -P -v > pg_basebackup_tar.log 2>&1 &

3. Take backup in Compressed Tar format (gzip)
nohup pg_basebackup -U postgres -D /pgBackup/pgsql17/backup/ -Ft -z -Xs -P -v > pg_basebackup_tar.log 2>&1 &

4. Take compressed Tar backup with transfer rate limit
nohup pg_basebackup -U postgres -D /pgBackup/pgsql17/backup/ -Ft -z -X stream -P --max-rate=5M -v > pg_basebackup_tar.log 2>&1 &

5. Take compressed Tar backup with server-side gzip compression at max level (9)
nohup pg_basebackup -U postgres -D /pgBackup/pgsql17/backup/ -Ft --compress=server-gzip:9 -Xs -P -v > pg_basebackup.log 2>&1 &

6. Take Tar backup from a remote host
nohup pg_basebackup -h remote_host -p port -U postgres -D /pgBackup/remote_tar_backup -Ft -Xs -P -v > pg_basebackup_remote_tar.log 2>&1 &

PG BASE BACKUP Flag	Description
`-U <username>`	Specifies the PostgreSQL user to connect as.
`-D <directory>`	Specifies the target directory for the backup.
`-F p`	Takes the backup in Plain format (file system copy).
`-F t`	Takes the backup in Tar archive format.
`-z`	Compresses the backup using gzip compression (only valid with tar format).
`--compress=server-gzip:<level>`	Enables server-side gzip compression with specified compression level (1-9).
`-X s`	Includes the Write-Ahead Log (WAL) files by copying the WAL segment files.
`-X stream`	Streams the WAL files while taking the backup for continuous consistency.
`-P`	Shows progress information during the backup.
`--max-rate=<rate>`	Limits the maximum transfer rate during the backup (e.g., 5M for 5 megabytes/sec).
`-v`	–verbose, extra output

———- Restore ———-

1. Restore is a File-Level Operation

A base backup is a physical copy of the database files — including system catalogs, user data, WAL files, and optionally config files.
Restoring is done by simply copying or extracting the backup files into a valid PostgreSQL data directory (PGDATA) on the target system.

Restore Steps:

Stop PostgreSQL (if running)
Copy or extract the backup into a clean data directory (PGDATA)
Place a file named recovery.signal in the data directory
Start PostgreSQL to begin recovery

2. Custom Tablespaces Outside `PGDATA`

Backups include symlinks to external tablespace locations
On restore:
- Ensure original paths exist and are accessible
- Or remap symlinks to new locations
- Check ownership and permissions (postgres:postgres, 0700)

3. Restoring on a Different Host

Ensure matching directory structure or adjust accordingly
PostgreSQL version and architecture must match
Update postgresql.conf and pg_hba.conf as needed

4. Restoring Across PostgreSQL Versions

pg_basebackup is version-specific.

Not allowed: PostgreSQL 14 → PostgreSQL 15 or 17 (Lower to Higher)
Not allowed: PostgreSQL 17 → PostgreSQL 14 (Higher to Lower)
Use pg_dump/pg_restore or pg_upgrade for version upgrades

———- Recovery ———-

How Recovery Works:

PostgreSQL detects recovery.signal at startup
WAL files (in pg_wal/ or archive) are replayed (Redo apply / Archive apply from restore_command location )
When recovery completes:
- PostgreSQL automatically removes recovery.signal
- The server becomes a primary (read/write)
Recovery stops when:
- All available WALs are applied, or
- A recovery target (e.g., timestamp, transaction ID) is reached

What is recovery.signal ?

File	Purpose
`recovery.signal`	Tells PostgreSQL to enter recovery mode during startup
Automatically removed?	Yes, after recovery completes
Required for standalone restore?	Yes, otherwise WAL replay is skipped

Summary

1. Take a base backup on the source server using ‘pg_basebackup’.
2. Take Backup of WAL Archive files separately on Source (Manually, because pg_basebackup does NOT take backup of WAL archive files)
3. Transfer both the base backup and WAL archive logs to the target server.
4. Restore the base backup to the PostgreSQL data directory on the target.
5. Copy the WAL files to the dedicated WAL location (e.g., ‘/pgwal/pgsql17/wals’).
6. Remove ‘$PGDATA/pg_wal’ and create a symbolic link to the WAL location:
‘ln -s /pgwal/pgsql17/wals /pgdata/pgsql17/data/pg_wal’
7. Create an empty ‘recovery.signal‘ file in ‘$PGDATA’.
8. Set ‘restore_command‘ in ‘postgresql.conf’ to point to WAL archive backup path (e.g., ‘/pgbackup/pgsql17/backup/wal_archive_bkp’).
9. Ensure WAL archive files are restored to ‘/pgbackup/pgsql17/backup/wal_archive_bkp’ for ‘restore_command’ to access.
10. Update ‘tablespace_map‘ to reflect correct paths if using custom tablespaces.
11. Start PostgreSQL on the target; recovery will complete and automatically remove ‘recovery.signal’.
12. Tablespace symbolic links will create automatically by PostgreSQL.

Operation	Key Point
Backup	File-level copy using replication protocol
Restore	Place files into `PGDATA`, handle symlinks, configs, and versions
Recovery	Triggered by `recovery.signal`, replays WAL, auto-removes signal file

Caution: Your use of any information or materials on this website is entirely at your own risk. It is provided for educational purposes only. It has been tested internally, however, we do not guarantee that it will work for you. Ensure that you run it in your test environment before using.

Thank you,
Rajasekhar Amudala
Email: br8dba@gmail.com
Linkedin: https://www.linkedin.com/in/rajasekhar-amudala/

PostgreSQL pg_hba.conf

PostgreSQLdatabase administration, Host-Based Authentication, pg_hba, pg_hba.conf, PostgreSQL, PostgreSQL 15, PostgreSQL Authentication, PostgreSQL Configuration, PostgreSQL Roles and Users, PostgreSQL security, PostgreSQL Tutorial

PostgreSQL pg_hba.conf Guide

1. What is pg_hba.conf?
2. Authentication Methods in pg_hba.conf
3. Create Database and User
4. Contents of pg_hba.conf
5. Play with peer
6. Play with trust
7. Play with reject
8. Restrict by User
9. Restrict by Network
10. Verify logs

1. What is pg_hba.conf?

HBA = Host-Based Authentication.
Location: usually inside PostgreSQL data directory (/var/lib/pgsql/<version>/data/pg_hba.conf or /pgData/pgsql15/data/pg_hba.conf depending on your setup).



Format:

# TYPE  DATABASE  USER  ADDRESS        METHOD
TYPE: local, host, hostssl, hostnossl
DATABASE: which DBs (e.g. all, postgres, mydb)
USER: which roles (e.g. all, myuser)
ADDRESS: client IP/CIDR (127.0.0.1/32, 192.168.2.0/24)
METHOD: authentication method (trust, md5, scram-sha-256, peer, reject, cert)

OPTIONS	: optional settings (e.g., clientcert=1)

2. Authentication Methods in pg_hba.conf

trust:
--- > No password needed. Anyone who can connect to the server is trusted.
--- > Use: testing only.
--- > Not secure in production.

Example:

host    all    all    127.0.0.1/32    trust

md5
--- > Password required, stored as MD5 hash.
--- > Legacy support. Weaker security, avoid if possible.

Example:

host    all    all    127.0.0.1/32    md5

scram-sha-256
--- > Password required, stored as salted SCRAM-SHA-256 hash.
--- > Stronger than MD5.
--- > Recommended method for production.

Example:

host    all    all    127.0.0.1/32    scram-sha-256


peer
--- > Works for local connections only.
--- > The OS user name must match the PostgreSQL role.
--- > Good for local scripts/services under same user.

Example:

local   all    all                     peer


reject
--- > Explicitly denies access.
----> Useful for blocking unwanted connections (like a firewall rule).

Example:

host    all    all    0.0.0.0/0       reject


cert
---> Requires SSL/TLS client certificate.
---> PostgreSQL role must match certificate username.
---> Very secure for enterprise / production with SSL.

Example:
hostssl all   all    192.168.1.0/24   cert clientcert=1

3. Create Database and User

postgres=# CREATE USER teja WITH PASSWORD 'teja123';
CREATE ROLE
postgres=# CREATE DATABASE orcl OWNER teja;
CREATE DATABASE
postgres=#

4. Contents of pg_hba.conf

[postgres@pg17 ~]$ cat /pgData/pgsql15/data/pg_hba.conf
# TYPE  DATABASE         USER            ADDRESS                METHOD

# Allow local peer access for postgres
local   all             postgres                                peer

# Allow local password access for all
local   all             all                                     scram-sha-256

[postgres@pg17 ~]$

5. Play with peer

Works for local connections only. The OS user name must match the PostgreSQL role.

[postgres@pg17 ~]$ cat /pgData/pgsql15/data/pg_hba.conf
# TYPE  DATABASE         USER            ADDRESS                METHOD

# Allow local peer access for postgres

local   all             postgres                                peer


# Allow local password access for all
local   all             all                                     scram-sha-256

[postgres@pg17 ~]$

[postgres@pg17 ~]$ psql -U teja -d orcl
 Password for user teja: <---- it's asking password 

psql (15.13)
Type "help" for help.

orcl=> exit
[postgres@pg17 ~]$

 Password Not asking for user postgres 
[postgres@pg17 ~]$ psql -U postgres -d orcl
psql (15.13)
Type "help" for help.

orcl=#

6. Play with trust

No password needed. Anyone who can connect to the server is trusted.
Use: testing only. Not secure in production.

Change pg_hba.conf:

[postgres@pg17 ~]$ cat /pgData/pgsql15/data/pg_hba.conf
# TYPE  DATABASE         USER            ADDRESS                METHOD

# Allow local peer access for postgres
local   all             postgres                                peer

# Allow local password access for all

local   all             all                                     trust

[postgres@pg17 ~]$

[postgres@pg17 ~]$ /usr/pgsql-15/bin/pg_ctl reload -D /pgData/pgsql15/data/
server signaled
[postgres@pg17 ~]$ psql -U teja -d orcl  <--- It won’t ask for a password. 
psql (15.13)
Type "help" for help.

orcl=>

7. Play with reject

[postgres@pg17 ~]$ cat /pgData/pgsql15/data/pg_hba.conf
# TYPE  DATABASE         USER            ADDRESS                METHOD

# Allow local peer access for postgres
local   all             postgres                                peer

# Allow local password access for all

local   all             all                                     reject

[postgres@pg17 ~]$

[postgres@pg17 ~]$ /usr/pgsql-15/bin/pg_ctl reload -D /pgData/pgsql15/data/
server signaled
[postgres@pg17 ~]$ psql -U teja -d orcl

psql: error: connection to server on socket "/run/postgresql/.s.PGSQL.5432" failed: FATAL:  pg_hba.conf rejects connection for host "[local]", user "teja", database "orcl", no encryption

[postgres@pg17 ~]$

8. Restrict by User

Allow only user teja, block everyone else:

[postgres@pg17 ~]$ cat /pgData/pgsql15/data/pg_hba.conf
# TYPE  DATABASE         USER            ADDRESS                METHOD

# Allow local peer access for postgres
local   all             postgres                                peer

# Allow local password access for all
local   all             all                                     trust

# Allow IPv4 localhost

host    orcl            teja             192.168.2.31/32         scram-sha-256
host    orcl            all              192.168.2.31/32         reject


[postgres@pg17 ~]$

[postgres@pg17 ~]$ /usr/pgsql-15/bin/pg_ctl reload -D /pgData/pgsql15/data/
server signaled
[postgres@pg17 ~]$ psql -U teja -d orcl -h 192.168.2.31
Password for user teja:
psql (15.13)
Type "help" for help.

orcl=> \conninfo
You are connected to database "orcl" as user "teja" on host "192.168.2.31" at port "5432".
orcl=>
orcl=> exit
[postgres@pg17 ~]$


[postgres@pg17 ~]$ psql -U postgres -d orcl -h 192.168.2.31

psql: error: connection to server at "192.168.2.31", port 5432 failed: FATAL:  pg_hba.conf rejects connection for host "192.168.2.31", user "postgres", database "orcl", no encryption

[postgres@pg17 ~]$


Notice: Only user Teja able to connect where as user postgres not able to connect

9. Restrict by Network

We want to block connections from IP 192.168.2.0/24 

[postgres@pg17 ~]$ cat /pgData/pgsql15/data/pg_hba.conf
# TYPE  DATABASE         USER            ADDRESS                METHOD

# Allow local peer access for postgres
local   all             postgres                                peer

# Allow local password access for all
local   all             all                                     trust

# Allow IPv4 localhost

host    all             all             192.168.2.0/24          reject

[postgres@pg17 ~]$

[postgres@pg17 ~]$ /usr/pgsql-15/bin/pg_ctl reload -D /pgData/pgsql15/data/
server signaled
[postgres@pg17 ~]$ 
[postgres@pg17 ~]$ psql -U teja -d orcl -h 192.168.2.31

psql: error: connection to server at "192.168.2.31", port 5432 failed: FATAL:  pg_hba.conf rejects connection for host "192.168.2.31", user "teja", database "orcl", no encryption

[postgres@pg17 ~]$

10. Verify logs

postgres=# SELECT * FROM pg_hba_file_rules;
 line_number | type  | database | user_name  |   address    |     netmask     |  auth_method  | options | error
-------------+-------+----------+------------+--------------+-----------------+---------------+---------+-------
           4 | local | {all}    | {postgres} |              |                 | peer          |         |
           7 | local | {all}    | {all}      |              |                 | trust         |         |
          11 | host  | {orcl}   | {teja}     | 192.168.2.31 | 255.255.255.255 | scram-sha-256 |         |
          12 | host  | {orcl}   | {all}      | 192.168.2.31 | 255.255.255.255 | reject        |         |
(4 rows)

postgres=#

[postgres@pg17 ~]$ tail -f /pgData/pgsql15/data/log/postgresql-Tue.log
2025-09-16 04:08:37.244 EDT [8294] LOG:  database system was shut down at 2025-09-16 04:08:32 EDT
2025-09-16 04:08:37.251 EDT [8289] LOG:  database system is ready to accept connections
2025-09-16 04:11:27.459 EDT [8289] LOG:  received SIGHUP, reloading configuration files
2025-09-16 04:11:31.842 EDT [8401] FATAL:  pg_hba.conf rejects connection for host "[local]", user "teja", database "orcl", no encryption
2025-09-16 04:13:37.568 EDT [8292] LOG:  checkpoint starting: time
2025-09-16 04:13:37.573 EDT [8292] LOG:  checkpoint complete: wrote 3 buffers (0.0%); 0 WAL file(s) added, 0 removed, 0 recycled; write=0.002 s, sync=0.002 s, total=0.006 s; sync files=2, longest=0.001 s, average=0.001 s; distance=0 kB, estimate=0 kB
2025-09-16 04:16:15.863 EDT [8289] LOG:  received SIGHUP, reloading configuration files
2025-09-16 04:16:52.318 EDT [8474] FATAL:  pg_hba.conf rejects connection for host "192.168.2.31", user "teja", database "orcl", no encryption
2025-09-16 04:27:15.932 EDT [8289] LOG:  received SIGHUP, reloading configuration files
2025-09-16 04:27:50.593 EDT [8613] FATAL:  pg_hba.conf rejects connection for host "192.168.2.31", user "postgres", database "orcl", no encryption

Thank you,
Rajasekhar Amudala
Email: br8dba@gmail.com
Linkedin: https://www.linkedin.com/in/rajasekhar-amudala/

PSQL

PostgreSQLadvanced PostgreSQL, asynchronous replication PostgreSQL, autovacuum tuning, change PGDATA, compile PostgreSQL, create database PostgreSQL, database administration, database performance tuning, DBA Training, install PostgreSQL Linux, Linux PostgreSQL DBA, logical replication PostgreSQL, manual failover PostgreSQL, migrate Oracle to PostgreSQL, Open Source Database, Oracle DBA to PostgreSQL, Patroni PostgreSQL, pg_basebackup, pg_dump, pg_dumpall, pg_hba.conf, pg_restore, pg_stat_activity, pg_wal, point in time recovery, Postgres admin guide, Postgres DBA course, Postgres PITR, Postgres query optimization, Postgres real time scenarios, PostgreSQL, PostgreSQL 17, PostgreSQL access control, PostgreSQL administration, PostgreSQL architecture, PostgreSQL archive mode, PostgreSQL Authentication, PostgreSQL automatic failover, PostgreSQL AWS, PostgreSQL Azure, PostgreSQL Backup, PostgreSQL backup and recovery, PostgreSQL CentOS, PostgreSQL cloud, PostgreSQL Cluster Backup, PostgreSQL clustering, PostgreSQL Configuration, PostgreSQL data directory, PostgreSQL database creation, PostgreSQL DBA, PostgreSQL disaster recovery, PostgreSQL failover, PostgreSQL for beginners, PostgreSQL GCP, PostgreSQL HA, PostgreSQL high availability, PostgreSQL Indexing, PostgreSQL installation, PostgreSQL internals, PostgreSQL Linux 7, PostgreSQL logical backup, postgresql migration, PostgreSQL Monitoring, PostgreSQL on Linux, PostgreSQL Performance, PostgreSQL performance tuning, PostgreSQL physical backup, PostgreSQL PITR, PostgreSQL recovery, PostgreSQL replication, PostgreSQL Restore, PostgreSQL RHEL, PostgreSQL roles, PostgreSQL Roles and Privileges, PostgreSQL security, PostgreSQL service management, PostgreSQL source installation, PostgreSQL SSL setup, PostgreSQL step by step, PostgreSQL storage management, PostgreSQL Tablespace, PostgreSQL training, PostgreSQL Troubleshooting, PostgreSQL Tutorial, PostgreSQL user management, PostgreSQL users, PostgreSQL WAL, PostgreSQL WAL directory, REPMGR, SQL Tuning, Start PostgreSQL, Stop PostgreSQL, streaming replication, streaming replication PostgreSQL, synchronous replication PostgreSQL, vacuum analyze PostgreSQL, WAL archiving, WAL archiving PostgreSQL, write-ahead logging

PostgreSQL DBA Step by Step Learning

#	PostgreSQL DBA Topics
1	How to Install PostgreSQL ON Linux?
2	How to Install PostgreSQL on Linux 7 using source code?
3	How to START/STOP PostgreSQL ON Linux?
4	How to Create Database in PostgreSQL?
5	PostgreSQL User Management
6	PostgreSQL pg_hba.conf Guide
7	PostgreSQL Change Data Directory
8	Understanding WAL Files in PostgreSQL – For Oracle DBAs
9	Change PostgreSQL WAL Directory Path (pg_wal)
10	Enable Archive Mode in PostgreSQL 17
11	How to Disable ARCHIVELOG Mode
12	PostgreSQL Tablespace Management
13	PostgreSQL pg_dump and pg_restore Guide
14	PostgreSQL Backup and Restore Using pg_dumpall and psql
15	pg_basebackup – Backup, Restore, and Recovery
16	Backup & Restore PostgreSQL DB Cluster to Another Host (No Archive Mode)
17	Backup & Restore PostgreSQL DB Cluster on Same Host
18	Restore PostgreSQL to New Host using pg_basebackup + WAL Archives
19	PostgreSQL PITR – Point in Time Recovery
20	Configure Streaming Replication in PostgreSQL
21	Manual Failover in PostgreSQL Streaming Replication
22	Convert Asynchronous Replication to Synchronous Replication

Thank you,
Rajasekhar Amudala
Email: br8dba@gmail.com
Linkedin: https://www.linkedin.com/in/rajasekhar-amudala/

BRIGHT DBA

ORACLE DBA – Tips and Techniques

Tag Archives: pg_hba.conf

PostgreSQL

PostgreSQL DBA Step by Step Learning

pg_basebackup

pg_basebackup – Backup, Restore, and Recovery

What is pg_basebackup?

Common Use Cases:

———- Backup ———-

Pre-requisites parameter and config:

1. User : Requires a user with replication role or superuser privileges

2. postgresql.conf

3. pg_hba.conf

How pg_basebackup Works Internally:

What It Includes:

WAL Handling Options:

How to take Backup using pg_basebackup ?

———- Restore ———-

1. Restore is a File-Level Operation

Restore Steps:

2. Custom Tablespaces Outside `PGDATA`

3. Restoring on a Different Host

4. Restoring Across PostgreSQL Versions

———- Recovery ———-

How Recovery Works:

What is recovery.signal ?

Summary

PostgreSQL pg_hba.conf

PostgreSQL pg_hba.conf Guide

Table of Contents

PSQL

PostgreSQL DBA Step by Step Learning

PostgreSQL DBA Step by Step Learning

pg_basebackup – Backup, Restore, and Recovery

What is pg_basebackup?

Common Use Cases:

———- Backup ———-

Pre-requisites parameter and config:

1. User : Requires a user with replication role or superuser privileges

2. postgresql.conf

3. pg_hba.conf

How pg_basebackup Works Internally:

What It Includes:

WAL Handling Options:

How to take Backup using pg_basebackup ?

———- Restore ———-

1. Restore is a File-Level Operation

Restore Steps:

2. Custom Tablespaces Outside PGDATA

3. Restoring on a Different Host

4. Restoring Across PostgreSQL Versions

———- Recovery ———-

How Recovery Works:

What is recovery.signal ?

Summary

PostgreSQL pg_hba.conf Guide

Table of Contents

PostgreSQL DBA Step by Step Learning

2. Custom Tablespaces Outside `PGDATA`