Compare commits

..

18 Commits

Author SHA1 Message Date
Mario Gonzalez
c0d9dc6dac Update HISTORY and appendix for v5.5.0
References: HL-38
2024-11-22 11:34:48 -03:00
Mario Gonzalez
836894c965 Bump repmgr.control to 5.5
References: HL-38
2024-11-21 14:42:50 +01:00
Mario Gonzalez
7f3a26f0d9 Add primary_node_info inline function
When a t_node_info struct must be re initilised, it was re-declared
only. Moreover, a macro was user for any var creation of this type
impeding use the same to reset the values later if needed.

This new function allows to re initilise again a t_node_info typed
variable without the need to redeclare it to create other varibles for
the same purpose, and also shadowing is now avoided from pg16.

Macros seems to be replaced by `static inline` functions in upstream
postgres, credits to  Alvaro Herrera <alvherre@alvh.no-ip.org> for this
idea.

References: HL-40
2024-11-18 09:46:14 -03:00
Mario Gonzalez
a469221e28 Fix shadowed declaration
Since b5934bfd6071 in postgresql.git the flag
`-Wshadow=compatible-local` is activated. This commit fixes any
duplicated declaration made in the same function.

References: HL-40
2024-11-18 09:46:14 -03:00
Mario Gonzalez
c6d9f38458 Bump repmgr version 5.5.0 2024-11-15 10:51:12 -03:00
Francisco Miguel Biete Banon
5abdbb0d39 Definition moved to a different header 2024-10-28 09:37:30 -03:00
Martín Marqués
8f27e3bc5d Fix wrong reference to connection from commit f69485c0
Commit f69485c0 introduced a change in how we check if the repmgr
user can run checkpoints on PG15 and newer.

There was a regression in the messages where the conn passed
was not declared. That is because the pointer we were using was
called local_conn instead of conn.

Signed-off-by: Martín Marqués <martin.marques@enterprisedb.com>
Co-authored-by: Mario Gonzalez <mario.gonzalez@enterprisedb.com>
2024-10-22 15:40:56 -03:00
RealGreenDragon
b92d43d136 Fixed repmgr.conf.sample 2024-10-14 14:46:27 +02:00
RealGreenDragon
4a28c57bc7 Check for USAGE (instead of MEMBER) privilege in all pg_has_role occurrences 2024-09-11 20:17:32 +02:00
RealGreenDragon
f69485c0ba Added check for pg_checkpoint role presence (#807)
* Added check for pg_checkpoint role presence

This commit provides the needed infrastructure in `repmgr` so if the `repmgr` database
user is a member of the `pg_checkpoint` role, and inherits its privileges, there is no 
need for such a user to be a superuser.

Co-authored-by: Martín Marqués <martin.marques@enterprisedb.com>
2024-09-11 15:13:44 -03:00
Martín Marqués
b4a0938081 Update Authors and version on README
Signed-off-by: Martín Marqués <martin.marques@enterprisedb.com>
2024-09-09 18:00:42 +02:00
Martín Marqués
569f906003 Add CODEOWNERS to the repmgr repo
Signed-off-by: Martín Marqués <martin.marques@enterprisedb.com>
2024-09-09 16:30:50 +02:00
RealGreenDragon
94b21ae8ac Fixed standby_disconnect_on_failover description in repmgr.conf 2024-09-09 15:29:48 +02:00
RealGreenDragon
4c9cca64d0 Fixed standby_disconnect_on_failover docs 2024-09-09 15:29:48 +02:00
RealGreenDragon
82e2fd66e1 Fixed can_disable_walsender indentation and warning message 2024-09-09 15:29:48 +02:00
RealGreenDragon
90fe1b8135 Fixed indentation 2024-09-09 15:29:48 +02:00
RealGreenDragon
1cd168360e Added ALTER SYSTEM permission in docs 2024-09-09 15:29:48 +02:00
RealGreenDragon
e8aa3aced7 Added check for ALTER SYSTEM permission presence 2024-09-09 15:29:48 +02:00
24 changed files with 463 additions and 187 deletions

7
.github/CODEOWNERS vendored Normal file
View File

@@ -0,0 +1,7 @@
# Each line is a file pattern followed by one or more owners.
# These owners will be the default owners for everything in
# the repo. Unless a later match takes precedence,
# @global-owner1 and @global-owner2 will be requested for
# review when someone opens a pull request.
* @EnterpriseDB/repmgr-dev

View File

@@ -1,99 +0,0 @@
###
# Foundation-security BlackDuck workflow
# version: 2.1
###
name: Foundation-Security/Black Duck Scan
on:
push:
tags:
- "**"
pull_request:
types: [opened, synchronize, reopened]
branches:
- "**"
schedule:
- cron: "0 3 * * *" # 3:00 AM UTC / 10PM EST
workflow_dispatch:
inputs:
scan-mode:
description: "BlackDuck Scan mode"
required: true
type: choice
options:
- RAPID
- INTELLIGENT
default: RAPID
ref:
description: "Branch to scan"
required: true
jobs:
Blackduck-Scan:
runs-on: ubuntu-22.04
permissions:
id-token: write
contents: read
steps:
- name: Checkout source repository for dispatch runs
id: checkout-source-dispatch
if: github.event_name == 'workflow_dispatch'
uses: actions/checkout@v4
with:
repository: ${{ github.repository }}
ref: ${{ inputs.ref }}
path: source
token: ${{ secrets.GH_SLONIK }}
- name: Set project name and version for dispatch runs
id: set-project-name-and-version-dispatch
if: github.event_name == 'workflow_dispatch'
run: |
echo "PROJECT_NAME=${{ github.event.repository.name }}" >> "$GITHUB_ENV"
echo "PROJECT_VERSION=${{ inputs.ref }}" >> "$GITHUB_ENV"
- name: Checkout source repository for non-dispatch runs
id: checkout-source
if: github.event_name != 'workflow_dispatch'
uses: actions/checkout@v4
with:
repository: ${{ github.repository }}
ref: ${{ github.ref }}
path: source
token: ${{ secrets.GH_SLONIK }}
- name: Set project name and version for non-dispatch runs
id: set-project-name-and-version
if: github.event_name != 'workflow_dispatch'
run: |
echo "PROJECT_NAME=${{ github.event.repository.name }}" >> "$GITHUB_ENV"
echo "PROJECT_VERSION=${{ github.ref_name }}" >> "$GITHUB_ENV"
- name: Get short hash
shell: bash
if: ${{ inputs.scan-mode == 'INTELLIGENT' }}
run: |
cd source
echo "sha_short=$(git rev-parse --short "$GITHUB_SHA")" >> "$GITHUB_ENV"
- name: Checkout foundation-security repository
id: checkout-foundation-security
uses: actions/checkout@v4
with:
repository: EnterpriseDB/foundation-security
ref: v2
path: foundation-security
token: ${{secrets.GH_SLONIK}}
- name: BlackDuck Scan
id: call-bd-action
uses: ./foundation-security/actions/blackduck
with:
github-token: ${{ secrets.GH_SLONIK }}
cloudsmith-token: ${{ secrets.CLOUDSMITH_READ_ALL }}
commit-hash: ${{ env.sha_short }}
git-tag: ${{ github.tag }}
blackduck-url: ${{ vars.BD_URL }}
blackduck-api-token: ${{ secrets.BLACKDUCK_API_TOKEN }}
project-name: ${{ env.PROJECT_NAME }}
project-version: ${{ env.PROJECT_VERSION }}

View File

@@ -1,4 +1,9 @@
5.4.1 2023-??-??
5.5.0 2024-11-20
Support for PostgreSQL 17 added
Fix warnings detected by the -Wshadow=compatible-local
added in PostgreSQL 16
5.4.1 2023-07-04
repmgrd: ensure witness node metadata is updated (Ian)
5.4.0 2023-03-16

View File

@@ -32,7 +32,9 @@ DATA = \
repmgr--5.2--5.3.sql \
repmgr--5.3.sql \
repmgr--5.3--5.4.sql \
repmgr--5.4.sql
repmgr--5.4.sql \
repmgr--5.4--5.5.sql \
repmgr--5.5.sql
REGRESS = repmgr_extension

View File

@@ -7,8 +7,9 @@ replication capabilities with utilities to set up standby servers, monitor
replication, and perform administrative tasks such as failover or switchover
operations.
The most recent `repmgr` version (5.3.2) supports all PostgreSQL versions from
9.5 to 15. PostgreSQL 9.4 is also supported, with some restrictions.
The most recent `repmgr` version (5.5.x) supports all PostgreSQL versions from
13 to 17. Despite it could be used with some older ones, some features might not
be available, however, it's strongly recommended to use the latest version.
`repmgr` is distributed under the GNU GPL 3 and maintained by EnterpriseDB.
@@ -56,8 +57,6 @@ There is a mailing list/forum to discuss contributions or issues:
* https://groups.google.com/group/repmgr
The IRC channel #repmgr is registered with freenode.
Please report bugs and other issues to:
* https://github.com/EnterpriseDB/repmgr
@@ -69,6 +68,14 @@ news are always welcome.
Thanks from the repmgr core team.
* Ian Barwick
* Israel Barth
* Mario González
* Martín Marqués
* Gianni Ciolli
Past contributors:
* Jaime Casanova
* Abhijit Menon-Sen
* Simon Riggs

View File

@@ -1,6 +1,6 @@
AC_INIT([repmgr], [5.4.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
AC_INIT([repmgr], [5.5.0], [repmgr@googlegroups.com], [repmgr], [https://repmgr.org/])
AC_COPYRIGHT([Copyright (c) 2010-2021, EnterpriseDB Corporation])
AC_COPYRIGHT([Copyright (c) 2010-2024, EnterpriseDB Corporation])
AC_CONFIG_HEADER(config.h)

106
dbutils.c
View File

@@ -1624,7 +1624,7 @@ get_ready_archive_files(PGconn *conn, const char *data_directory)
while ((arcdir_ent = readdir(arcdir)) != NULL)
{
struct stat statbuf;
struct stat local_statbuf;
char file_path[MAXPGPATH + sizeof(arcdir_ent->d_name)];
int basenamelen = 0;
@@ -1634,7 +1634,7 @@ get_ready_archive_files(PGconn *conn, const char *data_directory)
arcdir_ent->d_name);
/* skip non-files */
if (stat(file_path, &statbuf) == 0 && !S_ISREG(statbuf.st_mode))
if (stat(file_path, &local_statbuf) == 0 && !S_ISREG(local_statbuf.st_mode))
{
continue;
}
@@ -1852,6 +1852,51 @@ get_wal_receiver_pid(PGconn *conn)
/* =============================== */
/*
* Determine if the user associated with the current connection can execute CHECKPOINT command.
* User must be a supersuer or a member of the pg_checkpoint default role (available from PostgreSQL 15).
*/
bool
can_execute_checkpoint(PGconn *conn)
{
PQExpBufferData query;
PGresult *res;
bool has_pg_checkpoint_role = false;
/* superusers can do anything, no role check needed */
if (is_superuser_connection(conn, NULL) == true)
return true;
/* pg_checkpoint available from PostgreSQL 15 */
if (PQserverVersion(conn) < 150000)
return false;
initPQExpBuffer(&query);
appendPQExpBufferStr(&query,
" SELECT pg_catalog.pg_has_role('pg_checkpoint','USAGE') ");
res = PQexec(conn, query.data);
if (PQresultStatus(res) != PGRES_TUPLES_OK)
{
log_db_error(conn, query.data,
_("can_execute_checkpoint(): unable to query user roles"));
}
else
{
has_pg_checkpoint_role = atobool(PQgetvalue(res, 0, 0));
}
termPQExpBuffer(&query);
PQclear(res);
return has_pg_checkpoint_role;
}
/*
* Determine if the user associated with the current connection
* has sufficient permissions to use pg_promote function
*/
bool
can_execute_pg_promote(PGconn *conn)
{
@@ -1913,15 +1958,47 @@ can_disable_walsender(PGconn *conn)
if (is_superuser_connection(conn, NULL) == true)
return true;
/*
* As of PostgreSQL 14, it is not possible for a non-superuser
* to execute ALTER SYSTEM, so further checks are superfluous.
* This will need modifying for PostgreSQL 15.
*/
log_warning(_("\"standby_disconnect_on_failover\" specified, but repmgr user is not a superuser"));
log_detail(_("superuser permission required to disable standbys on failover"));
PQExpBufferData query;
PGresult *res;
bool has_alter_system_priv = false;
return false;
/* GRANT ALTER SYSTEM available from PostgreSQL 15 */
if (PQserverVersion(conn) >= 150000)
{
initPQExpBuffer(&query);
appendPQExpBufferStr(&query,
" SELECT pg_catalog.has_parameter_privilege('wal_retrieve_retry_interval', 'ALTER SYSTEM') ");
res = PQexec(conn, query.data);
if (PQresultStatus(res) != PGRES_TUPLES_OK)
{
log_db_error(conn, query.data,
_("can_disable_walsender(): unable to query user parameter privileges"));
}
else
{
has_alter_system_priv = atobool(PQgetvalue(res, 0, 0));
}
termPQExpBuffer(&query);
PQclear(res);
}
if (has_alter_system_priv == false)
{
log_warning(_("\"standby_disconnect_on_failover\" specified, but repmgr user is not authorized to perform ALTER SYSTEM wal_retrieve_retry_interval"));
if (PQserverVersion(conn) >= 150000)
{
log_detail(_("superuser or ALTER SYSTEM wal_retrieve_retry_interval permission required to disable standbys on failover"));
}
else
{
log_detail(_("superuser permission required to disable standbys on failover"));
}
}
return has_alter_system_priv;
}
/*
@@ -1947,13 +2024,13 @@ connection_has_pg_monitor_role(PGconn *conn, const char *subrole)
initPQExpBuffer(&query);
appendPQExpBufferStr(&query,
" SELECT CASE "
" WHEN pg_catalog.pg_has_role('pg_monitor','MEMBER') "
" WHEN pg_catalog.pg_has_role('pg_monitor','USAGE') "
" THEN TRUE ");
if (subrole != NULL)
{
appendPQExpBuffer(&query,
" WHEN pg_catalog.pg_has_role('%s','MEMBER') "
" WHEN pg_catalog.pg_has_role('%s','USAGE') "
" THEN TRUE ",
subrole);
}
@@ -2460,7 +2537,10 @@ get_repmgr_extension_status(PGconn *conn, t_extension_versions *extversions)
/* node management functions */
/* ========================= */
/* assumes superuser connection */
/*
* Assumes the connection can execute CHECKPOINT command.
* A check can be executed via 'can_execute_checkpoint' function.
*/
void
checkpoint(PGconn *conn)
{

View File

@@ -453,6 +453,7 @@ TimeLineHistoryEntry *get_timeline_history(PGconn *repl_conn, TimeLineID tli);
pid_t get_wal_receiver_pid(PGconn *conn);
/* user/role information functions */
bool can_execute_checkpoint(PGconn *conn);
bool can_execute_pg_promote(PGconn *conn);
bool can_disable_walsender(PGconn *conn);
bool connection_has_pg_monitor_role(PGconn *conn, const char *subrole);

View File

@@ -16,9 +16,24 @@
</para>
<!-- remember to update the release date in ../repmgr_version.h.in -->
<sect1 id="release-5.5.0">
<title>Release 5.5.0</title>
<para><emphasis>Wed 20 November, 2024</emphasis></para>
<para>
&repmgr; 5.5.0 is a major release.
</para>
<para>
This release adds support for PostgreSQL 17
</para>
<para>
Fixes warnings detected by the -Wshadow gcc flag added in PostgreSQL 16.
</para>
</sect1>
<sect1 id="release-5.4.1">
<title id="release-current">Release 5.4.1</title>
<para><emphasis>??? ?? ??????, 202?</emphasis></para>
<para><emphasis>Tue 04 Jul, 2023</emphasis></para>
<para>
&repmgr; 5.4.1 is a minor release providing ...
</para>

View File

@@ -79,6 +79,10 @@
Alternatively the meta-role <varname>pg_monitor</varname> can be granted, which includes membership
of the above predefined roles.
</para>
<para>
PostgreSQL 15 introduced the <varname>pg_checkpoint</varname> predefined role which allows a
non-superuser &repmgr; database user to perform a CHECKPOINT command.
</para>
<para>
Membership of these roles can be granted with e.g. <command>GRANT pg_read_all_stats TO repmgr</command>.
</para>
@@ -148,6 +152,8 @@
<link linkend="repmgr-standby-switchover">repmgr standby switchover</link>. This can only
be executed by a superuser; if the &repmgr; user is not a superuser,
the <option>-S</option>/<option>--superuser</option> should be used.
From PostgreSQL 15 the <varname>pg_checkpoint</varname> predefined role removes the need of
superuser permissions to perform <command>CHECKPOINT</command> command.
</simpara>
<simpara>
If &repmgr; is not able to execute <command>CHECKPOINT</command>,
@@ -159,8 +165,10 @@
<simpara>
The <command>ALTER SYSTEM</command> is executed by &repmgrd; if
<varname>standby_disconnect_on_failover</varname> is set to <literal>true</literal> in
<filename>repmgr.conf</filename>. <command>ALTER SYSTEM</command> can only be executed by
<filename>repmgr.conf</filename>. Until PostgreSQL 14 <command>ALTER SYSTEM</command> can only be executed by
a superuser; if the &repmgr; user is not a superuser, this functionality will not be available.
From PostgreSQL 15 a specific ALTER SYSTEM privilege can be granted with e.g.
<command>GRANT ALTER SYSTEM ON PARAMETER wal_retrieve_retry_interval TO repmgr</command>.
</simpara>
</listitem>
</itemizedlist>

View File

@@ -77,7 +77,8 @@
</para>
<para>
Note that a superuser connection is required to be able to execute the
<command>CHECKPOINT</command> command.
<command>CHECKPOINT</command> command. From PostgreSQL 15 the <varname>pg_checkpoint</varname>
predefined role removes the need for superuser permissions to perform <command>CHECKPOINT</command> command.
</para>
</listitem>
</varlistentry>

View File

@@ -79,7 +79,8 @@
<para>
Note that <command>CHECKPOINT</command> requires database superuser permissions to execute.
If the <literal>repmgr</literal> user is not a superuser, the name of a superuser should be
provided with the <option>-S</option>/<option>--superuser</option> option.
provided with the <option>-S</option>/<option>--superuser</option> option. From PostgreSQL 15 the <varname>pg_checkpoint</varname>
predefined role removes the need for superuser permissions to perform <command>CHECKPOINT</command> command.
</para>
<para>
If &repmgr; is unable to execute the <command>CHECKPOINT</command> command, the switchover

View File

@@ -26,7 +26,7 @@
<abstract>
<para>
This is the official documentation of &repmgr; &repmgrversion; for
use with PostgreSQL 9.4 - PostgreSQL 15.
use with PostgreSQL 12 - PostgreSQL 17.
</para>
<para>
&repmgr; is being continually developed and we strongly recommend using the

View File

@@ -279,7 +279,9 @@
<note>
<para>
<option>standby_disconnect_on_failover</option> is available with PostgreSQL 9.5 and later.
Additionally this requires that the <literal>repmgr</literal> database user is a superuser.
Until PostgreSQL 14 this requires that the <literal>repmgr</literal> database user is a superuser.
From PostgreSQL 15 a specific ALTER SYSTEM privilege can be granted to the <literal>repmgr</literal> database
user with e.g. <command>GRANT ALTER SYSTEM ON PARAMETER wal_retrieve_retry_interval TO repmgr</command>.
</para>
</note>
<para>

2
repmgr--5.4--5.5.sql Normal file
View File

@@ -0,0 +1,2 @@
-- complain if script is sourced in psql, rather than via CREAT EXTENSION
\echo Use "CREATE EXTENSION repmgr" to load this file. \quit

191
repmgr--5.5.sql Normal file
View File

@@ -0,0 +1,191 @@
-- complain if script is sourced in psql, rather than via CREATE EXTENSION
\echo Use "CREATE EXTENSION repmgr" to load this file. \quit
CREATE TABLE repmgr.nodes (
node_id INTEGER PRIMARY KEY,
upstream_node_id INTEGER NULL REFERENCES nodes (node_id) DEFERRABLE,
active BOOLEAN NOT NULL DEFAULT TRUE,
node_name TEXT NOT NULL,
type TEXT NOT NULL CHECK (type IN('primary','standby','witness','bdr')),
location TEXT NOT NULL DEFAULT 'default',
priority INT NOT NULL DEFAULT 100,
conninfo TEXT NOT NULL,
repluser VARCHAR(63) NOT NULL,
slot_name TEXT NULL,
config_file TEXT NOT NULL
);
SELECT pg_catalog.pg_extension_config_dump('repmgr.nodes', '');
CREATE TABLE repmgr.events (
node_id INTEGER NOT NULL,
event TEXT NOT NULL,
successful BOOLEAN NOT NULL DEFAULT TRUE,
event_timestamp TIMESTAMP WITH TIME ZONE NOT NULL DEFAULT CURRENT_TIMESTAMP,
details TEXT NULL
);
SELECT pg_catalog.pg_extension_config_dump('repmgr.events', '');
CREATE TABLE repmgr.monitoring_history (
primary_node_id INTEGER NOT NULL,
standby_node_id INTEGER NOT NULL,
last_monitor_time TIMESTAMP WITH TIME ZONE NOT NULL,
last_apply_time TIMESTAMP WITH TIME ZONE,
last_wal_primary_location PG_LSN NOT NULL,
last_wal_standby_location PG_LSN,
replication_lag BIGINT NOT NULL,
apply_lag BIGINT NOT NULL
);
CREATE INDEX idx_monitoring_history_time
ON repmgr.monitoring_history (last_monitor_time, standby_node_id);
SELECT pg_catalog.pg_extension_config_dump('repmgr.monitoring_history', '');
CREATE VIEW repmgr.show_nodes AS
SELECT n.node_id,
n.node_name,
n.active,
n.upstream_node_id,
un.node_name AS upstream_node_name,
n.type,
n.priority,
n.conninfo
FROM repmgr.nodes n
LEFT JOIN repmgr.nodes un
ON un.node_id = n.upstream_node_id;
CREATE TABLE repmgr.voting_term (
term INT NOT NULL
);
CREATE UNIQUE INDEX voting_term_restrict
ON repmgr.voting_term ((TRUE));
CREATE RULE voting_term_delete AS
ON DELETE TO repmgr.voting_term
DO INSTEAD NOTHING;
/* ================= */
/* repmgrd functions */
/* ================= */
/* monitoring functions */
CREATE FUNCTION set_local_node_id(INT)
RETURNS VOID
AS 'MODULE_PATHNAME', 'repmgr_set_local_node_id'
LANGUAGE C STRICT;
CREATE FUNCTION get_local_node_id()
RETURNS INT
AS 'MODULE_PATHNAME', 'repmgr_get_local_node_id'
LANGUAGE C STRICT;
CREATE FUNCTION standby_set_last_updated()
RETURNS TIMESTAMP WITH TIME ZONE
AS 'MODULE_PATHNAME', 'repmgr_standby_set_last_updated'
LANGUAGE C STRICT;
CREATE FUNCTION standby_get_last_updated()
RETURNS TIMESTAMP WITH TIME ZONE
AS 'MODULE_PATHNAME', 'repmgr_standby_get_last_updated'
LANGUAGE C STRICT;
CREATE FUNCTION set_upstream_last_seen(INT)
RETURNS VOID
AS 'MODULE_PATHNAME', 'repmgr_set_upstream_last_seen'
LANGUAGE C STRICT;
CREATE FUNCTION get_upstream_last_seen()
RETURNS INT
AS 'MODULE_PATHNAME', 'repmgr_get_upstream_last_seen'
LANGUAGE C STRICT;
CREATE FUNCTION get_upstream_node_id()
RETURNS INT
AS 'MODULE_PATHNAME', 'repmgr_get_upstream_node_id'
LANGUAGE C STRICT;
CREATE FUNCTION set_upstream_node_id(INT)
RETURNS VOID
AS 'MODULE_PATHNAME', 'repmgr_set_upstream_node_id'
LANGUAGE C STRICT;
/* failover functions */
CREATE FUNCTION notify_follow_primary(INT)
RETURNS VOID
AS 'MODULE_PATHNAME', 'repmgr_notify_follow_primary'
LANGUAGE C STRICT;
CREATE FUNCTION get_new_primary()
RETURNS INT
AS 'MODULE_PATHNAME', 'repmgr_get_new_primary'
LANGUAGE C STRICT;
CREATE FUNCTION reset_voting_status()
RETURNS VOID
AS 'MODULE_PATHNAME', 'repmgr_reset_voting_status'
LANGUAGE C STRICT;
CREATE FUNCTION get_repmgrd_pid()
RETURNS INT
AS 'MODULE_PATHNAME', 'get_repmgrd_pid'
LANGUAGE C STRICT;
CREATE FUNCTION get_repmgrd_pidfile()
RETURNS TEXT
AS 'MODULE_PATHNAME', 'get_repmgrd_pidfile'
LANGUAGE C STRICT;
CREATE FUNCTION set_repmgrd_pid(INT, TEXT)
RETURNS VOID
AS 'MODULE_PATHNAME', 'set_repmgrd_pid'
LANGUAGE C CALLED ON NULL INPUT;
CREATE FUNCTION repmgrd_is_running()
RETURNS BOOL
AS 'MODULE_PATHNAME', 'repmgrd_is_running'
LANGUAGE C STRICT;
CREATE FUNCTION repmgrd_pause(BOOL)
RETURNS VOID
AS 'MODULE_PATHNAME', 'repmgrd_pause'
LANGUAGE C STRICT;
CREATE FUNCTION repmgrd_is_paused()
RETURNS BOOL
AS 'MODULE_PATHNAME', 'repmgrd_is_paused'
LANGUAGE C STRICT;
CREATE FUNCTION get_wal_receiver_pid()
RETURNS INT
AS 'MODULE_PATHNAME', 'repmgr_get_wal_receiver_pid'
LANGUAGE C STRICT;
/* views */
CREATE VIEW repmgr.replication_status AS
SELECT m.primary_node_id, m.standby_node_id, n.node_name AS standby_name,
n.type AS node_type, n.active, last_monitor_time,
CASE WHEN n.type='standby' THEN m.last_wal_primary_location ELSE NULL END AS last_wal_primary_location,
m.last_wal_standby_location,
CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.replication_lag) ELSE NULL END AS replication_lag,
CASE WHEN n.type='standby' THEN
CASE WHEN replication_lag > 0 THEN age(now(), m.last_apply_time) ELSE '0'::INTERVAL END
ELSE NULL
END AS replication_time_lag,
CASE WHEN n.type='standby' THEN pg_catalog.pg_size_pretty(m.apply_lag) ELSE NULL END AS apply_lag,
AGE(NOW(), CASE WHEN pg_catalog.pg_is_in_recovery() THEN repmgr.standby_get_last_updated() ELSE m.last_monitor_time END) AS communication_time_lag
FROM repmgr.monitoring_history m
JOIN repmgr.nodes n ON m.standby_node_id = n.node_id
WHERE (m.standby_node_id, m.last_monitor_time) IN (
SELECT m1.standby_node_id, MAX(m1.last_monitor_time)
FROM repmgr.monitoring_history m1 GROUP BY 1
);

View File

@@ -394,7 +394,6 @@ do_node_status(void)
if (node_info.inactive_replication_slots > 0)
{
KeyValueList inactive_replication_slots = {NULL, NULL};
KeyValueListCell *cell = NULL;
(void) get_inactive_replication_slots(conn, &inactive_replication_slots);
@@ -524,8 +523,6 @@ do_node_status(void)
if (node_info.inactive_replication_slots)
{
KeyValueList inactive_replication_slots = {NULL, NULL};
KeyValueListCell *cell = NULL;
(void) get_inactive_replication_slots(conn, &inactive_replication_slots);
for (cell = inactive_replication_slots.head; cell; cell = cell->next)
{
@@ -2365,18 +2362,25 @@ do_node_service(void)
conn = establish_db_connection_by_params(&source_conninfo, true);
}
if (is_superuser_connection(conn, NULL) == false)
if (can_execute_checkpoint(conn) == false)
{
if (runtime_options.dry_run == true)
{
log_warning(_("a CHECKPOINT would be issued here but no superuser connection is available"));
log_warning(_("a CHECKPOINT would be issued here but no authorized connection is available"));
}
else
{
log_warning(_("a superuser connection is required to issue a CHECKPOINT"));
log_warning(_("an authorized connection is required to issue a CHECKPOINT"));
}
log_hint(_("provide a superuser with -S/--superuser"));
if (PQserverVersion(conn) >= 150000)
{
log_hint(_("provide a superuser with -S/--superuser or grant pg_checkpoint role to repmgr user"));
}
else
{
log_hint(_("provide a superuser with -S/--superuser"));
}
}
else
{
@@ -2539,6 +2543,7 @@ do_node_rejoin(void)
int server_version_num = UNKNOWN_SERVER_VERSION_NUM;
bool hide_standby_signal = false;
KeyValueListCell *cell = NULL;
PQExpBufferData command;
PQExpBufferData command_output;
PQExpBufferData follow_output;
@@ -2958,7 +2963,7 @@ do_node_rejoin(void)
else
{
while ((slotdir_ent = readdir(slotdir)) != NULL) {
struct stat statbuf;
struct stat local_statbuf;
PQExpBufferData slotdir_ent_path;
if (strcmp(slotdir_ent->d_name, ".") == 0 || strcmp(slotdir_ent->d_name, "..") == 0)
@@ -2971,7 +2976,7 @@ do_node_rejoin(void)
slotdir_path.data,
slotdir_ent->d_name);
if (stat(slotdir_ent_path.data, &statbuf) == 0 && !S_ISDIR(statbuf.st_mode))
if (stat(slotdir_ent_path.data, &local_statbuf) == 0 && !S_ISDIR(local_statbuf.st_mode))
{
termPQExpBuffer(&slotdir_ent_path);
continue;
@@ -3102,7 +3107,6 @@ do_node_rejoin(void)
else
{
KeyValueList inactive_replication_slots = {NULL, NULL};
KeyValueListCell *cell = NULL;
int inactive_count = 0;
PQExpBufferData slotinfo;

View File

@@ -235,6 +235,38 @@ do_primary_register(void)
return;
}
static inline void reset_node_info(t_node_info *info)
{
info->node_id = NODE_NOT_FOUND;
info->upstream_node_id = NO_UPSTREAM_NODE;
info->type = UNKNOWN;
info->node_name[0] = '\0';
info->upstream_node_name[0] = '\0';
info->conninfo[0] = '\0';
info->repluser[0] = '\0';
info->priority = DEFAULT_PRIORITY;
info->active = true;
info->slot_name[0] = '\0';
info->config_file[0] = '\0';
info->last_wal_receive_lsn = InvalidXLogRecPtr;
info->node_status = NODE_STATUS_UNKNOWN;
info->recovery_type = RECTYPE_UNKNOWN;
info->monitoring_state = MS_NORMAL;
info->conn = NULL;
info->details[0] = '\0';
info->reachable = true;
info->attached = true;
/* various statistics */
info->max_wal_senders = -1;
info->attached_wal_receivers = -1;
info->max_replication_slots = -1;
info->total_replication_slots = -1;
info->active_replication_slots = -1;
info->inactive_replication_slots = -1;
info->replication_info = NULL;
strlcpy(info->location, DEFAULT_LOCATION, sizeof(info->location));
}
/*
* do_primary_unregister()
@@ -436,7 +468,7 @@ do_primary_unregister(void)
}
else if (recovery_type == RECTYPE_PRIMARY)
{
t_node_info primary_node_info = T_NODE_INFO_INITIALIZER;
reset_node_info(&primary_node_info);
bool primary_record_found = false;
primary_record_found = get_primary_node_record(primary_conn, &primary_node_info);

View File

@@ -535,7 +535,7 @@ do_standby_clone(void)
if (external_config_files == true)
{
int r;
r = 0;
PQExpBufferData msg;
initPQExpBuffer(&msg);
@@ -762,7 +762,7 @@ do_standby_clone(void)
if (mode == pg_basebackup && runtime_options.verify_backup == true)
{
PQExpBufferData command;
int r;
r = 0;
struct stat st;
initPQExpBuffer(&command);
@@ -3927,7 +3927,6 @@ do_standby_switchover(void)
if (PQserverVersion(local_conn) < 130000 && is_wal_replay_paused(local_conn, false) == true)
{
ReplInfo replication_info;
init_replication_info(&replication_info);
if (get_replication_info(local_conn, STANDBY, &replication_info) == false)
@@ -4784,7 +4783,7 @@ do_standby_switchover(void)
{
NodeInfoListCell *cell = NULL;
ItemList repmgrd_connection_errors = {NULL, NULL};
int i = 0;
i = 0;
int unreachable_node_count = 0;
get_all_node_records(local_conn, &all_nodes);
@@ -5099,8 +5098,6 @@ do_standby_switchover(void)
/* database server could not be contacted */
if (ping_res == PQPING_NO_RESPONSE || ping_res == PQPING_NO_ATTEMPT)
{
bool command_success;
/*
* remote server can't be contacted at protocol level - that
* doesn't necessarily mean it's shut down, so we'll ask its
@@ -5288,7 +5285,7 @@ do_standby_switchover(void)
checkpoint_conn = superuser_conn;
}
if (is_superuser_connection(checkpoint_conn, NULL) == true)
if (can_execute_checkpoint(checkpoint_conn) == true)
{
log_notice(_("issuing CHECKPOINT on node \"%s\" (ID: %i) "),
config_file_options.node_name,
@@ -5297,7 +5294,16 @@ do_standby_switchover(void)
}
else
{
log_warning(_("no superuser connection available, unable to issue CHECKPOINT"));
log_warning(_("no authorized connection available, unable to issue CHECKPOINT"));
if (PQserverVersion(local_conn) >= 150000)
{
log_hint(_("provide a superuser with -S/--superuser or grant pg_checkpoint role to repmgr user"));
}
else
{
log_hint(_("provide a superuser with -S/--superuser"));
}
}
}
@@ -5669,7 +5675,7 @@ do_standby_switchover(void)
{
ItemList repmgrd_unpause_errors = {NULL, NULL};
NodeInfoListCell *cell = NULL;
int i = 0;
i = 0;
int error_node_count = 0;
for (cell = all_nodes.head; cell; cell = cell->next)
@@ -6504,12 +6510,12 @@ check_upstream_config(PGconn *conn, int server_version_num, t_node_info *upstrea
if (mode == pg_basebackup)
{
PGconn **connections;
int i;
int available_wal_senders;
int min_replication_connections = 1;
int possible_replication_connections = 0;
t_conninfo_param_list repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
PGconn **connections;
int available_wal_senders;
int min_replication_connections = 1;
int possible_replication_connections = 0;
i = 0;
t_conninfo_param_list repl_conninfo = T_CONNINFO_PARAM_LIST_INITIALIZER;
/*
@@ -8471,7 +8477,6 @@ check_sibling_nodes(NodeInfoList *sibling_nodes, SiblingNodeStats *sibling_nodes
if (sibling_nodes->node_count > 0)
{
PQExpBufferData nodes;
NodeInfoListCell *cell;
initPQExpBuffer(&nodes);

View File

@@ -70,7 +70,11 @@
#include "repmgr-action-service.h"
#include "repmgr-action-daemon.h"
#if (PG_VERSION_NUM >= 170000)
#include <common/file_utils.h> /* for PG_TEMP_FILE_PREFIX */
#else
#include <storage/fd.h> /* for PG_TEMP_FILE_PREFIX */
#endif
/* globally available variables *
* ============================ */

View File

@@ -12,7 +12,7 @@
#
# For details on the configuration file format see the documentation at:
#
# https://repmgr.org/docs/current/configuration-file.html#CONFIGURATION-FILE-FORMAT
# https://repmgr.org/docs/current/configuration-file.html#CONFIGURATION-FILE-FORMAT
#
# =============================================================================
# Required configuration items
@@ -76,7 +76,7 @@
#location='default' # An arbitrary string defining the location of the node; this
# is used during failover to check visibility of the
# current primary node. For further details see:
# https://repmgr.org/docs/current/repmgrd-network-split.html
# https://repmgr.org/docs/current/repmgrd-network-split.html
#use_replication_slots=no # whether to use physical replication slots
# NOTE: when using replication slots,
@@ -181,8 +181,8 @@
#pg_ctl_options='' # Options to append to "pg_ctl"
#pg_basebackup_options='' # Options to append to "pg_basebackup"
# (Note: when cloning from Barman, repmgr will honour any
# --waldir/--xlogdir setting present in "pg_basebackup_options"
# (Note: when cloning from Barman, repmgr will honour any
# --waldir/--xlogdir setting present in "pg_basebackup_options"
#rsync_options='' # Options to append to "rsync"
ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
@@ -212,8 +212,8 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
#recovery_min_apply_delay= # If provided, "recovery_min_apply_delay" will be set to
# this value (PostgreSQL 9.4 and later). Value can be
# an integer representing milliseconds, or a string
# representing a period of time (e.g. '5 min').
# an integer representing milliseconds, or a string
# representing a period of time (e.g. '5 min').
#------------------------------------------------------------------------------
@@ -299,7 +299,7 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
# a value of zero prevents the node being promoted to primary
# (default: 100)
#connection_check_type=ping # How to check availability of the upstream node; valid options:
#connection_check_type='ping' # How to check availability of the upstream node; valid options:
# 'ping': use PQping() to check if the node is accepting connections
# 'connection': attempt to make a new connection to the node
# 'query': execute an SQL statement on the node via the existing connection
@@ -340,22 +340,31 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
#repmgrd_exit_on_inactive_node=false # If "true", and the node record is marked as "inactive", abort repmgrd startup
#standby_disconnect_on_failover=false # If "true", in a failover situation wait for all standbys to
# disconnect their WAL receivers before electing a new primary
# (PostgreSQL 9.5 and later only; repmgr user must be a superuser for this)
# Can be true in PostgreSQL 9.5 and later only. Until PostgreSQL 14 repmgr user must be a superuser to use this.
# From PostgreSQL 15 repmgr must be a superuser or have 'ALTER SYSTEM wal_retrieve_retry_interval' privilege.
# (see: https://repmgr.org/docs/current/repmgrd-standby-disconnection-on-failover.html )
#sibling_nodes_disconnect_timeout=30 # If "standby_disconnect_on_failover" is true, the maximum length of time
# (in seconds) to wait for other standbys to confirm they have disconnected their
# (in seconds) to wait for other standbys to confirm they have disconnected their
# WAL receivers
#primary_visibility_consensus=false # If "true", only continue with failover if no standbys have seen
# the primary node recently. *Must* be the same on all nodes.
#always_promote=false # Always promote a node, even if repmgr metadata is outdated
#failover_validation_command='' # Script to execute for an external mechanism to validate the failover
# decision made by repmgrd. One or both of the following parameter placeholders
# should be provided, which will be replaced by repmgrd with the appropriate
# value: %n (node_id), %a (node_name). *Must* be the same on all nodes.
#failover_validation_command='' # Script to execute for an external mechanism to validate the failover
# decision made by repmgrd. Each of the following parameter placeholders
# should be provided, which will be replaced by repmgrd with the appropriate value:
# %n (node_id)
# %a (node_name)
# %v (number of visible nodes)
# %u (number of shared upstream nodes)
# %t (total number of nodes)
# *Must* be the same on all nodes.
#election_rerun_interval=15 # if "failover_validation_command" is set, and the command returns
# an error, pause the specified amount of seconds before rerunning the election.
#
# The following items are relevant for repmgrd running on the primary,
# and will be ignored on non-primary nodes
# The following items are relevant for repmgrd running on the primary,
# and will be ignored on non-primary nodes.
# (see: https://repmgr.org/docs/current/repmgrd-primary-child-disconnection.html )
#child_nodes_check_interval=5 # Interval (in seconds) to check for attached child nodes (standbys)
#child_nodes_connected_min_count=-1 # Minimum number of child nodes which must remain connected, otherwise
# disconnection command will be triggered
@@ -363,6 +372,7 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
# (ignored if "child_nodes_connected_min_count" set)
#child_nodes_disconnect_timeout=30 # Interval between child node disconnection and disconnection command execution
#child_nodes_disconnect_command='' # Command to execute if child node disconnection detected
#child_nodes_connected_include_witness=false # Whether to count the witness node (if in use) as a child node when determining whether to execute child_nodes_disconnect_command.
#------------------------------------------------------------------------------
# service control commands
@@ -385,20 +395,20 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
#
# For example, to use systemd, you can set
#
# service_start_command = 'sudo systemctl start postgresql-9.6'
# service_start_command = 'sudo systemctl start postgresql-16'
# (...)
#
# and then use the following sudoers configuration:
#
# # this is required when running sudo over ssh without -t:
# Defaults:postgres !requiretty
# postgres ALL = NOPASSWD: /usr/bin/systemctl stop postgresql-9.6, \
# /usr/bin/systemctl start postgresql-9.6, \
# /usr/bin/systemctl restart postgresql-9.6
# postgres ALL = NOPASSWD: /usr/bin/systemctl stop postgresql-16, \
# /usr/bin/systemctl start postgresql-16, \
# /usr/bin/systemctl restart postgresql-16
#
# Debian/Ubuntu users: use "sudo pg_ctlcluster" to execute service control commands.
#
# For more details, see: https://repmgr.org/docs/current/configuration-file-service-commands.html
# For further details, see: https://repmgr.org/docs/current/configuration-file-service-commands.html
#service_start_command = ''
#service_stop_command = ''
@@ -441,4 +451,3 @@ ssh_options='-q -o ConnectTimeout=10' # Options to append to "ssh"
# "repmgr standby switchover" to warn about potential
# issues with shutting down the demotion candidate.

View File

@@ -1,6 +1,6 @@
# repmgr extension
comment = 'Replication manager for PostgreSQL'
default_version = '5.4'
default_version = '5.5'
module_pathname = '$libdir/repmgr'
relocatable = false
schema = repmgr

View File

@@ -1,7 +1,7 @@
#define REPMGR_VERSION_DATE ""
#define REPMGR_VERSION "5.4dev"
#define REPMGR_VERSION_NUM 50400
#define REPMGR_EXTENSION_VERSION "5.4"
#define REPMGR_EXTENSION_NUM 50400
#define REPMGR_RELEASE_DATE "2022-XX-XX"
#define REPMGR_VERSION_DATE "2024-11-20"
#define REPMGR_VERSION "5.5.0"
#define REPMGR_VERSION_NUM 50500
#define REPMGR_EXTENSION_VERSION "5.5.0"
#define REPMGR_EXTENSION_NUM 50500
#define REPMGR_RELEASE_DATE "2024-XX-XX"
#define PG_ACTUAL_VERSION_NUM

View File

@@ -1359,6 +1359,8 @@ monitor_streaming_standby(void)
MonitoringState local_monitoring_state = MS_NORMAL;
instr_time local_degraded_monitoring_start;
bool upstream_check_result;
int degraded_monitoring_elapsed;
int last_known_upstream_node_id = UNKNOWN_NODE_ID;
log_debug("monitor_streaming_standby()");
@@ -1547,7 +1549,6 @@ monitor_streaming_standby(void)
while (true)
{
bool upstream_check_result;
log_verbose(LOG_DEBUG, "checking %s", upstream_node_info.conninfo);
@@ -1770,8 +1771,7 @@ monitor_streaming_standby(void)
if (monitoring_state == MS_DEGRADED)
{
int degraded_monitoring_elapsed = calculate_elapsed(degraded_monitoring_start);
bool upstream_check_result;
degraded_monitoring_elapsed = calculate_elapsed(degraded_monitoring_start);
if (config_file_options.degraded_monitoring_timeout > 0
&& degraded_monitoring_elapsed > config_file_options.degraded_monitoring_timeout)
@@ -1894,7 +1894,6 @@ monitor_streaming_standby(void)
*/
if (failover_state == FAILOVER_STATE_PROMOTION_FAILED)
{
int degraded_monitoring_elapsed;
int former_upstream_node_id = local_node_info.upstream_node_id;
NodeInfoList sibling_nodes = T_NODE_INFO_LIST_INITIALIZER;
PQExpBufferData event_details;
@@ -1953,7 +1952,7 @@ monitor_streaming_standby(void)
if (local_node_info.type == PRIMARY)
{
int degraded_monitoring_elapsed = calculate_elapsed(degraded_monitoring_start);
degraded_monitoring_elapsed = calculate_elapsed(degraded_monitoring_start);
log_notice(_("resuming monitoring as primary node after %i seconds"),
degraded_monitoring_elapsed);