Compare commits
No commits in common. "8d172e944c71a82ab704f80c6b48100475f17a85" and "8b03a8bc21647258257571380701fad9496779c1" have entirely different histories.
8d172e944c
...
8b03a8bc21
3 changed files with 328 additions and 357 deletions
|
@ -1,25 +0,0 @@
|
|||
# Pre-commit hooks to run tests and ensure code is cleaned.
|
||||
# See https://pre-commit.com for more information
|
||||
---
|
||||
repos:
|
||||
- repo: https://github.com/codespell-project/codespell
|
||||
rev: v2.2.2
|
||||
hooks:
|
||||
- id: codespell
|
||||
args:
|
||||
- --ignore-words-list=exten
|
||||
- --skip="./.*,*.csv,*.json,*.ini,*.subject,*.txt,*.html,*.log,*.conf"
|
||||
- --quiet-level=2
|
||||
- --ignore-regex=.*codespell-ignore$
|
||||
# - --write-changes # Uncomment to write changes
|
||||
exclude_types: [csv, json]
|
||||
- repo: https://github.com/adrienverge/yamllint
|
||||
rev: v1.32.0
|
||||
hooks:
|
||||
- id: yamllint
|
||||
ignore: .github/
|
||||
- repo: https://github.com/pre-commit/mirrors-prettier
|
||||
rev: v2.7.1
|
||||
hooks:
|
||||
- id: prettier
|
||||
args: ["--print-width", "100"]
|
14
README.md
14
README.md
|
@ -7,14 +7,14 @@ This script :
|
|||
- check if Postgres is running (_CRITICAL_ raise if not)
|
||||
- check if Postgres is in recovery mode :
|
||||
- if Postgres is in recovery mode :
|
||||
- retrieve from Postgres the last _xlog_ file receive and the _xlog_ file replay
|
||||
- retreive from Postgres the last _xlog_ file receive and the _xlog_ file replay
|
||||
- check if Postgres recovery configuration file is NOT present (_CRITICAL_ raise if present)
|
||||
- retrieve master connection information from Postgres recovery configuration file (_UNKNOWN_ raise on error). Default Postgres master TCP port will be used if port is not specify.
|
||||
- retrieve the current state and sync state of the host from Postgres master server by making a connection on master server (_UNKNOWN_ raise on error).
|
||||
- retreive master connection informations from Postgres recovery configuration file (_UNKNOWN_ raise on error). Default Postgres master TCP port will be used if port is not specify.
|
||||
- retreive the current state and sync state of the host from Postgres master server by making a connection on master server (_UNKNOWN_ raise on error).
|
||||
- check if the current state of the host is "streaming" (_CRITICAL_ raise if not)
|
||||
- check if the current sync state of the host is "sync" (or the state specified using `-e` parameter, _CRITICAL_ raise if not)
|
||||
- if the check of the current XLOG file of the master host is enabled :
|
||||
- retrieve current _xlog_ file from Postgres master server by making a connection on master server (_UNKNOWN_ raise on error).
|
||||
- retreive current _xlog_ file from Postgres master server by making a connection on master server (_UNKNOWN_ raise on error).
|
||||
- check if the current master _xlog_ file is the last received _xlog_ file (_CRITICAL_ raise if not)
|
||||
- check if the last received _xlog_ file is the last replay _xlog_ file : if not, check the current delay with the last replayed transaction against _replay_warn_delay_ and _replay_crit_delay_ thresholds and raise corresponding error if they are exceeded
|
||||
- Return _OK_ state
|
||||
|
@ -27,11 +27,11 @@ This script :
|
|||
|
||||
## Requirements
|
||||
|
||||
- Some CLI tools: `sudo`, `awk`, `sed`, `bc`, `psql` and `pg_lscluster`
|
||||
* Some CLI tools: `sudo`, `awk`, `sed`, `bc`, `psql` and `pg_lscluster`
|
||||
|
||||
- **On master node:** Slaves must be able to connect with user from `recovery.conf` / `postgresql.auto.conf` (or user specify using `-U`) to database with the same name (or another specified with `-D`) as `trust` (or using password specified in `~/.pgpass`). This user must have `SUPERUSER` privilege (need to get replication details).
|
||||
* **On master node:** Slaves must be able to connect with user from `recovery.conf` / `postgresql.auto.conf` (or user specify using `-U`) to database with the same name (or another specified with `-D`) as `trust` (or using password specified in `~/.pgpass`). This user must have `SUPERUSER` privilege (need to get replication details).
|
||||
|
||||
- **On standby node:** `PG_USER` must be able to connect locally on the database with the same name `(or another specified with -D)` as `trust` (or using password specified in `~/.pgpass`).
|
||||
* **On standby node:** `PG_USER` must be able to connect localy on the database with the same name `(or another specified with -D)` as `trust` (or using password specified in `~/.pgpass`).
|
||||
|
||||
## Installation
|
||||
|
||||
|
|
|
@ -1,5 +1,4 @@
|
|||
#!/bin/bash
|
||||
# vim: tabstop=4 shiftwidth=4 softtabstop=4 expandtab
|
||||
#
|
||||
# Nagios plugin to check Postgresql streamin replication state
|
||||
#
|
||||
|
@ -15,7 +14,7 @@
|
|||
# ~/.pgpass). This user must have SUPERUSER privilege (need to get replication
|
||||
# details).
|
||||
#
|
||||
# On standby node: PG_USER must be able to connect locally on the database with the same name
|
||||
# On standby node: PG_USER must be able to connect localy on the database with the same name
|
||||
# (or another specified with -D) as trust (or using password specified in
|
||||
# ~/.pgpass).
|
||||
#
|
||||
|
@ -58,7 +57,7 @@ Usage: $0 [-d] [-h] [options]
|
|||
-m pg_main Specify Postgres main directory path (Default: try to auto-detect or use
|
||||
$DEFAULT_PG_MAIN)
|
||||
-r recovery_conf Specify Postgres recovery configuration file path
|
||||
( Default: [PG_MAIN]/recovery.conf on PG <= 11, [PG_MAIN]/postgresql.auto.conf on PG >= 12)
|
||||
(Default: [PG_MAIN]/recovery.conf on PG <= 11, [PG_MAIN]/postgresql.auto.conf on PG >= 12)
|
||||
-U pg_master_user Specify Postgres user to use on master (Default: user from recovery.conf file)
|
||||
-p pg_port Specify default Postgres master TCP port (Default: same as local PostgreSQL
|
||||
port if detected or use $DEFAULT_PG_PORT)
|
||||
|
@ -126,7 +125,7 @@ do
|
|||
usage
|
||||
;;
|
||||
\?)
|
||||
echo -n "Unknown option"
|
||||
echo -n "Unkown option"
|
||||
usage
|
||||
esac
|
||||
done
|
||||
|
@ -281,19 +280,19 @@ then
|
|||
debug "Last replayed LSN: $LAST_REPLAYED_LSN"
|
||||
|
||||
|
||||
# Get master connection information from recovery.conf file
|
||||
# Get master connection informations from recovery.conf file
|
||||
MASTER_CONN_INFOS=$( egrep '^ *primary_conninfo' $RECOVERY_CONF|sed "s/^ *primary_conninfo *= *\(.\+\) *$/\1/" )
|
||||
if [ ! -n "$MASTER_CONN_INFOS" ]
|
||||
then
|
||||
echo "UNKNOWN: Can't retrieve master connection information form recovery.conf file"
|
||||
echo "UNKNOWN: Can't retreive master connection informations form recovery.conf file"
|
||||
exit 3
|
||||
fi
|
||||
debug "Master connection information: $MASTER_CONN_INFOS"
|
||||
debug "Master connection informations: $MASTER_CONN_INFOS"
|
||||
|
||||
M_HOST=$( echo "$MASTER_CONN_INFOS"| grep 'host=' | sed 's/^.*host= *\([0-9a-zA-Z.-]\+\) *.*$/\1/' )
|
||||
if [ ! -n "$M_HOST" ]
|
||||
then
|
||||
echo "UNKNOWN: Can't retrieve master host from recovery.conf file"
|
||||
echo "UNKNOWN: Can't retreive master host from recovery.conf file"
|
||||
exit 3
|
||||
fi
|
||||
debug "Master host: $M_HOST"
|
||||
|
@ -349,7 +348,7 @@ then
|
|||
M_CUR_REPL_STATE_INFO="$( psql_master_get "SELECT state, sync_state, $sent_lsn AS sent_lsn, $write_lsn AS write_lsn FROM pg_stat_replication WHERE application_name='$M_APP_NAME';" )"
|
||||
if [ ! -n "$M_CUR_REPL_STATE_INFO" ]
|
||||
then
|
||||
echo "UNKNOWN: Can't retrieve current replication state information from master server"
|
||||
echo "UNKNOWN: Can't retreive current replication state information from master server"
|
||||
exit 3
|
||||
fi
|
||||
debug "Master current replication state:\n\tstate|sync_state|sent_lsn|write_lsn\n\t$M_CUR_REPL_STATE_INFO"
|
||||
|
@ -381,7 +380,7 @@ then
|
|||
M_CUR_LSN="$( psql_master_get "SELECT $pg_current_wal_lsn" )"
|
||||
if [ ! -n "$M_CUR_LSN" ]
|
||||
then
|
||||
echo "UNKNOWN: Can't retrieve current LSN from master server"
|
||||
echo "UNKNOWN: Can't retreive current LSN from master server"
|
||||
exit 3
|
||||
fi
|
||||
debug "Master current LSN: $M_CUR_LSN"
|
||||
|
@ -424,10 +423,7 @@ then
|
|||
exit 1
|
||||
fi
|
||||
|
||||
echo "OK: Hot-standby server is up-to-date"
|
||||
echo "Replication state: $M_CUR_SYNC_STATE"
|
||||
echo "Last sent/writed LSN: '$M_CUR_SENT_LSN' / '$M_CUR_WRITED_LSN'"
|
||||
[ "$LAST_RECEIVED_LSN" != "$LAST_REPLAYED_LSN" ] && echo "Replay delay: ${REPLAY_DELAY}s"
|
||||
echo "OK: Hot-standby server is uptodate"
|
||||
exit 0
|
||||
else
|
||||
debug "File recovery.conf not found. Master mode."
|
||||
|
@ -440,11 +436,11 @@ else
|
|||
fi
|
||||
debug "Postgres is not in recovery mode"
|
||||
|
||||
# Retrieve current lsn
|
||||
# Retreive current lsn
|
||||
CURRENT_LSN=$( psql_get "SELECT $pg_current_wal_lsn" )
|
||||
if [ -z "$CURRENT_LSN" ]
|
||||
then
|
||||
echo "UNKNOWN: Fail to retrieve current LSN (Log Sequence Number)"
|
||||
echo "UNKNOWN: Fail to retreive current LSN (Log Sequence Number)"
|
||||
exit 3
|
||||
fi
|
||||
debug "Current LSN: $CURRENT_LSN"
|
||||
|
|
Loading…
Reference in a new issue