PostgreSQL : le cluster de haute disponibilité le plus simple entre deux serveurs redondants

Fichiers internes à SafeKit pour la haute disponibilité de PostgreSQL avec réplication temps réel synchrone et tolérance aux pannes

Fichiers internes au module Windows postgresql.safe

userconfig.xml on Windows (description dans le guide de l'utilisateur)

<!DOCTYPE safe>
<safe>
<service mode="mirror" defaultprim="alone" maxloop="3" loop_interval="24" failover="on">
  <!-- Heartbeat Configuration -->
  <!-- Names or IP addresses on the default network are set during initialization in the console -->
  <heart pulse="700" timeout="30000">
    <heartbeat name="default" ident="flow">
    </heartbeat>
  </heart>
  <!-- Virtual IP Configuration -->
  <!-- Replace
     * VIRTUAL_TO_BE_DEFINED by the name of your virtual server 
  -->
  <vip>
    <interface_list>
        <interface check="on" arpreroute="on"> 
	  <real_interface>
               <virtual_addr addr="VIRTUAL_TO_BE_DEFINED" where="one_side_alias" />
          </real_interface>
        </interface>
    </interface_list>
  </vip>
  <!-- Software Error Detection Configuration -->
  <errd polltimer="10">
    <!-- PostgreSQL Server -->
    <proc name="pg_ctl.exe" atleast="1" action="restart" class="prim" />
  </errd>
  <!-- File Replication Configuration -->
  <!-- Replicate
     * C:\Program Files\PostgreSQL\9.5\data\ default directory path of PostgreSQL database and redo log
  -->
  <rfs async="second" acl="off" nbrei="3">
	<replicated dir="C:\Program Files\PostgreSQL\9.5\data\" mode="read_only" />
  </rfs>
  <!-- User scripts activation -->
  <user nicestoptimeout="300" forcestoptimeout="300" logging="userlog" />
</service>
</safe>

start_prim.cmd on Windows

@echo off
rem Script called on the primary server for starting application services 

rem For logging into SafeKit log use:
rem "%SAFE%\safekit" printi | printe "message"

rem stdout goes into Application log
echo "Running start_prim %*" 

set res=0

net start postgresql-9.5 > nul
if not %errorlevel% == 0 (%SAFE%\safekit printi "PostgreSQL start failed") 
else (%SAFE%\safekit printi "PostgreSQL started")

if %res% == 0 goto end

:stop
set res=%errorlevel%
"%SAFE%\safekit" printe "start_prim failed"

rem uncomment to stop SafeKit when critical
rem "%SAFE%\safekit" stop -i "start_prim"

:end

stop_prim.cmd on Windows

@echo off
rem Script called on the primary server for stopping application services 

rem ----------------------------------------------------------
rem
rem 2 stop modes:
rem
rem - graceful stop
rem   call standard application stop with net stop
rem
rem - force stop (%1=force)
rem   kill application's processes
rem
rem ----------------------------------------------------------

rem For logging into SafeKit log use:
rem "%SAFE%\safekit" printi | printe "message"

rem stdout goes into Application log
echo "Running stop_prim %*" 

set res=0

rem default: no action on forcestop
if "%1" == "force" goto end

net stop postgresql-9.5 > nul
%SAFE%\safekit printi "PostgreSQL stopped"

rem wait a little for a real stop of services
%SAFEBIN%\sleep 10

:end

Fichiers internes au module Linux postgresql.safe

userconfig.xml on Linux (description dans le guide de l'utilisateur)

<!DOCTYPE safe>
<safe>
<service mode="mirror" defaultprim="alone" maxloop="3" loop_interval="24" failover="on">
  <!-- Heartbeat Configuration -->
  <!-- Names or IP addresses on the default network are set during initialization in the console -->
  <heart pulse="700" timeout="30000">
    <heartbeat name="default" ident="flow">
    </heartbeat>
  </heart>
  <!-- Virtual IP Configuration -->
  <!-- Replace
     * VIRTUAL_TO_BE_DEFINED by the name of your virtual server 
  -->
  <vip>
    <interface_list>
        <interface check="on" arpreroute="on"> 
	  <real_interface>
               <virtual_addr addr="VIRTUAL_TO_BE_DEFINED" where="one_side_alias" />
          </real_interface>
        </interface>
    </interface_list>
  </vip>
  <!-- Software Error Detection Configuration -->
  <errd polltimer="10">
    <!-- PostgreSQL Server -->
    <proc name="postgres" atleast="1" action="restart" class="prim" />
  </errd>
  <!-- File Replication Configuration -->
  <!-- Replicate
     * /usr/local/pgsql/data: default directory path of PostgreSQL database and redo log
  -->
  <rfs mountover="off" async="second" acl="off" nbrei="3">
	<replicated dir="/usr/local/pgsql/data" mode="read_only" />
	<replicated dir="/usr/local/pgsql/var" mode="read_only" />
  </rfs>
  <!-- User scripts activation -->
  <user nicestoptimeout="300" forcestoptimeout="300" logging="userlog" />
</service>
</safe>

start_prim on Linux

#!/bin/sh 
# Script called on the primary server for starting applications 

# For logging into SafeKit log use:
# $SAFE/safekit printi | printe "message" 

#---------- Clean PostgreSQL residual processes 
# Call this function before starting any PostgreSQL databases 
# to clean eventual resual PostgreSQL processes
clean_PostgreSQL()
{
  retval=0

  $SAFE/safekit printw "Cleaning PostgreSQL processes"

  # kill started PostgreSQL processes
  ps -e -o pid,comm | grep postgres | $AWK '{print "kill " $1}'| sh >/dev/null 2>&1

  return $retval
}

#---------- PostgreSQL Databases
# Call this function for starting PostgreSQL Server
start_PostgreSQL()
{
  retval=0

  $SAFE/safekit printw "Starting PostgreSQL Server"

  # PostgreSQL - Database Starting 
  service postgresql start  
  if [ $? -ne 0 ] ; then 
    $SAFE/safekit printw "PostgreSQL server start failed"
  else
    $SAFE/safekit printw "PostgreSQL server started"
  fi

  return $retval
}

# stdout goes into Application log
echo "Running start_prim $*" 

res=0

[ -z "$OSNAME" ] && OSNAME=`uname -s`
OSNAME=`uname -s`
case "$OSNAME" in
    Linux)
	AWK=/bin/awk
	;;
    *)
	AWK=/usr/bin/awk
	;;
esac

# TODO
# remove PostgreSQL boot start 

# Clean PostgreSQL residual processes 
clean_PostgreSQL || res=$?

# Start PostgreSQL databases
start_PostgreSQL || res=$?

if [ $res -ne 0 ] ; then
  $SAFE/safekit printi "start_prim failed"

  # uncomment to stop SafeKit when critical
  # $SAFE/safekit stop -i "start_prim"
fi

exit 0

stop_prim on Linux

#!/bin/sh
# Script called on the primary server for stopping application services

# For logging into SafeKit log use:
# $SAFE/safekit printi | printe "message" 

#----------------------------------------------------------
#
# 2 stop modes:
#
# - graceful stop
#   call standard application stop
#
# - force stop ($1=force)
#   kill application's processes
#
#----------------------------------------------------------

#---------- Clean PostgreSQL residual processes
# Call this function on force stop 
# to clean eventual resual PostgreSQL processes 
clean_PostgreSQL()
{
  retval=0

  $SAFE/safekit printw "Cleaning PostgreSQL processes "

  # kill started PostgreSQL 
  ps -e -o pid,comm | grep postgres | $AWK '{print "kill -9 " $1}'| sh >/dev/null 2>&1

  return $retval
}

#---------- PostgreSQL databases
# Call this function for stopping PostgreSQL databases
stop_PostgreSQL()
{
  retval=0

  if [ "$1" = "force" ] ; then
    # PostgreSQL databases force stop
    clean_PostgreSQL
    return $retval
  fi

  # PostgreSQL databases gracefull stop
  $SAFE/safekit printw "Stopping PostgreSQL server"  
  service postgresql stop
  if [ $? -ne 0 ] ; then 
    $SAFE/safekit printw "PostgreSQL server stop failed"
  else
    $SAFE/safekit printw "PostgreSQL server stopped"  
  fi

  return $retval
}

# stdout goes into Application log
echo "Running stop_prim $*" 

res=0

[ -z "$OSNAME" ] && OSNAME=`uname -s`
case "$OSNAME" in
    Linux)
	AWK=/bin/awk
	;;
    *)
	AWK=/usr/bin/awk
	;;
esac

mode=
if [ "$1" = "force" ] ; then
  mode=force
  shift
fi

# Stop PostgreSQL  server 
stop_PostgreSQL $mode || res=$?

[ $res -ne 0 ] && $SAFE/safekit printi "stop_prim failed"

exit 0