Command Center

# External static interface.
config_eth0=( "192.168.0.101 netmask 255.255.255.0 brd 192.168.0.255" )
routes_eth0=( "default gw 192.168.0.1" )
dns_servers_eth0="4.2.2.1 4.2.2.2"
dns_domain_eth0="yourdomain.tld"

# This is the heartbeat and disk syncing interface.
config_eth1=( "10.0.0.1 netmask 255.255.255.0 brd 10.0.0.255" )

# External static interface.
config_eth0=( "192.168.0.102 netmask 255.255.255.0 brd 192.168.0.255" )
routes_eth0=( "default gw 192.168.0.1" )
dns_servers_eth0="4.2.2.1 4.2.2.2"
dns_domain_eth0="yourdomain.tld"

# This the heartbeat and disk syncing interface.
config_eth1=( "10.0.0.2 netmask 255.255.255.0 brd 10.0.0.255" )

# IPv4 and IPv6 localhost aliases
127.0.0.1            localhost.localdomain localhost
192.168.0.100         testcluster.yourdomain.tld testcluster
192.168.0.101         testcluster1.yourdomain.tld testcluster1
192.168.0.102         testcluster2.yourdomain.tld testcluster2

global {
        usage-count no;
}

common {
}


#
# this need not be r#, you may use phony resource names,
# like "resource web" or "resource mail", too
#

resource "drbd0" {
        # transfer protocol to use.
        # C: write IO is reported as completed, if we know it has
        #    reached _both_ local and remote DISK.
        #    * for critical transactional data.
        # B: write IO is reported as completed, if it has reached
        #    local DISK and remote buffer cache.
        #    * for most cases.
        # A: write IO is reported as completed, if it has reached
        #    local DISK and local tcp send buffer. (see also sndbuf-size)
        #    * for high latency networks
        #
        protocol C;

        handlers {
                # what should be done in case the cluster starts up in
                # degraded mode, but knows it has inconsistent data.
                #pri-on-incon-degr "echo '!DRBD! pri on incon-degr' | wall ; sleep 60 ; halt -f";

                pri-on-incon-degr "echo 'DRBD: primary requested but inconsistent!' | wall; /etc/init.d/heartbeat stop"; #"halt -f";
                pri-lost-after-sb "echo 'DRBD: primary requested but lost!' | wall; /etc/init.d/heartbeat stop"; #"halt -f";

                #pri-on-incon-degr "echo o > /proc/sysrq-trigger";
                #pri-lost-after-sb "echo o > /proc/sysrq-trigger";
                #local-io-error "echo o > /proc/sysrq-trigger";
        }

        startup {
                #The init script drbd(8) blocks the boot process until the DRBD resources are connected.  When the  cluster  manager
                #starts later, it does not see a resource with internal split-brain.  In case you want to limit the wait time, do it
                #here.  Default is 0, which means unlimited. The unit is seconds.
                wfc-timeout 0;  # 2 minutes

                # Wait for connection timeout if this node was a degraded cluster.
                # In case a degraded cluster (= cluster with only one node left)
                # is rebooted, this timeout value is used.
                #
                degr-wfc-timeout 120;    # 2 minutes.
        }

        syncer {
                rate 100M;
                # This is now expressed with "after res-name"
                #group 1;
                al-extents 257;
        }

        net {
                # TODO: Should these timeouts be relative to some heartbeat settings?
                # timeout       60;    #  6 seconds  (unit = 0.1 seconds)
                # connect-int   10;    # 10 seconds  (unit = 1 second)
                # ping-int      10;    # 10 seconds  (unit = 1 second)

                # if the connection to the peer is lost you have the choice of
                #  "reconnect"   -> Try to reconnect (AKA WFConnection state)
                #  "stand_alone" -> Do not reconnect (AKA StandAlone state)
                #  "freeze_io"   -> Try to reconnect but freeze all IO until
                #                   the connection is established again.
                # FIXME This appears to be obsoleate
                #on-disconnect reconnect;

                # FIXME Experemental Crap
                #cram-hmac-alg "sha256";
                #shared-secret "secretPassword555";
                #after-sb-0pri discard-younger-primary;
                #after-sb-1pri consensus;
                #after-sb-2pri disconnect;
                #rr-conflict disconnect;
        }

        disk {
                # if the lower level device reports io-error you have the choice of
                #  "pass_on"  ->  Report the io-error to the upper layers.
                #                 Primary   -> report it to the mounted file system.
                #                 Secondary -> ignore it.
                #  "panic"    ->  The node leaves the cluster by doing a kernel panic.
                #  "detach"   ->  The node drops its backing storage device, and
                #                 continues in disk less mode.
                #
                on-io-error   pass_on;

                # Under  fencing  we understand preventive measures to avoid situations where both nodes are
                # primary and disconnected (AKA split brain).
                fencing dont-care;

                # In case you only want to use a fraction of the available space
                # you might use the "size" option here.
                #
                # size 10G;
        }


        on testcluster1 {
                device          /dev/drbd0;
                disk            /dev/sdb1;
                address         10.0.0.1:7788;
                meta-disk       internal;
        }

        on testcluster2 {
                device          /dev/drbd0;
                disk            /dev/sdb1;
                address         10.0.0.2:7788;
                meta-disk       internal;
        }
}

resource "drbd1" {
        # transfer protocol to use.
        # C: write IO is reported as completed, if we know it has
        #    reached _both_ local and remote DISK.
        #    * for critical transactional data.
        # B: write IO is reported as completed, if it has reached
        #    local DISK and remote buffer cache.
        #    * for most cases.
        # A: write IO is reported as completed, if it has reached
        #    local DISK and local tcp send buffer. (see also sndbuf-size)
        #    * for high latency networks
        #
        protocol C;

        handlers {
                # what should be done in case the cluster starts up in
                # degraded mode, but knows it has inconsistent data.
                #pri-on-incon-degr "echo '!DRBD! pri on incon-degr' | wall ; sleep 60 ; halt -f";

                pri-on-incon-degr "echo 'DRBD: primary requested but inconsistent!' | wall; /etc/init.d/heartbeat stop"; #"halt -f";
                pri-lost-after-sb "echo 'DRBD: primary requested but lost!' | wall; /etc/init.d/heartbeat stop"; #"halt -f";

                #pri-on-incon-degr "echo o > /proc/sysrq-trigger";
                #pri-lost-after-sb "echo o > /proc/sysrq-trigger";
                #local-io-error "echo o > /proc/sysrq-trigger";
        }

        startup {
                #The init script drbd(8) blocks the boot process until the DRBD resources are connected.  When the  cluster  manager
                #starts later, it does not see a resource with internal split-brain.  In case you want to limit the wait time, do it
                #here.  Default is 0, which means unlimited. The unit is seconds.
                wfc-timeout 0;  # 2 minutes

                # Wait for connection timeout if this node was a degraded cluster.
                # In case a degraded cluster (= cluster with only one node left)
                # is rebooted, this timeout value is used.
                #
                degr-wfc-timeout 120;    # 2 minutes.
        }

        syncer {
                rate 100M;
                # This is now expressed with "after res-name"
                #group 1;
                al-extents 257;
        }

        net {
                # TODO: Should these timeouts be relative to some heartbeat settings?
                # timeout       60;    #  6 seconds  (unit = 0.1 seconds)
                # connect-int   10;    # 10 seconds  (unit = 1 second)
                # ping-int      10;    # 10 seconds  (unit = 1 second)

                # if the connection to the peer is lost you have the choice of
                #  "reconnect"   -> Try to reconnect (AKA WFConnection state)
                #  "stand_alone" -> Do not reconnect (AKA StandAlone state)
                #  "freeze_io"   -> Try to reconnect but freeze all IO until
                #                   the connection is established again.
                # FIXME This appears to be obsoleate
                #on-disconnect reconnect;

                # FIXME Experemental Crap
                #cram-hmac-alg "sha256";
                #shared-secret "secretPassword555";
                #after-sb-0pri discard-younger-primary;
                #after-sb-1pri consensus;
                #after-sb-2pri disconnect;
                #rr-conflict disconnect;
        }

        disk {
                # if the lower level device reports io-error you have the choice of
                #  "pass_on"  ->  Report the io-error to the upper layers.
                #                 Primary   -> report it to the mounted file system.
                #                 Secondary -> ignore it.
                #  "panic"    ->  The node leaves the cluster by doing a kernel panic.
                #  "detach"   ->  The node drops its backing storage device, and
                #                 continues in disk less mode.
                #
                on-io-error   pass_on;

                # Under  fencing  we understand preventive measures to avoid situations where both nodes are
                # primary and disconnected (AKA split brain).
                fencing dont-care;

                # In case you only want to use a fraction of the available space
                # you might use the "size" option here.
                #
                # size 10G;
        }


        on testcluster1 {
                device          /dev/drbd1;
                disk            /dev/sdb2;
                address         10.0.0.1:7789;
                meta-disk       internal;
        }

        on testcluster2 {
                device          /dev/drbd1;
                disk            /dev/sdb2;
                address         10.0.0.2:7789;
                meta-disk       internal;
        }
}

#                                           

# NOTE: If your BOOT partition is ReiserFS, add the notail option to opts.
/dev/sda1               /boot           ext2            noatime         1 2
/dev/sda3               /               ext3            noatime         0 1
/dev/sda2               none            swap            sw              0 0
/dev/cdrom              /mnt/cdrom      audo            noauto,ro       0 0
#/dev/fd0               /mnt/floppy     auto            noauto          0 0
/dev/drbd0              /wwwjail/siteroot       ext3    noauto          0 0
/dev/drbd1              /wwwjail/mysql          ext3    noauto          0 0

proc                    /proc           proc            defaults        0 0

# glibc 2.2 and above expects tmpfs to be mounted at /dev/shm for
# POSIX shared memory (shm_open, shm_unlink).
# (tmpfs is a dynamically expandable/shrinkable ramdisk, and will
#  use almost no memory if not populated with files)
shm                     /dev/shm        tmpfs           nodev,nosuid,noexec     0 0

...
#bind-address                           = 127.0.0.1
...
#datadir                                        = /var/lib/mysql
datadir                                         = /wwwjail/mysql
...

# What interfaces to heartbeat over?
#udp  eth1
bcast eth1

# keepalive: how many seconds between heartbeats
keepalive 2

# Time in seconds before issuing a "late heartbeat" warning in the logs.
warntime 10

# Node is pronounced dead after 30 seconds.
deadtime 15

# With some configurations, the network takes some time to start working after a reboot.
# This is a separate "deadtime" to handle that case. It should be at least twice the normal deadtime.
initdead 30

# Mandatory. Hostname of machine in cluster as described by uname -n.
node    testcluster1
node    testcluster2


# When auto_failback is set to on once the master comes back online, it will take
# everything back from the slave.
auto_failback off

# Some default uid, gid info, This is required for ipfail
apiauth default uid=nobody gid=cluster
apiauth ipfail uid=cluster
apiauth ping gid=nobody uid=nobody,cluster

# This is to fail over if the outbound network connection goes down.
respawn cluster /usr/lib/heartbeat/ipfail

# IP to ping to check to see if the external connection is up.
ping 192.168.0.1
deadping 15

debugfile /var/log/ha-debug

# File to write other messages to
logfile /var/log/ha-log

# Facility to use for syslog()/logger
logfacility     local0

testcluster1 IPaddr::192.168.0.100
testcluster1 drbddisk::drbd0 Filesystem::/dev/drbd0::/wwwjail/siteroot::ext3::noatime apache2
testcluster1 drbddisk::drbd1 Filesystem::/dev/drbd1::/wwwjail/mysql::ext3::noatime mysql

auth 1
1 crc

auth 1
1 sha1 MySharedSecretPassword