Masato Taruishi
taru****@users*****
2004年 9月 28日 (火) 23:22:53 JST
===================================================================
RCS file: ultrapossum/module/failover/11failover,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- ultrapossum/module/failover/11failover 2004/09/17 02:56:22 1.4
+++ ultrapossum/module/failover/11failover 2004/09/28 14:22:53 1.5
@@ -28,6 +28,7 @@
# Failover configuration for slurpd
ULTRAPOSSUM_RECOVERY_CONFIN=$(ultrapossum_getconf ULTRAPOSSUM_RECOVERY_CONFIN $TEMPLATEDIR/recovery.conf.in)
ULTRAPOSSUM_RECOVERY_CONF=$(ultrapossum_getconf ULTRAPOSSUM_RECOVERY_CONF $CONFDIR/recovery.conf)
+FAILOVER_RECOVERY_PIDFILE=$(ultrapossum_getconf FAILOVER_RECOVERY_PIDFILE "$localstatedir/run/ultrapossum.recovery.pid")
# Mon configuration
ULTRAPOSSUM_MON_CFIN=$(ultrapossum_getconf ULTRAPOSSUM_MON_CFIN $TEMPLATEDIR/ultrapossum.mon.cf.in)
@@ -86,6 +87,7 @@
if test -f "$HACF"; then
HEARTBEAT_NICE_FAILBACK=`grep ^nice_failback $HACF | awk -F' ' '{print $2;}'`
+ HEARTBEAT_AUTO_FAILBACK=`grep ^auto_failback $HACF | awk -F' ' '{print $2;}'`
fi
if test "x$HOST" = "x$BACKUP"; then
@@ -97,19 +99,7 @@
if test "x$ULTRAPOSSUM_MODULE_FAILOVER" = "xinstalled"; then
wait_master_service() {
- (for i in 1 2 2 3 3 3 5 5 5 5 10 10 10 10 10 20 20 20
- do
- if test "`ldapmaster_status`" = "running"; then
- exit 0
- fi
- if test "`$MODULEDIR/server/pid status $HAPIDFILE`" = "stopped"; then
- exit 1
- fi
- sleep $i
- echo -n "."
- done
- echo "timeout" 1>&2
- exit 1) || exit 1
+ $MODULEDIR/server/pid wait $SLAPD_PIDFILE
echo -n " `basename $SLAPD`"
if test "x$SLURPDSLAVES" != "x"; then
$MODULEDIR/server/pid wait $SLURPD_PIDFILE
@@ -119,29 +109,24 @@
echo -n " mon"
}
-wait_nicefailback_service()
+wait_backup_service()
{
+ # handle initdead case
(for i in 1 2 2 3 3 3 5 5 5 5 10 10 10 10 10 20 20 20
- do
- if test "`$MODULEDIR/server/startup status`" = "running"; then
- exit 0
- fi
- if test "`$MODULEDIR/server/pid status $HAPIDFILE`" = "stopped"; then
- exit 1
+ do
+ # started as master service
+ if test "`ldapmaster_status`" = "running"; then
+ wait_master_service
+ exit 0
+ # started as slave service
+ elif test "`ldapslave_status`" = "running"; then
+ exit 0
fi
sleep $i
echo -n "."
- done
- echo "timeout" 1>&2
- exit 1) || exit 1
- if test "`ldapmaster_status`" = "running"; then
- wait_master_service
- elif include "$BACKUP" "$SYNCBACKUPS"; then
- echo -n " `basename $SLAPD`"
- else
- echo -n " "
- ldapslave_start
- fi
+ done
+ echo "timeout" 1>&2
+ exit 1 ) || exit 1
}
ldapmaster_service_start()
@@ -149,16 +134,21 @@
if test "x$BACKUP" = "x" ; then
ldapmaster_start
else
- if include "$BACKUP" "$SYNCBACKUPS"; then
+ if test "x`$MODULEDIR/server/startup slave_status`" = "xstopped"; then
ldapslave_start
echo -n " "
fi
/etc/init.d/heartbeat start | grep ERROR 1>&2 && exit 1
+ $MODULEDIR/server/pid wait $HAPIDFILE
echo -n "heartbeat"
- if test "x$HOST" = "x$MASTER" && test "x$HEARTBEAT_NICE_FAILBACK" = "x"; then
- wait_master_service
+ if test "x$HOST" = "x$MASTER"; then
+ if test "x$HEARTBEAT_NICE_FAILBACK" = "x" || test "x$HEARTBEAT_AUTO_FAILBACK" = "xon"; then
+ wait_master_service
+ else
+ wait_backup_service
+ fi
else
- wait_nicefailback_service
+ wait_backup_service
fi
fi
}
===================================================================
RCS file: ultrapossum/module/failover/Makefile.am,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- ultrapossum/module/failover/Makefile.am 2004/06/24 08:42:59 1.4
+++ ultrapossum/module/failover/Makefile.am 2004/09/28 14:22:53 1.5
@@ -6,7 +6,6 @@
module_DATA = 11failover
update_SCRIPTS = update-failover
-
modulesysconf_DATA = failover.cf
modulelocal_SCRIPTS = \
===================================================================
RCS file: ultrapossum/module/failover/ha.cf.in,v
retrieving revision 1.1.1.1
retrieving revision 1.2
diff -u -r1.1.1.1 -r1.2
--- ultrapossum/module/failover/ha.cf.in 2004/03/13 14:25:54 1.1.1.1
+++ ultrapossum/module/failover/ha.cf.in 2004/09/28 14:22:53 1.2
@@ -1,7 +1,17 @@
#
# There are lots of options in this file. All you have to have is a set
-# of nodes listedJ {"node ...}
-# and one of {serial, udp, or mcast}
+# of nodes listed {"node ...} one of {serial, bcast, mcast, or ucast},
+# and a value for "auto_failback".
+#
+# ATTENTION: As the configuration file is read line by line,
+# THE ORDER OF DIRECTIVE MATTERS!
+#
+# In particular, make sure that the udpport, serial baud rate
+# etc. are set before the heartbeat media are defined!
+# debug and log file directives go into effect when they
+# are encountered.
+#
+# All will be fine if you keep them ordered as in this example.
#
#
# Note on logging:
@@ -14,7 +24,7 @@
# defined then defaults will be used for debugfile and logfile as
# required and messages will be sent there.
#
-# File to wirte debug messages to
+# File to write debug messages to
#debugfile /var/log/ha-debug
#
#
@@ -25,16 +35,34 @@
#
# Facility to use for syslog()/logger
#
-#logfacility local0
+logfacility local0
+#
#
+# A note on specifying "how long" times below...
#
-# keepalive: how many seconds between heartbeats
+# The default time unit is seconds
+# 10 means ten seconds
+#
+# You can also specify them in milliseconds
+# 1500ms means 1.5 seconds
+#
+#
+# keepalive: how long between heartbeats?
#
#keepalive 2
#
-# deadtime: seconds-to-declare-host-dead
+# deadtime: how long-to-declare-host-dead?
+#
+# If you set this too low you will get the problematic
+# split-brain (or cluster partition) problem.
+# See the FAQ for how to use warntime to tune deadtime.
#
-#deadtime 10
+#deadtime 30
+#
+# warntime: how long before issuing "late heartbeat" warning?
+# See the FAQ for how to use warntime to tune deadtime.
+#
+#warntime 10
#
#
# Very first dead time (initdead)
@@ -46,24 +74,27 @@
#
#initdead 120
#
-# hopfudge maximum hop count minus number of nodes in config
-#hopfudge 1
-#
-# serial serialportname ...
-#serial /dev/ttyS0
#
+# What UDP port to use for bcast/ucast communication?
+#
+#udpport 694
#
# Baud rate for serial ports...
#
#baud 19200
+#
+# serial serialportname ...
+#serial /dev/ttyS0 # Linux
+#serial /dev/cuaa0 # FreeBSD
+#serial /dev/cua/a # Solaris
#
-# What UDP port to use for communication?
-#
-#udpport 694
#
-# What interfaces to heartbeat over?
+# What interfaces to broadcast heartbeats over?
#
-#udp eth0
+#bcast eth0 # Linux
+#bcast eth1 eth2 # Linux
+#bcast le0 # Solaris
+#bcast le1 le2 # Solaris
#
# Set up a multicast heartbeat medium
# mcast [dev] [mcast group] [port] [ttl] [loop]
@@ -71,23 +102,65 @@
# [dev] device to send/rcv heartbeats on
# [mcast group] multicast group to join (class D multicast address
# 224.0.0.0 - 239.255.255.255)
-# [port] udp port to sendto/rcvfrom (no real reason to differ
-# from the port used for broadcast heartbeats)
+# [port] udp port to sendto/rcvfrom (set this value to the
+# same value as "udpport" above)
# [ttl] the ttl value for outbound heartbeats. this effects
# how far the multicast packet will propagate. (0-255)
+# Must be greater than zero.
# [loop] toggles loopback for outbound multicast heartbeats.
# if enabled, an outbound packet will be looped back and
# received by the interface it was sent on. (0 or 1)
+# Set this value to zero.
#
#
-#mcast eth0 225.0.0.1 694 1 1
+#mcast eth0 225.0.0.1 694 1 0
+#
+# Set up a unicast / udp heartbeat medium
+# ucast [dev] [peer-ip-addr]
+#
+# [dev] device to send/rcv heartbeats on
+# [peer-ip-addr] IP address of peer to send packets to
+#
+#ucast eth0 192.168.1.2
+#
+#
+# About boolean values...
+#
+# Any of the following case-insensitive values will work for true:
+# true, on, yes, y, 1
+# Any of the following case-insensitive values will work for false:
+# false, off, no, n, 0
#
-# Watchdog is the watchdog timer. If our own heart doesn't beat for
-# a minute, then our machine will reboot.
#
-#watchdog /dev/watchdog
#
-# "Legacy" STONITH support
+# auto_failback: determines whether a resource will
+# automatically fail back to its "primary" node, or remain
+# on whatever node is serving it until that node fails, or
+# an administrator intervenes.
+#
+# The possible values for auto_failback are:
+# on - enable automatic failbacks
+# off - disable automatic failbacks
+# legacy - enable automatic failbacks in systems
+# where all nodes do not yet support
+# the auto_failback option.
+#
+# auto_failback "on" and "off" are backwards compatible with the old
+# "nice_failback on" setting.
+#
+# See the FAQ for information on how to convert
+# from "legacy" to "on" without a flash cut.
+# (i.e., using a "rolling upgrade" process)
+#
+# The default value for auto_failback is "legacy", which
+# will issue a warning at startup. So, make sure you put
+# an auto_failback directive in your ha.cf file.
+# (note: auto_failback can be any boolean or "legacy")
+#
+#auto_failback on
+#
+#
+# Basic STONITH support
# Using this directive assumes that there is one stonith
# device in the cluster. Parameters to this device are
# read from a configuration file. The format of this line is:
@@ -97,8 +170,6 @@
# NOTE: it is up to you to maintain this file on each node in the
# cluster!
#
-#nice_failback on
-#
#stonith baytech /etc/ha.d/conf/stonith.baytech
#
# STONITH support
@@ -118,12 +189,99 @@
# here, and you make this file publically readable, you're asking
# for a denial of service attack ;-)
#
+# To get a list of supported stonith devices, run
+# stonith -L
+# For detailed information on which stonith devices are supported
+# and their detailed configuration options, run this command:
+# stonith -h
#
#stonith_host * baytech 10.0.0.3 mylogin mysecretpassword
#stonith_host ken3 rps10 /dev/ttyS1 kathy 0
#stonith_host kathy rps10 /dev/ttyS1 ken3 0
+#
+# Watchdog is the watchdog timer. If our own heart doesn't beat for
+# a minute, then our machine will reboot.
+# NOTE: If you are using the software watchdog, you very likely
+# wish to load the module with the parameter "nowayout=0" or
+# compile it without CONFIG_WATCHDOG_NOWAYOUT set. Otherwise even
+# an orderly shutdown of heartbeat will trigger a reboot, which is
+# very likely NOT what you want.
+#
+#watchdog /dev/watchdog
#
# Tell what machines are in the cluster
# node nodename ... -- must match uname -n
#node ken3
#node kathy
+#
+# Less common options...
+#
+# Treats 10.10.10.254 as a psuedo-cluster-member
+# Used together with ipfail below...
+#
+#ping 10.10.10.254
+#
+# Treats 10.10.10.254 and 10.10.10.253 as a psuedo-cluster-member
+# called group1. If either 10.10.10.254 or 10.10.10.253 are up
+# then group1 is up
+# Used together with ipfail below...
+#
+#ping_group group1 10.10.10.254 10.10.10.253
+#
+# Processes started and stopped with heartbeat. Restarted unless
+# they exit with rc=100
+#
+#respawn userid /path/name/to/run
+#respawn hacluster /usr/lib/heartbeat/ipfail
+#
+# Access control for client api
+# default is no access
+#
+#apiauth client-name gid=gidlist uid=uidlist
+#apiauth ipfail gid=haclient uid=hacluster
+
+###########################
+#
+# Unusual options.
+#
+###########################
+#
+# hopfudge maximum hop count minus number of nodes in config
+#hopfudge 1
+#
+# deadping - dead time for ping nodes
+#deadping 30
+#
+# hbgenmethod - Heartbeat generation number creation method
+# Normally these are stored on disk and incremented as needed.
+#hbgenmethod time
+#
+# realtime - enable/disable realtime execution (high priority, etc.)
+# defaults to on
+#realtime off
+#
+# debug - set debug level
+# defaults to zero
+#debug 1
+#
+# API Authentication - replaces the fifo-permissions-based system of the past
+#
+#
+# You can put a uid list and/or a gid list.
+# If you put both, then a process is authorized if it qualifies under either
+# the uid list, or under the gid list.
+#
+# The groupname "default" has special meaning. If it is specified, then
+# this will be used for authorizing groupless clients, and any client groups
+# not otherwise specified.
+#
+#apiauth ipfail uid=hacluster
+#apiauth ccm uid=hacluster
+#apiauth ping gid=haclient uid=alanr,root
+#apiauth default gid=haclient
+
+# message format in the wire, it can be classic or netstring, default is classic
+#msgfmt netstring
+
+
+
===================================================================
RCS file: ultrapossum/module/failover/recovery,v
retrieving revision 1.4
retrieving revision 1.5
diff -u -r1.4 -r1.5
--- ultrapossum/module/failover/recovery 2004/06/22 10:10:07 1.4
+++ ultrapossum/module/failover/recovery 2004/09/28 14:22:53 1.5
@@ -93,3 +93,4 @@
rm -rf $TMPDIR/$TMPRPL
fi
fi
+