eventscripts: Add new option $CTDB_MONITOR_NFS_THREAD_COUNT

[ctdb.git] / config / ctdb.sysconfig

# Options to ctdbd. This is read by /etc/init.d/ctdb

# You must specify the location of a shared lock file across all the
# nodes for split brain prevention to work.
# This must be on shared storage.
# CTDB can operate without a reclock file, but this means that there is no
# protection against a split brain.
# It is strongly suggested to NOT run ctdb without a reclock file.
CTDB_RECOVERY_LOCK="/some/place/on/shared/storage"

# when doing IP takeover you also may specify what network interface
# to use by default for the public addresses. Otherwise you must
# specify an interface on each line of the public addresses file
# there is no default
# CTDB_PUBLIC_INTERFACE=eth0

# Should ctdb do IP takeover? If it should, then specify a file
# containing the list of public IP addresses that ctdb will manage
# Note that these IPs must be different from those in $NODES above
# there is no default.
# The syntax is one line per public address of the form :
#   <ipaddress>/<netmask> <interface>
# Example: 10.1.1.1/24 eth0
#
# CTDB_PUBLIC_ADDRESSES=/etc/ctdb/public_addresses

# Should CTDB present the cluster using a single public ip address to clients
# and multiplex clients across all CONNECTED nodes ?
# This is based on LVS 
# When this is enabled, the entire cluster will present one single ip address
# which clients will connect to.
# CTDB_LVS_PUBLIC_IP=10.1.1.1


# should ctdb manage starting/stopping the Samba service for you?
# default is to not manage Samba
# CTDB_MANAGES_SAMBA=yes

# If there are very many shares it may not be feasible to check that all
# of them are available during each monitoring interval.
# In that case this check can be disabled
# CTDB_SAMBA_SKIP_SHARE_CHECK=yes
# CTDB_NFS_SKIP_SHARE_CHECK=yes

# specify which ports we should check that there is a daemon listening to
# by default we use testparm and look in smb.conf to figure out.
# CTDB_SAMBA_CHECK_PORTS="445"

# should ctdb manage starting/stopping Winbind service?
# if left comented out then it will be autodetected based on smb.conf
# CTDB_MANAGES_WINBIND=yes

# should ctdb manage starting/stopping the VSFTPD service
# CTDB_MANAGES_VSFTPD=yes

# should ctdb manage starting/stopping the ISCSI service
# CTDB_MANAGES_ISCSI=yes

# should ctdb manage starting/stopping the NFS service
# CTDB_MANAGES_NFS=yes

# should ctdb manage starting/stopping the Apache web server httpd?
# CTDB_MANAGES_HTTPD

# The init style (redhat/suse/debian...) is usually auto-detected.
# The names of init scripts of services managed by CTDB are set
# based on the detected init style. You can override the init style
# auto-detection here to explicitly use a scheme. This might be
# useful when you have installed a packages (for instance samba
# packages) with a different init script layout.
# There is no default.
# CTDB_INIT_STYLE=redhat

# The following are specific Samba init scripts / services that you
# can override from auto-detection.
# There are no defaults.
# CTDB_SERVICE_SMB=smb
# CTDB_SERVICE_NMB=nmb
# CTDB_SERVICE_WINBIND=winbind

# you may wish to raise the file descriptor limit for ctdb
# use a ulimit command here. ctdb needs one file descriptor per
# connected client (ie. one per connected client in Samba)
#  ulimit -n 10000

# the NODES file must be specified or ctdb won't start
# it should contain a list of IPs that ctdb will use
# it must be exactly the same on all cluster nodes
# defaults to /etc/ctdb/nodes
# CTDB_NODES=/etc/ctdb/nodes

# a script to run when node health changes
# CTDB_NOTIFY_SCRIPT=/etc/ctdb/notify.sh

# a script to collect data when an eventscript has hung
# CTDB_DEBUG_HUNG_SCRIPT=/etc/ctdb/debug-hung-script.sh

# the directory to put the local ctdb database files in
# defaults to /var/ctdb
# CTDB_DBDIR=/var/ctdb

# the directory to put the local persistent ctdb database files in
# defaults to /var/ctdb/persistent
# CTDB_DBDIR_PERSISTENT=/var/ctdb/persistent

# the directory where service specific event scripts are stored
# defaults to /etc/ctdb/events.d
# CTDB_EVENT_SCRIPT_DIR=/etc/ctdb/events.d

# the location of the local ctdb socket
# defaults to /tmp/ctdb.socket
# CTDB_SOCKET=/tmp/ctdb.socket

# what transport to use. Only tcp is currently supported
# defaults to tcp
# CTDB_TRANSPORT="tcp"

# These setting allow monitoring for low/out-out of memory conditions.
#
# If set, once available memory drops below CTDB_MONITOR_FREE_MEMORY_WARN
# ctdb will start logging messages that memory is low, but will not
# take any further action.
#
# If the amount of free memory drops below CTDB_MONITOR_FREE_MEMORY 
# ctdb will fail all service over to a different node and finally shutdown.
# Once this occurs, the administrator needs to find the reason for the OOM
# situation, rectify it and restart ctdb with "service ctdb start"
# The unit is MByte
# CTDB_MONITOR_FREE_MEMORY_WARN=100
# CTDB_MONITOR_FREE_MEMORY=10

# Should the 60.nfs monitor event try to correct the number of nfsd
# threads?  This works around a limitation in some NFS initscripts
# where some threads can be stuck in host filesystem calls (perhaps
# due to slow storage), a restart occurs, some threads don't exit, the
# start only adds the missing number of threads, the stuck threads
# exit, and the result is a lower than expected thread count.  Note
# that if you must also set $RPCNFSDCOUNT (RedHat/Debian) or
# $USE_KERNEL_NFSD_NUMBER (SUSE) in your NFS configuration so the
# monitoring code knows how many threads there should be - if neither
# of these are set then this option will be ignored.  The default is
# to not do this check.
# CTDB_MONITOR_NFS_THREAD_COUNT="yes"

# When set to yes, the CTDB node will start in DISABLED mode and not host
# any public ip addresses. The administrator needs to explicitely enable
# the node with "ctdb enable"
# CTDB_START_AS_DISABLED="yes"

# LMASTER and RECMASTER capabilities.
# By default all nodes are capable of both being LMASTER for records and
# also for taking the RECMASTER role and perform recovery.
# These parameters can be used to disable these two roles on a node.
# Note: If there are NO available nodes left in a cluster that can perform
# the RECMASTER role, the cluster will not be able to recover from a failure
# and will remain in RECOVERY mode until an RECMASTER capable node becomes
# available. Same for LMASTER.
# These parametersd are useful for scenarios where you have one "remote" node
# in a cluster and you do not want the remote node to be fully participating
# in the cluster and slow things down.
# For that case, set both roles to "no" for the remote node on the remote site
# but leave the roles default to "yes" on the primary nodes in the central
# datacentre.
# CTDB_CAPABILITY_RECMASTER=yes
# CTDB_CAPABILITY_LMASTER=yes

# NAT-GW configuration
# Some services running on nthe CTDB node may need to originate traffic to
# remote servers before the node is assigned any IP addresses,
# This is problematic since before the node has public addresses the node might
# not be able to route traffic to the public networks.
# One solution is to have static public addresses assigned with routing
# in addition to the public address interfaces, thus guaranteeing that
# a node always can route traffic to the external network.
# This is the most simple solution but it uses up a large number of 
# additional ip addresses.
#
# A more complex solution is NAT-GW.
# In this mode we only need one additional ip address for the cluster from
# the exsternal public network.
# One of the nodes in the cluster is elected to be hosting this ip address
# so it can reach the external services. This node is also configured
# to use NAT MASQUERADING for all traffic from the internal private network
# to the external network. This node is the NAT-GW node.
#
# All other nodes are set up with a default rote with a metric of 10 to point
# to the nat-gw node.
# 
# The effect of this is that only when a node does not have a public address
# and thus no proper routes to the external world it will instead
# route all packets through the nat-gw node.
#
# CTDB_NATGW_NODES is the list of nodes that belong to this natgw group.
# You can have multiple natgw groups in one cluster but each node
# can only belong to one single natgw group.
#
# CTDB_NATGW_PUBLIC_IP=10.0.0.227/24
# CTDB_NATGW_PUBLIC_IFACE=eth0
# CTDB_NATGW_DEFAULT_GATEWAY=10.0.0.1
# CTDB_NATGW_PRIVATE_NETWORK=10.1.1.0/24
# CTDB_NATGW_NODES=/etc/ctdb/natgw_nodes
#
# Normally any node in the natgw group can act as the natgw master.
# In some configurations you may have special nodes that is a part of the
# cluster/natgw group, but where the node lacks connectivity to the 
# public network.
# For these cases, set this variable to make these nodes not able to
# become natgw master.
#
# CTDB_NATGW_SLAVE_ONLY=yes


# PER_IP_ROUTING configuration
#
# Some setups have multiple network interfaces connected to the
# same network. By default all traffic for a network is routed
# through only one interface, while the others are idle.
#
# On Linux it possible to use policy based routing to spread the load
# across all interfaces. The is implemented by using a separate
# routing table per public ip address.
#
# The configuration file configured by CTDB_PER_IP_ROUTING_CONF
# contains the list of additional routes. The routes are bound to the
# interface that is holding the public ip address.
#
# The format of the config file looks like this:
# <public_ip_address> <network> [<gateway>]
# and it's possible to have multiple routes per public ip address.
#
# If the special value "__auto_link_local__" is used, the config
# file autogenerated. Each public ip address gets a special route
# for its own subnet bound to it's current interface.
# E.g. 10.1.2.3/24 will result in a config file line
# 10.1.2.3 10.1.2.0/24
#
# The CTDB_PER_IP_ROUTING_RULE_PREF option needs to be configured.
# The value will be passed as "pref" argument of "ip rule".
# The value should be between 1 and 32765. So that the rule
# comes after the rule for "local" routing table and before
# the rule for the "main" routing table. This way the specific
# routing table just overloads the "main" routing table,
# this is useful because with the "__auto_link_local__" setup
# the default route still comes from the "main" routing table.
#
# The routing table ids are automaticly allocated. On
# Linux the routing table ids must be in the range of 0 to 255.
# But some are reserved values, see /etc/iproute2/rt_tables.
# You need to configure a range (CTDB_PER_IP_ROUTING_TABLE_ID_LOW
# and CTDB_PER_IP_ROUTING_TABLE_ID_HIGH) from which the table ids can be taken.
#
# The default value for CTDB_PER_IP_ROUTING_CONF is "",
# which means the feature is disabled by default.
#
# CTDB_PER_IP_ROUTING_CONF="/etc/ctdb/per_ip_routing.conf"
# CTDB_PER_IP_ROUTING_CONF="__auto_link_local__"
# CTDB_PER_IP_ROUTING_TABLE_ID_LOW=10
# CTDB_PER_IP_ROUTING_TABLE_ID_HIGH=250
# CTDB_PER_IP_ROUTING_RULE_PREF=10000

# Make offline interfaces not a reason for being UNHEALTHY.
# The CTDB_PARTIALLY_ONLINE_INTERFACES option changes
# the behavior of the 10.interface monitor event.
# In some setups it's desired that interfaces without
# an active link don't change the node to unhealthy.
# ctdbd is just informed about the interface status
# and "ctdb status" dislays the node as "PARTIALLYONLINE".
#
# CTDB_PARTIALLY_ONLINE_INTERFACES="yes"

# where to log messages
# the default is /var/log/log.ctdb
# CTDB_LOGFILE=/var/log/log.ctdb

# what debug level to run at. Higher means more verbose
# the default is ERR
CTDB_DEBUGLEVEL=ERR

# whether to suppress core files.  Default is no.
# CTDB_SUPPRESS_COREFILE=yes

# Write debug messages to syslog instead of logfile?
# The default is not to use syslog.
# CTDB_SYSLOG=no

# Should the 99.timeout monitor event script be run?
# This event script just sleeps long enough to trigger the
# event script timeout. Might be useful for debugging.
# The default is "no".
# CTDB_RUN_TIMEOUT_MONITOR=no

# Should ctdbd start with corrupted/unhealthy persistent databases?
# This parameter specifies the max error count for persistent health
# checks before the "startup" event. The value must be a positive
# interger value, "0" or "-1".
# The default is "0", which means ctdbd will not start.
# "-1" means wait forever.
# CTDB_MAX_PERSISTENT_CHECK_ERRORS=0

# All log entries up to level 9 are also collected into a in-memory ringbuffer
# in addition to the log that is written to the log file.
# This parameter controls how many entries we allow for this in memory log
# CTDB_LOG_RINGBUF_SIZE=500000

# Monitor filesystem useage.
# when set, and the 40.fs_use eventscript is enabled, this variable
# allows one to monitor the filesystem use and flag a node as unhealthy when
# the filesystem becomes too full.
# This is useful for example when /var grows too big.
# Example: monitor both / and /var and make the node unhealthy when eitehr go
# above 90%
# CTDB_CHECK_FS_USE="/:90 /var:90"

# Should CTDB automatically start and stop services when it is told to
# newly manage or no longer manage them?
CTDB_SERVICE_AUTOSTARTSTOP=yes

# 
#
# set any default tuning options for ctdb
# use CTDB_SET_XXXX=value where XXXX is the name of the tuning
# variable
# for example
#    CTDB_SET_TRAVERSETIMEOUT=60
# you can get a list of variables using "ctdb listvars"

# any other options you might want. Run ctdbd --help for a list
# CTDB_OPTIONS=