207 lines
7.7 KiB
Plaintext
207 lines
7.7 KiB
Plaintext
|
#
|
||
|
|
#
|
||
|
|
# Sample stanza file used as input to the rollupdate command
|
||
|
|
# This sample assumes that you have a simple set of updates that can
|
||
|
|
# be applied to all nodes in any order. Only the list of all nodes needs
|
||
|
|
# to be specified. You do not need to specify individual update groups.
|
||
|
|
#
|
||
|
|
# For more complex updates, see the sample file rollupdate.input.sample
|
||
|
|
#
|
||
|
|
# Unless otherwise noted in the descriptions below, if multiple stanza
|
||
|
|
# lines are specified for the same keyword, only the FIRST entry will be
|
||
|
|
# used and all others will be ignored.
|
||
|
|
#
|
||
|
|
#
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# scheduler: The job scheduler used to submit the rolling update jobs
|
||
|
|
# Currently only LoadLeveler is supported
|
||
|
|
scheduler=loadleveler
|
||
|
|
|
||
|
|
|
||
|
|
# scheduser: The userid with authority to submit scheduler jobs
|
||
|
|
# Note: LL does not allow jobs to be submitted by root
|
||
|
|
scheduser=loadl
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# updateall: Allows you to apply updates to all nodes without specifying
|
||
|
|
# specific update groups. This should be used for simple compute node
|
||
|
|
# updates that have no special dependencies on other nodes and update order
|
||
|
|
# is not important. Only those nodes that are currently active in
|
||
|
|
# in the scheduler will be updated.
|
||
|
|
# For LoadLeveler reservation jobs, you can control which nodes will be
|
||
|
|
# updated by specifying different machine requirements, classes, or other
|
||
|
|
# controls that LL allows you in the LL job template that you provide.
|
||
|
|
# If updateall is used, the following entries MUST be specified in this file:
|
||
|
|
# updateall_nodes
|
||
|
|
# updateall_numperupdate
|
||
|
|
# job_template
|
||
|
|
# job_dir
|
||
|
|
# If updateall is used, the following entries can also be used:
|
||
|
|
# maxupdates
|
||
|
|
# oldfeature
|
||
|
|
# newfeature
|
||
|
|
# reservationduration
|
||
|
|
# update_if_down
|
||
|
|
# prescript (but NO prescriptnodes)
|
||
|
|
# shutdowntimeout
|
||
|
|
# outofbandcmd (but NO outofbandnodes)
|
||
|
|
# bringupstatus,bringupappstatus
|
||
|
|
# bringuptimeout
|
||
|
|
# All other entries in this file will be ignored
|
||
|
|
updateall=yes
|
||
|
|
|
||
|
|
|
||
|
|
# updateall_nodes: The xCAT noderange of the nodes to be updated.
|
||
|
|
updateall_nodes=compute
|
||
|
|
|
||
|
|
|
||
|
|
# updateall_numperupdate: The number of nodes that will be reserved at one time
|
||
|
|
# in the scheduler and updated together. The smaller the number, the more
|
||
|
|
# scheduler reservation jobs that will be submitted.
|
||
|
|
# NOTE: LoadLeveler performance decreases with large numbers of
|
||
|
|
# reservations. Do not set this value so low that you will exceed
|
||
|
|
# the maximum number of reservations allowed for your cluster or
|
||
|
|
# that you will degrade LL performance for your production jobs.
|
||
|
|
updateall_numperupdate=3
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# Scheduler Feature values
|
||
|
|
# Node feature values that will be changed in the scheduler during the
|
||
|
|
# update process. These features can be used if users need to run jobs
|
||
|
|
# on only old nodes or only new nodes, but cannot have the job span both
|
||
|
|
# old and new nodes due to software incompatibilities.
|
||
|
|
# oldfeature: This feature value will be removed from the node definition
|
||
|
|
# in the scheduler after the node has been updated
|
||
|
|
oldfeature=oldvalue
|
||
|
|
|
||
|
|
# newfeature: A new feature value that will be set in the scheduler for each
|
||
|
|
# node after it has been updated.
|
||
|
|
newfeature=newvalue
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# maxupdates: Maximum number of updategroups that can be updated at one time
|
||
|
|
# This allows you to ensure you will always have enough computing
|
||
|
|
# resources in your cluster and that not all nodes will attempt to
|
||
|
|
# be updated at once.
|
||
|
|
# A value of "all" specifies that there is no restriction
|
||
|
|
#maxupdates=all
|
||
|
|
maxupdates=16
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
#jobtemplate: Scheduler job template file. See this sample LoadLeveler file
|
||
|
|
# for details on how the template will be processed:
|
||
|
|
jobtemplate=/opt/xcat/share/xcat/rollupdate/llall.tmpl
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
#jobdir: Directory to write the job command files to
|
||
|
|
# For LL, this directory needs to be on a filesystem available to all nodes.
|
||
|
|
jobdir=/u/loadl/rollupdate_jobs
|
||
|
|
|
||
|
|
|
||
|
|
#reservationcallback: INTERNAL KEYWORD used for development only.
|
||
|
|
# This is the reservation notify or callback command.
|
||
|
|
# For Loadleveler, this script must reside on the LoadLeveler central
|
||
|
|
# manager and will be called when the reservation for an updategroup
|
||
|
|
# becomes active.
|
||
|
|
# The default is:
|
||
|
|
#reservationcallback=/opt/xcat/bin/runrollupdate
|
||
|
|
#
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
#reservationduration: Maximum time to hold a LoadLeveler reservation for
|
||
|
|
# the update process. This value in minutes should be longer than the
|
||
|
|
# expected time to shutdown, update, and reboot all the nodes in an update
|
||
|
|
# group. xCAT will release the nodes from the reservation as they come
|
||
|
|
# back up, and will cancel the reservation when the last node has completed.
|
||
|
|
reservationduration=15
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
#update_if_down: If set to "yes", also attempt the update for any node in an
|
||
|
|
# updategroup that is down or not active/available in the scheduler
|
||
|
|
# (useful if you have nodes that are not part of your scheduler's cluster).
|
||
|
|
# If set to "no", any node in an updategroup that is not active in the
|
||
|
|
# scheduler will be skipped.
|
||
|
|
# If set to "cancel", if any node in an updategroup is not active,
|
||
|
|
# the entire updategroup will be skipped.
|
||
|
|
# NOTE: For updateall operation, update_if_down must be "no" or "cancel".
|
||
|
|
# If set to "yes", "cancel" will be assumed.
|
||
|
|
#update_if_down=yes
|
||
|
|
update_if_down=no
|
||
|
|
#update_if_down=cancel
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# prescript
|
||
|
|
# (optional) Command to be run on the xCAT management node before issuing
|
||
|
|
# the shutdown command for the nodes in the updategroup.
|
||
|
|
# NOTE: For updateall operation, prescriptnodes are not supported.
|
||
|
|
# Prescripts will be run for all nodes.
|
||
|
|
# You may specify the string $NODELIST if you would like the
|
||
|
|
# comma-delimited list of xCAT nodenames passed into your command.
|
||
|
|
# Multiple prescript entries can be specified. Each command will be run in
|
||
|
|
# order.
|
||
|
|
#prescript=/u/admin/bin/shutdownGPFS $NODELIST
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# NOT IMPLEMENTED YET! FUTURE SUPPORT FOR ROLLING UPDATE OF DISKFULL NODES
|
||
|
|
# shutdownrequired: Should a shutdown command be sent to the nodes.
|
||
|
|
# Shutdown is required for diskless nodes. For diskfull nodes, simple
|
||
|
|
# updates may be applied to the nodes through prescripts, and a node
|
||
|
|
# reboot may not be required.
|
||
|
|
# Default is "yes".
|
||
|
|
shutdownrequired=yes
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# shutdowntimeout: (optional) The number of minutes xCAT should wait for
|
||
|
|
# an OS shutdown to complete before giving up and issuing a hard power off
|
||
|
|
# command and continuing with the rolling update process.
|
||
|
|
shutdowntimeout=5
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# outofbandcmd
|
||
|
|
# (optional) Out-of-band command to run on the xCAT management
|
||
|
|
# node once the node has been shutdown but before it is rebooted.
|
||
|
|
# NOTE: For updateall operation, outofbandnodes are not supported.
|
||
|
|
# Out-of-band commands will be run for all nodes.
|
||
|
|
# You may specify the string $NODELIST if you would like the
|
||
|
|
# comma-delimited list of xCAT nodenames passed into your command.
|
||
|
|
# Multiple outofbandcmd (with optional outofbandnodes) entries can be
|
||
|
|
# specified. Each command will be run in order.
|
||
|
|
#outofbandcmd=/u/admin/bin/myfirmwareupdates $NODELIST
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# bringupstatus:
|
||
|
|
# OR
|
||
|
|
# bringupappstatus:
|
||
|
|
# The xCAT database node status or appstatus value that xCAT will check and
|
||
|
|
# will wait for to determine that the node is up. Once this status is
|
||
|
|
# reached, xCAT will continue bringing up more nodes (if bringuporder is set)
|
||
|
|
# and will release this node from the scheduler reservation.
|
||
|
|
# If both attributes are set, only bringupappstatus will be used.
|
||
|
|
#bringupappstatus="gpfs=ready"
|
||
|
|
bringupstatus=booted
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
# bringuptimeout: (optional) The maximum number of minutes xCAT should wait
|
||
|
|
# after issuing the rpower on command for the nodes to reach bringupstatus
|
||
|
|
# before giving up. If using bringuporder and this timeout is reached for
|
||
|
|
# one set of nodes, no additional nodes will be attempted to be brought up.
|
||
|
|
# The scheduler reservation will be cancelled.
|
||
|
|
bringuptimeout=10
|
||
|
|
|