cluster

MASTER

Instalar c3 tools desde http://www.csm.ornl.gov/torc/C3/C3softwarepage.shtml(external link)
creamos el archivo /etc/c3.conf
cluster local {
       gfif:gfif #head node
       wn[0-2] #compute nodes
     }




NODES

Dominios

para configurar los deminos primero se pone el fqnd y luego el alias en
/etc/hosts
127.0.0.1       wn0.udea.edu.co localhost wn0.local wn0
127.0.1.1       wn0.itm.edu.co wn0


y editar /etc/sysctl.conf
kernel.domainname = udea.edu.co

sysctl -p /etc/sysctl.conf



ssh

Editar /etc/ssh/ssh_config descomentar y poner en no
#   StrictHostKeyChecking ask


torque queue

#
# Create queues and set their attributes.
#
#
# Create and define queue batch
#
create queue batch
set queue batch queue_type = Execution
set queue batch max_queuable = 200
set queue batch resources_max.walltime = 24:00:00
set queue batch resources_default.nodes = 5
set queue batch resources_default.walltime = 12:00:00
set queue batch enabled = True
set queue batch started = True
#
# Create and define queue long
#
create queue long
set queue long queue_type = Execution
set queue long max_queuable = 200
set queue long resources_max.ncpus = 76
set queue long resources_default.nodes = 3
set queue long resources_default.walltime = 720:00:00
set queue long enabled = True
set queue long started = True
#
# Set server attributes.
#
set server scheduling = True
set server acl_hosts = localhost
set server acl_hosts += gfifmaster
set server acl_hosts += gfif.udea.edu.co
set server acl_hosts += gfif
set server acl_hosts += gfif-wn7
set server acl_hosts += gfif-wn6
set server acl_hosts += gfif-wn5
set server acl_hosts += gfif-wn4
set server acl_hosts += gfif-wn2
set server acl_hosts += gfif-wn1
set server default_queue = batch
set server log_events = 511
set server mail_from = adm
set server resources_max.walltime = 720:00:00
set server scheduler_iteration = 600
set server node_check_rate = 150
set server tcp_timeout = 6
set server poll_jobs = True
set server mom_job_sync = True
set server keep_completed = 300
set server submit_hosts = gfif
set server submit_hosts += localhost
set server next_job_number = 13598





El documento original está disponible en https://clustercien.udea.edu.co/web/tiki-index.php?page=cluster