Sun Grid Engine

My SGE installation process.




Links basics

Com funciona

User level


Hands on



User accounts

To use SMF on Solaris 10 or later hosts and run the Grid Engine software as an unprivileged user, perform the following additional steps as root user (or user with appropriate permissions):
For a local user:

  1. Create the new role sgeadmin:
    roleadd -c "Grid Engine SMF Administrator" -g <group> -d <home_dir> -u <UID> -s <profile_shell> -P "solaris.smf.manage.sge" "sgeadmin"
  1. Assign the just-created role sgeadmin to the user:
    usermod -R "sgeadmin" <login>

For a distributed name service, such as NIS, NIS+, or LDAP:

  • Create the new role sgeadmin and assign it to the user:
    /usr/sadm/bin/smrole add -D <domain_name> - -n "sgeadmin" -a "normal_user" -d <home_dir> -c "Grid Engine SMF Administrator" -p "solaris.smf.manage.sge"
Network services

Determine whether your site’s network services are defined in an NIS database or in an /etc/services file that is local to each workstation. If your site uses NIS, determine the host name of your NIS server so that you can add entries to the NIS services map.

The Grid Engine system services are sge_execd and sge_qmaster. To add the services to your NIS map, choose reserved, unused port numbers. The following examples show sge_qmaster and sge_execd entries.

sge_qmaster 6444/tcp
sge_execd 6445/tcp
Master host
Execution hosts
  • server
    apt-get -y install nfs-kernel-server nfs-common portmap
    echo "/var/nfs,sync,no_subtree_check)" >> /etc/exports
    exportsfs -a
  • client
    apt-get -y install nfs-common portmap
    echo " /mnt/nfs/var/nfs  nfs     rw,sync,hard,intr       0      0" >> /etc/fstab
    mkdir -p /mnt/nfs/var/nfs ; mount -a
  • permisions
    addgroup sgeadmin
    adduser -c "Grid Engine SMF Administrator" --home /home/sgeadmin -g sgeadmin  sgeadmin
    chown -R sgeadmin.sgeadmin /var/nfs/sgeroot

** Tots els nodes i/o masters han de tenir l’usuari sgeadmin

Edició de hostnames
 sudo sed -i "s/kickseed/$HOSTNAME/g" /etc/hosts
 sudo sed -i "s/kickseed/$HOSTNAME/g" /etc/hostname
 sudo hostname -v $HOSTNAME
Instalació del Master
  • Entorn: ** Variables entorn
    echo "
    export SGE_ROOT" >> /home/sgeadmin/.bashrc

    ** hostname

    sed -i "/`hostname`/s/`ifconfig | awk '/Bcast/ {print $2}'|cut -d: -f2`/g" /etc/hosts
  • Descomprimir:
    gzip -dc ../sge/ge-6.2u5-common.tar.gz | tar xvpf -
    gzip -dc ../sge/ge-6.2u5-bin-lx24-amd64.tar.gz |tar xvpf -
    gzip -dc ../sge/ge-6.2u5-bin-lx24-x86.tar.gz |tar xvpf -
    gzip -dc ../sge/ge-6.2u5-bin-lx24-ia64.tar.gz |tar xvpf -
  • Software necessari per a la intalació
    apt-get install binutils sun-java6-jre
  • Iniciar la instalació (as root)
    cd $SGE_ROOT
    ./inst_sge -m
  • JMX MBean server config
    Using the following JMX MBean server settings.
       libjvm_path              >/usr/lib/jvm/java-6-openjdk/jre/lib/amd64/server/<
       Additional JVM arguments >-Xmx256m<
       JMX port                 >6446<
       JMX ssl                  >true<
       JMX client ssl           >true<
       JMX server keystore      >/var/sgeCA/sge_qmaster/default/private/keystore<
       JMX server keystore pw   >*********< ;)   .
  • Berkeley Database spooling parameters
    Berkeley Database spooling parameters
    You are going to install a RPC Client/Server mechanism!
    In this case, qmaster will
    contact a RPC server running on a separate server machine.
    If you want to use the SGE shadowd, you have to use the
    RPC Client/Server mechanism.
    Enter database server name or
    hit <RETURN> to use default [labfbmsge01] >>
    Enter the database directory
    or hit <RETURN> to use default [/mnt/nfs/var/nfs/sgeroot/default/spooldb] >>
    creating directory: /mnt/nfs/var/nfs/sgeroot/default/spooldb
    Please remember these values, during Qmaster installation
    you will be asked for! Hit <RETURN> to continue!
    The Berkeley DB installation is completed now!
    If you are using a Berkely DB Server, please add the
    script to your crontab. This script is used for transaction
    checkpointing and cleanup in SGE installations with a
    Berkeley DB RPC Server. You will find this script in:
    It must be added to the crontab of the user (sgeadmin), who runs the
    berkeley_db_svc on the server host.
    e.g. * * * * * <full path to scripts> <sge-root dir> <sge-cell> <bdb-dir>
  • Sgeadmin Keystore => minim 6 lletres => 123456 leters 😉
  • Using Grid Engine
    Using Grid Engine
    You should now enter the command:
       source /mnt/nfs/var/nfs/sgeroot/default/common/settings.csh
    if you are a csh/tcsh user or
       # . /mnt/nfs/var/nfs/sgeroot/default/common/
    if you are a sh/ksh user.
    This will set or expand the following environment variables:
       - $SGE_ROOT         (always necessary)
       - $SGE_CELL         (if you are using a cell other than >default<)
       - $SGE_CLUSTER_NAME (always necessary)
       - $SGE_QMASTER_PORT (if you haven't added the service >sge_qmaster<)
       - $SGE_EXECD_PORT   (if you haven't added the service >sge_execd<)
       - $PATH/$path       (to find the Grid Engine binaries)
       - $MANPATH          (to access the manual pages)
  • autostart qmaster y bdb on boot as sgeadmin (dona un warning pero no passa res perque només ens interessa el runlevel 2 i en un futur potser el 5)
    echo "sudo -u sgemaster /etc/init.d/sgemaster.FBMGRID " >> /etc/rc.local
    echo "sudo -u sgemaster /etc/init.d/sgebdb start " >> /etc/rc.local
    sed -i "s/exit 0//g" /etc/rc.local
    echo "exit 0" >> /etc/rc.local
    cat /etc/rc.local


no funcionava i he hagut d’executar el  següent:

source /mnt/nfs/var/nfs/sgeroot/default/common/

I ara comença lo divertit, afegir nodes respectant permisos i que funcionin. Despres les cues.



Author: Marc

Leave a Reply

Your email address will not be published. Required fields are marked *