[SGE] SGE 설치, 구성, 삭제등(템플릿 활용)

1. Install master node

master# hostnamectl set-hostname qmaster.local

master# echo ‘192.168.56.101 qmaster.local qmaster’ >> /etc/hosts

master# echo ‘192.168.56.102 compute01.local compute01’ >> /etc/hosts

master# mkdir -p /BiO/src

master# yum -y install epel-release

master# yum -y install jemalloc-devel openssl-devel ncurses-devel pam-devel libXmu-devel hwloc-devel hwloc hwloc-libs java-devel javacc ant-junit libdb-devel motif-devel csh ksh xterm db4-utils perl-XML-Simple perl-Env xorg-x11-fonts-ISO8859-1-100dpi xorg-x11-fonts-ISO8859-1-75dpi

master# groupadd -g 490 sgeadmin

master# useradd -u 495 -g 490 -r -m -d /home/sgeadmin -s /bin/bash -c "SGE Admin" sgeadmin

master# visudo

%sgeadmin ALL=(ALL) NOPASSWD: ALL

master# yum -y install ant

master# cd /BiO/src

master# wget https://arc.liv.ac.uk/downloads/SGE/releases/8.1.9/sge-8.1.9.tar.gz

master# tar zxvfp sge-8.1.9.tar.gz

master# cd sge-8.1.9/source/

master# sh scripts/bootstrap.sh && ./aimk && ./aimk –man

master# export SGE_ROOT=/BiO/gridengine && mkdir $SGE_ROOT

master# echo Y | ./scripts/distinst -local -allall -libs -noexit

master# chown -R sgeadmin.sgeadmin /BiO/gridengine

master# cd $SGE_ROOT

master# vi config.conf

SGE_ROOT="/BiO/gridengine"

SGE_QMASTER_PORT="6444"

SGE_EXECD_PORT="6445"

SGE_ENABLE_SMF="false"

SGE_CLUSTER_NAME="cluster"

SGE_JMX_PORT=""

SGE_JMX_SSL="false"

SGE_JMX_SSL_CLIENT="false"

SGE_JMX_SSL_KEYSTORE=""

SGE_JMX_SSL_KEYSTORE_PW=""

SGE_JVM_LIB_PATH=""

SGE_ADDITIONAL_JVM_ARGS=""

CELL_NAME="default"

ADMIN_USER=sgeadmin

QMASTER_SPOOL_DIR=$SGE_ROOT/$CELL_NAME/spool/qmaster

EXECD_SPOOL_DIR=$SGE_ROOT/$CELL_NAME/default/spool

GID_RANGE="20000-20100"

SPOOLING_METHOD="classic"

DB_SPOOLING_DIR="$SGE_ROOT/$CELL_NAME/spool/spooldb"

PAR_EXECD_INST_COUNT="20"

ADMIN_HOST_LIST="qmaster"

SUBMIT_HOST_LIST="qmaster"

EXEC_HOST_LIST=""

EXECD_SPOOL_DIR_LOCAL=""

HOSTNAME_RESOLVING="true"

SHELL_NAME="ssh"

COPY_COMMAND="scp"

DEFAULT_DOMAIN="none"

ADMIN_MAIL="root"

ADD_TO_RC="true"

SET_FILE_PERMS="true"

RESCHEDULE_JOBS="wait"

SCHEDD_CONF="1"

SHADOW_HOST=""

EXEC_HOST_LIST_RM=""

REMOVE_RC="true"

WINDOWS_SUPPORT="false"

WIN_ADMIN_NAME="Administrator"

WIN_DOMAIN_ACCESS="false"

CSP_RECREATE="true"

CSP_COPY_CERTS="false"

CSP_COUNTRY_CODE="KO"

CSP_STATE="Daejeon"

CSP_LOCATION="YUSEONG-GU"

CSP_ORGA="KRIBB"

CSP_ORGA_UNIT="KOBIC"

CSP_MAIL_ADDRESS=isbyeon@kribb.re.kr

 

master# ./inst_sge -m -auto ./config.conf

master# cp default/common/settings.sh /etc/profile.d/

master# source /etc/profile

master# yum -y install nfs-utils

master# vi /etc/exports

/BiO 192.168.56.0/24(rw,no_root_squash)

master# systemctl start rpcbind nfs-server

master# systemctl enable rpcbind nfs-server

 

2. Add an administrative host

master# qconf -ah compute01

compute01.local added to administrative host list

 

3. SSH Public Key Authentication

master <=> compute01  // ssh-copy-id

 

4. Install compute node

compute01# yum -y install hwloc-devel

compute01# hostnamectl set-hostname compute01.local

compute01# groupadd -g 490 sgeadmin

compute01# useradd -u 495 -g 490 -r -m -d /home/sgeadmin -s /bin/bash -c "SGE Admin" sgeadmin

compute01# yum -y install nfs-utils

compute01# systemctl start rpcbind && systemctl enable rpcbind

compute01# mkdir /BiO

compute01# mount -t nfs 192.168.56.101:/BiO /BiO

compute01# vi /etc/fstab

192.168.56.101:/BiO /BiO nfs defaults 0 0

compute01# echo ‘192.168.56.101 qmaster.local qmaster’ >> /etc/hosts

compute01# echo ‘192.168.56.102 compute01.local compute01’ >> /etc/hosts

compute01# export SGE_ROOT=/BiO/gridengine; export SGE_CELL=default

compute01# SGE_ARCH=`$SGE_ROOT/util/arch`; export SGE_ARCH

compute01# cd $SGE_ROOT

 

compute01# vi compute.conf

SGE_ROOT="/BiO/gridengine"

SGE_QMASTER_PORT="6444"

SGE_EXECD_PORT="6445"

SGE_ENABLE_SMF="false"

SGE_CLUSTER_NAME="cluster"

SGE_JMX_PORT=""

SGE_JMX_SSL="false"

SGE_JMX_SSL_CLIENT="false"

SGE_JMX_SSL_KEYSTORE=""

SGE_JMX_SSL_KEYSTORE_PW=""

SGE_JVM_LIB_PATH=""

SGE_ADDITIONAL_JVM_ARGS=""

CELL_NAME="default"

ADMIN_USER=sgeadmin

QMASTER_SPOOL_DIR=$SGE_ROOT/$CELL_NAME/spool/qmaster

EXECD_SPOOL_DIR=$SGE_ROOT/$CELL_NAME/default/spool

GID_RANGE="20000-20100"

SPOOLING_METHOD="classic"

DB_SPOOLING_DIR="$SGE_ROOT/$CELL_NAME/spool/spooldb"

PAR_EXECD_INST_COUNT="20"

ADMIN_HOST_LIST="qmaster"

SUBMIT_HOST_LIST="qmaster"

EXEC_HOST_LIST="compute01"

EXECD_SPOOL_DIR_LOCAL=""

HOSTNAME_RESOLVING="true"

SHELL_NAME="ssh"

COPY_COMMAND="scp"

DEFAULT_DOMAIN="none"

ADMIN_MAIL="root"

ADD_TO_RC="true"

SET_FILE_PERMS="true"

RESCHEDULE_JOBS="wait"

SCHEDD_CONF="1"

SHADOW_HOST=""

EXEC_HOST_LIST_RM=""

REMOVE_RC="true"

WINDOWS_SUPPORT="false"

WIN_ADMIN_NAME="Administrator"

WIN_DOMAIN_ACCESS="false"

CSP_RECREATE="true"

CSP_COPY_CERTS="false"

CSP_COUNTRY_CODE="KO"

CSP_STATE="Daejeon"

CSP_LOCATION="YUSEONG-GU"

CSP_ORGA="KRIBB"

CSP_ORGA_UNIT="KOBIC"

CSP_MAIL_ADDRESS=isbyeon@kribb.re.kr

compute01# ./inst_sge -x -auto ./compute.conf

compute01# cp /BiO/gridengine/default/common/settings.sh /etc/profile.d/

compute01# source /etc/profile

 

5. Removing an execution host

master# cd /BiO/gridengine

master# cp config.conf remove.conf

master# sed -i -e 's/EXEC_HOST_LIST_RM=\"\"/EXEC_HOST_LIST_RM=\"compute01.local\"/g' remove.conf

master# cat remove.conf | grep EXEC_HOST_LIST_RM

EXEC_HOST_LIST_RM="compute01.local“

master# ./inst_sge -ux -auto ./remove.conf