CentOS 7 install slurm cluster

//slurm install

//CentOS 7 system

//192.168.159.141 node01

//192.168.159.142 node02

systemctl stop firewalld.service

systemctl disable firewalld.service

systemctl disable NetworkManager

systemctl stop NetworkManager

sed -i '7 s/enforcing/disabled/' /etc/sysconfig/selinux

getenforce #is disabled--->>continue or reboot

setenforce 0

yum -y update

yum -y remove mariadb-server mariadb-devel

cat /etc/passwd | grep slurm

userdel -r slurm

userdel -r munge

yum -y install mariadb-server mariadb-devel

export MUNGEUSER=1216

groupadd -m -c "MUNGE Uid 'N' Gid Emporium" -d /var/lib/munge -u $MUNGEUSER -g munge -s /sbin/nologin munge

export SLURMUSER=1217

groupadd -g $SLURMUSER slurm

useradd -m -c "SLURM workload manger" -d /var/lib/slurm -u $SLURMUSER -g slurm -s /bin/bash slurm

yum -y install epel-release

yum -y install munge munge-libs munge-devel

yum -y install rng-tools #node01

rngd -r /dev/urandom #node01

/usr/sbin/create-munge-key -r #node01

dd if=/dev/urandom bs=1 count=1024 > /etc/munge/munge.key #node01

chown munge: /etc/munge/munge.key #node01

chmod 400 /etc/munge/munge.key #node01

scp /etc/munge/munge.key root@node02:/etc/munge #node01

chown -R munge: /etc/munge/ /var/log/munge/

chmod 0700 /etc/munge/ /var/log/munge/

munge -n

munge -n | unmunge

munge -n | ssh node01/02 unmunge

remunge

yum -y install openssl openssl-devel pam-devel numactl numactl-devel hwloc hwloc-devel lua lua-devel readline-devel rrdtool-devel ncurses-devel man2html libmad libibumad

mkdir -p /nfs/slurm-rpms

cd /nfs

### wget https://www.schedmd.com/downloads.php/slurm-17.02.6.tar.bz2

yum -y install rpm-build

rpmbuild -ta slurm-16.08.9.tar.bz2

cd /root/rpmbuild/RPMS/x86_64

cp -p *.rpm /nfs/slurm-rpms

yum -y install --nogpgcheck loclainstall *.rpm

cd /etc/slurm ; cp -p slurm.conf.example slurm.conf #node01

vim slurm.conf #node01

ControlMachine=node01

ControlAddr=node01

StatSaveLocation=/var/spool/slurmctld

SlurmctldLogFile=/var/log/slurmctld.log

SlurmdLogFile=/var/log/slurmd.log

NodeName=node01 CPUs=1 State=UNKOWN

NodeName=node02 CPUs=1 State=UNKOWN

ParttionName=debug Nodes=node01,node02 Default=YES MaxTime=INFINITE State=UP

:wq

mkdir /var/spool/slurmctld

mkdir slurm: /var/spool/slurmctld

chmod 755 /var/spool/slutmctld

touch /var/log/slurmctld.log

chown slurm: /var/log/slurmctld.log

touch /var/log/slurm_jobacct.log /var/log/slurm_jobcomp.log

chown slurm: /var/log/slurm_jobacct.log /var/log/slurm_jobcomp.log

mkdir /var/spool/slurmd

chown slurm: /var/spool/slurmd

chmod 755 /var/spool/slurmd

touch /var/log/slurmd.log

chown slurm: /var/log/slurmd.log

slurmd -C

systemctl stop friewalld.service

systemctl diable firewalld.service

yum -y install ntp

chkconfig ntpd on

ntpdate pool.ntp.org

systemctl start ntpd

systemctl enable slurmd.service

systemctl start slurmd.service

systemctl status slurmd.service

systemctl enable munge.service

systemctl start munge.service

systemctl status munge.service

systemctl enable slurmctld.service #node01

systemctl start slurmctld.service #node01

systemctl status slurmctld.service #node01

scontrol show nodes

sinfo --Node

 

 -----------------------Have questions to contact me :QQ 1394466404----------------------------