centos下安装slurm
控制节点node16
计算节点node16，node18
删除安装失败的slurm
yum remove slurm -y
cat /etc/passwd | grep slurm
userdel - r slurm创建用户
export SLURMUSER=412
groupadd -g $SLURMUSER slurm
useradd -m -c "SLURM workload manager" -d /var/lib/slurm -u $SLURMUSER -g slurm -s /bin/bash slurm查看slurm用户组id是否一致,控制节点和所有计算节点都要一样
id slurm安装slurm
先装epel库：
yum install epel-release装slurm的依赖包：
yum install openssl openssl-devel pam-devel numactl numactl-devel hwloc hwloc-devel lua lua-devel readline-devel rrdtool-devel ncurses-devel man2html libibmad libibumad -y如果出现以下报错：
直接卸载冲突部分再重新运行上述命令即可：
yum -y remove ibacm-1.2.0-1.el7.x86_64
yum -y remove libipathverbs-1.3-2.el7.x86_64
yum -y remove ibacm-1.2.0-1.el7.x86_64
yum -y remove libipathverbs-1.3-2.el7.x86_64
装rpm：
yum install rpm-build下载slurm：
wget https://www.schedmd.com/archives.php/downloads/archive/slurm-17.02.4.tar.bz2
rpmbuild -ta slurm-17.02.4.tar.bz2对于控制节点和计算节点：
cd /root/rpmbuild/RPMS/x86_64
mkdir slurm-rpms
cp slurm-15.08.7-1.el7.centos.x86_64.rpm
slurm-devel-15.08.7-1.el7.centos.x86_64.rpm
slurm-munge-15.08.7-1.el7.centos.x86_64.rpm
slurm-pam_slurm-15.08.7-1.el7.centos.x86_64.rpm
slurm-perlapi-15.08.7-1.el7.centos.x86_64.rpm
slurm-plugins-15.08.7-1.el7.centos.x86_64.rpm
slurm-sjobexit-15.08.7-1.el7.centos.x86_64.rpm
slurm-sjstat-15.08.7-1.el7.centos.x86_64.rpm
slurm-slurmdbd-15.08.7-1.el7.centos.x86_64.rpm
slurm-slurmdb-direct-15.08.7-1.el7.centos.x86_64.rpm
slurm-sql-15.08.7-1.el7.centos.x86_64.rpm
slurm-torque-15.08.7-1.el7.centos.x86_64.rpm /slurm-rpms对于计算节点：
yum --nogpgcheck localinstall slurm-15.08.7-1.el7.centos.x86_64.rpm slurm-devel-15.08.7-1.el7.centos.x86_64.rpm slurm-munge-15.08.7-1.el7.centos.x86_64.rpm slurm-perlapi-15.08.7-1.el7.centos.x86_64.rpm slurm-plugins-15.08.7-1.el7.centos.x86_64.rpm slurm-sjobexit-15.08.7-1.el7.centos.x86_64.rpm slurm-sjstat-15.08.7-1.el7.centos.x86_64.rpm slurm-torque-15.08.7-1.el7.centos.x86_64.rpm配置slurm.conf：
cd /etc/slurm
cp slurm.conf.example slurm.conf
vim slurm.conf以下是配置好的slurm.conf：
ControlMachine=node16
ControlAddr=10.192.168.116
#MailProg=/bin/mail
MpiDefault=none
#MpiParams=ports=#-#
ProctrackType=proctrack/pgid
ReturnToService=1
SlurmctldPidFile=/var/run/slurmctld.pid
#SlurmctldPort=6817
SlurmdPidFile=/var/run/slurmd.pid
#SlurmdPort=6818
SlurmdSpoolDir=/var/spool/slurmd
SlurmUser=slurm
#SlurmdUser=root
StateSaveLocation=/var/spool/slurmctld
SwitchType=switch/none
TaskPlugin=task/none
#
#
# TIMERS
#KillWait=30
#MinJobAge=300
#SlurmctldTimeout=120
#SlurmdTimeout=300
#
#
# SCHEDULING
FastSchedule=1
SchedulerType=sched/backfill
#SchedulerPort=7321
SelectType=select/linear
#
#
# LOGGING AND ACCOUNTING
AccountingStorageType=accounting_storage/none
ClusterName=node
#JobAcctGatherFrequency=30
JobAcctGatherType=jobacct_gather/none
#SlurmctldDebug=3
SlurmctldLogFile=/var/log/slurmctld.log
#SlurmdDebug=3
SlurmdLogFile=/var/log/slurmd.log
#
#
# COMPUTE NODES
#NodeName=node16 CPUs=20 RealMemory=63989 Sockets=2 CoresPerSocket=10 ThreadsPerCore=1 State=IDLE
#NodeName=node11 CPUs=20 RealMemory=62138 Sockets=4 CoresPerSocket=5 ThreadsPerCore=1 State=IDLE
#NodeName=node18 CPUs=20 RealMemory=64306 Sockets=2 CoresPerSocket=10 ThreadsPerCore=1 State=IDLE
#PartitionName=control Nodes=node16 Default=NO MaxTime=INFINITE State=UP
#PartitionName=compute Nodes=node16,node11,node18 Default=YES MaxTime=INFINITE State=UP
NodeName=node16 NodeAddr=10.192.168.116 CPUs=20 State=UNKNOWN
#NodeName=node11 NodeAddr=10.192.168.111 CPUs=20 State=UNKNOWN
NodeName=node18 NodeAddr=10.192.168.118 CPUs=20 State=UNKNOWN
#PartitionName=debug Nodes=node16,node11,node18 Default=YES MaxTime=INFINITE State=UP
PartitionName=control Nodes=node16 Default=NO MaxTime=INFINITE State=UP
PartitionName=compute Nodes=node16,node18 Default=YES MaxTime=INFINITE State=UP查看配置文件：
scontrol show config将配置好的conf文件发送到计算节点：
scp slurm.conf root@snode18:/etc/slurm/slurm.conf在控制节点上配置：
mkdir /var/spool/slurmctld
chown slurm: /var/spool/slurmctld
chmod 755 /var/spool/slurmctld
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在计算节点上配置：
mkdir /var/spool/slurmctld
chown slurm: /var/spool/slurmctld chmod 755 /var/spool/slurmctld
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计算节点需关闭防火墙：
systemctl stop firewalld
systemctl disable firewalld测试slurm是否装成功：
如果出现不能连接控制节点的报错就重启一下slurm
slurmd -C
/etc/init.d/slurm start显示结果如下：
ClusterName=(null) NodeName=node16 CPUs=20 Boards=1 SocketsPerBoard=2 CoresPerSocket=10 ThreadsPerCore=1 RealMemory=63989 TmpDisk=51175
UpTime=18-18:49:53
