超算平台安装 CentOS7下安装slurm20.11

参考文档，https://blog.csdn.net/xuecangqiuye/article/details/109687256

初始环境：CentOS 7.9 最小化安装：
192.168.2.130   mgr
192.168.2.131   node1
192.168.2.132   node2
上传slurm-20.11.2的安装包到管理节点的/home/share/下面。

一、安装mysql（管理节点）
yum -y install mariadb-server
systemctl start mariadb
systemctl enable mariadb
mysql

点击(此处)折叠或打开

1. set password=password('123456');
   
2. create database slurm_acct_db;
   
3. quit

二、安装samba，用于传输文件，可忽略（管理节点）
yum -y install samba
mkdir /home/share
chmod 777 /home/share/
echo "[global]
        log file = /var/log/samba/log.%m
        max log size = 50
        security = user
        map to guest = Bad User
[share]
        path=/home/share
        readonly=yes
        browseable=yes
        writable = yes
        guest ok=yes" > /etc/samba/smb.conf
systemctl start smb
systemctl enable smb

systemctl disable firewalld
systemctl stop firewalld

三、配置初始设定（每个节点上执行，包括管理和计算节点）
export MUNGEUSER=991 && groupadd -g $MUNGEUSER munge
useradd  -m -c "MUNGE Uid 'N' Gid Emporium" -d /var/lib/munge -u $MUNGEUSER -g munge  -s /sbin/nologin munge
export SLURMUSER=992 && groupadd -g $SLURMUSER slurm
useradd  -m -c "SLURM workload manager" -d /var/lib/slurm -u $SLURMUSER -g slurm  -s /bin/bash slurm

yum -y install openssh-clients munge munge-libs munge-devel rng-tools openssl openssl-devel pam-devel numactl numactl-devel hwloc hwloc-devel lua lua-devel readline-devel rrdtool-devel ncurses-devel man2html libibmad libibumad python3-pip perl-ExtUtils-MakeMaker gcc rpm-build mysql-devel json-c json-c-devel http-parser http-parser-devel
yum -y install ucx* hdf5 hdf5-devel freeipmi
yum -y install gcc make libffi-devel openssl-devel 
yum -y install gcc gcc-c++ make autoconf m4 automake libtool 
yum -y install libgpg-error libgcrypt

rngd -r /dev/urandom

echo '192.168.2.130   mgr
192.168.2.131   node1
192.168.2.132   node2' >> /etc/hosts

四、开始安装和配置（在管理节点执行）
echo mgr >> /etc/hostname
ssh-keygen
ssh-copy-id node1
ssh-copy-id node2
ssh node1 "echo node1 > /etc/hostname"
ssh node2 "echo node2 > /etc/hostname"
ssh node1 reboot
ssh node2 reboot
reboot

/usr/sbin/create-munge-key -r
dd if=/dev/urandom bs=1 count=1024 > /etc/munge/munge.key
chown munge: /etc/munge/munge.key && chmod 400 /etc/munge/munge.key

scp /etc/munge/munge.key node1:/etc/munge/
scp /etc/munge/munge.key node2:/etc/munge/

chown -R munge: /etc/munge/ /var/log/munge/ && chmod 0700 /etc/munge/ /var/log/munge/
systemctl enable munge
systemctl start munge
systemctl status munge

ssh node1 "chown -R munge: /etc/munge/ /var/log/munge/ && chmod 0700 /etc/munge/ /var/log/munge/"
ssh node1 systemctl enable munge
ssh node1 systemctl start munge
ssh node1 systemctl status munge

ssh node2 "chown -R munge: /etc/munge/ /var/log/munge/ && chmod 0700 /etc/munge/ /var/log/munge/"
ssh node2 systemctl enable munge
ssh node2 systemctl start munge
ssh node2 systemctl status munge

systemctl stop firewalld
systemctl disable firewalld

ssh node1 systemctl stop firewalld
ssh node1 systemctl disable firewalld
ssh node2 systemctl stop firewalld
ssh node2 systemctl disable firewalld

yum -y install ucx* hdf5 hdf5-devel freeipmi
yum -y install gcc make libffi-devel openssl-devel 
yum -y install gcc gcc-c++ make autoconf m4 automake libtool 
yum -y install libgpg-error libgcrypt

cd /home/share/
rpmbuild -ta --with mysql slurm-20.11.2.tar.bz2
cd
cp -rf rpmbuild/RPMS/x86_64 ./

yum localinstall x86_64/slurm-*.rpm -y

scp -r x86_64/ node1:
scp -r x86_64/ node2:
ssh node1 "yum localinstall x86_64/slurm-*.rpm -y"
ssh node2 "yum localinstall x86_64/slurm-*.rpm -y"

cp /etc/slurm/slurm.conf.example /etc/slurm/slurm.conf
cp /etc/slurm/slurmdbd.conf.example /etc/slurm/slurmdbd.conf
cp /etc/slurm/cgroup.conf.example /etc/slurm/cgroup.conf

本文最后准备了slurm.conf 和 slurmdbd.conf文件供参考
cat /home/share/slurm.conf > /etc/slurm/slurm.conf
cat /home/share/slurmdbd.conf > /etc/slurm/slurmdbd.conf
#cat /home/share/cgroup.conf > /etc/slurm/cgroup.conf #使用默认即可

scp /etc/slurm/slurm.conf node1:/etc/slurm/slurm.conf
scp /etc/slurm/slurm.conf node2:/etc/slurm/slurm.conf
scp /etc/slurm/slurmdbd.conf node1:/etc/slurm/slurmdbd.conf
scp /etc/slurm/slurmdbd.conf node2:/etc/slurm/slurmdbd.conf
scp /etc/slurm/cgroup.conf node1:/etc/slurm/cgroup.conf
scp /etc/slurm/cgroup.conf node2:/etc/slurm/cgroup.conf

mkdir /var/spool/slurmctld && chown slurm: /var/spool/slurmctld && chmod 755 /var/spool/slurmctld
mkdir /var/log/slurm && touch /var/log/slurm/slurmctld.log && chown slurm: /var/log/slurm/slurmctld.log
touch /var/log/slurm/slurm_jobacct.log /var/log/slurm/slurm_jobcomp.log && chown slurm: /var/log/slurm/slurm_jobacct.log /var/log/slurm/slurm_jobcomp.log

ssh node1 "mkdir /var/spool/slurmd && chown slurm: /var/spool/slurmd && chmod 755 /var/spool/slurmd"
ssh node1 "mkdir /var/log/slurm && touch /var/log/slurm/slurmd.log && chown slurm: /var/log/slurm/slurmd.log"
ssh node2 "mkdir /var/spool/slurmd && chown slurm: /var/spool/slurmd && chmod 755 /var/spool/slurmd"
ssh node2 "mkdir /var/log/slurm && touch /var/log/slurm/slurmd.log && chown slurm: /var/log/slurm/slurmd.log"

systemctl enable slurmdbd
systemctl start slurmdbd
systemctl status slurmdbd

systemctl enable slurmctld
systemctl start slurmctld
systemctl status slurmctld

ssh node1 systemctl enable slurmd
ssh node1 systemctl restart slurmd
ssh node1 systemctl status slurmd
ssh node2 systemctl enable slurmd
ssh node2 systemctl restart slurmd
ssh node2 systemctl status slurmd

至此slurm安装完毕，如果启动服务的过程中报错，使用调试方式启动查看启动服务的过程中报错

$ slurmctld -Dvvvvv
$ slurmdbd -Dvvvvv
$ slurmd -Dvvvvv

slurm.conf

点击(此处)折叠或打开

1. SlurmctldHost=mgr
   
2.  
   
3. #
   
4. SlurmctldDebug=info
   
5. SlurmdDebug=debug3
   
6. GresTypes=gpu
   
7.  
   
8. MpiDefault=none
   
9. ProctrackType=proctrack/cgroup
   
10. SlurmctldPidFile=/var/run/slurmctld.pid
    
11. SlurmctldPort=6817
    
12. SlurmdPidFile=/var/run/slurmd.pid
    
13. SlurmdPort=6818
    
14. SlurmdSpoolDir=/var/spool/slurmd
    
15. SlurmUser=root
    
16. StateSaveLocation=/var/spool/slurmctld
    
17. SwitchType=switch/none
    
18. TaskPlugin=task/affinity,task/cgroup
    
19. TaskPluginParam=Sched
    
20.  
    
21. # TIMERS
    
22. InactiveLimit=0
    
23. KillWait=15
    
24. ResumeTimeout=600
    
25. MinJobAge=300
    
26. #OverTimeLimit=0
    
27. SlurmctldTimeout=12
    
28. SlurmdTimeout=300
    
29. Waittime=0
    
30. 
    
31. # SCHEDULING
    
32. SchedulerType=sched/backfill
    
33. SelectType=select/cons_tres
    
34. SelectTypeParameters=CR_Core
    
35. 
    
36. # LOGGING AND ACCOUNTING
    
37. AccountingStorageEnforce=associations
    
38. AccountingStorageHost=mgr
    
39. AccountingStoragePort=6819
    
40. AccountingStorageType=accounting_storage/slurmdbd
    
41. AccountingStoreJobComment=YES
    
42. ClusterName=slurm20_cluster
    
43. JobCompHost=localhost
    
44. JobCompPass=123456
    
45. JobCompPort=3306
    
46. JobCompType=jobcomp/mysql
    
47. JobCompUser=root
    
48. JobAcctGatherFrequency=1
    
49. JobAcctGatherType=jobacct_gather/linux
    
50. SlurmctldLogFile=/var/log/slurm/slurmctld.log
    
51. SlurmdLogFile=/var/log/slurm/slurmd.log
    
52.      
    
53. # POWER SAVE SUPPORT FOR IDLE NODES (optional)
    
54. SuspendTime=70
    
55. NodeName=node[1-2] Procs=1 State=UNKNOWN
    
56. PartitionName=debug Nodes=ALL Default=YES MaxTime=INFINITE State=UP

slurmdbd.conf

点击(此处)折叠或打开

1. # Authentication info
   
2. AuthType=auth/munge
   
3. AuthInfo=/var/run/munge/munge.socket.2
   
4. #DebugLevel=info
   
5. 
   
6. # slurmDBD info
   
7. DbdAddr=192.168.2.130
   
8. DbdHost=localhost
   
9. DbdPort=6819
   
10. SlurmUser=root
    
11. DebugLevel=verbose
    
12. LogFile=/var/log/slurm/slurmdbd.log
    
13. PidFile=/var/run/slurmdbd.pid
    
14. 
    
15. # Database info
    
16. StorageType=accounting_storage/mysql
    
17. StorageHost=localhost
    
18. StoragePort=3306
    
19. StoragePass=123456
    
20. StorageUser=root
    
21. StorageLoc=slurm_acct_db