DokuWiki

User Tools

Site Tools

Trace: • 100 • 193 • 112 • 153 • 113 • 171 • 186 • 137 • 114 • 182
cluster:224

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
cluster:224 [2023/10/14 19:32] – hmeij07cluster:224 [2024/01/12 14:36] (current) – hmeij07
Line 16: Line 16:
 10.10.102.48 n38-eth1 10.10.102.48 n38-eth1
 10.11.103.48 n38-ib0 10.11.103.48 n38-ib0
 +DEVROUTE=yes # others no
 +GATEWAY=192,168.102.251 # greentail52
  
 cd /etc/sysconfig/network-scripts/ cd /etc/sysconfig/network-scripts/
 vi ifcfg-eth0 # 192.168.102.x vi ifcfg-eth0 # 192.168.102.x
 vi ifcfg-eth1 # 10.10.102.x   # 'uuidgen eth1' to get uuid vi ifcfg-eth1 # 10.10.102.x   # 'uuidgen eth1' to get uuid
 +
 +# or via  rc.local? see n102
 +vi ifcfg-ib0
 +DEVICE=ib0
 +ONBOOT=yes
 +MTU=65520
 +CONNECTED_MODE=yes
 +BOOTPROTO=none
 +IPADDR=10.11.103.48
 +PREFIX=16
 +# check with ibstat
 + Port 1:
 + State: Active
 + Physical state: LinkUp
 +# check with ethtool ib0
 + Speed: 40000Mb/s
  
 # root: sync cottontail's master and known_hosts (tails+stores) # root: sync cottontail's master and known_hosts (tails+stores)
 ssh-keygen -t rsa ssh-keygen -t rsa
-scp 10.10.102.253:/root/.ssh/authorized_keys /root/.ssh/+scp 10.10.102.250:/root/.ssh/authorized_keys /root/.ssh/ #ctt2
 /etc/ssh/sshd_config (PermitRootLogin) /etc/ssh/sshd_config (PermitRootLogin)
 vi /etc/selinux/config # disabled, do not mistype, kernel will not boot! vi /etc/selinux/config # disabled, do not mistype, kernel will not boot!
Line 79: Line 97:
 rpm -qa | egrep  "libibverbs|libibverbs-devel" rpm -qa | egrep  "libibverbs|libibverbs-devel"
 # no # yum groupinstall "Infiniband Support" # ib already working # no # yum groupinstall "Infiniband Support" # ib already working
-yum install libibvers-devel ibutils infiniband-diags perftest qperf +yum install libibverbs-devel ibutils infiniband-diags perftest qperf -y
  
 # amber20 cmake readline error fix needs # amber20 cmake readline error fix needs
Line 111: Line 129:
 # compute nodes old level 3 # compute nodes old level 3
 systemctl set-default multi-user.target systemctl set-default multi-user.target
 +
 +### centos7 so not an OpenHPC environment
  
 # other configs # other configs
Line 132: Line 152:
 ### REST AT HOME ### REST AT HOME
  
-# or via  rc.local? see n102 
-vi ifcfg-ib0 
-DEVICE=ib0 
-ONBOOT=yes 
-MTU=65520 
-CONNECTED_MODE=yes 
-BOOTPROTO=none 
-IPADDR=10.11.103.48 
-PREFIX=16 
-# check with ibstat 
- Port 1: 
- State: Active 
- Physical state: LinkUp 
-# check with ethtool ib0 
- Speed: 40000Mb/s 
  
 # /etc/fstab # /etc/fstab
Line 182: Line 187:
 rocommunity public rocommunity public
 dontLogTCPWrappersConnects yes dontLogTCPWrappersConnects yes
-# enable, start, add to zenoss +# add to zenoss 
 +systemctl enable snmpd 
 +systemctl start snmpd 
  
  
Line 194: Line 202:
 ln -s /usr/local/slurm-22.05.2 /usr/local/slurm ln -s /usr/local/slurm-22.05.2 /usr/local/slurm
  
-# Put the warewulf cluster key in authorized_keys 
-cd /root/.ssh 
-scp -rp 10.10.102.89:/root/.ssh/authorized_keys . 
  
 # backup and update passwd, shadow, group and hosts files # backup and update passwd, shadow, group and hosts files
Line 210: Line 215:
 chown -R munge:munge /etc/munge /var/log/munge /var/lib/munge /var/run/munge chown -R munge:munge /etc/munge /var/log/munge /var/lib/munge /var/run/munge
 chown -R slurm:munge /var/log/slurm /var/spool/slurm chown -R slurm:munge /var/log/slurm /var/spool/slurm
-  +systemctl enable munge 
 +systemctl start munge 
 +# test unmunge 
 +/usr/local/slurm/sbin/slurmd 
 +# check log 
 # /etc/bashrc (login node) # /etc/bashrc (login node)
 export PATH=/usr/local/slurm/bin:$PATH export PATH=/usr/local/slurm/bin:$PATH
Line 226: Line 236:
 *                -       memlock         270039400 *                -       memlock         270039400
  
 +
 +/etc/rc.local
 +#timing issue with munge
 +#sleep 15
 +#/usr/local/slurm/sbin/slurmd
 +chmod +x /etc/rc.d/rc.local
 +
 +# important!! put private back in place
 +systemctl disable iptables
 +systemctl stop iptables
 +reboot
  
 # file date_ctt2.sh # file date_ctt2.sh
cluster/224.1697311967.txt.gz · Last modified: by hmeij07