Ubuntu安装HPC

cat>/etc/hosts<<EOF
127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
168.7.10.80 ldap01.huawei.com
168.7.10.61 master01
168.7.10.62 master02
168.7.10.63 master03
168.7.10.64 master04
168.7.10.65 agent01
168.7.10.66 agent02
168.7.10.67 agent03
EOF

hostname > /etc/hostname

cat>/etc/hosts<<EOF
127.0.0.1       localhost
168.17.0.4   master01
168.17.0.3   master02
168.17.0.5   agent
EOF

#------------------------------------------------
# install base software

apt install -y expect 

#------------------------------------------------
#config NTP Server

apt install -y ntp
apt install -y ntpdate
systemctl enable ntp
systemctl disable chrony && systemctl stop chrony

cat >/etc/ntp.conf<<EOF
driftfile /var/lib/ntp/ntp.drift
leapfile /usr/share/zoneinfo/leap-seconds.list
statistics loopstats peerstats clockstats
filegen loopstats file loopstats type day enable
filegen peerstats file peerstats type day enable
filegen clockstats file clockstats type day enable
pool ntp.ubuntu.com
restrict -4 default kod notrap nomodify nopeer noquery limited
restrict -6 default kod notrap nomodify nopeer noquery limited
restrict 127.0.0.1
restrict ::1
restrict source notrap nomodify noquery
#############################
# add User config
#############################
server 127.127.1.0 iburst
restrict default kod nomodify notrap nopeer noquery
server 0.uk.pool.ntp.org iburst
server 1.uk.pool.ntp.org iburst
server 2.uk.pool.ntp.org iburst
server 3.uk.pool.ntp.org iburst
server 127.127.1.0 #local clock
fudge 127.127.1.0 stratum 10
EOF
systemctl enable ntp
systemctl restart ntp
systemctl status ntp

#####################################################
apt install -y ntp 
echo server 168.17.0.2 >> /etc/ntp.conf
/etc/init.d/ntp restart

apt install -y ntp 
apt install -y ntpdate && ntpdate -u 168.17.0.2

#------------------------------------------------
#resource limits
cat>>/etc/security/limits.conf<<EOF
* soft memlock unlimited
* hard memlock unlimited
* soft stack unlimited
* hard stack unlimited
* soft nofile 1000000
* hard nofile 1000000
* hard nproc 1000000
* soft nproc 1000000
EOF

cat>/etc/locale.conf<<EOF
LANG="en_US.UTF-8"
EOF
systemctl enable NetworkManager
reboot


cat >/etc/hosts<<EOF
127.0.0.1   localhost localhost.localdomain localhost4 localhost4.localdomain4
::1         localhost localhost.localdomain localhost6 localhost6.localdomain6
168.7.10.80 ldap01.huawei.com
168.7.10.61 master01
168.7.10.62 master02
168.7.10.63 master03
168.7.10.64 master04
168.7.10.65 agent01
168.7.10.66 agent02
168.7.10.67 agent03
EOF
cat /etc/hosts









#------------------------------------------------
# config NFS Server
apt install -y nfs-common
apt install -y nfs-kernel-server
apt install -y rpcbind
mkdir -p /data
cat>/etc/exports<<EOF
/share *(rw,no_root_squash,sync)
EOF
systemctl enable rpcbind
systemctl start rpcbind
/etc/init.d/nfs-kernel-server restart
systemctl enable nfs-kernel-server
#------------------------------------------------

#客户端添加文件到/etc/fstab
apt install -y nfs-common
mkdir -p /workspace
mount.nfs 168.17.0.2:/data /workspace
echo "168.17.0.2:/data /workspace nfs defaults,_netdev 0 0">>/etc/fstab


#--------------------------------------------------------
# DonauScheduler User and group
groupadd -g 60001 donau_guest
useradd -g 60001 -m -u 60001 -s /bin/bash donau_guest
echo "donau_guest:huawei@123" | chpasswd 

groupadd -g 60002 ccs_master
useradd -g 60002 -m -u 60002 -s /bin/bash ccs_master
echo "ccs_master:huawei@123" | chpasswd 

groupadd -g 60003 ccs_agent
useradd -g 60003 -m -u 60003 -s /bin/bash ccs_agent
echo "ccs_agent:huawei@123" | chpasswd 

groupadd -g 60004 ccs_auth
useradd -g 60004 -m -u 60004 -s /bin/bash ccs_auth
echo "ccs_auth:huawei@123" | chpasswd 

groupadd -g 60005 ccs_ignite
useradd -g 60005 -m -u 60005 -s /bin/bash ccs_ignite
echo "ccs_ignite:huawei@123" | chpasswd 

groupadd -g 60006 ccs_cli
useradd -g 60006 -m -u 60006 -s /bin/bash ccs_cli
echo "ccs_cli:huawei@123" | chpasswd 

groupadd -g 60007 postgres
useradd -g 60007 -m -u 60007 -s /bin/bash postgres
echo "postgres:huawei@123" | chpasswd 

groupadd -g 60008 ccs_etcd
useradd -g 60008 -m -u 60008 -s /bin/bash ccs_etcd
echo "ccs_etcd:huawei@123" | chpasswd 

#--------------------------------------------------------
# DonauPortal User and group

groupadd -g 60009 ccp_sysadmin
useradd -g 60009 -m -u 60009 -s /bin/bash ccp_sysadmin
echo "ccp_sysadmin:huawei@123" | chpasswd 

groupadd -g 60010 ccp_audadmin
useradd -g 60010 -m -u 60010 -s /bin/bash ccp_audadmin
echo "ccp_audadmin:huawei@123" | chpasswd 

groupadd -g 60013 ccp_secadmin
useradd -g 60013 -m -u 60013 -s /bin/bash ccp_secadmin
echo "ccp_secadmin:huawei@123" | chpasswd 

useradd -g 60002 -m -u 60011 -s /bin/bash ccp_master
echo "ccp_master:huawei@123" | chpasswd 

#--------------------------------------------------------
#create directory and authorization

share_dir=workspace

mkdir -p /${share_dir}/donau
chown root:root /${share_dir}/donau
chmod 755 /${share_dir}/donau -R

mkdir -p /${share_dir}/license
chown ccs_master:ccs_master /${share_dir}/license
chmod 770 /${share_dir}/license -R

mkdir -p /${share_dir}/data
chown ccs_master:ccs_master /${share_dir}/data
chmod 750 /${share_dir}/data -R

mkdir -p /${share_dir}/dataupload
chown ccp_master:root /${share_dir}/dataupload
chmod 700 /${share_dir}/dataupload -R

mkdir -p /${share_dir}/jobdata
chown root:root /${share_dir}/jobdata
chmod 755 /${share_dir}/jobdata -R

mkdir -p /${share_dir}/portal_data
chown root:root /${share_dir}/portal_data
chmod 755 /${share_dir}/portal_data -R

mkdir -p /${share_dir}/scheduler_db
chown root:root /${share_dir}/scheduler_db
chmod 755 /${share_dir}/scheduler_db -R

mkdir -p /${share_dir}/portal_db
chown root:root /${share_dir}/portal_db
chmod 755 /${share_dir}/portal_db -R

mkdir -p /${share_dir}/backup
chown root:root /${share_dir}/backup
chmod 755 /${share_dir}/backup -R

mkdir -p /${share_dir}/scheduler_agent
chown root:root /${share_dir}/scheduler_agent
chmod 755 /${share_dir}/scheduler_agent -R

mkdir -p /${share_dir}/storage
chown ccp_master:root /${share_dir}/storage
chmod 755 /${share_dir}/storage -R

mkdir -p /${share_dir}/mpi
chown root:root /${share_dir}/mpi
chmod 755 /${share_dir}/mpi -R

mkdir -p /opt/donau/1.2.1/
chmod 755 /opt/donau/1.2.1

#------------------------------------------------------------



---
# 单网卡配置IP地址
network:
  version: 2
  renderer: networkd
  ethernets:
    enp131s0:
      addresses: [ 168.17.0.5/24 ]
      gateway4: 168.17.0.1
      nameservers:
          addresses:
              - "114.114.114.114"
---

---
#两张网卡配置bond4
network:
  ethernets:
    enp1s0f0:
      addresses: []
      dhcp4: true
      dhcp6: true
    enp1s0f1:
      addresses: []
      dhcp4: true
      dhcp6: true
  bonds:
    bond0:
      addresses: [ 168.17.0.6/24 ]
      gateway4: 168.17.0.1
      nameservers:
        addresses: [ 8.8.8.8,114.114.114.114 ]
      interfaces:
      - enp1s0f0
      - enp1s0f1
      parameters:
        lacp-rate: fast
        mode: 802.3ad
        transmit-hash-policy: layer2
---


---
#多网卡配置多个子接口
network:
  version: 2
  ethernets:
      enp132s0:
          dhcp4: no
      enp133s0:
          dhcp4: no        
  vlans:
      enp132s0.vlan22:
          id: 33
          link: enp133s0
          addresses: [ "172.31.33.103/24" ]
      enp132s0.vlan44:
          id: 44
          link: enp133s0
          addresses: [ "172.31.44.103/24" ]
      enp133s0.vlan10:
          id: 10
          link: enp133s0
          addresses: [ "172.31.10.103/24" ]    
      enp133s0.vlan11:
          id: 11
          link: enp133s0
          addresses: [ "172.31.11.103/24" ]        
---

netplan apply




@@@@@@@@@@@@@@@@@@@@@@
附录
@@@@@@@@@@@@@@@@@@@@@@
 
deb http://mirrors.aliyun.com/ubuntu/ focal main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-security main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-security main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-updates main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-updates main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-proposed main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-proposed main restricted universe multiverse
deb http://mirrors.aliyun.com/ubuntu/ focal-backports main restricted universe multiverse
deb-src http://mirrors.aliyun.com/ubuntu/ focal-backports main restricted universe multiverse


echo "168.7.10.235:/share /workspace nfs defaults,_netdev 0 0" >> /etc/fstab

cat>/etc/apt/sources.list<<OEF
deb https://repo.huaweicloud.com/ubuntu-ports/ focal-security main restricted universe multiverse
deb-src https://repo.huaweicloud.com/ubuntu-ports/ focal-security main restricted universe multiverse

deb https://repo.huaweicloud.com/ubuntu-ports/ focal-updates main restricted universe multiverse
deb-src https://repo.huaweicloud.com/ubuntu-ports/ focal-updates main restricted universe multiverse

deb https://repo.huaweicloud.com/ubuntu-ports/ focal-backports main restricted universe multiverse
deb-src https://repo.huaweicloud.com/ubuntu-ports/ focal-backports main restricted universe multiverse

OEF