|
环境: centos8.0 + slurm24.04 (编译安装 )+ MariaDB 10.3 (yum install mariadb-server),
systemctl status slurmdbd 启动提示
- slurmdbd.service - Slurm DBD accounting daemon
- Loaded: loaded (/usr/lib/systemd/system/slurmdbd.service; disabled; vendor preset: disabled)
- Active: failed (Result: exit-code) since Sun 2024-12-01 22:58:22 CST; 6s ago
- Process: 374548 ExecStart=/usr/local/sbin/slurmdbd -D -s $SLURMDBD_OPTIONS (code=exited, status=1/FAILURE)
- Main PID: 374548 (code=exited, status=1/FAILURE)
- 12月 01 22:58:22 master systemd[1]: Started Slurm DBD accounting daemon.
- 12月 01 22:58:22 master slurmdbd[374548]: slurmdbd: Not running as root. Can't drop supplementary groups
- <font color="#ff0000">12月 01 22:58:22 master slurmdbd[374548]: slurmdbd: error: Couldn't find the specified plugin name for accounting_stor>
- 12月 01 22:58:22 master slurmdbd[374548]: slurmdbd: error: cannot find accounting_storage plugin for accounting_storag>
- 12月 01 22:58:22 master slurmdbd[374548]: slurmdbd: error: cannot create accounting_storage context for accounting_sto>
- 12月 01 22:58:22 master slurmdbd[374548]: slurmdbd: fatal: Unable to initialize accounting_storage/mysql accounting st></font>
- 12月 01 22:58:22 master systemd[1]: slurmdbd.service: Main process exited, code=exited, status=1/FAILURE
- 12月 01 22:58:22 master systemd[1]: slurmdbd.service: Failed with result 'exit-code'
复制代码 slurmdbd.conf
- AuthType=auth/munge # 认证方式,该处采用 munge 进行认证
- AuthInfo=/var/run/munge/munge.socket.2
- #
- # slurmDBD info
- DbdAddr=master # 数据库节点名
- DbdHost=localhost # 数据库IP地址
- SlurmUser=slurm # 用户数据库操作的用户
- #DbdPort=7031
- MessageTimeout=60
- DebugLevel=verbose
- #DefaultQOS=normal,standby
- LogFile=/var/log/slurm/slurmdbd.log # slurmdbd 守护进程日志文件绝对路径
- PidFile=/run/slurm/slurmdbd.pid # slurmdbd 守护进程存储进程号文件绝对路径
- #PluginDir=/usr/lib/slurm
- #PrivateData=accounts,users,usage,jobs
- #TrackWCKey=yes
- #
- # Database info
- <font color="#0000ff">StorageType=accounting_storage/mysql </font> # 数据存储类型 mysql
- StorageHost=localhost
- StoragePort=3306
- StoragePass=123456 # 存储数据库密码
- StorageUser=slurm # 存储数据库用户名
- <font color="#0000ff">StorageLoc=slurm_acct_db </font> # 数据库名称
复制代码 slurm.conf
- ################################################
- # ACCOUNTING #
- ################################################
- AccountingStorageEnforce=associations,limits,qos # account 存储数据的配置选项
- AccountingStorageHost=localhost # 数据库存储节点
- AccountingStoragePass=/var/run/munge/munge.socket.2 # munge 认证文件,与 slurmdbd.conf 文件中的 AuthInfo 文件同名。 编译地址: /opt/munge/run/munge/munge.socket.2
- AccountingStoragePort=6819 # slurmd 服务监听端口,默认为 6819
- <font color="#0000ff">AccountingStorageType=accounting_storage/slurmdbd</font> # 数据库记账服务 accounting_storage/slurmdbd or accounting_storage/mysql
- AccountingStorageUser=slurm
- #
- AuthInfo=/var/run/munge/munge.socket.2
- AuthType=auth/munge
- ################################################
- # JOBS #
- ################################################
- JobCompHost=localhost # 作业完成信息的数据库本节点
- <font color="#0000ff">JobCompLoc=slurm_job_db</font> # 数据库名称
- JobCompPass=123456 # slurm 用户数据库密码
- JobCompPort=3306 # 数据库端口
- JobCompType=jobcomp/mysql # 作业完成信息数据存储类型,采用 mysql or mariadb 数据库
- JobCompUser=slurm # 作业完成信息数据库用户名
- #JobContainerType=job_container/linux
- #JobCompUser=
- #JobContainerType=
- JobAcctGatherFrequency=30
- JobAcctGatherType=jobacct_gather/linux
复制代码
/usr/lib/systemd/system/slurmdbd.service
- [Unit]
- Description=Slurm DBD accounting daemon
- After=network-online.target remote-fs.target munge.service mysql.service mysqld.service mariadb.service sssd.service
- Wants=network-online.target
- ConditionPathExists=/usr/local/etc/slurmdbd.conf
- [Service]
- Type=simple
- EnvironmentFile=-/etc/sysconfig/slurmdbd
- EnvironmentFile=-/etc/default/slurmdbd
- <font color="#0000ff">User=slurm
- Group=slurm</font>
- RuntimeDirectory=slurmdbd
- RuntimeDirectoryMode=0755
- ExecStart=/usr/local/sbin/slurmdbd -D -s $SLURMDBD_OPTIONS
- ExecReload=/bin/kill -HUP $MAINPID
- <font color="#0000ff">PIDFile=/run/slurm/slurmdbd.pid</font>
- LimitNOFILE=65536
- TasksMax=infinity
- # Uncomment the following lines to disable logging through journald.
- # NOTE: It may be preferable to set these through an override file instead.
- #StandardOutput=null
- #StandardError=null
- [Install]
- WantedBy=multi-user.target
复制代码
|
|