tyang816/aiweb repository overview

apt-get update
apt-get upgrade
apt-get install make hwloc libhwloc-dev libmunge-dev libmunge2 libmysqlclient-dev build-essential openssh-server -y

apt-get install munge
service start munge

tar -jxvf slurm-21.08.8.tar.bz2 # any version
cd slurm-21.08.8/
mkdir /etc/slurm
./configure --prefix=~/slurm --sysconfdir=/ect/slurm
make -j16
make install

apt-get slurm-wlm

vim /etc/slurm/slurm.conf

# GENERAL
ClusterName=dockercluster
ControlMachine=aiweb
GresTypes=gpu
# Slurm user
SlurmUser=root
# slurmctld daemon log file
SlurmctldLogFile=/etc/slurm/slurmctld.log
# slurmd daemon log file
SlurmdLogFile=/etc/slurm/slurmd.log
# Where to save slurm state files
StateSaveLocation=/etc/slurm/slurmctld.state
# Where slurmd should spool job state information
SlurmdSpoolDir=/etc/slurm/slurmd.spool
# ProctrackType
ProctrackType=proctrack/pgid
# SlurmctldPidFile
SlurmctldPidFile=/etc/slurm/slurmctld.pid
# SlurmdPidFile
SlurmdPidFile=/etc/slurm/slurmd.pid

# SCHEDULING AND ACCOUNTING
AccountingStorageType=accounting_storage/slurmdbd
JobAcctGatherFrequency=30
JobAcctGatherType=jobacct_gather/linux
JobCompType=jobcomp/none
SelectTypeParameters=CR_CPU_Memory
SelectType=select/cons_tres

# LOGGING
SlurmctldDebug=info
SlurmdDebug=info

# NODES AND PARTITIONS
NodeName=aiweb CPUs=20 Sockets=2 CoresPerSocket=10 RealMemory=30000 Gres=gpu:1
PartitionName=normal Nodes=aiweb Default=YES MaxTime=168:00:00 State=UP

# DISABLE MAIL PROGRAM
MailProg=/bin/true

vim /etc/gres.conf

NodeName=aiweb Name=gpu Type=gpu File=/dev/nvidia0

service slurmd start
service slurmctld start

apt-get install slurmdbd mariadb-server
service mariadb start

mysql -u root
CREATE USER 'slurm'@'localhost' IDENTIFIED BY '<password>';
GRANT ALL ON *.* TO 'slurm'@'localhost';
create database slurm_acct_db;
grant all on slurm_acct_db.* to 'slurm'@'localhost' identified by '<password>' with grant option;
exit;

touch /etc/slurm/slurmdbd.conf
chmod 600 /etc/slurm/slurmdbd.conf
vim /etc/slurm/slurmdbd.conf

AuthType=auth/munge
AuthInfo=/var/run/munge/munge.socket.2
#
# slurmDBD info
DbdAddr=127.0.0.1
DbdHost=localhost
#DbdPort=7031
SlurmUser=root
#MessageTimeout=300
DebugLevel=verbose
#DefaultQOS=normal,standby
LogFile=/etc/slurm/slurmdbd.log
PidFile=/etc/slurm/slurmdbd.pid
#PluginDir=/usr/lib/slurm
#PrivateData=accounts,users,usage,jobs
#TrackWCKey=yes
#
# Database info
StorageType=accounting_storage/mysql
StorageHost=localhost
StoragePort=3306
StoragePass=<password> 
StorageUser=slurm
StorageLoc=slurm_acct_db

service slurmdbd start

apt-get install nginx
# remmber change the user to root

apt-get remove --purge mariadb-server mariadb-client
rm -rf /etc/mysql /var/lib/mysql /var/log/mysql
apt-get autoremove
apt-get autoclean
apt-get update