forked from access-ci-org/Jetstream_Cluster
-
Notifications
You must be signed in to change notification settings - Fork 0
/
slurm.conf
115 lines (115 loc) · 2.75 KB
/
slurm.conf
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
#
# Example slurm.conf file. Please run configurator.html
# (in doc/html) to build a configuration file customized
# for your environment.
#
#
# slurm.conf file generated by configurator.html.
#
# See the slurm.conf man page for more information.
#
ClusterName=js-slurm-elastic
ControlMachine=slurm-example
#ControlAddr=
#BackupController=
#BackupAddr=
#
SlurmUser=slurm
SlurmdUser=root
SlurmctldPort=6817
SlurmdPort=6818
AuthType=auth/munge
#JobCredentialPrivateKey=
#JobCredentialPublicCertificate=
StateSaveLocation=/tmp
SlurmdSpoolDir=/tmp/slurmd
SwitchType=switch/none
MpiDefault=none
SlurmctldPidFile=/var/run/slurmctld.pid
SlurmdPidFile=/var/run/slurmd.pid
ProctrackType=proctrack/pgid
#PluginDir=
#FirstJobId=
ReturnToService=1
#MaxJobCount=
#PlugStackConfig=
#PropagatePrioProcess=
#PropagateResourceLimits=
#PropagateResourceLimitsExcept=
Prolog=/usr/local/sbin/slurm_prolog.sh
#Epilog=
#SrunProlog=
#SrunEpilog=
#TaskProlog=
#TaskEpilog=
#TaskPlugin=
#TrackWCKey=no
#TreeWidth=50
#TmpFS=
#UsePAM=
#
# TIMERS
SlurmctldTimeout=300
SlurmdTimeout=300
#make slurm a little more tolerant here
MessageTimeout=30
TCPTimeout=15
BatchStartTimeout=20
GetEnvTimeout=20
InactiveLimit=0
MinJobAge=604800
KillWait=30
Waittime=0
#
# SCHEDULING
SchedulerType=sched/backfill
#SchedulerAuth=
#SchedulerPort=
#SchedulerRootFilter=
#SelectType=select/linear
SelectType=select/cons_res
SelectTypeParameters=CR_CPU
FastSchedule=0
#PriorityType=priority/multifactor
#PriorityDecayHalfLife=14-0
#PriorityUsageResetPeriod=14-0
#PriorityWeightFairshare=100000
#PriorityWeightAge=1000
#PriorityWeightPartition=10000
#PriorityWeightJobSize=1000
#PriorityMaxAge=1-0
#
# LOGGING
SlurmctldDebug=3
SlurmctldLogFile=/var/log/slurm/slurmctld.log
SlurmdDebug=3
SlurmdLogFile=/var/log/slurmd.log
JobCompType=jobcomp/none
#JobCompLoc=
#
# ACCOUNTING
JobAcctGatherType=jobacct_gather/linux
JobAcctGatherFrequency=30
#
AccountingStorageType=accounting_storage/filetxt
AccountingStorageLoc=/var/log/slurm/slurm_jobacct.log
#AccountingStorageEnforce=associations,limits
#AccountingStoragePass=
#AccountingStorageUser=
#
#GENERAL RESOURCE
GresTypes=""
#
#CLOUD CONFIGURATION
PrivateData=cloud
ResumeProgram=/usr/local/sbin/slurm_resume.sh
SuspendProgram=/usr/local/sbin/slurm_suspend.sh
ResumeRate=0 #number of nodes per minute that can be created; 0 means no limit
ResumeTimeout=900 #max time in seconds between ResumeProgram running and when the node is ready for use
SuspendRate=0 #number of nodes per minute that can be suspended/destroyed
SuspendTime=60 #time in seconds before an idle node is suspended
SuspendTimeout=30 #time between running SuspendProgram and the node being completely down
#COMPUTE NODES
NodeName=compute-[0-1] State=CLOUD CPUs=2
#PARTITIONS
PartitionName=cloud Nodes=compute-[0-1] Default=YES MaxTime=INFINITE State=UP