-
Notifications
You must be signed in to change notification settings - Fork 8
/
Copy pathbibigrid.yaml
126 lines (103 loc) · 6.21 KB
/
bibigrid.yaml
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
116
117
118
119
120
121
122
123
124
125
126
# For an easy introduction see https://github.com/deNBI/bibigrid_clum
# For more detailed information see https://github.com/BiBiServ/bibigrid/blob/master/documentation/markdown/features/configuration.md
- # -- BEGIN: GENERAL CLUSTER INFORMATION --
# The following options configure cluster wide keys
# Modify these according to your requirements
# sshTimeout: 5 # number of attempts to connect to instances during startup with delay in between
## sshPublicKeyFiles listed here will be added to the master's authorized_keys. A temporary key is stored at ~/.config/bibigrid/keys
# sshPublicKeyFiles:
# - [public key one]
# masterMounts: DEPRECATED -- see `volumes` key for each instance instead
# nfsShares: # list of nfs shares. /vol/spool/ is automatically created as an nfs if nfs is true
# - [nfsShare one]
## Ansible Related
# userRoles: # see ansible_hosts for all 'hosts' options
# - hosts:
# - "master"
# roles: # roles placed in resources/playbook/roles_user
# - name: "resistance_nextflow"
# varsFiles: # (optional)
# - [...]
## If you use a gateway or start a cluster from the cloud, your master does not need a public ip.
# useMasterWithPublicIp: False # defaults True if False no public-ip (floating-ip) will be allocated
# gateway: # if you want to use a gateway for create.
# ip: # IP of gateway to use
# portFunction: 30000 + oct4 # variables are called: oct1.oct2.oct3.oct4
## Only relevant for specific projects (e.g. SimpleVM)
# deleteTmpKeypairAfter: False # warning: if you don't pass a key via sshPublicKeyFiles you lose access!
# dontUploadCredentials: False # warning: enabling this prevents you from scheduling on demand!
## Additional Software
# zabbix: False
# nfs: False
# ide: False # installs a web ide on the master node. A nice way to view your cluster (like Visual Studio Code)
### Slurm Related
# elastic_scheduling: # for large or slow clusters increasing these timeouts might be necessary to avoid failures
# SuspendTimeout: 60 # after SuspendTimeout seconds, slurm allows to power up the node again
# ResumeTimeout: 1200 # if a node doesn't start in ResumeTimeout seconds, the start is considered failed.
# cloudScheduling:
# sshTimeout: 5 # like sshTimeout but during the on demand scheduling on the running cluster
# useMasterAsCompute: True
# -- END: GENERAL CLUSTER INFORMATION --
# -- BEGIN: MASTER CLOUD INFORMATION --
infrastructure: openstack # former mode. Describes what cloud provider is used (others are not implemented yet)
cloud: openstack # name of clouds.yaml cloud-specification key (which is value to top level key clouds)
# waitForServices: # list of existing service names that affect apt. BiBiGrid's playbook will wait until service is "stopped" to avoid issues
# - de.NBI_Bielefeld_environment.service # uncomment for cloud site Bielefeld
## master configuration
masterInstance:
type: # existing type/flavor from your cloud. See launch instance>flavor for options
image: # existing active image from your cloud. Consider using regex to prevent image updates from breaking your running cluster
# features: # list
# - feature1
# partitions: # list
# - partition1
# bootVolume: # optional
# name: # optional; if you want to boot from a specific volume
# terminate: True # whether the volume is terminated on server termination
# size: 50
# volumes: # optional
# - name: volumeName # empty for temporary volumes
# snapshot: snapshotName # optional; to create volume from a snapshot
# mountPoint: /vol/mountPath
# size: 50
# fstype: ext4 # must support chown
# type: # storage type; available values depend on your location; for Bielefeld CEPH_HDD, CEPH_NVME
## Select up to one of the following options; otherwise temporary is picked
# exists: False # if True looks for existing volume with exact name. count must be 1. Volume is never deleted.
# permanent: False # if True volume is never deleted; overwrites semiPermanent if both are given
# semiPermanent: False # if True volume is only deleted during cluster termination
# fallbackOnOtherImage: False # if True, most similar image by name will be picked. A regex can also be given instead.
## worker configuration
# workerInstances:
# - type: # existing type/flavor from your cloud. See launch instance>flavor for options
# image: # same as master. Consider using regex to prevent image updates from breaking your running cluster
# count: 1 # number of workers you would like to create with set type, image combination
# # features: # list
# # partitions: # list of slurm features that all nodes of this group have
# # bootVolume: # optional
# # name: # optional; if you want to boot from a specific volume
# # terminate: True # whether the volume is terminated on server termination
# # size: 50
# # volumes: # optional
# # - name: volumeName # optional
# # snapshot: snapshotName # optional; to create volume from a snapshot
# # mountPoint: /vol/mountPath # optional; not mounted if no path is given
# # size: 50
# # fstype: ext4 # must support chown
# # type: # storage type; available values depend on your location; for Bielefeld CEPH_HDD, CEPH_NVME
# ## Select up to one of the following options; otherwise temporary is picked
# # exists: False # if True looks for existing volume with exact name. count must be 1. Volume is never deleted.
# # permanent: False # if True volume is never deleted; overwrites semiPermanent if both are given
# # semiPermanent: False # if True volume is only deleted during cluster termination
# Depends on image
sshUser: # for example 'ubuntu'
# Depends on project
subnet: # existing subnet from your cloud. See https://openstack.cebitec.uni-bielefeld.de/project/networks/
# network: # only if no subnet is given
# features: # list of slurm features that all nodes of this cloud have
# - feature1
# bootVolume: # optional (cloud wide)
# name: # optional; if you want to boot from a specific volume
# terminate: True # whether the volume is terminated on server termination
# size: 50
#- [next configurations]