1 # Azure configuration for Arvados Node Manager.
2 # All times are in seconds unless specified otherwise.
5 # The dispatcher can customize the start and stop procedure for
6 # cloud nodes. For example, the SLURM dispatcher drains nodes
7 # through SLURM before shutting them down.
10 # Node Manager will ensure that there are at least this many nodes running at
11 # all times. If node manager needs to start new idle nodes for the purpose of
12 # satisfying min_nodes, it will use the cheapest node type. However, depending
13 # on usage patterns, it may also satisfy min_nodes by keeping alive some
14 # more-expensive nodes
17 # Node Manager will not start any compute nodes when at least this
21 # Upper limit on rate of spending (in $/hr), will not boot additional nodes
22 # if total price of already running nodes meets or exceeds this threshold.
23 # default 0 means no limit.
26 # Poll Azure nodes and Arvados for new information every N seconds.
29 # Polls have exponential backoff when services fail to respond.
30 # This is the longest time to wait between polls.
33 # If Node Manager can't succesfully poll a service for this long,
34 # it will never start or stop compute nodes, on the assumption that its
35 # information is too outdated.
36 poll_stale_after = 600
38 # If Node Manager boots a cloud node, and it does not pair with an Arvados
39 # node before this long, assume that there was a cloud bootstrap failure and
40 # shut it down. Note that normal shutdown windows apply (see the Cloud
41 # section), so this should be shorter than the first shutdown window value.
42 boot_fail_after = 1800
44 # "Node stale time" affects two related behaviors.
45 # 1. If a compute node has been running for at least this long, but it
46 # isn't paired with an Arvados node, do not shut it down, but leave it alone.
47 # This prevents the node manager from shutting down a node that might
48 # actually be doing work, but is having temporary trouble contacting the
50 # 2. When the Node Manager starts a new compute node, it will try to reuse
51 # an Arvados node that hasn't been updated for this long.
52 node_stale_after = 14400
54 # File path for Certificate Authorities
55 certs_file = /etc/ssl/certs/ca-certificates.crt
59 file = /var/log/arvados/node-manager.log
61 # Log level for most Node Manager messages.
62 # Choose one of DEBUG, INFO, WARNING, ERROR, or CRITICAL.
63 # WARNING lets you know when polling a service fails.
64 # INFO additionally lets you know when a compute node is started or stopped.
67 # You can also set different log levels for specific libraries.
68 # Pykka is the Node Manager's actor library.
69 # Setting this to DEBUG will display tracebacks for uncaught
70 # exceptions in the actors, but it's also very chatty.
73 # Setting apiclient to INFO will log the URL of every Arvados API request.
77 host = zyxwv.arvadosapi.com
81 # Accept an untrusted SSL certificate from the API server?
87 # Shutdown windows define periods of time when a node may and may not be shut
88 # down. These are windows in full minutes, separated by commas. Counting from
89 # the time the node is booted, the node WILL NOT shut down for N1 minutes; then
90 # it MAY shut down for N2 minutes; then it WILL NOT shut down for N3 minutes;
91 # and so on. For example, "20, 999999" means the node may shut down between
92 # the 20th and 999999th minutes of uptime.
93 # Azure bills by the minute, so it makes sense to agressively shut down idle
94 # nodes. Specify at least two windows. You can add as many as you need beyond
96 shutdown_windows = 20, 999999
99 # Use "azure account list" with the azure CLI to get these values.
100 tenant_id = 00000000-0000-0000-0000-000000000000
101 subscription_id = 00000000-0000-0000-0000-000000000000
103 # The following directions are based on
104 # https://azure.microsoft.com/en-us/documentation/articles/resource-group-authenticate-service-principal/
106 # azure config mode arm
107 # azure ad app create --name "<Your Application Display Name>" --home-page "<https://YourApplicationHomePage>" --identifier-uris "<https://YouApplicationUri>" --password <Your_Password>
108 # azure ad sp create "<Application_Id>"
109 # azure role assignment create --objectId "<Object_Id>" -o Owner -c /subscriptions/{subscriptionId}/
111 # Use <Application_Id> for "key" and the <Your_Password> for "secret"
113 key = 00000000-0000-0000-0000-000000000000
119 # The resource group in which the compute node virtual machines will be created
121 ex_resource_group = ArvadosResourceGroup
124 # The image id, in the form "Publisher:Offer:SKU:Version"
125 image = Canonical:UbuntuServer:14.04.3-LTS:14.04.201508050
127 # Path to a local ssh key file that will be used to provision new nodes.
128 ssh_key = /home/arvadosuser/.ssh/id_rsa.pub
130 # The account name for the admin user that will be provisioned on new nodes.
131 ex_user_name = arvadosuser
133 # The Azure storage account that will be used to store the node OS disk images.
134 ex_storage_account = arvadosstorage
136 # The virtual network the VMs will be associated with.
137 ex_network = ArvadosNetwork
139 # Optional subnet of the virtual network.
143 tag_arvados-class = dynamic-compute
146 # the API server to ping
147 ping_host = hostname:port
149 # You can define any number of Size sections to list Azure sizes you're willing
150 # to use. The Node Manager should boot the cheapest size(s) that can run jobs
151 # in the queue. You must also provide price per hour as the Azure driver
152 # compute currently does not report prices.
154 # See https://azure.microsoft.com/en-us/pricing/details/virtual-machines/
155 # for a list of known machine types that may be used as a Size parameter.
157 # Each size section MUST define the number of cores are available in this
158 # size class (since libcloud does not provide any consistent API for exposing
160 # You may also want to define the amount of scratch space (expressed
161 # in GB) for Crunch jobs. You can also override Microsoft's provided
162 # data fields by setting them here.