# Google Compute Engine configuration for Arvados Node Manager.
# All times are in seconds unless specified otherwise.

[Daemon]
# Node Manager will ensure that there are at least this many nodes
# running at all times.
min_nodes = 0

# Node Manager will not start any compute nodes when at least this
# many are running.
max_nodes = 8

# Poll compute nodes and Arvados for new information every N seconds.
poll_time = 60

# Polls have exponential backoff when services fail to respond.
# This is the longest time to wait between polls.
max_poll_time = 300

# If Node Manager can't succesfully poll a service for this long,
# it will never start or stop compute nodes, on the assumption that its
# information is too outdated.
poll_stale_after = 600

# "Node stale time" affects two related behaviors.
# 1. If a compute node has been running for at least this long, but it
# isn't paired with an Arvados node, do not shut it down, but leave it alone.
# This prevents the node manager from shutting down a node that might
# actually be doing work, but is having temporary trouble contacting the
# API server.
# 2. When the Node Manager starts a new compute node, it will try to reuse
# an Arvados node that hasn't been updated for this long.
node_stale_after = 14400

# File path for Certificate Authorities
certs_file = /etc/ssl/certs/ca-certificates.crt

[Logging]
# Log file path
file = /var/log/arvados/node-manager.log

# Log level for most Node Manager messages.
# Choose one of DEBUG, INFO, WARNING, ERROR, or CRITICAL.
# WARNING lets you know when polling a service fails.
# INFO additionally lets you know when a compute node is started or stopped.
level = INFO

# You can also set different log levels for specific libraries.
# Pykka is the Node Manager's actor library.
# Setting this to DEBUG will display tracebacks for uncaught
# exceptions in the actors, but it's also very chatty.
pykka = WARNING

# Setting apiclient to INFO will log the URL of every Arvados API request.
apiclient = WARNING

[Arvados]
host = zyxwv.arvadosapi.com
token = ARVADOS_TOKEN
timeout = 15

# Accept an untrusted SSL certificate from the API server?
insecure = no

[Cloud]
provider = gce

# XXX(twp): figure out good default settings for GCE
# It's usually most cost-effective to shut down compute nodes during narrow
# windows of time.  For example, EC2 bills each node by the hour, so the best
# time to shut down a node is right before a new hour of uptime starts.
# Shutdown windows define these periods of time.  These are windows in
# full minutes, separated by commas.  Counting from the time the node is
# booted, the node WILL NOT shut down for N1 minutes; then it MAY shut down
# for N2 minutes; then it WILL NOT shut down for N3 minutes; and so on.
# For example, "54, 5, 1" means the node may shut down from the 54th to the
# 59th minute of each hour of uptime.
# Specify at least two windows.  You can add as many as you need beyond that.
shutdown_windows = 54, 5, 1

[Cloud Credentials]
json_credential_file = /path/to/credential_file.json
project = project-id-from-google-cloud-dashboard
timeout = 60

# Optional settings. For full documentation see
# http://libcloud.readthedocs.org/en/latest/compute/drivers/gce.html#libcloud.compute.drivers.gce.GCENodeDriver
#
# datacenter = us-central1-a
# auth_type = SA               # SA, IA or GCE
# scopes = https://www.googleapis.com/auth/compute
# credential_file =

[Cloud List]
# Keywords here will be used to populate the metadata field for a GCE node.

[Cloud Create]
# New compute nodes will send pings to Arvados at this host.
# You may specify a port, and use brackets to disambiguate IPv6 addresses.
ping_host = hostname:port

# A file path for an SSH key that can log in to the compute node.
# ssh_key = path

# The GCE image name and network zone name to use when creating new nodes.
# * Valid image aliases: https://cloud.google.com/sdk/gcloud/reference/compute/instances/create
# * Valid location (zone) names: https://cloud.google.com/compute/docs/zones
image = debian-7
location = us-central1-a

# JSON string of service account authorizations for this cluster.
# See http://libcloud.readthedocs.org/en/latest/compute/drivers/gce.html#specifying-service-account-scopes
# service_accounts = [ { 'email': 'ex@mple.com', 'scopes': ['storage-ro'] } ]

[Size n1-standard-2]
# You can define any number of Size sections to list node sizes you're
# willing to use.  The Node Manager should boot the cheapest size(s) that
# can run jobs in the queue (N.B.: defining more than one size has not been
# tested yet).
#
# The Size fields are interpreted the same way as with a libcloud NodeSize:
# http://libcloud.readthedocs.org/en/latest/compute/api.html#libcloud.compute.base.NodeSize
#
# See https://cloud.google.com/compute/docs/machine-types for a list
# of known machine types that may be used as a Size parameter.
#
# Each size section MUST define the number of cores are available in this
# size class (since libcloud does not provide any consistent API for exposing
# this setting).
# You may also want to define the amount of scratch space (expressed
# in GB) for Crunch jobs.
cores = 2
scratch = 100
ram = 512