# Copyright (C) The Arvados Authors. All rights reserved. # # SPDX-License-Identifier: AGPL-3.0 # Google Compute Engine configuration for Arvados Node Manager. # All times are in seconds unless specified otherwise. [Manage] # The management server responds to http://addr:port/status.json with # a snapshot of internal state. # Management server listening address (default 127.0.0.1) #address = 0.0.0.0 # Management server port number (default -1, server is disabled) #port = 8989 [Daemon] # Node Manager will ensure that there are at least this many nodes running at # all times. If node manager needs to start new idle nodes for the purpose of # satisfying min_nodes, it will use the cheapest node type. However, depending # on usage patterns, it may also satisfy min_nodes by keeping alive some # more-expensive nodes min_nodes = 0 # Node Manager will not start any compute nodes when at least this # running at all times. By default, these will be the cheapest node size. max_nodes = 8 # Poll compute nodes and Arvados for new information every N seconds. poll_time = 60 # Upper limit on rate of spending (in $/hr), will not boot additional nodes # if total price of already running nodes meets or exceeds this threshold. # default 0 means no limit. max_total_price = 0 # 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a service for this long, # it will never start or stop compute nodes, on the assumption that its # information is too outdated.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 # Number of consecutive times a node must report as "idle" before it # will be considered eligible for shutdown. Node status is checked # each poll period, and node can go idle at any point during a poll # period (meaning a node could be reported as idle that has only been # idle for 1 second). With a 60 second poll period, three consecutive # status updates of "idle" suggests the node has been idle at least # 121 seconds. consecutive_idle_count = 3 # Scaling factor to be applied to nodes' available RAM size. Usually there's a # variable discrepancy between the advertised RAM value on cloud nodes and the # actual amount available. # If not set, this value will be set to 0.95 node_mem_scaling = 0.95 # 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 jobs_queue = yes # Get work request from Arvados jobs queue (jobs API) slurm_queue = yes # Get work request from squeue (containers API) # Accept an untrusted SSL certificate from the API server? insecure = no [Cloud] provider = gce # Shutdown windows define periods of time when a node may and may not # be shut down. 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. # GCE bills by the minute, and does not provide information about when # a node booted. Node Manager will store this information in metadata # when it boots a node; if that information is not available, it will # assume the node booted at the epoch. These shutdown settings are # very aggressive. You may want to adjust this if you want more # continuity of service from a single node. shutdown_windows = 20, 999999 [Cloud Credentials] user_id = client_email_address@developer.gserviceaccount.com key = path_to_certificate.pem project = project-id-from-google-cloud-dashboard timeout = 60 # Valid location (zone) names: https://cloud.google.com/compute/docs/zones datacenter = us-central1-a # Optional settings. For full documentation see # http://libcloud.readthedocs.org/en/latest/compute/drivers/gce.html#libcloud.compute.drivers.gce.GCENodeDriver # # auth_type = SA # SA, IA or GCE # scopes = https://www.googleapis.com/auth/compute # credential_file = [Cloud List] # A comma-separated list of tags that must be applied to a node for it to # be considered a compute node. # The driver will automatically apply these tags to nodes it creates. tags = zyxwv, compute [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. image = debian-7 # network = your_network_name # 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':'account@example.com', 'scopes':['storage-ro']}] # 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. # # 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. # You can also override Google's provided data fields (such as price per hour) # by setting them here. [Size n1-standard-2] cores = 2 price = 0.076 scratch = 100 [Size n1-standard-4] cores = 4 price = 0.152 scratch = 200