+# 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.
+# 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
-# many are running.
+# 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
-# Polls have exponential backoff when services fail to respond.
-# This is the longest time to wait between polls.
-max_poll_time = 300
-
# 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# information is too outdated.
# 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
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