Merge branch 'master' into 13804-no-shutdown-wanted-nodes

[arvados.git] / services / nodemanager / doc / ec2.example.cfg

diff --git a/services/nodemanager/doc/ec2.example.cfg b/services/nodemanager/doc/ec2.example.cfg
index b25bf940cf4564a9da43b254c08812b74bf8f528..f5329ebe16213ad1d7fa37aff09212efce299603 100644 (file)
--- a/services/nodemanager/doc/ec2.example.cfg
+++ b/services/nodemanager/doc/ec2.example.cfg
@@ -1,6 +1,20 @@
+# Copyright (C) The Arvados Authors. All rights reserved.
+#
+# SPDX-License-Identifier: AGPL-3.0
+
 # EC2 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]
 # The dispatcher can customize the start and stop procedure for
 # cloud nodes.  For example, the SLURM dispatcher drains nodes
@@ -51,6 +65,15 @@ boot_fail_after = 1800
 # 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.
@@ -83,6 +106,8 @@ apiclient = WARNING
 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
@@ -137,6 +162,11 @@ subnet_id = idstring
 # compute node.
 security_groups = idstring1, idstring2
 
+# Apply an Instance Profile ARN to the newly created compute nodes
+# For more info, see:
+# https://aws.amazon.com/premiumsupport/knowledge-center/iam-policy-restrict-vpc/
+# ex_iamprofile = arn:aws:iam::ACCOUNTNUMBER:instance-profile/ROLENAME
+
 
 # You can define any number of Size sections to list EC2 sizes you're
 # willing to use.  The Node Manager should boot the cheapest size(s) that
@@ -148,12 +178,24 @@ security_groups = idstring1, idstring2
 # You may also want to define the amount of scratch space (expressed
 # in GB) for Crunch jobs.  You can also override Amazon's provided
 # data fields (such as price per hour) by setting them here.
+#
+# Additionally, you can ask for a preemptible instance (AWS's spot instance)
+# by adding the appropriate boolean configuration flag. If you want to have
+# both spot & reserved versions of the same size, you can do so by renaming
+# the Size section and specifying the instance type inside it.
 
 [Size m4.large]
 cores = 2
 price = 0.126
 scratch = 100
 
+[Size m4.large.spot]
+instance_type = m4.large
+preemptible = true
+cores = 2
+price = 0.126
+scratch = 100
+
 [Size m4.xlarge]
 cores = 4
 price = 0.252