X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/df9e166a5ffc4aa79658bec1a5d552a3b413f0d8..8aaefe016ee75d3878946190bb476f9bcccc32bc:/services/nodemanager/doc/ec2.example.cfg

diff --git a/services/nodemanager/doc/ec2.example.cfg b/services/nodemanager/doc/ec2.example.cfg
index 9b41ca14d5..3bc905b085 100644
--- a/services/nodemanager/doc/ec2.example.cfg
+++ b/services/nodemanager/doc/ec2.example.cfg
@@ -1,20 +1,42 @@
+# 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
 # through SLURM before shutting them down.
 #dispatcher = slurm
 
-# 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.
 max_nodes = 8
 
+# 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
+
 # Poll EC2 nodes and Arvados for new information every N seconds.
 poll_time = 60
 
@@ -43,6 +65,21 @@ 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.
+# 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
 
@@ -69,6 +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
@@ -123,16 +162,44 @@ subnet_id = idstring
 # compute node.
 security_groups = idstring1, idstring2
 
-[Size t2.medium]
+# 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
-# can run jobs in the queue (N.B.: defining more than one size has not been
-# tested yet).
+# can run jobs in the queue.
+#
 # 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 Amazon's provided
-# data fields by setting the same names here.
+# in MB) 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.
+
+# 100 GB scratch space
+[Size m4.large]
+cores = 2
+price = 0.126
+scratch = 100000
+
+# 10 GB scratch space
+[Size m4.large.spot]
+instance_type = m4.large
+preemptible = true
 cores = 2
-scratch = 100
+price = 0.126
+scratch = 10000
+
+# 200 GB scratch space
+[Size m4.xlarge]
+cores = 4
+price = 0.252
+scratch = 200000