X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/505be2eb9ac1f36a5e31b374451193bc1ab7e90e..55aafbb07904ca24390dd47ea960eae7cb2b909a:/services/nodemanager/doc/azure.example.cfg

diff --git a/services/nodemanager/doc/azure.example.cfg b/services/nodemanager/doc/azure.example.cfg
index ceeff5a729..efd2445175 100644
--- a/services/nodemanager/doc/azure.example.cfg
+++ b/services/nodemanager/doc/azure.example.cfg
@@ -1,20 +1,42 @@
+# Copyright (C) The Arvados Authors. All rights reserved.
+#
+# SPDX-License-Identifier: AGPL-3.0
+
 # Azure 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 Azure nodes and Arvados for new information every N seconds.
 poll_time = 60
 
@@ -43,6 +65,12 @@ boot_fail_after = 1800
 # an Arvados node that hasn't been updated for this long.
 node_stale_after = 14400
 
+# 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 +97,8 @@ 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
@@ -95,6 +125,7 @@ subscription_id = 00000000-0000-0000-0000-000000000000
 # The following directions are based on
 # https://azure.microsoft.com/en-us/documentation/articles/resource-group-authenticate-service-principal/
 #
+# azure config mode arm
 # azure ad app create --name "<Your Application Display Name>" --home-page "<https://YourApplicationHomePage>" --identifier-uris "<https://YouApplicationUri>" --password <Your_Password>
 # azure ad sp create "<Application_Id>"
 # azure role assignment create --objectId "<Object_Id>" -o Owner -c /subscriptions/{subscriptionId}/
@@ -137,16 +168,25 @@ tag_cluster = zyxwv
 # the API server to ping
 ping_host = hostname:port
 
-[Size Standard_D3]
-# You can define any number of Size sections to list Azure 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).
+# You can define any number of Size sections to list Azure sizes you're willing
+# to use.  The Node Manager should boot the cheapest size(s) that can run jobs
+# in the queue.  You must also provide price per hour as the Azure driver
+# compute currently does not report prices.
+#
+# See https://azure.microsoft.com/en-us/pricing/details/virtual-machines/
+# 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 Microsoft's provided
-# data fields by setting the same names here.
+# data fields by setting them here.
+
+[Size Standard_D3]
 cores = 4
-scratch = 200
+price = 0.56
+
+[Size Standard_D4]
+cores = 8
+price = 1.12