[ARVADOS] updated: 6ec328c00af03d4542866a2bfcd5f85cb1626c12
Git user
git at public.curoverse.com
Mon Sep 25 14:06:54 EDT 2017
Summary of changes:
.../_nodemanager_azure_example_cfg.liquid | 1 +
doc/_includes/_nodemanager_ec2_example_cfg.liquid | 1 +
doc/_includes/_nodemanager_gce_example_cfg.liquid | 1 +
.../install-nodemanager.html.textile.liquid | 536 +--------------------
services/nodemanager/arvnodeman/daemon.py | 18 +-
services/nodemanager/tests/test_daemon.py | 15 +
6 files changed, 36 insertions(+), 536 deletions(-)
create mode 120000 doc/_includes/_nodemanager_azure_example_cfg.liquid
create mode 120000 doc/_includes/_nodemanager_ec2_example_cfg.liquid
create mode 120000 doc/_includes/_nodemanager_gce_example_cfg.liquid
via 6ec328c00af03d4542866a2bfcd5f85cb1626c12 (commit)
via 2a3f9db14a340dac40812e9e7a04e65efa88f80d (commit)
from 0f1bac0cc06ffa93ddc67ff7d281a5218eaf93f5 (commit)
Those revisions listed above that are new to this repository have
not appeared on any other notification email; so we list those
revisions in full, below.
commit 6ec328c00af03d4542866a2bfcd5f85cb1626c12
Author: Lucas Di Pentima <ldipentima at veritasgenetics.com>
Date: Mon Sep 25 15:02:25 2017 -0300
12073: Updated criteria by which an arvados node record is considered stale.
Added node record cleanup call on successful cloud node shutdown.
Added related test.
Arvados-DCO-1.1-Signed-off-by: Lucas Di Pentima <ldipentima at veritasgenetics.com>
diff --git a/services/nodemanager/arvnodeman/daemon.py b/services/nodemanager/arvnodeman/daemon.py
index 65f55a5..886d4e5 100644
--- a/services/nodemanager/arvnodeman/daemon.py
+++ b/services/nodemanager/arvnodeman/daemon.py
@@ -234,9 +234,11 @@ class NodeManagerDaemonActor(actor_class):
self._update_poll_time('arvados_nodes')
# Check for stale node records
for node in nodelist:
- if node['crunch_worker_state'] == 'down' and \
- node['slot_number'] and \
- arvados_node_missing(node, self.node_stale_after):
+ if node['crunch_worker_state'] in ('down', None) and \
+ arvados_node_missing(node, self.node_stale_after) and \
+ any([node[attr] is not None for attr in (
+ 'slot_number', 'hostname', 'ip_address', 'first_ping_at',
+ 'last_ping_at')]):
self._logger.info(
"Requesting cleanup for stale Arvados node record %s, "
"slot number %s",
@@ -524,6 +526,16 @@ class NodeManagerDaemonActor(actor_class):
record.actor.stop()
record.actor = None
+ # Cleanup related arvados node record
+ if record.arvados_node is not None:
+ self._logger.info(
+ "Cleaning up arvados node record %s, "
+ "slot number %s after successful cloud node shutdown.",
+ record.arvados_node['uuid'],
+ record.arvados_node['slot_number'])
+ self._arvados_node_cleaner.clean_node(record.arvados_node['uuid'],
+ cleanup_reason='Cloud node successfully shutdown')
+
# If the node went from being booted to being shut down without ever
# appearing in the cloud node list, it will have the
# _nodemanager_recently_booted tag, so get rid of it so that the node
diff --git a/services/nodemanager/tests/test_daemon.py b/services/nodemanager/tests/test_daemon.py
index fcb4f2f..9369d9e 100644
--- a/services/nodemanager/tests/test_daemon.py
+++ b/services/nodemanager/tests/test_daemon.py
@@ -179,6 +179,21 @@ class NodeManagerDaemonActorTestCase(testutil.ActorTestMixin,
self.make_daemon([cloud_node], [arv_node])
self.assertFalse(self.node_record_cleaner.clean_node.called)
+ def test_arvados_node_cleanup_after_cloud_node_shutdown(self):
+ cloud_node = testutil.cloud_node_mock(5)
+ self.make_daemon([cloud_node], [testutil.arvados_node_mock(5)])
+ self.assertEqual(1, self.alive_monitor_count())
+ monitor = self.monitor_list()[0].proxy()
+ self.daemon.node_can_shutdown(monitor).get(self.TIMEOUT)
+ self.last_shutdown.success.get.return_value = True
+ self.last_shutdown.stop.side_effect = lambda: monitor.stop()
+ self.assertFalse(self.node_record_cleaner.clean_node.called,
+ "arvados node record cleaned before shutdown")
+ self.daemon.node_finished_shutdown(self.last_shutdown).get(self.TIMEOUT)
+ self.busywait(lambda: 0 == self.paired_monitor_count())
+ self.assertTrue(self.node_record_cleaner.clean_node.called,
+ "arvados node record not cleaned after shutdown")
+
def test_node_pairing(self):
cloud_node = testutil.cloud_node_mock(1)
arv_node = testutil.arvados_node_mock(1)
commit 2a3f9db14a340dac40812e9e7a04e65efa88f80d
Author: Lucas Di Pentima <ldipentima at veritasgenetics.com>
Date: Thu Sep 21 16:18:52 2017 -0300
12073: Nodemanager cloud configuration examples included from
services/nodemanager/doc/ directory to avoid duplication.
Arvados-DCO-1.1-Signed-off-by: Lucas Di Pentima <ldipentima at veritasgenetics.com>
diff --git a/doc/_includes/_nodemanager_azure_example_cfg.liquid b/doc/_includes/_nodemanager_azure_example_cfg.liquid
new file mode 120000
index 0000000..37978f5
--- /dev/null
+++ b/doc/_includes/_nodemanager_azure_example_cfg.liquid
@@ -0,0 +1 @@
+../../services/nodemanager/doc/azure.example.cfg
\ No newline at end of file
diff --git a/doc/_includes/_nodemanager_ec2_example_cfg.liquid b/doc/_includes/_nodemanager_ec2_example_cfg.liquid
new file mode 120000
index 0000000..55082aa
--- /dev/null
+++ b/doc/_includes/_nodemanager_ec2_example_cfg.liquid
@@ -0,0 +1 @@
+../../services/nodemanager/doc/ec2.example.cfg
\ No newline at end of file
diff --git a/doc/_includes/_nodemanager_gce_example_cfg.liquid b/doc/_includes/_nodemanager_gce_example_cfg.liquid
new file mode 120000
index 0000000..8cebe4a
--- /dev/null
+++ b/doc/_includes/_nodemanager_gce_example_cfg.liquid
@@ -0,0 +1 @@
+../../services/nodemanager/doc/gce.example.cfg
\ No newline at end of file
diff --git a/doc/install/install-nodemanager.html.textile.liquid b/doc/install/install-nodemanager.html.textile.liquid
index 09c6b5c..585cd31 100644
--- a/doc/install/install-nodemanager.html.textile.liquid
+++ b/doc/install/install-nodemanager.html.textile.liquid
@@ -50,549 +50,19 @@ The configuration file at @/etc/arvados-node-manager/config.ini@ . Some configu
h3(#aws). Amazon Web Services
<pre>
-# 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. 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
-
-# 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
-
-# If Node Manager boots a cloud node, and it does not pair with an Arvados
-# node before this long, assume that there was a cloud bootstrap failure and
-# shut it down. Note that normal shutdown windows apply (see the Cloud
-# section), so this should be shorter than the first shutdown window value.
-boot_fail_after = 1800
-
-# "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
-
-# 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
-
-# Accept an untrusted SSL certificate from the API server?
-insecure = no
-
-[Cloud]
-provider = ec2
-
-# It's usually most cost-effective to shut down compute nodes during narrow
-# windows of time. For example, EC2 bills each node by the hour, so the best
-# time to shut down a node is right before a new hour of uptime starts.
-# Shutdown windows define these periods of time. 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.
-# Specify at least two windows. You can add as many as you need beyond that.
-shutdown_windows = 54, 5, 1
-
-[Cloud Credentials]
-key = KEY
-secret = SECRET_KEY
-region = us-east-1
-timeout = 60
-
-[Cloud List]
-# This section defines filters that find compute nodes.
-# Tags that you specify here will automatically be added to nodes you create.
-# Replace colons in Amazon filters with underscores
-# (e.g., write "tag:mytag" as "tag_mytag").
-instance-state-name = running
-tag_arvados-class = dynamic-compute
-tag_cluster = zyxwv
-
-[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
-
-# Give the name of an SSH key on AWS...
-ex_keyname = string
-
-# ... or a file path for an SSH key that can log in to the compute node.
-# (One or the other, not both.)
-# ssh_key = path
-
-# The EC2 IDs of the image and subnet compute nodes should use.
-image_id = idstring
-subnet_id = idstring
-
-# Comma-separated EC2 IDs for the security group(s) assigned to each
-# 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
-# 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 (such as price per hour) by setting them here.
-
-[Size m4.large]
-cores = 2
-price = 0.126
-scratch = 100
-
-[Size m4.xlarge]
-cores = 4
-price = 0.252
-scratch = 100
+{% include 'nodemanager_ec2_example_cfg' %}
</pre>
h3(#gcp). Google Cloud Platform
<pre>
-# 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
-
-# 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
-
-# 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 at 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 at 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
+{% include 'nodemanager_gce_example_cfg' %}
</pre>
h3(#azure). Microsoft Azure
<pre>
-# 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. 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
-
-# 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
-
-# If Node Manager boots a cloud node, and it does not pair with an Arvados
-# node before this long, assume that there was a cloud bootstrap failure and
-# shut it down. Note that normal shutdown windows apply (see the Cloud
-# section), so this should be shorter than the first shutdown window value.
-boot_fail_after = 1800
-
-# "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
-
-# 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
-
-# Accept an untrusted SSL certificate from the API server?
-insecure = no
-
-[Cloud]
-provider = azure
-
-# 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, "20, 999999" means the node may shut down between
-# the 20th and 999999th minutes of uptime.
-# Azure bills by the minute, so it makes sense to agressively shut down idle
-# nodes. Specify at least two windows. You can add as many as you need beyond
-# that.
-shutdown_windows = 20, 999999
-
-[Cloud Credentials]
-# Use "azure account list" with the azure CLI to get these values.
-tenant_id = 00000000-0000-0000-0000-000000000000
-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}/
-#
-# Use <Application_Id> for "key" and the <Your_Password> for "secret"
-#
-key = 00000000-0000-0000-0000-000000000000
-secret = PASSWORD
-timeout = 60
-region = East US
-
-[Cloud List]
-# The resource group in which the compute node virtual machines will be created
-# and listed.
-ex_resource_group = ArvadosResourceGroup
-
-[Cloud Create]
-# The compute node image, as a link to a VHD in Azure blob store.
-image = https://example.blob.core.windows.net/system/Microsoft.Compute/Images/images/zyxwv-compute-osDisk.vhd
-
-# Path to a local ssh key file that will be used to provision new nodes.
-ssh_key = /home/arvadosuser/.ssh/id_rsa.pub
-
-# The account name for the admin user that will be provisioned on new nodes.
-ex_user_name = arvadosuser
-
-# The Azure storage account that will be used to store the node OS disk images.
-ex_storage_account = arvadosstorage
-
-# The virtual network the VMs will be associated with.
-ex_network = ArvadosNetwork
-
-# Optional subnet of the virtual network.
-#ex_subnet = default
-
-# Node tags
-tag_arvados-class = dynamic-compute
-tag_cluster = zyxwv
-
-# the API server to ping
-ping_host = hostname:port
-
-# 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 them here.
-
-[Size Standard_D3]
-cores = 4
-price = 0.56
-
-[Size Standard_D4]
-cores = 8
-price = 1.12
+{% include 'nodemanager_azure_example_cfg' %}
</pre>
h2. Running
-----------------------------------------------------------------------
hooks/post-receive
--
More information about the arvados-commits
mailing list