X-Git-Url: https://git.arvados.org/arvados.git/blobdiff_plain/0df5f0feeced5bff0adfb806dae2d3811257827f..6762d1501f67860180045bbce3e63ef573d07fec:/doc/install/install-dispatch-cloud.html.textile.liquid
diff --git a/doc/install/install-dispatch-cloud.html.textile.liquid b/doc/install/install-dispatch-cloud.html.textile.liquid
index 42c814b879..7bff6a4a24 100644
--- a/doc/install/install-dispatch-cloud.html.textile.liquid
+++ b/doc/install/install-dispatch-cloud.html.textile.liquid
@@ -2,7 +2,6 @@
layout: default
navsection: installguide
title: Install the cloud dispatcher
-
...
{% comment %}
Copyright (C) The Arvados Authors. All rights reserved.
@@ -10,25 +9,40 @@ Copyright (C) The Arvados Authors. All rights reserved.
SPDX-License-Identifier: CC-BY-SA-3.0
{% endcomment %}
-The cloud dispatch service is an *experimental* service for running containers on cloud VMs. It eliminates the need for SLURM, Node Manager, and SLURM dispatcher. It works with Microsoft Azure and Amazon EC2; future versions will also support Google Compute Engine.
+{% include 'notebox_begin_warning' %}
+arvados-dispatch-cloud is only relevant for cloud installations. Skip this section if you are installing a on premise cluster that will spool jobs to Slurm.
+{% include 'notebox_end' %}
+
+# "Introduction":#introduction
+# "Create compute node VM image":#create-image
+# "Update config.yml":#update-config
+# "Install arvados-dispatch-cloud":#install-packages
+# "Start the service":#start-service
+# "Restart the API server and controller":#restart-api
+# "Confirm working installation":#confirm-working
+
+h2(#introduction). Introduction
+
+The cloud dispatch service is for running containers on cloud VMs. It works with Microsoft Azure and Amazon EC2; future versions will also support Google Compute Engine.
The cloud dispatch service can run on any node that can connect to the Arvados API service, the cloud provider's API, and the SSH service on cloud VMs. It is not resource-intensive, so you can run it on the API server node.
-*Only one dispatch process should be running at a time.* If you are migrating a system that currently runs @crunch-dispatch-slurm@, it is safest to remove the @crunch-dispatch-slurm@ service entirely before installing @arvados-dispatch-cloud@.
+h2(#create-image). Create compute node VM image and configure resolver
-
-~$ sudo systemctl --now disable crunch-dispatch-slurm
-~$ sudo apt-get remove crunch-dispatch-slurm
-
10.20.30.40 ClusterID.example.com
+10.20.30.41 keep1.ClusterID.example.com
+10.20.30.42 keep2.ClusterID.example.com
+
Clusters:
- uuid_prefix:
- ManagementToken: xyzzy
- SystemRootToken: zzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzzz
- NodeProfiles:
- # The key "apiserver" corresponds to ARVADOS_NODE_PROFILE in environment file (see below).
- apiserver:
- arvados-dispatch-cloud:
- Listen: ":9006"
- Services:
- Controller:
- ExternalURL: "https://uuid_prefix.arvadosapi.com"
- CloudVMs:
- # BootProbeCommand is a shell command that succeeds when an instance is ready for service
- BootProbeCommand: "sudo systemctl status docker"
-
- # --- driver-specific configuration goes here --- see Amazon and Azure examples below ---
-
- Dispatch:
- PrivateKey: |
+
Services:
+ DispatchCloud:
+ InternalURLs:
+ "http://localhost:9006": {}
+ Containers:
+ CloudVMs:
+ # BootProbeCommand is a shell command that succeeds when an instance is ready for service
+ BootProbeCommand: "sudo systemctl status docker"
+
+ # --- driver-specific configuration goes here --- see Amazon and Azure examples below ---
+
+ DispatchPrivateKey: |
-----BEGIN RSA PRIVATE KEY-----
MIIEpQIBAAKCAQEAqXoCzcOBkFQ7w4dvXf9B++1ctgZRqEbgRYL3SstuMV4oawks
ttUuxJycDdsPmeYcHsKo8vsEZpN6iYsX6ZZzhkO5nEayUTU8sBjmg1ZCTo4QqKXr
@@ -108,93 +114,174 @@ Add or update the following portions of your cluster configuration file, @/etc/a
Clusters:
- uuid_prefix:
- CloudVMs:
- ImageID: ami-01234567890abcdef
- Driver: ec2
- DriverParameters:
- AccessKeyID: EALMF21BJC7MKNF9FVVR
- SecretAccessKey: yKJAPmoCQOMtYWzEUQ1tKTyrocTcbH60CRvGP3pM
- SecurityGroupIDs:
- - sg-0123abcd
- SubnetID: subnet-0123abcd
- Region: us-east-1
- EBSVolumeType: gp2
- AdminUsername: debian
+
Containers:
+ CloudVMs:
+ ImageID: ami-01234567890abcdef
+ Driver: ec2
+ DriverParameters:
+ AccessKeyID: XXXXXXXXXXXXXXXXXXXX
+ SecretAccessKey: YYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYYY
+ SecurityGroupIDs:
+ - sg-0123abcd
+ SubnetID: subnet-0123abcd
+ Region: us-east-1
+ EBSVolumeType: gp2
+ AdminUsername: arvados
Clusters:
- uuid_prefix:
- CloudVMs:
- ImageID: "https://zzzzzzzz.blob.core.windows.net/system/Microsoft.Compute/Images/images/zzzzz-compute-osDisk.55555555-5555-5555-5555-555555555555.vhd"
- Driver: azure
- DriverParameters:
- SubscriptionID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
- ClientID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
- ClientSecret: 2WyXt0XFbEtutnf2hp528t6Wk9S5bOHWkRaaWwavKQo=
- TenantID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
- CloudEnvironment: AzurePublicCloud
- ResourceGroup: zzzzz
- Location: centralus
- Network: zzzzz
- Subnet: zzzzz-subnet-private
- StorageAccount: example
- BlobContainer: vhds
- DeleteDanglingResourcesAfter: 20s
- AdminUsername: arvados
+
Containers:
+ CloudVMs:
+ ImageID: "https://zzzzzzzz.blob.core.windows.net/system/Microsoft.Compute/Images/images/zzzzz-compute-osDisk.55555555-5555-5555-5555-555555555555.vhd"
+ Driver: azure
+ DriverParameters:
+ SubscriptionID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
+ ClientID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
+ ClientSecret: XXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX
+ TenantID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX
+ CloudEnvironment: AzurePublicCloud
+ ResourceGroup: zzzzz
+ Location: centralus
+ Network: zzzzz
+ Subnet: zzzzz-subnet-private
+ StorageAccount: example
+ BlobContainer: vhds
+ DeleteDanglingResourcesAfter: 20s
+ AdminUsername: arvados
+$ az account list +[ + { + "cloudName": "AzureCloud", + "id": "XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXX", + "isDefault": true, + "name": "Your Subscription", + "state": "Enabled", + "tenantId": "YYYYYYYY-YYYY-YYYY-YYYYYYYY", + "user": { + "name": "you@example.com", + "type": "user" + } + } +] ++ +You will need to create a "service principal" to use as a delegated authority for API access. + +
$ az ad app create --display-name "Arvados Dispatch Cloud (ClusterID)" --homepage "https://arvados.org" --identifier-uris "https://ClusterID.example.com" --end-date 2299-12-31 --password Your_Password
+$ az ad sp create "appId"
+(appId is part of the response of the previous command)
+$ az role assignment create --assignee "objectId" --role Owner --scope /subscriptions/{subscriptionId}/
+(objectId is part of the response of the previous command)
+
ARVADOS_NODE_PROFILE=apiserver
+~$ arvados-server cloudtest && echo "OK!"
~$ sudo yum install arvados-dispatch-cloud
-~$ sudo systemctl enable arvados-dispatch-cloud
+~$ sudo journalctl -o cat -fu arvados-dispatch-cloud.service
~$ sudo apt-get install arvados-dispatch-cloud
+shell:~$ arv container_request create --container-request '{
+ "name": "test",
+ "state": "Committed",
+ "priority": 1,
+ "container_image": "arvados/jobs:latest",
+ "command": ["echo", "Hello, Crunch!"],
+ "output_path": "/out",
+ "mounts": {
+ "/out": {
+ "kind": "tmp",
+ "capacity": 1000
+ }
+ },
+ "runtime_constraints": {
+ "vcpus": 1,
+ "ram": 1048576
+ }
+}'
~$ curl ...
+
+~$ token="xyzzy"
-~$ curl -H "Authorization: Bearer $token" http://localhost:9006/metrics
-# HELP arvados_dispatchcloud_containers_running Number of containers reported running by cloud VMs.
-# TYPE arvados_dispatchcloud_containers_running gauge
-arvados_dispatchcloud_containers_running 0
-[...]
+shell:~$ arv get zzzzz-dz642-hdp2vpu9nq14tx0
+{
+ ...
+ "exit_code":0,
+ "log":"a01df2f7e5bc1c2ad59c60a837e90dc6+166",
+ "output":"d41d8cd98f00b204e9800998ecf8427e+0",
+ "state":"Complete",
+ ...
+}
+
+
~$ arv keep ls a01df2f7e5bc1c2ad59c60a837e90dc6+166
+./crunch-run.txt
+./stderr.txt
+./stdout.txt
+~$ arv-get a01df2f7e5bc1c2ad59c60a837e90dc6+166/stdout.txt
+2016-08-05T13:53:06.201011Z Hello, Crunch!