Bump version to 0.9.7

Before, the default False was problematic and would reset consoles if
the template was otherwise modified. Instead switch the flags to be full
true/false flags, and on modify, adjust the default to be None so they
will not be changed.

README.md

@@ -5,7 +5,6 @@
 <br/><br/>
 <a href="https://github.com/parallelvirtualcluster/pvc"><img alt="License" src="https://img.shields.io/github/license/parallelvirtualcluster/pvc"/></a>
 <a href="https://github.com/parallelvirtualcluster/pvc/releases"><img alt="Release" src="https://img.shields.io/github/release-pre/parallelvirtualcluster/pvc"/></a>
-<a href="https://git.bonifacelabs.ca/parallelvirtualcluster/pvc/pipelines"><img alt="Pipeline Status" src="https://git.bonifacelabs.ca/parallelvirtualcluster/pvc/badges/master/pipeline.svg"/></a>
 <a href="https://parallelvirtualcluster.readthedocs.io/en/latest/?badge=latest"><img alt="Documentation Status" src="https://readthedocs.org/projects/parallelvirtualcluster/badge/?version=latest"/></a>
 </p>
 
@@ -17,10 +16,25 @@ The major goal of PVC is to be administrator friendly, providing the power of En
 
 ## Getting Started
 
-To get started with PVC, read the [Cluster Architecture document](https://parallelvirtualcluster.readthedocs.io/en/latest/architecture/cluster/), then see [Installing](https://parallelvirtualcluster.readthedocs.io/en/latest/installing) for details on setting up a set of PVC nodes, using the [PVC Ansible](https://parallelvirtualcluster.readthedocs.io/en/latest/manuals/ansible) framework to configure and bootstrap a cluster, and managing it with the [`pvc` CLI tool](https://parallelvirtualcluster.readthedocs.io/en/latest/manuals/cli) or [RESTful HTTP API](https://parallelvirtualcluster.readthedocs.io/en/latest/manuals/api). For details on the project, its motivation, and architectural details, see [the About page](https://parallelvirtualcluster.readthedocs.io/en/latest/about).
+To get started with PVC, please see the [About](https://parallelvirtualcluster.readthedocs.io/en/latest/about/) page for general information about the project, and the [Getting Started](https://parallelvirtualcluster.readthedocs.io/en/latest/getting-started/) page for details on configuring your cluster.
 
 ## Changelog
 
+#### v0.9.7
+
+  * Fixes bug with provisioner system template modifications
+
+#### v0.9.6
+
+  * Fixes bug with migrations
+
+#### v0.9.5
+
+  * Fixes bug with line count in log follow
+  * Fixes bug with disk stat output being None
+  * Adds short pretty health output
+  * Documentation updates
+
 #### v0.9.4
 
   * Fixes major bug in OVA parser

client-cli/cli_lib/cluster.py

@@ -104,6 +104,20 @@ def format_info(cluster_information, oformat):
         storage_health_colour = ansiprint.yellow()
 
     ainformation = []
+
+    if oformat == 'short':
+        ainformation.append('{}PVC cluster status:{}'.format(ansiprint.bold(), ansiprint.end()))
+        ainformation.append('{}Cluster health:{}      {}{}{}'.format(ansiprint.purple(), ansiprint.end(), health_colour, cluster_information['health'], ansiprint.end()))
+        if cluster_information['health_msg']:
+            for line in cluster_information['health_msg']:
+                ainformation.append('                     > {}'.format(line))
+        ainformation.append('{}Storage health:{}      {}{}{}'.format(ansiprint.purple(), ansiprint.end(), storage_health_colour, cluster_information['storage_health'], ansiprint.end()))
+        if cluster_information['storage_health_msg']:
+            for line in cluster_information['storage_health_msg']:
+                ainformation.append('                     > {}'.format(line))
+
+        return '\n'.join(ainformation)
+
     ainformation.append('{}PVC cluster status:{}'.format(ansiprint.bold(), ansiprint.end()))
     ainformation.append('')
     ainformation.append('{}Cluster health:{}      {}{}{}'.format(ansiprint.purple(), ansiprint.end(), health_colour, cluster_information['health'], ansiprint.end()))
@@ -114,6 +128,7 @@ def format_info(cluster_information, oformat):
     if cluster_information['storage_health_msg']:
         for line in cluster_information['storage_health_msg']:
             ainformation.append('                     > {}'.format(line))
+
     ainformation.append('')
     ainformation.append('{}Primary node:{}        {}'.format(ansiprint.purple(), ansiprint.end(), cluster_information['primary_node']))
     ainformation.append('{}Cluster upstream IP:{} {}'.format(ansiprint.purple(), ansiprint.end(), cluster_information['upstream_ip']))

client-cli/cli_lib/vm.py

@@ -539,7 +539,10 @@ def vm_networks_add(config, vm, network, macaddr, model, restart):
     device_xml = fromstring(device_string)
 
     last_interface = None
-    for interface in parsed_xml.devices.find('interface'):
+    all_interfaces = parsed_xml.devices.find('interface')
+    if all_interfaces is None:
+        all_interfaces = []
+    for interface in all_interfaces:
         last_interface = re.match(r'[vm]*br([0-9a-z]+)', interface.source.attrib.get('bridge')).group(1)
         if last_interface == network:
             return False, 'Network {} is already configured for VM {}.'.format(network, vm)
@@ -547,6 +550,8 @@ def vm_networks_add(config, vm, network, macaddr, model, restart):
         for interface in parsed_xml.devices.find('interface'):
             if last_interface == re.match(r'[vm]*br([0-9a-z]+)', interface.source.attrib.get('bridge')).group(1):
                 interface.addnext(device_xml)
+    else:
+        parsed_xml.devices.find('emulator').addprevious(device_xml)
 
     try:
         new_xml = tostring(parsed_xml, pretty_print=True)
@@ -732,7 +737,10 @@ def vm_volumes_add(config, vm, volume, disk_id, bus, disk_type, restart):
 
     last_disk = None
     id_list = list()
-    for disk in parsed_xml.devices.find('disk'):
+    all_disks = parsed_xml.devices.find('disk')
+    if all_disks is None:
+        all_disks = []
+    for disk in all_disks:
         id_list.append(disk.target.attrib.get('dev'))
         if disk.source.attrib.get('protocol') == disk_type:
             if disk_type == 'rbd':
@@ -782,9 +790,14 @@ def vm_volumes_add(config, vm, volume, disk_id, bus, disk_type, restart):
     elif disk_type == 'file':
         new_disk_details.source.set('file', volume)
 
-    for disk in parsed_xml.devices.find('disk'):
+    all_disks = parsed_xml.devices.find('disk')
+    if all_disks is None:
+        all_disks = []
+    for disk in all_disks:
         last_disk = disk
-    last_disk.addnext(new_disk_details)
+
+    if last_disk is None:
+        parsed_xml.devices.find('emulator').addprevious(new_disk_details)
 
     try:
         new_xml = tostring(parsed_xml, pretty_print=True)
@@ -1007,8 +1020,11 @@ def follow_console_log(config, vm, lines=10):
     print(loglines, end='')
 
     while True:
-        # Grab the next line set
+        # Grab the next line set (500 is a reasonable number of lines per second; any more are skipped)
         try:
+            params = {
+                'lines': 500
+            }
             response = call_api(config, 'get', '/vm/{vm}/console'.format(vm=vm), params=params)
             new_console_log = response.json()['data']
         except Exception:
@@ -1066,20 +1082,20 @@ def format_info(config, domain_information, long_output):
         ainformation.append('')
         ainformation.append('{0}Memory stats:{1}       {2}Swap In  Swap Out  Faults (maj/min)  Available  Usable  Unused  RSS{3}'.format(ansiprint.purple(), ansiprint.end(), ansiprint.bold(), ansiprint.end()))
         ainformation.append('                    {0: <7}  {1: <8}  {2: <16}  {3: <10} {4: <7} {5: <7} {6: <10}'.format(
-            format_metric(domain_information['memory_stats'].get('swap_in')),
-            format_metric(domain_information['memory_stats'].get('swap_out')),
-            '/'.join([format_metric(domain_information['memory_stats'].get('major_fault')), format_metric(domain_information['memory_stats'].get('minor_fault'))]),
-            format_bytes(domain_information['memory_stats'].get('available') * 1024),
-            format_bytes(domain_information['memory_stats'].get('usable') * 1024),
-            format_bytes(domain_information['memory_stats'].get('unused') * 1024),
-            format_bytes(domain_information['memory_stats'].get('rss') * 1024)
+            format_metric(domain_information['memory_stats'].get('swap_in', 0)),
+            format_metric(domain_information['memory_stats'].get('swap_out', 0)),
+            '/'.join([format_metric(domain_information['memory_stats'].get('major_fault', 0)), format_metric(domain_information['memory_stats'].get('minor_fault', 0))]),
+            format_bytes(domain_information['memory_stats'].get('available', 0) * 1024),
+            format_bytes(domain_information['memory_stats'].get('usable', 0) * 1024),
+            format_bytes(domain_information['memory_stats'].get('unused', 0) * 1024),
+            format_bytes(domain_information['memory_stats'].get('rss', 0) * 1024)
         ))
         ainformation.append('')
         ainformation.append('{0}vCPU stats:{1}         {2}CPU time (ns)     User time (ns)    System time (ns){3}'.format(ansiprint.purple(), ansiprint.end(), ansiprint.bold(), ansiprint.end()))
         ainformation.append('                    {0: <16}  {1: <16}  {2: <15}'.format(
-            str(domain_information['vcpu_stats'].get('cpu_time')),
-            str(domain_information['vcpu_stats'].get('user_time')),
-            str(domain_information['vcpu_stats'].get('system_time'))
+            str(domain_information['vcpu_stats'].get('cpu_time', 0)),
+            str(domain_information['vcpu_stats'].get('user_time', 0)),
+            str(domain_information['vcpu_stats'].get('system_time', 0))
         ))
 
     # PVC cluster information
@@ -1166,8 +1182,8 @@ def format_info(config, domain_information, long_output):
                 disk['name'],
                 disk['dev'],
                 disk['bus'],
-                '/'.join([str(format_metric(disk['rd_req'])), str(format_metric(disk['wr_req']))]),
-                '/'.join([str(format_bytes(disk['rd_bytes'])), str(format_bytes(disk['wr_bytes']))]),
+                '/'.join([str(format_metric(disk.get('rd_req', 0))), str(format_metric(disk.get('wr_req', 0)))]),
+                '/'.join([str(format_bytes(disk.get('rd_bytes', 0))), str(format_bytes(disk.get('wr_bytes', 0)))]),
                 width=name_length
             ))
         ainformation.append('')
@@ -1179,9 +1195,9 @@ def format_info(config, domain_information, long_output):
                 net['source'],
                 net['model'],
                 net['mac'],
-                '/'.join([str(format_bytes(net['rd_bytes'])), str(format_bytes(net['wr_bytes']))]),
-                '/'.join([str(format_metric(net['rd_packets'])), str(format_metric(net['wr_packets']))]),
-                '/'.join([str(format_metric(net['rd_errors'])), str(format_metric(net['wr_errors']))]),
+                '/'.join([str(format_bytes(net.get('rd_bytes', 0))), str(format_bytes(net.get('wr_bytes', 0)))]),
+                '/'.join([str(format_metric(net.get('rd_packets', 0))), str(format_metric(net.get('wr_packets', 0)))]),
+                '/'.join([str(format_metric(net.get('rd_errors', 0))), str(format_metric(net.get('wr_errors', 0)))]),
             ))
         # Controller list
         ainformation.append('')

client-cli/pvc.py

@@ -2721,14 +2721,14 @@ def provisioner_template_system_list(limit):
     help='The amount of vRAM (in MB).'
 )
 @click.option(
-    '-s', '--serial', 'serial',
+    '-s/-S', '--serial/--no-serial', 'serial',
     is_flag=True, default=False,
     help='Enable the virtual serial console.'
 )
 @click.option(
-    '-n', '--vnc', 'vnc',
+    '-n/-N', '--vnc/--no-vnc', 'vnc',
     is_flag=True, default=False,
-    help='Enable the VNC console.'
+    help='Enable/disable the VNC console.'
 )
 @click.option(
     '-b', '--vnc-bind', 'vnc_bind',
@@ -2801,14 +2801,14 @@ def provisioner_template_system_add(name, vcpus, vram, serial, vnc, vnc_bind, no
     help='The amount of vRAM (in MB).'
 )
 @click.option(
-    '-s', '--serial', 'serial',
+    '-s/-S', '--serial/--no-serial', 'serial',
     is_flag=True, default=None,
     help='Enable the virtual serial console.'
 )
 @click.option(
-    '-n', '--vnc', 'vnc',
+    '-n/-N', '--vnc/--no-vnc', 'vnc',
     is_flag=True, default=None,
-    help='Enable the VNC console.'
+    help='Enable/disable the VNC console.'
 )
 @click.option(
     '-b', '--vnc-bind', 'vnc_bind',
@@ -4057,13 +4057,19 @@ def maintenance_off():
 @click.command(name='status', short_help='Show current cluster status.')
 @click.option(
     '-f', '--format', 'oformat', default='plain', show_default=True,
-    type=click.Choice(['plain', 'json', 'json-pretty']),
+    type=click.Choice(['plain', 'short', 'json', 'json-pretty']),
     help='Output format of cluster status information.'
 )
 @cluster_req
 def status_cluster(oformat):
     """
     Show basic information and health for the active PVC cluster.
+
+    Output formats:
+      plain: Full text, full colour output for human-readability.
+      short: Health-only, full colour output for human-readability.
+      json: Compact JSON representation for machine parsing.
+      json-pretty: Pretty-printed JSON representation for machine parsing or human-readability.
     """
 
     retcode, retdata = pvc_cluster.get_info(config)

debian/changelog

@@ -1,3 +1,24 @@
+pvc (0.9.7-0) unstable; urgency=high
+
+  * Fixes bug with provisioner system template modifications
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Thu, 19 Nov 2020 10:48:28 -0500
+
+pvc (0.9.6-0) unstable; urgency=high
+
+  * Fixes bug with migrations
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Tue, 17 Nov 2020 13:01:54 -0500
+
+pvc (0.9.5-0) unstable; urgency=high
+
+  * Fixes bug with line count in log follow
+  * Fixes bug with disk stat output being None
+  * Adds short pretty health output
+  * Documentation updates
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Tue, 17 Nov 2020 12:34:04 -0500
+
 pvc (0.9.4-0) unstable; urgency=high
 
   * Fixes major bug in OVA parser

docs/about.md

@@ -1,65 +1,149 @@
-# About the Parallel Virtual Cluster suite
+# About the Parallel Virtual Cluster system
 
-## Project Goals and Philosophy
+- [About the Parallel Virtual Cluster system](#about-the-parallel-virtual-cluster-system)
+  * [Project Motivation](#project-motivation)
+  * [Building Blocks](#building-blocks)
+  * [Cluster Architecture](#cluster-architecture)
+  * [Clients](#clients)
+    + [API Client](#api-client)
+    + [Direct Bindings](#direct-bindings)
+    + [CLI Client](#cli-client)
+  * [Deployment](#deployment)
+  * [Frequently Asked Questions](#frequently-asked-questions)
+    + [General Questions](#general-questions)
+    + [Feature Questions](#feature-questions)
+    + [Storage Questions](#storage-questions)
+  * [About The Author](#about-the-author)
+
+This document contains information about the project itself, the software stack, its motivations, and a number of frequently-asked questions.
+
+## Project Motivation
 
 Server management and system administration have changed significantly in the last decade. Computing as a resource is here, and software-defined is the norm. Gone are the days of pet servers, of tweaking configuration files by hand, and of painstakingly installing from ISO images in 52x CD-ROM drives. This is a brave new world.
 
-As part of this trend, the rise of IaaS (Infrastructure as a Service) has created an entirely new way for administrators and, increasingly, developers, to interact with servers. They need to be able to provision virtual machines easily and quickly, to ensure those virtual machines are reliable and consistent, and to avoid downtime wherever possible.
+As part of this trend, the rise of IaaS (Infrastructure as a Service) has created an entirely new way for administrators and, increasingly, developers, to interact with servers. They need to be able to provision virtual machines easily and quickly, to ensure those virtual machines are reliable and consistent, and to avoid downtime wherever possible. Even in a world of containers, VMs are still important, and are not going away, so some virtual management solution is a must.
 
-However, the state of the Free Software, virtual management ecosystem at the start of 2020 is quite disappointing. On the one hand are the giant, IaaS products like OpenStack and CloudStack. These are massive pieces of software, featuring dozens of interlocking parts, designed for massive clusters and public cloud deployments. They're great for a "hyperscale" provider, a large-scale SaaS/IaaS provider, or an enterprise. But they're not designed for small teams or small clusters. On the other hand, tools like Proxmox, oVirt, and even good old fashioned shell scripts are barely scalable, are showing their age, and have become increasingly unwieldy for advanced use-cases - great for one server, not so great for 9 in a highly-available cluster. Not to mention the constant attempts to monetize by throwing features behind Enterprise subscriptions. In short, there is a massive gap between the old-style, pet-based virtualization and the modern, large-scale, IaaS-type virtualization. This is not to mention the well-entrenched, proprietary solutions like VMWare and Nutanix which provide many of the features a small cluster administrator requires, but can be prohibitively expensive for small organizations.
+However, the current state of this ecosystem is lacking. At present there are 3 primary categories: the large "Stack" open-source projects, the smaller traditional "VM management" open-source projects, and the entrenched proprietary solutions.
 
-PVC aims to bridge these gaps. As a Python 3-based, fully-Free Software, scalable, and redundant private "cloud" that isn't afraid to say it's for small clusters, PVC is able to provide the simple, easy-to-use, small cluster you need today, with minimal administrator work, while being able to scale as your system grows, supporting hundreds or thousands of VMs across dozens of nodes. High availability is baked right into the core software at every layer, giving you piece of mind about your cluster, and ensuring that your systems keep running no matter what happens. And the interface couldn't be easier - a straightforward Click-based CLI and a Flask-based HTTP API provide access to the cluster for you to manage, either directly or though scripts or WebUIs. And since everything is Free Software, you can always inspect it, customize it to your use-case, add features, and contribute back to the community if you so choose.
+At the high end of the open-source ecosystem, are the "Stacks": OpenStack, CloudStack, and their numerous "vendorware" derivatives. These are large, unwieldy projects with dozens or hundreds of pieces of software to deploy in production, and can often require a large team just to understand and manage them. They're great if you're a large enterprise, building a public cloud, or have a team to get you going. But if you just want to run a small- to medium-sized virtual cluster for your SMB or ISP, they're definitely overkill and will cause you more headaches than they will solve long-term.
 
-PVC provides all the features you'd expect of a "cloud" system - easy management of VMs, including live migration between nodes for maximum uptime; virtual networking support using either vLANs or EVPN-based VXLAN; shared, redundant, object-based storage using Ceph, and a Python function library and convenient API interface for building your own interfaces. It is able to do this without being excessively complex, and without making sacrifices for legacy ideas.
+At the low end of the open source ecosystem, are what I call the "traditional tools". The biggest name in this space is ProxMox, though other, mostly defunct projects like Ganeti, tangential projects like Corosync/Pacemaker, and even traditional "I just use scripts" methods fit as well. These projects are great if you want to run a small server or homelab, but they quickly get unwieldy, though for the opposite reason from the Stacks: they're too simplistic, designed around single-host models, and when they provide redundancy at all it is often haphazard and nowhere near production-grade.
 
-If you need to run virtual machines, and don't have the time to learn the Stacks, the patience to deal with the old-style FOSS tools, or the money to spend on proprietary solutions, PVC might be just what you're looking for.
+Finally, the proprietary solutions like VMWare and Nutanix have entrenched themselves in the industry. They're excellent pieces of software providing just about anything you would need, but this comes at a significant cost, both in terms of money and also in software freedom and vendor lock-in. The licensing costs of Nutanix for instance can often make even enterprise-grade customers' accountants' heads spin.
+
+PVC seeks to bridge the gaps between these 3 categories. It is fully Free Software like the first two categories, and even more so - PVC is committed to never be "open-core" software and to never hide a single feature behind a paywall; it is able to scale from very small (1 or 3 node) clusters up to a dozen or more nodes, bridging the first two categories as effortlessly as the third does; it makes use of a hyperconverged architecture like ProxMox or Nuntanix to avoid wasting hardware resources on dedicated controller, hypervisor, and storage nodes; it is redundant at every layer from the ground-up, something that is not designed into any other free solution, and is able to tolerate the loss any single disk or entire node with barely a blip, all without administrator intervention; and finally, it is designed to be as simple to use as possible, with an Ansible-based node management framework, a RESTful API client interface, and a consistent, self-documenting CLI administration tool, allowing an administrator to create and manage their cluster quickly and simply, and then get on with more interesting things.
+
+In short, it is a Free Software, scalable, redundant, self-healing, and self-managing private cloud solution designed with administrator simplicity in mind.
+
+## Building Blocks
+
+PVC is build from a number of other, open source components. The main system itself is a series of software daemons (services) written in Python 3, with the CLI interface also written in Python 3.
+
+Virtual machines themselves are run with the Linux KVM subsystem via the Libvirt virtual machine management library. This provides the maximum flexibility and compatibility for running various guest operating systems in multiple modes (fully-virtualized, para-virtualized, virtio-enabled, etc.).
+
+To manage cluster state, PVC uses Zookeeper. This is an Apache project designed to provide a highly-available and always-consistent key-value database. The various daemons all connect to the distributed Zookeeper database to both obtain details about cluster state, and to manage that state. For instance the node daemon watches Zookeeper for information on what VMs to run, networks to create, etc., while the API writes information to Zookeeper in response to requests.
+
+Additional relational database functionality, specifically for the DNS aggregation subsystem and the VM provisioner, is provided by the PostgreSQL database and the Patroni management tool, which provides automatic clustering and failover for PostgreSQL database instances.
+
+Node network routing for managed networks providing EBGP VXLAN and route-learning is provided by FRRouting, a descendant project of Quaaga and GNU Zebra.
+
+The storage subsystem is provided by Ceph, a distributed object-based storage subsystem with extensive scalability, self-managing, and self-healing functionality. The Ceph RBD (Rados Block Device) subsystem is used to provide VM block devices similar to traditional LVM or ZFS zvols, but in a distributed, shared-storage manner.
+
+All the components are designed to be run on top of Debian GNU/Linux, specifically Debian 10.X "Buster", with the SystemD system service manager. This OS provides a stable base to run the various other subsystems while remaining truly Free Software, while SystemD provides functionality such as automatic daemon restarting and complex startup/shutdown ordering.
 
 ## Cluster Architecture
 
-A PVC cluster is based around "nodes", which are physical servers on which the various daemons, storage, networks, and virtual machines run. Each node is self-contained; it is able to perform any and all cluster functions if needed, and there is no segmentation of function between different types of physical hosts.
+A PVC cluster is based around "nodes", which are physical servers on which the various daemons, storage, networks, and virtual machines run. Each node is self-contained and is able to perform any and all cluster functions if needed; there is no segmentation of function between different types of physical hosts.
 
-A limited number of nodes, called "coordinators", are statically configured to provide additional services for the cluster. All databases for instance run on the coordinators, but not other nodes. This prevents any issues with scaling database clusters across dozens of hosts, while still retaining maximum redundancy. In a standard configuration, 3 or 5 nodes are designated as coordinators, and additional nodes connect to the coordinators for database access where required. For quorum purposes, there should always be an odd number of coordinators, and exceeding 5 is likely not required even for large clusters. PVC also supports a single node cluster format for extremely small clusters, homelabs, or testing where redundancy is not required.
+A limited number of nodes, called "coordinators", are statically configured to provide additional services for the cluster. For instance, all databases, FRRouting instances, and Ceph management daemons run only on the set of cluster coordinators. At cluster bootstrap, 1 (testing-only), 3 (small clusters), or 5 (large clusters) nodes may be chosen as the coordinators. Other nodes can then be added as "hypervisor" nodes, which then provide only block device (storage) and VM (compute) functionality by connecting to the set of coordinators. This limits the scaling problem of the databases while ensuring there is still maximum redundancy and resiliency for the core cluster services. Which nodes are designated as coordinators can be changed should the administrator so desire, simply by installing the required software on additional nodes, though this is not recommended (the Ceph system in particular is cumbersome to reconfigure).
 
-The primary database for PVC is Zookeeper, a highly-available key-value store designed with consistency in mind. Each node connects to the Zookeeper cluster running on the coordinators to send and receive data from the rest of the cluster. The API client (and Python function library) interface with this Zookeeper cluster directly to configure and obtain state about the various objects in the cluster. This database is the central authority for all nodes.
+During runtime, one coordinator is elected the "primary" for the cluster. This designation can shift dynamically in response to cluster events, or be manually migrated by an administrator. The coordinator takes on a number of roles for which only one host may be active at once, for instance to provide DHCP services to managed client networks or to interface with the API.
 
-Nodes are networked together via at least 3 different networks, set during bootstrap. The first is the "upstream" network, which provides upstream access for the nodes, for instance Internet connectivity, sending routes to client networks to upstream routers, etc. This should usually be a private/firewalled network to prevent unauthorized access to the cluster. The second is the "cluster" network, which is a private RFC1918 network that is unrouted and that nodes use to communicate between one another for Zookeeper access, Libvirt migrations, EVPN VXLAN tunnels, etc. The third is the "storage" network, which is used by the Ceph storage cluster for inter-OSD communication, allowing it to be separate from the main cluster network for maximum performance flexibility.
+Nodes are networked together via a set of statically-configured networks. At a minimum, 2 discrete networks are required, with an optional 3rd. The "upstream" network is the primary network for the nodes, and provides functions such as upstream Internet access, routing to and from the cluster nodes, and management via the API; it may be either a firewalled public or NAT'd RFC1918 network, but should never be exposed directly to the Internet. The "cluster" network is an unrouted RFC1918 network which provides inter-node communication for managed client network traffic (VXLANs), cross-node routing, VM migration and failover, and database replication and access. Finally, though optionally collapsed with the "cluster" network, the "storage" network is another unrouted RFC1918 network which provides a dedicated logical and/or physical link between the nodes for storage traffic, including VM block device storage traffic, inter-OSD replication traffic, and Ceph heartbeat traffic, thus allowing it to be completely isolated from the other networks for maximum performance. With each network is a single "floating" IP address which follows the primary coordinator, providing a single interface to the cluster. Once configured, the cluster is then able to create additional networks of two kinds, "bridged" traditional vLANs and "managed" routed VXLANs, to provide network access to VMs.
 
-Further information about the general cluster architecture can be found at the [cluster architecture page](/architecture/cluster).
+Further information about the general cluster architecture, including important considerations for node specifications/sizing and network configuration, can be found at the [cluster architecture page](/cluster-architecture).
 
-## Node Architecture
+## Clients
 
-Within each node, the PVC daemon is a single Python 3 program which handles all node functionality, including networking, starting cluster services, managing creation/removal of VMs, networks, and storage, and providing utilization statistics and information to the cluster.
+### API Client
 
-The daemon uses an object-oriented approach, with most cluster objects being represented by class objects of a specific type. Each node has a full view of all cluster objects and can interact with them based on events from the cluster as needed.
+The API client is a Flask-based RESTful API and is the core interface to PVC. By default the API will run on the primary coordinator, listening on TCP port 7370 on the "upstream" network floating IP address. All other clients communicate with this API to perform actions against the cluster. The API features basic authentication using UUID-based API keys to prevent unauthorized access, and can optionally be configured with full TLS encryption to provide integrity and confidentiality across public networks.
 
-Further information about the node daemon manual can be found at the [daemon manual page](/manuals/daemon).
+The API generally accepts all requests as HTTP form requests following standard RESTful guidelines, supporting arguments in the URI string or, with limited exceptions, in the message body. The API returns JSON response bodies to all requests consisting either of the information requested, or a `{ "message": "text" }` construct to pass informational status messages back to the client.
 
-## Client Architecture
+The API client manual can be found at the [API manual page](/manuals/api), and the full API documentation can be found at the [API reference page](/manuals/api-reference.html).
 
-### API client
+### Direct Bindings
 
-The API client is the core interface to PVC. It is a Flask RESTful API interface capable of performing all functions, and by default runs on the primary coordinator listening on port 7370 at the upstream floating IP address. Other clients, such as the CLI client, connect to the API to perform actions against the cluster. The API features a basic key-based authentication mechanism to prevent unauthorized access to the cluster if desired, and can also provide TLS-encrypted access for maximum security over public networks.
+The API client uses a dedicated set of Python libraries, packaged as the `pvc-daemon-common` Debian package, to communicate with the cluster. It is thus possible to build custom Python clients that directly interface with the PVC cluster, without having to get "into the weeds" of the Zookeeper or PostgreSQL databases.
 
-The API accepts all requests as HTTP form requests, supporting arguments both in the URI string as well as in the POST/PUT body. The API returns JSON response bodies to all requests.
+### CLI Client
 
-The API client manual can be found at the [API manual page](/manuals/api), and the [API documentation page](/manuals/api-reference.html).
+The CLI client is a Python Click application, which provides a convenient CLI interface to the API client. It supports connecting to multiple clusters from a single instance, with or without authentication and over both HTTP or HTTPS, including a special "local" cluster if the client determines that an API configuration exists on the local host. Information about the configured clusters is stored in a local JSON document, and a default cluster can be set with an environment variable.
 
-### Direct bindings
+The CLI client is self-documenting using the `-h`/`--help` arguments throughout, easing the administrator learning curve and providing easy access to command details. A short manual can also be found at the [CLI manual page](/manuals/cli).
 
-The API client uses a dedicated, independent set of functions to perform the actual communication with the cluster, which is packaged separately as the `pvc-client-common` package. These functions can be used directly by 3rd-party Python interfaces for PVC if desired.
+## Deployment
 
-### CLI client
-
-The CLI client interface is a Click application, which provides a convenient CLI interface to the API client. It supports connecting to multiple clusters, over both HTTP and HTTPS and with authentication, including a special "local" cluster if the client determines that an `/etc/pvc/pvcapid.yaml` configuration exists on the host.
-
-The CLI client is self-documenting using the `-h`/`--help` arguments, though a short manual can be found at the [CLI manual page](/manuals/cli).
-
-## Deployment architecture
-
-The overall management, deployment, bootstrapping, and configuring of nodes is accomplished via a set of Ansible roles, found in the [`pvc-ansible` repository](https://github.com/parallelvirtualcluster/pvc-ansible), and nodes are installed via a custom installer ISO generated by the [`pvc-installer` repository](https://github.com/parallelvirtualcluster/pvc-installer). Once the cluster is set up, nodes can be added, replaced, or updated using this Ansible framework.
+The overall management, deployment, bootstrapping, and configuring of nodes is accomplished via a set of Ansible roles and playbooks, found in the [`pvc-ansible` repository](https://github.com/parallelvirtualcluster/pvc-ansible), and nodes are installed via a custom installer ISO generated by the [`pvc-installer` repository](https://github.com/parallelvirtualcluster/pvc-installer). Once the cluster is set up, nodes can be added, replaced, updated, or reconfigured using this Ansible framework.
 
 The Ansible configuration and architecture manual can be found at the [Ansible manual page](/manuals/ansible).
 
-## About the author
+## Frequently Asked Questions
+
+### General Questions
+
+#### What is it?
+
+PVC is a virtual machine management suite designed around high-availability and ease-of-use. It can be considered an alternative to OpenStack, ProxMox, Nutanix, and other similar solutions that manage not just the VMs, but the surrounding infrastructure as well.
+
+#### Why would you make this?
+
+After becoming frustrated by numerous other management tools, I discovered that what I wanted didn't exist as FLOSS software, so I built it myself. Since then, I have also been able to leverage PVC both for my own purposes as well as for my employer, a win-win for the project.
+
+#### Is PVC right for me?
+
+PVC might be right for you if:
+
+1. You need KVM-based VMs.
+2. You want management of storage and networking (a.k.a. "batteries-included") in the same tool.
+3. You want hypervisor-level redundancy, able to tolerate hypervisor downtime seamlessly, for all elements of the stack.
+
+I built PVC for my homelab first, found a perfect use-case with my employer, and think it might be useful to you too.
+
+#### Is 3 hypervisors really the minimum?
+
+For a redundant cluster, yes. PVC requires a majority quorum for proper operation at various levels, and the smallest possible majority quorum is 2-of-3; thus 3 nodes is the safe minimum. That said, you can run PVC on a single node for testing/lab purposes without host-level redundancy, should you wish to do so, and it might also be possible to run 2 "main" systems with a 3rd "quorum observer" hosting only the management tools but no VMs, however this is not officially supported.
+
+### Feature Questions
+
+#### Does PVC support containers (Docker/Kubernetes/LXC/etc.)?
+
+No, not directly. PVC supports only KVM VMs. To run containers, you would need to run a VM which then runs your containers. For instance PVC makes an excellent underlying layer for a virtual Kubernetes cluster, instead of bare hardware.
+
+#### Does PVC have a WebUI?
+
+Not yet. Right now, PVC management is done exclusively with the CLI interface to the API. A WebUI can and likely will be built in the future, but I'm not a frontend developer and I do not consider this a personal priority. As of late 2020 the API is generally stable, so I would welcome 3rd party assistance here.
+
+### Storage Questions
+
+#### Can I use RAID-5/RAID-6 with PVC?
+
+The short answer is no. The long answer is: Ceph, the storage backend used by PVC, does support "erasure coded" pools which implement a RAID-5-like (striped with distributed parity) functionality, but PVC does not support this for several reasons, mostly related to ease of management and performance. If you use PVC, you must accept at the very least a 2x storage penalty, and for true multi-node safety and resiliency, a 3x storage penalty for VM storage. This is a trade-off of the architecture and should be taken into account when sizing storage in nodes.
+
+#### Can I use spinning HDDs with PVC?
+
+You can, but you won't like the results. SSDs, and specifically datacentre-grade SSDs for resiliency, are required to obtain any sort of reasonable performance when running multiple VMs. The higher-performance the drives, the faster the storage.
+
+#### What network speed does PVC require?
+
+For optimal performance, nodes should use at least 10-Gigabit Ethernet network interfaces wherever possible, and on large clusters a dedicated 10-Gigabit "storage" network, separate from the "upstream"/"cluster" networks, is strongly recommended. The storage system performance, especially for writes, is more heavily bottlenecked by the network speed than the actual storage device speed when speaking of high-performance disks. 1-Gigabit Ethernet will be sufficient for some use-cases and is sufficient for the non-storage networks (VM traffic notwithstanding), but storage performance will become severely limited as the cluster grows. Even slower network speeds (e.g. 100-Megabit) are not sufficient for PVC to operate properly except in very limited testing scenarios.
+
+#### What Ceph version does PVC use?
+
+PVC requires Ceph 14.x (Nautilus). The official PVC repository at https://repo.bonifacelabs.ca includes Ceph 14.2.x (updated regularly), since Debian Buster by default includes only 12.x (Luminous).
+
+## About The Author
+
+PVC is written by [Joshua](https://www.boniface.me) [M.](https://bonifacelabs.ca) [Boniface](https://github.com/joshuaboniface). A Linux system administrator by trade, Joshua is always looking for the best solutions to his user's problems, be they developers or end users. PVC grew out of his frustration with the various FOSS virtualization tools, as well as and specifically, the constant failures of Pacemaker/Corosync to gracefully manage a virtualization cluster. He started work on PVC at the end of May 2018 as a simple alternative to a Corosync/Pacemaker-managed virtualization cluster, and has been growing the feature set and stability of the system ever since.
 
-PVC is written by [Joshua](https://www.boniface.me) [M.](https://bonifacelabs.ca) [Boniface](https://github.com/joshuaboniface). A Linux system administrator by trade, Joshua is always looking for the best solutions to his user's problems, be they developers or end users. PVC grew out of his frustration with the various FOSS virtualization tools, as well as and specifically, the constant failures of Pacemaker/Corosync to gracefully manage a virtualization cluster. He started work on PVC at the end of May 2018 as a simple alternative to a Corosync/Pacemaker-managed virtualization cluster, and has been growing the feature set in starts and stops ever since.

docs/cluster-architecture.md

@@ -80,7 +80,7 @@ PVC Ceph pools make use of the replication mechanism of Ceph to store multiple c
 
 The default replication level for a new pool is `copies=3, mincopies=2`. This will store 3 copies of each object, with a host-level failure domain, and will allow I/O as long as 2 copies are available. Thus, in a cluster of any size, all data is fully available even if a single host becomes unavailable. It will however use 3x the space for each piece of data stored, which must be considered when sizing the disk space for the cluster: a pool in this configuration, running on 3 nodes each with a single 400GB disk, will effectively have 400GB of total space available for use. As mentioned above, new disks must also be added in groups across nodes equal to the total number of `copies` to ensure new space is usable.
 
-Non-default values can also be set at pool creation time. For instance, one could create a `copies=3, mincopies=1` pool, which would allow I/O with two hosts down but leaves the cluster susceptible to a write hole should a disk fail in this state. Alternatively, for more resilience, one could create a `copies=4, mincopies=2` pool, which will allow 2 hosts to fail without a write hole, but would consume 4x the space for each piece of data stored and require new disks to be added in groups of 4 instead. Practically any combination of values is possible, however these 3 are the most relevant for most use-cases, and for most, especially small, clusters, the default is sufficient to provide solid redundancy and guard against host failures until the administrator can respond.
+Non-default values can also be set at pool creation time. For instance, one could create a `copies=3, mincopies=1` pool, which would allow I/O with two hosts down but leaves the cluster susceptible to a write hole should a disk fail in this state. Alternatively, for more resilience, one could create a `copies=4, mincopies=3` pool, which will allow 2 hosts to fail without a write hole, but would consume 4x the space for each piece of data stored and require new disks to be added in groups of 4 instead. Practically any combination of values is possible, however these 3 are the most relevant for most use-cases, and for most, especially small, clusters, the default is sufficient to provide solid redundancy and guard against host failures until the administrator can respond.
 
 Replication levels cannot be changed within PVC once a pool is created, however they can be changed via manual Ceph commands on a coordinator should the administrator require this. In any case, the administrator should carefully consider sizing, failure domains, and performance when selecting storage devices to ensure the right level of resiliency versus data usage for their use-case and cluster size.
 
@@ -152,7 +152,7 @@ The floating IP address in the storage network can be used as a single point of
 
 Nodes in this network are generally assigned IPs automatically based on their node number (e.g. node1 at `.1`, node2 at `.2`, etc.). The network should be large enough to include all nodes sequentially.
 
-The administrator may choose to collocate the storage network on the same physical interface as the cluster network, or on a separate physical interface. This should be decided based on the size of the cluster and the perceived ratios of client network versus storage traffic. In large (>3 node) or storage-intensive clusters, this network should generally be a separate set of fast physical interfaces, separate from both the upstream and cluster networks, in order to maximize and isolate the storage bandwidth. If the administrator does choose to colocate these networks, they may also share the same IP address, thus eliminating any distinction between the Cluster and Storage networks. The PVC software handles this natively when the Cluster and Storage IPs of a node are identical.
+The administrator may choose to collocate the storage network on the same physical interface as the cluster network, or on a separate physical interface. This should be decided based on the size of the cluster and the perceived ratios of client network versus storage traffic. In large (>3 node) or storage-intensive clusters, this network should generally be a separate set of fast physical interfaces, separate from both the upstream and cluster networks, in order to maximize and isolate the storage bandwidth. If the administrator does choose to collocate these networks, they may also share the same IP address, thus eliminating any distinction between the Cluster and Storage networks. The PVC software handles this natively when the Cluster and Storage IPs of a node are identical.
 
 ### PVC client networks
 
@@ -162,7 +162,7 @@ The first type of client network is the unmanaged bridged network. These network
 
 With this client network type, PVC does no management of the network. This is left entirely to the administrator. It requires switch support and the configuration of the vLANs on the switchports of each node's physical interfaces before enabling the network.
 
-Generally, the same physical network interface will underly both the cluster networks as well as bridged client networks. PVC does however support specifying a separate physical device for bridged client networks, for instance to separate these networks onto a different physical interface from the main cluster networks.
+Generally, the same physical network interface will underlay both the cluster networks as well as bridged client networks. PVC does however support specifying a separate physical device for bridged client networks, for instance to separate these networks onto a different physical interface from the main cluster networks.
 
 #### VXLAN (managed) Client Networks
 

docs/faq.md

@@ -1,49 +0,0 @@
-# Frequently Asked Questions about Parallel Virtual Cluster
-
-## General Questions
-
-### What is it?
-
-PVC is a virtual machine management suite designed around high-availability. It can be considered an alternative to ProxMox, VMWare, Nutanix, and other similar solutions that manage not just the VMs, but the surrounding infrastructure as well.
-
-### Why would you make this?
-
-The full story can be found in the [about page](https://parallelvirtualcluster.readthedocs.io/en/latest/about), but after becoming frustrated by numerous other management tools, I discovered that what I wanted didn't exist as FLOSS software, so I built it myself.
-
-### Is PVC right for me?
-
-PVC might be right for you if your requirements are:
-
-1. You need KVM-based VMs.
-2. You want management of storage and networking (a.k.a. "batteries-included") in the same tool.
-3. You want hypervisor-level redundancy, able to tolerate hypervisor downtime seamlessly, for all elements of the stack.
-
-I built PVC for my homelab first, found a perfect usecase with my employer, and think it might be useful to you too.
-
-### Is 3 hypervisors really the minimum?
-
-For a redundant cluster, yes. PVC requires a majority quorum for several subsystems, and the smallest possible majority quorum is 2/3. That said, you can run PVC on a single node for testing/lab purposes without host-level reundancy, should you wish to do so.
-
-## Feature Questions
-
-### Does PVC support Docker/Kubernetes/LXC/etc.
-
-No. PVC supports only KVM VMs. To run Docker containers, etc., you would need to run a VM which then runs your containers.
-
-### Does PVC have a WebUI?
-
-Not yet. Right now, PVC management is done almost exclusively with an API and the included CLI interface to that API. A WebUI could and likely will be built in the future, but I'm not a frontend developer.
-
-## Storage Questions
-
-### Can I use RAID-5 with PVC?
-
-The short answer is no. The long answer is: Ceph, the storage backend used by PVC, does support "erasure coded" pools which implement a RAID-5-like functionality. PVC does not support this for several reasons. If you use PVC, you must accept at the very least a 2x storage penalty, and for true safety and resiliency a 3x storage penalty, for VM storage. This is a trade-off of the architecture.
-
-### Can I use spinning HDDs with PVC?
-
-You can, but you won't like the results. SSDs are effectively required to obtain any sort of reasonable performance when running multiple VMs. Ideally, datacentre-grade SSDs as well, due to their significantly increased write endurance.
-
-### What Ceph version does PVC use?
-
-PVC requires Ceph 14.x (Nautilus). The official PVC repository includes Ceph 14.2.8. Debian Buster by default includes only 12.x (Luminous).

docs/getting-started.md

@@ -55,19 +55,20 @@ This guide will walk you through setting up a simple 3-node PVC cluster from scr
 0. Perform the initial bootstrap. From the `pvc-ansible` repository directory, execute the following `ansible-playbook` command, replacing `<cluster_name>` with the Ansible group name from the `hosts` file. Make special note of the additional `bootstrap=yes` variable, which tells the playbook that this is an initial bootstrap run.  
     `$ ansible-playbook -v -i hosts pvc.yml -l <cluster_name> -e bootstrap=yes`
 
+    **WARNING:** Never rerun this playbook with the `-e bootstrap=yes` option against an active cluster. This will have unintended, disastrous consequences.
+
 0. Wait for the Ansible playbook run to finish. Once completed, the cluster bootstrap will be finished, and all 3 nodes will have rebooted into a working PVC cluster.
 
-0. Install the CLI client on your administrative host, and verify connectivity to the cluster, for instance by running the following command, which should show all 3 nodes as present and running:  
-    `$ pvc -z pvchv1:2181,pvchv2:2181,pvchv3:2181 node list`
+0. Install the CLI client on your administrative host, and add and verify connectivity to the cluster; this will also verify that the API is working. You will need to know the cluster upstream floating IP address here, and if you configured SSL or authentication for the API in your `group_vars`, adjust the first command as needed (see `pvc cluster add -h` for details).  
+    `$ pvc cluster add -a <upstream_floating_ip> mycluster`  
+    `$ pvc -c mycluster node list`
 
-0. Optionally, verify the API is listening on the `upstream_floating_ip` address configured in the cluster `group_vars`, for instance by running the following command which shows, in JSON format, the same information as in the previous step:  
-    `$ curl -X GET http://<upstream_floating_ip>:7370/api/v1`
+    We can also set a default cluster by exporting the `PVC_CLUSTER` environment variable to avoid requiring `-c cluster` with every subsequent command:  
+    `$ export PVC_CLUSTER="mycluster"`
 
 ### Part Four - Configuring the Ceph storage cluster
 
-All steps in this and following sections can be performed using either the CLI client or the HTTP API; for clarity, only the CLI commands are shown.
-
-0. Determine the Ceph OSD block devices on each host, via an `ssh` shell. For instance, check `/dev/disk/by-path` to show the block devices by their physical SAS/SATA bus location, and obtain the relevant `/dev/sdX` name for each disk you wish to be a Ceph OSD on each host.
+0. Determine the Ceph OSD block devices on each host, via an `ssh` shell. For instance, use `lsblk` or check `/dev/disk/by-path` to show the block devices by their physical SAS/SATA bus location, and obtain the relevant `/dev/sdX` name for each disk you wish to be a Ceph OSD on each host.
 
 0. Add each OSD device to each host. The general command is:  
     `$ pvc storage osd add --weight <weight> <node> <device>`
@@ -80,9 +81,11 @@ All steps in this and following sections can be performed using either the CLI c
     `$ pvc storage osd add --weight 1.0 pvchv3 /dev/sdb`  
     `$ pvc storage osd add --weight 1.0 pvchv3 /dev/sdc`   
 
-    **NOTE:** On the CLI, the `--weight` argument is optional, and defaults to `1.0`. In the API, it must be specified explicitly. OSD weights determine the relative amount of data which can fit onto each OSD. Under normal circumstances, you would want all OSDs to be of identical size, and hence all should have the same weight. If your OSDs are instead different sizes, the weight should be proportional to the size, e.g. `1.0` for a 100GB disk, `2.0` for a 200GB disk, etc. For more details, see the Ceph documentation.
+    **NOTE:** On the CLI, the `--weight` argument is optional, and defaults to `1.0`. In the API, it must be specified explicitly, but the CLI sets a default value. OSD weights determine the relative amount of data which can fit onto each OSD. Under normal circumstances, you would want all OSDs to be of identical size, and hence all should have the same weight. If your OSDs are instead different sizes, the weight should be proportional to the size, e.g. `1.0` for a 100GB disk, `2.0` for a 200GB disk, etc. For more details, see the Ceph documentation.
 
-    **NOTE:** OSD commands wait for the action to complete on the node, and can take some time (up to 30s normally). Be cautious of HTTP timeouts when using the API to perform these steps.
+    **NOTE:** OSD commands wait for the action to complete on the node, and can take some time.
+
+    **NOTE:** You can add OSDs in any order you wish, for instance you can add the first OSD to each node and then add the second to each node, or you can add all nodes' OSDs together at once like the example. This ordering does not affect the cluster in any way.
 
 0. Verify that the OSDs were added and are functional (`up` and `in`):  
     `$ pvc storage osd list`
@@ -93,19 +96,18 @@ All steps in this and following sections can be performed using either the CLI c
     For example, to create a pool named `vms` with 256 placement groups (a good default with 6 OSD disks), run the command as follows:  
     `$ pvc storage pool add vms 256`
 
-    **NOTE:** Ceph placement groups are a complex topic; as a general rule it's easier to grow than shrink, so start small and grow as your cluster grows. For more details see the Ceph documentation and the [placement group calculator](https://ceph.com/pgcalc/).
+    **NOTE:** Ceph placement groups are a complex topic; as a general rule it's easier to grow than shrink, so start small and grow as your cluster grows. The general formula is to calculate the ideal number of PGs is `pgs * maxcopies / osds = ~250`, then round `pgs` down to the closest power of 2; generally, you want as close to 250 PGs per OSD as possible, but no more than 250. With 3-6 OSDs, 256 is a good number, and with 9+ OSDs, 512 is a good number. Ceph will error if the total number exceeds the limit. For more details see the Ceph documentation and the [placement group calculator](https://ceph.com/pgcalc/).
 
-    **NOTE:** All PVC RBD pools use `copies=3` and `mincopies=2` for data storage. This provides, for each object, 3 copies of the data, with writes being accepted with 1 degraded copy. This provides maximum resiliency against single-node outages, but will use 3x the amount of storage for each unit stored inside the image. Take this into account when sizing OSD disks and VM images. This cannot be changed as any less storage will result in a non-HA cluster that could not handle a single node failure.
+    **NOTE:** As detailed in the [cluster architecture documentation](/cluster-architecture), you can also set a custom replica configuration for each pool if the default of 3 replica copies with 2 minimum copies is not acceptable. See `pvc storage pool add -h` or that document for full details.
 
 0. Verify that the pool was added:  
     `$ pvc storage pool list`
 
 ### Part Five - Creating virtual networks
 
-0. Determine a domain name, IPv4, and/or IPv6 network for your first client network, and any other client networks you may wish to create. For this guide we will create a single "managed" virtual client network with DHCP.
+0. Determine a domain name and IPv4, and/or IPv6 network for your first client network, and any other client networks you may wish to create. These networks should never overlap with the cluster networks. For full details on the client network types, see the [cluster architecture documentation](/cluster-architecture).
 
-0. Create the virtual network. The general command for an IPv4-only network with DHCP is:  
-    `$ pvc network add <vni_id> --type <type> --description <space-less_description> --domain <domain> --ipnet <ipv4_network_in_CIDR> --gateway <ipv4_gateway_address> --dhcp --dhcp-start <first_address> --dhcp-end <last_address>`
+0. Create the virtual network. There are many options here, so see `pvc network add -h` for details.  
 
     For example, to create the managed (EVPN VXLAN) network `100` with subnet `10.100.0.0/24`,  gateway `.1` and DHCP from `.100` to `.199`, run the command as follows:  
     `$ pvc network add 100 --type managed --description my-managed-network --domain myhosts.local --ipnet 10.100.0.0/24 --gateway 10.100.0.1 --dhcp --dhcp-start 10.100.0.100 --dhcp-end 10.100.0.199`
@@ -113,24 +115,27 @@ All steps in this and following sections can be performed using either the CLI c
     For another example, to create the static bridged (switch-configured, tagged VLAN, with no PVC management of IPs) network `200`, run the command as follows:  
     `$ pvc network add 200 --type bridged --description my-bridged-network`
 
+    **NOTE:** Network descriptions cannot contain spaces or special characters; keep them short, sweet, and dash or underscore delimited.
+
 0. Verify that the network(s) were added:  
     `$ pvc network list`
 
 0. On the upstream router, configure one of:
 
-    a) A BGP neighbour relationship with the `upstream_floating_address` to automatically learn routes.
+    a) A BGP neighbour relationship with the cluster upstream floating address to automatically learn routes.
 
-    b) Static routes for the configured client IP networks towards the `upstream_floating_address`.
+    b) Static routes for the configured client IP networks towards the cluster upstream floating address.
 
 0. On the upstream router, if required, configure NAT for the configured client IP networks.
 
 0. Verify the client networks are reachable by pinging the managed gateway from outside the cluster.
 
-0. Set all 3 nodes to `ready` state, allowing them to run virtual machines. The general command is:  
-    `$ pvc node ready <node>`
 
 ### You're Done!
 
+0. Set all 3 nodes to `ready` state, allowing them to run virtual machines. The general command is:  
+    `$ pvc node ready <node>`
+
 Congratulations, you now have a basic PVC storage cluster, ready to run your VMs.
 
 For next steps, see the [Provisioner manual](/manuals/provisioner) for details on how to use the PVC provisioner to create new Virtual Machines, as well as the [CLI manual](/manuals/cli) and [API manual](/manuals/api) for details on day-to-day usage of PVC.

docs/index.md

@@ -5,7 +5,6 @@
 <br/><br/>
 <a href="https://github.com/parallelvirtualcluster/pvc"><img alt="License" src="https://img.shields.io/github/license/parallelvirtualcluster/pvc"/></a>
 <a href="https://github.com/parallelvirtualcluster/pvc/releases"><img alt="Release" src="https://img.shields.io/github/release-pre/parallelvirtualcluster/pvc"/></a>
-<a href="https://git.bonifacelabs.ca/parallelvirtualcluster/pvc/pipelines"><img alt="Pipeline Status" src="https://git.bonifacelabs.ca/parallelvirtualcluster/pvc/badges/master/pipeline.svg"/></a>
 <a href="https://parallelvirtualcluster.readthedocs.io/en/latest/?badge=latest"><img alt="Documentation Status" src="https://readthedocs.org/projects/parallelvirtualcluster/badge/?version=latest"/></a>
 </p>
 
@@ -15,10 +14,25 @@ The major goal of PVC is to be administrator friendly, providing the power of En
 
 ## Getting Started
 
-To get started with PVC, read the [Cluster Architecture document](https://parallelvirtualcluster.readthedocs.io/en/latest/architecture/cluster/) and [Frequently Asked Questions](https://parallelvirtualcluster.readthedocs.io/en/latest/faq/), then see [Installing](https://parallelvirtualcluster.readthedocs.io/en/latest/installing) for details on setting up a set of PVC nodes, using the [PVC Ansible](https://parallelvirtualcluster.readthedocs.io/en/latest/manuals/ansible) framework to configure and bootstrap a cluster, and managing it with the [`pvc` CLI tool](https://parallelvirtualcluster.readthedocs.io/en/latest/manuals/cli) or [RESTful HTTP API](https://parallelvirtualcluster.readthedocs.io/en/latest/manuals/api). For details on the project, its motivation, and architectural details, see [the About page](https://parallelvirtualcluster.readthedocs.io/en/latest/about).
+To get started with PVC, please see the [About](https://parallelvirtualcluster.readthedocs.io/en/latest/about/) page for general information about the project, and the [Getting Started](https://parallelvirtualcluster.readthedocs.io/en/latest/getting-started/) page for details on configuring your cluster.
 
 ## Changelog
 
+#### v0.9.7
+
+  * Fixes bug with provisioner system template modifications
+
+#### v0.9.6
+
+  * Fixes bug with migrations
+
+#### v0.9.5
+
+  * Fixes bug with line count in log follow
+  * Fixes bug with disk stat output being None
+  * Adds short pretty health output
+  * Documentation updates
+
 #### v0.9.4
 
   * Fixes major bug in OVA parser

node-daemon/pvcnoded/Daemon.py

@@ -54,7 +54,7 @@ import pvcnoded.CephInstance as CephInstance
 import pvcnoded.MetadataAPIInstance as MetadataAPIInstance
 
 # Version string for startup output
-version = '0.9.4'
+version = '0.9.7'
 
 ###############################################################################
 # PVCD - node daemon startup program

node-daemon/pvcnoded/VMInstance.py

@@ -381,6 +381,7 @@ class VMInstance(object):
             })
             migrate_lock_node.release()
             migrate_lock_state.release()
+            self.inmigrate = False
             self.logger.out('Aborted migration: {}'.format(reason), state='i', prefix='Domain {}'.format(self.domuuid))
 
         # Acquire exclusive lock on the domain node key