Bump version to 0.9.103

Since storage_hosts now includes the storage domain as FQDNs, don't
re-append it within vmbuilder.

.bbuilder-tasks.yaml

@@ -4,4 +4,4 @@ bbuilder:
     published:
       - git submodule update --init
       - /bin/bash build-stable-deb.sh
-      - sudo /usr/local/bin/deploy-package -C pvc
+      - sudo /usr/local/bin/deploy-package -C pvc -D bookworm

.file-header

@@ -3,7 +3,7 @@
 # <Filename> - <Description>
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

.flake8

@@ -8,7 +8,7 @@
 ignore = W503, E501, F403, F405
 extend-ignore = E203
 # We exclude the Debian, migrations, and provisioner examples
-exclude = debian,api-daemon/migrations/versions,api-daemon/provisioner/examples,node-daemon/monitoring
+exclude = debian,monitoring,api-daemon/migrations/versions,api-daemon/provisioner/examples
 # Set the max line length to 88 for Black
 max-line-length = 88
 

.version

@@ -1 +1 @@
-0.9.86
+0.9.103

CHANGELOG.md

@@ -1,5 +1,149 @@
 ## PVC Changelog
 
+###### [v0.9.103](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.103)
+
+  * [Provisioner] Fixes a bug with the change in `storage_hosts` to FQDNs affecting the VM Builder
+  * [Monitoring] Fixes the Munin plugin to work properly with sudo
+
+###### [v0.9.102](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.102)
+
+  * [API Daemon] Ensures that received config snapshots update storage hosts in addition to secret UUIDs
+  * [CLI Client] Fixes several bugs around local connection handling and connection listings
+
+###### [v0.9.101](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.101)
+
+  **New Feature**: Adds VM snapshot sending (`vm snapshot send`), VM mirroring (`vm mirror create`), and (offline) mirror promotion (`vm mirror promote`). Permits transferring VM snapshots to remote clusters, individually or repeatedly, and promoting them to active status, for disaster recovery and migration between clusters.
+  **Breaking Change**: Migrates the API daemon into Gunicorn when in production mode. Permits more scalable and performant operation of the API. **Requires additional dependency packages on all coordinator nodes** (`gunicorn`, `python3-gunicorn`, `python3-setuptools`); upgrade via `pvc-ansible` is strongly recommended.
+  **Enhancement**: Provides whole cluster utilization stats in the cluster status data. Permits better observability into the overall resource utilization of the cluster.
+  **Enhancement**: Adds a new storage benchmark format (v2) which includes additional resource utilization statistics. This allows for better evaluation of storage performance impact on the cluster as a whole. The updated format also permits arbitrary benchmark job names for easier parsing and tracking.
+
+  * [API Daemon] Allows scanning of new volumes added manually via other commands
+  * [API Daemon/CLI Client] Adds whole cluster utilization statistics to cluster status
+  * [API Daemon] Moves production API execution into Gunicorn
+  * [API Daemon] Adds a new storage benchmark format (v2) with additional resource tracking
+  * [API Daemon] Adds support for named storage benchmark jobs
+  * [API Daemon] Fixes a bug in OSD creation which would create `split` OSDs if `--osd-count` was set to 1
+  * [API Daemon] Adds support for the `mirror` VM state used by snapshot mirrors
+  * [CLI Client] Fixes several output display bugs in various commands and in Worker task outputs
+  * [CLI Client] Improves and shrinks the status progress bar output to support longer messages
+  * [API Daemon] Adds support for sending snapshots to remote clusters
+  * [API Daemon] Adds support for updating and promoting snapshot mirrors to remote clusters
+  * [Node Daemon] Improves timeouts during primary/secondary coordinator transitions to avoid deadlocks
+  * [Node Daemon] Improves timeouts during keepalive updates to avoid deadlocks
+  * [Node Daemon] Refactors fencing thread structure to ensure a single fencing task per cluster and sequential node fences to avoid potential anomalies (e.g. fencing 2 nodes simultaneously)
+  * [Node Daemon] Fixes a bug in fencing if VM locks were already freed, leaving VMs in an invalid state
+  * [Node Daemon] Increases the wait time during system startup to ensure Zookeeper has more time to synchronize
+
+###### [v0.9.100](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.100)
+
+  * [API Daemon] Improves the handling of "detect:" disk strings on newer systems by leveraging the "nvme" command
+  * [Client CLI] Update help text about "detect:" disk strings
+  * [Meta] Updates deprecation warnings and updates builder to only add this version for Debian 12 (Bookworm)
+
+###### [v0.9.99](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.99)
+
+  **Deprecation Warning**: `pvc vm backup` commands are now deprecated and will be removed in a future version. Use `pvc vm snapshot` commands instead.
+  **Breaking Change**: The on-disk format of VM snapshot exports differs from backup exports, and the PVC autobackup system now leverages these. It is recommended to start fresh with a new tree of backups for `pvc autobackup` for maximum compatibility.
+  **Breaking Change**: VM autobackups now run in `pvcworkerd` instead of the CLI client directly, allowing them to be triggerd from any node (or externally). It is important to apply the timer unit changes from the `pvc-ansible` role after upgrading to 0.9.99 to avoid duplicate runs.
+  **Usage Note**: VM snapshots are displayed in the `pvc vm list` and `pvc vm info` outputs, not in a unique "list" endpoint.
+
+  * [API Daemon] Adds a proper error when an invalid provisioner profile is specified
+  * [Node Daemon] Sorts Ceph pools properly in node keepalive to avoid incorrect ordering
+  * [Health Daemon] Improves handling of IPMI checks by adding multiple tries but a shorter timeout
+  * [API Daemon] Improves handling of XML parsing errors in VM configurations
+  * [ALL] Adds support for whole VM snapshots, including configuration XML details, and direct rollback to snapshots
+  * [ALL] Adds support for exporting and importing whole VM snapshots
+  * [Client CLI] Removes vCPU topology from short VM info output
+  * [Client CLI] Improves output format of VM info output
+  * [API Daemon] Adds an endpoint to get the current primary node
+  * [Client CLI] Fixes a bug where API requests were made 3 times
+  * [Other] Improves the build-and-deploy.sh script
+  * [API Daemon] Improves the "vm rename" command to avoid redefining VM, preserving history etc.
+  * [API Daemon] Adds an indication when a task is run on the primary node
+  * [API Daemon] Fixes a bug where the ZK schema relative path didn't work sometimes
+
+###### [v0.9.98](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.98)
+
+  * [CLI Client] Fixed output when API call times out
+  * [Node Daemon] Improves the handling of fence states
+  * [API Daemon/CLI Client] Adds support for storage snapshot rollback
+  * [CLI Client] Adds additional warning messages about snapshot consistency to help output
+  * [API Daemon] Fixes a bug listing snapshots by pool/volume
+  * [Node Daemon] Adds a --version flag for information gathering by update-motd.sh
+
+###### [v0.9.97](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.97)
+
+  * [Client CLI] Ensures --lines is always an integer value
+  * [Node Daemon] Fixes a bug if d_network changes during iteration
+  * [Node Daemon] Moves to using allocated instead of free memory for node reporting
+  * [API Daemon] Fixes a bug if lingering RBD snapshots exist when removing a volume (#180)
+
+###### [v0.9.96](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.96)
+
+  * [API Daemon] Fixes a bug when reporting node stats
+  * [API Daemon] Fixes a bug deleteing successful benchmark results
+
+###### [v0.9.95](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.95)
+
+  * [API Daemon/CLI Client] Adds a flag to allow duplicate VNIs in network templates
+  * [API Daemon] Ensures that storage template disks are returned in disk ID order
+  * [Client CLI] Fixes a display bug showing all OSDs as split
+
+###### [v0.9.94](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.94)
+
+  * [CLI Client] Fixes an incorrect ordering issue with autobackup summary emails
+  * [API Daemon/CLI Client] Adds an additional safety check for 80% cluster fullness when doing volume adds or resizes
+  * [API Daemon/CLI Client] Adds safety checks to volume clones as well
+  * [API Daemon] Fixes a few remaining memory bugs for stopped/disabled VMs
+
+###### [v0.9.93](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.93)
+
+  * [API Daemon] Fixes a bug where stuck zkhandler threads were not cleaned up on error
+
+###### [v0.9.92](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.92)
+
+  * [CLI Client] Adds the new restore state to the colours list for VM status
+  * [API Daemon] Fixes an incorrect variable assignment
+  * [Provisioner] Improves the error handling of various steps in the debootstrap and rinse example scripts
+  * [CLI Client] Fixes two bugs around missing keys that were added recently (uses get() instead direct dictionary refs)
+  * [CLI Client] Improves API error handling via GET retries (x3) and better server status code handling
+
+###### [v0.9.91](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.91)
+
+  * [Client CLI] Fixes a bug and improves output during cluster task events.
+  * [Client CLI] Improves the output of the task list display.
+  * [Provisioner] Fixes some missing cloud-init modules in the default debootstrap script.
+  * [Client CLI] Fixes a bug with a missing argument to the vm_define helper function.
+  * [All] Fixes inconsistent package find + rm commands to avoid errors in dpkg.
+
+###### [v0.9.90](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.90)
+
+  * [Client CLI/API Daemon] Adds additional backup metainfo and an emailed report option to autobackups.
+  * [All] Adds a live migration maximum downtime selector to help with busy VM migrations.
+  * [API Daemon] Fixes a database migration bug on Debian 10/11.
+  * [Node Daemon] Fixes a race condition when applying Zookeeper schema changes.
+
+###### [v0.9.89](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.89)
+
+  * [API/Worker Daemons] Fixes a bug with the Celery result backends not being properly initialized on Debian 10/11.
+  * [API Daemon] Fixes a bug if VM CPU stats are missing on Debian 10.
+
+###### [v0.9.88](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.88)
+
+  * [API Daemon] Adds an additional Prometheus metrics proxy for Zookeeper stats.
+  * [API Daemon] Adds a new configuration to enable or disable metric endpoints if desired, defaulting to enabled.
+  * [API Daemon] Alters and adjusts the metrics output for VMs to complement new dashboard.
+  * [CLI Client] Adds a "json-prometheus" output format to "pvc connection list" to auto-generate file SD configs.
+  * [Monitoring] Adds a new VM dashboard, updates the Cluster dashboard, and adds a README.
+
+###### [v0.9.87](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.87)
+
+  * [API Daemon] Adds cluster Prometheus resource utilization metrics and an updated Grafana dashboard.
+  * [Node Daemon] Adds network traffic rate calculation subsystem.
+  * [All Daemons] Fixes a printing bug where newlines were not added atomically.
+  * [CLI Client] Fixes a bug listing connections if no default is specified.
+  * [All Daemons] Simplifies debug logging conditionals by moving into the Logger instance itself.
+
 ###### [v0.9.86](https://github.com/parallelvirtualcluster/pvc/releases/tag/v0.9.86)
 
   * [API Daemon] Significantly improves the performance of several commands via async Zookeeper calls and removal of superfluous backend calls.

README.md

@@ -1,10 +1,11 @@
 <p align="center">
-<img alt="Logo banner" src="images/pvc_logo_black.png"/>
+<img alt="Logo banner" src="https://docs.parallelvirtualcluster.org/en/latest/images/pvc_logo_black.png"/>
 <br/><br/>
+<a href="https://www.parallelvirtualcluster.org"><img alt="Website" src="https://img.shields.io/badge/visit-website-blue"/></a>
+<a href="https://github.com/parallelvirtualcluster/pvc/releases"><img alt="Latest Release" src="https://img.shields.io/github/release-pre/parallelvirtualcluster/pvc"/></a>
+<a href="https://docs.parallelvirtualcluster.org/en/latest/?badge=latest"><img alt="Documentation Status" src="https://readthedocs.org/projects/parallelvirtualcluster/badge/?version=latest"/></a>
 <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/psf/black"><img alt="Code style: Black" src="https://img.shields.io/badge/code%20style-black-000000.svg"/></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://docs.parallelvirtualcluster.org/en/latest/?badge=latest"><img alt="Documentation Status" src="https://readthedocs.org/projects/parallelvirtualcluster/badge/?version=latest"/></a>
 </p>
 
 ## What is PVC?
@@ -19,66 +20,68 @@ As a consequence of its features, PVC makes administrating very high-uptime VMs
 
 PVC also features an optional, fully customizable VM provisioning framework, designed to automate and simplify VM deployments using custom provisioning profiles, scripts, and CloudInit userdata API support.
 
-Installation of PVC is accomplished by two main components: a [Node installer ISO](https://github.com/parallelvirtualcluster/pvc-installer) which creates on-demand installer ISOs, and an [Ansible role framework](https://github.com/parallelvirtualcluster/pvc-ansible) to configure, bootstrap, and administrate the nodes. Installation can also be fully automated with a companion [cluster bootstrapping system](https://github.com/parallelvirtualcluster/pvc-bootstrap). Once up, the cluster is managed via an HTTP REST API, accessible via a Python Click CLI client or WebUI.
+Installation of PVC is accomplished by two main components: a [Node installer ISO](https://github.com/parallelvirtualcluster/pvc-installer) which creates on-demand installer ISOs, and an [Ansible role framework](https://github.com/parallelvirtualcluster/pvc-ansible) to configure, bootstrap, and administrate the nodes. Installation can also be fully automated with a companion [cluster bootstrapping system](https://github.com/parallelvirtualcluster/pvc-bootstrap). Once up, the cluster is managed via an HTTP REST API, accessible via a Python Click CLI client ~~or WebUI~~ (eventually).
 
 Just give it physical servers, and it will run your VMs without you having to think about it, all in just an hour or two of setup time.
 
+More information about PVC, its motivations, the hardware requirements, and setting up and managing a cluster [can be found over at our docs page](https://docs.parallelvirtualcluster.org).
+
 ## Getting Started
 
 To get started with PVC, please see the [About](https://docs.parallelvirtualcluster.org/en/latest/about-pvc/) page for general information about the project, and the [Getting Started](https://docs.parallelvirtualcluster.org/en/latest/deployment/getting-started/) page for details on configuring your first cluster.
 
 ## Changelog
 
-View the changelog in [CHANGELOG.md](CHANGELOG.md). **Please note that any breaking changes are announced here; ensure you read the changelog before upgrading!**
+View the changelog in [CHANGELOG.md](https://github.com/parallelvirtualcluster/pvc/blob/master/CHANGELOG.md). **Please note that any breaking changes are announced here; ensure you read the changelog before upgrading!**
 
 ## Screenshots
 
 These screenshots show some of the available functionality of the PVC system and CLI as of PVC v0.9.85.
 
-<p><img alt="0. Integrated help" src="images/0-integrated-help.png"/><br/>
+<p><img alt="0. Integrated help" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/0-integrated-help.png"/><br/>
 <i>The CLI features an integrated, fully-featured help system to show details about every possible command.</i>
 </p>
 
-<p><img alt="1. Connection management" src="images/1-connection-management.png"/><br/>
+<p><img alt="1. Connection management" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/1-connection-management.png"/><br/>
 <i>A single CLI instance can manage multiple clusters, including a quick detail view, and will default to a "local" connection if an "/etc/pvc/pvc.conf" file is found; sensitive API keys are hidden by default.</i>
 </p>
 
-<p><img alt="2. Cluster details and output formats" src="images/2-cluster-details-and-output-formats.png"/><br/>
+<p><img alt="2. Cluster details and output formats" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/2-cluster-details-and-output-formats.png"/><br/>
 <i>PVC can show the key details of your cluster at a glance, including health, persistent fault events, and key resources; the CLI can output both in pretty human format and JSON for easier machine parsing in scripts.</i>
 </p>
 
-<p><img alt="3. Node information" src="images/3-node-information.png"/><br/>
+<p><img alt="3. Node information" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/3-node-information.png"/><br/>
 <i>PVC can show details about the nodes in the cluster, including their live health and resource utilization.</i>
 </p>
 
-<p><img alt="4. VM information" src="images/4-vm-information.png"/><br/>
+<p><img alt="4. VM information" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/4-vm-information.png"/><br/>
 <i>PVC can show details about the VMs in the cluster, including their state, resource allocations, current hosting node, and metadata.</i>
 </p>
 
-<p><img alt="5. VM details" src="images/5-vm-details.png"/><br/>
+<p><img alt="5. VM details" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/5-vm-details.png"/><br/>
 <i>In addition to the above basic details, PVC can also show extensive information about a running VM's devices and other resource utilization.</i>
 </p>
 
-<p><img alt="6. Network information" src="images/6-network-information.png"/><br/>
+<p><img alt="6. Network information" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/6-network-information.png"/><br/>
 <i>PVC has two major client network types, and ensures a consistent configuration of client networks across the entire cluster; managed networks can feature DHCP, DNS, firewall, and other functionality including DHCP reservations.</i>
 </p>
 
-<p><img alt="7. Storage information" src="images/7-storage-information.png"/><br/>
+<p><img alt="7. Storage information" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/7-storage-information.png"/><br/>
 <i>PVC provides a convenient abstracted view of the underlying Ceph system and can manage all core aspects of it.</i>
 </p>
 
-<p><img alt="8. VM and node logs" src="images/8-vm-and-node-logs.png"/><br/>
+<p><img alt="8. VM and node logs" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/8-vm-and-node-logs.png"/><br/>
 <i>PVC can display logs from VM serial consoles (if properly configured) and nodes in-client to facilitate quick troubleshooting.</i>
 </p>
 
-<p><img alt="9. VM and worker tasks" src="images/9-vm-and-worker-tasks.png"/><br/>
+<p><img alt="9. VM and worker tasks" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/9-vm-and-worker-tasks.png"/><br/>
 <i>PVC provides full VM lifecycle management, as well as long-running worker-based commands (in this example, clearing a VM's storage locks).</i>
 </p>
 
-<p><img alt="10. Provisioner" src="images/10-provisioner.png"/><br/>
+<p><img alt="10. Provisioner" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/10-provisioner.png"/><br/>
 <i>PVC features an extensively customizable and configurable VM provisioner system, including EC2-compatible CloudInit support, allowing you to define flexible VM profiles and provision new VMs with a single command.</i>
 </p>
 
-<p><img alt="11. Prometheus and Grafana dashboard" src="images/11-prometheus-grafana.png"/><br/>
+<p><img alt="11. Prometheus and Grafana dashboard" src="https://raw.githubusercontent.com/parallelvirtualcluster/pvc/refs/heads/master/images/11-prometheus-grafana.png"/><br/>
 <i>PVC features several monitoring integration examples under "node-daemon/monitoring", including CheckMK, Munin, and, most recently, Prometheus, including an example Grafana dashboard for cluster monitoring and alerting.</i>
 </p>

api-daemon/migrations/versions/977e7b4d3497_pvc_version_0_9_89.py

@@ -0,0 +1,28 @@
+"""PVC version 0.9.89
+
+Revision ID: 977e7b4d3497
+Revises: 88fa0d88a9f8
+Create Date: 2024-01-10 16:09:44.659027
+
+"""
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision = '977e7b4d3497'
+down_revision = '88fa0d88a9f8'
+branch_labels = None
+depends_on = None
+
+
+def upgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('system_template', sa.Column('migration_max_downtime', sa.Integer(), default="300", server_default="300", nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade():
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('system_template', 'migration_max_downtime')
+    # ### end Alembic commands ###

api-daemon/provisioner/examples/script/1-noop.py

@@ -3,7 +3,7 @@
 # 1-noop.py - PVC Provisioner example script for noop install
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

api-daemon/provisioner/examples/script/2-ova.py

@@ -3,7 +3,7 @@
 # 2-ova.py - PVC Provisioner example script for OVA profile install
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

api-daemon/provisioner/examples/script/3-debootstrap.py

@@ -3,7 +3,7 @@
 # 3-debootstrap.py - PVC Provisioner example script for debootstrap install
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -150,6 +150,10 @@
 from daemon_lib.vmbuilder import VMBuilder
 
 
+# These are some global variables used below
+default_root_password = "test123"
+
+
 # The VMBuilderScript class must be named as such, and extend VMBuilder.
 class VMBuilderScript(VMBuilder):
     def setup(self):
@@ -498,11 +502,15 @@ class VMBuilderScript(VMBuilder):
         ret = os.system(
             f"debootstrap --include={','.join(deb_packages)} {deb_release} {temp_dir} {deb_mirror}"
         )
+        ret = int(ret >> 8)
         if ret > 0:
-            self.fail("Failed to run debootstrap")
+            self.fail(f"Debootstrap failed with exit code {ret}")
 
         # Bind mount the devfs so we can grub-install later
-        os.system("mount --bind /dev {}/dev".format(temp_dir))
+        ret = os.system("mount --bind /dev {}/dev".format(temp_dir))
+        ret = int(ret >> 8)
+        if ret > 0:
+            self.fail(f"/dev bind mount failed with exit code {ret}")
 
         # Create an fstab entry for each volume
         fstab_file = "{}/etc/fstab".format(temp_dir)
@@ -589,11 +597,13 @@ After=multi-user.target
                  - migrator
                  - bootcmd
                  - write-files
+                 - growpart
                  - resizefs
                  - set_hostname
                  - update_hostname
                  - update_etc_hosts
                  - ca-certs
+                 - users-groups
                  - ssh
                 
                 cloud_config_modules:
@@ -686,23 +696,36 @@ GRUB_DISABLE_LINUX_UUID=false
         # Do some tasks inside the chroot using the provided context manager
         with chroot(temp_dir):
             # Install and update GRUB
-            os.system(
+            ret = os.system(
                 "grub-install --force /dev/rbd/{}/{}_{}".format(
                     root_volume["pool"], vm_name, root_volume["disk_id"]
                 )
             )
-            os.system("update-grub")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"GRUB install failed with exit code {ret}")
+
+            ret = os.system("update-grub")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"GRUB update failed with exit code {ret}")
 
             # Set a really dumb root password so the VM can be debugged
             # EITHER CHANGE THIS YOURSELF, here or in Userdata, or run something after install
             # to change the root password: don't leave it like this on an Internet-facing machine!
-            os.system("echo root:test123 | chpasswd")
+            ret = os.system(f"echo root:{default_root_password} | chpasswd")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Root password change failed with exit code {ret}")
 
             # Enable cloud-init target on (first) boot
             # Your user-data should handle this and disable it once done, or things get messy.
             # That cloud-init won't run without this hack seems like a bug... but even the official
             # Debian cloud images are affected, so who knows.
-            os.system("systemctl enable cloud-init.target")
+            ret = os.system("systemctl enable cloud-init.target")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Enable of cloud-init failed with exit code {ret}")
 
     def cleanup(self):
         """
@@ -727,7 +750,7 @@ GRUB_DISABLE_LINUX_UUID=false
         temp_dir = "/tmp/target"
 
         # Unmount the bound devfs
-        os.system("umount {}/dev".format(temp_dir))
+        os.system("umount -f {}/dev".format(temp_dir))
 
         # Use this construct for reversing the list, as the normal reverse() messes with the list
         for volume in list(reversed(self.vm_data["volumes"])):
@@ -744,7 +767,7 @@ GRUB_DISABLE_LINUX_UUID=false
             ):
                 # Unmount filesystem
                 retcode, stdout, stderr = pvc_common.run_os_command(
-                    f"umount {mount_path}"
+                    f"umount -f {mount_path}"
                 )
                 if retcode:
                     self.log_err(

api-daemon/provisioner/examples/script/4-rinse.py

@@ -3,7 +3,7 @@
 # 4-rinse.py - PVC Provisioner example script for rinse install
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -150,6 +150,11 @@
 from daemon_lib.vmbuilder import VMBuilder
 
 
+# These are some global variables used below
+default_root_password = "test123"
+default_local_time = "UTC"
+
+
 # The VMBuilderScript class must be named as such, and extend VMBuilder.
 class VMBuilderScript(VMBuilder):
     def setup(self):
@@ -524,13 +529,23 @@ class VMBuilderScript(VMBuilder):
         ret = os.system(
             f"rinse --arch {rinse_architecture} --directory {temporary_directory} --distribution {rinse_release} --cache-dir {rinse_cache} --add-pkg-list /tmp/addpkg --verbose {mirror_arg}"
         )
+        ret = int(ret >> 8)
         if ret > 0:
-            self.fail("Failed to run rinse")
+            self.fail(f"Rinse failed with exit code {ret}")
 
         # Bind mount the devfs, sysfs, and procfs so we can grub-install later
-        os.system("mount --bind /dev {}/dev".format(temporary_directory))
-        os.system("mount --bind /sys {}/sys".format(temporary_directory))
-        os.system("mount --bind /proc {}/proc".format(temporary_directory))
+        ret = os.system("mount --bind /dev {}/dev".format(temporary_directory))
+        ret = int(ret >> 8)
+        if ret > 0:
+            self.fail(f"/dev bind mount failed with exit code {ret}")
+        ret = os.system("mount --bind /sys {}/sys".format(temporary_directory))
+        ret = int(ret >> 8)
+        if ret > 0:
+            self.fail(f"/sys bind mount failed with exit code {ret}")
+        ret = os.system("mount --bind /proc {}/proc".format(temporary_directory))
+        ret = int(ret >> 8)
+        if ret > 0:
+            self.fail(f"/proc bind mount failed with exit code {ret}")
 
         # Create an fstab entry for each volume
         fstab_file = "{}/etc/fstab".format(temporary_directory)
@@ -642,41 +657,76 @@ GRUB_SERIAL_COMMAND="serial --speed=115200 --unit=0 --word=8 --parity=no --stop=
         # Do some tasks inside the chroot using the provided context manager
         with chroot(temporary_directory):
             # Fix the broken kernel from rinse by setting a systemd machine ID and running the post scripts
-            os.system("systemd-machine-id-setup")
-            os.system(
+            ret = os.system("systemd-machine-id-setup")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Machine ID setup failed with exit code {ret}")
+
+            ret = os.system(
                 "rpm -q --scripts kernel-core | grep -A20  'posttrans scriptlet' | tail -n+2 | bash -x"
             )
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"RPM kernel reinstall failed with exit code {ret}")
 
             # Install any post packages
-            os.system(f"dnf install -y {' '.join(post_packages)}")
+            if len(post_packages) > 0:
+                ret = os.system(f"dnf install -y {' '.join(post_packages)}")
+                ret = int(ret >> 8)
+                if ret > 0:
+                    self.fail(f"DNF install failed with exit code {ret}")
 
             # Install and update GRUB config
-            os.system(
+            ret = os.system(
                 "grub2-install --force /dev/rbd/{}/{}_{}".format(
                     root_volume["pool"], vm_name, root_volume["disk_id"]
                 )
             )
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"GRUB install failed with exit code {ret}")
+
             os.system("grub2-mkconfig -o /boot/grub2/grub.cfg")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"GRUB update failed with exit code {ret}")
 
             # Set a really dumb root password so the VM can be debugged
             # EITHER CHANGE THIS YOURSELF, here or in Userdata, or run something after install
             # to change the root password: don't leave it like this on an Internet-facing machine!
-            os.system("echo root:test123 | chpasswd")
+            ret = os.system(f"echo root:{default_root_password} | chpasswd")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Root password change failed with exit code {ret}")
 
             # Enable dbus-broker
-            os.system("systemctl enable dbus-broker.service")
+            ret = os.system("systemctl enable dbus-broker.service")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Enable of dbus-broker failed with exit code {ret}")
 
             # Enable NetworkManager
             os.system("systemctl enable NetworkManager.service")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Enable of NetworkManager failed with exit code {ret}")
 
             # Enable cloud-init target on (first) boot
             # Your user-data should handle this and disable it once done, or things get messy.
             # That cloud-init won't run without this hack seems like a bug... but even the official
             # Debian cloud images are affected, so who knows.
             os.system("systemctl enable cloud-init.target")
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Enable of cloud-init failed with exit code {ret}")
 
             # Set the timezone to UTC
-            os.system("ln -sf ../usr/share/zoneinfo/UTC /etc/localtime")
+            ret = os.system(
+                f"ln -sf ../usr/share/zoneinfo/{default_local_time} /etc/localtime"
+            )
+            ret = int(ret >> 8)
+            if ret > 0:
+                self.fail(f"Localtime update failed with exit code {ret}")
 
     def cleanup(self):
         """

api-daemon/provisioner/examples/script/5-pfsense.py

@@ -3,7 +3,7 @@
 # 6-pfsense.py - PVC Provisioner example script for pfSense install
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

api-daemon/pvc-api-db-upgrade

@@ -12,15 +12,7 @@ fi
 
 pushd /usr/share/pvc
 
-case "$( cat /etc/debian_version )" in
-    10.*|11.*)
-        # Debian 10 & 11
-        ./pvcapid-manage_legacy.py db upgrade
-    ;;
-    *)
-        # Debian 12+
-        flask --app ./pvcapid-manage_flask.py db upgrade
-    ;;
-esac
+export FLASK_APP=./pvcapid-manage-flask.py
+flask db upgrade
 
 popd

api-daemon/pvcapid-manage-flask.py

@@ -3,7 +3,7 @@
 # pvcapid-manage_flask.py - PVC Database management tasks (via Flask CLI)
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

api-daemon/pvcapid-manage-zk.py

@@ -3,7 +3,7 @@
 # pvcapid-manage-zk.py - PVC Zookeeper migration generator
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -21,4 +21,5 @@
 
 from daemon_lib.zkhandler import ZKSchema
 
-ZKSchema.write()
+schema = ZKSchema(root_path=".")
+schema.write()

api-daemon/pvcapid-manage_legacy.py

@@ -1,33 +0,0 @@
-#!/usr/bin/env python3
-
-# pvcapid-manage_legacy.py - PVC Database management tasks (Legacy)
-# Part of the Parallel Virtual Cluster (PVC) system
-#
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
-#
-#    This program is free software: you can redistribute it and/or modify
-#    it under the terms of the GNU General Public License as published by
-#    the Free Software Foundation, version 3.
-#
-#    This program is distributed in the hope that it will be useful,
-#    but WITHOUT ANY WARRANTY; without even the implied warranty of
-#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-#    GNU General Public License for more details.
-#
-#    You should have received a copy of the GNU General Public License
-#    along with this program.  If not, see <https://www.gnu.org/licenses/>.
-#
-###############################################################################
-
-from flask_migrate import Migrate, MigrateCommand, Manager
-
-from pvcapid.flaskapi import app, db
-from pvcapid.models import *  # noqa F401,F403
-
-migrate = Migrate(app, db)
-manager = Manager(app)
-
-manager.add_command("db", MigrateCommand)
-
-if __name__ == "__main__":
-    manager.run()

api-daemon/pvcapid.py

@@ -3,7 +3,7 @@
 # pvcapid.py - API daemon startup stub
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -19,6 +19,13 @@
 #
 ###############################################################################
 
-import pvcapid.Daemon  # noqa: F401
+import sys
+from os import path
+
+# Ensure current directory (/usr/share/pvc) is in the system path for Gunicorn
+current_dir = path.dirname(path.abspath(__file__))
+sys.path.append(current_dir)
+
+import pvcapid.Daemon  # noqa: F401, E402
 
 pvcapid.Daemon.entrypoint()

api-daemon/pvcapid/Daemon.py

@@ -3,7 +3,7 @@
 # Daemon.py - PVC HTTP API daemon
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -19,15 +19,13 @@
 #
 ###############################################################################
 
-
+import subprocess
 from ssl import SSLContext, TLSVersion
-
 from distutils.util import strtobool as dustrtobool
-
 import daemon_lib.config as cfg
 
 # Daemon version
-version = "0.9.86"
+version = "0.9.100~git-73c0834f"
 
 # API version
 API_VERSION = 1.0
@@ -53,7 +51,6 @@ def strtobool(stringv):
 # Configuration Parsing
 ##########################################################
 
-
 # Get our configuration
 config = cfg.get_configuration()
 config["daemon_name"] = "pvcapid"
@@ -61,22 +58,16 @@ config["daemon_version"] = version
 
 
 ##########################################################
-# Entrypoint
+# Flask App Creation for Gunicorn
 ##########################################################
 
 
-def entrypoint():
-    import pvcapid.flaskapi as pvc_api  # noqa: E402
-
-    if config["api_ssl_enabled"]:
-        context = SSLContext()
-        context.minimum_version = TLSVersion.TLSv1
-        context.get_ca_certs()
-        context.load_cert_chain(
-            config["api_ssl_cert_file"], keyfile=config["api_ssl_key_file"]
-        )
-    else:
-        context = None
+def create_app():
+    """
+    Create and return the Flask app and SSL context if necessary.
+    """
+    # Import the Flask app from pvcapid.flaskapi after adjusting the path
+    import pvcapid.flaskapi as pvc_api
 
     # Print our startup messages
     print("")
@@ -102,9 +93,69 @@ def entrypoint():
     print("")
 
     pvc_api.celery_startup()
-    pvc_api.app.run(
-        config["api_listen_address"],
-        config["api_listen_port"],
-        threaded=True,
-        ssl_context=context,
-    )
+
+    return pvc_api.app
+
+
+##########################################################
+# Entrypoint
+##########################################################
+
+
+def entrypoint():
+    if config["debug"]:
+        app = create_app()
+
+        if config["api_ssl_enabled"]:
+            ssl_context = SSLContext()
+            ssl_context.minimum_version = TLSVersion.TLSv1
+            ssl_context.get_ca_certs()
+            ssl_context.load_cert_chain(
+                config["api_ssl_cert_file"], keyfile=config["api_ssl_key_file"]
+            )
+        else:
+            ssl_context = None
+
+        app.run(
+            config["api_listen_address"],
+            config["api_listen_port"],
+            threaded=True,
+            ssl_context=ssl_context,
+        )
+    else:
+        # Build the command to run Gunicorn
+        gunicorn_cmd = [
+            "gunicorn",
+            "--workers",
+            "1",
+            "--threads",
+            "8",
+            "--timeout",
+            "86400",
+            "--bind",
+            "{}:{}".format(config["api_listen_address"], config["api_listen_port"]),
+            "pvcapid.Daemon:create_app()",
+            "--log-level",
+            "info",
+            "--access-logfile",
+            "-",
+            "--error-logfile",
+            "-",
+        ]
+
+        if config["api_ssl_enabled"]:
+            gunicorn_cmd += [
+                "--certfile",
+                config["api_ssl_cert_file"],
+                "--keyfile",
+                config["api_ssl_key_file"],
+            ]
+
+        # Run Gunicorn
+        try:
+            subprocess.run(gunicorn_cmd)
+        except KeyboardInterrupt:
+            exit(0)
+        except Exception as e:
+            print(e)
+            exit(1)

api-daemon/pvcapid/helper.py

@@ -3,7 +3,7 @@
 # helper.py - PVC HTTP API helper functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -21,7 +21,9 @@
 
 import flask
 import json
+import logging
 import lxml.etree as etree
+import sys
 
 from re import match
 from requests import get
@@ -40,6 +42,15 @@ import daemon_lib.network as pvc_network
 import daemon_lib.ceph as pvc_ceph
 
 
+logger = logging.getLogger(__name__)
+logger.setLevel(logging.INFO)
+handler = logging.StreamHandler(sys.stdout)
+handler.setLevel(logging.INFO)
+formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
+handler.setFormatter(formatter)
+logger.addHandler(handler)
+
+
 #
 # Cluster base functions
 #
@@ -126,12 +137,27 @@ def cluster_maintenance(zkhandler, maint_state="false"):
 #
 @pvc_common.Profiler(config)
 @ZKConnection(config)
-def cluster_metrics(zkhandler):
+def cluster_health_metrics(zkhandler):
     """
-    Format status data from cluster_status into Prometheus-compatible metrics
+    Get cluster-wide Prometheus metrics for health
     """
 
-    retflag, retdata = pvc_cluster.get_metrics(zkhandler)
+    retflag, retdata = pvc_cluster.get_health_metrics(zkhandler)
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+    return retdata, retcode
+
+
+@pvc_common.Profiler(config)
+@ZKConnection(config)
+def cluster_resource_metrics(zkhandler):
+    """
+    Get cluster-wide Prometheus metrics for resource utilization
+    """
+
+    retflag, retdata = pvc_cluster.get_resource_metrics(zkhandler)
     if retflag:
         retcode = 200
     else:
@@ -184,6 +210,38 @@ def ceph_metrics(zkhandler):
     return output, status_code
 
 
+@pvc_common.Profiler(config)
+@ZKConnection(config)
+def zookeeper_metrics(zkhandler):
+    """
+    Obtain current Zookeeper Prometheus metrics from the active coordinator node
+    """
+    primary_node = zkhandler.read("base.config.primary_node")
+    if primary_node is not None:
+        # Get the data from the endpoint
+        # We use the default port of 9141
+        zookeeper_prometheus_uri = f"http://{primary_node}:9141/metrics"
+        response = get(zookeeper_prometheus_uri)
+
+        if response.status_code == 200:
+            output = response.text
+            # Parse the text to remove annoying ports (":2181")
+            output = output.replace(":2181", "")
+            # Sort the output text
+            output_lines = output.split("\n")
+            output_lines.sort()
+            output = "\n".join(output_lines) + "\n"
+            status_code = 200
+        else:
+            output = f"Error: Failed to obtain metric data from {primary_node} primary node daemon\n"
+            status_code = 400
+    else:
+        output = "Error: Failed to find an active primary node\n"
+        status_code = 400
+
+    return output, status_code
+
+
 #
 # Fault functions
 #
@@ -594,6 +652,7 @@ def vm_define(
     selector,
     autostart,
     migration_method,
+    migration_max_downtime=300,
     user_tags=[],
     protected_tags=[],
 ):
@@ -621,6 +680,7 @@ def vm_define(
         selector,
         autostart,
         migration_method,
+        migration_max_downtime,
         profile=None,
         tags=tags,
     )
@@ -716,6 +776,134 @@ def vm_restore(
     return output, retcode
 
 
+@ZKConnection(config)
+def create_vm_snapshot(
+    zkhandler,
+    domain,
+    snapshot_name=None,
+):
+    """
+    Take a snapshot of a VM.
+    """
+    retflag, retdata = pvc_vm.create_vm_snapshot(
+        zkhandler,
+        domain,
+        snapshot_name,
+    )
+
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+
+    output = {"message": retdata.replace('"', "'")}
+    return output, retcode
+
+
+@ZKConnection(config)
+def remove_vm_snapshot(
+    zkhandler,
+    domain,
+    snapshot_name,
+):
+    """
+    Take a snapshot of a VM.
+    """
+    retflag, retdata = pvc_vm.remove_vm_snapshot(
+        zkhandler,
+        domain,
+        snapshot_name,
+    )
+
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+
+    output = {"message": retdata.replace('"', "'")}
+    return output, retcode
+
+
+@ZKConnection(config)
+def rollback_vm_snapshot(
+    zkhandler,
+    domain,
+    snapshot_name,
+):
+    """
+    Roll back to a snapshot of a VM.
+    """
+    retflag, retdata = pvc_vm.rollback_vm_snapshot(
+        zkhandler,
+        domain,
+        snapshot_name,
+    )
+
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+
+    output = {"message": retdata.replace('"', "'")}
+    return output, retcode
+
+
+@ZKConnection(config)
+def export_vm_snapshot(
+    zkhandler,
+    domain,
+    snapshot_name,
+    export_path,
+    incremental_parent=None,
+):
+    """
+    Export a snapshot of a VM to files.
+    """
+    retflag, retdata = pvc_vm.export_vm_snapshot(
+        zkhandler,
+        domain,
+        snapshot_name,
+        export_path,
+        incremental_parent,
+    )
+
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+
+    output = {"message": retdata.replace('"', "'")}
+    return output, retcode
+
+
+@ZKConnection(config)
+def import_vm_snapshot(
+    zkhandler,
+    domain,
+    snapshot_name,
+    export_path,
+    retain_snapshot=False,
+):
+    """
+    Import a snapshot of a VM from files.
+    """
+    retflag, retdata = pvc_vm.import_vm_snapshot(
+        zkhandler,
+        domain,
+        snapshot_name,
+        export_path,
+        retain_snapshot,
+    )
+
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+
+    output = {"message": retdata.replace('"', "'")}
+    return output, retcode
+
+
 @ZKConnection(config)
 def vm_attach_device(zkhandler, vm, device_spec_xml):
     """
@@ -779,6 +967,7 @@ def get_vm_meta(zkhandler, vm):
         domain_node_selector,
         domain_node_autostart,
         domain_migrate_method,
+        domain_migrate_max_downtime,
     ) = pvc_common.getDomainMetadata(zkhandler, dom_uuid)
 
     retcode = 200
@@ -788,6 +977,7 @@ def get_vm_meta(zkhandler, vm):
         "node_selector": domain_node_selector.lower(),
         "node_autostart": domain_node_autostart,
         "migration_method": domain_migrate_method.lower(),
+        "migration_max_downtime": int(domain_migrate_max_downtime),
     }
 
     return retdata, retcode
@@ -795,7 +985,14 @@ def get_vm_meta(zkhandler, vm):
 
 @ZKConnection(config)
 def update_vm_meta(
-    zkhandler, vm, limit, selector, autostart, provisioner_profile, migration_method
+    zkhandler,
+    vm,
+    limit,
+    selector,
+    autostart,
+    provisioner_profile,
+    migration_method,
+    migration_max_downtime,
 ):
     """
     Update metadata of a VM.
@@ -811,7 +1008,14 @@ def update_vm_meta(
             autostart = False
 
     retflag, retdata = pvc_vm.modify_vm_metadata(
-        zkhandler, vm, limit, selector, autostart, provisioner_profile, migration_method
+        zkhandler,
+        vm,
+        limit,
+        selector,
+        autostart,
+        provisioner_profile,
+        migration_method,
+        migration_max_downtime,
     )
 
     if retflag:
@@ -949,11 +1153,11 @@ def vm_remove(zkhandler, name):
 
 
 @ZKConnection(config)
-def vm_start(zkhandler, name):
+def vm_start(zkhandler, name, force=False):
     """
     Start a VM in the PVC cluster.
     """
-    retflag, retdata = pvc_vm.start_vm(zkhandler, name)
+    retflag, retdata = pvc_vm.start_vm(zkhandler, name, force=force)
 
     if retflag:
         retcode = 200
@@ -997,11 +1201,11 @@ def vm_shutdown(zkhandler, name, wait):
 
 
 @ZKConnection(config)
-def vm_stop(zkhandler, name):
+def vm_stop(zkhandler, name, force=False):
     """
     Forcibly stop a VM in the PVC cluster.
     """
-    retflag, retdata = pvc_vm.stop_vm(zkhandler, name)
+    retflag, retdata = pvc_vm.stop_vm(zkhandler, name, force=force)
 
     if retflag:
         retcode = 200
@@ -1015,7 +1219,7 @@ def vm_stop(zkhandler, name):
 @ZKConnection(config)
 def vm_disable(zkhandler, name, force=False):
     """
-    Disable (shutdown or force stop if required)a  VM in the PVC cluster.
+    Disable (shutdown or force stop if required) a VM in the PVC cluster.
     """
     retflag, retdata = pvc_vm.disable_vm(zkhandler, name, force=force)
 
@@ -1087,7 +1291,7 @@ def vm_flush_locks(zkhandler, vm):
         zkhandler, None, None, None, vm, is_fuzzy=False, negate=False
     )
 
-    if retdata[0].get("state") not in ["stop", "disable"]:
+    if retdata[0].get("state") not in ["stop", "disable", "mirror"]:
         return {"message": "VM must be stopped to flush locks"}, 400
 
     retflag, retdata = pvc_vm.flush_locks(zkhandler, vm)
@@ -1101,6 +1305,342 @@ def vm_flush_locks(zkhandler, vm):
     return output, retcode
 
 
+@ZKConnection(config)
+def vm_snapshot_receive_block_full(zkhandler, pool, volume, snapshot, size, request):
+    """
+    Receive an RBD volume from a remote system
+    """
+    import rados
+    import rbd
+
+    _, rbd_detail = pvc_ceph.get_list_volume(
+        zkhandler, pool, limit=volume, is_fuzzy=False
+    )
+    if len(rbd_detail) > 0:
+        volume_exists = True
+    else:
+        volume_exists = False
+
+    cluster = rados.Rados(conffile="/etc/ceph/ceph.conf")
+    cluster.connect()
+    ioctx = cluster.open_ioctx(pool)
+
+    if not volume_exists:
+        rbd_inst = rbd.RBD()
+        rbd_inst.create(ioctx, volume, size)
+        retflag, retdata = pvc_ceph.add_volume(
+            zkhandler, pool, volume, str(size) + "B", force_flag=True, zk_only=True
+        )
+        if not retflag:
+            ioctx.close()
+            cluster.shutdown()
+
+            if retflag:
+                retcode = 200
+            else:
+                retcode = 400
+
+            output = {"message": retdata.replace('"', "'")}
+            return output, retcode
+
+    image = rbd.Image(ioctx, volume)
+
+    last_chunk = 0
+    chunk_size = 1024 * 1024 * 1024
+
+    logger.info(f"Importing full snapshot {pool}/{volume}@{snapshot}")
+    while True:
+        chunk = request.stream.read(chunk_size)
+        if not chunk:
+            break
+        image.write(chunk, last_chunk)
+        last_chunk += len(chunk)
+
+    image.close()
+    ioctx.close()
+    cluster.shutdown()
+
+    return {"message": "Successfully received RBD block device"}, 200
+
+
+@ZKConnection(config)
+def vm_snapshot_receive_block_diff(
+    zkhandler, pool, volume, snapshot, source_snapshot, request
+):
+    """
+    Receive an RBD volume from a remote system
+    """
+    import rados
+    import rbd
+
+    cluster = rados.Rados(conffile="/etc/ceph/ceph.conf")
+    cluster.connect()
+    ioctx = cluster.open_ioctx(pool)
+    image = rbd.Image(ioctx, volume)
+
+    if len(request.files) > 0:
+        logger.info(f"Applying {len(request.files)} RBD diff chunks for {snapshot}")
+
+        for i in range(len(request.files)):
+            object_key = f"object_{i}"
+            if object_key in request.files:
+                object_data = request.files[object_key].read()
+                offset = int.from_bytes(object_data[:8], "big")
+                length = int.from_bytes(object_data[8:16], "big")
+                data = object_data[16 : 16 + length]
+                logger.info(f"Applying RBD diff chunk at {offset} ({length} bytes)")
+                image.write(data, offset)
+    else:
+        return {"message": "No data received"}, 400
+
+    image.close()
+    ioctx.close()
+    cluster.shutdown()
+
+    return {
+        "message": f"Successfully received {len(request.files)} RBD diff chunks"
+    }, 200
+
+
+@ZKConnection(config)
+def vm_snapshot_receive_block_createsnap(zkhandler, pool, volume, snapshot):
+    """
+    Create the snapshot of a remote volume
+    """
+    import rados
+    import rbd
+
+    cluster = rados.Rados(conffile="/etc/ceph/ceph.conf")
+    cluster.connect()
+    ioctx = cluster.open_ioctx(pool)
+    image = rbd.Image(ioctx, volume)
+    image.create_snap(snapshot)
+    image.close()
+    ioctx.close()
+    cluster.shutdown()
+
+    retflag, retdata = pvc_ceph.add_snapshot(
+        zkhandler, pool, volume, snapshot, zk_only=True
+    )
+    if not retflag:
+
+        if retflag:
+            retcode = 200
+        else:
+            retcode = 400
+
+        output = {"message": retdata.replace('"', "'")}
+        return output, retcode
+
+    return {"message": "Successfully received RBD snapshot"}, 200
+
+
+@ZKConnection(config)
+def vm_snapshot_receive_config(zkhandler, snapshot, vm_config, source_snapshot=None):
+    """
+    Receive a VM configuration snapshot from a remote system, and modify it to work on our system
+    """
+
+    def parse_unified_diff(diff_text, original_text):
+        """
+        Take a unified diff and apply it to an original string
+        """
+        # Split the original string into lines
+        original_lines = original_text.splitlines(keepends=True)
+        patched_lines = []
+        original_idx = 0  # Track position in original lines
+
+        diff_lines = diff_text.splitlines(keepends=True)
+
+        for line in diff_lines:
+            if line.startswith("---") or line.startswith("+++"):
+                # Ignore prefix lines
+                continue
+            if line.startswith("@@"):
+                # Extract line numbers from the diff hunk header
+                hunk_header = line
+                parts = hunk_header.split(" ")
+                original_range = parts[1]
+
+                # Get the starting line number and range length for the original file
+                original_start, _ = map(int, original_range[1:].split(","))
+
+                # Adjust for zero-based indexing
+                original_start -= 1
+
+                # Add any lines between the current index and the next hunk's start
+                while original_idx < original_start:
+                    patched_lines.append(original_lines[original_idx])
+                    original_idx += 1
+
+            elif line.startswith("-"):
+                # This line should be removed from the original, skip it
+                original_idx += 1
+            elif line.startswith("+"):
+                # This line should be added to the patched version, removing the '+'
+                patched_lines.append(line[1:])
+            else:
+                # Context line (unchanged), it has no prefix, add from the original
+                patched_lines.append(original_lines[original_idx])
+                original_idx += 1
+
+        # Add any remaining lines from the original file after the last hunk
+        patched_lines.extend(original_lines[original_idx:])
+
+        return "".join(patched_lines).strip()
+
+    # Get our XML configuration for this snapshot
+    # We take the main XML configuration, then apply the diff for this particular incremental
+    current_snapshot = [s for s in vm_config["snapshots"] if s["name"] == snapshot][0]
+    vm_xml = vm_config["xml"]
+    vm_xml_diff = "\n".join(current_snapshot["xml_diff_lines"])
+    snapshot_vm_xml = parse_unified_diff(vm_xml_diff, vm_xml)
+    xml_data = etree.fromstring(snapshot_vm_xml)
+
+    # Replace the Ceph storage secret UUID with this cluster's
+    our_ceph_secret_uuid = config["ceph_secret_uuid"]
+    ceph_secrets = xml_data.xpath("//secret[@type='ceph']")
+    for ceph_secret in ceph_secrets:
+        ceph_secret.set("uuid", our_ceph_secret_uuid)
+
+    # Replace the Ceph source hosts with this cluster's
+    our_ceph_storage_hosts = config["storage_hosts"]
+    our_ceph_storage_port = str(config["ceph_monitor_port"])
+    ceph_sources = xml_data.xpath("//source[@protocol='rbd']")
+    for ceph_source in ceph_sources:
+        for host in ceph_source.xpath("host"):
+            ceph_source.remove(host)
+        for ceph_storage_host in our_ceph_storage_hosts:
+            new_host = etree.Element("host")
+            new_host.set("name", ceph_storage_host)
+            new_host.set("port", our_ceph_storage_port)
+            ceph_source.append(new_host)
+
+    # Regenerate the VM XML
+    snapshot_vm_xml = etree.tostring(xml_data, pretty_print=True).decode("utf8")
+
+    if (
+        source_snapshot is not None
+        or pvc_vm.searchClusterByUUID(zkhandler, vm_config["uuid"]) is not None
+    ):
+        logger.info(
+            f"Receiving incremental VM configuration for {vm_config['name']}@{snapshot}"
+        )
+
+        # Modify the VM based on our passed detail
+        retcode, retmsg = pvc_vm.modify_vm(
+            zkhandler,
+            vm_config["uuid"],
+            False,
+            snapshot_vm_xml,
+        )
+        if not retcode:
+            retcode = 400
+            retdata = {"message": retmsg}
+            return retdata, retcode
+
+        retcode, retmsg = pvc_vm.modify_vm_metadata(
+            zkhandler,
+            vm_config["uuid"],
+            None,  # Node limits are left unchanged
+            vm_config["node_selector"],
+            vm_config["node_autostart"],
+            vm_config["profile"],
+            vm_config["migration_method"],
+            vm_config["migration_max_downtime"],
+        )
+        if not retcode:
+            retcode = 400
+            retdata = {"message": retmsg}
+            return retdata, retcode
+
+        current_vm_tags = zkhandler.children(("domain.meta.tags", vm_config["uuid"]))
+        new_vm_tags = [t["name"] for t in vm_config["tags"]]
+        remove_tags = []
+        add_tags = []
+        for tag in vm_config["tags"]:
+            if tag["name"] not in current_vm_tags:
+                add_tags.append((tag["name"], tag["protected"]))
+        for tag in current_vm_tags:
+            if tag not in new_vm_tags:
+                remove_tags.append(tag)
+
+        for tag in add_tags:
+            name, protected = tag
+            pvc_vm.modify_vm_tag(
+                zkhandler, vm_config["uuid"], "add", name, protected=protected
+            )
+        for tag in remove_tags:
+            pvc_vm.modify_vm_tag(zkhandler, vm_config["uuid"], "remove", name)
+    else:
+        logger.info(
+            f"Receiving full VM configuration for {vm_config['name']}@{snapshot}"
+        )
+
+        # Define the VM based on our passed detail
+        retcode, retmsg = pvc_vm.define_vm(
+            zkhandler,
+            snapshot_vm_xml,
+            None,  # Target node is autoselected
+            None,  # Node limits are invalid here so ignore them
+            vm_config["node_selector"],
+            vm_config["node_autostart"],
+            vm_config["migration_method"],
+            vm_config["migration_max_downtime"],
+            vm_config["profile"],
+            vm_config["tags"],
+            "mirror",
+        )
+        if not retcode:
+            retcode = 400
+            retdata = {"message": retmsg}
+            return retdata, retcode
+
+    # Add this snapshot to the VM manually in Zookeeper
+    zkhandler.write(
+        [
+            (
+                (
+                    "domain.snapshots",
+                    vm_config["uuid"],
+                    "domain_snapshot.name",
+                    snapshot,
+                ),
+                snapshot,
+            ),
+            (
+                (
+                    "domain.snapshots",
+                    vm_config["uuid"],
+                    "domain_snapshot.timestamp",
+                    snapshot,
+                ),
+                current_snapshot["timestamp"],
+            ),
+            (
+                (
+                    "domain.snapshots",
+                    vm_config["uuid"],
+                    "domain_snapshot.xml",
+                    snapshot,
+                ),
+                snapshot_vm_xml,
+            ),
+            (
+                (
+                    "domain.snapshots",
+                    vm_config["uuid"],
+                    "domain_snapshot.rbd_snapshots",
+                    snapshot,
+                ),
+                ",".join(current_snapshot["rbd_snapshots"]),
+            ),
+        ]
+    )
+
+    return {"message": "Successfully received VM configuration snapshot"}, 200
+
+
 #
 # Network functions
 #
@@ -1804,11 +2344,29 @@ def ceph_volume_list(zkhandler, pool=None, limit=None, is_fuzzy=True):
 
 
 @ZKConnection(config)
-def ceph_volume_add(zkhandler, pool, name, size):
+def ceph_volume_scan(zkhandler, pool, name):
+    """
+    (Re)scan a Ceph RBD volume for stats in the PVC Ceph storage cluster.
+    """
+    retflag, retdata = pvc_ceph.scan_volume(zkhandler, pool, name)
+
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+
+    output = {"message": retdata.replace('"', "'")}
+    return output, retcode
+
+
+@ZKConnection(config)
+def ceph_volume_add(zkhandler, pool, name, size, force_flag=False):
     """
     Add a Ceph RBD volume to the PVC Ceph storage cluster.
     """
-    retflag, retdata = pvc_ceph.add_volume(zkhandler, pool, name, size)
+    retflag, retdata = pvc_ceph.add_volume(
+        zkhandler, pool, name, size, force_flag=force_flag
+    )
 
     if retflag:
         retcode = 200
@@ -1820,11 +2378,13 @@ def ceph_volume_add(zkhandler, pool, name, size):
 
 
 @ZKConnection(config)
-def ceph_volume_clone(zkhandler, pool, name, source_volume):
+def ceph_volume_clone(zkhandler, pool, name, source_volume, force_flag):
     """
     Clone a Ceph RBD volume to a new volume on the PVC Ceph storage cluster.
     """
-    retflag, retdata = pvc_ceph.clone_volume(zkhandler, pool, source_volume, name)
+    retflag, retdata = pvc_ceph.clone_volume(
+        zkhandler, pool, source_volume, name, force_flag=force_flag
+    )
 
     if retflag:
         retcode = 200
@@ -1836,11 +2396,13 @@ def ceph_volume_clone(zkhandler, pool, name, source_volume):
 
 
 @ZKConnection(config)
-def ceph_volume_resize(zkhandler, pool, name, size):
+def ceph_volume_resize(zkhandler, pool, name, size, force_flag):
     """
     Resize an existing Ceph RBD volume in the PVC Ceph storage cluster.
     """
-    retflag, retdata = pvc_ceph.resize_volume(zkhandler, pool, name, size)
+    retflag, retdata = pvc_ceph.resize_volume(
+        zkhandler, pool, name, size, force_flag=force_flag
+    )
 
     if retflag:
         retcode = 200
@@ -2112,6 +2674,22 @@ def ceph_volume_snapshot_rename(zkhandler, pool, volume, name, new_name):
     return output, retcode
 
 
+@ZKConnection(config)
+def ceph_volume_snapshot_rollback(zkhandler, pool, volume, name):
+    """
+    Roll back a Ceph RBD volume to a given snapshot in the PVC Ceph storage cluster.
+    """
+    retflag, retdata = pvc_ceph.rollback_snapshot(zkhandler, pool, volume, name)
+
+    if retflag:
+        retcode = 200
+    else:
+        retcode = 400
+
+    output = {"message": retdata.replace('"', "'")}
+    return output, retcode
+
+
 @ZKConnection(config)
 def ceph_volume_snapshot_remove(zkhandler, pool, volume, name):
     """

api-daemon/pvcapid/models.py

@@ -3,7 +3,7 @@
 # models.py - PVC Database models
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -36,6 +36,7 @@ class DBSystemTemplate(db.Model):
     node_selector = db.Column(db.Text)
     node_autostart = db.Column(db.Boolean, nullable=False)
     migration_method = db.Column(db.Text)
+    migration_max_downtime = db.Column(db.Integer, default=300, server_default="300")
     ova = db.Column(db.Integer, db.ForeignKey("ova.id"), nullable=True)
 
     def __init__(
@@ -50,6 +51,7 @@ class DBSystemTemplate(db.Model):
         node_selector,
         node_autostart,
         migration_method,
+        migration_max_downtime,
         ova=None,
     ):
         self.name = name
@@ -62,6 +64,7 @@ class DBSystemTemplate(db.Model):
         self.node_selector = node_selector
         self.node_autostart = node_autostart
         self.migration_method = migration_method
+        self.migration_max_downtime = migration_max_downtime
         self.ova = ova
 
     def __repr__(self):

api-daemon/pvcapid/ova.py

@@ -3,7 +3,7 @@
 # ova.py - PVC OVA parser library
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

api-daemon/pvcapid/provisioner.py

@@ -3,7 +3,7 @@
 # provisioner.py - PVC API Provisioner functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -125,7 +125,7 @@ def list_template(limit, table, is_fuzzy=True):
             args = (template_data["id"],)
             cur.execute(query, args)
             disks = cur.fetchall()
-            data[template_id]["disks"] = disks
+            data[template_id]["disks"] = sorted(disks, key=lambda x: x["disk_id"])
 
     close_database(conn, cur)
 
@@ -221,6 +221,7 @@ def create_template_system(
     node_selector=None,
     node_autostart=False,
     migration_method=None,
+    migration_max_downtime=None,
     ova=None,
 ):
     if list_template_system(name, is_fuzzy=False)[-1] != 404:
@@ -231,7 +232,7 @@ def create_template_system(
     if node_selector == "none":
         node_selector = None
 
-    query = "INSERT INTO system_template (name, vcpu_count, vram_mb, serial, vnc, vnc_bind, node_limit, node_selector, node_autostart, migration_method, ova) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s);"
+    query = "INSERT INTO system_template (name, vcpu_count, vram_mb, serial, vnc, vnc_bind, node_limit, node_selector, node_autostart, migration_method, migration_max_downtime, ova) VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s);"
     args = (
         name,
         vcpu_count,
@@ -243,6 +244,7 @@ def create_template_system(
         node_selector,
         node_autostart,
         migration_method,
+        migration_max_downtime,
         ova,
     )
 
@@ -282,27 +284,28 @@ def create_template_network(name, mac_template=None):
     return retmsg, retcode
 
 
-def create_template_network_element(name, vni):
+def create_template_network_element(name, vni, permit_duplicate=False):
     if list_template_network(name, is_fuzzy=False)[-1] != 200:
         retmsg = {"message": 'The network template "{}" does not exist.'.format(name)}
         retcode = 400
         return retmsg, retcode
 
-    networks, code = list_template_network_vnis(name)
-    if code != 200:
-        networks = []
-    found_vni = False
-    for network in networks:
-        if network["vni"] == vni:
-            found_vni = True
-    if found_vni:
-        retmsg = {
-            "message": 'The VNI "{}" in network template "{}" already exists.'.format(
-                vni, name
-            )
-        }
-        retcode = 400
-        return retmsg, retcode
+    if not permit_duplicate:
+        networks, code = list_template_network_vnis(name)
+        if code != 200:
+            networks = []
+        found_vni = False
+        for network in networks:
+            if network["vni"] == vni:
+                found_vni = True
+        if found_vni:
+            retmsg = {
+                "message": 'The VNI "{}" in network template "{}" already exists.'.format(
+                    vni, name
+                )
+            }
+            retcode = 400
+            return retmsg, retcode
 
     conn, cur = open_database(config)
     try:
@@ -438,6 +441,7 @@ def modify_template_system(
     node_selector=None,
     node_autostart=None,
     migration_method=None,
+    migration_max_downtime=None,
 ):
     if list_template_system(name, is_fuzzy=False)[-1] != 200:
         retmsg = {"message": 'The system template "{}" does not exist.'.format(name)}
@@ -505,6 +509,11 @@ def modify_template_system(
     if migration_method is not None:
         fields.append({"field": "migration_method", "data": migration_method})
 
+    if migration_max_downtime is not None:
+        fields.append(
+            {"field": "migration_max_downtime", "data": int(migration_max_downtime)}
+        )
+
     conn, cur = open_database(config)
     try:
         for field in fields:

api-daemon/swagger.html

@@ -1,13 +0,0 @@
-<!DOCTYPE html>
-<html>
-  <head>
-    <title>PVC Client API Documentation</title>
-    <meta charset="utf-8"/>
-    <meta name="viewport" content="width=device-width, initial-scale=1">
-    <style> body { margin: 0; padding: 0; } </style>
-  </head>
-  <body>
-    <redoc spec-url='./swagger.json' hide-loading></redoc>
-    <script src="https://rebilly.github.io/ReDoc/releases/latest/redoc.min.js"> </script>
-  </body>
-</html>

build-and-deploy.sh

@@ -13,6 +13,8 @@ else
 fi
 
 KEEP_ARTIFACTS=""
+API_ONLY=""
+PRIMARY_NODE=""
 if [[ -n ${1} ]]; then
     for arg in ${@}; do
         case ${arg} in
@@ -20,33 +22,45 @@ if [[ -n ${1} ]]; then
                 KEEP_ARTIFACTS="y"
                 shift
             ;;
+            -a|--api-only)
+                API_ONLY="y"
+                shift
+            ;;
+            -p=*|--become-primary=*)
+                PRIMARY_NODE=$( awk -F'=' '{ print $NF }' <<<"${arg}" )
+                shift
+            ;;
         esac
     done
 fi
 
 HOSTS=( ${@} )
-echo "> Deploying to host(s): ${HOSTS[@]}"
+echo "Deploying to host(s): ${HOSTS[@]}"
+if [[ -n ${PRIMARY_NODE} ]]; then
+    echo "Will become primary on ${PRIMARY_NODE} after updating it"
+fi
 
 # Move to repo root if we're not
 pushd $( git rev-parse --show-toplevel ) &>/dev/null
 
 # Prepare code
-echo "Preparing code (format and lint)..."
+echo "> Preparing code (format and lint)..."
 ./format || exit 1
 ./lint || exit 1
 
 # Build the packages
-echo -n "Building packages..."
+echo -n "> Building packages..."
 version="$( ./build-unstable-deb.sh 2>/dev/null )"
 echo " done. Package version ${version}."
 
 # Install the client(s) locally
-echo -n "Installing client packages locally..."
+echo -n "> Installing client packages locally..."
 $SUDO dpkg -i --force-all ../pvc-client*_${version}*.deb &>/dev/null
 echo " done".
 
+echo "> Copying packages..."
 for HOST in ${HOSTS[@]}; do
-    echo -n "Copying packages to host ${HOST}..."
+    echo -n ">>> Copying packages to host ${HOST}..."
     ssh $HOST $SUDO rm -rf /tmp/pvc &>/dev/null
     ssh $HOST mkdir /tmp/pvc &>/dev/null
     scp ../pvc-*_${version}*.deb $HOST:/tmp/pvc/ &>/dev/null
@@ -57,26 +71,34 @@ if [[ -z ${KEEP_ARTIFACTS} ]]; then
 fi
 
 for HOST in ${HOSTS[@]}; do
-    echo "> Deploying packages to host ${HOST}"
-    echo -n "Installing packages..."
+    echo "> Deploying packages on host ${HOST}"
+    echo -n ">>> Installing packages..."
     ssh $HOST $SUDO dpkg -i --force-all /tmp/pvc/*.deb &>/dev/null
     ssh $HOST rm -rf /tmp/pvc &>/dev/null
     echo " done."
-    echo -n "Restarting PVC daemons..."
+    echo -n ">>> Restarting PVC daemons..."
     ssh $HOST $SUDO systemctl restart pvcapid &>/dev/null
     sleep 2
     ssh $HOST $SUDO systemctl restart pvcworkerd &>/dev/null
+    if [[ -z ${API_ONLY} ]]; then
     sleep 2
     ssh $HOST $SUDO systemctl restart pvchealthd &>/dev/null
     sleep 2
     ssh $HOST $SUDO systemctl restart pvcnoded &>/dev/null
     echo " done."
-    echo -n "Waiting for node daemon to be running..."
+    echo -n ">>> Waiting for node daemon to be running..."
     while [[ $( ssh $HOST "pvc -q node list -f json ${HOST%%.*} | jq -r '.[].daemon_state'" 2>/dev/null ) != "run" ]]; do
         sleep 5
         echo -n "."
     done
+    fi
     echo " done."
+    if [[ -n ${PRIMARY_NODE} && ${PRIMARY_NODE} == ${HOST} ]]; then
+        echo -n ">>> Setting node $HOST to primary coordinator state... "
+        ssh $HOST pvc -q node primary --wait &>/dev/null
+        ssh $HOST $SUDO systemctl restart pvcworkerd &>/dev/null
+        echo "done."
+    fi
 done
 
 popd &>/dev/null

client-cli/pvc.py

@@ -3,7 +3,7 @@
 # pvc.py - PVC client command-line interface (stub testing interface)
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

client-cli/pvc/cli/formatters.py

@@ -3,7 +3,7 @@
 # formatters.py - PVC Click CLI output formatters library
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2023 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -83,6 +83,37 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
     total_volumes = data.get("volumes", 0)
     total_snapshots = data.get("snapshots", 0)
 
+    total_cpu_total = data.get("resources", {}).get("cpu", {}).get("total", 0)
+    total_cpu_load = data.get("resources", {}).get("cpu", {}).get("load", 0)
+    total_cpu_utilization = (
+        data.get("resources", {}).get("cpu", {}).get("utilization", 0)
+    )
+    total_cpu_string = (
+        f"{total_cpu_utilization:.1f}% ({total_cpu_load:.1f} / {total_cpu_total})"
+    )
+
+    total_memory_total = (
+        data.get("resources", {}).get("memory", {}).get("total", 0) / 1024
+    )
+    total_memory_used = (
+        data.get("resources", {}).get("memory", {}).get("used", 0) / 1024
+    )
+    total_memory_utilization = (
+        data.get("resources", {}).get("memory", {}).get("utilization", 0)
+    )
+    total_memory_string = f"{total_memory_utilization:.1f}% ({total_memory_used:.1f} GB / {total_memory_total:.1f} GB)"
+
+    total_disk_total = (
+        data.get("resources", {}).get("disk", {}).get("total", 0) / 1024 / 1024
+    )
+    total_disk_used = (
+        data.get("resources", {}).get("disk", {}).get("used", 0) / 1024 / 1024
+    )
+    total_disk_utilization = round(
+        data.get("resources", {}).get("disk", {}).get("utilization", 0)
+    )
+    total_disk_string = f"{total_disk_utilization:.1f}% ({total_disk_used:.1f} GB / {total_disk_total:.1f} GB)"
+
     if maintenance == "true" or health == -1:
         health_colour = ansii["blue"]
     elif health > 90:
@@ -94,12 +125,9 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
 
     output = list()
 
-    output.append(f"{ansii['bold']}PVC cluster status:{ansii['end']}")
-    output.append("")
-
-    output.append(f"{ansii['purple']}Primary node:{ansii['end']}  {primary_node}")
-    output.append(f"{ansii['purple']}PVC version:{ansii['end']}   {pvc_version}")
-    output.append(f"{ansii['purple']}Upstream IP:{ansii['end']}   {upstream_ip}")
+    output.append(f"{ansii['purple']}Primary node:{ansii['end']}   {primary_node}")
+    output.append(f"{ansii['purple']}PVC version:{ansii['end']}    {pvc_version}")
+    output.append(f"{ansii['purple']}Upstream IP:{ansii['end']}    {upstream_ip}")
     output.append("")
 
     if health != "-1":
@@ -111,7 +139,7 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
         health = f"{health} (maintenance on)"
 
     output.append(
-        f"{ansii['purple']}Health:{ansii['end']}        {health_colour}{health}{ansii['end']}"
+        f"{ansii['purple']}Health:{ansii['end']}         {health_colour}{health}{ansii['end']}"
     )
 
     if messages is not None and len(messages) > 0:
@@ -135,8 +163,18 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
                 )
             )
 
-        messages = "\n               ".join(message_list)
-        output.append(f"{ansii['purple']}Active Faults:{ansii['end']} {messages}")
+        messages = "\n                ".join(message_list)
+    else:
+        messages = "None"
+    output.append(f"{ansii['purple']}Active faults:{ansii['end']}  {messages}")
+
+    output.append(f"{ansii['purple']}Total CPU:{ansii['end']}      {total_cpu_string}")
+
+    output.append(
+        f"{ansii['purple']}Total memory:{ansii['end']}   {total_memory_string}"
+    )
+
+    output.append(f"{ansii['purple']}Total disk:{ansii['end']}     {total_disk_string}")
 
     output.append("")
 
@@ -166,14 +204,14 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
 
     nodes_string = ", ".join(nodes_strings)
 
-    output.append(f"{ansii['purple']}Nodes:{ansii['end']}         {nodes_string}")
+    output.append(f"{ansii['purple']}Nodes:{ansii['end']}          {nodes_string}")
 
-    vm_states = ["start", "disable"]
+    vm_states = ["start", "disable", "mirror"]
     vm_states.extend(
         [
             state
             for state in data.get("vms", {}).keys()
-            if state not in ["total", "start", "disable"]
+            if state not in ["total", "start", "disable", "mirror"]
         ]
     )
 
@@ -183,8 +221,10 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
             continue
         if state in ["start"]:
             state_colour = ansii["green"]
-        elif state in ["migrate", "disable", "provision"]:
+        elif state in ["migrate", "disable", "provision", "mirror"]:
             state_colour = ansii["blue"]
+        elif state in ["mirror"]:
+            state_colour = ansii["purple"]
         elif state in ["stop", "fail"]:
             state_colour = ansii["red"]
         else:
@@ -196,7 +236,7 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
 
     vms_string = ", ".join(vms_strings)
 
-    output.append(f"{ansii['purple']}VMs:{ansii['end']}           {vms_string}")
+    output.append(f"{ansii['purple']}VMs:{ansii['end']}            {vms_string}")
 
     osd_states = ["up,in"]
     osd_states.extend(
@@ -222,15 +262,15 @@ def cli_cluster_status_format_pretty(CLI_CONFIG, data):
 
     osds_string = " ".join(osds_strings)
 
-    output.append(f"{ansii['purple']}OSDs:{ansii['end']}          {osds_string}")
+    output.append(f"{ansii['purple']}OSDs:{ansii['end']}           {osds_string}")
 
-    output.append(f"{ansii['purple']}Pools:{ansii['end']}         {total_pools}")
+    output.append(f"{ansii['purple']}Pools:{ansii['end']}          {total_pools}")
 
-    output.append(f"{ansii['purple']}Volumes:{ansii['end']}       {total_volumes}")
+    output.append(f"{ansii['purple']}Volumes:{ansii['end']}        {total_volumes}")
 
-    output.append(f"{ansii['purple']}Snapshots:{ansii['end']}     {total_snapshots}")
+    output.append(f"{ansii['purple']}Snapshots:{ansii['end']}      {total_snapshots}")
 
-    output.append(f"{ansii['purple']}Networks:{ansii['end']}      {total_networks}")
+    output.append(f"{ansii['purple']}Networks:{ansii['end']}       {total_networks}")
 
     output.append("")
 
@@ -258,9 +298,6 @@ def cli_cluster_status_format_short(CLI_CONFIG, data):
 
     output = list()
 
-    output.append(f"{ansii['bold']}PVC cluster status:{ansii['end']}")
-    output.append("")
-
     if health != "-1":
         health = f"{health}%"
     else:
@@ -270,7 +307,7 @@ def cli_cluster_status_format_short(CLI_CONFIG, data):
         health = f"{health} (maintenance on)"
 
     output.append(
-        f"{ansii['purple']}Health:{ansii['end']}        {health_colour}{health}{ansii['end']}"
+        f"{ansii['purple']}Health:{ansii['end']}         {health_colour}{health}{ansii['end']}"
     )
 
     if messages is not None and len(messages) > 0:
@@ -295,7 +332,48 @@ def cli_cluster_status_format_short(CLI_CONFIG, data):
             )
 
         messages = "\n               ".join(message_list)
-        output.append(f"{ansii['purple']}Active Faults:{ansii['end']} {messages}")
+    else:
+        messages = "None"
+    output.append(f"{ansii['purple']}Active faults:{ansii['end']}  {messages}")
+
+    total_cpu_total = data.get("resources", {}).get("cpu", {}).get("total", 0)
+    total_cpu_load = data.get("resources", {}).get("cpu", {}).get("load", 0)
+    total_cpu_utilization = (
+        data.get("resources", {}).get("cpu", {}).get("utilization", 0)
+    )
+    total_cpu_string = (
+        f"{total_cpu_utilization:.1f}% ({total_cpu_load:.1f} / {total_cpu_total})"
+    )
+
+    total_memory_total = (
+        data.get("resources", {}).get("memory", {}).get("total", 0) / 1024
+    )
+    total_memory_used = (
+        data.get("resources", {}).get("memory", {}).get("used", 0) / 1024
+    )
+    total_memory_utilization = (
+        data.get("resources", {}).get("memory", {}).get("utilization", 0)
+    )
+    total_memory_string = f"{total_memory_utilization:.1f}% ({total_memory_used:.1f} GB / {total_memory_total:.1f} GB)"
+
+    total_disk_total = (
+        data.get("resources", {}).get("disk", {}).get("total", 0) / 1024 / 1024
+    )
+    total_disk_used = (
+        data.get("resources", {}).get("disk", {}).get("used", 0) / 1024 / 1024
+    )
+    total_disk_utilization = round(
+        data.get("resources", {}).get("disk", {}).get("utilization", 0)
+    )
+    total_disk_string = f"{total_disk_utilization:.1f}% ({total_disk_used:.1f} GB / {total_disk_total:.1f} GB)"
+
+    output.append(f"{ansii['purple']}CPU usage:{ansii['end']}      {total_cpu_string}")
+
+    output.append(
+        f"{ansii['purple']}Memory usage:{ansii['end']}   {total_memory_string}"
+    )
+
+    output.append(f"{ansii['purple']}Disk usage:{ansii['end']}     {total_disk_string}")
 
     output.append("")
 
@@ -580,9 +658,11 @@ def cli_cluster_fault_list_format_long(CLI_CONFIG, fault_data):
                 fault_id=fault["id"],
                 fault_status=fault["status"].title(),
                 fault_health_delta=f"-{fault['health_delta']}%",
-                fault_acknowledged_at=fault["acknowledged_at"]
-                if fault["acknowledged_at"] != ""
-                else "N/A",
+                fault_acknowledged_at=(
+                    fault["acknowledged_at"]
+                    if fault["acknowledged_at"] != ""
+                    else "N/A"
+                ),
                 fault_last_reported=fault["last_reported"],
                 fault_first_reported=fault["first_reported"],
             )
@@ -645,6 +725,24 @@ def cli_cluster_task_format_pretty(CLI_CONFIG, task_data):
         if _task_type_length > task_type_length:
             task_type_length = _task_type_length
 
+        for arg_name, arg_data in task["kwargs"].items():
+            # Skip the "run_on" argument
+            if arg_name == "run_on":
+                continue
+
+            # task_arg_name column
+            _task_arg_name_length = len(str(arg_name)) + 1
+            if _task_arg_name_length > task_arg_name_length:
+                task_arg_name_length = _task_arg_name_length
+
+    task_header_length = (
+        task_id_length + task_name_length + task_type_length + task_worker_length + 3
+    )
+    max_task_data_length = (
+        MAX_CONTENT_WIDTH - task_header_length - task_arg_name_length - 2
+    )
+
+    for task in task_data:
         updated_kwargs = list()
         for arg_name, arg_data in task["kwargs"].items():
             # Skip the "run_on" argument
@@ -656,15 +754,30 @@ def cli_cluster_task_format_pretty(CLI_CONFIG, task_data):
             if _task_arg_name_length > task_arg_name_length:
                 task_arg_name_length = _task_arg_name_length
 
-            if len(str(arg_data)) > 17:
-                arg_data = arg_data[:17] + "..."
+            if isinstance(arg_data, list):
+                for subarg_data in arg_data:
+                    if len(subarg_data) > max_task_data_length:
+                        subarg_data = (
+                            str(subarg_data[: max_task_data_length - 4]) + " ..."
+                        )
 
-            # task_arg_data column
-            _task_arg_data_length = len(str(arg_data)) + 1
-            if _task_arg_data_length > task_arg_data_length:
-                task_arg_data_length = _task_arg_data_length
+                    # task_arg_data column
+                    _task_arg_data_length = len(str(subarg_data)) + 1
+                    if _task_arg_data_length > task_arg_data_length:
+                        task_arg_data_length = _task_arg_data_length
+
+                    updated_kwargs.append({"name": arg_name, "data": subarg_data})
+            else:
+                if len(str(arg_data)) > 24:
+                    arg_data = str(arg_data[:24]) + " ..."
+
+                    # task_arg_data column
+                    _task_arg_data_length = len(str(arg_data)) + 1
+                    if _task_arg_data_length > task_arg_data_length:
+                        task_arg_data_length = _task_arg_data_length
+
+                updated_kwargs.append({"name": arg_name, "data": arg_data})
 
-            updated_kwargs.append({"name": arg_name, "data": arg_data})
         task["kwargs"] = updated_kwargs
         tasks.append(task)
 
@@ -792,7 +905,7 @@ def cli_connection_list_format_pretty(CLI_CONFIG, data):
     # Parse each connection and adjust field lengths
     for connection in data:
         for field, length in [(f, fields[f]["length"]) for f in fields]:
-            _length = len(str(connection[field]))
+            _length = len(str(connection[field])) + 1
             if _length > length:
                 length = len(str(connection[field])) + 1
 
@@ -846,6 +959,28 @@ def cli_connection_list_format_pretty(CLI_CONFIG, data):
     return "\n".join(output)
 
 
+def cli_connection_list_format_prometheus_json(CLI_CONFIG, data):
+    """
+    Format the output of cli_connection_list as Prometheus file service discovery JSON
+    """
+
+    from json import dumps
+
+    output = list()
+    for connection in data:
+        output_obj = {
+            "targets": [f"{connection['address']}:{connection['port']}"],
+            "labels": {
+                "job": "pvc",
+                "pvc_cluster_name": f"{connection['name']}: {connection['description']}",
+                "pvc_cluster_id": connection["name"],
+            },
+        }
+        output.append(output_obj)
+
+    return dumps(output, indent=2)
+
+
 def cli_connection_detail_format_pretty(CLI_CONFIG, data):
     """
     Pretty format the output of cli_connection_detail
@@ -870,7 +1005,7 @@ def cli_connection_detail_format_pretty(CLI_CONFIG, data):
     # Parse each connection and adjust field lengths
     for connection in data:
         for field, length in [(f, fields[f]["length"]) for f in fields]:
-            _length = len(str(connection[field]))
+            _length = len(str(connection[field])) + 1
             if _length > length:
                 length = len(str(connection[field])) + 1
 

client-cli/pvc/cli/helpers.py

@@ -3,7 +3,7 @@
 # helpers.py - PVC Click CLI helper function library
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2023 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -20,25 +20,16 @@
 ###############################################################################
 
 from click import echo as click_echo
-from click import confirm
-from datetime import datetime
 from distutils.util import strtobool
-from getpass import getuser
 from json import load as jload
 from json import dump as jdump
-from os import chmod, environ, getpid, path, makedirs, get_terminal_size
-from re import findall
+from os import chmod, environ, getpid, path, get_terminal_size
 from socket import gethostname
-from subprocess import run, PIPE
 from sys import argv
 from syslog import syslog, openlog, closelog, LOG_AUTH
 from yaml import load as yload
 from yaml import SafeLoader
 
-import pvc.lib.provisioner
-import pvc.lib.vm
-import pvc.lib.node
-
 
 DEFAULT_STORE_DATA = {"cfgfile": "/etc/pvc/pvc.conf"}
 DEFAULT_STORE_FILENAME = "pvc.json"
@@ -176,9 +167,17 @@ def get_store(store_path):
     with open(store_file) as fh:
         try:
             store_data = jload(fh)
-            return store_data
         except Exception:
-            return dict()
+            store_data = dict()
+
+    if path.exists(DEFAULT_STORE_DATA["cfgfile"]):
+        if store_data.get("local", None) != DEFAULT_STORE_DATA:
+            del store_data["local"]
+        if "local" not in store_data.keys():
+            store_data["local"] = DEFAULT_STORE_DATA
+            update_store(store_path, store_data)
+
+    return store_data
 
 
 def update_store(store_path, store_data):
@@ -195,322 +194,3 @@ def update_store(store_path, store_data):
 
     with open(store_file, "w") as fh:
         jdump(store_data, fh, sort_keys=True, indent=4)
-
-
-def get_autobackup_config(CLI_CONFIG, cfgfile):
-    try:
-        config = dict()
-        with open(cfgfile) as fh:
-            backup_config = yload(fh, Loader=SafeLoader)["autobackup"]
-
-        config["backup_root_path"] = backup_config["backup_root_path"]
-        config["backup_root_suffix"] = backup_config["backup_root_suffix"]
-        config["backup_tags"] = backup_config["backup_tags"]
-        config["backup_schedule"] = backup_config["backup_schedule"]
-        config["auto_mount_enabled"] = backup_config["auto_mount"]["enabled"]
-        if config["auto_mount_enabled"]:
-            config["mount_cmds"] = list()
-            _mount_cmds = backup_config["auto_mount"]["mount_cmds"]
-            for _mount_cmd in _mount_cmds:
-                if "{backup_root_path}" in _mount_cmd:
-                    _mount_cmd = _mount_cmd.format(
-                        backup_root_path=backup_config["backup_root_path"]
-                    )
-                config["mount_cmds"].append(_mount_cmd)
-
-            config["unmount_cmds"] = list()
-            _unmount_cmds = backup_config["auto_mount"]["unmount_cmds"]
-            for _unmount_cmd in _unmount_cmds:
-                if "{backup_root_path}" in _unmount_cmd:
-                    _unmount_cmd = _unmount_cmd.format(
-                        backup_root_path=backup_config["backup_root_path"]
-                    )
-                config["unmount_cmds"].append(_unmount_cmd)
-
-    except FileNotFoundError:
-        echo(CLI_CONFIG, "ERROR: Specified backup configuration does not exist!")
-        exit(1)
-    except KeyError as e:
-        echo(CLI_CONFIG, f"ERROR: Backup configuration is invalid: {e}")
-        exit(1)
-
-    return config
-
-
-def vm_autobackup(
-    CLI_CONFIG,
-    autobackup_cfgfile=DEFAULT_AUTOBACKUP_FILENAME,
-    force_full_flag=False,
-    cron_flag=False,
-):
-    """
-    Perform automatic backups of VMs based on an external config file.
-    """
-
-    # Validate that we are running on the current primary coordinator of the 'local' cluster connection
-    real_connection = CLI_CONFIG["connection"]
-    CLI_CONFIG["connection"] = "local"
-    retcode, retdata = pvc.lib.node.node_info(CLI_CONFIG, DEFAULT_NODE_HOSTNAME)
-    if not retcode or retdata.get("coordinator_state") != "primary":
-        if cron_flag:
-            echo(
-                CLI_CONFIG,
-                "Current host is not the primary coordinator of the local cluster and running in cron mode. Exiting cleanly.",
-            )
-            exit(0)
-        else:
-            echo(
-                CLI_CONFIG,
-                f"ERROR: Current host is not the primary coordinator of the local cluster; got connection '{real_connection}', host '{DEFAULT_NODE_HOSTNAME}'.",
-            )
-            echo(
-                CLI_CONFIG,
-                "Autobackup MUST be run from the cluster active primary coordinator using the 'local' connection. See '-h'/'--help' for details.",
-            )
-            exit(1)
-
-    # Ensure we're running as root, or show a warning & confirmation
-    if getuser() != "root":
-        confirm(
-            "WARNING: You are not running this command as 'root'. This command should be run under the same user as the API daemon, which is usually 'root'. Are you sure you want to continue?",
-            prompt_suffix=" ",
-            abort=True,
-        )
-
-    # Load our YAML config
-    autobackup_config = get_autobackup_config(CLI_CONFIG, autobackup_cfgfile)
-
-    # Get a list of all VMs on the cluster
-    # We don't do tag filtering here, because we could match an arbitrary number of tags; instead, we
-    # parse the list after
-    retcode, retdata = pvc.lib.vm.vm_list(CLI_CONFIG, None, None, None, None, None)
-    if not retcode:
-        echo(CLI_CONFIG, f"ERROR: Failed to fetch VM list: {retdata}")
-        exit(1)
-    cluster_vms = retdata
-
-    # Parse the list to match tags; too complex for list comprehension alas
-    backup_vms = list()
-    for vm in cluster_vms:
-        vm_tag_names = [t["name"] for t in vm["tags"]]
-        matching_tags = (
-            True
-            if len(
-                set(vm_tag_names).intersection(set(autobackup_config["backup_tags"]))
-            )
-            > 0
-            else False
-        )
-        if matching_tags:
-            backup_vms.append(vm["name"])
-
-    if len(backup_vms) < 1:
-        echo(CLI_CONFIG, "Found no suitable VMs for autobackup.")
-        exit(0)
-
-    # Pretty print the names of the VMs we'll back up (to stderr)
-    maxnamelen = max([len(n) for n in backup_vms]) + 2
-    cols = 1
-    while (cols * maxnamelen + maxnamelen + 2) <= MAX_CONTENT_WIDTH:
-        cols += 1
-    rows = len(backup_vms) // cols
-    vm_list_rows = list()
-    for row in range(0, rows + 1):
-        row_start = row * cols
-        row_end = (row * cols) + cols
-        row_str = ""
-        for x in range(row_start, row_end):
-            if x < len(backup_vms):
-                row_str += "{:<{}}".format(backup_vms[x], maxnamelen)
-        vm_list_rows.append(row_str)
-
-    echo(CLI_CONFIG, f"Found {len(backup_vms)} suitable VM(s) for autobackup.")
-    echo(CLI_CONFIG, "Full VM list:", stderr=True)
-    echo(CLI_CONFIG, "  {}".format("\n  ".join(vm_list_rows)), stderr=True)
-    echo(CLI_CONFIG, "", stderr=True)
-
-    if autobackup_config["auto_mount_enabled"]:
-        # Execute each mount_cmds command in sequence
-        for cmd in autobackup_config["mount_cmds"]:
-            echo(
-                CLI_CONFIG,
-                f"Executing mount command '{cmd.split()[0]}'... ",
-                newline=False,
-            )
-            tstart = datetime.now()
-            ret = run(
-                cmd.split(),
-                stdout=PIPE,
-                stderr=PIPE,
-            )
-            tend = datetime.now()
-            ttot = tend - tstart
-            if ret.returncode != 0:
-                echo(
-                    CLI_CONFIG,
-                    f"failed. [{ttot.seconds}s]",
-                )
-                echo(
-                    CLI_CONFIG,
-                    f"Exiting; command reports: {ret.stderr.decode().strip()}",
-                )
-                exit(1)
-            else:
-                echo(CLI_CONFIG, f"done. [{ttot.seconds}s]")
-
-    # For each VM, perform the backup
-    for vm in backup_vms:
-        backup_suffixed_path = f"{autobackup_config['backup_root_path']}{autobackup_config['backup_root_suffix']}"
-        if not path.exists(backup_suffixed_path):
-            makedirs(backup_suffixed_path)
-
-        backup_path = f"{backup_suffixed_path}/{vm}"
-        autobackup_state_file = f"{backup_path}/.autobackup.json"
-        if not path.exists(backup_path) or not path.exists(autobackup_state_file):
-            # There are no new backups so the list is empty
-            state_data = dict()
-            tracked_backups = list()
-        else:
-            with open(autobackup_state_file) as fh:
-                state_data = jload(fh)
-            tracked_backups = state_data["tracked_backups"]
-
-        full_interval = autobackup_config["backup_schedule"]["full_interval"]
-        full_retention = autobackup_config["backup_schedule"]["full_retention"]
-
-        full_backups = [b for b in tracked_backups if b["type"] == "full"]
-        if len(full_backups) > 0:
-            last_full_backup = full_backups[0]
-            last_full_backup_idx = tracked_backups.index(last_full_backup)
-            if force_full_flag:
-                this_backup_type = "forced-full"
-                this_backup_incremental_parent = None
-                this_backup_retain_snapshot = True
-            elif last_full_backup_idx >= full_interval - 1:
-                this_backup_type = "full"
-                this_backup_incremental_parent = None
-                this_backup_retain_snapshot = True
-            else:
-                this_backup_type = "incremental"
-                this_backup_incremental_parent = last_full_backup["datestring"]
-                this_backup_retain_snapshot = False
-        else:
-            # The very first backup must be full to start the tree
-            this_backup_type = "full"
-            this_backup_incremental_parent = None
-            this_backup_retain_snapshot = True
-
-        # Perform the backup
-        echo(
-            CLI_CONFIG,
-            f"Backing up VM '{vm}' ({this_backup_type})... ",
-            newline=False,
-        )
-        tstart = datetime.now()
-        retcode, retdata = pvc.lib.vm.vm_backup(
-            CLI_CONFIG,
-            vm,
-            backup_suffixed_path,
-            incremental_parent=this_backup_incremental_parent,
-            retain_snapshot=this_backup_retain_snapshot,
-        )
-        tend = datetime.now()
-        ttot = tend - tstart
-        if not retcode:
-            echo(CLI_CONFIG, f"failed. [{ttot.seconds}s]")
-            echo(CLI_CONFIG, f"Skipping cleanups; command reports: {retdata}")
-            continue
-        else:
-            backup_datestring = findall(r"[0-9]{14}", retdata)[0]
-            echo(
-                CLI_CONFIG,
-                f"done. Backup '{backup_datestring}' created. [{ttot.seconds}s]",
-            )
-
-        # Read backup file to get details
-        backup_json_file = f"{backup_path}/{backup_datestring}/pvcbackup.json"
-        with open(backup_json_file) as fh:
-            backup_json = jload(fh)
-        backup = {
-            "datestring": backup_json["datestring"],
-            "type": backup_json["type"],
-            "parent": backup_json["incremental_parent"],
-            "retained_snapshot": backup_json["retained_snapshot"],
-        }
-        tracked_backups.insert(0, backup)
-
-        # Delete any full backups that are expired
-        marked_for_deletion = list()
-        found_full_count = 0
-        for backup in tracked_backups:
-            if backup["type"] == "full":
-                found_full_count += 1
-                if found_full_count > full_retention:
-                    marked_for_deletion.append(backup)
-
-        # Depete any incremental backups that depend on marked parents
-        for backup in tracked_backups:
-            if backup["type"] == "incremental" and backup["parent"] in [
-                b["datestring"] for b in marked_for_deletion
-            ]:
-                marked_for_deletion.append(backup)
-
-        # Execute deletes
-        for backup_to_delete in marked_for_deletion:
-            echo(
-                CLI_CONFIG,
-                f"Removing old VM '{vm}' backup '{backup_to_delete['datestring']}' ({backup_to_delete['type']})... ",
-                newline=False,
-            )
-            tstart = datetime.now()
-            retcode, retdata = pvc.lib.vm.vm_remove_backup(
-                CLI_CONFIG,
-                vm,
-                backup_suffixed_path,
-                backup_to_delete["datestring"],
-            )
-            tend = datetime.now()
-            ttot = tend - tstart
-            if not retcode:
-                echo(CLI_CONFIG, f"failed. [{ttot.seconds}s]")
-                echo(
-                    CLI_CONFIG,
-                    f"Skipping removal from tracked backups; command reports: {retdata}",
-                )
-                continue
-            else:
-                tracked_backups.remove(backup_to_delete)
-                echo(CLI_CONFIG, f"done. [{ttot.seconds}s]")
-
-        # Update tracked state information
-        state_data["tracked_backups"] = tracked_backups
-        with open(autobackup_state_file, "w") as fh:
-            jdump(state_data, fh)
-
-    if autobackup_config["auto_mount_enabled"]:
-        # Execute each unmount_cmds command in sequence
-        for cmd in autobackup_config["unmount_cmds"]:
-            echo(
-                CLI_CONFIG,
-                f"Executing unmount command '{cmd.split()[0]}'... ",
-                newline=False,
-            )
-            tstart = datetime.now()
-            ret = run(
-                cmd.split(),
-                stdout=PIPE,
-                stderr=PIPE,
-            )
-            tend = datetime.now()
-            ttot = tend - tstart
-            if ret.returncode != 0:
-                echo(
-                    CLI_CONFIG,
-                    f"failed. [{ttot.seconds}s]",
-                )
-                echo(
-                    CLI_CONFIG,
-                    f"Continuing; command reports: {ret.stderr.decode().strip()}",
-                )
-            else:
-                echo(CLI_CONFIG, f"done. [{ttot.seconds}s]")

client-cli/pvc/cli/parsers.py

@@ -3,7 +3,7 @@
 # parsers.py - PVC Click CLI data parser function library
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2023 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -68,7 +68,8 @@ def cli_connection_list_parser(connections_config, show_keys_flag):
                 }
             )
 
-    return connections_data
+    # Return, ensuring local is always first
+    return sorted(connections_data, key=lambda x: (x.get("name") != "local"))
 
 
 def cli_connection_detail_parser(connections_config):
@@ -121,4 +122,5 @@ def cli_connection_detail_parser(connections_config):
                 }
             )
 
-    return connections_data
+    # Return, ensuring local is always first
+    return sorted(connections_data, key=lambda x: (x.get("name") != "local"))

client-cli/pvc/cli/waiters.py

@@ -3,7 +3,7 @@
 # waiters.py - PVC Click CLI output waiters library
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2023 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -19,6 +19,8 @@
 #
 ###############################################################################
 
+import sys
+
 from click import progressbar
 from time import sleep, time
 
@@ -105,7 +107,7 @@ def wait_for_celery_task(CLI_CONFIG, task_detail, start_late=False):
 
     # Start following the task state, updating progress as we go
     total_task = task_status.get("total")
-    with progressbar(length=total_task, show_eta=False) as bar:
+    with progressbar(length=total_task, width=20, show_eta=False) as bar:
         last_task = 0
         maxlen = 21
         echo(
@@ -115,26 +117,39 @@ def wait_for_celery_task(CLI_CONFIG, task_detail, start_late=False):
         )
         while True:
             sleep(0.5)
-            if task_status.get("state") != "RUNNING":
-                break
-            if task_status.get("current") > last_task:
-                current_task = int(task_status.get("current"))
-                bar.update(current_task - last_task)
-                last_task = current_task
-                # The extensive spaces at the end cause this to overwrite longer previous messages
-                curlen = len(str(task_status.get("status")))
-                if curlen > maxlen:
-                    maxlen = curlen
-                lendiff = maxlen - curlen
-                overwrite_whitespace = " " * lendiff
-                echo(
-                    CLI_CONFIG,
-                    "  " + task_status.get("status") + overwrite_whitespace,
-                    newline=False,
-                )
+
             task_status = pvc.lib.common.task_status(
                 CLI_CONFIG, task_id=task_id, is_watching=True
             )
+
+            if isinstance(task_status, tuple):
+                continue
+            if task_status.get("state") != "RUNNING":
+                break
+            if task_status.get("current") == 0:
+                continue
+
+            current_task = int(task_status.get("current"))
+            total_task = int(task_status.get("total"))
+            bar.length = total_task
+
+            if current_task > last_task:
+                bar.update(current_task - last_task)
+                last_task = current_task
+
+            curlen = len(str(task_status.get("status")))
+            if curlen > maxlen:
+                maxlen = curlen
+            lendiff = maxlen - curlen
+            overwrite_whitespace = " " * lendiff
+
+            percent_complete = (current_task / total_task) * 100
+            bar_output = f"[{bar.format_bar()}]  {percent_complete:3.0f}%"
+            sys.stdout.write(
+                f"\r  {bar_output}  {task_status['status']}{overwrite_whitespace}"
+            )
+            sys.stdout.flush()
+
         if task_status.get("state") == "SUCCESS":
             bar.update(total_task - last_task)
 

client-cli/pvc/lib/ansiprint.py

@@ -3,7 +3,7 @@
 # ansiprint.py - Printing function for formatted messages
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

client-cli/pvc/lib/cluster.py

@@ -3,7 +3,7 @@
 # cluster.py - PVC CLI client function library, cluster management
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -21,6 +21,8 @@
 
 import json
 
+from time import sleep
+
 from pvc.lib.common import call_api
 
 
@@ -114,3 +116,22 @@ def get_info(config):
         return True, response.json()
     else:
         return False, response.json().get("message", "")
+
+
+def get_primary_node(config):
+    """
+    Get the current primary node of the PVC cluster
+
+    API endpoint: GET /api/v1/status/primary_node
+    API arguments:
+    API schema: {json_data_object}
+    """
+    while True:
+        response = call_api(config, "get", "/status/primary_node")
+        resp_code = response.status_code
+        if resp_code == 200:
+            break
+        else:
+            sleep(1)
+
+    return True, response.json()["primary_node"]

client-cli/pvc/lib/common.py

@@ -3,7 +3,7 @@
 # common.py - PVC CLI client function library, Common functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -83,7 +83,7 @@ class UploadProgressBar(object):
         else:
             self.end_suffix = ""
 
-        self.bar = click.progressbar(length=self.length, show_eta=True)
+        self.bar = click.progressbar(length=self.length, width=20, show_eta=True)
 
     def update(self, monitor):
         bytes_cur = monitor.bytes_read
@@ -108,9 +108,10 @@ class UploadProgressBar(object):
 
 
 class ErrorResponse(requests.Response):
-    def __init__(self, json_data, status_code):
+    def __init__(self, json_data, status_code, headers):
         self.json_data = json_data
         self.status_code = status_code
+        self.headers = headers
 
     def json(self):
         return self.json_data
@@ -140,15 +141,32 @@ def call_api(
     # Determine the request type and hit the API
     disable_warnings()
     try:
+        response = None
         if operation == "get":
-            response = requests.get(
-                uri,
-                timeout=timeout,
-                headers=headers,
-                params=params,
-                data=data,
-                verify=config["verify_ssl"],
-            )
+            retry_on_code = [429, 500, 502, 503, 504]
+            for i in range(3):
+                failed = False
+                try:
+                    response = requests.get(
+                        uri,
+                        timeout=timeout,
+                        headers=headers,
+                        params=params,
+                        data=data,
+                        verify=config["verify_ssl"],
+                    )
+                    if response.status_code in retry_on_code:
+                        failed = True
+                        continue
+                    break
+                except requests.exceptions.ConnectionError:
+                    failed = True
+                    continue
+            if failed:
+                error = f"Code {response.status_code}" if response else "Timeout"
+                raise requests.exceptions.ConnectionError(
+                    f"Failed to connect after 3 tries ({error})"
+                )
         if operation == "post":
             response = requests.post(
                 uri,
@@ -189,7 +207,8 @@ def call_api(
             )
     except Exception as e:
         message = "Failed to connect to the API: {}".format(e)
-        response = ErrorResponse({"message": message}, 500)
+        code = response.status_code if response else 504
+        response = ErrorResponse({"message": message}, code, None)
 
     # Display debug output
     if config["debug"]:

client-cli/pvc/lib/faults.py

@@ -3,7 +3,7 @@
 # faults.py - PVC CLI client function library, faults management
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

client-cli/pvc/lib/network.py

@@ -3,7 +3,7 @@
 # network.py - PVC CLI client function library, Network functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

client-cli/pvc/lib/node.py

@@ -3,7 +3,7 @@
 # node.py - PVC CLI client function library, node management
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

client-cli/pvc/lib/provisioner.py

@@ -3,7 +3,7 @@
 # provisioner.py - PVC CLI client function library, Provisioner functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -779,7 +779,8 @@ def format_list_template_system(template_data):
     template_node_limit_length = 6
     template_node_selector_length = 9
     template_node_autostart_length = 10
-    template_migration_method_length = 10
+    template_migration_method_length = 12
+    template_migration_max_downtime_length = 13
 
     for template in template_data:
         # template_name column
@@ -826,6 +827,17 @@ def format_list_template_system(template_data):
         _template_migration_method_length = len(str(template["migration_method"])) + 1
         if _template_migration_method_length > template_migration_method_length:
             template_migration_method_length = _template_migration_method_length
+        # template_migration_max_downtime column
+        _template_migration_max_downtime_length = (
+            len(str(template["migration_max_downtime"])) + 1
+        )
+        if (
+            _template_migration_max_downtime_length
+            > template_migration_max_downtime_length
+        ):
+            template_migration_max_downtime_length = (
+                _template_migration_max_downtime_length
+            )
 
     # Format the string (header)
     template_list_output.append(
@@ -842,7 +854,8 @@ def format_list_template_system(template_data):
             + template_node_selector_length
             + template_node_autostart_length
             + template_migration_method_length
-            + 3,
+            + template_migration_max_downtime_length
+            + 4,
             template_header="System Templates "
             + "".join(
                 ["-" for _ in range(17, template_name_length + template_id_length)]
@@ -874,7 +887,8 @@ def format_list_template_system(template_data):
                         + template_node_selector_length
                         + template_node_autostart_length
                         + template_migration_method_length
-                        + 2,
+                        + template_migration_max_downtime_length
+                        + 3,
                     )
                 ]
             ),
@@ -891,7 +905,8 @@ def format_list_template_system(template_data):
 {template_node_limit: <{template_node_limit_length}} \
 {template_node_selector: <{template_node_selector_length}} \
 {template_node_autostart: <{template_node_autostart_length}} \
-{template_migration_method: <{template_migration_method_length}}{end_bold}".format(
+{template_migration_method: <{template_migration_method_length}} \
+{template_migration_max_downtime: <{template_migration_max_downtime_length}}{end_bold}".format(
             bold=ansiprint.bold(),
             end_bold=ansiprint.end(),
             template_name_length=template_name_length,
@@ -905,6 +920,7 @@ def format_list_template_system(template_data):
             template_node_selector_length=template_node_selector_length,
             template_node_autostart_length=template_node_autostart_length,
             template_migration_method_length=template_migration_method_length,
+            template_migration_max_downtime_length=template_migration_max_downtime_length,
             template_name="Name",
             template_id="ID",
             template_vcpu="vCPUs",
@@ -915,7 +931,8 @@ def format_list_template_system(template_data):
             template_node_limit="Limit",
             template_node_selector="Selector",
             template_node_autostart="Autostart",
-            template_migration_method="Migration",
+            template_migration_method="Mig. Method",
+            template_migration_max_downtime="Max Downtime",
         )
     )
 
@@ -931,7 +948,8 @@ def format_list_template_system(template_data):
 {template_node_limit: <{template_node_limit_length}} \
 {template_node_selector: <{template_node_selector_length}} \
 {template_node_autostart: <{template_node_autostart_length}} \
-{template_migration_method: <{template_migration_method_length}}{end_bold}".format(
+{template_migration_method: <{template_migration_method_length}} \
+{template_migration_max_downtime: <{template_migration_max_downtime_length}}{end_bold}".format(
                 template_name_length=template_name_length,
                 template_id_length=template_id_length,
                 template_vcpu_length=template_vcpu_length,
@@ -943,6 +961,7 @@ def format_list_template_system(template_data):
                 template_node_selector_length=template_node_selector_length,
                 template_node_autostart_length=template_node_autostart_length,
                 template_migration_method_length=template_migration_method_length,
+                template_migration_max_downtime_length=template_migration_max_downtime_length,
                 bold="",
                 end_bold="",
                 template_name=str(template["name"]),
@@ -956,6 +975,7 @@ def format_list_template_system(template_data):
                 template_node_selector=str(template["node_selector"]),
                 template_node_autostart=str(template["node_autostart"]),
                 template_migration_method=str(template["migration_method"]),
+                template_migration_max_downtime=f"{str(template['migration_max_downtime'])} ms",
             )
         )
 

client-cli/pvc/lib/storage.py

@@ -3,7 +3,7 @@
 # ceph.py - PVC CLI client function library, Ceph cluster functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -30,6 +30,7 @@ from requests_toolbelt.multipart.encoder import (
 
 import pvc.lib.ansiprint as ansiprint
 from pvc.lib.common import UploadProgressBar, call_api, get_wait_retdata
+from pvc.cli.helpers import MAX_CONTENT_WIDTH
 
 #
 # Supplemental functions
@@ -430,7 +431,9 @@ def format_list_osd(config, osd_list):
             )
             continue
 
-        if osd_information["is_split"]:
+        if osd_information.get("is_split") is not None and osd_information.get(
+            "is_split"
+        ):
             osd_information["device"] = f"{osd_information['device']} [s]"
 
         # Deal with the size to human readable
@@ -1172,15 +1175,15 @@ def ceph_volume_list(config, limit, pool):
         return False, response.json().get("message", "")
 
 
-def ceph_volume_add(config, pool, volume, size):
+def ceph_volume_add(config, pool, volume, size, force_flag=False):
     """
     Add new Ceph volume
 
     API endpoint: POST /api/v1/storage/ceph/volume
-    API arguments: volume={volume}, pool={pool}, size={size}
+    API arguments: volume={volume}, pool={pool}, size={size}, force={force_flag}
     API schema: {"message":"{data}"}
     """
-    params = {"volume": volume, "pool": pool, "size": size}
+    params = {"volume": volume, "pool": pool, "size": size, "force": force_flag}
     response = call_api(config, "post", "/storage/ceph/volume", params=params)
 
     if response.status_code == 200:
@@ -1261,12 +1264,14 @@ def ceph_volume_remove(config, pool, volume):
     return retstatus, response.json().get("message", "")
 
 
-def ceph_volume_modify(config, pool, volume, new_name=None, new_size=None):
+def ceph_volume_modify(
+    config, pool, volume, new_name=None, new_size=None, force_flag=False
+):
     """
     Modify Ceph volume
 
     API endpoint: PUT /api/v1/storage/ceph/volume/{pool}/{volume}
-    API arguments:
+    API arguments: [new_name={new_name}], [new_size={new_size}], force_flag={force_flag}
     API schema: {"message":"{data}"}
     """
 
@@ -1275,6 +1280,7 @@ def ceph_volume_modify(config, pool, volume, new_name=None, new_size=None):
         params["new_name"] = new_name
     if new_size:
         params["new_size"] = new_size
+        params["force"] = force_flag
 
     response = call_api(
         config,
@@ -1291,15 +1297,15 @@ def ceph_volume_modify(config, pool, volume, new_name=None, new_size=None):
     return retstatus, response.json().get("message", "")
 
 
-def ceph_volume_clone(config, pool, volume, new_volume):
+def ceph_volume_clone(config, pool, volume, new_volume, force_flag=False):
     """
     Clone Ceph volume
 
     API endpoint: POST /api/v1/storage/ceph/volume/{pool}/{volume}
-    API arguments: new_volume={new_volume
+    API arguments: new_volume={new_volume, force_flag={force_flag}
     API schema: {"message":"{data}"}
     """
-    params = {"new_volume": new_volume}
+    params = {"new_volume": new_volume, "force_flag": force_flag}
     response = call_api(
         config,
         "post",
@@ -1539,6 +1545,30 @@ def ceph_snapshot_add(config, pool, volume, snapshot):
     return retstatus, response.json().get("message", "")
 
 
+def ceph_snapshot_rollback(config, pool, volume, snapshot):
+    """
+    Roll back Ceph volume to snapshot
+
+    API endpoint: POST /api/v1/storage/ceph/snapshot/{pool}/{volume}/{snapshot}/rollback
+    API arguments:
+    API schema: {"message":"{data}"}
+    """
+    response = call_api(
+        config,
+        "post",
+        "/storage/ceph/snapshot/{pool}/{volume}/{snapshot}/rollback".format(
+            snapshot=snapshot, volume=volume, pool=pool
+        ),
+    )
+
+    if response.status_code == 200:
+        retstatus = True
+    else:
+        retstatus = False
+
+    return retstatus, response.json().get("message", "")
+
+
 def ceph_snapshot_remove(config, pool, volume, snapshot):
     """
     Remove Ceph snapshot
@@ -1695,15 +1725,17 @@ def format_list_snapshot(config, snapshot_list):
 #
 # Benchmark functions
 #
-def ceph_benchmark_run(config, pool, wait_flag):
+def ceph_benchmark_run(config, pool, name, wait_flag):
     """
     Run a storage benchmark against {pool}
 
     API endpoint: POST /api/v1/storage/ceph/benchmark
-    API arguments: pool={pool}
+    API arguments: pool={pool}, name={name}
     API schema: {message}
     """
     params = {"pool": pool}
+    if name:
+        params["name"] = name
     response = call_api(config, "post", "/storage/ceph/benchmark", params=params)
 
     return get_wait_retdata(response, wait_flag)
@@ -1775,7 +1807,7 @@ def get_benchmark_list_results(benchmark_format, benchmark_data):
         benchmark_bandwidth, benchmark_iops = get_benchmark_list_results_legacy(
             benchmark_data
         )
-    elif benchmark_format == 1:
+    elif benchmark_format == 1 or benchmark_format == 2:
         benchmark_bandwidth, benchmark_iops = get_benchmark_list_results_json(
             benchmark_data
         )
@@ -1977,6 +2009,7 @@ def format_info_benchmark(config, benchmark_information):
     benchmark_matrix = {
         0: format_info_benchmark_legacy,
         1: format_info_benchmark_json,
+        2: format_info_benchmark_json,
     }
 
     benchmark_version = benchmark_information[0]["test_format"]
@@ -2311,12 +2344,15 @@ def format_info_benchmark_json(config, benchmark_information):
     if benchmark_information["benchmark_result"] == "Running":
         return "Benchmark test is still running."
 
+    benchmark_format = benchmark_information["test_format"]
     benchmark_details = benchmark_information["benchmark_result"]
 
     # Format a nice output; do this line-by-line then concat the elements at the end
     ainformation = []
     ainformation.append(
-        "{}Storage Benchmark details:{}".format(ansiprint.bold(), ansiprint.end())
+        "{}Storage Benchmark details (format {}):{}".format(
+            ansiprint.bold(), benchmark_format, ansiprint.end()
+        )
     )
 
     nice_test_name_map = {
@@ -2364,7 +2400,7 @@ def format_info_benchmark_json(config, benchmark_information):
             if element[1] != 0:
                 useful_latency_tree.append(element)
 
-        max_rows = 9
+        max_rows = 5
         if len(useful_latency_tree) > 9:
             max_rows = len(useful_latency_tree)
         elif len(useful_latency_tree) < 9:
@@ -2373,15 +2409,10 @@ def format_info_benchmark_json(config, benchmark_information):
 
         # Format the static data
         overall_label = [
-            "Overall BW/s:",
-            "Overall IOPS:",
-            "Total I/O:",
-            "Runtime (s):",
-            "User CPU %:",
-            "System CPU %:",
-            "Ctx Switches:",
-            "Major Faults:",
-            "Minor Faults:",
+            "BW/s:",
+            "IOPS:",
+            "I/O:",
+            "Time:",
         ]
         while len(overall_label) < max_rows:
             overall_label.append("")
@@ -2390,68 +2421,149 @@ def format_info_benchmark_json(config, benchmark_information):
             format_bytes_tohuman(int(job_details[io_class]["bw_bytes"])),
             format_ops_tohuman(int(job_details[io_class]["iops"])),
             format_bytes_tohuman(int(job_details[io_class]["io_bytes"])),
-            job_details["job_runtime"] / 1000,
-            job_details["usr_cpu"],
-            job_details["sys_cpu"],
-            job_details["ctx"],
-            job_details["majf"],
-            job_details["minf"],
+            str(job_details["job_runtime"] / 1000) + "s",
         ]
         while len(overall_data) < max_rows:
             overall_data.append("")
 
+        cpu_label = [
+            "Total:",
+            "User:",
+            "Sys:",
+            "OSD:",
+            "MON:",
+        ]
+        while len(cpu_label) < max_rows:
+            cpu_label.append("")
+
+        cpu_data = [
+            (
+                benchmark_details[test]["avg_cpu_util_percent"]["total"]
+                if benchmark_format > 1
+                else "N/A"
+            ),
+            round(job_details["usr_cpu"], 2),
+            round(job_details["sys_cpu"], 2),
+            (
+                benchmark_details[test]["avg_cpu_util_percent"]["ceph-osd"]
+                if benchmark_format > 1
+                else "N/A"
+            ),
+            (
+                benchmark_details[test]["avg_cpu_util_percent"]["ceph-mon"]
+                if benchmark_format > 1
+                else "N/A"
+            ),
+        ]
+        while len(cpu_data) < max_rows:
+            cpu_data.append("")
+
+        memory_label = [
+            "Total:",
+            "OSD:",
+            "MON:",
+        ]
+        while len(memory_label) < max_rows:
+            memory_label.append("")
+
+        memory_data = [
+            (
+                benchmark_details[test]["avg_memory_util_percent"]["total"]
+                if benchmark_format > 1
+                else "N/A"
+            ),
+            (
+                benchmark_details[test]["avg_memory_util_percent"]["ceph-osd"]
+                if benchmark_format > 1
+                else "N/A"
+            ),
+            (
+                benchmark_details[test]["avg_memory_util_percent"]["ceph-mon"]
+                if benchmark_format > 1
+                else "N/A"
+            ),
+        ]
+        while len(memory_data) < max_rows:
+            memory_data.append("")
+
+        network_label = [
+            "Total:",
+            "Sent:",
+            "Recv:",
+        ]
+        while len(network_label) < max_rows:
+            network_label.append("")
+
+        network_data = [
+            (
+                format_bytes_tohuman(
+                    int(benchmark_details[test]["avg_network_util_bps"]["total"])
+                )
+                if benchmark_format > 1
+                else "N/A"
+            ),
+            (
+                format_bytes_tohuman(
+                    int(benchmark_details[test]["avg_network_util_bps"]["sent"])
+                )
+                if benchmark_format > 1
+                else "N/A"
+            ),
+            (
+                format_bytes_tohuman(
+                    int(benchmark_details[test]["avg_network_util_bps"]["recv"])
+                )
+                if benchmark_format > 1
+                else "N/A"
+            ),
+        ]
+        while len(network_data) < max_rows:
+            network_data.append("")
+
         bandwidth_label = [
             "Min:",
             "Max:",
             "Mean:",
             "StdDev:",
             "Samples:",
-            "",
-            "",
-            "",
-            "",
         ]
         while len(bandwidth_label) < max_rows:
             bandwidth_label.append("")
 
         bandwidth_data = [
-            format_bytes_tohuman(int(job_details[io_class]["bw_min"]) * 1024),
-            format_bytes_tohuman(int(job_details[io_class]["bw_max"]) * 1024),
-            format_bytes_tohuman(int(job_details[io_class]["bw_mean"]) * 1024),
-            format_bytes_tohuman(int(job_details[io_class]["bw_dev"]) * 1024),
-            job_details[io_class]["bw_samples"],
-            "",
-            "",
-            "",
-            "",
+            format_bytes_tohuman(int(job_details[io_class]["bw_min"]) * 1024)
+            + " / "
+            + format_ops_tohuman(int(job_details[io_class]["iops_min"])),
+            format_bytes_tohuman(int(job_details[io_class]["bw_max"]) * 1024)
+            + " / "
+            + format_ops_tohuman(int(job_details[io_class]["iops_max"])),
+            format_bytes_tohuman(int(job_details[io_class]["bw_mean"]) * 1024)
+            + " / "
+            + format_ops_tohuman(int(job_details[io_class]["iops_mean"])),
+            format_bytes_tohuman(int(job_details[io_class]["bw_dev"]) * 1024)
+            + " / "
+            + format_ops_tohuman(int(job_details[io_class]["iops_stddev"])),
+            str(job_details[io_class]["bw_samples"])
+            + " / "
+            + str(job_details[io_class]["iops_samples"]),
         ]
         while len(bandwidth_data) < max_rows:
             bandwidth_data.append("")
 
-        iops_data = [
-            format_ops_tohuman(int(job_details[io_class]["iops_min"])),
-            format_ops_tohuman(int(job_details[io_class]["iops_max"])),
-            format_ops_tohuman(int(job_details[io_class]["iops_mean"])),
-            format_ops_tohuman(int(job_details[io_class]["iops_stddev"])),
-            job_details[io_class]["iops_samples"],
-            "",
-            "",
-            "",
-            "",
+        lat_label = [
+            "Min:",
+            "Max:",
+            "Mean:",
+            "StdDev:",
         ]
-        while len(iops_data) < max_rows:
-            iops_data.append("")
+        while len(lat_label) < max_rows:
+            lat_label.append("")
 
         lat_data = [
             int(job_details[io_class]["lat_ns"]["min"]) / 1000,
             int(job_details[io_class]["lat_ns"]["max"]) / 1000,
             int(job_details[io_class]["lat_ns"]["mean"]) / 1000,
             int(job_details[io_class]["lat_ns"]["stddev"]) / 1000,
-            "",
-            "",
-            "",
-            "",
-            "",
         ]
         while len(lat_data) < max_rows:
             lat_data.append("")
@@ -2460,98 +2572,119 @@ def format_info_benchmark_json(config, benchmark_information):
         lat_bucket_label = list()
         lat_bucket_data = list()
         for element in useful_latency_tree:
-            lat_bucket_label.append(element[0])
-            lat_bucket_data.append(element[1])
+            lat_bucket_label.append(element[0] + ":" if element[0] else "")
+            lat_bucket_data.append(round(float(element[1]), 2) if element[1] else "")
+        while len(lat_bucket_label) < max_rows:
+            lat_bucket_label.append("")
+        while len(lat_bucket_data) < max_rows:
+            lat_bucket_label.append("")
 
         # Column default widths
-        overall_label_length = 0
+        overall_label_length = 5
         overall_column_length = 0
-        bandwidth_label_length = 0
-        bandwidth_column_length = 11
-        iops_column_length = 4
-        latency_column_length = 12
+        cpu_label_length = 6
+        cpu_column_length = 0
+        memory_label_length = 6
+        memory_column_length = 0
+        network_label_length = 6
+        network_column_length = 6
+        bandwidth_label_length = 8
+        bandwidth_column_length = 0
+        latency_label_length = 7
+        latency_column_length = 0
         latency_bucket_label_length = 0
+        latency_bucket_column_length = 0
 
         # Column layout:
-        #    General    Bandwidth   IOPS      Latency   Percentiles
-        #    ---------  ----------  --------  --------  ---------------
-        #    Size       Min         Min       Min       A
-        #    BW         Max         Max       Max       B
-        #    IOPS       Mean        Mean      Mean      ...
-        #    Runtime    StdDev      StdDev    StdDev    Z
-        #    UsrCPU     Samples     Samples
-        #    SysCPU
-        #    CtxSw
-        #    MajFault
-        #    MinFault
+        #    Overall    CPU   Memory  Network  Bandwidth/IOPS  Latency   Percentiles
+        #    ---------  ----- ------- -------- --------------  --------  ---------------
+        #    BW         Total Total   Total    Min             Min       A
+        #    IOPS       Usr   OSD     Send     Max             Max       B
+        #    Time       Sys   MON     Recv     Mean            Mean      ...
+        #    Size       OSD                    StdDev          StdDev    Z
+        #               MON                    Samples
 
         # Set column widths
-        for item in overall_label:
-            _item_length = len(str(item))
-            if _item_length > overall_label_length:
-                overall_label_length = _item_length
-
         for item in overall_data:
             _item_length = len(str(item))
             if _item_length > overall_column_length:
                 overall_column_length = _item_length
 
-        test_name_length = len(nice_test_name_map[test])
-        if test_name_length > overall_label_length + overall_column_length:
-            _diff = test_name_length - (overall_label_length + overall_column_length)
-            overall_column_length += _diff
-
-        for item in bandwidth_label:
+        for item in cpu_data:
             _item_length = len(str(item))
-            if _item_length > bandwidth_label_length:
-                bandwidth_label_length = _item_length
+            if _item_length > cpu_column_length:
+                cpu_column_length = _item_length
+
+        for item in memory_data:
+            _item_length = len(str(item))
+            if _item_length > memory_column_length:
+                memory_column_length = _item_length
+
+        for item in network_data:
+            _item_length = len(str(item))
+            if _item_length > network_column_length:
+                network_column_length = _item_length
 
         for item in bandwidth_data:
             _item_length = len(str(item))
             if _item_length > bandwidth_column_length:
                 bandwidth_column_length = _item_length
 
-        for item in iops_data:
-            _item_length = len(str(item))
-            if _item_length > iops_column_length:
-                iops_column_length = _item_length
-
         for item in lat_data:
             _item_length = len(str(item))
             if _item_length > latency_column_length:
                 latency_column_length = _item_length
 
-        for item in lat_bucket_label:
+        for item in lat_bucket_data:
             _item_length = len(str(item))
-            if _item_length > latency_bucket_label_length:
-                latency_bucket_label_length = _item_length
+            if _item_length > latency_bucket_column_length:
+                latency_bucket_column_length = _item_length
 
         # Top row (Headers)
         ainformation.append(
-            "{bold}\
-{overall_label: <{overall_label_length}}    \
-{bandwidth_label: <{bandwidth_label_length}} \
-{bandwidth: <{bandwidth_length}}   \
-{iops: <{iops_length}}   \
-{latency: <{latency_length}}   \
-{latency_bucket_label: <{latency_bucket_label_length}} \
-{latency_bucket} \
-{end_bold}".format(
+            "{bold}{overall_label: <{overall_label_length}} {header_fill}{end_bold}".format(
                 bold=ansiprint.bold(),
                 end_bold=ansiprint.end(),
                 overall_label=nice_test_name_map[test],
                 overall_label_length=overall_label_length,
-                bandwidth_label="",
-                bandwidth_label_length=bandwidth_label_length,
-                bandwidth="Bandwidth/s",
-                bandwidth_length=bandwidth_column_length,
-                iops="IOPS",
-                iops_length=iops_column_length,
-                latency="Latency (μs)",
-                latency_length=latency_column_length,
-                latency_bucket_label="Latency Buckets (μs/%)",
-                latency_bucket_label_length=latency_bucket_label_length,
-                latency_bucket="",
+                header_fill="-"
+                * (
+                    (MAX_CONTENT_WIDTH if MAX_CONTENT_WIDTH <= 120 else 120)
+                    - len(nice_test_name_map[test])
+                    - 4
+                ),
+            )
+        )
+
+        ainformation.append(
+            "{bold}\
+{overall_label: <{overall_label_length}}  \
+{cpu_label: <{cpu_label_length}}  \
+{memory_label: <{memory_label_length}}  \
+{network_label: <{network_label_length}}  \
+{bandwidth_label: <{bandwidth_label_length}}  \
+{latency_label: <{latency_label_length}}  \
+{latency_bucket_label: <{latency_bucket_label_length}}\
+{end_bold}".format(
+                bold=ansiprint.bold(),
+                end_bold=ansiprint.end(),
+                overall_label="Overall",
+                overall_label_length=overall_label_length + overall_column_length + 1,
+                cpu_label="CPU (%)",
+                cpu_label_length=cpu_label_length + cpu_column_length + 1,
+                memory_label="Memory (%)",
+                memory_label_length=memory_label_length + memory_column_length + 1,
+                network_label="Network (bps)",
+                network_label_length=network_label_length + network_column_length + 1,
+                bandwidth_label="Bandwidth / IOPS",
+                bandwidth_label_length=bandwidth_label_length
+                + bandwidth_column_length
+                + 1,
+                latency_label="Latency (μs)",
+                latency_label_length=latency_label_length + latency_column_length + 1,
+                latency_bucket_label="Buckets (μs/%)",
+                latency_bucket_label_length=latency_bucket_label_length
+                + latency_bucket_column_length,
             )
         )
 
@@ -2559,14 +2692,20 @@ def format_info_benchmark_json(config, benchmark_information):
             # Top row (Headers)
             ainformation.append(
                 "{bold}\
-{overall_label: >{overall_label_length}} \
-{overall: <{overall_length}}   \
-{bandwidth_label: >{bandwidth_label_length}} \
-{bandwidth: <{bandwidth_length}}   \
-{iops: <{iops_length}}   \
-{latency: <{latency_length}}   \
-{latency_bucket_label: >{latency_bucket_label_length}} \
-{latency_bucket} \
+{overall_label: <{overall_label_length}} \
+{overall: <{overall_length}}  \
+{cpu_label: <{cpu_label_length}} \
+{cpu: <{cpu_length}}  \
+{memory_label: <{memory_label_length}} \
+{memory: <{memory_length}}  \
+{network_label: <{network_label_length}} \
+{network: <{network_length}}  \
+{bandwidth_label: <{bandwidth_label_length}} \
+{bandwidth: <{bandwidth_length}}  \
+{latency_label: <{latency_label_length}} \
+{latency: <{latency_length}}  \
+{latency_bucket_label: <{latency_bucket_label_length}} \
+{latency_bucket}\
 {end_bold}".format(
                     bold="",
                     end_bold="",
@@ -2574,12 +2713,24 @@ def format_info_benchmark_json(config, benchmark_information):
                     overall_label_length=overall_label_length,
                     overall=overall_data[idx],
                     overall_length=overall_column_length,
+                    cpu_label=cpu_label[idx],
+                    cpu_label_length=cpu_label_length,
+                    cpu=cpu_data[idx],
+                    cpu_length=cpu_column_length,
+                    memory_label=memory_label[idx],
+                    memory_label_length=memory_label_length,
+                    memory=memory_data[idx],
+                    memory_length=memory_column_length,
+                    network_label=network_label[idx],
+                    network_label_length=network_label_length,
+                    network=network_data[idx],
+                    network_length=network_column_length,
                     bandwidth_label=bandwidth_label[idx],
                     bandwidth_label_length=bandwidth_label_length,
                     bandwidth=bandwidth_data[idx],
                     bandwidth_length=bandwidth_column_length,
-                    iops=iops_data[idx],
-                    iops_length=iops_column_length,
+                    latency_label=lat_label[idx],
+                    latency_label_length=latency_label_length,
                     latency=lat_data[idx],
                     latency_length=latency_column_length,
                     latency_bucket_label=lat_bucket_label[idx],
@@ -2588,4 +2739,4 @@ def format_info_benchmark_json(config, benchmark_information):
                 )
             )
 
-    return "\n".join(ainformation)
+    return "\n".join(ainformation) + "\n"

client-cli/pvc/lib/vm.py

@@ -3,7 +3,7 @@
 # vm.py - PVC CLI client function library, VM functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -89,6 +89,7 @@ def vm_define(
     node_selector,
     node_autostart,
     migration_method,
+    migration_max_downtime,
     user_tags,
     protected_tags,
 ):
@@ -96,7 +97,7 @@ def vm_define(
     Define a new VM on the cluster
 
     API endpoint: POST /vm
-    API arguments: xml={xml}, node={node}, limit={node_limit}, selector={node_selector}, autostart={node_autostart}, migration_method={migration_method}, user_tags={user_tags}, protected_tags={protected_tags}
+    API arguments: xml={xml}, node={node}, limit={node_limit}, selector={node_selector}, autostart={node_autostart}, migration_method={migration_method}, migration_max_downtime={migration_max_downtime}, user_tags={user_tags}, protected_tags={protected_tags}
     API schema: {"message":"{data}"}
     """
     params = {
@@ -105,6 +106,7 @@ def vm_define(
         "selector": node_selector,
         "autostart": node_autostart,
         "migration_method": migration_method,
+        "migration_max_downtime": migration_max_downtime,
         "user_tags": user_tags,
         "protected_tags": protected_tags,
     }
@@ -205,6 +207,7 @@ def vm_metadata(
     node_selector,
     node_autostart,
     migration_method,
+    migration_max_downtime,
     provisioner_profile,
 ):
     """
@@ -229,6 +232,9 @@ def vm_metadata(
     if migration_method is not None:
         params["migration_method"] = migration_method
 
+    if migration_max_downtime is not None:
+        params["migration_max_downtime"] = migration_max_downtime
+
     if provisioner_profile is not None:
         params["profile"] = provisioner_profile
 
@@ -377,8 +383,8 @@ def vm_state(config, vm, target_state, force=False, wait=False):
     """
     params = {
         "state": target_state,
-        "force": str(force).lower(),
-        "wait": str(wait).lower(),
+        "force": force,
+        "wait": wait,
     }
     response = call_api(config, "post", "/vm/{vm}/state".format(vm=vm), params=params)
 
@@ -415,7 +421,7 @@ def vm_node(config, vm, target_node, action, force=False, wait=False, force_live
     return retstatus, response.json().get("message", "")
 
 
-def vm_locks(config, vm, wait_flag):
+def vm_locks(config, vm, wait_flag=True):
     """
     Flush RBD locks of (stopped) VM
 
@@ -492,6 +498,222 @@ def vm_restore(config, vm, backup_path, backup_datestring, retain_snapshot=False
         return True, response.json().get("message", "")
 
 
+def vm_create_snapshot(config, vm, snapshot_name=None, wait_flag=True):
+    """
+    Take a snapshot of a VM's disks and configuration
+
+    API endpoint: POST /vm/{vm}/snapshot
+    API arguments: snapshot_name=snapshot_name
+    API schema: {"message":"{data}"}
+    """
+    params = dict()
+    if snapshot_name is not None:
+        params["snapshot_name"] = snapshot_name
+    response = call_api(
+        config, "post", "/vm/{vm}/snapshot".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_remove_snapshot(config, vm, snapshot_name, wait_flag=True):
+    """
+    Remove a snapshot of a VM's disks and configuration
+
+    API endpoint: DELETE /vm/{vm}/snapshot
+    API arguments: snapshot_name=snapshot_name
+    API schema: {"message":"{data}"}
+    """
+    params = {"snapshot_name": snapshot_name}
+    response = call_api(
+        config, "delete", "/vm/{vm}/snapshot".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_rollback_snapshot(config, vm, snapshot_name, wait_flag=True):
+    """
+    Roll back to a snapshot of a VM's disks and configuration
+
+    API endpoint: POST /vm/{vm}/snapshot/rollback
+    API arguments: snapshot_name=snapshot_name
+    API schema: {"message":"{data}"}
+    """
+    params = {"snapshot_name": snapshot_name}
+    response = call_api(
+        config, "post", "/vm/{vm}/snapshot/rollback".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_export_snapshot(
+    config, vm, snapshot_name, export_path, incremental_parent=None, wait_flag=True
+):
+    """
+    Export an (existing) snapshot of a VM's disks and configuration to export_path, optionally
+    incremental with incremental_parent
+
+    API endpoint: POST /vm/{vm}/snapshot/export
+    API arguments: snapshot_name=snapshot_name, export_path=export_path, incremental_parent=incremental_parent
+    API schema: {"message":"{data}"}
+    """
+    params = {
+        "snapshot_name": snapshot_name,
+        "export_path": export_path,
+    }
+    if incremental_parent is not None:
+        params["incremental_parent"] = incremental_parent
+
+    response = call_api(
+        config, "post", "/vm/{vm}/snapshot/export".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_import_snapshot(
+    config, vm, snapshot_name, import_path, retain_snapshot=False, wait_flag=True
+):
+    """
+    Import a snapshot of {vm} and its volumes from a local primary coordinator filesystem path
+
+    API endpoint: POST /vm/{vm}/snapshot/import
+    API arguments: snapshot_name={snapshot_name}, import_path={import_path}, retain_snapshot={retain_snapshot}
+    API schema: {"message":"{data}"}
+    """
+    params = {
+        "snapshot_name": snapshot_name,
+        "import_path": import_path,
+        "retain_snapshot": retain_snapshot,
+    }
+    response = call_api(
+        config, "post", "/vm/{vm}/snapshot/import".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_send_snapshot(
+    config,
+    vm,
+    snapshot_name,
+    destination_api_uri,
+    destination_api_key,
+    destination_api_verify_ssl=True,
+    destination_storage_pool=None,
+    incremental_parent=None,
+    wait_flag=True,
+):
+    """
+    Send an (existing) snapshot of a VM's disks and configuration to a destination PVC cluster, optionally
+    incremental with incremental_parent
+
+    API endpoint: POST /vm/{vm}/snapshot/send
+    API arguments: snapshot_name=snapshot_name, destination_api_uri=destination_api_uri, destination_api_key=destination_api_key, destination_api_verify_ssl=destination_api_verify_ssl, incremental_parent=incremental_parent, destination_storage_pool=destination_storage_pool
+    API schema: {"message":"{data}"}
+    """
+    params = {
+        "snapshot_name": snapshot_name,
+        "destination_api_uri": destination_api_uri,
+        "destination_api_key": destination_api_key,
+        "destination_api_verify_ssl": destination_api_verify_ssl,
+    }
+    if destination_storage_pool is not None:
+        params["destination_storage_pool"] = destination_storage_pool
+    if incremental_parent is not None:
+        params["incremental_parent"] = incremental_parent
+
+    response = call_api(
+        config, "post", "/vm/{vm}/snapshot/send".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_create_mirror(
+    config,
+    vm,
+    destination_api_uri,
+    destination_api_key,
+    destination_api_verify_ssl=True,
+    destination_storage_pool=None,
+    wait_flag=True,
+):
+    """
+    Create a new snapshot and send the snapshot to a destination PVC cluster, with automatic incremental handling
+
+    API endpoint: POST /vm/{vm}/mirror/create
+    API arguments: destination_api_uri=destination_api_uri, destination_api_key=destination_api_key, destination_api_verify_ssl=destination_api_verify_ssl, destination_storage_pool=destination_storage_pool
+    API schema: {"message":"{data}"}
+    """
+    params = {
+        "destination_api_uri": destination_api_uri,
+        "destination_api_key": destination_api_key,
+        "destination_api_verify_ssl": destination_api_verify_ssl,
+    }
+    if destination_storage_pool is not None:
+        params["destination_storage_pool"] = destination_storage_pool
+
+    response = call_api(
+        config, "post", "/vm/{vm}/mirror/create".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_promote_mirror(
+    config,
+    vm,
+    destination_api_uri,
+    destination_api_key,
+    destination_api_verify_ssl=True,
+    destination_storage_pool=None,
+    remove_on_source=False,
+    wait_flag=True,
+):
+    """
+    Shut down a VM, create a new snapshot, send the snapshot to a destination PVC cluster, start the VM on the remote cluster, and optionally remove the local VM, with automatic incremental handling
+
+    API endpoint: POST /vm/{vm}/mirror/promote
+    API arguments: destination_api_uri=destination_api_uri, destination_api_key=destination_api_key, destination_api_verify_ssl=destination_api_verify_ssl, destination_storage_pool=destination_storage_pool, remove_on_source=remove_on_source
+    API schema: {"message":"{data}"}
+    """
+    params = {
+        "destination_api_uri": destination_api_uri,
+        "destination_api_key": destination_api_key,
+        "destination_api_verify_ssl": destination_api_verify_ssl,
+        "remove_on_source": remove_on_source,
+    }
+    if destination_storage_pool is not None:
+        params["destination_storage_pool"] = destination_storage_pool
+
+    response = call_api(
+        config, "post", "/vm/{vm}/mirror/promote".format(vm=vm), params=params
+    )
+
+    return get_wait_retdata(response, wait_flag)
+
+
+def vm_autobackup(config, email_recipients=None, force_full_flag=False, wait_flag=True):
+    """
+    Perform a cluster VM autobackup
+
+    API endpoint: POST /vm//autobackup
+    API arguments: email_recipients=email_recipients, force_full_flag=force_full_flag
+    API schema: {"message":"{data}"}
+    """
+    params = {
+        "email_recipients": email_recipients,
+        "force_full": force_full_flag,
+    }
+
+    response = call_api(config, "post", "/vm/autobackup", params=params)
+
+    return get_wait_retdata(response, wait_flag)
+
+
 def vm_vcpus_set(config, vm, vcpus, topology, restart):
     """
     Set the vCPU count of the VM with topology
@@ -1516,29 +1738,40 @@ def format_info(config, domain_information, long_output):
             ansiprint.purple(), ansiprint.end(), domain_information["vcpu"]
         )
     )
-    ainformation.append(
-        "{}Topology (S/C/T):{}   {}".format(
-            ansiprint.purple(), ansiprint.end(), domain_information["vcpu_topology"]
+    if long_output:
+        ainformation.append(
+            "{}Topology (S/C/T):{}   {}".format(
+                ansiprint.purple(), ansiprint.end(), domain_information["vcpu_topology"]
+            )
         )
-    )
 
     if (
-        domain_information["vnc"].get("listen", "None") != "None"
-        and domain_information["vnc"].get("port", "None") != "None"
-    ):
+        domain_information["vnc"].get("listen")
+        and domain_information["vnc"].get("port")
+    ) or long_output:
+        listen = (
+            domain_information["vnc"]["listen"]
+            if domain_information["vnc"].get("listen")
+            else "N/A"
+        )
+        port = (
+            domain_information["vnc"]["port"]
+            if domain_information["vnc"].get("port")
+            else "N/A"
+        )
         ainformation.append("")
         ainformation.append(
             "{}VNC listen:{}         {}".format(
-                ansiprint.purple(), ansiprint.end(), domain_information["vnc"]["listen"]
+                ansiprint.purple(), ansiprint.end(), listen
             )
         )
         ainformation.append(
             "{}VNC port:{}           {}".format(
-                ansiprint.purple(), ansiprint.end(), domain_information["vnc"]["port"]
+                ansiprint.purple(), ansiprint.end(), port
             )
         )
 
-    if long_output is True:
+    if long_output:
         # Virtualization information
         ainformation.append("")
         ainformation.append(
@@ -1626,6 +1859,9 @@ def format_info(config, domain_information, long_output):
         "migrate": ansiprint.blue(),
         "unmigrate": ansiprint.blue(),
         "provision": ansiprint.blue(),
+        "restore": ansiprint.blue(),
+        "import": ansiprint.blue(),
+        "mirror": ansiprint.purple(),
     }
     ainformation.append(
         "{}State:{}              {}{}{}".format(
@@ -1637,14 +1873,14 @@ def format_info(config, domain_information, long_output):
         )
     )
     ainformation.append(
-        "{}Current Node:{}       {}".format(
+        "{}Current node:{}       {}".format(
             ansiprint.purple(), ansiprint.end(), domain_information["node"]
         )
     )
     if not domain_information["last_node"]:
         domain_information["last_node"] = "N/A"
     ainformation.append(
-        "{}Previous Node:{}      {}".format(
+        "{}Previous node:{}      {}".format(
             ansiprint.purple(), ansiprint.end(), domain_information["last_node"]
         )
     )
@@ -1658,12 +1894,18 @@ def format_info(config, domain_information, long_output):
             )
         )
 
-    if not domain_information.get("node_selector"):
+    if (
+        not domain_information.get("node_selector")
+        or domain_information.get("node_selector") == "None"
+    ):
         formatted_node_selector = "Default"
     else:
         formatted_node_selector = str(domain_information["node_selector"]).title()
 
-    if not domain_information.get("node_limit"):
+    if (
+        not domain_information.get("node_limit")
+        or domain_information.get("node_limit") == "None"
+    ):
         formatted_node_limit = "Any"
     else:
         formatted_node_limit = ", ".join(domain_information["node_limit"])
@@ -1675,16 +1917,16 @@ def format_info(config, domain_information, long_output):
         autostart_colour = ansiprint.green()
         formatted_node_autostart = "True"
 
-    if not domain_information.get("migration_method"):
-        formatted_migration_method = "Any"
+    if (
+        not domain_information.get("migration_method")
+        or domain_information.get("migration_method") == "None"
+    ):
+        formatted_migration_method = "Live, Shutdown"
     else:
-        formatted_migration_method = str(domain_information["migration_method"]).title()
-
-    ainformation.append(
-        "{}Migration selector:{} {}".format(
-            ansiprint.purple(), ansiprint.end(), formatted_node_selector
+        formatted_migration_method = (
+            f"{str(domain_information['migration_method']).title()} only"
         )
-    )
+
     ainformation.append(
         "{}Node limit:{}         {}".format(
             ansiprint.purple(), ansiprint.end(), formatted_node_limit
@@ -1700,10 +1942,22 @@ def format_info(config, domain_information, long_output):
         )
     )
     ainformation.append(
-        "{}Migration Method:{}   {}".format(
+        "{}Migration method:{}   {}".format(
             ansiprint.purple(), ansiprint.end(), formatted_migration_method
         )
     )
+    ainformation.append(
+        "{}Migration selector:{} {}".format(
+            ansiprint.purple(), ansiprint.end(), formatted_node_selector
+        )
+    )
+    ainformation.append(
+        "{}Max live downtime:{}  {}".format(
+            ansiprint.purple(),
+            ansiprint.end(),
+            f"{domain_information.get('migration_max_downtime')} ms",
+        )
+    )
 
     # Tag list
     tags_name_length = 5
@@ -1749,9 +2003,9 @@ def format_info(config, domain_information, long_output):
                     tags_name=tag["name"],
                     tags_type=tag["type"],
                     tags_protected=str(tag["protected"]),
-                    tags_protected_colour=ansiprint.green()
-                    if tag["protected"]
-                    else ansiprint.blue(),
+                    tags_protected_colour=(
+                        ansiprint.green() if tag["protected"] else ansiprint.blue()
+                    ),
                     end=ansiprint.end(),
                 )
             )
@@ -1764,6 +2018,78 @@ def format_info(config, domain_information, long_output):
             )
         )
 
+    # Snapshot list
+    snapshots_name_length = 5
+    snapshots_age_length = 4
+    snapshots_xml_changes_length = 12
+    for snapshot in domain_information.get("snapshots", list()):
+        xml_diff_plus = 0
+        xml_diff_minus = 0
+        for line in snapshot["xml_diff_lines"]:
+            if re.match(r"^\+ ", line):
+                xml_diff_plus += 1
+            elif re.match(r"^- ", line):
+                xml_diff_minus += 1
+        xml_diff_counts = f"+{xml_diff_plus}/-{xml_diff_minus}"
+
+        _snapshots_name_length = len(snapshot["name"]) + 1
+        if _snapshots_name_length > snapshots_name_length:
+            snapshots_name_length = _snapshots_name_length
+
+        _snapshots_age_length = len(snapshot["age"]) + 1
+        if _snapshots_age_length > snapshots_age_length:
+            snapshots_age_length = _snapshots_age_length
+
+        _snapshots_xml_changes_length = len(xml_diff_counts) + 1
+        if _snapshots_xml_changes_length > snapshots_xml_changes_length:
+            snapshots_xml_changes_length = _snapshots_xml_changes_length
+
+    if len(domain_information.get("snapshots", list())) > 0:
+        ainformation.append("")
+        ainformation.append(
+            "{purple}Snapshots:{end}          {bold}{snapshots_name: <{snapshots_name_length}} {snapshots_age: <{snapshots_age_length}} {snapshots_xml_changes: <{snapshots_xml_changes_length}}{end}".format(
+                purple=ansiprint.purple(),
+                bold=ansiprint.bold(),
+                end=ansiprint.end(),
+                snapshots_name_length=snapshots_name_length,
+                snapshots_age_length=snapshots_age_length,
+                snapshots_xml_changes_length=snapshots_xml_changes_length,
+                snapshots_name="Name",
+                snapshots_age="Age",
+                snapshots_xml_changes="XML Changes",
+            )
+        )
+
+        for snapshot in domain_information.get("snapshots", list()):
+            xml_diff_plus = 0
+            xml_diff_minus = 0
+            for line in snapshot["xml_diff_lines"]:
+                if re.match(r"^\+ ", line):
+                    xml_diff_plus += 1
+                elif re.match(r"^- ", line):
+                    xml_diff_minus += 1
+            xml_diff_counts = f"{ansiprint.green()}+{xml_diff_plus}{ansiprint.end()}/{ansiprint.red()}-{xml_diff_minus}{ansiprint.end()}"
+
+            ainformation.append(
+                "                    {snapshots_name: <{snapshots_name_length}} {snapshots_age: <{snapshots_age_length}} {snapshots_xml_changes: <{snapshots_xml_changes_length}}{end}".format(
+                    snapshots_name_length=snapshots_name_length,
+                    snapshots_age_length=snapshots_age_length,
+                    snapshots_xml_changes_length=snapshots_xml_changes_length,
+                    snapshots_name=snapshot["name"],
+                    snapshots_age=snapshot["age"],
+                    snapshots_xml_changes=xml_diff_counts,
+                    end=ansiprint.end(),
+                )
+            )
+    else:
+        ainformation.append("")
+        ainformation.append(
+            "{purple}Snapshots:{end}          N/A".format(
+                purple=ansiprint.purple(),
+                end=ansiprint.end(),
+            )
+        )
+
     # Network list
     net_list = []
     cluster_net_list = call_api(config, "get", "/network").json()
@@ -1790,7 +2116,7 @@ def format_info(config, domain_information, long_output):
         )
     )
 
-    if long_output is True:
+    if long_output:
         # Disk list
         ainformation.append("")
         name_length = 0
@@ -1926,6 +2252,7 @@ def format_list(config, vm_list):
     vm_name_length = 5
     vm_state_length = 6
     vm_tags_length = 5
+    vm_snapshots_length = 10
     vm_nets_length = 9
     vm_ram_length = 8
     vm_vcpu_length = 6
@@ -1946,6 +2273,12 @@ def format_list(config, vm_list):
         _vm_tags_length = len(",".join(tag_list)) + 1
         if _vm_tags_length > vm_tags_length:
             vm_tags_length = _vm_tags_length
+        # vm_snapshots column
+        _vm_snapshots_length = (
+            len(str(len(domain_information.get("snapshots", list())))) + 1
+        )
+        if _vm_snapshots_length > vm_snapshots_length:
+            vm_snapshots_length = _vm_snapshots_length
         # vm_nets column
         _vm_nets_length = len(",".join(net_list)) + 1
         if _vm_nets_length > vm_nets_length:
@@ -1962,7 +2295,11 @@ def format_list(config, vm_list):
     # Format the string (header)
     vm_list_output.append(
         "{bold}{vm_header: <{vm_header_length}} {resource_header: <{resource_header_length}} {node_header: <{node_header_length}}{end_bold}".format(
-            vm_header_length=vm_name_length + vm_state_length + vm_tags_length + 2,
+            vm_header_length=vm_name_length
+            + vm_state_length
+            + vm_tags_length
+            + vm_snapshots_length
+            + 3,
             resource_header_length=vm_nets_length + vm_ram_length + vm_vcpu_length + 2,
             node_header_length=vm_node_length + vm_migrated_length + 1,
             bold=ansiprint.bold(),
@@ -1972,7 +2309,12 @@ def format_list(config, vm_list):
                 [
                     "-"
                     for _ in range(
-                        4, vm_name_length + vm_state_length + vm_tags_length + 1
+                        4,
+                        vm_name_length
+                        + vm_state_length
+                        + vm_tags_length
+                        + +vm_snapshots_length
+                        + 2,
                     )
                 ]
             ),
@@ -1994,6 +2336,7 @@ def format_list(config, vm_list):
         "{bold}{vm_name: <{vm_name_length}} \
 {vm_state_colour}{vm_state: <{vm_state_length}}{end_colour} \
 {vm_tags: <{vm_tags_length}} \
+{vm_snapshots: <{vm_snapshots_length}} \
 {vm_networks: <{vm_nets_length}} \
 {vm_memory: <{vm_ram_length}} {vm_vcpu: <{vm_vcpu_length}} \
 {vm_node: <{vm_node_length}} \
@@ -2001,6 +2344,7 @@ def format_list(config, vm_list):
             vm_name_length=vm_name_length,
             vm_state_length=vm_state_length,
             vm_tags_length=vm_tags_length,
+            vm_snapshots_length=vm_snapshots_length,
             vm_nets_length=vm_nets_length,
             vm_ram_length=vm_ram_length,
             vm_vcpu_length=vm_vcpu_length,
@@ -2013,6 +2357,7 @@ def format_list(config, vm_list):
             vm_name="Name",
             vm_state="State",
             vm_tags="Tags",
+            vm_snapshots="Snapshots",
             vm_networks="Networks",
             vm_memory="RAM (M)",
             vm_vcpu="vCPUs",
@@ -2026,16 +2371,14 @@ def format_list(config, vm_list):
 
     # Format the string (elements)
     for domain_information in sorted(vm_list, key=lambda v: v["name"]):
-        if domain_information["state"] == "start":
+        if domain_information["state"] in ["start"]:
             vm_state_colour = ansiprint.green()
-        elif domain_information["state"] == "restart":
+        elif domain_information["state"] in ["restart", "shutdown"]:
             vm_state_colour = ansiprint.yellow()
-        elif domain_information["state"] == "shutdown":
-            vm_state_colour = ansiprint.yellow()
-        elif domain_information["state"] == "stop":
-            vm_state_colour = ansiprint.red()
-        elif domain_information["state"] == "fail":
+        elif domain_information["state"] in ["stop", "fail"]:
             vm_state_colour = ansiprint.red()
+        elif domain_information["state"] in ["mirror"]:
+            vm_state_colour = ansiprint.purple()
         else:
             vm_state_colour = ansiprint.blue()
 
@@ -2059,8 +2402,10 @@ def format_list(config, vm_list):
             else:
                 net_invalid_list.append(False)
 
+        display_net_string_list = []
         net_string_list = []
         for net_idx, net_vni in enumerate(net_list):
+            display_net_string_list.append(net_vni)
             if net_invalid_list[net_idx]:
                 net_string_list.append(
                     "{}{}{}".format(
@@ -2069,9 +2414,6 @@ def format_list(config, vm_list):
                         ansiprint.end(),
                     )
                 )
-                # Fix the length due to the extra fake characters
-                vm_nets_length -= len(net_vni)
-                vm_nets_length += len(net_string_list[net_idx])
             else:
                 net_string_list.append(net_vni)
 
@@ -2079,6 +2421,7 @@ def format_list(config, vm_list):
             "{bold}{vm_name: <{vm_name_length}} \
 {vm_state_colour}{vm_state: <{vm_state_length}}{end_colour} \
 {vm_tags: <{vm_tags_length}} \
+{vm_snapshots: <{vm_snapshots_length}} \
 {vm_networks: <{vm_nets_length}} \
 {vm_memory: <{vm_ram_length}} {vm_vcpu: <{vm_vcpu_length}} \
 {vm_node: <{vm_node_length}} \
@@ -2086,7 +2429,10 @@ def format_list(config, vm_list):
                 vm_name_length=vm_name_length,
                 vm_state_length=vm_state_length,
                 vm_tags_length=vm_tags_length,
-                vm_nets_length=vm_nets_length,
+                vm_snapshots_length=vm_snapshots_length,
+                vm_nets_length=vm_nets_length
+                + len(",".join(net_string_list))
+                - len(",".join(display_net_string_list)),
                 vm_ram_length=vm_ram_length,
                 vm_vcpu_length=vm_vcpu_length,
                 vm_node_length=vm_node_length,
@@ -2098,7 +2444,9 @@ def format_list(config, vm_list):
                 vm_name=domain_information["name"],
                 vm_state=domain_information["state"],
                 vm_tags=",".join(tag_list),
-                vm_networks=",".join(net_string_list),
+                vm_snapshots=len(domain_information.get("snapshots", list())),
+                vm_networks=",".join(net_string_list)
+                + ("" if all(net_invalid_list) else " "),
                 vm_memory=domain_information["memory"],
                 vm_vcpu=domain_information["vcpu"],
                 vm_node=domain_information["node"],

client-cli/pvc/lib/zkhandler.py

@@ -3,7 +3,7 @@
 # zkhandler.py - Secure versioned ZooKeeper updates
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

client-cli/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name="pvc",
-    version="0.9.86",
+    version="0.9.103",
     packages=["pvc.cli", "pvc.lib"],
     install_requires=[
         "Click",

daemon-common/autobackup.py

@@ -0,0 +1,695 @@
+#!/usr/bin/env python3
+
+# autobackup.py - PVC API Autobackup functions
+# Part of the Parallel Virtual Cluster (PVC) system
+#
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
+#
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU General Public License as published by
+#    the Free Software Foundation, version 3.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU General Public License for more details.
+#
+#    You should have received a copy of the GNU General Public License
+#    along with this program.  If not, see <https://www.gnu.org/licenses/>.
+#
+###############################################################################
+
+from datetime import datetime
+from json import load as jload
+from json import dump as jdump
+from os import popen, makedirs, path, scandir
+from shutil import rmtree
+from subprocess import run, PIPE
+
+from daemon_lib.common import run_os_command
+from daemon_lib.config import get_autobackup_configuration
+from daemon_lib.celery import start, fail, log_info, log_err, update, finish
+
+import daemon_lib.ceph as ceph
+import daemon_lib.vm as vm
+
+
+def send_execution_failure_report(
+    celery_conf, config, recipients=None, total_time=0, error=None
+):
+    if recipients is None:
+        return
+
+    from email.utils import formatdate
+    from socket import gethostname
+
+    log_message = f"Sending email failure report to {', '.join(recipients)}"
+    log_info(celery_conf[0], log_message)
+    update(
+        celery_conf[0],
+        log_message,
+        current=celery_conf[1] + 1,
+        total=celery_conf[2],
+    )
+
+    current_datetime = datetime.now()
+    email_datetime = formatdate(float(current_datetime.strftime("%s")))
+
+    email = list()
+    email.append(f"Date: {email_datetime}")
+    email.append(
+        f"Subject: PVC Autobackup execution failure for cluster '{config['cluster']}'"
+    )
+
+    email_to = list()
+    for recipient in recipients:
+        email_to.append(f"<{recipient}>")
+
+    email.append(f"To: {', '.join(email_to)}")
+    email.append(f"From: PVC Autobackup System <pvc@{gethostname()}>")
+    email.append("")
+
+    email.append(
+        f"A PVC autobackup has FAILED at {current_datetime} in {total_time}s due to an execution error."
+    )
+    email.append("")
+    email.append("The reported error message is:")
+    email.append(f"  {error}")
+
+    try:
+        with popen("/usr/sbin/sendmail -t", "w") as p:
+            p.write("\n".join(email))
+    except Exception as e:
+        log_err(f"Failed to send report email: {e}")
+
+
+def send_execution_summary_report(
+    celery_conf, config, recipients=None, total_time=0, summary=dict()
+):
+    if recipients is None:
+        return
+
+    from email.utils import formatdate
+    from socket import gethostname
+
+    log_message = f"Sending email summary report to {', '.join(recipients)}"
+    log_info(celery_conf[0], log_message)
+    update(
+        celery_conf[0],
+        log_message,
+        current=celery_conf[1] + 1,
+        total=celery_conf[2],
+    )
+
+    current_datetime = datetime.now()
+    email_datetime = formatdate(float(current_datetime.strftime("%s")))
+
+    email = list()
+    email.append(f"Date: {email_datetime}")
+    email.append(f"Subject: PVC Autobackup report for cluster '{config['cluster']}'")
+
+    email_to = list()
+    for recipient in recipients:
+        email_to.append(f"<{recipient}>")
+
+    email.append(f"To: {', '.join(email_to)}")
+    email.append(f"From: PVC Autobackup System <pvc@{gethostname()}>")
+    email.append("")
+
+    email.append(
+        f"A PVC autobackup has been completed at {current_datetime} in {total_time}."
+    )
+    email.append("")
+    email.append(
+        "The following is a summary of all current VM backups after cleanups, most recent first:"
+    )
+    email.append("")
+
+    for vm_name in summary.keys():
+        email.append(f"VM: {vm_name}:")
+        for backup in summary[vm_name]:
+            datestring = backup.get("datestring")
+            backup_date = datetime.strptime(datestring, "%Y%m%d%H%M%S")
+            if backup.get("result", False):
+                email.append(
+                    f"    {backup_date}: Success in {backup.get('runtime_secs', 0)} seconds, ID {backup.get('snapshot_name')}, type {backup.get('type', 'unknown')}"
+                )
+                email.append(
+                    f"                         Backup contains {len(backup.get('export_files'))} files totaling {ceph.format_bytes_tohuman(backup.get('export_size_bytes', 0))} ({backup.get('export_size_bytes', 0)} bytes)"
+                )
+            else:
+                email.append(
+                    f"    {backup_date}: Failure in {backup.get('runtime_secs', 0)} seconds, ID {backup.get('snapshot_name')}, type {backup.get('type', 'unknown')}"
+                )
+                email.append(f"                         {backup.get('result_message')}")
+
+    try:
+        with popen("/usr/sbin/sendmail -t", "w") as p:
+            p.write("\n".join(email))
+    except Exception as e:
+        log_err(f"Failed to send report email: {e}")
+
+
+def run_vm_backup(zkhandler, celery, config, vm_detail, force_full=False):
+    vm_name = vm_detail["name"]
+    dom_uuid = vm_detail["uuid"]
+    backup_suffixed_path = f"{config['backup_root_path']}{config['backup_root_suffix']}"
+    vm_backup_path = f"{backup_suffixed_path}/{vm_name}"
+    autobackup_state_file = f"{vm_backup_path}/.autobackup.json"
+    full_interval = config["backup_schedule"]["full_interval"]
+    full_retention = config["backup_schedule"]["full_retention"]
+
+    if not path.exists(vm_backup_path) or not path.exists(autobackup_state_file):
+        # There are no existing backups so the list is empty
+        state_data = dict()
+        tracked_backups = list()
+    else:
+        with open(autobackup_state_file) as fh:
+            state_data = jload(fh)
+        tracked_backups = state_data["tracked_backups"]
+
+    full_backups = [b for b in tracked_backups if b["type"] == "full"]
+    if len(full_backups) > 0:
+        last_full_backup = full_backups[0]
+        last_full_backup_idx = tracked_backups.index(last_full_backup)
+        if force_full:
+            this_backup_incremental_parent = None
+            this_backup_retain_snapshot = True
+        elif last_full_backup_idx >= full_interval - 1:
+            this_backup_incremental_parent = None
+            this_backup_retain_snapshot = True
+        else:
+            this_backup_incremental_parent = last_full_backup["snapshot_name"]
+            this_backup_retain_snapshot = False
+    else:
+        # The very first ackup must be full to start the tree
+        this_backup_incremental_parent = None
+        this_backup_retain_snapshot = True
+
+    export_type = (
+        "incremental" if this_backup_incremental_parent is not None else "full"
+    )
+
+    now = datetime.now()
+    datestring = now.strftime("%Y%m%d%H%M%S")
+    snapshot_name = f"ab{datestring}"
+
+    # Take the VM snapshot (vm.vm_worker_create_snapshot)
+    snap_list = list()
+
+    failure = False
+    export_files = None
+    export_files_size = 0
+
+    def update_tracked_backups():
+        # Read export file to get details
+        backup_json_file = (
+            f"{backup_suffixed_path}/{vm_name}/{snapshot_name}/snapshot.json"
+        )
+        try:
+            with open(backup_json_file) as fh:
+                backup_json = jload(fh)
+            tracked_backups.insert(0, backup_json)
+        except Exception as e:
+            log_err(celery, f"Could not open export JSON: {e}")
+            return list()
+
+        state_data["tracked_backups"] = tracked_backups
+        with open(autobackup_state_file, "w") as fh:
+            jdump(state_data, fh)
+
+        return tracked_backups
+
+    def write_backup_summary(success=False, message=""):
+        ttotal = (datetime.now() - now).total_seconds()
+        export_details = {
+            "type": export_type,
+            "result": success,
+            "message": message,
+            "datestring": datestring,
+            "runtime_secs": ttotal,
+            "snapshot_name": snapshot_name,
+            "incremental_parent": this_backup_incremental_parent,
+            "vm_detail": vm_detail,
+            "export_files": export_files,
+            "export_size_bytes": export_files_size,
+        }
+        try:
+            with open(
+                f"{backup_suffixed_path}/{vm_name}/{snapshot_name}/snapshot.json",
+                "w",
+            ) as fh:
+                jdump(export_details, fh)
+        except Exception as e:
+            log_err(celery, f"Error exporting snapshot details: {e}")
+            return False, e
+
+        return True, ""
+
+    def cleanup_failure():
+        for snapshot in snap_list:
+            rbd, snapshot_name = snapshot.split("@")
+            pool, volume = rbd.split("/")
+            # We capture no output here, because if this fails too we're in a deep
+            # error chain and will just ignore it
+            ceph.remove_snapshot(zkhandler, pool, volume, snapshot_name)
+
+    rbd_list = zkhandler.read(("domain.storage.volumes", dom_uuid)).split(",")
+
+    for rbd in rbd_list:
+        pool, volume = rbd.split("/")
+        ret, msg = ceph.add_snapshot(
+            zkhandler, pool, volume, snapshot_name, zk_only=False
+        )
+        if not ret:
+            cleanup_failure()
+            error_message = msg.replace("ERROR: ", "")
+            log_err(celery, error_message)
+            failure = True
+            break
+        else:
+            snap_list.append(f"{pool}/{volume}@{snapshot_name}")
+
+    if failure:
+        error_message = (f"[{vm_name}] Error in snapshot export, skipping",)
+        write_backup_summary(message=error_message)
+        tracked_backups = update_tracked_backups()
+        return tracked_backups
+
+    # Get the current domain XML
+    vm_config = zkhandler.read(("domain.xml", dom_uuid))
+
+    # Add the snapshot entry to Zookeeper
+    ret = zkhandler.write(
+        [
+            (
+                (
+                    "domain.snapshots",
+                    dom_uuid,
+                    "domain_snapshot.name",
+                    snapshot_name,
+                ),
+                snapshot_name,
+            ),
+            (
+                (
+                    "domain.snapshots",
+                    dom_uuid,
+                    "domain_snapshot.timestamp",
+                    snapshot_name,
+                ),
+                now.strftime("%s"),
+            ),
+            (
+                (
+                    "domain.snapshots",
+                    dom_uuid,
+                    "domain_snapshot.xml",
+                    snapshot_name,
+                ),
+                vm_config,
+            ),
+            (
+                (
+                    "domain.snapshots",
+                    dom_uuid,
+                    "domain_snapshot.rbd_snapshots",
+                    snapshot_name,
+                ),
+                ",".join(snap_list),
+            ),
+        ]
+    )
+    if not ret:
+        error_message = (f"[{vm_name}] Error in snapshot export, skipping",)
+        log_err(celery, error_message)
+        write_backup_summary(message=error_message)
+        tracked_backups = update_tracked_backups()
+        return tracked_backups
+
+    # Export the snapshot (vm.vm_worker_export_snapshot)
+    export_target_path = f"{backup_suffixed_path}/{vm_name}/{snapshot_name}/images"
+
+    try:
+        makedirs(export_target_path)
+    except Exception as e:
+        error_message = (
+            f"[{vm_name}] Failed to create target directory '{export_target_path}': {e}",
+        )
+        log_err(celery, error_message)
+        return tracked_backups
+
+    def export_cleanup():
+        from shutil import rmtree
+
+        rmtree(f"{backup_suffixed_path}/{vm_name}/{snapshot_name}")
+
+    # Set the export filetype
+    if this_backup_incremental_parent is not None:
+        export_fileext = "rbddiff"
+    else:
+        export_fileext = "rbdimg"
+
+    snapshot_volumes = list()
+    for rbdsnap in snap_list:
+        pool, _volume = rbdsnap.split("/")
+        volume, name = _volume.split("@")
+        ret, snapshots = ceph.get_list_snapshot(
+            zkhandler, pool, volume, limit=name, is_fuzzy=False
+        )
+        if ret:
+            snapshot_volumes += snapshots
+
+    export_files = list()
+    for snapshot_volume in snapshot_volumes:
+        snap_pool = snapshot_volume["pool"]
+        snap_volume = snapshot_volume["volume"]
+        snap_snapshot_name = snapshot_volume["snapshot"]
+        snap_size = snapshot_volume["stats"]["size"]
+
+        if this_backup_incremental_parent is not None:
+            retcode, stdout, stderr = run_os_command(
+                f"rbd export-diff --from-snap {this_backup_incremental_parent} {snap_pool}/{snap_volume}@{snap_snapshot_name} {export_target_path}/{snap_pool}.{snap_volume}.{export_fileext}"
+            )
+            if retcode:
+                error_message = (
+                    f"[{vm_name}] Failed to export snapshot for volume(s) '{snap_pool}/{snap_volume}'",
+                )
+                failure = True
+                break
+            else:
+                export_files.append(
+                    (
+                        f"images/{snap_pool}.{snap_volume}.{export_fileext}",
+                        snap_size,
+                    )
+                )
+        else:
+            retcode, stdout, stderr = run_os_command(
+                f"rbd export --export-format 2 {snap_pool}/{snap_volume}@{snap_snapshot_name} {export_target_path}/{snap_pool}.{snap_volume}.{export_fileext}"
+            )
+            if retcode:
+                error_message = (
+                    f"[{vm_name}] Failed to export snapshot for volume(s) '{snap_pool}/{snap_volume}'",
+                )
+                failure = True
+                break
+            else:
+                export_files.append(
+                    (
+                        f"images/{snap_pool}.{snap_volume}.{export_fileext}",
+                        snap_size,
+                    )
+                )
+
+    if failure:
+        log_err(celery, error_message)
+        write_backup_summary(message=error_message)
+        tracked_backups = update_tracked_backups()
+        return tracked_backups
+
+    def get_dir_size(pathname):
+        total = 0
+        with scandir(pathname) as it:
+            for entry in it:
+                if entry.is_file():
+                    total += entry.stat().st_size
+                elif entry.is_dir():
+                    total += get_dir_size(entry.path)
+        return total
+
+    export_files_size = get_dir_size(export_target_path)
+
+    ret, e = write_backup_summary(success=True)
+    if not ret:
+        error_message = (f"[{vm_name}] Failed to export configuration snapshot: {e}",)
+        log_err(celery, error_message)
+        write_backup_summary(message=error_message)
+        tracked_backups = update_tracked_backups()
+        return tracked_backups
+
+    # Clean up the snapshot (vm.vm_worker_remove_snapshot)
+    if not this_backup_retain_snapshot:
+        for snap in snap_list:
+            rbd, name = snap.split("@")
+            pool, volume = rbd.split("/")
+            ret, msg = ceph.remove_snapshot(zkhandler, pool, volume, name)
+            if not ret:
+                error_message = msg.replace("ERROR: ", f"[{vm_name}] ")
+                failure = True
+                break
+
+        if failure:
+            log_err(celery, error_message)
+            write_backup_summary(message=error_message)
+            tracked_backups = update_tracked_backups()
+            return tracked_backups
+
+        ret = zkhandler.delete(
+            ("domain.snapshots", dom_uuid, "domain_snapshot.name", snapshot_name)
+        )
+        if not ret:
+            error_message = (f"[{vm_name}] Failed to remove VM snapshot; continuing",)
+            log_err(celery, error_message)
+
+    marked_for_deletion = list()
+    # Find any full backups that are expired
+    found_full_count = 0
+    for backup in tracked_backups:
+        if backup["type"] == "full":
+            found_full_count += 1
+            if found_full_count > full_retention:
+                marked_for_deletion.append(backup)
+    # Find any incremental backups that depend on marked parents
+    for backup in tracked_backups:
+        if backup["type"] == "incremental" and backup["incremental_parent"] in [
+            b["snapshot_name"] for b in marked_for_deletion
+        ]:
+            marked_for_deletion.append(backup)
+
+    if len(marked_for_deletion) > 0:
+        for backup_to_delete in marked_for_deletion:
+            ret = vm.vm_worker_remove_snapshot(
+                zkhandler, None, vm_name, backup_to_delete["snapshot_name"]
+            )
+            if ret is False:
+                error_message = f"Failed to remove obsolete backup snapshot '{backup_to_delete['snapshot_name']}', leaving in tracked backups"
+                log_err(celery, error_message)
+            else:
+                rmtree(f"{vm_backup_path}/{backup_to_delete['snapshot_name']}")
+                tracked_backups.remove(backup_to_delete)
+
+    tracked_backups = update_tracked_backups()
+    return tracked_backups
+
+
+def worker_cluster_autobackup(
+    zkhandler, celery, force_full=False, email_recipients=None
+):
+    config = get_autobackup_configuration()
+
+    backup_summary = dict()
+
+    current_stage = 0
+    total_stages = 1
+    if email_recipients is not None:
+        total_stages += 1
+
+    start(
+        celery,
+        f"Starting cluster '{config['cluster']}' VM autobackup",
+        current=current_stage,
+        total=total_stages,
+    )
+
+    if not config["autobackup_enabled"]:
+        message = "Autobackups are not configured on this cluster."
+        log_info(celery, message)
+        return finish(
+            celery,
+            message,
+            current=total_stages,
+            total=total_stages,
+        )
+
+    autobackup_start_time = datetime.now()
+
+    retcode, vm_list = vm.get_list(zkhandler)
+    if not retcode:
+        error_message = f"Failed to fetch VM list: {vm_list}"
+        log_err(celery, error_message)
+        send_execution_failure_report(
+            (celery, current_stage, total_stages),
+            config,
+            recipients=email_recipients,
+            error=error_message,
+        )
+        fail(celery, error_message)
+        return False
+
+    backup_suffixed_path = f"{config['backup_root_path']}{config['backup_root_suffix']}"
+    if not path.exists(backup_suffixed_path):
+        makedirs(backup_suffixed_path)
+
+    full_interval = config["backup_schedule"]["full_interval"]
+
+    backup_vms = list()
+    for vm_detail in vm_list:
+        vm_tag_names = [t["name"] for t in vm_detail["tags"]]
+        matching_tags = (
+            True
+            if len(set(vm_tag_names).intersection(set(config["backup_tags"]))) > 0
+            else False
+        )
+        if matching_tags:
+            backup_vms.append(vm_detail)
+
+    if len(backup_vms) < 1:
+        message = "Found no VMs tagged for autobackup."
+        log_info(celery, message)
+        return finish(
+            celery,
+            message,
+            current=total_stages,
+            total=total_stages,
+        )
+
+    if config["auto_mount_enabled"]:
+        total_stages += len(config["mount_cmds"])
+        total_stages += len(config["unmount_cmds"])
+
+    total_stages += len(backup_vms)
+
+    log_info(
+        celery,
+        f"Found {len(backup_vms)} suitable VM(s) for autobackup: {', '.join([b['name'] for b in backup_vms])}",
+    )
+
+    # Handle automount mount commands
+    if config["auto_mount_enabled"]:
+        for cmd in config["mount_cmds"]:
+            current_stage += 1
+            update(
+                celery,
+                f"Executing mount command '{cmd.split()[0]}'",
+                current=current_stage,
+                total=total_stages,
+            )
+
+            ret = run(
+                cmd.split(),
+                stdout=PIPE,
+                stderr=PIPE,
+            )
+
+            if ret.returncode != 0:
+                error_message = f"Failed to execute mount command '{cmd.split()[0]}': {ret.stderr.decode().strip()}"
+                log_err(celery, error_message)
+                send_execution_failure_report(
+                    (celery, current_stage, total_stages),
+                    config,
+                    recipients=email_recipients,
+                    total_time=datetime.now() - autobackup_start_time,
+                    error=error_message,
+                )
+                fail(celery, error_message)
+                return False
+
+    # Execute the backup: take a snapshot, then export the snapshot
+    for vm_detail in backup_vms:
+        vm_backup_path = f"{backup_suffixed_path}/{vm_detail['name']}"
+        autobackup_state_file = f"{vm_backup_path}/.autobackup.json"
+        if not path.exists(vm_backup_path) or not path.exists(autobackup_state_file):
+            # There are no existing backups so the list is empty
+            state_data = dict()
+            tracked_backups = list()
+        else:
+            with open(autobackup_state_file) as fh:
+                state_data = jload(fh)
+            tracked_backups = state_data["tracked_backups"]
+
+        full_backups = [b for b in tracked_backups if b["type"] == "full"]
+        if len(full_backups) > 0:
+            last_full_backup = full_backups[0]
+            last_full_backup_idx = tracked_backups.index(last_full_backup)
+            if force_full:
+                this_backup_incremental_parent = None
+            elif last_full_backup_idx >= full_interval - 1:
+                this_backup_incremental_parent = None
+            else:
+                this_backup_incremental_parent = last_full_backup["snapshot_name"]
+        else:
+            # The very first ackup must be full to start the tree
+            this_backup_incremental_parent = None
+
+        export_type = (
+            "incremental" if this_backup_incremental_parent is not None else "full"
+        )
+
+        current_stage += 1
+        update(
+            celery,
+            f"Performing autobackup of VM {vm_detail['name']} ({export_type})",
+            current=current_stage,
+            total=total_stages,
+        )
+
+        summary = run_vm_backup(
+            zkhandler,
+            celery,
+            config,
+            vm_detail,
+            force_full=force_full,
+        )
+        backup_summary[vm_detail["name"]] = summary
+
+    # Handle automount unmount commands
+    if config["auto_mount_enabled"]:
+        for cmd in config["unmount_cmds"]:
+            current_stage += 1
+            update(
+                celery,
+                f"Executing unmount command '{cmd.split()[0]}'",
+                current=current_stage,
+                total=total_stages,
+            )
+
+            ret = run(
+                cmd.split(),
+                stdout=PIPE,
+                stderr=PIPE,
+            )
+
+            if ret.returncode != 0:
+                error_message = f"Failed to execute unmount command '{cmd.split()[0]}': {ret.stderr.decode().strip()}"
+                log_err(celery, error_message)
+                send_execution_failure_report(
+                    (celery, current_stage, total_stages),
+                    config,
+                    recipients=email_recipients,
+                    total_time=datetime.now() - autobackup_start_time,
+                    error=error_message,
+                )
+                fail(celery, error_message)
+                return False
+
+    autobackup_end_time = datetime.now()
+    autobackup_total_time = autobackup_end_time - autobackup_start_time
+
+    if email_recipients is not None:
+        send_execution_summary_report(
+            (celery, current_stage, total_stages),
+            config,
+            recipients=email_recipients,
+            total_time=autobackup_total_time,
+            summary=backup_summary,
+        )
+        current_stage += 1
+
+    current_stage += 1
+    return finish(
+        celery,
+        f"Successfully completed cluster '{config['cluster']}' VM autobackup",
+        current=current_stage,
+        total=total_stages,
+    )

daemon-common/benchmark.py

@@ -3,7 +3,7 @@
 # benchmark.py - PVC API Benchmark functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -19,31 +19,34 @@
 #
 ###############################################################################
 
+import os
+import psutil
 import psycopg2
 import psycopg2.extras
+import subprocess
 
 from datetime import datetime
 from json import loads, dumps
+from time import sleep
 
 from daemon_lib.celery import start, fail, log_info, update, finish
 
-import daemon_lib.common as pvc_common
 import daemon_lib.ceph as pvc_ceph
 
 
 # Define the current test format
-TEST_FORMAT = 1
+TEST_FORMAT = 2
 
 
 # We run a total of 8 tests, to give a generalized idea of performance on the cluster:
-#   1. A sequential read test of 8GB with a 4M block size
-#   2. A sequential write test of 8GB with a 4M block size
-#   3. A random read test of 8GB with a 4M block size
-#   4. A random write test of 8GB with a 4M block size
-#   5. A random read test of 8GB with a 256k block size
-#   6. A random write test of 8GB with a 256k block size
-#   7. A random read test of 8GB with a 4k block size
-#   8. A random write test of 8GB with a 4k block size
+#   1. A sequential read test of 64GB with a 4M block size
+#   2. A sequential write test of 64GB with a 4M block size
+#   3. A random read test of 64GB with a 4M block size
+#   4. A random write test of 64GB with a 4M block size
+#   5. A random read test of 64GB with a 256k block size
+#   6. A random write test of 64GB with a 256k block size
+#   7. A random read test of 64GB with a 4k block size
+#   8. A random write test of 64GB with a 4k block size
 # Taken together, these 8 results should give a very good indication of the overall storage performance
 # for a variety of workloads.
 test_matrix = {
@@ -100,7 +103,7 @@ test_matrix = {
 
 # Specify the benchmark volume name and size
 benchmark_volume_name = "pvcbenchmark"
-benchmark_volume_size = "8G"
+benchmark_volume_size = "64G"
 
 
 #
@@ -115,12 +118,13 @@ class BenchmarkError(Exception):
 #
 
 
-def cleanup(job_name, db_conn=None, db_cur=None, zkhandler=None):
+def cleanup(job_name, db_conn=None, db_cur=None, zkhandler=None, final=False):
     if db_conn is not None and db_cur is not None:
-        # Clean up our dangling result
-        query = "DELETE FROM storage_benchmarks WHERE job = %s;"
-        args = (job_name,)
-        db_cur.execute(query, args)
+        if not final:
+            # Clean up our dangling result (non-final runs only)
+            query = "DELETE FROM storage_benchmarks WHERE job = %s;"
+            args = (job_name,)
+            db_cur.execute(query, args)
         db_conn.commit()
         # Close the database connections cleanly
         close_database(db_conn, db_cur)
@@ -225,7 +229,7 @@ def cleanup_benchmark_volume(
 
 
 def run_benchmark_job(
-    test, pool, job_name=None, db_conn=None, db_cur=None, zkhandler=None
+    config, test, pool, job_name=None, db_conn=None, db_cur=None, zkhandler=None
 ):
     test_spec = test_matrix[test]
     log_info(None, f"Running test '{test}'")
@@ -255,31 +259,165 @@ def run_benchmark_job(
     )
 
     log_info(None, "Running fio job: {}".format(" ".join(fio_cmd.split())))
-    retcode, stdout, stderr = pvc_common.run_os_command(fio_cmd)
+
+    # Run the fio command manually instead of using our run_os_command wrapper
+    # This will help us gather statistics about this node while it's running
+    process = subprocess.Popen(
+        fio_cmd.split(),
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
+        text=True,
+    )
+
+    # Wait 15 seconds for the test to start
+    log_info(None, "Waiting 15 seconds for test resource stabilization")
+    sleep(15)
+
+    # Set up function to get process CPU utilization by name
+    def get_cpu_utilization_by_name(process_name):
+        cpu_usage = 0
+        for proc in psutil.process_iter(["name", "cpu_percent"]):
+            if proc.info["name"] == process_name:
+                cpu_usage += proc.info["cpu_percent"]
+        return cpu_usage
+
+    # Set up function to get process memory utilization by name
+    def get_memory_utilization_by_name(process_name):
+        memory_usage = 0
+        for proc in psutil.process_iter(["name", "memory_percent"]):
+            if proc.info["name"] == process_name:
+                memory_usage += proc.info["memory_percent"]
+        return memory_usage
+
+    # Set up function to get network traffic utilization in bps
+    def get_network_traffic_bps(interface, duration=1):
+        # Get initial network counters
+        net_io_start = psutil.net_io_counters(pernic=True)
+        if interface not in net_io_start:
+            return None, None
+
+        stats_start = net_io_start[interface]
+        bytes_sent_start = stats_start.bytes_sent
+        bytes_recv_start = stats_start.bytes_recv
+
+        # Wait for the specified duration
+        sleep(duration)
+
+        # Get final network counters
+        net_io_end = psutil.net_io_counters(pernic=True)
+        stats_end = net_io_end[interface]
+        bytes_sent_end = stats_end.bytes_sent
+        bytes_recv_end = stats_end.bytes_recv
+
+        # Calculate bytes per second
+        bytes_sent_per_sec = (bytes_sent_end - bytes_sent_start) / duration
+        bytes_recv_per_sec = (bytes_recv_end - bytes_recv_start) / duration
+
+        # Convert to bits per second (bps)
+        bits_sent_per_sec = bytes_sent_per_sec * 8
+        bits_recv_per_sec = bytes_recv_per_sec * 8
+        bits_total_per_sec = bits_sent_per_sec + bits_recv_per_sec
+
+        return bits_sent_per_sec, bits_recv_per_sec, bits_total_per_sec
+
+    log_info(None, f"Starting system resource polling for test '{test}'")
+    storage_interface = config["storage_dev"]
+    total_cpus = psutil.cpu_count(logical=True)
+    ticks = 1
+    osd_cpu_utilization = 0
+    osd_memory_utilization = 0
+    mon_cpu_utilization = 0
+    mon_memory_utilization = 0
+    total_cpu_utilization = 0
+    total_memory_utilization = 0
+    storage_sent_bps = 0
+    storage_recv_bps = 0
+    storage_total_bps = 0
+
+    while process.poll() is None:
+        # Do collection of statistics like network bandwidth and cpu utilization
+        current_osd_cpu_utilization = get_cpu_utilization_by_name("ceph-osd")
+        current_osd_memory_utilization = get_memory_utilization_by_name("ceph-osd")
+        current_mon_cpu_utilization = get_cpu_utilization_by_name("ceph-mon")
+        current_mon_memory_utilization = get_memory_utilization_by_name("ceph-mon")
+        current_total_cpu_utilization = psutil.cpu_percent(interval=1)
+        current_total_memory_utilization = psutil.virtual_memory().percent
+        (
+            current_storage_sent_bps,
+            current_storage_recv_bps,
+            current_storage_total_bps,
+        ) = get_network_traffic_bps(storage_interface)
+        # Recheck if the process is done yet; if it's not, we add the values and increase the ticks
+        # This helps ensure that if the process finishes earlier than the longer polls above,
+        # this particular tick isn't counted which can skew the average
+        if process.poll() is None:
+            osd_cpu_utilization += current_osd_cpu_utilization
+            osd_memory_utilization += current_osd_memory_utilization
+            mon_cpu_utilization += current_mon_cpu_utilization
+            mon_memory_utilization += current_mon_memory_utilization
+            total_cpu_utilization += current_total_cpu_utilization
+            total_memory_utilization += current_total_memory_utilization
+            storage_sent_bps += current_storage_sent_bps
+            storage_recv_bps += current_storage_recv_bps
+            storage_total_bps += current_storage_total_bps
+            ticks += 1
+
+    # Get the 1-minute load average and CPU utilization, which covers the test duration
+    load1, _, _ = os.getloadavg()
+    load1 = round(load1, 2)
+
+    # Calculate the average CPU utilization values over the runtime
+    # Divide the OSD and MON CPU utilization by the total number of CPU cores, because
+    # the total is divided this way
+    avg_osd_cpu_utilization = round(osd_cpu_utilization / ticks / total_cpus, 2)
+    avg_osd_memory_utilization = round(osd_memory_utilization / ticks, 2)
+    avg_mon_cpu_utilization = round(mon_cpu_utilization / ticks / total_cpus, 2)
+    avg_mon_memory_utilization = round(mon_memory_utilization / ticks, 2)
+    avg_total_cpu_utilization = round(total_cpu_utilization / ticks, 2)
+    avg_total_memory_utilization = round(total_memory_utilization / ticks, 2)
+    avg_storage_sent_bps = round(storage_sent_bps / ticks, 2)
+    avg_storage_recv_bps = round(storage_recv_bps / ticks, 2)
+    avg_storage_total_bps = round(storage_total_bps / ticks, 2)
+
+    stdout, stderr = process.communicate()
+    retcode = process.returncode
+
+    resource_data = {
+        "avg_cpu_util_percent": {
+            "total": avg_total_cpu_utilization,
+            "ceph-mon": avg_mon_cpu_utilization,
+            "ceph-osd": avg_osd_cpu_utilization,
+        },
+        "avg_memory_util_percent": {
+            "total": avg_total_memory_utilization,
+            "ceph-mon": avg_mon_memory_utilization,
+            "ceph-osd": avg_osd_memory_utilization,
+        },
+        "avg_network_util_bps": {
+            "sent": avg_storage_sent_bps,
+            "recv": avg_storage_recv_bps,
+            "total": avg_storage_total_bps,
+        },
+    }
+
     try:
         jstdout = loads(stdout)
         if retcode:
             raise
     except Exception:
-        cleanup(
-            job_name,
-            db_conn=db_conn,
-            db_cur=db_cur,
-            zkhandler=zkhandler,
-        )
-        fail(
-            None,
-            f"Failed to run fio test '{test}': {stderr}",
-        )
+        return None, None
 
-    return jstdout
+    return resource_data, jstdout
 
 
-def worker_run_benchmark(zkhandler, celery, config, pool):
+def worker_run_benchmark(zkhandler, celery, config, pool, name):
     # Phase 0 - connect to databases
-    cur_time = datetime.now().isoformat(timespec="seconds")
-    cur_primary = zkhandler.read("base.config.primary_node")
-    job_name = f"{cur_time}_{cur_primary}"
+    if not name:
+        cur_time = datetime.now().isoformat(timespec="seconds")
+        cur_primary = zkhandler.read("base.config.primary_node")
+        job_name = f"{cur_time}_{cur_primary}"
+    else:
+        job_name = name
 
     current_stage = 0
     total_stages = 13
@@ -357,7 +495,8 @@ def worker_run_benchmark(zkhandler, celery, config, pool):
             total=total_stages,
         )
 
-        results[test] = run_benchmark_job(
+        resource_data, fio_data = run_benchmark_job(
+            config,
             test,
             pool,
             job_name=job_name,
@@ -365,6 +504,25 @@ def worker_run_benchmark(zkhandler, celery, config, pool):
             db_cur=db_cur,
             zkhandler=zkhandler,
         )
+        if resource_data is None or fio_data is None:
+            cleanup_benchmark_volume(
+                pool,
+                job_name=job_name,
+                db_conn=db_conn,
+                db_cur=db_cur,
+                zkhandler=zkhandler,
+            )
+            cleanup(
+                job_name,
+                db_conn=db_conn,
+                db_cur=db_cur,
+                zkhandler=zkhandler,
+            )
+            fail(
+                None,
+                f"Failed to run fio test '{test}'",
+            )
+        results[test] = {**resource_data, **fio_data}
 
     # Phase 3 - cleanup
     current_stage += 1
@@ -410,6 +568,7 @@ def worker_run_benchmark(zkhandler, celery, config, pool):
         db_conn=db_conn,
         db_cur=db_cur,
         zkhandler=zkhandler,
+        final=True,
     )
 
     current_stage += 1

daemon-common/celery.py

@@ -3,7 +3,7 @@
 # celery.py - PVC client function library, Celery helper fuctions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2023 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

daemon-common/ceph.py

@@ -3,7 +3,7 @@
 # ceph.py - PVC client function library, Ceph cluster fuctions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -123,13 +123,13 @@ def format_bytes_tohuman(databytes):
 def format_bytes_fromhuman(datahuman):
     if not re.search(r"[A-Za-z]+", datahuman):
         dataunit = "B"
-        datasize = int(datahuman)
+        datasize = float(datahuman)
     else:
-        dataunit = str(re.match(r"[0-9]+([A-Za-z])[iBb]*", datahuman).group(1))
-        datasize = int(re.match(r"([0-9]+)[A-Za-z]+", datahuman).group(1))
+        dataunit = str(re.match(r"[0-9\.]+([A-Za-z])[iBb]*", datahuman).group(1))
+        datasize = float(re.match(r"([0-9\.]+)[A-Za-z]+", datahuman).group(1))
 
-    if byte_unit_matrix.get(dataunit):
-        databytes = datasize * byte_unit_matrix[dataunit]
+    if byte_unit_matrix.get(dataunit.upper()):
+        databytes = int(datasize * byte_unit_matrix[dataunit.upper()])
         return databytes
     else:
         return None
@@ -155,7 +155,7 @@ def format_ops_fromhuman(datahuman):
     # Trim off human-readable character
     dataunit = datahuman[-1]
     datasize = int(datahuman[:-1])
-    dataops = datasize * ops_unit_matrix[dataunit]
+    dataops = datasize * ops_unit_matrix[dataunit.upper()]
     return "{}".format(dataops)
 
 
@@ -320,7 +320,11 @@ def get_list_osd(zkhandler, limit=None, is_fuzzy=True):
 #
 def getPoolInformation(zkhandler, pool):
     # Parse the stats data
-    (pool_stats_raw, tier, pgs,) = zkhandler.read_many(
+    (
+        pool_stats_raw,
+        tier,
+        pgs,
+    ) = zkhandler.read_many(
         [
             ("pool.stats", pool),
             ("pool.tier", pool),
@@ -536,7 +540,10 @@ def getCephVolumes(zkhandler, pool):
         pool_list = [pool]
 
     for pool_name in pool_list:
-        for volume_name in zkhandler.children(("volume", pool_name)):
+        children = zkhandler.children(("volume", pool_name))
+        if children is None:
+            continue
+        for volume_name in children:
             volume_list.append("{}/{}".format(pool_name, volume_name))
 
     return volume_list
@@ -553,7 +560,21 @@ def getVolumeInformation(zkhandler, pool, volume):
     return volume_information
 
 
-def add_volume(zkhandler, pool, name, size):
+def scan_volume(zkhandler, pool, name):
+    retcode, stdout, stderr = common.run_os_command(
+        "rbd info --format json {}/{}".format(pool, name)
+    )
+    volstats = stdout
+
+    # 3. Add the new volume to Zookeeper
+    zkhandler.write(
+        [
+            (("volume.stats", f"{pool}/{name}"), volstats),
+        ]
+    )
+
+
+def add_volume(zkhandler, pool, name, size, force_flag=False, zk_only=False):
     # 1. Verify the size of the volume
     pool_information = getPoolInformation(zkhandler, pool)
     size_bytes = format_bytes_fromhuman(size)
@@ -563,46 +584,88 @@ def add_volume(zkhandler, pool, name, size):
             f"ERROR: Requested volume size '{size}' does not have a valid SI unit",
         )
 
-    if size_bytes >= int(pool_information["stats"]["free_bytes"]):
+    pool_total_free_bytes = int(pool_information["stats"]["free_bytes"])
+    if size_bytes >= pool_total_free_bytes:
         return (
             False,
             f"ERROR: Requested volume size '{format_bytes_tohuman(size_bytes)}' is greater than the available free space in the pool ('{format_bytes_tohuman(pool_information['stats']['free_bytes'])}')",
         )
 
-    # 2. Create the volume
-    retcode, stdout, stderr = common.run_os_command(
-        "rbd create --size {}B {}/{}".format(size_bytes, pool, name)
+    # Check if we're greater than 80% utilization after the create; error if so unless we have the force flag
+    pool_total_bytes = (
+        int(pool_information["stats"]["used_bytes"]) + pool_total_free_bytes
     )
-    if retcode:
-        return False, 'ERROR: Failed to create RBD volume "{}": {}'.format(name, stderr)
+    pool_safe_total_bytes = int(pool_total_bytes * 0.80)
+    pool_safe_free_bytes = pool_safe_total_bytes - int(
+        pool_information["stats"]["used_bytes"]
+    )
+    if size_bytes >= pool_safe_free_bytes and not force_flag:
+        return (
+            False,
+            f"ERROR: Requested volume size '{format_bytes_tohuman(size_bytes)}' is greater than the safe free space in the pool ('{format_bytes_tohuman(pool_safe_free_bytes)}' for 80% full); retry with force to ignore this error",
+        )
 
-    # 2. Get volume stats
-    retcode, stdout, stderr = common.run_os_command(
-        "rbd info --format json {}/{}".format(pool, name)
-    )
-    volstats = stdout
+    # 2. Create the volume
+    # zk_only flag skips actually creating the volume - this would be done by some other mechanism
+    if not zk_only:
+        retcode, stdout, stderr = common.run_os_command(
+            "rbd create --size {}B {}/{}".format(size_bytes, pool, name)
+        )
+        if retcode:
+            return False, 'ERROR: Failed to create RBD volume "{}": {}'.format(
+                name, stderr
+            )
 
     # 3. Add the new volume to Zookeeper
     zkhandler.write(
         [
             (("volume", f"{pool}/{name}"), ""),
-            (("volume.stats", f"{pool}/{name}"), volstats),
+            (("volume.stats", f"{pool}/{name}"), ""),
             (("snapshot", f"{pool}/{name}"), ""),
         ]
     )
 
+    # 4. Scan the volume stats
+    scan_volume(zkhandler, pool, name)
+
     return True, 'Created RBD volume "{}" of size "{}" in pool "{}".'.format(
         name, format_bytes_tohuman(size_bytes), pool
     )
 
 
-def clone_volume(zkhandler, pool, name_src, name_new):
+def clone_volume(zkhandler, pool, name_src, name_new, force_flag=False):
+    # 1. Verify the volume
     if not verifyVolume(zkhandler, pool, name_src):
         return False, 'ERROR: No volume with name "{}" is present in pool "{}".'.format(
             name_src, pool
         )
 
-    # 1. Clone the volume
+    volume_stats_raw = zkhandler.read(("volume.stats", f"{pool}/{name_src}"))
+    volume_stats = dict(json.loads(volume_stats_raw))
+    size_bytes = volume_stats["size"]
+    pool_information = getPoolInformation(zkhandler, pool)
+    pool_total_free_bytes = int(pool_information["stats"]["free_bytes"])
+    if size_bytes >= pool_total_free_bytes:
+        return (
+            False,
+            f"ERROR: Clone volume size '{format_bytes_tohuman(size_bytes)}' is greater than the available free space in the pool ('{format_bytes_tohuman(pool_information['stats']['free_bytes'])}')",
+        )
+
+    # Check if we're greater than 80% utilization after the create; error if so unless we have the force flag
+    pool_total_bytes = (
+        int(pool_information["stats"]["used_bytes"]) + pool_total_free_bytes
+    )
+    pool_safe_total_bytes = int(pool_total_bytes * 0.80)
+    pool_safe_free_bytes = pool_safe_total_bytes - int(
+        pool_information["stats"]["used_bytes"]
+    )
+    if size_bytes >= pool_safe_free_bytes and not force_flag:
+        return (
+            False,
+            f"ERROR: Clone volume size '{format_bytes_tohuman(size_bytes)}' is greater than the safe free space in the pool ('{format_bytes_tohuman(pool_safe_free_bytes)}' for 80% full); retry with force to ignore this error",
+        )
+
+    # 2. Clone the volume
     retcode, stdout, stderr = common.run_os_command(
         "rbd copy {}/{} {}/{}".format(pool, name_src, pool, name_new)
     )
@@ -614,27 +677,24 @@ def clone_volume(zkhandler, pool, name_src, name_new):
             ),
         )
 
-    # 2. Get volume stats
-    retcode, stdout, stderr = common.run_os_command(
-        "rbd info --format json {}/{}".format(pool, name_new)
-    )
-    volstats = stdout
-
     # 3. Add the new volume to Zookeeper
     zkhandler.write(
         [
             (("volume", f"{pool}/{name_new}"), ""),
-            (("volume.stats", f"{pool}/{name_new}"), volstats),
+            (("volume.stats", f"{pool}/{name_new}"), ""),
             (("snapshot", f"{pool}/{name_new}"), ""),
         ]
     )
 
+    # 4. Scan the volume stats
+    scan_volume(zkhandler, pool, name_new)
+
     return True, 'Cloned RBD volume "{}" to "{}" in pool "{}"'.format(
         name_src, name_new, pool
     )
 
 
-def resize_volume(zkhandler, pool, name, size):
+def resize_volume(zkhandler, pool, name, size, force_flag=False):
     if not verifyVolume(zkhandler, pool, name):
         return False, 'ERROR: No volume with name "{}" is present in pool "{}".'.format(
             name, pool
@@ -649,12 +709,27 @@ def resize_volume(zkhandler, pool, name, size):
             f"ERROR: Requested volume size '{size}' does not have a valid SI unit",
         )
 
-    if size_bytes >= int(pool_information["stats"]["free_bytes"]):
+    pool_total_free_bytes = int(pool_information["stats"]["free_bytes"])
+    if size_bytes >= pool_total_free_bytes:
         return (
             False,
             f"ERROR: Requested volume size '{format_bytes_tohuman(size_bytes)}' is greater than the available free space in the pool ('{format_bytes_tohuman(pool_information['stats']['free_bytes'])}')",
         )
 
+    # Check if we're greater than 80% utilization after the create; error if so unless we have the force flag
+    pool_total_bytes = (
+        int(pool_information["stats"]["used_bytes"]) + pool_total_free_bytes
+    )
+    pool_safe_total_bytes = int(pool_total_bytes * 0.80)
+    pool_safe_free_bytes = pool_safe_total_bytes - int(
+        pool_information["stats"]["used_bytes"]
+    )
+    if size_bytes >= pool_safe_free_bytes and not force_flag:
+        return (
+            False,
+            f"ERROR: Requested volume size '{format_bytes_tohuman(size_bytes)}' is greater than the safe free space in the pool ('{format_bytes_tohuman(pool_safe_free_bytes)}' for 80% full); retry with force to ignore this error",
+        )
+
     # 2. Resize the volume
     retcode, stdout, stderr = common.run_os_command(
         "rbd resize --size {} {}/{}".format(
@@ -698,20 +773,8 @@ def resize_volume(zkhandler, pool, name, size):
         except Exception:
             pass
 
-    # 4. Get volume stats
-    retcode, stdout, stderr = common.run_os_command(
-        "rbd info --format json {}/{}".format(pool, name)
-    )
-    volstats = stdout
-
-    # 5. Update the volume in Zookeeper
-    zkhandler.write(
-        [
-            (("volume", f"{pool}/{name}"), ""),
-            (("volume.stats", f"{pool}/{name}"), volstats),
-            (("snapshot", f"{pool}/{name}"), ""),
-        ]
-    )
+    # 4. Scan the volume stats
+    scan_volume(zkhandler, pool, name)
 
     return True, 'Resized RBD volume "{}" to size "{}" in pool "{}".'.format(
         name, format_bytes_tohuman(size_bytes), pool
@@ -744,18 +807,8 @@ def rename_volume(zkhandler, pool, name, new_name):
         ]
     )
 
-    # 3. Get volume stats
-    retcode, stdout, stderr = common.run_os_command(
-        "rbd info --format json {}/{}".format(pool, new_name)
-    )
-    volstats = stdout
-
-    # 4. Update the volume stats in Zookeeper
-    zkhandler.write(
-        [
-            (("volume.stats", f"{pool}/{new_name}"), volstats),
-        ]
-    )
+    # 3. Scan the volume stats
+    scan_volume(zkhandler, pool, new_name)
 
     return True, 'Renamed RBD volume "{}" to "{}" in pool "{}".'.format(
         name, new_name, pool
@@ -768,10 +821,22 @@ def remove_volume(zkhandler, pool, name):
             name, pool
         )
 
-    # 1. Remove volume snapshots
+    # 1a. Remove PVC-managed volume snapshots
     for snapshot in zkhandler.children(("snapshot", f"{pool}/{name}")):
         remove_snapshot(zkhandler, pool, name, snapshot)
 
+    # 1b. Purge any remaining volume snapshots
+    retcode, stdout, stderr = common.run_os_command(
+        "rbd snap purge {}/{}".format(pool, name)
+    )
+    if retcode:
+        return (
+            False,
+            'ERROR: Failed to purge snapshots from RBD volume "{}" in pool "{}": {}'.format(
+                name, pool, stderr
+            ),
+        )
+
     # 2. Remove the volume
     retcode, stdout, stderr = common.run_os_command("rbd rm {}/{}".format(pool, name))
     if retcode:
@@ -940,23 +1005,27 @@ def add_snapshot(zkhandler, pool, volume, name, zk_only=False):
                 ),
             )
 
-    # 2. Add the snapshot to Zookeeper
+    # 2. Get snapshot stats
+    retcode, stdout, stderr = common.run_os_command(
+        "rbd info --format json {}/{}@{}".format(pool, volume, name)
+    )
+    snapstats = stdout
+
+    # 3. Add the snapshot to Zookeeper
     zkhandler.write(
         [
             (("snapshot", f"{pool}/{volume}/{name}"), ""),
-            (("snapshot.stats", f"{pool}/{volume}/{name}"), "{}"),
+            (("snapshot.stats", f"{pool}/{volume}/{name}"), snapstats),
         ]
     )
 
-    # 3. Update the count of snapshots on this volume
+    # 4. Update the count of snapshots on this volume
     volume_stats_raw = zkhandler.read(("volume.stats", f"{pool}/{volume}"))
     volume_stats = dict(json.loads(volume_stats_raw))
-    # Format the size to something nicer
     volume_stats["snapshot_count"] = volume_stats["snapshot_count"] + 1
-    volume_stats_raw = json.dumps(volume_stats)
     zkhandler.write(
         [
-            (("volume.stats", f"{pool}/{volume}"), volume_stats_raw),
+            (("volume.stats", f"{pool}/{volume}"), json.dumps(volume_stats)),
         ]
     )
 
@@ -1010,6 +1079,36 @@ def rename_snapshot(zkhandler, pool, volume, name, new_name):
     )
 
 
+def rollback_snapshot(zkhandler, pool, volume, name):
+    if not verifyVolume(zkhandler, pool, volume):
+        return False, 'ERROR: No volume with name "{}" is present in pool "{}".'.format(
+            volume, pool
+        )
+    if not verifySnapshot(zkhandler, pool, volume, name):
+        return (
+            False,
+            'ERROR: No snapshot with name "{}" is present for volume "{}" in pool "{}".'.format(
+                name, volume, pool
+            ),
+        )
+
+    # 1. Roll back the snapshot
+    retcode, stdout, stderr = common.run_os_command(
+        "rbd snap rollback {}/{}@{}".format(pool, volume, name)
+    )
+    if retcode:
+        return (
+            False,
+            'ERROR: Failed to roll back RBD volume "{}" in pool "{}" to snapshot "{}": {}'.format(
+                volume, pool, name, stderr
+            ),
+        )
+
+    return True, 'Rolled back RBD volume "{}" in pool "{}" to snapshot "{}".'.format(
+        volume, pool, name
+    )
+
+
 def remove_snapshot(zkhandler, pool, volume, name):
     if not verifyVolume(zkhandler, pool, volume):
         return False, 'ERROR: No volume with name "{}" is present in pool "{}".'.format(
@@ -1051,20 +1150,9 @@ def remove_snapshot(zkhandler, pool, volume, name):
     )
 
 
-def get_list_snapshot(zkhandler, pool, volume, limit=None, is_fuzzy=True):
+def get_list_snapshot(zkhandler, target_pool, target_volume, limit=None, is_fuzzy=True):
     snapshot_list = []
-    if pool and not verifyPool(zkhandler, pool):
-        return False, 'ERROR: No pool with name "{}" is present in the cluster.'.format(
-            pool
-        )
-
-    if volume and not verifyPool(zkhandler, volume):
-        return (
-            False,
-            'ERROR: No volume with name "{}" is present in the cluster.'.format(volume),
-        )
-
-    full_snapshot_list = getCephSnapshots(zkhandler, pool, volume)
+    full_snapshot_list = getCephSnapshots(zkhandler, target_pool, target_volume)
 
     if is_fuzzy and limit:
         # Implicitly assume fuzzy limits
@@ -1076,6 +1164,18 @@ def get_list_snapshot(zkhandler, pool, volume, limit=None, is_fuzzy=True):
     for snapshot in full_snapshot_list:
         volume, snapshot_name = snapshot.split("@")
         pool_name, volume_name = volume.split("/")
+        if target_pool and pool_name != target_pool:
+            continue
+        if target_volume and volume_name != target_volume:
+            continue
+        try:
+            snapshot_stats = json.loads(
+                zkhandler.read(
+                    ("snapshot.stats", f"{pool_name}/{volume_name}/{snapshot_name}")
+                )
+            )
+        except Exception:
+            snapshot_stats = []
         if limit:
             try:
                 if re.fullmatch(limit, snapshot_name):
@@ -1084,13 +1184,19 @@ def get_list_snapshot(zkhandler, pool, volume, limit=None, is_fuzzy=True):
                             "pool": pool_name,
                             "volume": volume_name,
                             "snapshot": snapshot_name,
+                            "stats": snapshot_stats,
                         }
                     )
             except Exception as e:
                 return False, "Regex Error: {}".format(e)
         else:
             snapshot_list.append(
-                {"pool": pool_name, "volume": volume_name, "snapshot": snapshot_name}
+                {
+                    "pool": pool_name,
+                    "volume": volume_name,
+                    "snapshot": snapshot_name,
+                    "stats": snapshot_stats,
+                }
             )
 
     return True, sorted(snapshot_list, key=lambda x: str(x["snapshot"]))
@@ -1125,16 +1231,16 @@ def osd_worker_add_osd(
     current_stage = 0
     total_stages = 5
     if split_count is None:
-        _split_count = 1
+        split_count = 1
     else:
-        _split_count = split_count
-    total_stages = total_stages + 3 * int(_split_count)
+        split_count = int(split_count)
+    total_stages = total_stages + 3 * int(split_count)
     if ext_db_ratio is not None or ext_db_size is not None:
-        total_stages = total_stages + 3 * int(_split_count) + 1
+        total_stages = total_stages + 3 * int(split_count) + 1
 
     start(
         celery,
-        f"Adding {_split_count} new OSD(s) on device {device} with weight {weight}",
+        f"Adding {split_count} new OSD(s) on device {device} with weight {weight}",
         current=current_stage,
         total=total_stages,
     )
@@ -1175,7 +1281,7 @@ def osd_worker_add_osd(
     else:
         ext_db_flag = False
 
-    if split_count is not None:
+    if split_count > 1:
         split_flag = f"--osds-per-device {split_count}"
         is_split = True
         log_info(

daemon-common/common.py

@@ -3,7 +3,7 @@
 # common.py - PVC client function library, common fuctions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -26,8 +26,10 @@ import subprocess
 import signal
 from json import loads
 from re import match as re_match
+from re import search as re_search
 from re import split as re_split
 from re import sub as re_sub
+from difflib import unified_diff
 from distutils.util import strtobool
 from threading import Thread
 from shlex import split as shlex_split
@@ -53,6 +55,10 @@ node_state_combinations = [
     "init,flush",
     "init,flushed",
     "init,unflush",
+    "shutdown,ready",
+    "shutdown,flush",
+    "shutdown,flushed",
+    "shutdown,unflush",
     "stop,ready",
     "stop,flush",
     "stop,flushed",
@@ -77,6 +83,9 @@ vm_state_combinations = [
     "migrate",
     "unmigrate",
     "provision",
+    "import",
+    "restore",
+    "mirror",
 ]
 ceph_osd_state_combinations = [
     "up,in",
@@ -423,6 +432,96 @@ def getDomainTags(zkhandler, dom_uuid):
     return tags
 
 
+#
+# Get a list of domain snapshots
+#
+def getDomainSnapshots(zkhandler, dom_uuid):
+    """
+    Get a list of snapshots for domain dom_uuid
+
+    The UUID must be validated before calling this function!
+    """
+    snapshots = list()
+
+    all_snapshots = zkhandler.children(("domain.snapshots", dom_uuid))
+
+    current_timestamp = time.time()
+    current_dom_xml = zkhandler.read(("domain.xml", dom_uuid))
+
+    snapshots = list()
+    for snapshot in all_snapshots:
+        (
+            snap_name,
+            snap_timestamp,
+            _snap_rbd_snapshots,
+            snap_dom_xml,
+        ) = zkhandler.read_many(
+            [
+                ("domain.snapshots", dom_uuid, "domain_snapshot.name", snapshot),
+                ("domain.snapshots", dom_uuid, "domain_snapshot.timestamp", snapshot),
+                (
+                    "domain.snapshots",
+                    dom_uuid,
+                    "domain_snapshot.rbd_snapshots",
+                    snapshot,
+                ),
+                ("domain.snapshots", dom_uuid, "domain_snapshot.xml", snapshot),
+            ]
+        )
+
+        snap_rbd_snapshots = _snap_rbd_snapshots.split(",")
+
+        snap_dom_xml_diff = list(
+            unified_diff(
+                current_dom_xml.split("\n"),
+                snap_dom_xml.split("\n"),
+                fromfile="current",
+                tofile="snapshot",
+                fromfiledate="",
+                tofiledate="",
+                n=1,
+                lineterm="",
+            )
+        )
+
+        _snap_timestamp = float(snap_timestamp)
+        snap_age_secs = int(current_timestamp) - int(_snap_timestamp)
+        snap_age = f"{snap_age_secs} seconds"
+        snap_age_minutes = int(snap_age_secs / 60)
+        if snap_age_minutes > 0:
+            if snap_age_minutes > 1:
+                s = "s"
+            else:
+                s = ""
+            snap_age = f"{snap_age_minutes} minute{s}"
+        snap_age_hours = int(snap_age_secs / 3600)
+        if snap_age_hours > 0:
+            if snap_age_hours > 1:
+                s = "s"
+            else:
+                s = ""
+            snap_age = f"{snap_age_hours} hour{s}"
+        snap_age_days = int(snap_age_secs / 86400)
+        if snap_age_days > 0:
+            if snap_age_days > 1:
+                s = "s"
+            else:
+                s = ""
+            snap_age = f"{snap_age_days} day{s}"
+
+        snapshots.append(
+            {
+                "name": snap_name,
+                "timestamp": snap_timestamp,
+                "age": snap_age,
+                "xml_diff_lines": snap_dom_xml_diff,
+                "rbd_snapshots": snap_rbd_snapshots,
+            }
+        )
+
+    return sorted(snapshots, key=lambda s: s["timestamp"], reverse=True)
+
+
 #
 # Get a set of domain metadata
 #
@@ -437,12 +536,14 @@ def getDomainMetadata(zkhandler, dom_uuid):
         domain_node_selector,
         domain_node_autostart,
         domain_migration_method,
+        domain_migration_max_downtime,
     ) = zkhandler.read_many(
         [
             ("domain.meta.node_limit", dom_uuid),
             ("domain.meta.node_selector", dom_uuid),
             ("domain.meta.autostart", dom_uuid),
             ("domain.meta.migrate_method", dom_uuid),
+            ("domain.meta.migrate_max_downtime", dom_uuid),
         ]
     )
 
@@ -460,11 +561,15 @@ def getDomainMetadata(zkhandler, dom_uuid):
     if not domain_migration_method or domain_migration_method == "none":
         domain_migration_method = None
 
+    if not domain_migration_max_downtime or domain_migration_max_downtime == "none":
+        domain_migration_max_downtime = 300
+
     return (
         domain_node_limit,
         domain_node_selector,
         domain_node_autostart,
         domain_migration_method,
+        domain_migration_max_downtime,
     )
 
 
@@ -501,9 +606,11 @@ def getInformationFromXML(zkhandler, uuid):
         domain_node_selector,
         domain_node_autostart,
         domain_migration_method,
+        domain_migration_max_downtime,
     ) = getDomainMetadata(zkhandler, uuid)
 
     domain_tags = getDomainTags(zkhandler, uuid)
+    domain_snapshots = getDomainSnapshots(zkhandler, uuid)
 
     if domain_vnc:
         domain_vnc_listen, domain_vnc_port = domain_vnc.split(":")
@@ -561,7 +668,9 @@ def getInformationFromXML(zkhandler, uuid):
         "node_selector": domain_node_selector,
         "node_autostart": bool(strtobool(domain_node_autostart)),
         "migration_method": domain_migration_method,
+        "migration_max_downtime": int(domain_migration_max_downtime),
         "tags": domain_tags,
+        "snapshots": domain_snapshots,
         "description": domain_description,
         "profile": domain_profile,
         "memory": int(domain_memory),
@@ -966,7 +1075,7 @@ def sortInterfaceNames(interface_names):
 #
 # Parse a "detect" device into a real block device name
 #
-def get_detect_device(detect_string):
+def get_detect_device_lsscsi(detect_string):
     """
     Parses a "detect:" string into a normalized block device path using lsscsi.
 
@@ -1033,3 +1142,96 @@ def get_detect_device(detect_string):
             break
 
     return blockdev
+
+
+def get_detect_device_nvme(detect_string):
+    """
+    Parses a "detect:" string into a normalized block device path using nvme.
+
+    A detect string is formatted "detect:<NAME>:<SIZE>:<ID>", where
+    NAME is some unique identifier in lsscsi, SIZE is a human-readable
+    size value to within +/- 3% of the real size of the device, and
+    ID is the Nth (0-indexed) matching entry of that NAME and SIZE.
+    """
+
+    unit_map = {
+        "kB": 1000,
+        "MB": 1000 * 1000,
+        "GB": 1000 * 1000 * 1000,
+        "TB": 1000 * 1000 * 1000 * 1000,
+        "PB": 1000 * 1000 * 1000 * 1000 * 1000,
+        "EB": 1000 * 1000 * 1000 * 1000 * 1000 * 1000,
+    }
+
+    _, name, _size, idd = detect_string.split(":")
+    if _ != "detect":
+        return None
+
+    size_re = re_search(r"([\d.]+)([kKMGTP]B)", _size)
+    size_val = float(size_re.group(1))
+    size_unit = size_re.group(2)
+    size_bytes = int(size_val * unit_map[size_unit])
+
+    retcode, stdout, stderr = run_os_command("nvme list --output-format json")
+    if retcode:
+        print(f"Failed to run nvme: {stderr}")
+        return None
+
+    # Parse the output with json
+    nvme_data = loads(stdout).get("Devices", list())
+
+    # Handle size determination (+/- 3%)
+    size = None
+    nvme_sizes = set()
+    for entry in nvme_data:
+        nvme_sizes.add(entry["PhysicalSize"])
+    for l_size in nvme_sizes:
+        plusthreepct = size_bytes * 1.03
+        minusthreepct = size_bytes * 0.97
+
+        if l_size > minusthreepct and l_size < plusthreepct:
+            size = l_size
+            break
+    if size is None:
+        return None
+
+    blockdev = None
+    matches = list()
+    for entry in nvme_data:
+        # Skip if name is not contained in the line (case-insensitive)
+        if name.lower() not in entry["ModelNumber"].lower():
+            continue
+        # Skip if the size does not match
+        if size != entry["PhysicalSize"]:
+            continue
+        # Get our blockdev and append to the list
+        matches.append(entry["DevicePath"])
+
+    blockdev = None
+    # Find the blockdev at index {idd}
+    for idx, _blockdev in enumerate(matches):
+        if int(idx) == int(idd):
+            blockdev = _blockdev
+            break
+
+    return blockdev
+
+
+def get_detect_device(detect_string):
+    """
+    Parses a "detect:" string into a normalized block device path.
+
+    First tries to parse using "lsscsi" (get_detect_device_lsscsi). If this returns an invalid
+    block device name, then try to parse using "nvme" (get_detect_device_nvme). This works around
+    issues with more recent devices (e.g. the Dell R6615 series) not properly reporting block
+    device paths for NVMe devices with "lsscsi".
+    """
+
+    device = get_detect_device_lsscsi(detect_string)
+    if device is None or not re_match(r"^/dev", device):
+        device = get_detect_device_nvme(detect_string)
+
+    if device is not None and re_match(r"^/dev", device):
+        return device
+    else:
+        return None

daemon-common/config.py

@@ -3,7 +3,7 @@
 # config.py - Utility functions for pvcnoded configuration parsing
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -176,6 +176,7 @@ def get_parsed_configuration(config_file):
             "enable_storage": o_subsystem.get("enable_storage", True),
             "enable_worker": o_subsystem.get("enable_worker", True),
             "enable_api": o_subsystem.get("enable_api", True),
+            "enable_prometheus": o_subsystem.get("enable_prometheus", True),
         }
         config = {**config, **config_subsystem}
 
@@ -243,9 +244,9 @@ def get_parsed_configuration(config_file):
                     ]
                 ][0]
 
-            config_cluster_networks_specific[
-                f"{network_type}_dev_ip"
-            ] = f"{list(network.hosts())[address_id]}/{network.prefixlen}"
+            config_cluster_networks_specific[f"{network_type}_dev_ip"] = (
+                f"{list(network.hosts())[address_id]}/{network.prefixlen}"
+            )
 
             config = {**config, **config_cluster_networks_specific}
 
@@ -374,8 +375,11 @@ def get_parsed_configuration(config_file):
         config = {**config, **config_api_ssl}
 
         # Use coordinators as storage hosts if not explicitly specified
+        # These are added as FQDNs in the storage domain
         if not config["storage_hosts"] or len(config["storage_hosts"]) < 1:
-            config["storage_hosts"] = config["coordinators"]
+            config["storage_hosts"] = []
+            for host in config["coordinators"]:
+                config["storage_hosts"].append(f"{host}.{config['storage_domain']}")
 
         # Set up our token list if specified
         if config["api_auth_source"] == "token":
@@ -405,6 +409,78 @@ def get_configuration():
     return config
 
 
+def get_parsed_autobackup_configuration(config_file):
+    """
+    Load the configuration; this is the same main pvc.conf that the daemons read
+    """
+    print('Loading configuration from file "{}"'.format(config_file))
+
+    with open(config_file, "r") as cfgfh:
+        try:
+            o_config = yaml.load(cfgfh, Loader=yaml.SafeLoader)
+        except Exception as e:
+            print(f"ERROR: Failed to parse configuration file: {e}")
+            os._exit(1)
+
+    config = dict()
+
+    try:
+        o_cluster = o_config["cluster"]
+        config_cluster = {
+            "cluster": o_cluster["name"],
+            "autobackup_enabled": True,
+        }
+        config = {**config, **config_cluster}
+
+        o_autobackup = o_config["autobackup"]
+        if o_autobackup is None:
+            config["autobackup_enabled"] = False
+            return config
+
+        config_autobackup = {
+            "backup_root_path": o_autobackup["backup_root_path"],
+            "backup_root_suffix": o_autobackup["backup_root_suffix"],
+            "backup_tags": o_autobackup["backup_tags"],
+            "backup_schedule": o_autobackup["backup_schedule"],
+        }
+        config = {**config, **config_autobackup}
+
+        o_automount = o_autobackup["auto_mount"]
+        config_automount = {
+            "auto_mount_enabled": o_automount["enabled"],
+        }
+        config = {**config, **config_automount}
+        if config["auto_mount_enabled"]:
+            config["mount_cmds"] = list()
+            for _mount_cmd in o_automount["mount_cmds"]:
+                if "{backup_root_path}" in _mount_cmd:
+                    _mount_cmd = _mount_cmd.format(
+                        backup_root_path=config["backup_root_path"]
+                    )
+                config["mount_cmds"].append(_mount_cmd)
+            config["unmount_cmds"] = list()
+            for _unmount_cmd in o_automount["unmount_cmds"]:
+                if "{backup_root_path}" in _unmount_cmd:
+                    _unmount_cmd = _unmount_cmd.format(
+                        backup_root_path=config["backup_root_path"]
+                    )
+                config["unmount_cmds"].append(_unmount_cmd)
+
+    except Exception as e:
+        raise MalformedConfigurationError(e)
+
+    return config
+
+
+def get_autobackup_configuration():
+    """
+    Get the configuration.
+    """
+    pvc_config_file = get_configuration_path()
+    config = get_parsed_autobackup_configuration(pvc_config_file)
+    return config
+
+
 def validate_directories(config):
     if not os.path.exists(config["dynamic_directory"]):
         os.makedirs(config["dynamic_directory"])

daemon-common/faults.py

@@ -3,7 +3,7 @@
 # faults.py - PVC client function library, faults management
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

daemon-common/libvirt_schema.py

@@ -3,7 +3,7 @@
 # libvirt_schema.py - Libvirt schema elements
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

daemon-common/log.py

@@ -3,7 +3,7 @@
 # log.py - PVC daemon logger functions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -115,6 +115,10 @@ class Logger(object):
 
     # Output function
     def out(self, message, state=None, prefix=""):
+        # Only handle d-state (debug) messages if we're in debug mode
+        if state in ["d"] and not self.config["debug"]:
+            return
+
         # Get the date
         if self.config["log_dates"]:
             date = "{} ".format(datetime.now().strftime("%Y/%m/%d %H:%M:%S.%f"))
@@ -146,7 +150,7 @@ class Logger(object):
         if self.config["stdout_logging"]:
             # Assemble output string
             output = colour + prompt + endc + date + prefix + message
-            print(output)
+            print(output + "\n", end="")
 
         # Log to file
         if self.config["file_logging"]:

daemon-common/migrations/versions/12.json

@@ -0,0 +1 @@
+{"version": "12", "root": "", "base": {"root": "", "schema": "/schema", "schema.version": "/schema/version", "config": "/config", "config.maintenance": "/config/maintenance", "config.primary_node": "/config/primary_node", "config.primary_node.sync_lock": "/config/primary_node/sync_lock", "config.upstream_ip": "/config/upstream_ip", "config.migration_target_selector": "/config/migration_target_selector", "logs": "/logs", "faults": "/faults", "node": "/nodes", "domain": "/domains", "network": "/networks", "storage": "/ceph", "storage.health": "/ceph/health", "storage.util": "/ceph/util", "osd": "/ceph/osds", "pool": "/ceph/pools", "volume": "/ceph/volumes", "snapshot": "/ceph/snapshots"}, "logs": {"node": "", "messages": "/messages"}, "faults": {"id": "", "last_time": "/last_time", "first_time": "/first_time", "ack_time": "/ack_time", "status": "/status", "delta": "/delta", "message": "/message"}, "node": {"name": "", "keepalive": "/keepalive", "mode": "/daemonmode", "data.active_schema": "/activeschema", "data.latest_schema": "/latestschema", "data.static": "/staticdata", "data.pvc_version": "/pvcversion", "running_domains": "/runningdomains", "count.provisioned_domains": "/domainscount", "count.networks": "/networkscount", "state.daemon": "/daemonstate", "state.router": "/routerstate", "state.domain": "/domainstate", "cpu.load": "/cpuload", "vcpu.allocated": "/vcpualloc", "memory.total": "/memtotal", "memory.used": "/memused", "memory.free": "/memfree", "memory.allocated": "/memalloc", "memory.provisioned": "/memprov", "ipmi.hostname": "/ipmihostname", "ipmi.username": "/ipmiusername", "ipmi.password": "/ipmipassword", "sriov": "/sriov", "sriov.pf": "/sriov/pf", "sriov.vf": "/sriov/vf", "monitoring.plugins": "/monitoring_plugins", "monitoring.data": "/monitoring_data", "monitoring.health": "/monitoring_health", "network.stats": "/network_stats"}, "monitoring_plugin": {"name": "", "last_run": "/last_run", "health_delta": "/health_delta", "message": "/message", "data": "/data", "runtime": "/runtime"}, "sriov_pf": {"phy": "", "mtu": "/mtu", "vfcount": "/vfcount"}, "sriov_vf": {"phy": "", "pf": "/pf", "mtu": "/mtu", "mac": "/mac", "phy_mac": "/phy_mac", "config": "/config", "config.vlan_id": "/config/vlan_id", "config.vlan_qos": "/config/vlan_qos", "config.tx_rate_min": "/config/tx_rate_min", "config.tx_rate_max": "/config/tx_rate_max", "config.spoof_check": "/config/spoof_check", "config.link_state": "/config/link_state", "config.trust": "/config/trust", "config.query_rss": "/config/query_rss", "pci": "/pci", "pci.domain": "/pci/domain", "pci.bus": "/pci/bus", "pci.slot": "/pci/slot", "pci.function": "/pci/function", "used": "/used", "used_by": "/used_by"}, "domain": {"name": "", "xml": "/xml", "state": "/state", "profile": "/profile", "stats": "/stats", "node": "/node", "last_node": "/lastnode", "failed_reason": "/failedreason", "storage.volumes": "/rbdlist", "console.log": "/consolelog", "console.vnc": "/vnc", "meta.autostart": "/node_autostart", "meta.migrate_method": "/migration_method", "meta.node_selector": "/node_selector", "meta.node_limit": "/node_limit", "meta.tags": "/tags", "migrate.sync_lock": "/migrate_sync_lock"}, "tag": {"name": "", "type": "/type", "protected": "/protected"}, "network": {"vni": "", "type": "/nettype", "mtu": "/mtu", "rule": "/firewall_rules", "rule.in": "/firewall_rules/in", "rule.out": "/firewall_rules/out", "nameservers": "/name_servers", "domain": "/domain", "reservation": "/dhcp4_reservations", "lease": "/dhcp4_leases", "ip4.gateway": "/ip4_gateway", "ip4.network": "/ip4_network", "ip4.dhcp": "/dhcp4_flag", "ip4.dhcp_start": "/dhcp4_start", "ip4.dhcp_end": "/dhcp4_end", "ip6.gateway": "/ip6_gateway", "ip6.network": "/ip6_network", "ip6.dhcp": "/dhcp6_flag"}, "reservation": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname"}, "lease": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname", "expiry": "/expiry", "client_id": "/clientid"}, "rule": {"description": "", "rule": "/rule", "order": "/order"}, "osd": {"id": "", "node": "/node", "device": "/device", "db_device": "/db_device", "fsid": "/fsid", "ofsid": "/fsid/osd", "cfsid": "/fsid/cluster", "lvm": "/lvm", "vg": "/lvm/vg", "lv": "/lvm/lv", "is_split": "/is_split", "stats": "/stats"}, "pool": {"name": "", "pgs": "/pgs", "tier": "/tier", "stats": "/stats"}, "volume": {"name": "", "stats": "/stats"}, "snapshot": {"name": "", "stats": "/stats"}}

daemon-common/migrations/versions/13.json

@@ -0,0 +1 @@
+{"version": "13", "root": "", "base": {"root": "", "schema": "/schema", "schema.version": "/schema/version", "config": "/config", "config.maintenance": "/config/maintenance", "config.primary_node": "/config/primary_node", "config.primary_node.sync_lock": "/config/primary_node/sync_lock", "config.upstream_ip": "/config/upstream_ip", "config.migration_target_selector": "/config/migration_target_selector", "logs": "/logs", "faults": "/faults", "node": "/nodes", "domain": "/domains", "network": "/networks", "storage": "/ceph", "storage.health": "/ceph/health", "storage.util": "/ceph/util", "osd": "/ceph/osds", "pool": "/ceph/pools", "volume": "/ceph/volumes", "snapshot": "/ceph/snapshots"}, "logs": {"node": "", "messages": "/messages"}, "faults": {"id": "", "last_time": "/last_time", "first_time": "/first_time", "ack_time": "/ack_time", "status": "/status", "delta": "/delta", "message": "/message"}, "node": {"name": "", "keepalive": "/keepalive", "mode": "/daemonmode", "data.active_schema": "/activeschema", "data.latest_schema": "/latestschema", "data.static": "/staticdata", "data.pvc_version": "/pvcversion", "running_domains": "/runningdomains", "count.provisioned_domains": "/domainscount", "count.networks": "/networkscount", "state.daemon": "/daemonstate", "state.router": "/routerstate", "state.domain": "/domainstate", "cpu.load": "/cpuload", "vcpu.allocated": "/vcpualloc", "memory.total": "/memtotal", "memory.used": "/memused", "memory.free": "/memfree", "memory.allocated": "/memalloc", "memory.provisioned": "/memprov", "ipmi.hostname": "/ipmihostname", "ipmi.username": "/ipmiusername", "ipmi.password": "/ipmipassword", "sriov": "/sriov", "sriov.pf": "/sriov/pf", "sriov.vf": "/sriov/vf", "monitoring.plugins": "/monitoring_plugins", "monitoring.data": "/monitoring_data", "monitoring.health": "/monitoring_health", "network.stats": "/network_stats"}, "monitoring_plugin": {"name": "", "last_run": "/last_run", "health_delta": "/health_delta", "message": "/message", "data": "/data", "runtime": "/runtime"}, "sriov_pf": {"phy": "", "mtu": "/mtu", "vfcount": "/vfcount"}, "sriov_vf": {"phy": "", "pf": "/pf", "mtu": "/mtu", "mac": "/mac", "phy_mac": "/phy_mac", "config": "/config", "config.vlan_id": "/config/vlan_id", "config.vlan_qos": "/config/vlan_qos", "config.tx_rate_min": "/config/tx_rate_min", "config.tx_rate_max": "/config/tx_rate_max", "config.spoof_check": "/config/spoof_check", "config.link_state": "/config/link_state", "config.trust": "/config/trust", "config.query_rss": "/config/query_rss", "pci": "/pci", "pci.domain": "/pci/domain", "pci.bus": "/pci/bus", "pci.slot": "/pci/slot", "pci.function": "/pci/function", "used": "/used", "used_by": "/used_by"}, "domain": {"name": "", "xml": "/xml", "state": "/state", "profile": "/profile", "stats": "/stats", "node": "/node", "last_node": "/lastnode", "failed_reason": "/failedreason", "storage.volumes": "/rbdlist", "console.log": "/consolelog", "console.vnc": "/vnc", "meta.autostart": "/node_autostart", "meta.migrate_method": "/migration_method", "meta.migrate_max_downtime": "/migration_max_downtime", "meta.node_selector": "/node_selector", "meta.node_limit": "/node_limit", "meta.tags": "/tags", "migrate.sync_lock": "/migrate_sync_lock"}, "tag": {"name": "", "type": "/type", "protected": "/protected"}, "network": {"vni": "", "type": "/nettype", "mtu": "/mtu", "rule": "/firewall_rules", "rule.in": "/firewall_rules/in", "rule.out": "/firewall_rules/out", "nameservers": "/name_servers", "domain": "/domain", "reservation": "/dhcp4_reservations", "lease": "/dhcp4_leases", "ip4.gateway": "/ip4_gateway", "ip4.network": "/ip4_network", "ip4.dhcp": "/dhcp4_flag", "ip4.dhcp_start": "/dhcp4_start", "ip4.dhcp_end": "/dhcp4_end", "ip6.gateway": "/ip6_gateway", "ip6.network": "/ip6_network", "ip6.dhcp": "/dhcp6_flag"}, "reservation": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname"}, "lease": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname", "expiry": "/expiry", "client_id": "/clientid"}, "rule": {"description": "", "rule": "/rule", "order": "/order"}, "osd": {"id": "", "node": "/node", "device": "/device", "db_device": "/db_device", "fsid": "/fsid", "ofsid": "/fsid/osd", "cfsid": "/fsid/cluster", "lvm": "/lvm", "vg": "/lvm/vg", "lv": "/lvm/lv", "is_split": "/is_split", "stats": "/stats"}, "pool": {"name": "", "pgs": "/pgs", "tier": "/tier", "stats": "/stats"}, "volume": {"name": "", "stats": "/stats"}, "snapshot": {"name": "", "stats": "/stats"}}

daemon-common/migrations/versions/14.json

@@ -0,0 +1 @@
+{"version": "14", "root": "", "base": {"root": "", "schema": "/schema", "schema.version": "/schema/version", "config": "/config", "config.maintenance": "/config/maintenance", "config.primary_node": "/config/primary_node", "config.primary_node.sync_lock": "/config/primary_node/sync_lock", "config.upstream_ip": "/config/upstream_ip", "config.migration_target_selector": "/config/migration_target_selector", "logs": "/logs", "faults": "/faults", "node": "/nodes", "domain": "/domains", "network": "/networks", "storage": "/ceph", "storage.health": "/ceph/health", "storage.util": "/ceph/util", "osd": "/ceph/osds", "pool": "/ceph/pools", "volume": "/ceph/volumes", "snapshot": "/ceph/snapshots"}, "logs": {"node": "", "messages": "/messages"}, "faults": {"id": "", "last_time": "/last_time", "first_time": "/first_time", "ack_time": "/ack_time", "status": "/status", "delta": "/delta", "message": "/message"}, "node": {"name": "", "keepalive": "/keepalive", "mode": "/daemonmode", "data.active_schema": "/activeschema", "data.latest_schema": "/latestschema", "data.static": "/staticdata", "data.pvc_version": "/pvcversion", "running_domains": "/runningdomains", "count.provisioned_domains": "/domainscount", "count.networks": "/networkscount", "state.daemon": "/daemonstate", "state.router": "/routerstate", "state.domain": "/domainstate", "cpu.load": "/cpuload", "vcpu.allocated": "/vcpualloc", "memory.total": "/memtotal", "memory.used": "/memused", "memory.free": "/memfree", "memory.allocated": "/memalloc", "memory.provisioned": "/memprov", "ipmi.hostname": "/ipmihostname", "ipmi.username": "/ipmiusername", "ipmi.password": "/ipmipassword", "sriov": "/sriov", "sriov.pf": "/sriov/pf", "sriov.vf": "/sriov/vf", "monitoring.plugins": "/monitoring_plugins", "monitoring.data": "/monitoring_data", "monitoring.health": "/monitoring_health", "network.stats": "/network_stats"}, "monitoring_plugin": {"name": "", "last_run": "/last_run", "health_delta": "/health_delta", "message": "/message", "data": "/data", "runtime": "/runtime"}, "sriov_pf": {"phy": "", "mtu": "/mtu", "vfcount": "/vfcount"}, "sriov_vf": {"phy": "", "pf": "/pf", "mtu": "/mtu", "mac": "/mac", "phy_mac": "/phy_mac", "config": "/config", "config.vlan_id": "/config/vlan_id", "config.vlan_qos": "/config/vlan_qos", "config.tx_rate_min": "/config/tx_rate_min", "config.tx_rate_max": "/config/tx_rate_max", "config.spoof_check": "/config/spoof_check", "config.link_state": "/config/link_state", "config.trust": "/config/trust", "config.query_rss": "/config/query_rss", "pci": "/pci", "pci.domain": "/pci/domain", "pci.bus": "/pci/bus", "pci.slot": "/pci/slot", "pci.function": "/pci/function", "used": "/used", "used_by": "/used_by"}, "domain": {"name": "", "xml": "/xml", "state": "/state", "profile": "/profile", "stats": "/stats", "node": "/node", "last_node": "/lastnode", "failed_reason": "/failedreason", "storage.volumes": "/rbdlist", "console.log": "/consolelog", "console.vnc": "/vnc", "meta.autostart": "/node_autostart", "meta.migrate_method": "/migration_method", "meta.migrate_max_downtime": "/migration_max_downtime", "meta.node_selector": "/node_selector", "meta.node_limit": "/node_limit", "meta.tags": "/tags", "migrate.sync_lock": "/migrate_sync_lock", "snapshots": "/snapshots"}, "tag": {"name": "", "type": "/type", "protected": "/protected"}, "domain_snapshot": {"name": "", "timestamp": "/timestamp", "xml": "/xml", "rbd_snapshots": "/rbdsnaplist"}, "network": {"vni": "", "type": "/nettype", "mtu": "/mtu", "rule": "/firewall_rules", "rule.in": "/firewall_rules/in", "rule.out": "/firewall_rules/out", "nameservers": "/name_servers", "domain": "/domain", "reservation": "/dhcp4_reservations", "lease": "/dhcp4_leases", "ip4.gateway": "/ip4_gateway", "ip4.network": "/ip4_network", "ip4.dhcp": "/dhcp4_flag", "ip4.dhcp_start": "/dhcp4_start", "ip4.dhcp_end": "/dhcp4_end", "ip6.gateway": "/ip6_gateway", "ip6.network": "/ip6_network", "ip6.dhcp": "/dhcp6_flag"}, "reservation": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname"}, "lease": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname", "expiry": "/expiry", "client_id": "/clientid"}, "rule": {"description": "", "rule": "/rule", "order": "/order"}, "osd": {"id": "", "node": "/node", "device": "/device", "db_device": "/db_device", "fsid": "/fsid", "ofsid": "/fsid/osd", "cfsid": "/fsid/cluster", "lvm": "/lvm", "vg": "/lvm/vg", "lv": "/lvm/lv", "is_split": "/is_split", "stats": "/stats"}, "pool": {"name": "", "pgs": "/pgs", "tier": "/tier", "stats": "/stats"}, "volume": {"name": "", "stats": "/stats"}, "snapshot": {"name": "", "stats": "/stats"}}

daemon-common/migrations/versions/15.json

@@ -0,0 +1 @@
+{"version": "15", "root": "", "base": {"root": "", "schema": "/schema", "schema.version": "/schema/version", "config": "/config", "config.maintenance": "/config/maintenance", "config.fence_lock": "/config/fence_lock", "config.primary_node": "/config/primary_node", "config.primary_node.sync_lock": "/config/primary_node/sync_lock", "config.upstream_ip": "/config/upstream_ip", "config.migration_target_selector": "/config/migration_target_selector", "logs": "/logs", "faults": "/faults", "node": "/nodes", "domain": "/domains", "network": "/networks", "storage": "/ceph", "storage.health": "/ceph/health", "storage.util": "/ceph/util", "osd": "/ceph/osds", "pool": "/ceph/pools", "volume": "/ceph/volumes", "snapshot": "/ceph/snapshots"}, "logs": {"node": "", "messages": "/messages"}, "faults": {"id": "", "last_time": "/last_time", "first_time": "/first_time", "ack_time": "/ack_time", "status": "/status", "delta": "/delta", "message": "/message"}, "node": {"name": "", "keepalive": "/keepalive", "mode": "/daemonmode", "data.active_schema": "/activeschema", "data.latest_schema": "/latestschema", "data.static": "/staticdata", "data.pvc_version": "/pvcversion", "running_domains": "/runningdomains", "count.provisioned_domains": "/domainscount", "count.networks": "/networkscount", "state.daemon": "/daemonstate", "state.router": "/routerstate", "state.domain": "/domainstate", "cpu.load": "/cpuload", "vcpu.allocated": "/vcpualloc", "memory.total": "/memtotal", "memory.used": "/memused", "memory.free": "/memfree", "memory.allocated": "/memalloc", "memory.provisioned": "/memprov", "ipmi.hostname": "/ipmihostname", "ipmi.username": "/ipmiusername", "ipmi.password": "/ipmipassword", "sriov": "/sriov", "sriov.pf": "/sriov/pf", "sriov.vf": "/sriov/vf", "monitoring.plugins": "/monitoring_plugins", "monitoring.data": "/monitoring_data", "monitoring.health": "/monitoring_health", "network.stats": "/network_stats"}, "monitoring_plugin": {"name": "", "last_run": "/last_run", "health_delta": "/health_delta", "message": "/message", "data": "/data", "runtime": "/runtime"}, "sriov_pf": {"phy": "", "mtu": "/mtu", "vfcount": "/vfcount"}, "sriov_vf": {"phy": "", "pf": "/pf", "mtu": "/mtu", "mac": "/mac", "phy_mac": "/phy_mac", "config": "/config", "config.vlan_id": "/config/vlan_id", "config.vlan_qos": "/config/vlan_qos", "config.tx_rate_min": "/config/tx_rate_min", "config.tx_rate_max": "/config/tx_rate_max", "config.spoof_check": "/config/spoof_check", "config.link_state": "/config/link_state", "config.trust": "/config/trust", "config.query_rss": "/config/query_rss", "pci": "/pci", "pci.domain": "/pci/domain", "pci.bus": "/pci/bus", "pci.slot": "/pci/slot", "pci.function": "/pci/function", "used": "/used", "used_by": "/used_by"}, "domain": {"name": "", "xml": "/xml", "state": "/state", "profile": "/profile", "stats": "/stats", "node": "/node", "last_node": "/lastnode", "failed_reason": "/failedreason", "storage.volumes": "/rbdlist", "console.log": "/consolelog", "console.vnc": "/vnc", "meta.autostart": "/node_autostart", "meta.migrate_method": "/migration_method", "meta.migrate_max_downtime": "/migration_max_downtime", "meta.node_selector": "/node_selector", "meta.node_limit": "/node_limit", "meta.tags": "/tags", "migrate.sync_lock": "/migrate_sync_lock", "snapshots": "/snapshots"}, "tag": {"name": "", "type": "/type", "protected": "/protected"}, "domain_snapshot": {"name": "", "timestamp": "/timestamp", "xml": "/xml", "rbd_snapshots": "/rbdsnaplist"}, "network": {"vni": "", "type": "/nettype", "mtu": "/mtu", "rule": "/firewall_rules", "rule.in": "/firewall_rules/in", "rule.out": "/firewall_rules/out", "nameservers": "/name_servers", "domain": "/domain", "reservation": "/dhcp4_reservations", "lease": "/dhcp4_leases", "ip4.gateway": "/ip4_gateway", "ip4.network": "/ip4_network", "ip4.dhcp": "/dhcp4_flag", "ip4.dhcp_start": "/dhcp4_start", "ip4.dhcp_end": "/dhcp4_end", "ip6.gateway": "/ip6_gateway", "ip6.network": "/ip6_network", "ip6.dhcp": "/dhcp6_flag"}, "reservation": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname"}, "lease": {"mac": "", "ip": "/ipaddr", "hostname": "/hostname", "expiry": "/expiry", "client_id": "/clientid"}, "rule": {"description": "", "rule": "/rule", "order": "/order"}, "osd": {"id": "", "node": "/node", "device": "/device", "db_device": "/db_device", "fsid": "/fsid", "ofsid": "/fsid/osd", "cfsid": "/fsid/cluster", "lvm": "/lvm", "vg": "/lvm/vg", "lv": "/lvm/lv", "is_split": "/is_split", "stats": "/stats"}, "pool": {"name": "", "pgs": "/pgs", "tier": "/tier", "stats": "/stats"}, "volume": {"name": "", "stats": "/stats"}, "snapshot": {"name": "", "stats": "/stats"}}

daemon-common/network.py

@@ -3,7 +3,7 @@
 # network.py - PVC client function library, Network fuctions
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

daemon-common/node.py

@@ -3,7 +3,7 @@
 # node.py - PVC client function library, node management
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -69,6 +69,8 @@ def getNodeHealthDetails(zkhandler, node_name, node_health_plugins):
             plugin_message,
             plugin_data,
         ) = tuple(all_plugin_data[pos_start:pos_end])
+        if plugin_data is None:
+            continue
         plugin_output = {
             "name": plugin,
             "last_run": int(plugin_last_run) if plugin_last_run is not None else None,
@@ -103,6 +105,7 @@ def getNodeInformation(zkhandler, node_name):
         _node_running_domains,
         _node_health,
         _node_health_plugins,
+        _node_network_stats,
     ) = zkhandler.read_many(
         [
             ("node.state.daemon", node_name),
@@ -121,6 +124,7 @@ def getNodeInformation(zkhandler, node_name):
             ("node.running_domains", node_name),
             ("node.monitoring.health", node_name),
             ("node.monitoring.plugins", node_name),
+            ("node.network.stats", node_name),
         ]
     )
 
@@ -154,6 +158,11 @@ def getNodeInformation(zkhandler, node_name):
         zkhandler, node_name, node_health_plugins
     )
 
+    try:
+        node_network_stats = json.loads(_node_network_stats)
+    except Exception:
+        node_network_stats = dict()
+
     # Construct a data structure to represent the data
     node_information = {
         "name": node_name,
@@ -182,6 +191,7 @@ def getNodeInformation(zkhandler, node_name):
             "used": node_mem_used,
             "free": node_mem_free,
         },
+        "interfaces": node_network_stats,
     }
     return node_information
 

daemon-common/vmbuilder.py

@@ -258,6 +258,13 @@ def worker_create_vm(
         args = (vm_profile,)
         db_cur.execute(query, args)
         profile_data = db_cur.fetchone()
+        if profile_data is None:
+            fail(
+                celery,
+                f'Provisioner profile "{vm_profile}" is not present on the cluster',
+                exception=ClusterError,
+            )
+
         if profile_data.get("arguments"):
             vm_data["script_arguments"] = profile_data.get("arguments").split("|")
         else:
@@ -329,11 +336,7 @@ def worker_create_vm(
     retcode, stdout, stderr = pvc_common.run_os_command("uname -m")
     vm_data["system_architecture"] = stdout.strip()
 
-    monitor_list = list()
-    monitor_names = config["storage_hosts"]
-    for monitor in monitor_names:
-        monitor_list.append("{}.{}".format(monitor, config["storage_domain"]))
-    vm_data["ceph_monitor_list"] = monitor_list
+    vm_data["ceph_monitor_list"] = config["storage_hosts"]
     vm_data["ceph_monitor_port"] = config["ceph_monitor_port"]
     vm_data["ceph_monitor_secret"] = config["ceph_secret_uuid"]
 
@@ -744,6 +747,7 @@ def worker_create_vm(
         node_selector = vm_data["system_details"]["node_selector"]
         node_autostart = vm_data["system_details"]["node_autostart"]
         migration_method = vm_data["system_details"]["migration_method"]
+        migration_max_downtime = vm_data["system_details"]["migration_max_downtime"]
         with open_zk(config) as zkhandler:
             retcode, retmsg = pvc_vm.define_vm(
                 zkhandler,
@@ -753,6 +757,7 @@ def worker_create_vm(
                 node_selector,
                 node_autostart,
                 migration_method,
+                migration_max_downtime,
                 vm_profile,
                 initial_state="provision",
             )

daemon-common/zkhandler.py

@@ -3,7 +3,7 @@
 # zkhandler.py - Secure versioned ZooKeeper updates
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -30,6 +30,10 @@ from kazoo.client import KazooClient, KazooState
 from kazoo.exceptions import NoNodeError
 
 
+DEFAULT_ROOT_PATH = "/usr/share/pvc"
+SCHEMA_PATH = "daemon_lib/migrations/versions"
+
+
 #
 # Function decorators
 #
@@ -57,10 +61,11 @@ class ZKConnection(object):
                 schema_version = 0
             zkhandler.schema.load(schema_version, quiet=True)
 
-            ret = function(zkhandler, *args, **kwargs)
-
-            zkhandler.disconnect()
-            del zkhandler
+            try:
+                ret = function(zkhandler, *args, **kwargs)
+            finally:
+                zkhandler.disconnect()
+                del zkhandler
 
             return ret
 
@@ -572,7 +577,7 @@ class ZKHandler(object):
 #
 class ZKSchema(object):
     # Current version
-    _version = 11
+    _version = 15
 
     # Root for doing nested keys
     _schema_root = ""
@@ -588,6 +593,7 @@ class ZKSchema(object):
             "schema.version": f"{_schema_root}/schema/version",
             "config": f"{_schema_root}/config",
             "config.maintenance": f"{_schema_root}/config/maintenance",
+            "config.fence_lock": f"{_schema_root}/config/fence_lock",
             "config.primary_node": f"{_schema_root}/config/primary_node",
             "config.primary_node.sync_lock": f"{_schema_root}/config/primary_node/sync_lock",
             "config.upstream_ip": f"{_schema_root}/config/upstream_ip",
@@ -651,6 +657,7 @@ class ZKSchema(object):
             "monitoring.plugins": "/monitoring_plugins",
             "monitoring.data": "/monitoring_data",
             "monitoring.health": "/monitoring_health",
+            "network.stats": "/network_stats",
         },
         # The schema of an individual monitoring plugin data entry (/nodes/{node_name}/monitoring_data/{plugin})
         "monitoring_plugin": {
@@ -706,17 +713,26 @@ class ZKSchema(object):
             "console.vnc": "/vnc",
             "meta.autostart": "/node_autostart",
             "meta.migrate_method": "/migration_method",
+            "meta.migrate_max_downtime": "/migration_max_downtime",
             "meta.node_selector": "/node_selector",
             "meta.node_limit": "/node_limit",
             "meta.tags": "/tags",
             "migrate.sync_lock": "/migrate_sync_lock",
+            "snapshots": "/snapshots",
         },
         # The schema of an individual domain tag entry (/domains/{domain}/tags/{tag})
         "tag": {
-            "name": "",
+            "name": "",  # The root key
             "type": "/type",
             "protected": "/protected",
-        },  # The root key
+        },
+        # The schema of an individual domain snapshot entry (/domains/{domain}/snapshots/{snapshot})
+        "domain_snapshot": {
+            "name": "",  # The root key
+            "timestamp": "/timestamp",
+            "xml": "/xml",
+            "rbd_snapshots": "/rbdsnaplist",
+        },
         # The schema of an individual network entry (/networks/{vni})
         "network": {
             "vni": "",  # The root key
@@ -817,8 +833,8 @@ class ZKSchema(object):
     def schema(self, schema):
         self._schema = schema
 
-    def __init__(self):
-        pass
+    def __init__(self, root_path=DEFAULT_ROOT_PATH):
+        self.schema_path = f"{root_path}/{SCHEMA_PATH}"
 
     def __repr__(self):
         return f"ZKSchema({self.version})"
@@ -858,7 +874,7 @@ class ZKSchema(object):
         if not quiet:
             print(f"Loading schema version {version}")
 
-        with open(f"daemon_lib/migrations/versions/{version}.json", "r") as sfh:
+        with open(f"{self.schema_path}/{version}.json", "r") as sfh:
             self.schema = json.load(sfh)
             self.version = self.schema.get("version")
 
@@ -1025,6 +1041,8 @@ class ZKSchema(object):
                             default_data = "False"
                         elif elem == "pool" and ikey == "tier":
                             default_data = "default"
+                        elif elem == "domain" and ikey == "meta.migrate_max_downtime":
+                            default_data = "300"
                         else:
                             default_data = ""
                         zkhandler.zk_conn.create(
@@ -1118,7 +1136,7 @@ class ZKSchema(object):
     # Migrate from older to newer schema
     def migrate(self, zkhandler, new_version):
         # Determine the versions in between
-        versions = ZKSchema.find_all(start=self.version, end=new_version)
+        versions = self.find_all(start=self.version, end=new_version)
         if versions is None:
             return
 
@@ -1134,7 +1152,7 @@ class ZKSchema(object):
     # Rollback from newer to older schema
     def rollback(self, zkhandler, old_version):
         # Determine the versions in between
-        versions = ZKSchema.find_all(start=old_version - 1, end=self.version - 1)
+        versions = self.find_all(start=old_version - 1, end=self.version - 1)
         if versions is None:
             return
 
@@ -1149,6 +1167,12 @@ class ZKSchema(object):
             # Apply those changes
             self.run_migrate(zkhandler, changes)
 
+    # Write the latest schema to a file
+    def write(self):
+        schema_file = f"{self.schema_path}/{self._version}.json"
+        with open(schema_file, "w") as sfh:
+            json.dump(self._schema, sfh)
+
     @classmethod
     def key_diff(cls, schema_a, schema_b):
         # schema_a = current
@@ -1194,26 +1218,10 @@ class ZKSchema(object):
 
         return {"add": diff_add, "remove": diff_remove, "rename": diff_rename}
 
-    # Load in the schemal of the current cluster
-    @classmethod
-    def load_current(cls, zkhandler):
-        new_instance = cls()
-        version = new_instance.get_version(zkhandler)
-        new_instance.load(version)
-        return new_instance
-
-    # Write the latest schema to a file
-    @classmethod
-    def write(cls):
-        schema_file = "daemon_lib/migrations/versions/{}.json".format(cls._version)
-        with open(schema_file, "w") as sfh:
-            json.dump(cls._schema, sfh)
-
     # Static methods for reading information from the files
-    @staticmethod
-    def find_all(start=0, end=None):
+    def find_all(self, start=0, end=None):
         versions = list()
-        for version in os.listdir("daemon_lib/migrations/versions"):
+        for version in os.listdir(self.schema_path):
             sequence_id = int(version.split(".")[0])
             if end is None:
                 if sequence_id > start:
@@ -1226,11 +1234,18 @@ class ZKSchema(object):
         else:
             return None
 
-    @staticmethod
-    def find_latest():
+    def find_latest(self):
         latest_version = 0
-        for version in os.listdir("daemon_lib/migrations/versions"):
+        for version in os.listdir(self.schema_path):
             sequence_id = int(version.split(".")[0])
             if sequence_id > latest_version:
                 latest_version = sequence_id
         return latest_version
+
+    # Load in the schema of the current cluster
+    @classmethod
+    def load_current(cls, zkhandler):
+        new_instance = cls()
+        version = new_instance.get_version(zkhandler)
+        new_instance.load(version)
+        return new_instance

debian/changelog

@@ -1,3 +1,181 @@
+pvc (0.9.103-0) unstable; urgency=high
+
+  * [Provisioner] Fixes a bug with the change in `storage_hosts` to FQDNs affecting the VM Builder
+  * [Monitoring] Fixes the Munin plugin to work properly with sudo
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Fri, 01 Nov 2024 17:19:44 -0400
+
+pvc (0.9.102-0) unstable; urgency=high
+
+  * [API Daemon] Ensures that received config snapshots update storage hosts in addition to secret UUIDs
+  * [CLI Client] Fixes several bugs around local connection handling and connection listings
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Thu, 17 Oct 2024 10:48:31 -0400
+
+pvc (0.9.101-0) unstable; urgency=high
+
+  **New Feature**: Adds VM snapshot sending (`vm snapshot send`), VM mirroring (`vm mirror create`), and (offline) mirror promotion (`vm mirror promote`). Permits transferring VM snapshots to remote clusters, individually or repeatedly, and promoting them to active status, for disaster recovery and migration between clusters.
+  **Breaking Change**: Migrates the API daemon into Gunicorn when in production mode. Permits more scalable and performant operation of the API. **Requires additional dependency packages on all coordinator nodes** (`gunicorn`, `python3-gunicorn`, `python3-setuptools`); upgrade via `pvc-ansible` is strongly recommended.
+  **Enhancement**: Provides whole cluster utilization stats in the cluster status data. Permits better observability into the overall resource utilization of the cluster.
+  **Enhancement**: Adds a new storage benchmark format (v2) which includes additional resource utilization statistics. This allows for better evaluation of storage performance impact on the cluster as a whole. The updated format also permits arbitrary benchmark job names for easier parsing and tracking.
+
+  * [API Daemon] Allows scanning of new volumes added manually via other commands
+  * [API Daemon/CLI Client] Adds whole cluster utilization statistics to cluster status
+  * [API Daemon] Moves production API execution into Gunicorn
+  * [API Daemon] Adds a new storage benchmark format (v2) with additional resource tracking
+  * [API Daemon] Adds support for named storage benchmark jobs
+  * [API Daemon] Fixes a bug in OSD creation which would create `split` OSDs if `--osd-count` was set to 1
+  * [API Daemon] Adds support for the `mirror` VM state used by snapshot mirrors
+  * [CLI Client] Fixes several output display bugs in various commands and in Worker task outputs
+  * [CLI Client] Improves and shrinks the status progress bar output to support longer messages
+  * [API Daemon] Adds support for sending snapshots to remote clusters
+  * [API Daemon] Adds support for updating and promoting snapshot mirrors to remote clusters
+  * [Node Daemon] Improves timeouts during primary/secondary coordinator transitions to avoid deadlocks
+  * [Node Daemon] Improves timeouts during keepalive updates to avoid deadlocks
+  * [Node Daemon] Refactors fencing thread structure to ensure a single fencing task per cluster and sequential node fences to avoid potential anomalies (e.g. fencing 2 nodes simultaneously)
+  * [Node Daemon] Fixes a bug in fencing if VM locks were already freed, leaving VMs in an invalid state
+  * [Node Daemon] Increases the wait time during system startup to ensure Zookeeper has more time to synchronize
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Tue, 15 Oct 2024 11:39:11 -0400
+
+pvc (0.9.100-0) unstable; urgency=high
+
+  * [API Daemon] Improves the handling of "detect:" disk strings on newer systems by leveraging the "nvme" command
+  * [Client CLI] Update help text about "detect:" disk strings
+  * [Meta] Updates deprecation warnings and updates builder to only add this version for Debian 12 (Bookworm)
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Fri, 30 Aug 2024 11:03:33 -0400
+
+pvc (0.9.99-0) unstable; urgency=high
+
+  **Deprecation Warning**: `pvc vm backup` commands are now deprecated and will be removed in **0.9.100**. Use `pvc vm snapshot` commands instead.
+  **Breaking Change**: The on-disk format of VM snapshot exports differs from backup exports, and the PVC autobackup system now leverages these. It is recommended to start fresh with a new tree of backups for `pvc autobackup` for maximum compatibility.
+  **Breaking Change**: VM autobackups now run in `pvcworkerd` instead of the CLI client directly, allowing them to be triggerd from any node (or externally). It is important to apply the timer unit changes from the `pvc-ansible` role after upgrading to 0.9.99 to avoid duplicate runs.
+  **Usage Note**: VM snapshots are displayed in the `pvc vm list` and `pvc vm info` outputs, not in a unique "list" endpoint.
+
+  * [API Daemon] Adds a proper error when an invalid provisioner profile is specified
+  * [Node Daemon] Sorts Ceph pools properly in node keepalive to avoid incorrect ordering
+  * [Health Daemon] Improves handling of IPMI checks by adding multiple tries but a shorter timeout
+  * [API Daemon] Improves handling of XML parsing errors in VM configurations
+  * [ALL] Adds support for whole VM snapshots, including configuration XML details, and direct rollback to snapshots
+  * [ALL] Adds support for exporting and importing whole VM snapshots
+  * [Client CLI] Removes vCPU topology from short VM info output
+  * [Client CLI] Improves output format of VM info output
+  * [API Daemon] Adds an endpoint to get the current primary node
+  * [Client CLI] Fixes a bug where API requests were made 3 times
+  * [Other] Improves the build-and-deploy.sh script
+  * [API Daemon] Improves the "vm rename" command to avoid redefining VM, preserving history etc.
+  * [API Daemon] Adds an indication when a task is run on the primary node
+  * [API Daemon] Fixes a bug where the ZK schema relative path didn't work sometimes
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Wed, 28 Aug 2024 11:15:55 -0400
+
+pvc (0.9.98-0) unstable; urgency=high
+
+  * [CLI Client] Fixed output when API call times out
+  * [Node Daemon] Improves the handling of fence states
+  * [API Daemon/CLI Client] Adds support for storage snapshot rollback
+  * [CLI Client] Adds additional warning messages about snapshot consistency to help output
+  * [API Daemon] Fixes a bug listing snapshots by pool/volume
+  * [Node Daemon] Adds a --version flag for information gathering by update-motd.sh
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Wed, 05 Jun 2024 12:01:31 -0400
+
+pvc (0.9.97-0) unstable; urgency=high
+
+  * [Client CLI] Ensures --lines is always an integer value
+  * [Node Daemon] Fixes a bug if d_network changes during iteration
+  * [Node Daemon] Moves to using allocated instead of free memory for node reporting
+  * [API Daemon] Fixes a bug if lingering RBD snapshots exist when removing a volume (#180)
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Fri, 19 Apr 2024 10:32:16 -0400
+
+pvc (0.9.96-0) unstable; urgency=high
+
+  * [API Daemon] Fixes a bug when reporting node stats
+  * [API Daemon] Fixes a bug deleteing successful benchmark results
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Fri, 08 Mar 2024 14:23:06 -0500
+
+pvc (0.9.95-0) unstable; urgency=high
+
+  * [API Daemon/CLI Client] Adds a flag to allow duplicate VNIs in network templates
+  * [API Daemon] Ensures that storage template disks are returned in disk ID order
+  * [Client CLI] Fixes a display bug showing all OSDs as split
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Fri, 09 Feb 2024 12:42:00 -0500
+
+pvc (0.9.94-0) unstable; urgency=high
+
+  * [CLI Client] Fixes an incorrect ordering issue with autobackup summary emails
+  * [API Daemon/CLI Client] Adds an additional safety check for 80% cluster fullness when doing volume adds or resizes
+  * [API Daemon/CLI Client] Adds safety checks to volume clones as well
+  * [API Daemon] Fixes a few remaining memory bugs for stopped/disabled VMs
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Mon, 05 Feb 2024 09:58:07 -0500
+
+pvc (0.9.93-0) unstable; urgency=high
+
+  * [API Daemon] Fixes a bug where stuck zkhandler threads were not cleaned up on error
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Tue, 30 Jan 2024 09:51:21 -0500
+
+pvc (0.9.92-0) unstable; urgency=high
+
+  * [CLI Client] Adds the new restore state to the colours list for VM status
+  * [API Daemon] Fixes an incorrect variable assignment
+  * [Provisioner] Improves the error handling of various steps in the debootstrap and rinse example scripts
+  * [CLI Client] Fixes two bugs around missing keys that were added recently (uses get() instead direct dictionary refs)
+  * [CLI Client] Improves API error handling via GET retries (x3) and better server status code handling
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Mon, 29 Jan 2024 09:39:10 -0500
+
+pvc (0.9.91-0) unstable; urgency=high
+
+  * [Client CLI] Fixes a bug and improves output during cluster task events.
+  * [Client CLI] Improves the output of the task list display.
+  * [Provisioner] Fixes some missing cloud-init modules in the default debootstrap script.
+  * [Client CLI] Fixes a bug with a missing argument to the vm_define helper function.
+  * [All] Fixes inconsistent package find + rm commands to avoid errors in dpkg.
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Tue, 23 Jan 2024 10:02:19 -0500
+
+pvc (0.9.90-0) unstable; urgency=high
+
+  * [Client CLI/API Daemon] Adds additional backup metainfo and an emailed report option to autobackups.
+  * [All] Adds a live migration maximum downtime selector to help with busy VM migrations.
+  * [API Daemon] Fixes a database migration bug on Debian 10/11.
+  * [Node Daemon] Fixes a race condition when applying Zookeeper schema changes.
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Thu, 11 Jan 2024 00:14:49 -0500
+
+pvc (0.9.89-0) unstable; urgency=high
+
+  * [API/Worker Daemons] Fixes a bug with the Celery result backends not being properly initialized on Debian 10/11.
+  * [API Daemon] Fixes a bug if VM CPU stats are missing on Debian 10.
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Tue, 09 Jan 2024 12:15:53 -0500
+
+pvc (0.9.88-0) unstable; urgency=high
+
+  * [API Daemon] Adds an additional Prometheus metrics proxy for Zookeeper stats.
+  * [API Daemon] Adds a new configuration to enable or disable metric endpoints if desired, defaulting to enabled.
+  * [API Daemon] Alters and adjusts the metrics output for VMs to complement new dashboard.
+  * [CLI Client] Adds a "json-prometheus" output format to "pvc connection list" to auto-generate file SD configs.
+  * [Monitoring] Adds a new VM dashboard, updates the Cluster dashboard, and adds a README.
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Fri, 29 Dec 2023 14:50:40 -0500
+
+pvc (0.9.87-0) unstable; urgency=high
+
+  * [API Daemon] Adds cluster Prometheus resource utilization metrics and an updated Grafana dashboard.
+  * [Node Daemon] Adds network traffic rate calculation subsystem.
+  * [All Daemons] Fixes a printing bug where newlines were not added atomically.
+  * [CLI Client] Fixes a bug listing connections if no default is specified.
+  * [All Daemons] Simplifies debug logging conditionals by moving into the Logger instance itself.
+
+ -- Joshua M. Boniface <joshua@boniface.me>  Wed, 27 Dec 2023 13:40:51 -0500
+
 pvc (0.9.86-0) unstable; urgency=high
 
   * [API Daemon] Significantly improves the performance of several commands via async Zookeeper calls and removal of superfluous backend calls.

debian/control

@@ -32,7 +32,7 @@ Description: Parallel Virtual Cluster worker daemon
 
 Package: pvc-daemon-api
 Architecture: all
-Depends: systemd, pvc-daemon-common, python3-yaml, python3-flask, python3-flask-restful, python3-celery, python3-distutils, python3-redis, python3-lxml, python3-flask-migrate
+Depends: systemd, pvc-daemon-common, gunicorn, python3-gunicorn, python3-yaml, python3-flask, python3-flask-restful, python3-celery, python3-distutils, python3-redis, python3-lxml, python3-flask-migrate
 Description: Parallel Virtual Cluster API daemon
  A KVM/Zookeeper/Ceph-based VM and private cloud manager
  .

debian/pvc-client-cli.postinst

@@ -2,7 +2,12 @@
 
 # Generate the bash completion configuration
 if [ -d /etc/bash_completion.d ]; then
+    echo "Installing BASH completion configuration"
     _PVC_COMPLETE=source_bash pvc > /etc/bash_completion.d/pvc
 fi
 
+# Remove any cached CPython directories or files
+echo "Cleaning up CPython caches"
+find /usr/lib/python3/dist-packages/pvc -type d -name "__pycache__" -exec rm -fr {} + &>/dev/null || true
+
 exit 0

debian/pvc-daemon-api.postinst

@@ -9,11 +9,6 @@ if systemctl is-active --quiet pvcapid.service; then
     /usr/share/pvc/pvc-api-db-upgrade
     systemctl start pvcapid.service
 fi
-# Restart the worker daemon
-if systemctl is-active --quiet pvcworkerd.service; then
-    systemctl stop pvcworkerd.service
-    systemctl start pvcworkerd.service
-fi
 
 if [ ! -f /etc/pvc/pvc.conf ]; then
     echo "NOTE: The PVC client API daemon (pvcapid.service) and the PVC Worker daemon (pvcworkerd.service) have not been started; create a config file at /etc/pvc/pvc.conf, then run the database configuration (/usr/share/pvc/pvc-api-db-upgrade) and start them manually."

debian/pvc-daemon-api.preinst

@@ -1,5 +1,5 @@
 #!/bin/sh
 
 # Remove any cached CPython directories or files
-echo "Cleaning up existing CPython files"
-find /usr/share/pvc/pvcapid -type d -name "__pycache__" -exec rm -rf {} \; &>/dev/null || true
+echo "Cleaning up CPython caches"
+find /usr/share/pvc/pvcapid -type d -name "__pycache__" -exec rm -fr {} + &>/dev/null || true

debian/pvc-daemon-common.preinst

@@ -0,0 +1,5 @@
+#!/bin/sh
+
+# Remove any cached CPython directories or files
+echo "Cleaning up CPython caches"
+find /usr/share/pvc/daemon_lib -type d -name "__pycache__" -exec rm -fr {} + &>/dev/null || true

debian/pvc-daemon-health.preinst

@@ -1,6 +1,6 @@
 #!/bin/sh
 
 # Remove any cached CPython directories or files
-echo "Cleaning up existing CPython files"
-find /usr/share/pvc/pvchealthd -type d -name "__pycache__" -exec rm -rf {} \; &>/dev/null || true
-find /usr/share/pvc/plugins -type d -name "__pycache__" -exec rm -rf {} \; &>/dev/null || true
+echo "Cleaning up CPython caches"
+find /usr/share/pvc/pvchealthd -type d -name "__pycache__" -exec rm -fr {} + &>/dev/null || true
+find /usr/share/pvc/plugins -type d -name "__pycache__" -exec rm -fr {} + &>/dev/null || true

debian/pvc-daemon-node.install

@@ -3,4 +3,4 @@ node-daemon/pvcnoded usr/share/pvc
 node-daemon/pvcnoded.service lib/systemd/system
 node-daemon/pvc.target lib/systemd/system
 node-daemon/pvcautoready.service lib/systemd/system
-node-daemon/monitoring usr/share/pvc
+monitoring usr/share/pvc

debian/pvc-daemon-node.preinst

@@ -1,5 +1,5 @@
 #!/bin/sh
 
 # Remove any cached CPython directories or files
-echo "Cleaning up existing CPython files"
-find /usr/share/pvc/pvcnoded -type d -name "__pycache__" -exec rm -rf {} \; &>/dev/null || true
+echo "Cleaning up CPython caches"
+find /usr/share/pvc/pvcnoded -type d -name "__pycache__" -exec rm -fr {} + &>/dev/null || true

debian/pvc-daemon-worker.preinst

@@ -1,5 +1,5 @@
 #!/bin/sh
 
 # Remove any cached CPython directories or files
-echo "Cleaning up existing CPython files"
-find /usr/share/pvc/pvcworkerd -type d -name "__pycache__" -exec rm -rf {} \; &>/dev/null || true
+echo "Cleaning up CPython caches"
+find /usr/share/pvc/pvcworkerd -type d -name "__pycache__" -exec rm -fr {} + &>/dev/null || true

debian/rules

@@ -13,7 +13,7 @@ override_dh_python3:
 	rm -r $(CURDIR)/client-cli/.pybuild $(CURDIR)/client-cli/pvc.egg-info
 
 override_dh_auto_clean:
-	find . -name "__pycache__" -o -name ".pybuild" -exec rm -r {} \; || true
+	find . -name "__pycache__" -o -name ".pybuild" -exec rm -fr {} + || true
 
 # If you need to rebuild the Sphinx documentation
 # Add spinxdoc to the dh --with line

gen-api-migrations

@@ -2,12 +2,19 @@
 
 # Generate the database migration files
 
+set -o xtrace
+
 VERSION="$( head -1 debian/changelog | awk -F'[()-]' '{ print $2 }' )"
 
+sudo ip addr add 10.0.1.250/32 dev lo
+
 pushd $( git rev-parse --show-toplevel ) &>/dev/null
 pushd api-daemon &>/dev/null
 export PVC_CONFIG_FILE="../pvc.sample.conf"
-./pvcapid-manage_flask.py db migrate -m "PVC version ${VERSION}"
-./pvcapid-manage_flask.py db upgrade
+export FLASK_APP=./pvcapid-manage_flask.py
+flask db migrate -m "PVC version ${VERSION}"
+flask db upgrade
 popd &>/dev/null
 popd &>/dev/null
+
+sudo ip addr del 10.0.1.250/32 dev lo

health-daemon/plugins/disk

@@ -3,7 +3,7 @@
 # disk.py - PVC Monitoring example plugin for disk (system + OSD)
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/dpkg

@@ -3,7 +3,7 @@
 # dpkg.py - PVC Monitoring example plugin for dpkg status
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/edac

@@ -3,7 +3,7 @@
 # edac.py - PVC Monitoring example plugin for EDAC
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/hwrd

@@ -3,7 +3,7 @@
 # hwrd.py - PVC Monitoring example plugin for hardware RAID Arrays
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2023 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/ipmi

@@ -3,7 +3,7 @@
 # ipmi.py - PVC Monitoring example plugin for IPMI
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -69,26 +69,33 @@ class MonitoringPluginScript(MonitoringPlugin):
 
         # Run any imports first
         from daemon_lib.common import run_os_command
+        from time import sleep
 
         # Check the node's IPMI interface
         ipmi_hostname = self.config["ipmi_hostname"]
         ipmi_username = self.config["ipmi_username"]
         ipmi_password = self.config["ipmi_password"]
-        retcode, _, _ = run_os_command(
-            f"/usr/bin/ipmitool -I lanplus -H {ipmi_hostname} -U {ipmi_username} -P {ipmi_password} chassis power status",
-            timeout=5
-        )
+        retcode = 1
+        trycount = 0
+        while retcode > 0 and trycount < 3:
+            retcode, _, _ = run_os_command(
+                f"/usr/bin/ipmitool -I lanplus -H {ipmi_hostname} -U {ipmi_username} -P {ipmi_password} chassis power status",
+                timeout=2
+            )
+            trycount += 1
+            if retcode > 0 and trycount < 3:
+                sleep(trycount)
 
         if retcode > 0:
             # Set the health delta to 10 (subtract 10 from the total of 100)
             health_delta = 10
             # Craft a message that can be used by the clients
-            message = f"IPMI via {ipmi_username}@{ipmi_hostname} is NOT responding"
+            message = f"IPMI via {ipmi_username}@{ipmi_hostname} is NOT responding after 3 attempts"
         else:
             # Set the health delta to 0 (no change)
             health_delta = 0
             # Craft a message that can be used by the clients
-            message = f"IPMI via {ipmi_username}@{ipmi_hostname} is responding"
+            message = f"IPMI via {ipmi_username}@{ipmi_hostname} is responding after {trycount} attempts"
 
         # Set the health delta in our local PluginResult object
         self.plugin_result.set_health_delta(health_delta)

health-daemon/plugins/kydb

@@ -3,7 +3,7 @@
 # kydb.py - PVC Monitoring example plugin for KeyDB/Redis
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2023 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/lbvt

@@ -3,7 +3,7 @@
 # lbvt.py - PVC Monitoring example plugin for Libvirtd
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/load

@@ -3,7 +3,7 @@
 # load.py - PVC Monitoring example plugin for load
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/nics

@@ -3,7 +3,7 @@
 # nics.py - PVC Monitoring example plugin for NIC interfaces
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/psql

@@ -3,7 +3,7 @@
 # psql.py - PVC Monitoring example plugin for Postgres/Patroni
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/psur

@@ -3,7 +3,7 @@
 # psur.py - PVC Monitoring example plugin for PSU Redundancy
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/plugins/zkpr

@@ -3,7 +3,7 @@
 # zkpr.py - PVC Monitoring example plugin for Zookeeper
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/pvchealthd.py

@@ -3,7 +3,7 @@
 # pvchealthd.py - Health daemon startup stub
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/pvchealthd/Daemon.py

@@ -3,7 +3,7 @@
 # Daemon.py - Health daemon main entrypoing
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -33,7 +33,7 @@ import os
 import signal
 
 # Daemon version
-version = "0.9.86"
+version = "0.9.103"
 
 
 ##########################################################

health-daemon/pvchealthd/objects/MonitoringInstance.py

@@ -3,7 +3,7 @@
 # MonitoringInstance.py - Class implementing a PVC monitor in pvchealthd
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by
@@ -157,9 +157,6 @@ class MonitoringPlugin(object):
             "w": warning
             "e": error
         """
-        if state == "d" and not self.config["debug"]:
-            return
-
         self.logger.out(message, state=state, prefix=self.plugin_name)
 
     #
@@ -523,11 +520,10 @@ class MonitoringInstance(object):
 
             entries = fault_data["entries"]()
 
-            if self.config["debug"]:
-                self.logger.out(
-                    f"Entries for fault check {fault_type}: {dumps(entries)}",
-                    state="d",
-                )
+            self.logger.out(
+                f"Entries for fault check {fault_type}: {dumps(entries)}",
+                state="d",
+            )
 
             for _entry in entries:
                 entry = _entry["entry"]
@@ -699,7 +695,7 @@ class MonitoringInstance(object):
             health_text = f"{health_colour}{self.this_node.health}%{self.logger.fmt_end} node health"
             result_text.append(health_text)
         else:
-            health_text = "{self.logger.fmt_blue}N/A{self.logger.fmt_end} node health"
+            health_text = f"{self.logger.fmt_blue}N/A{self.logger.fmt_end} node health"
             result_text.append(health_text)
 
         self.logger.out(

health-daemon/pvchealthd/objects/NodeInstance.py

@@ -3,7 +3,7 @@
 # NodeInstance.py - Class implementing a PVC node in pvchealthd
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

health-daemon/pvchealthd/util/zookeeper.py

@@ -4,7 +4,7 @@
 # zookeeper.py - Utility functions for pvcnoded Zookeeper connections
 # Part of the Parallel Virtual Cluster (PVC) system
 #
-#    Copyright (C) 2018-2022 Joshua M. Boniface <joshua@boniface.me>
+#    Copyright (C) 2018-2024 Joshua M. Boniface <joshua@boniface.me>
 #
 #    This program is free software: you can redistribute it and/or modify
 #    it under the terms of the GNU General Public License as published by

monitoring/README.md

@@ -6,9 +6,7 @@ This directory contains several monitoring resources that can be used with vario
 
 The included example Prometheus configuration and Grafana dashboard can be used to query the PVC API for Prometheus data and display it with a consistent dashboard.
 
-Note that the default configuration here also includes Ceph cluster information; a Ceph dashboard can be found externally.
-
-Note too that this does not include node export examples from individual PVC nodes; those must be set up separately.
+See the README in the `prometheus` folder for more details.
 
 ## Munin
 

monitoring/munin/pvc

@@ -34,7 +34,7 @@ warning=0.99
 critical=1.99
 
 export PVC_CLIENT_DIR="/run/shm/munin-pvc"
-PVC_CMD="/usr/bin/pvc --quiet --cluster local status --format json-pretty"
+PVC_CMD="/usr/bin/sudo -E /usr/bin/pvc --quiet cluster status --format json-pretty"
 JQ_CMD="/usr/bin/jq"
 
 output_usage() {
@@ -126,7 +126,7 @@ output_values() {
     is_maintenance="$( $JQ_CMD ".maintenance" <<<"${PVC_OUTPUT}" | tr -d '"' )"
 
     cluster_health="$( $JQ_CMD ".cluster_health.health" <<<"${PVC_OUTPUT}" | tr -d '"' )"
-    cluster_health_messages="$( $JQ_CMD -r ".cluster_health.messages | @csv" <<<"${PVC_OUTPUT}" | tr -d '"' | sed 's/,/, /g' )"
+    cluster_health_messages="$( $JQ_CMD -r ".cluster_health.messages | map(.text) | join(\", \")" <<<"${PVC_OUTPUT}" )"
     echo 'multigraph pvc_cluster_health'
     echo "pvc_cluster_health.value ${cluster_health}"
     echo "pvc_cluster_health.extinfo ${cluster_health_messages}"
@@ -142,7 +142,7 @@ output_values() {
     echo "pvc_cluster_alert.value ${cluster_health_alert}"
 
     node_health="$( $JQ_CMD ".node_health.${HOST}.health" <<<"${PVC_OUTPUT}" | tr -d '"' )"
-    node_health_messages="$( $JQ_CMD -r ".node_health.${HOST}.messages | @csv" <<<"${PVC_OUTPUT}" | tr -d '"' | sed 's/,/, /g' )"
+    node_health_messages="$( $JQ_CMD -r ".node_health.${HOST}.messages | join(\", \")" <<<"${PVC_OUTPUT}" )"
     echo 'multigraph pvc_node_health'
     echo "pvc_node_health.value ${node_health}"
     echo "pvc_node_health.extinfo ${node_health_messages}"

monitoring/prometheus/README.md

@@ -0,0 +1,44 @@
+# Prometheus Monitoring for PVC
+
+This example contains a Prometheus config snippit, an example `file_sd_configs` file, and a Grafana dashboard for monitoring a PVC cluster using the inbuilt metrics (`/api/v1/metrics`).
+
+## `prometheus.yml`
+
+This snippit shows how to set up a scrape config leveraging the `file_sd_configs` file.
+
+This example uses `http` transport; if you use HTTPS for PVC API traffic (e.g. if it traverses the Internet), use `https` here. You can optionally disable certificate checking like so:
+
+```
+[...]
+scheme: "https"
+tls_config:
+  insecure_skip_verify: true
+file_sd_configs:
+[...]
+```
+
+Note that due to the limitations of the Prometheus configuration, this is a global option for all service discovery entries specified; it cannot be toggled for each connection individually.
+
+## `targets-pvc_cluster.json`
+
+This JSON-based config shows two example clusters as two discrete entries. This is required for proper labeling.
+
+Each entry must contain:
+
+* A single `targets` entry, pointing at the API address and port of the PVC cluster.
+
+* Two `labels` which are leveraged by the Grafana dashboard:
+
+   * `pvc_cluster_id`: An identifier for the cluster. Likely, the `Name` in your `pvc connection list` entry for the cluster.
+
+   * `pvc_cluster_name`: A nicer, more human-readable description of the cluster. Likely, the `Description` in your `pvc connection list` entry for the cluster.
+
+This file can be autogenerated from the list of configured PVC clusters in a PVC CLI client using the `pvc connection list --format json-prometheus` option.
+
+## `grafana-pvc-cluster-dashboard.json`
+
+This JSON-based Grafana dashboard allows for a nice presentation of the Cluster and Node metrics collected by the above Prometheus pollers. The cluster can be selected (based on the `pvc_cluster_name` value) and useful information about the cluster is then displayed.
+
+## `grafana-pvc-vms-dashboard.json`
+
+This JSON-based Grafana dashboard allows for a nice presentation of the VM metrics collected by the above Prometheus pollers. The cluster can be selected (based on the `pvc_cluster_name` value) and useful information about a given VM is then displayed.