Bump version to 0.9.102

1. Ensure the local connection is actually always present if it exists,
and stored in the store file.

2. Remove any invalid "local" store entries if present (i.e.
pvcapid.yaml entries from legacy versions).

3. Order the connection lists such that "local" is always first.

4. Improve pretty list output format such that all fields are wider if
needed

.version

@@ -1 +1 @@
-0.9.100
+0.9.102

CHANGELOG.md

@@ -1,5 +1,34 @@
 ## PVC Changelog
 
+###### [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

api-daemon/pvcapid/helper.py

@@ -1438,15 +1438,7 @@ def vm_snapshot_receive_block_createsnap(zkhandler, pool, volume, snapshot):
 @ZKConnection(config)
 def vm_snapshot_receive_config(zkhandler, snapshot, vm_config, source_snapshot=None):
     """
-    Receive a VM configuration from a remote system
+    Receive a VM configuration snapshot from a remote system, and modify it to work on our system
-
-    This function requires some explanation.
-
-    We get a full JSON dump of the VM configuration as provided by `pvc vm info`. This contains all the information we
-    reasonably need to replicate the VM at the given snapshot, including metainformation.
-
-    First, we need to determine if this is an incremental or full send. If it's full, and the VM already exists,
-    this is an issue and we have to error. But this should have already happened with the RBD volumes.
     """
 
     def parse_unified_diff(diff_text, original_text):
@@ -1503,13 +1495,28 @@ def vm_snapshot_receive_config(zkhandler, snapshot, vm_config, source_snapshot=N
     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"]
-    xml_data = etree.fromstring(snapshot_vm_xml)
     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 (

client-cli/pvc/cli/formatters.py

@@ -905,7 +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
 
@@ -1005,7 +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

@@ -167,9 +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):

client-cli/pvc/cli/parsers.py

@@ -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/lib/vm.py

@@ -2402,8 +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(
@@ -2428,7 +2430,9 @@ def format_list(config, vm_list):
                 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_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,

client-cli/setup.py

@@ -2,7 +2,7 @@ from setuptools import setup
 
 setup(
     name="pvc",
-    version="0.9.100",
+    version="0.9.102",
     packages=["pvc.cli", "pvc.lib"],
     install_requires=[
         "Click",

daemon-common/config.py

@@ -375,8 +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":

daemon-common/vm.py

@@ -1997,11 +1997,14 @@ def vm_worker_flush_locks(zkhandler, celery, domain, force_unlock=False):
         )
 
         if lock_remove_retcode != 0:
-            fail(
+            if force_unlock and "No such file or directory" in lock_remove_stderr:
-                celery,
+                continue
-                f"Failed to free RBD lock {lock['id']} on volume {rbd}: {lock_remove_stderr}",
+            else:
-            )
+                fail(
-            return False
+                    celery,
+                    f"Failed to free RBD lock {lock['id']} on volume {rbd}: {lock_remove_stderr}",
+                )
+                return False
 
     current_stage += 1
     return finish(
@@ -3266,7 +3269,7 @@ def vm_worker_send_snapshot(
         )
         return False
 
-    expected_destination_pvc_version = "0.9.100"  # TODO: 0.9.101 when completed
+    expected_destination_pvc_version = "0.9.101"
     # Work around development versions
     current_destination_pvc_version = re.sub(
         r"~git-.*", "", current_destination_pvc_version
@@ -3810,7 +3813,7 @@ def vm_worker_create_mirror(
         )
         return False
 
-    expected_destination_pvc_version = "0.9.100"  # TODO: 0.9.101 when completed
+    expected_destination_pvc_version = "0.9.101"
     # Work around development versions
     current_destination_pvc_version = re.sub(
         r"~git-.*", "", current_destination_pvc_version
@@ -4406,7 +4409,7 @@ def vm_worker_promote_mirror(
         )
         return False
 
-    expected_destination_pvc_version = "0.9.100"  # TODO: 0.9.101 when completed
+    expected_destination_pvc_version = "0.9.101"
     # Work around development versions
     current_destination_pvc_version = re.sub(
         r"~git-.*", "", current_destination_pvc_version

debian/changelog

@@ -1,3 +1,36 @@
+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

health-daemon/pvchealthd/Daemon.py

@@ -33,7 +33,7 @@ import os
 import signal
 
 # Daemon version
-version = "0.9.100"
+version = "0.9.102"
 
 
 ##########################################################

node-daemon/pvcnoded/Daemon.py

@@ -49,7 +49,7 @@ import re
 import json
 
 # Daemon version
-version = "0.9.100"
+version = "0.9.102"
 
 
 ##########################################################

node-daemon/pvcnoded/util/fencing.py

@@ -247,7 +247,7 @@ def migrateFromFencedNode(zkhandler, node_name, config, logger):
             )
             zkhandler.write(
                 {
-                    (("domain.state", dom_uuid), "stopped"),
+                    (("domain.state", dom_uuid), "stop"),
                     (("domain.meta.autostart", dom_uuid), "True"),
                 }
             )

node-daemon/pvcnoded/util/services.py

@@ -102,5 +102,5 @@ def start_system_services(logger, config):
     start_workerd(logger, config)
     start_healthd(logger, config)
 
-    logger.out("Waiting 5 seconds for daemons to start", state="s")
+    logger.out("Waiting 10 seconds for daemons to start", state="s")
-    sleep(5)
+    sleep(10)

node-daemon/pvcnoded/util/zookeeper.py

@@ -188,3 +188,6 @@ def setup_node(logger, config, zkhandler):
                 (("node.count.networks", config["node_hostname"]), "0"),
             ]
         )
+
+    logger.out("Waiting 5 seconds for Zookeeper to synchronize", state="s")
+    time.sleep(5)

worker-daemon/pvcworkerd/Daemon.py

@@ -55,7 +55,7 @@ from daemon_lib.autobackup import (
 )
 
 # Daemon version
-version = "0.9.100"
+version = "0.9.102"
 
 
 config = cfg.get_configuration()