Remove WebUI from README

Adds a new physical network interface stats parser to the node
keepalives, and leverages this information to provide a network
utilization overview in the Prometheus metrics.

README.md

@@ -19,7 +19,7 @@ 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.
 

api-daemon/pvcapid/flaskapi.py

@@ -640,14 +640,15 @@ class API_Metrics(Resource):
           400:
             description: Bad request
         """
-        cluster_output, cluster_retcode = api_helper.cluster_metrics()
+        health_output, health_retcode = api_helper.cluster_health_metrics()
+        resource_output, resource_retcode = api_helper.cluster_resource_metrics()
         ceph_output, ceph_retcode = api_helper.ceph_metrics()
 
-        if cluster_retcode != 200 or ceph_retcode != 200:
+        if health_retcode != 200 or resource_retcode != 200 or ceph_retcode != 200:
             output = "Error: Failed to obtain data"
             retcode = 400
         else:
-            output = cluster_output + ceph_output
+            output = health_output + resource_output + ceph_output
             retcode = 200
 
         response = flask.make_response(output, retcode)
@@ -658,11 +659,11 @@ class API_Metrics(Resource):
 api.add_resource(API_Metrics, "/metrics")
 
 
-# /metrics/pvc
+# /metrics/health
-class API_Metrics_PVC(Resource):
+class API_Metrics_Health(Resource):
     def get(self):
         """
-        Return the current PVC cluster status in Prometheus-compatible metrics format
+        Return the current PVC cluster health status in Prometheus-compatible metrics format
 
         Endpoint is unauthenticated to allow metrics exfiltration without having to deal
         with the Prometheus compatibility later.
@@ -675,13 +676,13 @@ class API_Metrics_PVC(Resource):
           400:
             description: Bad request
         """
-        cluster_output, cluster_retcode = api_helper.cluster_metrics()
+        health_output, health_retcode = api_helper.cluster_health_metrics()
 
-        if cluster_retcode != 200:
+        if health_retcode != 200:
             output = "Error: Failed to obtain data"
             retcode = 400
         else:
-            output = cluster_output
+            output = health_output
             retcode = 200
 
         response = flask.make_response(output, retcode)
@@ -689,7 +690,41 @@ class API_Metrics_PVC(Resource):
         return response
 
 
-api.add_resource(API_Metrics_PVC, "/metrics/pvc")
+api.add_resource(API_Metrics_Health, "/metrics/health")
+
+
+# /metrics/resource
+class API_Metrics_Resource(Resource):
+    def get(self):
+        """
+        Return the current PVC cluster resource utilizations in Prometheus-compatible metrics format
+
+        Endpoint is unauthenticated to allow metrics exfiltration without having to deal
+        with the Prometheus compatibility later.
+        ---
+        tags:
+          - root
+        responses:
+          200:
+            description: OK
+          400:
+            description: Bad request
+        """
+        resource_output, resource_retcode = api_helper.cluster_resource_metrics()
+
+        if resource_retcode != 200:
+            output = "Error: Failed to obtain data"
+            retcode = 400
+        else:
+            output = resource_output
+            retcode = 200
+
+        response = flask.make_response(output, retcode)
+        response.mimetype = "text/plain"
+        return response
+
+
+api.add_resource(API_Metrics_Resource, "/metrics/resource")
 
 
 # /metrics/ceph
@@ -1133,6 +1168,9 @@ class API_Node_Root(Resource):
                     provisioned:
                       type: integer
                       description: The total amount of RAM provisioned to all domains (regardless of state) on this node in MB
+                interfaces:
+                  type: object
+                  description: Details on speed, bytes, and packets per second of each node physical network interface
         parameters:
           - in: query
             name: limit

api-daemon/pvcapid/helper.py

@@ -126,12 +126,27 @@ 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:

daemon-common/log.py

@@ -146,7 +146,7 @@ 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/node.py

@@ -103,6 +103,7 @@ 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 +122,7 @@ 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 +156,8 @@ def getNodeInformation(zkhandler, node_name):
         zkhandler, node_name, node_health_plugins
     )
 
+    node_network_stats = json.loads(_node_network_stats)
+
     # Construct a data structure to represent the data
     node_information = {
         "name": node_name,
@@ -182,6 +186,7 @@ def getNodeInformation(zkhandler, node_name):
             "used": node_mem_used,
             "free": node_mem_free,
         },
+        "interfaces": node_network_stats,
     }
     return node_information
 

daemon-common/zkhandler.py

@@ -572,7 +572,7 @@ class ZKHandler(object):
 #
 class ZKSchema(object):
     # Current version
-    _version = 11
+    _version = 12
 
     # Root for doing nested keys
     _schema_root = ""
@@ -651,6 +651,7 @@ 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": {

node-daemon/monitoring/prometheus/grafana-pvc-health-dashboard.json

@@ -1510,7 +1510,7 @@
               {
                 "id": "color",
                 "value": {
-                  "fixedColor": "light-red",
+                  "fixedColor": "super-light-red",
                   "mode": "fixed"
                 }
               }
@@ -1525,7 +1525,7 @@
               {
                 "id": "color",
                 "value": {
-                  "fixedColor": "semi-dark-red",
+                  "fixedColor": "red",
                   "mode": "fixed"
                 }
               }
@@ -1540,7 +1540,7 @@
               {
                 "id": "color",
                 "value": {
-                  "fixedColor": "semi-dark-blue",
+                  "fixedColor": "dark-red",
                   "mode": "fixed"
                 }
               }
@@ -2556,7 +2556,8 @@
   "refresh": "5s",
   "schemaVersion": 38,
   "tags": [
-    "pvc"
+    "pvc",
+    "health"
   ],
   "templating": {
     "list": [
@@ -2592,8 +2593,8 @@
   },
   "timepicker": {},
   "timezone": "",
-  "title": "PVC Cluster",
+  "title": "PVC Cluster Health",
   "uid": "fbddd9f9-aadb-4c97-8aea-57c29e5de234",
-  "version": 57,
+  "version": 1,
   "weekStart": ""
 }

node-daemon/pvcnoded/Daemon.py

@@ -31,6 +31,7 @@ import pvcnoded.objects.MetadataAPIInstance as MetadataAPIInstance
 import pvcnoded.objects.VMInstance as VMInstance
 import pvcnoded.objects.NodeInstance as NodeInstance
 import pvcnoded.objects.VXNetworkInstance as VXNetworkInstance
+import pvcnoded.objects.NetstatsInstance as NetstatsInstance
 import pvcnoded.objects.SRIOVVFInstance as SRIOVVFInstance
 import pvcnoded.objects.CephInstance as CephInstance
 
@@ -200,9 +201,9 @@ def entrypoint():
 
     # Define a cleanup function
     def cleanup(failure=False):
-        nonlocal logger, zkhandler, keepalive_timer, d_domain
+        nonlocal logger, zkhandler, keepalive_timer, d_domain, netstats
 
-        logger.out("Terminating pvcnoded and cleaning up", state="s")
+        logger.out("Terminating pvcnoded", state="s")
 
         # Set shutdown state in Zookeeper
         zkhandler.write([(("node.state.daemon", config["node_hostname"]), "shutdown")])
@@ -249,12 +250,20 @@ def entrypoint():
         except Exception:
             pass
 
-        # Set stop state in Zookeeper
+        logger.out("Cleaning up", state="s")
-        zkhandler.write([(("node.state.daemon", config["node_hostname"]), "stop")])
+
+        # Stop netstats instance
+        try:
+            netstats.shutdown()
+        except Exception:
+            pass
 
         # Forcibly terminate dnsmasq because it gets stuck sometimes
         common.run_os_command("killall dnsmasq")
 
+        # Set stop state in Zookeeper
+        zkhandler.write([(("node.state.daemon", config["node_hostname"]), "stop")])
+
         # Close the Zookeeper connection
         try:
             zkhandler.disconnect(persistent=True)
@@ -1000,9 +1009,12 @@ def entrypoint():
                         state="s",
                     )
 
+    # Set up netstats
+    netstats = NetstatsInstance.NetstatsInstance(logger, config, zkhandler, this_node)
+
     # Start keepalived thread
     keepalive_timer = pvcnoded.util.keepalive.start_keepalive_timer(
-        logger, config, zkhandler, this_node
+        logger, config, zkhandler, this_node, netstats
     )
 
     # Tick loop; does nothing since everything is async

node-daemon/pvcnoded/objects/NetstatsInstance.py

@@ -0,0 +1,293 @@
+#!/usr/bin/env python3
+
+# NetstatsInstance.py - Class implementing a PVC network stats gatherer and run by pvcnoded
+# Part of the Parallel Virtual Cluster (PVC) system
+#
+#    Copyright (C) 2018-2023 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 apscheduler.schedulers.background import BackgroundScheduler
+from collections import deque
+from json import dumps
+from os import walk
+from os.path import exists
+
+
+class NetstatsIfaceInstance(object):
+    """
+    NetstatsIfaceInstance
+
+    This class implements a rolling statistics poller for a network interface,
+    collecting stats on the bits and packets per second in both directions every
+    second.
+
+    Via the get_stats() function, it returns the rolling average of all 4 values,
+    as well as totals, over the last 5 seconds (self.avg_samples) as a tuple of:
+      (rx_bps, rx_pps, tx_bps, tx_pps, total_bps, total_pps, link_speed, state)
+    """
+
+    def __init__(self, logger, iface, avg_samples):
+        """
+        Initialize the class instance, creating our BackgroundScheduler, setting
+        the average sample rate, and creating the deques and average values.
+        """
+        self.logger = logger
+        self.iface = iface
+
+        self.data_valid = False
+        self.data_polls = 0
+
+        self.timer = BackgroundScheduler()
+        self.timer.add_job(self.gather_stats, trigger="interval", seconds=1)
+
+        self.avg_samples = avg_samples
+
+        self.link_speed = 0
+        self.state = "down"
+
+        self.rx_bits_rolling = deque(list(), self.avg_samples + 1)
+        self.rx_bps = 0
+
+        self.rx_packets_rolling = deque(list(), self.avg_samples + 1)
+        self.rx_pps = 0
+
+        self.tx_bits_rolling = deque(list(), self.avg_samples + 1)
+        self.tx_bps = 0
+
+        self.tx_packets_rolling = deque(list(), self.avg_samples + 1)
+        self.tx_pps = 0
+
+        self.total_bps = 0
+        self.total_pps = 0
+
+    def get_iface_stats(self):
+        """
+        Reads the interface statistics from the sysfs for the interface.
+        """
+        iface_state_path = f"/sys/class/net/{self.iface}/operstate"
+        with open(iface_state_path) as stfh:
+            self.state = stfh.read().strip()
+
+        iface_speed_path = f"/sys/class/net/{self.iface}/speed"
+        try:
+            with open(iface_speed_path) as spfh:
+                # The speed key is always in Mbps so multiply by 1000*1000 to get bps
+                self.link_speed = int(spfh.read()) * 1000 * 1000
+        except OSError:
+            self.link_speed = 0
+
+        iface_stats_path = f"/sys/class/net/{self.iface}/statistics"
+        with open(f"{iface_stats_path}/rx_bytes") as rxbfh:
+            self.rx_bits_rolling.append(int(rxbfh.read()) * 8)
+        with open(f"{iface_stats_path}/tx_bytes") as txbfh:
+            self.tx_bits_rolling.append(int(txbfh.read()) * 8)
+        with open(f"{iface_stats_path}/rx_packets") as rxpfh:
+            self.rx_packets_rolling.append(int(rxpfh.read()) * 8)
+        with open(f"{iface_stats_path}/tx_packets") as txpfh:
+            self.tx_packets_rolling.append(int(txpfh.read()) * 8)
+
+    def calculate_averages(self):
+        """
+        Calculates the bps/pps values from the rolling values.
+        """
+
+        rx_bits_diffs = list()
+        for sample_idx in range(self.avg_samples, 0, -1):
+            rx_bits_diffs.append(
+                self.rx_bits_rolling[sample_idx] - self.rx_bits_rolling[sample_idx - 1]
+            )
+        self.rx_bps = int(sum(rx_bits_diffs) / self.avg_samples)
+
+        rx_packets_diffs = list()
+        for sample_idx in range(self.avg_samples, 0, -1):
+            rx_packets_diffs.append(
+                self.rx_packets_rolling[sample_idx]
+                - self.rx_packets_rolling[sample_idx - 1]
+            )
+        self.rx_pps = int(sum(rx_packets_diffs) / self.avg_samples)
+
+        tx_bits_diffs = list()
+        for sample_idx in range(self.avg_samples, 0, -1):
+            tx_bits_diffs.append(
+                self.tx_bits_rolling[sample_idx] - self.tx_bits_rolling[sample_idx - 1]
+            )
+        self.tx_bps = int(sum(tx_bits_diffs) / self.avg_samples)
+
+        tx_packets_diffs = list()
+        for sample_idx in range(self.avg_samples, 0, -1):
+            tx_packets_diffs.append(
+                self.tx_packets_rolling[sample_idx]
+                - self.tx_packets_rolling[sample_idx - 1]
+            )
+        self.tx_pps = int(sum(tx_packets_diffs) / self.avg_samples)
+
+        self.total_bps = self.rx_bps + self.tx_bps
+        self.total_pps = self.rx_pps + self.tx_pps
+
+    def gather_stats(self):
+        """
+        Gathers the current stats and then calculates the averages.
+
+        Runs via the BackgroundScheduler timer every 1 second.
+        """
+        self.get_iface_stats()
+        if self.data_valid:
+            self.calculate_averages()
+
+        # Handle data validity: our data is invalid until we hit enough polls
+        # to make a valid average (avg_samples plus 1).
+        if not self.data_valid:
+            self.data_polls += 1
+            if self.data_polls > self.avg_samples:
+                self.data_valid = True
+
+    def start(self):
+        """
+        Starts the timer.
+        """
+        self.timer.start()
+
+    def stop(self):
+        """
+        Stops the timer.
+        """
+        self.timer.shutdown()
+
+    def get_stats(self):
+        """
+        Returns a tuple of the current statistics.
+        """
+        if not self.data_valid:
+            return None
+
+        return (
+            self.rx_bps,
+            self.rx_pps,
+            self.tx_bps,
+            self.tx_pps,
+            self.total_bps,
+            self.total_pps,
+            self.link_speed,
+            self.state,
+        )
+
+
+class NetstatsInstance(object):
+    """
+    NetstatsInstance
+
+    This class implements a rolling statistics poller for all PHYSICAL network interfaces,
+    on the system, initializing a NetstatsIfaceInstance for each, as well as handling
+    value updates into Zookeeper.
+    """
+
+    def __init__(self, logger, config, zkhandler, this_node):
+        """
+        Initialize the class instance.
+        """
+        self.logger = logger
+        self.config = config
+        self.zkhandler = zkhandler
+        self.node_name = this_node.name
+
+        self.interfaces = dict()
+
+        self.logger.out(
+            f"Starting netstats collector ({self.config['keepalive_interval']} second interval)",
+            state="s",
+        )
+
+        self.set_interfaces()
+
+    def shutdown(self):
+        """
+        Stop all pollers and delete the NetstatsIfaceInstance objects
+        """
+        # Empty the network stats object
+        self.zkhandler.write([(("node.network.stats", self.node_name), dumps({}))])
+
+        for iface in self.interfaces.keys():
+            self.interfaces[iface].stop()
+
+    def set_interfaces(self):
+        """
+        Sets the list of interfaces on the system, and then ensures that each
+        interface has a NetstatsIfaceInstance assigned to it and polling.
+        """
+        # Get a list of all active interfaces
+        net_root_path = "/sys/class/net"
+        all_ifaces = list()
+        for (_, dirnames, _) in walk(net_root_path):
+            all_ifaces.extend(dirnames)
+        all_ifaces.sort()
+
+        self.logger.out(
+            f"Parsing network list: {all_ifaces}", state="d", prefix="netstats-thread"
+        )
+
+        # Add any missing interfaces
+        for iface in all_ifaces:
+            if not exists(f"{net_root_path}/{iface}/device"):
+                # This is not a physical interface; skip it
+                continue
+
+            if iface not in self.interfaces.keys():
+                # Set the number of samples to be equal to the keepalive interval, so that each
+                # keepalive has a fresh set of data from the last keepalive_interval seconds.
+                self.interfaces[iface] = NetstatsIfaceInstance(
+                    self.logger, iface, self.config["keepalive_interval"]
+                )
+                self.interfaces[iface].start()
+        # Remove any superfluous interfaces
+        for iface in self.interfaces.keys():
+            if iface not in all_ifaces:
+                self.interfaces[iface].stop()
+                del self.interfaces[iface]
+
+    def set_data(self):
+        data = dict()
+        for iface in self.interfaces.keys():
+            self.logger.out(
+                f"Getting data for interface {iface}",
+                state="d",
+                prefix="netstats-thread",
+            )
+            iface_stats = self.interfaces[iface].get_stats()
+            if iface_stats is None:
+                continue
+            (
+                iface_rx_bps,
+                iface_rx_pps,
+                iface_tx_bps,
+                iface_tx_pps,
+                iface_total_bps,
+                iface_total_pps,
+                iface_link_speed,
+                iface_state,
+            ) = iface_stats
+            data[iface] = {
+                "rx_bps": iface_rx_bps,
+                "rx_pps": iface_rx_pps,
+                "tx_bps": iface_tx_bps,
+                "tx_pps": iface_tx_pps,
+                "total_bps": iface_total_bps,
+                "total_pps": iface_total_pps,
+                "link_speed": iface_link_speed,
+                "state": iface_state,
+            }
+
+        self.zkhandler.write([(("node.network.stats", self.node_name), dumps(data))])

node-daemon/pvcnoded/util/keepalive.py

@@ -51,7 +51,7 @@ libvirt_vm_states = {
 }
 
 
-def start_keepalive_timer(logger, config, zkhandler, this_node):
+def start_keepalive_timer(logger, config, zkhandler, this_node, netstats):
     keepalive_interval = config["keepalive_interval"]
     logger.out(
         f"Starting keepalive timer ({keepalive_interval} second interval)", state="s"
@@ -59,7 +59,7 @@ def start_keepalive_timer(logger, config, zkhandler, this_node):
     keepalive_timer = BackgroundScheduler()
     keepalive_timer.add_job(
         node_keepalive,
-        args=(logger, config, zkhandler, this_node),
+        args=(logger, config, zkhandler, this_node, netstats),
         trigger="interval",
         seconds=keepalive_interval,
     )
@@ -684,7 +684,7 @@ def collect_vm_stats(logger, config, zkhandler, this_node, queue):
 
 
 # Keepalive update function
-def node_keepalive(logger, config, zkhandler, this_node):
+def node_keepalive(logger, config, zkhandler, this_node, netstats):
     debug = config["debug"]
 
     # Display node information to the terminal
@@ -793,6 +793,10 @@ def node_keepalive(logger, config, zkhandler, this_node):
     this_node.memfree = int(psutil.virtual_memory().free / 1024 / 1024)
     this_node.cpuload = round(os.getloadavg()[0], 2)
 
+    # Get node network statistics via netstats instance
+    netstats.set_interfaces()
+    netstats.set_data()
+
     # Join against running threads
     if config["enable_hypervisor"]:
         vm_stats_thread.join(timeout=config["keepalive_interval"])