2.4.190

add exclusion toggle

.github/DISCUSSION_TEMPLATE/2-4.yml

@@ -31,6 +31,7 @@ body:
         - 2.4.160
         - 2.4.170
         - 2.4.180
+        - 2.4.190
         - Other (please provide detail below)
     validations:
       required: true

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 2.4.180-20250916 ISO image released on 2025/09/17
+### 2.4.190-20251024 ISO image released on 2025/10/24
 
 
 ### Download and Verify
 
-2.4.180-20250916 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-2.4.180-20250916.iso
+2.4.190-20251024 ISO image:  
+https://download.securityonion.net/file/securityonion/securityonion-2.4.190-20251024.iso
  
-MD5: DE93880E38DE4BE45D05A41E1745CB1F  
-SHA1: AEA6948911E50A4A38E8729E0E965C565402E3FC  
-SHA256: C9BD8CA071E43B048ABF9ED145B87935CB1D4BB839B2244A06FAD1BBA8EAC84A  
+MD5: 25358481FB876226499C011FC0710358  
+SHA1: 0B26173C0CE136F2CA40A15046D1DFB78BCA1165  
+SHA256: 4FD9F62EDA672408828B3C0C446FE5EA9FF3C4EE8488A7AB1101544A3C487872  
 
 Signature for ISO image:  
-https://github.com/Security-Onion-Solutions/securityonion/raw/2.4/main/sigs/securityonion-2.4.180-20250916.iso.sig
+https://github.com/Security-Onion-Solutions/securityonion/raw/2.4/main/sigs/securityonion-2.4.190-20251024.iso.sig
 
 Signing key:  
 https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/2.4/main/KEYS  
@@ -25,22 +25,22 @@ wget https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/2.
 
 Download the signature file for the ISO:  
 ```
-wget https://github.com/Security-Onion-Solutions/securityonion/raw/2.4/main/sigs/securityonion-2.4.180-20250916.iso.sig
+wget https://github.com/Security-Onion-Solutions/securityonion/raw/2.4/main/sigs/securityonion-2.4.190-20251024.iso.sig
 ```
 
 Download the ISO image:  
 ```
-wget https://download.securityonion.net/file/securityonion/securityonion-2.4.180-20250916.iso
+wget https://download.securityonion.net/file/securityonion/securityonion-2.4.190-20251024.iso
 ```
 
 Verify the downloaded ISO image using the signature file:  
 ```
-gpg --verify securityonion-2.4.180-20250916.iso.sig securityonion-2.4.180-20250916.iso
+gpg --verify securityonion-2.4.190-20251024.iso.sig securityonion-2.4.190-20251024.iso
 ```
 
 The output should show "Good signature" and the Primary key fingerprint should match what's shown below:
 ```
-gpg: Signature made Tue 16 Sep 2025 06:30:19 PM EDT using RSA key ID FE507013
+gpg: Signature made Thu 23 Oct 2025 07:21:46 AM EDT using RSA key ID FE507013
 gpg: Good signature from "Security Onion Solutions, LLC <info@securityonionsolutions.com>"
 gpg: WARNING: This key is not certified with a trusted signature!
 gpg:          There is no indication that the signature belongs to the owner.

VERSION

@@ -1 +1 @@
-2.4.180
+2.4.190

salt/_modules/hypervisor.py

@@ -0,0 +1,91 @@
+#!/opt/saltstack/salt/bin/python3
+
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+#
+# Note: Per the Elastic License 2.0, the second limitation states:
+#
+#   "You may not move, change, disable, or circumvent the license key functionality
+#    in the software, and you may not remove or obscure any functionality in the
+#    software that is protected by the license key."
+
+"""
+Salt execution module for hypervisor operations.
+
+This module provides functions for managing hypervisor configurations,
+including VM file management.
+"""
+
+import json
+import logging
+import os
+
+log = logging.getLogger(__name__)
+
+__virtualname__ = 'hypervisor'
+
+
+def __virtual__():
+    """
+    Only load this module if we're on a system that can manage hypervisors.
+    """
+    return __virtualname__
+
+
+def remove_vm_from_vms_file(vms_file_path, vm_hostname, vm_role):
+    """
+    Remove a VM entry from the hypervisorVMs file.
+    
+    Args:
+        vms_file_path (str): Path to the hypervisorVMs file
+        vm_hostname (str): Hostname of the VM to remove (without role suffix)
+        vm_role (str): Role of the VM
+        
+    Returns:
+        dict: Result dictionary with success status and message
+        
+    CLI Example:
+        salt '*' hypervisor.remove_vm_from_vms_file /opt/so/saltstack/local/salt/hypervisor/hosts/hypervisor1VMs node1 nsm
+    """
+    try:
+        # Check if file exists
+        if not os.path.exists(vms_file_path):
+            msg = f"VMs file not found: {vms_file_path}"
+            log.error(msg)
+            return {'result': False, 'comment': msg}
+        
+        # Read current VMs
+        with open(vms_file_path, 'r') as f:
+            content = f.read().strip()
+            vms = json.loads(content) if content else []
+        
+        # Find and remove the VM entry
+        original_count = len(vms)
+        vms = [vm for vm in vms if not (vm.get('hostname') == vm_hostname and vm.get('role') == vm_role)]
+        
+        if len(vms) < original_count:
+            # VM was found and removed, write back to file
+            with open(vms_file_path, 'w') as f:
+                json.dump(vms, f, indent=2)
+            
+            # Set socore:socore ownership (939:939)
+            os.chown(vms_file_path, 939, 939)
+            
+            msg = f"Removed VM {vm_hostname}_{vm_role} from {vms_file_path}"
+            log.info(msg)
+            return {'result': True, 'comment': msg}
+        else:
+            msg = f"VM {vm_hostname}_{vm_role} not found in {vms_file_path}"
+            log.warning(msg)
+            return {'result': False, 'comment': msg}
+            
+    except json.JSONDecodeError as e:
+        msg = f"Failed to parse JSON in {vms_file_path}: {str(e)}"
+        log.error(msg)
+        return {'result': False, 'comment': msg}
+    except Exception as e:
+        msg = f"Failed to remove VM {vm_hostname}_{vm_role} from {vms_file_path}: {str(e)}"
+        log.error(msg)
+        return {'result': False, 'comment': msg}

salt/_modules/qcow2.py

@@ -7,12 +7,14 @@
 
 """
 Salt module for managing QCOW2 image configurations and VM hardware settings. This module provides functions
-for modifying network configurations within QCOW2 images and adjusting virtual machine hardware settings.
-It serves as a Salt interface to the so-qcow2-modify-network and so-kvm-modify-hardware scripts.
+for modifying network configurations within QCOW2 images, adjusting virtual machine hardware settings, and
+creating virtual storage volumes. It serves as a Salt interface to the so-qcow2-modify-network,
+so-kvm-modify-hardware, and so-kvm-create-volume scripts.
 
-The module offers two main capabilities:
+The module offers three main capabilities:
 1. Network Configuration: Modify network settings (DHCP/static IP) within QCOW2 images
 2. Hardware Configuration: Adjust VM hardware settings (CPU, memory, PCI passthrough)
+3. Volume Management: Create and attach virtual storage volumes for NSM data
 
 This module is intended to work with Security Onion's virtualization infrastructure and is typically
 used in conjunction with salt-cloud for VM provisioning and management.
@@ -244,3 +246,90 @@ def modify_hardware_config(vm_name, cpu=None, memory=None, pci=None, start=False
     except Exception as e:
         log.error('qcow2 module: An error occurred while executing the script: {}'.format(e))
         raise
+
+def create_volume_config(vm_name, size_gb, start=False):
+    '''
+    Usage:
+        salt '*' qcow2.create_volume_config vm_name=<name> size_gb=<size> [start=<bool>]
+
+    Options:
+        vm_name
+            Name of the virtual machine to attach the volume to
+        size_gb
+            Volume size in GB (positive integer)
+            This determines the capacity of the virtual storage volume
+        start
+            Boolean flag to start the VM after volume creation
+            Optional - defaults to False
+
+    Examples:
+        1. **Create 500GB Volume:**
+            ```bash
+            salt '*' qcow2.create_volume_config vm_name='sensor1_sensor' size_gb=500
+            ```
+            This creates a 500GB virtual volume for NSM storage
+
+        2. **Create 1TB Volume and Start VM:**
+            ```bash
+            salt '*' qcow2.create_volume_config vm_name='sensor1_sensor' size_gb=1000 start=True
+            ```
+            This creates a 1TB volume and starts the VM after attachment
+
+    Notes:
+        - VM must be stopped before volume creation
+        - Volume is created as a qcow2 image and attached to the VM
+        - This is an alternative to disk passthrough via modify_hardware_config
+        - Volume is automatically attached to the VM's libvirt configuration
+        - Requires so-kvm-create-volume script to be installed
+        - Volume files are stored in the hypervisor's VM storage directory
+
+    Description:
+        This function creates and attaches a virtual storage volume to a KVM virtual machine
+        using the so-kvm-create-volume script. It creates a qcow2 disk image of the specified
+        size and attaches it to the VM for NSM (Network Security Monitoring) storage purposes.
+        This provides an alternative to physical disk passthrough, allowing flexible storage
+        allocation without requiring dedicated hardware. The VM can optionally be started
+        after the volume is successfully created and attached.
+
+    Exit Codes:
+        0: Success
+        1: Invalid parameters
+        2: VM state error (running when should be stopped)
+        3: Volume creation error
+        4: System command error
+        255: Unexpected error
+
+    Logging:
+        - All operations are logged to the salt minion log
+        - Log entries are prefixed with 'qcow2 module:'
+        - Volume creation and attachment operations are logged
+        - Errors include detailed messages and stack traces
+        - Final status of volume creation is logged
+    '''
+
+    # Validate size_gb parameter
+    if not isinstance(size_gb, int) or size_gb <= 0:
+        raise ValueError('size_gb must be a positive integer.')
+
+    cmd = ['/usr/sbin/so-kvm-create-volume', '-v', vm_name, '-s', str(size_gb)]
+
+    if start:
+        cmd.append('-S')
+
+    log.info('qcow2 module: Executing command: {}'.format(' '.join(shlex.quote(arg) for arg in cmd)))
+
+    try:
+        result = subprocess.run(cmd, capture_output=True, text=True, check=False)
+        ret = {
+            'retcode': result.returncode,
+            'stdout': result.stdout,
+            'stderr': result.stderr
+        }
+        if result.returncode != 0:
+            log.error('qcow2 module: Script execution failed with return code {}: {}'.format(result.returncode, result.stderr))
+        else:
+            log.info('qcow2 module: Script executed successfully.')
+        return ret
+    except Exception as e:
+        log.error('qcow2 module: An error occurred while executing the script: {}'.format(e))
+        raise

salt/common/grains.sls

@@ -0,0 +1,21 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+{% set nsm_exists = salt['file.directory_exists']('/nsm') %}
+{% if nsm_exists %}
+{%   set nsm_total = salt['cmd.shell']('df -BG /nsm | tail -1 | awk \'{print $2}\'') %}
+
+nsm_total:
+  grains.present:
+    - name: nsm_total
+    - value: {{ nsm_total }}
+
+{% else %}
+
+nsm_missing:
+  test.succeed_without_changes:
+    - name: /nsm does not exist, skipping grain assignment
+
+{% endif %}

salt/common/init.sls

@@ -4,6 +4,7 @@
 {% from 'vars/globals.map.jinja' import GLOBALS %}
 
 include:
+  - common.grains
   - common.packages
 {% if GLOBALS.role in GLOBALS.manager_roles %}
   - manager.elasticsearch # needed for elastic_curl_config state

salt/common/tools/sbin/so-common

@@ -441,8 +441,7 @@ lookup_grain() {
 
 lookup_role() {
 	id=$(lookup_grain id)
-	pieces=($(echo $id | tr '_' ' '))
-	echo ${pieces[1]}
+	echo "${id##*_}"
 }
 
 is_feature_enabled() {

salt/common/tools/sbin/so-log-check

@@ -222,6 +222,7 @@ if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Initialized license manager"  # SOC log: before fields.status was changed to fields.licenseStatus
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|from NIC checksum offloading" # zeek reporter.log
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|marked for removal"           # docker container getting recycled
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|tcp 127.0.0.1:6791: bind: address already in use" # so-elastic-fleet agent restarting. Seen starting w/ 8.18.8 https://github.com/elastic/kibana/issues/201459
 fi
 
 RESULT=0
@@ -268,6 +269,13 @@ for log_file in $(cat /tmp/log_check_files); do
     tail -n $RECENT_LOG_LINES $log_file > /tmp/log_check
     check_for_errors
 done
+# Look for OOM specific errors in /var/log/messages which can lead to odd behavior / test failures
+if [[ -f /var/log/messages ]]; then
+    status "Checking log file /var/log/messages"
+    if journalctl --since "24 hours ago" | grep -iE 'out of memory|oom-kill'; then
+        RESULT=1
+    fi
+fi
 
 # Cleanup temp files
 rm -f /tmp/log_check_files

salt/common/tools/sbin_jinja/so-import-pcap

@@ -173,7 +173,7 @@ for PCAP in $INPUT_FILES; do
   status "- assigning unique identifier to import: $HASH"
 
   pcap_data=$(pcapinfo "${PCAP}")
-  if ! echo "$pcap_data" | grep -q "First packet time:" || echo "$pcap_data" |egrep -q "Last packet time:    1970-01-01|Last packet time:    n/a"; then
+  if ! echo "$pcap_data" | grep -q "Earliest packet time:" || echo "$pcap_data" |egrep -q "Latest packet time:   1970-01-01|Latest packet time:   n/a"; then
     status "- this PCAP file is invalid; skipping"
     INVALID_PCAPS_COUNT=$((INVALID_PCAPS_COUNT + 1))
   else
@@ -205,8 +205,8 @@ for PCAP in $INPUT_FILES; do
       HASHES="${HASHES} ${HASH}"
     fi
 
-    START=$(pcapinfo "${PCAP}" -a |grep "First packet time:" | awk '{print $4}')
-    END=$(pcapinfo "${PCAP}" -e |grep "Last packet time:" | awk '{print $4}')
+    START=$(pcapinfo "${PCAP}" -a |grep "Earliest packet time:" | awk '{print $4}')
+    END=$(pcapinfo "${PCAP}" -e |grep "Latest packet time:" | awk '{print $4}')
     status "- found PCAP data spanning dates $START through $END"
 
     # compare $START to $START_OLDEST

salt/elasticfleet/enabled.sls

@@ -135,12 +135,18 @@ so-elastic-fleet-package-statefile:
 so-elastic-fleet-package-upgrade:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
+    - retry:
+        attempts: 3
+        interval: 10
     - onchanges:
       - file: /opt/so/state/elastic_fleet_packages.txt
 
 so-elastic-fleet-integrations:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-integration-policy-load
+    - retry:
+        attempts: 3
+        interval: 10
 
 so-elastic-agent-grid-upgrade:
   cmd.run:
@@ -152,7 +158,11 @@ so-elastic-agent-grid-upgrade:
 so-elastic-fleet-integration-upgrade:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-integration-upgrade
+    - retry:
+        attempts: 3
+        interval: 10
 
+{# Optional integrations script doesn't need the retries like so-elastic-fleet-integration-upgrade which loads the default integrations #}
 so-elastic-fleet-addon-integrations:
   cmd.run:
     - name: /usr/sbin/so-elastic-fleet-optional-integrations-load

salt/elasticfleet/files/integrations/grid-nodes_general/elasticsearch-logs.json

@@ -40,7 +40,7 @@
           "enabled": true,
           "vars": {
             "paths": [
-              "/opt/so/log/elasticsearch/*.log"
+              "/opt/so/log/elasticsearch/*.json"
             ]
           }
         },

salt/elasticfleet/files/integrations/grid-nodes_general/import-evtx-logs.json

@@ -20,7 +20,7 @@
             ],
             "data_stream.dataset": "import",
             "custom": "",
-            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.5.4\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.1.2\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.5.4\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.5.4\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.1.2\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
+            "processors": "- dissect:\n    tokenizer: \"/nsm/import/%{import.id}/evtx/%{import.file}\"\n    field: \"log.file.path\"\n    target_prefix: \"\"\n- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- drop_fields:\n    fields: [\"host\"]\n    ignore_missing: true\n- add_fields:\n    target: data_stream\n    fields:\n      type: logs\n      dataset: system.security\n- add_fields:\n    target: event\n    fields:\n      dataset: system.security\n      module: system\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: logs-system.security-2.6.1\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.sysmon_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.sysmon_operational-3.1.2\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.application-2.6.1\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-system.system-2.6.1\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: data_stream\n        fields:\n          dataset: windows.powershell_operational\n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n    - add_fields:\n        target: \"@metadata\"\n        fields:\n            pipeline: logs-windows.powershell_operational-3.1.2\n- add_fields:\n    target: data_stream\n    fields:\n        dataset: import",
             "tags": [
               "import"
             ]

salt/elasticfleet/tools/sbin/so-elastic-fleet-common

@@ -23,6 +23,13 @@ fi
 # Define a banner to separate sections
 banner="========================================================================="
 
+fleet_api() {
+    local QUERYPATH=$1
+    shift
+
+    curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/${QUERYPATH}" "$@" --retry 3 --retry-delay 10 --fail 2>/dev/null
+}
+
 elastic_fleet_integration_check() {
 
     AGENT_POLICY=$1
@@ -39,7 +46,9 @@ elastic_fleet_integration_create() {
 
     JSON_STRING=$1
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/package_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
+        return 1
+    fi
 }
 
 
@@ -56,7 +65,10 @@ elastic_fleet_integration_remove() {
                     '{"packagePolicyIds":[$INTEGRATIONID]}'
                     )
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/package_policies/delete" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies/delete" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+        echo "Error: Unable to delete '$NAME' from '$AGENT_POLICY'"
+        return 1
+    fi
 }
 
 elastic_fleet_integration_update() {
@@ -65,7 +77,9 @@ elastic_fleet_integration_update() {
 
     JSON_STRING=$2
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/package_policies/$UPDATE_ID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies/$UPDATE_ID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPUT -d "$JSON_STRING"; then
+        return 1
+    fi
 }
 
 elastic_fleet_integration_policy_upgrade() {
@@ -77,78 +91,83 @@ elastic_fleet_integration_policy_upgrade() {
                     '{"packagePolicyIds":[$INTEGRATIONID]}'
                     )
 
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/package_policies/upgrade" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "package_policies/upgrade" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+        return 1
+    fi
 }
 
 
 elastic_fleet_package_version_check() {
     PACKAGE=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/epm/packages/$PACKAGE" | jq -r '.item.version'
+
+    if output=$(fleet_api "epm/packages/$PACKAGE"); then
+        echo "$output" | jq -r '.item.version'
+    else
+        echo "Error: Failed to get current package version for '$PACKAGE'"
+        return 1
+    fi
 }
 
 elastic_fleet_package_latest_version_check() {
     PACKAGE=$1
-    if output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/epm/packages/$PACKAGE" --fail); then
+    if output=$(fleet_api "epm/packages/$PACKAGE"); then
         if version=$(jq -e -r '.item.latestVersion' <<< $output); then
             echo "$version"
         fi
     else
-        echo "Error: Failed to get latest version for $PACKAGE"
+        echo "Error: Failed to get latest version for '$PACKAGE'"
+        return 1
     fi
 }
 
 elastic_fleet_package_install() {
     PKG=$1
     VERSION=$2
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X POST -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  -d '{"force":true}' "localhost:5601/api/fleet/epm/packages/$PKG/$VERSION"
+    if ! fleet_api "epm/packages/$PKG/$VERSION" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d '{"force":true}'; then
+        return 1
+    fi
 }
 
 elastic_fleet_bulk_package_install() {
     BULK_PKG_LIST=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X POST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d@$1 "localhost:5601/api/fleet/epm/packages/_bulk"
-}
-
-elastic_fleet_package_is_installed() {
-    PACKAGE=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET -H 'kbn-xsrf: true' "localhost:5601/api/fleet/epm/packages/$PACKAGE" | jq -r '.item.status'
-}
-
-elastic_fleet_installed_packages() {
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET -H 'kbn-xsrf: true' -H 'Content-Type: application/json' "localhost:5601/api/fleet/epm/packages/installed?perPage=500"
-}
-
-elastic_fleet_agent_policy_ids() {
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies" | jq -r .items[].id
-    if [ $? -ne 0 ]; then
-        echo "Error: Failed to retrieve agent policies."
-        exit 1
+    if ! fleet_api "epm/packages/_bulk" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d@$BULK_PKG_LIST; then
+        return 1
     fi
 }
 
-elastic_fleet_agent_policy_names() {
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies" | jq -r .items[].name
-    if [ $? -ne 0 ]; then
+elastic_fleet_installed_packages() {
+    if ! fleet_api "epm/packages/installed?perPage=500"; then
+        return 1
+    fi
+}
+
+elastic_fleet_agent_policy_ids() {
+    if output=$(fleet_api "agent_policies"); then
+        echo "$output" | jq -r .items[].id
+    else
         echo "Error: Failed to retrieve agent policies."
-        exit 1
+        return 1
     fi
 }
 
 elastic_fleet_integration_policy_names() {
     AGENT_POLICY=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" | jq -r .item.package_policies[].name
-    if [ $? -ne 0 ]; then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "$output" | jq -r .item.package_policies[].name
+    else
         echo "Error: Failed to retrieve integrations for '$AGENT_POLICY'."
-        exit 1
+        return 1
     fi
 }
 
 elastic_fleet_integration_policy_package_name() {
     AGENT_POLICY=$1
     INTEGRATION=$2
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.name'
-    if [ $? -ne 0 ]; then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "$output" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.name'
+    else
         echo "Error: Failed to retrieve package name for '$INTEGRATION' in '$AGENT_POLICY'."
-        exit 1
+        return 1
     fi
 }
 
@@ -156,32 +175,32 @@ elastic_fleet_integration_policy_package_version() {
     AGENT_POLICY=$1
     INTEGRATION=$2
 
-    if output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" --fail); then
-        if version=$(jq -e -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.version' <<< $output); then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        if version=$(jq -e -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .package.version' <<< "$output"); then
             echo "$version"
         fi
     else
-        echo "Error: Failed to retrieve agent policy $AGENT_POLICY"
-        exit 1
+        echo "Error: Failed to retrieve integration version for '$INTEGRATION' in policy '$AGENT_POLICY'"
+        return 1
     fi
 }
 
 elastic_fleet_integration_id() {
     AGENT_POLICY=$1
     INTEGRATION=$2
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -L -X GET "localhost:5601/api/fleet/agent_policies/$AGENT_POLICY" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .id'
-    if [ $? -ne 0 ]; then
+    if output=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "$output" | jq -r --arg INTEGRATION "$INTEGRATION" '.item.package_policies[] | select(.name==$INTEGRATION)| .id'
+    else
         echo "Error: Failed to retrieve integration ID for '$INTEGRATION' in '$AGENT_POLICY'."
-        exit 1
+        return 1
     fi
 }
 
 elastic_fleet_integration_policy_dryrun_upgrade() {
     INTEGRATION_ID=$1
-    curl -s -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -H "Content-Type: application/json" -H 'kbn-xsrf: true' -L -X POST "localhost:5601/api/fleet/package_policies/upgrade/dryrun" -d "{\"packagePolicyIds\":[\"$INTEGRATION_ID\"]}"
-    if [ $? -ne 0 ]; then
+    if ! fleet_api "package_policies/upgrade/dryrun" -H "Content-Type: application/json" -H 'kbn-xsrf: true' -XPOST -d "{\"packagePolicyIds\":[\"$INTEGRATION_ID\"]}"; then
         echo "Error: Failed to complete dry run for '$INTEGRATION_ID'."
-        exit 1
+        return 1
     fi
 }
 
@@ -190,25 +209,18 @@ elastic_fleet_policy_create() {
     NAME=$1
     DESC=$2
     FLEETSERVER=$3
-        TIMEOUT=$4
+    TIMEOUT=$4
 
     JSON_STRING=$( jq -n \
-                    --arg NAME "$NAME" \
-                    --arg DESC "$DESC" \
-                    --arg TIMEOUT $TIMEOUT \
-                    --arg FLEETSERVER "$FLEETSERVER" \
-                    '{"name": $NAME,"id":$NAME,"description":$DESC,"namespace":"default","monitoring_enabled":["logs"],"inactivity_timeout":$TIMEOUT,"has_fleet_server":$FLEETSERVER}'
-                    )
+        --arg NAME "$NAME" \
+        --arg DESC "$DESC" \
+        --arg TIMEOUT $TIMEOUT \
+        --arg FLEETSERVER "$FLEETSERVER" \
+            '{"name": $NAME,"id":$NAME,"description":$DESC,"namespace":"default","monitoring_enabled":["logs"],"inactivity_timeout":$TIMEOUT,"has_fleet_server":$FLEETSERVER}'
+        )
     # Create Fleet Policy
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/agent_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+    if ! fleet_api "agent_policies" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+        return 1
+    fi
 
 }
-
-elastic_fleet_policy_update() {
-
-    POLICYID=$1
-    JSON_STRING=$2
-
-    curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/agent_policies/$POLICYID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
-}
-

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-defend

@@ -8,6 +8,7 @@
 
 . /usr/sbin/so-elastic-fleet-common
 
+ERROR=false
 # Manage Elastic Defend Integration for Initial Endpoints Policy
 for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/elastic-defend/*.json
 do
@@ -15,9 +16,20 @@ do
   elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
   if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Upgrading integration policy\n"
-      elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"
+      if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
+        echo -e "\nFailed to upgrade integration policy for ${INTEGRATION##*/}"
+        ERROR=true
+        continue
+      fi
   else
     printf "\n\nIntegration does not exist - Creating integration\n"
-    elastic_fleet_integration_create "@$INTEGRATION"
+    if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+        ERROR=true
+        continue
+    fi
   fi
 done
+if [[ "$ERROR" == "true" ]]; then
+    exit 1
+fi

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server

@@ -25,5 +25,9 @@ for POLICYNAME in $POLICY; do
     .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 
     # Now update the integration policy using the modified JSON
-    elastic_fleet_integration_update "$INTEGRATION_ID" "$UPDATED_INTEGRATION_POLICY"
+    if ! elastic_fleet_integration_update "$INTEGRATION_ID" "$UPDATED_INTEGRATION_POLICY"; then
+        # exit 1 on failure to update fleet integration policies, let salt handle retries
+        echo "Failed to update $POLICYNAME.."
+        exit 1
+    fi
 done

salt/elasticfleet/tools/sbin/so-elastic-fleet-integration-policy-load

@@ -13,11 +13,10 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
   /usr/sbin/so-elastic-fleet-package-upgrade
 
   # Second, update Fleet Server policies
-  /sbin/so-elastic-fleet-integration-policy-elastic-fleet-server
+  /usr/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server
 
   # Third, configure Elastic Defend Integration seperately
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-defend
-
   # Initial Endpoints
   for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/endpoints-initial/*.json
   do
@@ -25,10 +24,18 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
     elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
     if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Updating integration\n"
-      elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     else
       printf "\n\nIntegration does not exist - Creating integration\n"
-      elastic_fleet_integration_create "@$INTEGRATION"
+      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     fi
   done
 
@@ -39,10 +46,18 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
     elastic_fleet_integration_check "so-grid-nodes_general" "$INTEGRATION"
     if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Updating integration\n"
-      elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     else
       printf "\n\nIntegration does not exist - Creating integration\n"
-      elastic_fleet_integration_create "@$INTEGRATION"
+      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     fi
   done
   if [[ "$RETURN_CODE" != "1" ]]; then
@@ -56,11 +71,19 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
     elastic_fleet_integration_check "so-grid-nodes_heavy" "$INTEGRATION"
     if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Updating integration\n"
-      elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+        RETURN_CODE=1
+        continue
+      fi
     else
       printf "\n\nIntegration does not exist - Creating integration\n"
       if [ "$NAME" != "elasticsearch-logs" ]; then
-        elastic_fleet_integration_create "@$INTEGRATION"
+        if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+          echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+          RETURN_CODE=1
+          continue
+        fi
       fi
     fi
   done
@@ -77,11 +100,19 @@ if [ ! -f /opt/so/state/eaintegrations.txt ]; then
       elastic_fleet_integration_check "$FLEET_POLICY" "$INTEGRATION"
       if [ -n "$INTEGRATION_ID" ]; then
         printf "\n\nIntegration $NAME exists - Updating integration\n"
-        elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"
+        if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+          echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
+          RETURN_CODE=1
+          continue
+        fi
       else
         printf "\n\nIntegration does not exist - Creating integration\n"
         if [ "$NAME" != "elasticsearch-logs" ]; then
-          elastic_fleet_integration_create "@$INTEGRATION"
+          if ! elastic_fleet_integration_create "@$INTEGRATION"; then
+            echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
+            RETURN_CODE=1
+            continue
+          fi
         fi
       fi
     fi

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-integration-upgrade

@@ -24,12 +24,18 @@ fi
 
 default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.last %} {% endif %}{% endfor %})
 
+ERROR=false
 for AGENT_POLICY in $agent_policies; do
-    integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY")
+    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+        # this script upgrades default integration packages, exit 1 and let salt handle retrying
+        exit 1
+    fi
     for INTEGRATION in $integrations; do
         if ! [[ "$INTEGRATION" == "elastic-defend-endpoints" ]] && ! [[ "$INTEGRATION" == "fleet_server-"* ]]; then
             # Get package name so we know what package to look for when checking the current and latest available version
-            PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION")
+            if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+                exit 1
+            fi
             {%- if not AUTO_UPGRADE_INTEGRATIONS %}
             if [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
             {%- endif %}
@@ -48,7 +54,9 @@ for AGENT_POLICY in $agent_policies; do
                 fi
 
                 # Get integration ID
-                INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION")
+                if ! INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION"); then
+                    exit 1
+                fi
 
                 if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
                     # Dry run of the upgrade
@@ -56,20 +64,23 @@ for AGENT_POLICY in $agent_policies; do
                     echo "Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."
                     echo "Upgrading $INTEGRATION..."
                     echo "Starting dry run..."
-                    DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID")
+                    if ! DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID"); then
+                        exit 1
+                    fi
                     DRYRUN_ERRORS=$(echo "$DRYRUN_OUTPUT" | jq .[].hasErrors)
 
                     # If no errors with dry run, proceed with actual upgrade
                     if [[ "$DRYRUN_ERRORS" == "false" ]]; then
                         echo "No errors detected. Proceeding with upgrade..."
-                        elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"
-                        if [ $? -ne 0 ]; then
+                        if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
                             echo "Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."
-                            exit 1
+                            ERROR=true
+                            continue
                         fi
                     else
                         echo "Errors detected during dry run for $PACKAGE_NAME policy upgrade..."
-                        exit 1
+                        ERROR=true
+                        continue
                     fi
                 fi
             {%- if not AUTO_UPGRADE_INTEGRATIONS %}
@@ -78,4 +89,7 @@ for AGENT_POLICY in $agent_policies; do
         fi
     done
 done
+if [[ "$ERROR" == "true" ]]; then
+    exit 1
+fi
 echo

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-optional-integrations-load

@@ -62,9 +62,17 @@ default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.l
 in_use_integrations=()
 
 for AGENT_POLICY in $agent_policies; do
-    integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY")
+
+    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+        # skip the agent policy if we can't get required info, let salt retry. Integrations loaded by this script are non-default integrations.
+        echo "Skipping $AGENT_POLICY.. "
+        continue
+    fi
     for INTEGRATION in $integrations; do
-        PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION")
+        if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+            echo  "Not adding $INTEGRATION, couldn't get package name"
+            continue
+        fi
         # non-default integrations that are in-use in any policy
         if ! [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
             in_use_integrations+=("$PACKAGE_NAME")
@@ -160,7 +168,11 @@ if [[ -f $STATE_FILE_SUCCESS  ]]; then
 
             for file in "${pkg_filename}_"*.json; do
                 [ -e "$file" ] || continue
-                elastic_fleet_bulk_package_install $file >> $BULK_INSTALL_OUTPUT
+                if ! elastic_fleet_bulk_package_install $file >> $BULK_INSTALL_OUTPUT; then
+                    # integrations loaded my this script are non-essential and shouldn't cause exit, skip them for now next highstate run can retry
+                    echo "Failed to complete a chunk of bulk package installs -- $file "
+                    continue
+                fi
             done
             # cleanup any temp files for chunked package install
             rm -f ${pkg_filename}_*.json $BULK_INSTALL_PACKAGE_LIST
@@ -168,8 +180,9 @@ if [[ -f $STATE_FILE_SUCCESS  ]]; then
             echo "Elastic integrations don't appear to need installation/updating..."
         fi
         # Write out file for generating index/component/ilm templates
-        latest_installed_package_list=$(elastic_fleet_installed_packages)
-        echo $latest_installed_package_list | jq '[.items[] | {name: .name, es_index_patterns: .dataStreams}]' > $PACKAGE_COMPONENTS
+        if latest_installed_package_list=$(elastic_fleet_installed_packages); then
+            echo $latest_installed_package_list | jq '[.items[] | {name: .name, es_index_patterns: .dataStreams}]' > $PACKAGE_COMPONENTS
+        fi
         if retry 3 1 "so-elasticsearch-query / --fail --output /dev/null"; then
             # Refresh installed component template list
             latest_component_templates_list=$(so-elasticsearch-query _component_template | jq '.component_templates[] | .name' | jq -s '.')

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-outputs-update

@@ -15,8 +15,21 @@ if ! is_manager_node; then
 fi
 
 function update_logstash_outputs() {
-	# Generate updated JSON payload
-    JSON_STRING=$(jq -n --arg UPDATEDLIST $NEW_LIST_JSON '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":""}')
+    if logstash_policy=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_logstash" --retry 3 --retry-delay 10 --fail 2>/dev/null); then
+        SSL_CONFIG=$(echo "$logstash_policy" | jq -r '.item.ssl')
+        if SECRETS=$(echo "$logstash_policy" | jq -er '.item.secrets' 2>/dev/null); then
+            JSON_STRING=$(jq -n \
+                --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                --argjson SECRETS "$SECRETS" \
+                --argjson SSL_CONFIG "$SSL_CONFIG" \
+                '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":"","ssl": $SSL_CONFIG,"secrets": $SECRETS}')
+        else
+            JSON_STRING=$(jq -n \
+                --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                --argjson SSL_CONFIG "$SSL_CONFIG" \
+                '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":"","ssl": $SSL_CONFIG}')
+        fi
+    fi
 
     # Update Logstash Outputs
     curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_logstash" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" | jq

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-load

@@ -10,8 +10,16 @@
 
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
 echo "Setting up {{ PACKAGE }} package..."
-VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}")
-elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"
+if VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}"); then
+    if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; then
+        # packages loaded by this script should never fail to install and REQUIRED before an installation of SO can be considered successful
+        echo -e "\nERROR: Failed to install default integration package -- $PACKAGE $VERSION"
+        exit 1
+    fi
+else
+    echo -e "\nERROR: Failed to get version information for integration $PACKAGE"
+    exit 1
+fi
 echo
 {%- endfor %}
 echo

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade

@@ -10,8 +10,15 @@
 
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
 echo "Upgrading {{ PACKAGE }} package..."
-VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}")
-elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"
+if VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+    if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; then
+        # exit 1 on failure to upgrade a default package, allow salt to handle retries
+        echo -e "\nERROR: Failed to upgrade $PACKAGE to version: $VERSION"
+        exit 1
+    fi
+else
+    echo -e "\nERROR: Failed to get version information for integration $PACKAGE"
+fi
 echo
 {%- endfor %}
 echo

salt/elasticfleet/tools/sbin_jinja/so-elastic-fleet-setup

@@ -23,18 +23,17 @@ if [[ "$RETURN_CODE" != "0" ]]; then
     exit 1
 fi
 
-ALIASES=".fleet-servers .fleet-policies-leader .fleet-policies .fleet-agents .fleet-artifacts .fleet-enrollment-api-keys .kibana_ingest"
-for ALIAS in ${ALIASES}
-do
+ALIASES=(.fleet-servers .fleet-policies-leader .fleet-policies .fleet-agents .fleet-artifacts .fleet-enrollment-api-keys .kibana_ingest)
+for ALIAS in "${ALIASES[@]}"; do
     # Get all concrete indices from alias
-    INDXS=$(curl -K /opt/so/conf/kibana/curl.config -s -k -L -H "Content-Type: application/json" "https://localhost:9200/_resolve/index/${ALIAS}"  | jq -r '.aliases[].indices[]')
-
-    # Delete all resolved indices
-    for INDX in ${INDXS}
-    do
+    if INDXS_RAW=$(curl -sK /opt/so/conf/kibana/curl.config -s -k -L -H "Content-Type: application/json" "https://localhost:9200/_resolve/index/${ALIAS}" --fail 2>/dev/null); then
+        INDXS=$(echo "$INDXS_RAW" | jq -r '.aliases[].indices[]')
+        # Delete all resolved indices
+        for INDX in ${INDXS}; do
             status "Deleting $INDX"
             curl -K /opt/so/conf/kibana/curl.config -s -k -L -H "Content-Type: application/json" "https://localhost:9200/${INDX}" -XDELETE
-    done
+        done
+    fi
 done
 
 # Restarting Kibana...
@@ -51,22 +50,61 @@ if [[ "$RETURN_CODE" != "0" ]]; then
 fi
 
 printf "\n### Create ES Token ###\n"
-ESTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/service_tokens" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' |  jq -r .value)
+if ESTOKEN_RAW=$(fleet_api "service_tokens" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    ESTOKEN=$(echo "$ESTOKEN_RAW" | jq -r .value)
+else
+    echo -e "\nFailed to create ES token..."
+    exit 1
+fi
 
 ### Create Outputs, Fleet Policy and Fleet URLs ###
 # Create the Manager Elasticsearch Output first and set it as the default output
 printf "\nAdd Manager Elasticsearch Output...\n"
-ESCACRT=$(openssl x509 -in  $INTCA)
-JSON_STRING=$( jq -n \
-                  --arg ESCACRT "$ESCACRT" \
-                  '{"name":"so-manager_elasticsearch","id":"so-manager_elasticsearch","type":"elasticsearch","hosts":["https://{{ GLOBALS.manager_ip }}:9200","https://{{ GLOBALS.manager }}:9200"],"is_default":true,"is_default_monitoring":true,"config_yaml":"","ssl":{"certificate_authorities": [$ESCACRT]}}' )
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/outputs" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+ESCACRT=$(openssl x509 -in "$INTCA" -outform DER | sha256sum | cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+JSON_STRING=$(jq -n \
+    --arg ESCACRT "$ESCACRT" \
+        '{"name":"so-manager_elasticsearch","id":"so-manager_elasticsearch","type":"elasticsearch","hosts":["https://{{ GLOBALS.manager_ip }}:9200","https://{{ GLOBALS.manager }}:9200"],"is_default":false,"is_default_monitoring":false,"config_yaml":"","ca_trusted_fingerprint": $ESCACRT}')
+
+if ! fleet_api "outputs" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+    echo -e "\nFailed to create so-elasticsearch_manager policy..."
+    exit 1
+fi
 printf "\n\n"
 
+# so-manager_elasticsearch should exist and be disabled. Now update it before checking its the only default policy
+MANAGER_OUTPUT_ENABLED=$(echo "$JSON_STRING" | jq 'del(.id) | .is_default = true | .is_default_monitoring = true')
+if ! curl -sK /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_elasticsearch" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$MANAGER_OUTPUT_ENABLED"; then
+    echo -e "\n failed to update so-manager_elasticsearch"
+    exit 1
+fi
+
+# At this point there should only be two policies. fleet-default-output & so-manager_elasticsearch
+status "Verifying so-manager_elasticsearch policy is configured as the current default"
+
+# Grab the fleet-default-output policy instead of so-manager_elasticsearch, because a weird state can exist where both fleet-default-output & so-elasticsearch_manager can be set as the active default output for logs / metrics. Resulting in logs not ingesting on import/eval nodes
+if DEFAULTPOLICY=$(fleet_api "outputs/fleet-default-output"); then
+    fleet_default=$(echo "$DEFAULTPOLICY" | jq -er '.item.is_default')
+    fleet_default_monitoring=$(echo "$DEFAULTPOLICY" | jq -er '.item.is_default_monitoring')
+#   Check that fleet-default-output isn't configured as a default for anything ( both variables return false )
+    if [[ $fleet_default == "false" ]] && [[ $fleet_default_monitoring == "false" ]]; then
+        echo -e "\nso-manager_elasticsearch is configured as the current default policy..."
+    else
+        echo -e "\nVerification of so-manager_elasticsearch policy failed... The default 'fleet-default-output' output is still active..."
+        exit 1
+    fi
+else
+    # fleet-output-policy is created automatically by fleet when started. Should always exist on any installation type
+    echo -e "\nDefault fleet-default-output policy doesn't exist...\n"
+    exit 1
+fi
+
 # Create the Manager Fleet Server Host Agent Policy
 # This has to be done while the Elasticsearch Output is set to the default Output
 printf "Create Manager Fleet Server Policy...\n"
-elastic_fleet_policy_create "FleetServer_{{ GLOBALS.hostname }}" "Fleet Server - {{ GLOBALS.hostname }}" "false" "120"
+if ! elastic_fleet_policy_create "FleetServer_{{ GLOBALS.hostname }}" "Fleet Server - {{ GLOBALS.hostname }}" "false" "120"; then
+    echo -e "\n Failed to create Manager fleet server policy..."
+    exit 1
+fi
 
 # Modify the default integration policy to update the policy_id with the correct naming
 UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "FleetServer_{{ GLOBALS.hostname }}" --arg name "fleet_server-{{ GLOBALS.hostname }}" '
@@ -74,7 +112,10 @@ UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "FleetServer_{{ GLOBALS.hostname
 .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 
 # Add the Fleet Server Integration to the new Fleet Policy
-elastic_fleet_integration_create "$UPDATED_INTEGRATION_POLICY"
+if ! elastic_fleet_integration_create "$UPDATED_INTEGRATION_POLICY"; then
+    echo -e "\nFailed to create Fleet server integration for Manager.."
+    exit 1
+fi
 
 # Now we can create the Logstash Output and set it to to be the default Output
 printf "\n\nCreate Logstash Output Config if node is not an Import or Eval install\n"
@@ -86,9 +127,12 @@ JSON_STRING=$( jq -n \
                   --arg LOGSTASHCRT "$LOGSTASHCRT" \
                   --arg LOGSTASHKEY "$LOGSTASHKEY" \
                   --arg LOGSTASHCA "$LOGSTASHCA" \
-                  '{"name":"grid-logstash","is_default":true,"is_default_monitoring":true,"id":"so-manager_logstash","type":"logstash","hosts":["{{ GLOBALS.manager_ip }}:5055", "{{ GLOBALS.manager }}:5055"],"config_yaml":"","ssl":{"certificate": $LOGSTASHCRT,"key": $LOGSTASHKEY,"certificate_authorities":[ $LOGSTASHCA ]},"proxy_id":null}'
+                  '{"name":"grid-logstash","is_default":true,"is_default_monitoring":true,"id":"so-manager_logstash","type":"logstash","hosts":["{{ GLOBALS.manager_ip }}:5055", "{{ GLOBALS.manager }}:5055"],"config_yaml":"","ssl":{"certificate": $LOGSTASHCRT,"certificate_authorities":[ $LOGSTASHCA ]},"secrets":{"ssl":{"key": $LOGSTASHKEY }},"proxy_id":null}'
                   )
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/outputs" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+if ! fleet_api "outputs" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+    echo -e "\nFailed to create logstash fleet output"
+    exit 1
+fi
 printf "\n\n"
 {%- endif %}
 
@@ -106,7 +150,10 @@ else
 fi
 
 ## This array replaces whatever URLs are currently configured
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/fleet_server_hosts" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d  "$JSON_STRING"
+if ! fleet_api "fleet_server_hosts" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d  "$JSON_STRING"; then
+    echo -e "\nFailed to add manager fleet URL"
+    exit 1
+fi
 printf "\n\n"
 
 ### Create Policies & Associated Integration Configuration ###
@@ -117,13 +164,22 @@ printf "\n\n"
 /usr/sbin/so-elasticsearch-templates-load
 
 # Initial Endpoints Policy
-elastic_fleet_policy_create "endpoints-initial" "Initial Endpoint Policy" "false" "1209600"
+if ! elastic_fleet_policy_create "endpoints-initial" "Initial Endpoint Policy" "false" "1209600"; then
+    echo -e "\nFailed to create endpoints-initial policy..."
+    exit 1
+fi
 
 # Grid Nodes - General Policy
-elastic_fleet_policy_create "so-grid-nodes_general" "SO Grid Nodes - General Purpose" "false" "1209600"
+if ! elastic_fleet_policy_create "so-grid-nodes_general" "SO Grid Nodes - General Purpose" "false" "1209600"; then
+    echo -e "\nFailed to create so-grid-nodes_general policy..."
+    exit 1
+fi
 
 # Grid Nodes - Heavy Node Policy
-elastic_fleet_policy_create "so-grid-nodes_heavy" "SO Grid Nodes - Heavy Node" "false" "1209600"
+if ! elastic_fleet_policy_create "so-grid-nodes_heavy" "SO Grid Nodes - Heavy Node" "false" "1209600"; then
+    echo -e "\nFailed to create so-grid-nodes_heavy policy..."
+    exit 1
+fi
 
 # Load Integrations for default policies
 so-elastic-fleet-integration-policy-load
@@ -135,14 +191,34 @@ JSON_STRING=$( jq -n \
                 '{"name":$NAME,"host":$URL,"is_default":true}'
                 )
 
-curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/agent_download_sources" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+if ! fleet_api "agent_download_sources" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+    echo -e "\nFailed to update Elastic Agent artifact URL"
+    exit 1
+fi
 
 ### Finalization ###
 
 # Query for Enrollment Tokens for default policies
-ENDPOINTSENROLLMENTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
-GRIDNODESENROLLMENTOKENGENERAL=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_general")) | .api_key')
-GRIDNODESENROLLMENTOKENHEAVY=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
+if ENDPOINTSENROLLMENTOKEN_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    ENDPOINTSENROLLMENTOKEN=$(echo "$ENDPOINTSENROLLMENTOKEN_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+else
+    echo -e "\nFailed to query for Endpoints enrollment token"
+    exit 1
+fi
+
+if GRIDNODESENROLLMENTOKENGENERAL_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    GRIDNODESENROLLMENTOKENGENERAL=$(echo "$GRIDNODESENROLLMENTOKENGENERAL_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_general")) | .api_key')
+else
+    echo -e "\nFailed to query for Grid nodes - General enrollment token"
+    exit 1
+fi
+
+if GRIDNODESENROLLMENTOKENHEAVY_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+    GRIDNODESENROLLMENTOKENHEAVY=$(echo "$GRIDNODESENROLLMENTOKENHEAVY_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("so-grid-nodes_heavy")) | .api_key')
+else
+    echo -e "\nFailed to query for Grid nodes - Heavy enrollment token"
+    exit 1
+fi
 
 # Store needed data in minion pillar
 pillar_file=/opt/so/saltstack/local/pillar/minions/{{ GLOBALS.minion_id }}.sls

salt/elasticsearch/defaults.yaml

@@ -1,6 +1,6 @@
 elasticsearch:
   enabled: false
-  version: 8.18.6
+  version: 8.18.8
   index_clean: true
   config:
     action:
@@ -1991,6 +1991,70 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
+    so-logs-elasticsearch_x_server:
+      index_sorting: false
+      index_template:
+        composed_of:
+        - logs-elasticsearch.server@package
+        - logs-elasticsearch.server@custom
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates:
+        - logs-elasticsearch.server@custom
+        index_patterns:
+        - logs-elasticsearch.server-*
+        priority: 501
+        template:
+          mappings:
+            _meta:
+              managed: true
+              managed_by: security_onion
+              package:
+                name: elastic_agent
+          settings:
+            index:
+              lifecycle:
+                name: so-logs-elasticsearch.server-logs
+              mapping:
+                total_fields:
+                  limit: 5000
+              number_of_replicas: 0
+              sort:
+                field: '@timestamp'
+                order: desc
+      policy:
+        _meta:
+          managed: true
+          managed_by: security_onion
+          package:
+            name: elastic_agent
+        phases:
+          cold:
+            actions:
+              set_priority:
+                priority: 0
+            min_age: 60d
+          delete:
+            actions:
+              delete: {}
+            min_age: 365d
+          hot:
+            actions:
+              rollover:
+                max_age: 30d
+                max_primary_shard_size: 50gb
+              set_priority:
+                priority: 100
+            min_age: 0ms
+          warm:
+            actions:
+              set_priority:
+                priority: 50
+            min_age: 30d
     so-logs-endpoint_x_actions:
       index_sorting: false
       index_template:

salt/elasticsearch/files/ingest/global@custom

@@ -23,6 +23,7 @@
     { "set":        { "if": "ctx.event?.module == 'fim'", "override": true, "field": "event.module", "value": "file_integrity" } },
     { "rename":       { "if": "ctx.winlog?.provider_name == 'Microsoft-Windows-Windows Defender'", "ignore_missing": true, "field": "winlog.event_data.Threat Name", "target_field": "winlog.event_data.threat_name" } },
     { "set":        { "if": "ctx?.metadata?.kafka != null" , "field": "kafka.id", "value": "{{metadata.kafka.partition}}{{metadata.kafka.offset}}{{metadata.kafka.timestamp}}", "ignore_failure": true } },
+    { "set":        { "if": "ctx.event?.dataset != null && ctx.event?.dataset == 'elasticsearch.server'", "field": "event.module", "value":"elasticsearch" }},
     {"append":      {"field":"related.ip","value":["{{source.ip}}","{{destination.ip}}"],"allow_duplicates":false,"if":"ctx?.event?.dataset == 'endpoint.events.network' && ctx?.source?.ip != null","ignore_failure":true}},
     {"foreach":     {"field":"host.ip","processor":{"append":{"field":"related.ip","value":"{{_ingest._value}}","allow_duplicates":false}},"if":"ctx?.event?.module == 'endpoint' && ctx?.host?.ip != null","ignore_missing":true, "description":"Extract IPs from Elastic Agent events (host.ip) and adds them to related.ip"}},
     { "remove":     { "field": [ "message2", "type", "fields", "category", "module", "dataset", "event.dataset_temp", "dataset_tag_temp", "module_temp", "datastream_dataset_temp" ], "ignore_missing": true, "ignore_failure": true } }

salt/elasticsearch/files/log4j2.properties

@@ -20,8 +20,28 @@ appender.rolling.strategy.type = DefaultRolloverStrategy
 appender.rolling.strategy.action.type = Delete
 appender.rolling.strategy.action.basepath = /var/log/elasticsearch
 appender.rolling.strategy.action.condition.type = IfFileName
-appender.rolling.strategy.action.condition.glob = *.gz
+appender.rolling.strategy.action.condition.glob = *.log.gz
 appender.rolling.strategy.action.condition.nested_condition.type = IfLastModified
 appender.rolling.strategy.action.condition.nested_condition.age = 7D
+
+appender.rolling_json.type = RollingFile
+appender.rolling_json.name = rolling_json
+appender.rolling_json.fileName = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}.json
+appender.rolling_json.layout.type = ECSJsonLayout
+appender.rolling_json.layout.dataset = elasticsearch.server
+appender.rolling_json.filePattern = ${sys:es.logs.base_path}${sys:file.separator}${sys:es.logs.cluster_name}-%d{yyyy-MM-dd}.json.gz
+appender.rolling_json.policies.type = Policies
+appender.rolling_json.policies.time.type = TimeBasedTriggeringPolicy
+appender.rolling_json.policies.time.interval = 1
+appender.rolling_json.policies.time.modulate = true
+appender.rolling_json.strategy.type = DefaultRolloverStrategy
+appender.rolling_json.strategy.action.type = Delete
+appender.rolling_json.strategy.action.basepath = /var/log/elasticsearch
+appender.rolling_json.strategy.action.condition.type = IfFileName
+appender.rolling_json.strategy.action.condition.glob = *.json.gz
+appender.rolling_json.strategy.action.condition.nested_condition.type = IfLastModified
+appender.rolling_json.strategy.action.condition.nested_condition.age = 1D
+
 rootLogger.level = info
 rootLogger.appenderRef.rolling.ref = rolling
+rootLogger.appenderRef.rolling_json.ref = rolling_json

salt/elasticsearch/soc_elasticsearch.yaml

@@ -392,6 +392,7 @@ elasticsearch:
     so-logs-elastic_agent_x_metricbeat: *indexSettings
     so-logs-elastic_agent_x_osquerybeat: *indexSettings
     so-logs-elastic_agent_x_packetbeat: *indexSettings
+    so-logs-elasticsearch_x_server: *indexSettings
     so-metrics-endpoint_x_metadata: *indexSettings
     so-metrics-endpoint_x_metrics: *indexSettings
     so-metrics-endpoint_x_policy: *indexSettings

salt/hypervisor/map.jinja

@@ -13,6 +13,7 @@
 
 {# Import defaults.yaml for model hardware capabilities #}
 {% import_yaml 'hypervisor/defaults.yaml' as DEFAULTS %}
+{% set HYPERVISORMERGED = salt['pillar.get']('hypervisor', default=DEFAULTS.hypervisor, merge=True) %}
 
 {# Get hypervisor nodes from pillar #}
 {% set NODES = salt['pillar.get']('hypervisor:nodes', {}) %}
@@ -30,9 +31,10 @@
     {% set model = '' %}
     {% if grains %}
       {% set minion_id = grains.keys() | first %}
-      {% set model = grains[minion_id].get('sosmodel', '') %}
+      {% set model = grains[minion_id].get('sosmodel', grains[minion_id].get('byodmodel', '')) %}
     {% endif %}
-    {% set model_config = DEFAULTS.hypervisor.model.get(model, {}) %}
+
+    {% set model_config = HYPERVISORMERGED.model.get(model, {}) %}
     
     {# Get VM list from VMs file #}
     {% set vms = {} %}
@@ -56,10 +58,26 @@
       {% set role = vm.get('role', '') %}
       {% do salt.log.debug('salt/hypervisor/map.jinja: Processing VM - hostname: ' ~ hostname ~ ', role: ' ~ role) %}
       
-      {# Load VM configuration from config file #}
+      {# Try to load VM configuration from config file first, then .error file if config doesn't exist #}
       {% set vm_file = 'hypervisor/hosts/' ~ hypervisor ~ '/' ~ hostname ~ '_' ~ role %}
+      {% set vm_error_file = vm_file ~ '.error' %}
       {% do salt.log.debug('salt/hypervisor/map.jinja: VM config file: ' ~ vm_file) %}
-      {% import_json vm_file as vm_state %}
+      
+      {# Check if base config file exists #}
+      {% set config_exists = salt['file.file_exists']('/opt/so/saltstack/local/salt/' ~ vm_file) %}
+      {% set error_exists = salt['file.file_exists']('/opt/so/saltstack/local/salt/' ~ vm_error_file) %}
+      
+      {% set vm_state = none %}
+      {% if config_exists %}
+        {% import_json vm_file as vm_state %}
+        {% do salt.log.debug('salt/hypervisor/map.jinja: Loaded VM config from base file') %}
+      {% elif error_exists %}
+        {% import_json vm_error_file as vm_state %}
+        {% do salt.log.debug('salt/hypervisor/map.jinja: Loaded VM config from .error file') %}
+      {% else %}
+        {% do salt.log.warning('salt/hypervisor/map.jinja: No config or error file found for VM ' ~ hostname ~ '_' ~ role) %}
+      {% endif %}
+      
       {% if vm_state %}
         {% do salt.log.debug('salt/hypervisor/map.jinja: VM config content: ' ~ vm_state | tojson) %}
         {% set vm_data = {'config': vm_state.config} %}
@@ -83,7 +101,7 @@
         {% endif %}
         {% do vms.update({hostname ~ '_' ~ role: vm_data}) %}
       {% else %}
-        {% do salt.log.debug('salt/hypervisor/map.jinja: Config file empty: ' ~ vm_file) %}
+        {% do salt.log.debug('salt/hypervisor/map.jinja: Skipping VM ' ~ hostname ~ '_' ~ role ~ ' - no config available') %}
       {% endif %}
     {% endfor %}
     

salt/hypervisor/tools/sbin/so-nvme-raid1.sh

@@ -30,7 +30,9 @@
 #
 # WARNING: This script will DESTROY all data on the target drives!
 #
-# USAGE: sudo ./so-nvme-raid1.sh
+# USAGE: 
+#   sudo ./so-nvme-raid1.sh              # Normal operation
+#   sudo ./so-nvme-raid1.sh --force-cleanup  # Force cleanup of existing RAID
 #
 #################################################################
 
@@ -41,6 +43,19 @@ set -e
 RAID_ARRAY_NAME="md0"
 RAID_DEVICE="/dev/${RAID_ARRAY_NAME}"
 MOUNT_POINT="/nsm"
+FORCE_CLEANUP=false
+
+# Parse command line arguments
+for arg in "$@"; do
+    case $arg in
+        --force-cleanup)
+            FORCE_CLEANUP=true
+            shift
+            ;;
+        *)
+            ;;
+    esac
+done
 
 # Function to log messages
 log() {
@@ -55,6 +70,91 @@ check_root() {
     fi
 }
 
+# Function to force cleanup all RAID components
+force_cleanup_raid() {
+    log "=== FORCE CLEANUP MODE ==="
+    log "This will destroy all RAID configurations and data on target drives!"
+    
+    # Stop all MD arrays
+    log "Stopping all MD arrays"
+    mdadm --stop --scan 2>/dev/null || true
+    
+    # Wait for arrays to stop
+    sleep 2
+    
+    # Remove any running md devices
+    for md in /dev/md*; do
+        if [ -b "$md" ]; then
+            log "Stopping $md"
+            mdadm --stop "$md" 2>/dev/null || true
+        fi
+    done
+    
+    # Force cleanup both NVMe drives
+    for device in "/dev/nvme0n1" "/dev/nvme1n1"; do
+        log "Force cleaning $device"
+        
+        # Kill any processes using the device
+        fuser -k "${device}"* 2>/dev/null || true
+        
+        # Unmount any mounted partitions
+        for part in "${device}"*; do
+            if [ -b "$part" ]; then
+                umount -f "$part" 2>/dev/null || true
+            fi
+        done
+        
+        # Force zero RAID superblocks on partitions
+        for part in "${device}"p*; do
+            if [ -b "$part" ]; then
+                log "Zeroing RAID superblock on $part"
+                mdadm --zero-superblock --force "$part" 2>/dev/null || true
+            fi
+        done
+        
+        # Zero superblock on the device itself
+        log "Zeroing RAID superblock on $device"
+        mdadm --zero-superblock --force "$device" 2>/dev/null || true
+        
+        # Remove LVM physical volumes
+        pvremove -ff -y "$device" 2>/dev/null || true
+        
+        # Wipe all filesystem and partition signatures
+        log "Wiping all signatures from $device"
+        wipefs -af "$device" 2>/dev/null || true
+        
+        # Overwrite the beginning of the drive (partition table area)
+        log "Clearing partition table on $device"
+        dd if=/dev/zero of="$device" bs=1M count=10 2>/dev/null || true
+        
+        # Clear the end of the drive (backup partition table area)
+        local device_size=$(blockdev --getsz "$device" 2>/dev/null || echo "0")
+        if [ "$device_size" -gt 0 ]; then
+            dd if=/dev/zero of="$device" bs=512 seek=$(( device_size - 2048 )) count=2048 2>/dev/null || true
+        fi
+        
+        # Force kernel to re-read partition table
+        blockdev --rereadpt "$device" 2>/dev/null || true
+        partprobe -s "$device" 2>/dev/null || true
+    done
+    
+    # Clear mdadm configuration
+    log "Clearing mdadm configuration"
+    echo "DEVICE partitions" > /etc/mdadm.conf
+    
+    # Remove any fstab entries for the RAID device or mount point
+    log "Cleaning fstab entries"
+    sed -i "\|${RAID_DEVICE}|d" /etc/fstab
+    sed -i "\|${MOUNT_POINT}|d" /etc/fstab
+    
+    # Wait for system to settle
+    udevadm settle
+    sleep 5
+    
+    log "Force cleanup complete!"
+    log "Proceeding with RAID setup..."
+}
+
 # Function to find MD arrays using specific devices
 find_md_arrays_using_devices() {
     local target_devices=("$@")
@@ -205,10 +305,15 @@ check_existing_raid() {
             fi
             
             log "Error: $device appears to be part of an existing RAID array"
-            log "To reuse this device, you must first:"
-            log "1. Unmount any filesystems"
-            log "2. Stop the RAID array: mdadm --stop $array_name"
-            log "3. Zero the superblock: mdadm --zero-superblock ${device}p1"
+            log "Old RAID metadata detected but array is not running."
+            log ""
+            log "To fix this, run the script with --force-cleanup:"
+            log "  sudo $0 --force-cleanup"
+            log ""
+            log "Or manually clean up with:"
+            log "1. Stop any arrays: mdadm --stop --scan"
+            log "2. Zero superblocks: mdadm --zero-superblock --force ${device}p1"
+            log "3. Wipe signatures: wipefs -af $device"
             exit 1
         fi
     done
@@ -238,7 +343,7 @@ ensure_devices_free() {
     done
     
     # Clear MD superblock
-    mdadm --zero-superblock "${device}"* 2>/dev/null || true
+    mdadm --zero-superblock --force "${device}"* 2>/dev/null || true
     
     # Remove LVM PV if exists
     pvremove -ff -y "$device" 2>/dev/null || true
@@ -263,6 +368,11 @@ main() {
     # Check if running as root
     check_root
     
+    # If force cleanup flag is set, do aggressive cleanup first
+    if [ "$FORCE_CLEANUP" = true ]; then
+        force_cleanup_raid
+    fi
+    
     # Check for existing RAID setup
     check_existing_raid
     

salt/hypervisor/tools/sbin_jinja/so-kvm-create-volume

@@ -0,0 +1,586 @@
+#!/usr/bin/python3
+
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+#
+# Note: Per the Elastic License 2.0, the second limitation states:
+#
+#   "You may not move, change, disable, or circumvent the license key functionality
+#    in the software, and you may not remove or obscure any functionality in the
+#    software that is protected by the license key."
+
+{% if 'vrt' in salt['pillar.get']('features', []) %}
+
+"""
+Script for creating and attaching virtual volumes to KVM virtual machines for NSM storage.
+This script provides functionality to create pre-allocated raw disk images and attach them
+to VMs as virtio-blk devices for high-performance network security monitoring data storage.
+
+The script handles the complete volume lifecycle:
+1. Volume Creation: Creates pre-allocated raw disk images using qemu-img
+2. Volume Attachment: Attaches volumes to VMs as virtio-blk devices
+3. VM Management: Stops/starts VMs as needed during the process
+
+This script is designed to work with Security Onion's virtualization infrastructure and is typically
+used during VM provisioning to add dedicated NSM storage volumes.
+
+**Usage:**
+    so-kvm-create-volume -v <vm_name> -s <size_gb> [-S]
+
+**Options:**
+    -v, --vm          Name of the virtual machine to attach the volume to (required).
+    -s, --size        Size of the volume in GB (required, must be a positive integer).
+    -S, --start       Start the VM after volume creation and attachment (optional).
+
+**Examples:**
+
+1. **Create and Attach 500GB Volume:**
+
+    ```bash
+    so-kvm-create-volume -v vm1_sensor -s 500
+    ```
+
+    This command creates and attaches a volume with the following settings:
+    - VM Name: `vm1_sensor`
+    - Volume Size: `500` GB
+    - Volume Path: `/nsm/libvirt/volumes/vm1_sensor-nsm.img`
+    - Device: `/dev/vdb` (virtio-blk)
+    - VM remains stopped after attachment
+
+2. **Create Volume and Start VM:**
+
+    ```bash
+    so-kvm-create-volume -v vm2_sensor -s 1000 -S
+    ```
+
+    This command creates a volume and starts the VM:
+    - VM Name: `vm2_sensor`
+    - Volume Size: `1000` GB (1 TB)
+    - VM is started after volume attachment due to the `-S` flag
+
+3. **Create Large Volume for Heavy Traffic:**
+
+    ```bash
+    so-kvm-create-volume -v vm3_sensor -s 2000 -S
+    ```
+
+    This command creates a large volume for high-traffic environments:
+    - VM Name: `vm3_sensor`
+    - Volume Size: `2000` GB (2 TB)
+    - VM is started after attachment
+
+**Notes:**
+
+- The script automatically stops the VM if it's running before creating and attaching the volume.
+- Volumes are created with full pre-allocation for optimal performance.
+- Volume files are stored in `/nsm/libvirt/volumes/` with naming pattern `<vm_name>-nsm.img`.
+- Volumes are attached as `/dev/vdb` using virtio-blk for high performance.
+- The script checks available disk space before creating the volume.
+- Ownership is set to `qemu:qemu` with permissions `640`.
+- Without the `-S` flag, the VM remains stopped after volume attachment.
+
+**Description:**
+
+The `so-kvm-create-volume` script creates and attaches NSM storage volumes using the following process:
+
+1. **Pre-flight Checks:**
+   - Validates input parameters (VM name, size)
+   - Checks available disk space in `/nsm/libvirt/volumes/`
+   - Ensures sufficient space for the requested volume size
+
+2. **VM State Management:**
+   - Connects to the local libvirt daemon
+   - Stops the VM if it's currently running
+   - Retrieves current VM configuration
+
+3. **Volume Creation:**
+   - Creates volume directory if it doesn't exist
+   - Uses `qemu-img create` with full pre-allocation
+   - Sets proper ownership (qemu:qemu) and permissions (640)
+   - Validates volume creation success
+
+4. **Volume Attachment:**
+   - Modifies VM's libvirt XML configuration
+   - Adds disk element with virtio-blk driver
+   - Configures cache='none' and io='native' for performance
+   - Attaches volume as `/dev/vdb`
+
+5. **VM Redefinition:**
+   - Applies the new configuration by redefining the VM
+   - Optionally starts the VM if requested
+   - Emits deployment status events for monitoring
+
+6. **Error Handling:**
+   - Validates all input parameters
+   - Checks disk space before creation
+   - Handles volume creation failures
+   - Handles volume attachment failures
+   - Provides detailed error messages for troubleshooting
+
+**Exit Codes:**
+
+- `0`: Success
+- `1`: An error occurred during execution
+
+**Logging:**
+
+- Logs are written to `/opt/so/log/hypervisor/so-kvm-create-volume.log`
+- Both file and console logging are enabled for real-time monitoring
+- Log entries include timestamps and severity levels
+- Log prefixes: VOLUME:, VM:, HARDWARE:, SPACE:
+- Detailed error messages are logged for troubleshooting
+"""
+
+import argparse
+import sys
+import os
+import libvirt
+import logging
+import socket
+import subprocess
+import pwd
+import grp
+import xml.etree.ElementTree as ET
+from io import StringIO
+from so_vm_utils import start_vm, stop_vm
+from so_logging_utils import setup_logging
+
+# Get hypervisor name from local hostname
+HYPERVISOR = socket.gethostname()
+
+# Volume storage directory
+VOLUME_DIR = '/nsm/libvirt/volumes'
+
+# Custom exception classes
+class InsufficientSpaceError(Exception):
+    """Raised when there is insufficient disk space for volume creation."""
+    pass
+
+class VolumeCreationError(Exception):
+    """Raised when volume creation fails."""
+    pass
+
+class VolumeAttachmentError(Exception):
+    """Raised when volume attachment fails."""
+    pass
+
+# Custom log handler to capture output
+class StringIOHandler(logging.Handler):
+    def __init__(self):
+        super().__init__()
+        self.strio = StringIO()
+
+    def emit(self, record):
+        msg = self.format(record)
+        self.strio.write(msg + '\n')
+
+    def get_value(self):
+        return self.strio.getvalue()
+
+def parse_arguments():
+    """Parse command-line arguments."""
+    parser = argparse.ArgumentParser(description='Create and attach a virtual volume to a KVM virtual machine for NSM storage.')
+    parser.add_argument('-v', '--vm', required=True, help='Name of the virtual machine to attach the volume to.')
+    parser.add_argument('-s', '--size', type=int, required=True, help='Size of the volume in GB (must be a positive integer).')
+    parser.add_argument('-S', '--start', action='store_true', help='Start the VM after volume creation and attachment.')
+    args = parser.parse_args()
+    
+    # Validate size is positive
+    if args.size <= 0:
+        parser.error("Volume size must be a positive integer.")
+    
+    return args
+
+def check_disk_space(size_gb, logger):
+    """
+    Check if there is sufficient disk space available for volume creation.
+    
+    Args:
+        size_gb: Size of the volume in GB
+        logger: Logger instance
+        
+    Raises:
+        InsufficientSpaceError: If there is not enough disk space
+    """
+    try:
+        stat = os.statvfs(VOLUME_DIR)
+        # Available space in bytes
+        available_bytes = stat.f_bavail * stat.f_frsize
+        # Required space in bytes (add 10% buffer)
+        required_bytes = size_gb * 1024 * 1024 * 1024 * 1.1
+        
+        available_gb = available_bytes / (1024 * 1024 * 1024)
+        required_gb = required_bytes / (1024 * 1024 * 1024)
+        
+        logger.info(f"SPACE: Available: {available_gb:.2f} GB, Required: {required_gb:.2f} GB")
+        
+        if available_bytes < required_bytes:
+            raise InsufficientSpaceError(
+                f"Insufficient disk space. Available: {available_gb:.2f} GB, Required: {required_gb:.2f} GB"
+            )
+        
+        logger.info(f"SPACE: Sufficient disk space available for {size_gb} GB volume")
+        
+    except OSError as e:
+        logger.error(f"SPACE: Failed to check disk space: {e}")
+        raise
+
+def create_volume_file(vm_name, size_gb, logger):
+    """
+    Create a pre-allocated raw disk image for the VM.
+    
+    Args:
+        vm_name: Name of the VM
+        size_gb: Size of the volume in GB
+        logger: Logger instance
+        
+    Returns:
+        Path to the created volume file
+        
+    Raises:
+        VolumeCreationError: If volume creation fails
+    """
+    # Define volume path (directory already created in main())
+    volume_path = os.path.join(VOLUME_DIR, f"{vm_name}-nsm.img")
+    
+    # Check if volume already exists
+    if os.path.exists(volume_path):
+        logger.error(f"VOLUME: Volume already exists: {volume_path}")
+        raise VolumeCreationError(f"Volume already exists: {volume_path}")
+    
+    logger.info(f"VOLUME: Creating {size_gb} GB volume at {volume_path}")
+    
+    # Create volume using qemu-img with full pre-allocation
+    try:
+        cmd = [
+            'qemu-img', 'create',
+            '-f', 'raw',
+            '-o', 'preallocation=full',
+            volume_path,
+            f"{size_gb}G"
+        ]
+        
+        result = subprocess.run(
+            cmd,
+            capture_output=True,
+            text=True,
+            check=True
+        )
+        
+        logger.info(f"VOLUME: Volume created successfully")
+        if result.stdout:
+            logger.debug(f"VOLUME: qemu-img output: {result.stdout.strip()}")
+        
+    except subprocess.CalledProcessError as e:
+        logger.error(f"VOLUME: Failed to create volume: {e}")
+        if e.stderr:
+            logger.error(f"VOLUME: qemu-img error: {e.stderr.strip()}")
+        raise VolumeCreationError(f"Failed to create volume: {e}")
+    
+    # Set ownership to qemu:qemu
+    try:
+        qemu_uid = pwd.getpwnam('qemu').pw_uid
+        qemu_gid = grp.getgrnam('qemu').gr_gid
+        os.chown(volume_path, qemu_uid, qemu_gid)
+        logger.info(f"VOLUME: Set ownership to qemu:qemu")
+    except (KeyError, OSError) as e:
+        logger.error(f"VOLUME: Failed to set ownership: {e}")
+        raise VolumeCreationError(f"Failed to set ownership: {e}")
+    
+    # Set permissions to 640
+    try:
+        os.chmod(volume_path, 0o640)
+        logger.info(f"VOLUME: Set permissions to 640")
+    except OSError as e:
+        logger.error(f"VOLUME: Failed to set permissions: {e}")
+        raise VolumeCreationError(f"Failed to set permissions: {e}")
+    
+    # Verify volume was created
+    if not os.path.exists(volume_path):
+        logger.error(f"VOLUME: Volume file not found after creation: {volume_path}")
+        raise VolumeCreationError(f"Volume file not found after creation: {volume_path}")
+    
+    volume_size = os.path.getsize(volume_path)
+    logger.info(f"VOLUME: Volume created: {volume_path} ({volume_size} bytes)")
+    
+    return volume_path
+
+def attach_volume_to_vm(conn, vm_name, volume_path, logger):
+    """
+    Attach the volume to the VM's libvirt XML configuration.
+    
+    Args:
+        conn: Libvirt connection
+        vm_name: Name of the VM
+        volume_path: Path to the volume file
+        logger: Logger instance
+        
+    Raises:
+        VolumeAttachmentError: If volume attachment fails
+    """
+    try:
+        # Get the VM domain
+        dom = conn.lookupByName(vm_name)
+        
+        # Get the XML description of the VM
+        xml_desc = dom.XMLDesc()
+        root = ET.fromstring(xml_desc)
+        
+        # Find the devices element
+        devices_elem = root.find('./devices')
+        if devices_elem is None:
+            logger.error("VM: Could not find <devices> element in XML")
+            raise VolumeAttachmentError("Could not find <devices> element in VM XML")
+        
+        # Log ALL devices with PCI addresses to find conflicts
+        logger.info("DISK_DEBUG: Examining ALL devices with PCI addresses")
+        for device in devices_elem:
+            address = device.find('./address')
+            if address is not None and address.get('type') == 'pci':
+                bus = address.get('bus', 'unknown')
+                slot = address.get('slot', 'unknown')
+                function = address.get('function', 'unknown')
+                logger.info(f"DISK_DEBUG: Device {device.tag}: bus={bus}, slot={slot}, function={function}")
+        
+        # Log existing disk configuration for debugging
+        logger.info("DISK_DEBUG: Examining existing disk configuration")
+        existing_disks = devices_elem.findall('./disk')
+        for idx, disk in enumerate(existing_disks):
+            target = disk.find('./target')
+            source = disk.find('./source')
+            address = disk.find('./address')
+            
+            dev_name = target.get('dev') if target is not None else 'unknown'
+            source_file = source.get('file') if source is not None else 'unknown'
+            
+            if address is not None:
+                slot = address.get('slot', 'unknown')
+                bus = address.get('bus', 'unknown')
+                logger.info(f"DISK_DEBUG: Disk {idx}: dev={dev_name}, source={source_file}, slot={slot}, bus={bus}")
+            else:
+                logger.info(f"DISK_DEBUG: Disk {idx}: dev={dev_name}, source={source_file}, no address element")
+        
+        # Check if vdb already exists
+        for disk in devices_elem.findall('./disk'):
+            target = disk.find('./target')
+            if target is not None and target.get('dev') == 'vdb':
+                logger.error("VM: Device vdb already exists in VM configuration")
+                raise VolumeAttachmentError("Device vdb already exists in VM configuration")
+        
+        logger.info(f"VM: Attaching volume to {vm_name} as /dev/vdb")
+        
+        # Create disk element
+        disk_elem = ET.SubElement(devices_elem, 'disk', attrib={
+            'type': 'file',
+            'device': 'disk'
+        })
+        
+        # Add driver element
+        ET.SubElement(disk_elem, 'driver', attrib={
+            'name': 'qemu',
+            'type': 'raw',
+            'cache': 'none',
+            'io': 'native'
+        })
+        
+        # Add source element
+        ET.SubElement(disk_elem, 'source', attrib={
+            'file': volume_path
+        })
+        
+        # Add target element
+        ET.SubElement(disk_elem, 'target', attrib={
+            'dev': 'vdb',
+            'bus': 'virtio'
+        })
+        
+        # Add address element
+        # Use bus 0x07 with slot 0x00 to ensure NSM volume appears after OS disk (which is on bus 0x04)
+        # Bus 0x05 is used by memballoon, bus 0x06 is used by rng device
+        # Libvirt requires slot <= 0 for non-zero buses
+        # This ensures vda = OS disk, vdb = NSM volume
+        ET.SubElement(disk_elem, 'address', attrib={
+            'type': 'pci',
+            'domain': '0x0000',
+            'bus': '0x07',
+            'slot': '0x00',
+            'function': '0x0'
+        })
+        
+        logger.info(f"HARDWARE: Added disk configuration for vdb")
+        
+        # Log disk ordering after adding new disk
+        logger.info("DISK_DEBUG: Disk configuration after adding NSM volume")
+        all_disks = devices_elem.findall('./disk')
+        for idx, disk in enumerate(all_disks):
+            target = disk.find('./target')
+            source = disk.find('./source')
+            address = disk.find('./address')
+            
+            dev_name = target.get('dev') if target is not None else 'unknown'
+            source_file = source.get('file') if source is not None else 'unknown'
+            
+            if address is not None:
+                slot = address.get('slot', 'unknown')
+                bus = address.get('bus', 'unknown')
+                logger.info(f"DISK_DEBUG: Disk {idx}: dev={dev_name}, source={source_file}, slot={slot}, bus={bus}")
+            else:
+                logger.info(f"DISK_DEBUG: Disk {idx}: dev={dev_name}, source={source_file}, no address element")
+        
+        # Convert XML back to string
+        new_xml_desc = ET.tostring(root, encoding='unicode')
+        
+        # Redefine the VM with the new XML
+        conn.defineXML(new_xml_desc)
+        logger.info(f"VM: VM redefined with volume attached")
+        
+    except libvirt.libvirtError as e:
+        logger.error(f"VM: Failed to attach volume: {e}")
+        raise VolumeAttachmentError(f"Failed to attach volume: {e}")
+    except Exception as e:
+        logger.error(f"VM: Failed to attach volume: {e}")
+        raise VolumeAttachmentError(f"Failed to attach volume: {e}")
+
+def emit_status_event(vm_name, status):
+    """
+    Emit a deployment status event.
+    
+    Args:
+        vm_name: Name of the VM
+        status: Status message
+    """
+    try:
+        subprocess.run([
+            'so-salt-emit-vm-deployment-status-event',
+            '-v', vm_name,
+            '-H', HYPERVISOR,
+            '-s', status
+        ], check=True)
+    except subprocess.CalledProcessError as e:
+        # Don't fail the entire operation if status event fails
+        pass
+
+def main():
+    """Main function to orchestrate volume creation and attachment."""
+    # Set up logging using the so_logging_utils library
+    string_handler = StringIOHandler()
+    string_handler.setFormatter(logging.Formatter('%(asctime)s - %(levelname)s - %(message)s'))
+    logger = setup_logging(
+        logger_name='so-kvm-create-volume',
+        log_file_path='/opt/so/log/hypervisor/so-kvm-create-volume.log',
+        log_level=logging.INFO,
+        format_str='%(asctime)s - %(levelname)s - %(message)s'
+    )
+    logger.addHandler(string_handler)
+
+    vm_name = None
+    
+    try:
+        # Parse arguments
+        args = parse_arguments()
+        
+        vm_name = args.vm
+        size_gb = args.size
+        start_vm_flag = args.start
+        
+        logger.info(f"VOLUME: Starting volume creation for VM '{vm_name}' with size {size_gb} GB")
+        
+        # Emit start status event
+        emit_status_event(vm_name, 'Volume Creation')
+        
+        # Ensure volume directory exists before checking disk space
+        try:
+            os.makedirs(VOLUME_DIR, mode=0o754, exist_ok=True)
+            qemu_uid = pwd.getpwnam('qemu').pw_uid
+            qemu_gid = grp.getgrnam('qemu').gr_gid
+            os.chown(VOLUME_DIR, qemu_uid, qemu_gid)
+            logger.debug(f"VOLUME: Ensured volume directory exists: {VOLUME_DIR}")
+        except Exception as e:
+            logger.error(f"VOLUME: Failed to create volume directory: {e}")
+            emit_status_event(vm_name, 'Volume Configuration Failed')
+            sys.exit(1)
+        
+        # Check disk space
+        check_disk_space(size_gb, logger)
+        
+        # Connect to libvirt
+        try:
+            conn = libvirt.open(None)
+            logger.info("VM: Connected to libvirt")
+        except libvirt.libvirtError as e:
+            logger.error(f"VM: Failed to open connection to libvirt: {e}")
+            emit_status_event(vm_name, 'Volume Configuration Failed')
+            sys.exit(1)
+        
+        # Stop VM if running
+        dom = stop_vm(conn, vm_name, logger)
+        
+        # Create volume file
+        volume_path = create_volume_file(vm_name, size_gb, logger)
+        
+        # Attach volume to VM
+        attach_volume_to_vm(conn, vm_name, volume_path, logger)
+        
+        # Start VM if -S or --start argument is provided
+        if start_vm_flag:
+            dom = conn.lookupByName(vm_name)
+            start_vm(dom, logger)
+            logger.info(f"VM: VM '{vm_name}' started successfully")
+        else:
+            logger.info("VM: Start flag not provided; VM will remain stopped")
+        
+        # Close connection
+        conn.close()
+        
+        # Emit success status event
+        emit_status_event(vm_name, 'Volume Configuration')
+        
+        logger.info(f"VOLUME: Volume creation and attachment completed successfully for VM '{vm_name}'")
+        
+    except KeyboardInterrupt:
+        error_msg = "Operation cancelled by user"
+        logger.error(error_msg)
+        if vm_name:
+            emit_status_event(vm_name, 'Volume Configuration Failed')
+        sys.exit(1)
+        
+    except InsufficientSpaceError as e:
+        error_msg = f"SPACE: {str(e)}"
+        logger.error(error_msg)
+        if vm_name:
+            emit_status_event(vm_name, 'Volume Configuration Failed')
+        sys.exit(1)
+        
+    except VolumeCreationError as e:
+        error_msg = f"VOLUME: {str(e)}"
+        logger.error(error_msg)
+        if vm_name:
+            emit_status_event(vm_name, 'Volume Configuration Failed')
+        sys.exit(1)
+        
+    except VolumeAttachmentError as e:
+        error_msg = f"VM: {str(e)}"
+        logger.error(error_msg)
+        if vm_name:
+            emit_status_event(vm_name, 'Volume Configuration Failed')
+        sys.exit(1)
+        
+    except Exception as e:
+        error_msg = f"An error occurred: {str(e)}"
+        logger.error(error_msg)
+        if vm_name:
+            emit_status_event(vm_name, 'Volume Configuration Failed')
+        sys.exit(1)
+
+if __name__ == '__main__':
+    main()
+
+{%- else -%}
+
+echo "Hypervisor nodes are a feature supported only for customers with a valid license. \
+      Contact Security Onion Solutions, LLC via our website at https://securityonionsolutions.com \
+      for more information about purchasing a license to enable this feature."
+
+{% endif -%}

salt/kibana/defaults.yaml

@@ -22,7 +22,7 @@ kibana:
           - default
           - file
     migrations:
-      discardCorruptObjects: "8.18.6"
+      discardCorruptObjects: "8.18.8"
     telemetry:
       enabled: False
     security:

salt/kratos/enabled.sls

@@ -54,6 +54,9 @@ so-kratos:
       - file: kratosconfig
       - file: kratoslogdir
       - file: kratosdir
+    - retry:
+        attempts: 10
+        interval: 10
 
 delete_so-kratos_so-status.disabled:
   file.uncomment:

salt/libvirt/bridge.sls

@@ -4,6 +4,9 @@
 # Elastic License 2.0.
 
 # We do not import GLOBALS in this state because it is called during setup
+include:
+  - salt.minion.service_file
+  - salt.mine_functions
 
 down_original_mgmt_interface:
   cmd.run:
@@ -28,29 +31,14 @@ wait_for_br0_ip:
     - timeout: 95
     - onchanges:
       - cmd: down_original_mgmt_interface
-
-{% if grains.role == 'so-hypervisor' %}
-
-update_mine_functions:
-  file.managed:
-    - name: /etc/salt/minion.d/mine_functions.conf
-    - contents: |
-        mine_interval: 25
-        mine_functions:
-          network.ip_addrs:
-            - interface: br0
-        {%- if role in ['so-eval','so-import','so-manager','so-managerhype','so-managersearch','so-standalone'] %}
-          x509.get_pem_entries:
-            - glob_path: '/etc/pki/ca.crt'
-        {% endif %}
-    - onchanges:
-      - cmd: wait_for_br0_ip
+    - onchanges_in:
+      - file: salt_minion_service_unit_file
+      - file: mine_functions
 
 restart_salt_minion_service:
   service.running:
     - name: salt-minion
     - enable: True
     - listen:
-      - file: update_mine_functions
-
-{% endif %}
+      - file: salt_minion_service_unit_file
+      - file: mine_functions

salt/logstash/tools/sbin/so-logstash-flow-stats

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+curl -s -L http://localhost:9600/_node/stats/flow | jq

salt/logstash/tools/sbin/so-logstash-health

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+curl -s -L http://localhost:9600/_health_report | jq

salt/logstash/tools/sbin/so-logstash-jvm-stats

@@ -0,0 +1,3 @@
+#!/bin/bash
+
+curl -s -L http://localhost:9600/_node/stats/jvm | jq

salt/manager/tools/sbin/so-saltstack-update

@@ -5,10 +5,12 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
 default_salt_dir=/opt/so/saltstack/default
-clone_to_tmp() {
+VERBOSE=0
+VERY_VERBOSE=0
+TEST_MODE=0
 
+clone_to_tmp() {
   # TODO Need to add a air gap option
   # Make a temp location for the files
   mkdir /tmp/sogh
@@ -16,19 +18,110 @@ clone_to_tmp() {
   #git clone -b dev https://github.com/Security-Onion-Solutions/securityonion.git
   git clone https://github.com/Security-Onion-Solutions/securityonion.git
   cd /tmp
+}
 
+show_file_changes() {
+  local source_dir="$1"
+  local dest_dir="$2"
+  local dir_type="$3"  # "salt" or "pillar"
+  
+  if [ $VERBOSE -eq 0 ]; then
+    return
+  fi
+  
+  echo "=== Changes for $dir_type directory ==="
+  
+  # Find all files in source directory
+  if [ -d "$source_dir" ]; then
+    find "$source_dir" -type f | while read -r source_file; do
+      # Get relative path
+      rel_path="${source_file#$source_dir/}"
+      dest_file="$dest_dir/$rel_path"
+      
+      if [ ! -f "$dest_file" ]; then
+        echo "ADDED: $dest_file"
+        if [ $VERY_VERBOSE -eq 1 ]; then
+          echo "  (New file - showing first 20 lines)"
+          head -n 20 "$source_file" | sed 's/^/  + /'
+          echo ""
+        fi
+      elif ! cmp -s "$source_file" "$dest_file"; then
+        echo "MODIFIED: $dest_file"
+        if [ $VERY_VERBOSE -eq 1 ]; then
+          echo "  (Changes:)"
+          diff -u "$dest_file" "$source_file" | sed 's/^/  /'
+          echo ""
+        fi
+      fi
+    done
+  fi
+  
+  # Find deleted files (exist in dest but not in source)
+  if [ -d "$dest_dir" ]; then
+    find "$dest_dir" -type f | while read -r dest_file; do
+      # Get relative path
+      rel_path="${dest_file#$dest_dir/}"
+      source_file="$source_dir/$rel_path"
+      
+      if [ ! -f "$source_file" ]; then
+        echo "DELETED: $dest_file"
+        if [ $VERY_VERBOSE -eq 1 ]; then
+          echo "  (File was deleted)"
+          echo ""
+        fi
+      fi
+    done
+  fi
+  
+  echo ""
 }
 
 copy_new_files() {
-
   # Copy new files over to the salt dir
   cd /tmp/sogh/securityonion
   git checkout $BRANCH
   VERSION=$(cat VERSION)
+  
+  if [ $TEST_MODE -eq 1 ]; then
+    echo "=== TEST MODE: Showing what would change without making changes ==="
+    echo "Branch: $BRANCH"
+    echo "Version: $VERSION"
+    echo ""
+  fi
+  
+  # Show changes before copying if verbose mode is enabled OR if in test mode
+  if [ $VERBOSE -eq 1 ] || [ $TEST_MODE -eq 1 ]; then
+    if [ $TEST_MODE -eq 1 ]; then
+      # In test mode, force at least basic verbose output
+      local old_verbose=$VERBOSE
+      if [ $VERBOSE -eq 0 ]; then
+        VERBOSE=1
+      fi
+    fi
+    
+    echo "Analyzing file changes..."
+    show_file_changes "$(pwd)/salt" "$default_salt_dir/salt" "salt"
+    show_file_changes "$(pwd)/pillar" "$default_salt_dir/pillar" "pillar"
+    
+    if [ $TEST_MODE -eq 1 ] && [ $old_verbose -eq 0 ]; then
+      # Restore original verbose setting
+      VERBOSE=$old_verbose
+    fi
+  fi
+  
+  # If in test mode, don't copy files
+  if [ $TEST_MODE -eq 1 ]; then
+    echo "=== TEST MODE: No files were modified ==="
+    echo "To apply these changes, run without --test option"
+    rm -rf /tmp/sogh
+    return
+  fi
+  
   # We need to overwrite if there is a repo file
   if [ -d /opt/so/repo ]; then
     tar -czf /opt/so/repo/"$VERSION".tar.gz -C "$(pwd)/.." .
   fi
+  
   rsync -a salt $default_salt_dir/
   rsync -a pillar $default_salt_dir/
   chown -R socore:socore $default_salt_dir/salt
@@ -45,11 +138,64 @@ got_root(){
     fi
 }
 
-got_root
-if [ $# -ne 1 ] ; then
+show_usage() {
+    echo "Usage: $0 [-v] [-vv] [--test] [branch]"
+    echo "  -v       Show verbose output (files changed/added/deleted)"
+    echo "  -vv      Show very verbose output (includes file diffs)"
+    echo "  --test   Test mode - show what would change without making changes"
+    echo "  branch   Git branch to checkout (default: 2.4/main)"
+    echo ""
+    echo "Examples:"
+    echo "  $0                    # Normal operation"
+    echo "  $0 -v                 # Show which files change"
+    echo "  $0 -vv                # Show files and their diffs"
+    echo "  $0 --test             # See what would change (dry run)"
+    echo "  $0 --test -vv         # Test mode with detailed diffs"
+    echo "  $0 -v dev-branch      # Use specific branch with verbose output"
+    exit 1
+}
+
+# Parse command line arguments
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    -v)
+      VERBOSE=1
+      shift
+      ;;
+    -vv)
+      VERBOSE=1
+      VERY_VERBOSE=1
+      shift
+      ;;
+    --test)
+      TEST_MODE=1
+      shift
+      ;;
+    -h|--help)
+      show_usage
+      ;;
+    -*)
+      echo "Unknown option $1"
+      show_usage
+      ;;
+    *)
+      # This should be the branch name
+      if [ -z "$BRANCH" ]; then
+        BRANCH="$1"
+      else
+        echo "Too many arguments"
+        show_usage
+      fi
+      shift
+      ;;
+  esac
+done
+
+# Set default branch if not provided
+if [ -z "$BRANCH" ]; then
   BRANCH=2.4/main
-else
-  BRANCH=$1
 fi
+
+got_root
 clone_to_tmp
 copy_new_files

salt/manager/tools/sbin/so-user

@@ -387,7 +387,7 @@ function syncElastic() {
     if [[ -z "$SKIP_STATE_APPLY" ]]; then
       echo "Elastic state will be re-applied to affected minions. This will run in the background and may take several minutes to complete."
       echo "Applying elastic state to elastic minions at $(date)" >> /opt/so/log/soc/sync.log 2>&1
-      salt --async -C 'G@role:so-standalone or G@role:so-eval or G@role:so-import or G@role:so-manager or G@role:so-managersearch or G@role:so-searchnode or G@role:so-heavynode' state.apply elasticsearch queue=True >> /opt/so/log/soc/sync.log 2>&1
+      salt --async -C 'I@elasticsearch:enabled:true' state.apply elasticsearch queue=True >> /opt/so/log/soc/sync.log 2>&1
     fi
   else
     echo "Newly generated users/roles files are incomplete; aborting."

salt/manager/tools/sbin/soup

@@ -169,6 +169,8 @@ airgap_update_dockers() {
       tar xf "$AGDOCKER/registry.tar" -C /nsm/docker-registry/docker
       echo "Add Registry back"
       docker load -i "$AGDOCKER/registry_image.tar"
+      echo "Restart registry container"
+      salt-call state.apply registry queue=True
     fi
   fi
 }
@@ -420,6 +422,7 @@ preupgrade_changes() {
     [[ "$INSTALLEDVERSION" == 2.4.150 ]] && up_to_2.4.160
     [[ "$INSTALLEDVERSION" == 2.4.160 ]] && up_to_2.4.170
     [[ "$INSTALLEDVERSION" == 2.4.170 ]] && up_to_2.4.180
+    [[ "$INSTALLEDVERSION" == 2.4.180 ]] && up_to_2.4.190
     true
 }
 
@@ -450,6 +453,7 @@ postupgrade_changes() {
     [[ "$POSTVERSION"  == 2.4.150 ]] && post_to_2.4.160
     [[ "$POSTVERSION"  == 2.4.160 ]] && post_to_2.4.170
     [[ "$POSTVERSION"  == 2.4.170 ]] && post_to_2.4.180
+    [[ "$POSTVERSION"  == 2.4.180 ]] && post_to_2.4.190
     true
 }
 
@@ -599,15 +603,36 @@ post_to_2.4.170() {
 }
 
 post_to_2.4.180() {
-  echo "Regenerating Elastic Agent Installers"
-  /sbin/so-elastic-agent-gen-installers
-
   # Force update to Kafka output policy
   /usr/sbin/so-kafka-fleet-output-policy --force
 
   POSTVERSION=2.4.180
 }
 
+post_to_2.4.190() {
+    echo "Regenerating Elastic Agent Installers"
+    /sbin/so-elastic-agent-gen-installers
+
+    # Only need to update import / eval nodes
+    if [[ "$MINION_ROLE" == "import" ]] || [[ "$MINION_ROLE" == "eval" ]]; then
+        update_import_fleet_output
+    fi
+
+    # Check if expected default policy is logstash (global.pipeline is REDIS or "")
+    pipeline=$(lookup_pillar "pipeline" "global")
+    if [[ -z "$pipeline" ]] || [[ "$pipeline" == "REDIS" ]]; then
+        # Check if this grid is currently affected by corrupt fleet output policy
+        if elastic-agent status | grep "config: key file not configured" > /dev/null 2>&1; then
+            echo "Elastic Agent shows an ssl error connecting to logstash output. Updating output policy..."
+            update_default_logstash_output
+        fi
+    fi
+    # Apply new elasticsearch.server index template
+    rollover_index "logs-elasticsearch.server-default"
+
+  POSTVERSION=2.4.190
+}
+
 repo_sync() {
   echo "Sync the local repo."
   su socore -c '/usr/sbin/so-repo-sync' || fail "Unable to complete so-repo-sync."
@@ -864,10 +889,15 @@ up_to_2.4.170() {
 }
 
 up_to_2.4.180() {
+  echo "Nothing to do for 2.4.180"
+  INSTALLEDVERSION=2.4.180
+}
+
+up_to_2.4.190() {
   # Elastic Update for this release, so download Elastic Agent files
   determine_elastic_agent_upgrade
 
-  INSTALLEDVERSION=2.4.180
+  INSTALLEDVERSION=2.4.190
 }
 
 add_hydra_pillars() {
@@ -1143,6 +1173,44 @@ update_elasticsearch_index_settings() {
   done
 }
 
+update_import_fleet_output() {
+    if output=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/outputs/so-manager_elasticsearch" --retry 3 --fail 2>/dev/null); then
+        # Update the current config of so-manager_elasticsearch output policy in place (leaving any customizations like having changed the preset value from 'balanced' to 'performance')
+        CAFINGERPRINT=$(openssl x509 -in /etc/pki/tls/certs/intca.crt -outform DER | sha256sum | cut -d' ' -f1 | tr '[:lower:]' '[:upper:]')
+        updated_policy=$(jq --arg CAFINGERPRINT "$CAFINGERPRINT" '.item | (del(.id) | .ca_trusted_fingerprint = $CAFINGERPRINT)' <<< "$output")
+        if curl -sK /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/outputs/so-manager_elasticsearch" -XPUT -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$updated_policy" --retry 3 --fail 2>/dev/null; then
+            echo "Successfully updated so-manager_elasticsearch fleet output policy"
+        else
+            fail "Failed to update so-manager_elasticsearch fleet output policy"
+        fi
+    fi
+}
+
+update_default_logstash_output() {
+    echo "Updating fleet logstash output policy grid-logstash"
+    if logstash_policy=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_logstash" --retry 3 --retry-delay 10 --fail 2>/dev/null); then
+        # Keep already configured hosts for this update, subsequent host updates come from so-elastic-fleet-outputs-update
+        HOSTS=$(echo "$logstash_policy" | jq -r '.item.hosts')
+        DEFAULT_ENABLED=$(echo "$logstash_policy" | jq -r '.item.is_default')
+        DEFAULT_MONITORING_ENABLED=$(echo "$logstash_policy" | jq -r '.item.is_default_monitoring')
+        LOGSTASHKEY=$(openssl rsa -in  /etc/pki/elasticfleet-logstash.key)
+        LOGSTASHCRT=$(openssl x509 -in /etc/pki/elasticfleet-logstash.crt)
+        LOGSTASHCA=$(openssl x509 -in  /etc/pki/tls/certs/intca.crt)
+        JSON_STRING=$(jq -n \
+            --argjson HOSTS "$HOSTS" \
+            --arg DEFAULT_ENABLED "$DEFAULT_ENABLED" \
+            --arg DEFAULT_MONITORING_ENABLED "$DEFAULT_MONITORING_ENABLED" \
+            --arg LOGSTASHKEY "$LOGSTASHKEY" \
+            --arg LOGSTASHCRT "$LOGSTASHCRT" \
+            --arg LOGSTASHCA "$LOGSTASHCA" \
+            '{"name":"grid-logstash","type":"logstash","hosts": $HOSTS,"is_default": $DEFAULT_ENABLED,"is_default_monitoring": $DEFAULT_MONITORING_ENABLED,"config_yaml":"","ssl":{"certificate": $LOGSTASHCRT,"certificate_authorities":[ $LOGSTASHCA ]},"secrets":{"ssl":{"key": $LOGSTASHKEY }}}')
+    fi
+
+    if curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_logstash" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" --retry 3 --retry-delay 10 --fail; then
+        echo "Successfully updated grid-logstash fleet output policy"
+    fi
+}
+
 update_salt_mine() {
     echo "Populating the mine with mine_functions for each host."
     set +e
@@ -1359,6 +1427,7 @@ main() {
   fi
 
   set_minionid
+  MINION_ROLE=$(lookup_role)
   echo "Found that Security Onion $INSTALLEDVERSION is currently installed."
   echo ""
   if [[ $is_airgap -eq 0 ]]; then
@@ -1401,7 +1470,7 @@ main() {
   if [ "$is_hotfix" == "true" ]; then
     echo "Applying $HOTFIXVERSION hotfix"
     # since we don't run the backup.config_backup state on import we wont snapshot previous version states and pillars
-    if [[ ! "$MINIONID" =~ "_import" ]]; then
+    if [[ ! "$MINION_ROLE" == "import" ]]; then
       backup_old_states_pillars
     fi
     copy_new_files
@@ -1464,7 +1533,7 @@ main() {
     fi
 
     # since we don't run the backup.config_backup state on import we wont snapshot previous version states and pillars
-    if [[ ! "$MINIONID" =~ "_import" ]]; then
+    if [[ ! "$MINION_ROLE" == "import" ]]; then
       echo ""
       echo "Creating snapshots of default and local Salt states and pillars and saving to /nsm/backup/"
       backup_old_states_pillars

salt/manager/tools/sbin_jinja/so-salt-cloud

@@ -211,7 +211,7 @@ Exit Codes:
 
 Logging:
 
-- Logs are written to /opt/so/log/salt/so-salt-cloud.log.
+- Logs are written to /opt/so/log/salt/so-salt-cloud.
 - Both file and console logging are enabled for real-time monitoring.
 
 """
@@ -233,7 +233,7 @@ local = salt.client.LocalClient()
 logger = logging.getLogger(__name__)
 logger.setLevel(logging.INFO)
 
-file_handler = logging.FileHandler('/opt/so/log/salt/so-salt-cloud.log')
+file_handler = logging.FileHandler('/opt/so/log/salt/so-salt-cloud')
 console_handler = logging.StreamHandler()
 
 formatter = logging.Formatter('%(asctime)s %(message)s')
@@ -516,23 +516,85 @@ def run_qcow2_modify_hardware_config(profile, vm_name, cpu=None, memory=None, pc
     target = hv_name + "_*"
 
     try:
-        args_list = [
-            'vm_name=' + vm_name,
-            'cpu=' + str(cpu) if cpu else '',
-            'memory=' + str(memory) if memory else '',
-            'start=' + str(start)
-        ]
-
+        args_list = ['vm_name=' + vm_name]
+        
+        # Only add parameters that are actually specified
+        if cpu is not None:
+            args_list.append('cpu=' + str(cpu))
+        if memory is not None:
+            args_list.append('memory=' + str(memory))
+        
         # Add PCI devices if provided
         if pci_list:
             # Pass all PCI devices as a comma-separated list
             args_list.append('pci=' + ','.join(pci_list))
+        
+        # Always add start parameter
+        args_list.append('start=' + str(start))
 
         result = local.cmd(target, 'qcow2.modify_hardware_config', args_list)
         format_qcow2_output('Hardware configuration', result)
     except Exception as e:
         logger.error(f"An error occurred while running qcow2.modify_hardware_config: {e}")
 
+def run_qcow2_create_volume_config(profile, vm_name, size_gb, cpu=None, memory=None, start=False):
+    """Create a volume for the VM and optionally configure CPU/memory.
+    
+    Args:
+        profile (str): The cloud profile name
+        vm_name (str): The name of the VM
+        size_gb (int): Size of the volume in GB
+        cpu (int, optional): Number of CPUs to assign
+        memory (int, optional): Amount of memory in MiB
+        start (bool): Whether to start the VM after configuration
+    """
+    hv_name = profile.split('_')[1]
+    target = hv_name + "_*"
+
+    try:
+        # Step 1: Create the volume
+        logger.info(f"Creating {size_gb}GB volume for VM {vm_name}")
+        volume_result = local.cmd(
+            target,
+            'qcow2.create_volume_config',
+            kwarg={
+                'vm_name': vm_name,
+                'size_gb': size_gb,
+                'start': False  # Don't start yet if we need to configure CPU/memory
+            }
+        )
+        format_qcow2_output('Volume creation', volume_result)
+        
+        # Step 2: Configure CPU and memory if specified
+        if cpu or memory:
+            logger.info(f"Configuring hardware for VM {vm_name}: CPU={cpu}, Memory={memory}MiB")
+            hw_result = local.cmd(
+                target,
+                'qcow2.modify_hardware_config',
+                kwarg={
+                    'vm_name': vm_name,
+                    'cpu': cpu,
+                    'memory': memory,
+                    'start': start
+                }
+            )
+            format_qcow2_output('Hardware configuration', hw_result)
+        elif start:
+            # If no CPU/memory config needed but we need to start the VM
+            logger.info(f"Starting VM {vm_name}")
+            start_result = local.cmd(
+                target,
+                'qcow2.modify_hardware_config',
+                kwarg={
+                    'vm_name': vm_name,
+                    'start': True
+                }
+            )
+            format_qcow2_output('VM startup', start_result)
+            
+    except Exception as e:
+        logger.error(f"An error occurred while creating volume and configuring hardware: {e}")
+
 def run_qcow2_modify_network_config(profile, vm_name, mode, ip=None, gateway=None, dns=None, search_domain=None):
     hv_name = profile.split('_')[1]
     target = hv_name + "_*"
@@ -586,6 +648,7 @@ def parse_arguments():
     network_group.add_argument('-c', '--cpu', type=int, help='Number of virtual CPUs to assign.')
     network_group.add_argument('-m', '--memory', type=int, help='Amount of memory to assign in MiB.')
     network_group.add_argument('-P', '--pci', action='append', help='PCI hardware ID(s) to passthrough to the VM (e.g., 0000:c7:00.0). Can be specified multiple times.')
+    network_group.add_argument('--nsm-size', type=int, help='Size in GB for NSM volume creation. Can be used with copper/sfp NICs (--pci). Only disk passthrough (without --nsm-size) prevents volume creation.')
 
     args = parser.parse_args()
 
@@ -621,6 +684,8 @@ def main():
                 hw_config.append(f"{args.memory}MB RAM")
             if args.pci:
                 hw_config.append(f"PCI devices: {', '.join(args.pci)}")
+            if args.nsm_size:
+                hw_config.append(f"NSM volume: {args.nsm_size}GB")
             hw_string = f" and hardware config: {', '.join(hw_config)}" if hw_config else ""
             
             logger.info(f"Received request to create VM '{args.vm_name}' using profile '{args.profile}' {network_config}{hw_string}")
@@ -643,8 +708,58 @@ def main():
             # Step 2: Provision the VM (without starting it)
             call_salt_cloud(args.profile, args.vm_name)
 
-            # Step 3: Modify hardware configuration
-            run_qcow2_modify_hardware_config(args.profile, args.vm_name, cpu=args.cpu, memory=args.memory, pci_list=args.pci, start=True)
+            # Step 3: Determine storage configuration approach
+            # Priority: disk passthrough > volume creation (but volume can coexist with copper/sfp NICs)
+            # Note: virtual_node_manager.py already filters out --nsm-size when disk is present,
+            # so if both --pci and --nsm-size are present here, the PCI devices are copper/sfp NICs
+            use_passthrough = False
+            use_volume_creation = False
+            has_nic_passthrough = False
+            
+            if args.nsm_size:
+                # Validate nsm_size
+                if args.nsm_size <= 0:
+                    logger.error(f"Invalid nsm_size value: {args.nsm_size}. Must be a positive integer.")
+                    sys.exit(1)
+                use_volume_creation = True
+                logger.info(f"Using volume creation with size {args.nsm_size}GB (--nsm-size parameter specified)")
+                
+                if args.pci:
+                    # If both nsm_size and PCI are present, PCI devices are copper/sfp NICs
+                    # (virtual_node_manager.py filters out nsm_size when disk is present)
+                    has_nic_passthrough = True
+                    logger.info(f"PCI devices (copper/sfp NICs) will be passed through along with volume: {', '.join(args.pci)}")
+            elif args.pci:
+                # Only PCI devices, no nsm_size - could be disk or NICs
+                # this script is called by virtual_node_manager and that strips any possibility that nsm_size and the disk pci slot is sent to this script
+                # we might have not specified a disk passthrough or nsm_size, but pass another pci slot and we end up here
+                use_passthrough = True
+                logger.info(f"Configuring PCI device passthrough.(--pci parameter specified without --nsm-size)")
+            
+            # Step 4: Configure hardware based on storage approach
+            if use_volume_creation:
+                # Create volume first
+                run_qcow2_create_volume_config(args.profile, args.vm_name, size_gb=args.nsm_size, cpu=args.cpu, memory=args.memory, start=False)
+                
+                # Then configure NICs if present
+                if has_nic_passthrough:
+                    logger.info(f"Configuring NIC passthrough for VM {args.vm_name}")
+                    run_qcow2_modify_hardware_config(args.profile, args.vm_name, cpu=None, memory=None, pci_list=args.pci, start=True)
+                else:
+                    # No NICs, just start the VM
+                    logger.info(f"Starting VM {args.vm_name}")
+                    run_qcow2_modify_hardware_config(args.profile, args.vm_name, cpu=None, memory=None, pci_list=None, start=True)
+            elif use_passthrough:
+                # Use existing passthrough logic via modify_hardware_config
+                run_qcow2_modify_hardware_config(args.profile, args.vm_name, cpu=args.cpu, memory=args.memory, pci_list=args.pci, start=True)
+            else:
+                # No storage configuration, just configure CPU/memory if specified
+                if args.cpu or args.memory:
+                    run_qcow2_modify_hardware_config(args.profile, args.vm_name, cpu=args.cpu, memory=args.memory, pci_list=None, start=True)
+                else:
+                    # No hardware configuration needed, just start the VM
+                    logger.info(f"No hardware configuration specified, starting VM {args.vm_name}")
+                    run_qcow2_modify_hardware_config(args.profile, args.vm_name, cpu=None, memory=None, pci_list=None, start=True)
 
     except KeyboardInterrupt:
         logger.error("so-salt-cloud: Operation cancelled by user.")

salt/salt/engines/master/virtual_node_manager.py

@@ -117,7 +117,7 @@ Exit Codes:
     4: VM provisioning failure (so-salt-cloud execution failed)
 
 Logging:
-    Log files are written to /opt/so/log/salt/engines/virtual_node_manager.log
+    Log files are written to /opt/so/log/salt/engines/virtual_node_manager
     Comprehensive logging includes:
     - Hardware validation details
     - PCI ID conversion process
@@ -138,29 +138,56 @@ import pwd
 import grp
 import salt.config
 import salt.runner
+import salt.client
 from typing import Dict, List, Optional, Tuple, Any
 from datetime import datetime, timedelta
 from threading import Lock
 
-# Get socore uid/gid
-SOCORE_UID = pwd.getpwnam('socore').pw_uid
-SOCORE_GID = grp.getgrnam('socore').gr_gid
-
-# Initialize Salt runner once
+# Initialize Salt runner and local client once
 opts = salt.config.master_config('/etc/salt/master')
 opts['output'] = 'json'
 runner = salt.runner.RunnerClient(opts)
+local = salt.client.LocalClient()
+
+# Get socore uid/gid for file ownership
+SOCORE_UID = pwd.getpwnam('socore').pw_uid
+SOCORE_GID = grp.getgrnam('socore').gr_gid
 
 # Configure logging
 log = logging.getLogger(__name__)
 log.setLevel(logging.DEBUG)
 
+# Prevent propagation to parent loggers to avoid duplicate log entries
+log.propagate = False
+
+# Add file handler for dedicated log file
+log_dir = '/opt/so/log/salt'
+log_file = os.path.join(log_dir, 'virtual_node_manager')
+
+# Create log directory if it doesn't exist
+os.makedirs(log_dir, exist_ok=True)
+
+# Create file handler
+file_handler = logging.FileHandler(log_file)
+file_handler.setLevel(logging.DEBUG)
+
+# Create formatter
+formatter = logging.Formatter(
+    '%(asctime)s [%(name)s:%(lineno)d][%(levelname)-8s][%(process)d] %(message)s',
+    datefmt='%Y-%m-%d %H:%M:%S'
+)
+file_handler.setFormatter(formatter)
+
+# Add handler to logger
+log.addHandler(file_handler)
+
 # Constants
 DEFAULT_INTERVAL = 30
 DEFAULT_BASE_PATH = '/opt/so/saltstack/local/salt/hypervisor/hosts'
 VALID_ROLES = ['sensor', 'searchnode', 'idh', 'receiver', 'heavynode', 'fleet']
 LICENSE_PATH = '/opt/so/saltstack/local/pillar/soc/license.sls'
 DEFAULTS_PATH = '/opt/so/saltstack/default/salt/hypervisor/defaults.yaml'
+HYPERVISOR_PILLAR_PATH = '/opt/so/saltstack/local/pillar/hypervisor/soc_hypervisor.sls'
 # Define the retention period for destroyed VMs (in hours)
 DESTROYED_VM_RETENTION_HOURS = 48
 
@@ -202,6 +229,39 @@ def write_json_file(file_path: str, data: Any) -> None:
     except Exception as e:
         log.error("Failed to write JSON file %s: %s", file_path, str(e))
         raise
+def remove_vm_from_vms_file(vms_file_path: str, vm_hostname: str, vm_role: str) -> bool:
+    """
+    Remove a VM entry from the hypervisorVMs file.
+    
+    Args:
+        vms_file_path: Path to the hypervisorVMs file
+        vm_hostname: Hostname of the VM to remove (without role suffix)
+        vm_role: Role of the VM
+        
+    Returns:
+        bool: True if VM was removed, False otherwise
+    """
+    try:
+        # Read current VMs
+        vms = read_json_file(vms_file_path)
+        
+        # Find and remove the VM entry
+        original_count = len(vms)
+        vms = [vm for vm in vms if not (vm.get('hostname') == vm_hostname and vm.get('role') == vm_role)]
+        
+        if len(vms) < original_count:
+            # VM was found and removed, write back to file
+            write_json_file(vms_file_path, vms)
+            log.info("Removed VM %s_%s from %s", vm_hostname, vm_role, vms_file_path)
+            return True
+        else:
+            log.warning("VM %s_%s not found in %s", vm_hostname, vm_role, vms_file_path)
+            return False
+            
+    except Exception as e:
+        log.error("Failed to remove VM %s_%s from %s: %s", vm_hostname, vm_role, vms_file_path, str(e))
+        return False
+
 
 def read_yaml_file(file_path: str) -> dict:
     """Read and parse a YAML file."""
@@ -271,7 +331,7 @@ def parse_hardware_indices(hw_value: Any) -> List[int]:
     return indices
 
 def get_hypervisor_model(hypervisor: str) -> str:
-    """Get sosmodel from hypervisor grains."""
+    """Get sosmodel or byodmodel from hypervisor grains."""
     try:
         # Get cached grains using Salt runner
         grains = runner.cmd(
@@ -283,9 +343,9 @@ def get_hypervisor_model(hypervisor: str) -> str:
             
         # Get the first minion ID that matches our hypervisor
         minion_id = next(iter(grains.keys()))
-        model = grains[minion_id].get('sosmodel')
+        model = grains[minion_id].get('sosmodel', grains[minion_id].get('byodmodel', ''))
         if not model:
-            raise ValueError(f"No sosmodel grain found for hypervisor {hypervisor}")
+            raise ValueError(f"No sosmodel or byodmodel grain found for hypervisor {hypervisor}")
             
         log.debug("Found model %s for hypervisor %s", model, hypervisor)
         return model
@@ -295,16 +355,48 @@ def get_hypervisor_model(hypervisor: str) -> str:
         raise
 
 def load_hardware_defaults(model: str) -> dict:
-    """Load hardware configuration from defaults.yaml."""
+    """Load hardware configuration from defaults.yaml and optionally override with pillar configuration."""
+    config = None
+    config_source = None
+    
     try:
+        # First, try to load from defaults.yaml
+        log.debug("Checking for model %s in %s", model, DEFAULTS_PATH)
         defaults = read_yaml_file(DEFAULTS_PATH)
         if not defaults or 'hypervisor' not in defaults:
             raise ValueError("Invalid defaults.yaml structure")
         if 'model' not in defaults['hypervisor']:
             raise ValueError("No model configurations found in defaults.yaml")
-        if model not in defaults['hypervisor']['model']:
-            raise ValueError(f"Model {model} not found in defaults.yaml")
-        return defaults['hypervisor']['model'][model]
+        
+        # Check if model exists in defaults
+        if model in defaults['hypervisor']['model']:
+            config = defaults['hypervisor']['model'][model]
+            config_source = DEFAULTS_PATH
+            log.debug("Found model %s in %s", model, DEFAULTS_PATH)
+        
+        # Then, try to load from pillar file (if it exists)
+        try:
+            log.debug("Checking for model %s in %s", model, HYPERVISOR_PILLAR_PATH)
+            pillar_config = read_yaml_file(HYPERVISOR_PILLAR_PATH)
+            if pillar_config and 'hypervisor' in pillar_config:
+                if 'model' in pillar_config['hypervisor']:
+                    if model in pillar_config['hypervisor']['model']:
+                        # Override with pillar configuration
+                        config = pillar_config['hypervisor']['model'][model]
+                        config_source = HYPERVISOR_PILLAR_PATH
+                        log.debug("Found model %s in %s (overriding defaults)", model, HYPERVISOR_PILLAR_PATH)
+        except FileNotFoundError:
+            log.debug("Pillar file %s not found, using defaults only", HYPERVISOR_PILLAR_PATH)
+        except Exception as e:
+            log.warning("Failed to read pillar file %s: %s (using defaults)", HYPERVISOR_PILLAR_PATH, str(e))
+        
+        # If model was not found in either file, raise an error
+        if config is None:
+            raise ValueError(f"Model {model} not found in {DEFAULTS_PATH} or {HYPERVISOR_PILLAR_PATH}")
+        
+        log.debug("Using hardware configuration for model %s from %s", model, config_source)
+        return config
+        
     except Exception as e:
         log.error("Failed to load hardware defaults: %s", str(e))
         raise
@@ -525,6 +617,13 @@ def mark_vm_failed(vm_file: str, error_code: int, message: str) -> None:
             # Remove the original file since we'll create an error file
             os.remove(vm_file)
 
+        # Clear hardware resource claims so failed VMs don't consume resources
+        # Keep nsm_size for reference but clear cpu, memory, sfp, copper
+        config.pop('cpu', None)
+        config.pop('memory', None)
+        config.pop('sfp', None)
+        config.pop('copper', None)
+
         # Create error file
         error_file = f"{vm_file}.error"
         data = {
@@ -553,8 +652,16 @@ def mark_invalid_hardware(hypervisor_path: str, vm_name: str, config: dict, erro
         # Join all messages with proper sentence structure
         full_message = "Hardware validation failure: " + " ".join(error_messages)
         
+        # Clear hardware resource claims so failed VMs don't consume resources
+        # Keep nsm_size for reference but clear cpu, memory, sfp, copper
+        config_copy = config.copy()
+        config_copy.pop('cpu', None)
+        config_copy.pop('memory', None)
+        config_copy.pop('sfp', None)
+        config_copy.pop('copper', None)
+        
         data = {
-            'config': config,
+            'config': config_copy,
             'status': 'error',
             'timestamp': datetime.now().isoformat(),
             'error_details': {
@@ -601,6 +708,61 @@ def validate_vrt_license() -> bool:
         log.error("Error reading license file: %s", str(e))
         return False
 
+def check_hypervisor_disk_space(hypervisor: str, size_gb: int) -> Tuple[bool, Optional[str]]:
+    """
+    Check if hypervisor has sufficient disk space for volume creation.
+    
+    Args:
+        hypervisor: Hypervisor hostname
+        size_gb: Required size in GB
+        
+    Returns:
+        Tuple of (has_space, error_message)
+    """
+    try:
+        # Get hypervisor minion ID
+        hypervisor_minion = f"{hypervisor}_hypervisor"
+        
+        # Check disk space on /nsm/libvirt/volumes using LocalClient
+        result = local.cmd(
+            hypervisor_minion,
+            'cmd.run',
+            ["df -BG /nsm/libvirt/volumes | tail -1 | awk '{print $4}' | sed 's/G//'"]
+        )
+        
+        if not result or hypervisor_minion not in result:
+            log.error("Failed to check disk space on hypervisor %s", hypervisor)
+            return False, "Failed to check disk space on hypervisor"
+        
+        available_gb_str = result[hypervisor_minion].strip()
+        if not available_gb_str:
+            log.error("Empty disk space response from hypervisor %s", hypervisor)
+            return False, "Failed to get disk space information"
+            
+        try:
+            available_gb = float(available_gb_str)
+        except ValueError:
+            log.error("Invalid disk space value from hypervisor %s: %s", hypervisor, available_gb_str)
+            return False, f"Invalid disk space value: {available_gb_str}"
+        
+        # Add 10% buffer for filesystem overhead
+        required_gb = size_gb * 1.1
+        
+        log.debug("Hypervisor %s disk space check: Available=%.2fGB, Required=%.2fGB",
+                 hypervisor, available_gb, required_gb)
+        
+        if available_gb < required_gb:
+            error_msg = f"Insufficient disk space on hypervisor {hypervisor}. Available: {available_gb:.2f}GB, Required: {required_gb:.2f}GB (including 10% overhead)"
+            log.error(error_msg)
+            return False, error_msg
+        
+        log.info("Hypervisor %s has sufficient disk space for %dGB volume", hypervisor, size_gb)
+        return True, None
+        
+    except Exception as e:
+        log.error("Error checking disk space on hypervisor %s: %s", hypervisor, str(e))
+        return False, f"Error checking disk space: {str(e)}"
+
 def process_vm_creation(hypervisor_path: str, vm_config: dict) -> None:
     """
     Process a single VM creation request.
@@ -633,6 +795,62 @@ def process_vm_creation(hypervisor_path: str, vm_config: dict) -> None:
         except subprocess.CalledProcessError as e:
             logger.error(f"Failed to emit success status event: {e}")
 
+        # Validate nsm_size if present
+        if 'nsm_size' in vm_config:
+            try:
+                size = int(vm_config['nsm_size'])
+                if size <= 0:
+                    log.error("VM: %s - nsm_size must be a positive integer, got: %d", vm_name, size)
+                    mark_invalid_hardware(hypervisor_path, vm_name, vm_config,
+                                        {'nsm_size': 'Invalid nsm_size: must be positive integer'})
+                    return
+                if size > 10000:  # 10TB reasonable maximum
+                    log.error("VM: %s - nsm_size %dGB exceeds reasonable maximum (10000GB)", vm_name, size)
+                    mark_invalid_hardware(hypervisor_path, vm_name, vm_config,
+                                        {'nsm_size': f'Invalid nsm_size: {size}GB exceeds maximum (10000GB)'})
+                    return
+                log.debug("VM: %s - nsm_size validated: %dGB", vm_name, size)
+            except (ValueError, TypeError) as e:
+                log.error("VM: %s - nsm_size must be a valid integer, got: %s", vm_name, vm_config.get('nsm_size'))
+                mark_invalid_hardware(hypervisor_path, vm_name, vm_config,
+                                    {'nsm_size': 'Invalid nsm_size: must be valid integer'})
+                return
+
+        # Check for conflicting storage configurations
+        has_disk = 'disk' in vm_config and vm_config['disk']
+        has_nsm_size = 'nsm_size' in vm_config and vm_config['nsm_size']
+
+        if has_disk and has_nsm_size:
+            log.warning("VM: %s - Both disk and nsm_size specified. disk takes precedence, nsm_size will be ignored.",
+                       vm_name)
+
+        # Check disk space BEFORE creating VM if nsm_size is specified
+        if has_nsm_size and not has_disk:
+            size_gb = int(vm_config['nsm_size'])
+            has_space, space_error = check_hypervisor_disk_space(hypervisor, size_gb)
+            if not has_space:
+                log.error("VM: %s - %s", vm_name, space_error)
+                
+                # Send Hypervisor NSM Disk Full status event
+                try:
+                    subprocess.run([
+                        'so-salt-emit-vm-deployment-status-event',
+                        '-v', vm_name,
+                        '-H', hypervisor,
+                        '-s', 'Hypervisor NSM Disk Full'
+                    ], check=True)
+                except subprocess.CalledProcessError as e:
+                    log.error("Failed to emit volume create failed event for %s: %s", vm_name, str(e))
+                
+                mark_invalid_hardware(
+                    hypervisor_path,
+                    vm_name,
+                    vm_config,
+                    {'disk_space': f"Insufficient disk space for {size_gb}GB volume: {space_error}"}
+                )
+                return
+            log.debug("VM: %s - Hypervisor has sufficient space for %dGB volume", vm_name, size_gb)
+
         # Initial hardware validation against model
         is_valid, errors = validate_hardware_request(model_config, vm_config)
         if not is_valid:
@@ -668,6 +886,11 @@ def process_vm_creation(hypervisor_path: str, vm_config: dict) -> None:
         if 'memory' in vm_config:
             memory_mib = int(vm_config['memory']) * 1024
             cmd.extend(['-m', str(memory_mib)])
+
+        # Add nsm_size if specified and disk is not specified
+        if 'nsm_size' in vm_config and vm_config['nsm_size'] and not ('disk' in vm_config and vm_config['disk']):
+            cmd.extend(['--nsm-size', str(vm_config['nsm_size'])])
+            log.debug("VM: %s - Adding nsm_size parameter: %s", vm_name, vm_config['nsm_size'])
             
         # Add PCI devices
         for hw_type in ['disk', 'copper', 'sfp']:
@@ -900,12 +1123,21 @@ def process_hypervisor(hypervisor_path: str) -> None:
         if not nodes_config:
             log.debug("Empty VMs configuration in %s", vms_file)
             
-        # Get existing VMs
+        # Get existing VMs and track failed VMs separately
         existing_vms = set()
+        failed_vms = set()  # VMs with .error files
         for file_path in glob.glob(os.path.join(hypervisor_path, '*_*')):
             basename = os.path.basename(file_path)
-            # Skip error and status files
-            if not basename.endswith('.error') and not basename.endswith('.status'):
+            # Skip status files
+            if basename.endswith('.status'):
+                continue
+            # Track VMs with .error files separately
+            if basename.endswith('.error'):
+                vm_name = basename[:-6]  # Remove '.error' suffix
+                failed_vms.add(vm_name)
+                existing_vms.add(vm_name)  # Also add to existing to prevent recreation
+                log.debug(f"Found failed VM with .error file: {vm_name}")
+            else:
                 existing_vms.add(basename)
                 
         # Process new VMs
@@ -922,12 +1154,37 @@ def process_hypervisor(hypervisor_path: str) -> None:
                 # process_vm_creation handles its own locking
                 process_vm_creation(hypervisor_path, vm_config)
                 
-        # Process VM deletions
+        # Process VM deletions (but skip failed VMs that only have .error files)
         vms_to_delete = existing_vms - configured_vms
         log.debug(f"Existing VMs: {existing_vms}")
         log.debug(f"Configured VMs: {configured_vms}")
+        log.debug(f"Failed VMs: {failed_vms}")
         log.debug(f"VMs to delete: {vms_to_delete}")
         for vm_name in vms_to_delete:
+            # Skip deletion if VM only has .error file (no actual VM to delete)
+            if vm_name in failed_vms:
+                error_file = os.path.join(hypervisor_path, f"{vm_name}.error")
+                base_file = os.path.join(hypervisor_path, vm_name)
+                # Only skip if there's no base file (VM never successfully created)
+                if not os.path.exists(base_file):
+                    log.info(f"Skipping deletion of failed VM {vm_name} (VM never successfully created)")
+                    # Clean up the .error and .status files since VM is no longer configured
+                    if os.path.exists(error_file):
+                        os.remove(error_file)
+                        log.info(f"Removed .error file for unconfigured VM: {vm_name}")
+                    status_file = os.path.join(hypervisor_path, f"{vm_name}.status")
+                    if os.path.exists(status_file):
+                        os.remove(status_file)
+                        log.info(f"Removed .status file for unconfigured VM: {vm_name}")
+                    
+                    # Trigger hypervisor annotation update to reflect the removal
+                    try:
+                        log.info(f"Triggering hypervisor annotation update after removing failed VM: {vm_name}")
+                        runner.cmd('state.orch', ['orch.dyanno_hypervisor'])
+                    except Exception as e:
+                        log.error(f"Failed to trigger hypervisor annotation update for {vm_name}: {str(e)}")
+                    
+                    continue
             log.info(f"Initiating deletion process for VM: {vm_name}")
             process_vm_deletion(hypervisor_path, vm_name)
             

salt/salt/map.jinja

@@ -4,7 +4,10 @@
    Elastic License 2.0. #}
 
 {% set role = salt['grains.get']('role', '') %}
-{% if role in ['so-hypervisor','so-managerhype'] and salt['network.ip_addrs']('br0')|length > 0 %}
+{# We are using usebr0 mostly for setup of the so-managerhype node and controlling when we use br0 vs the physical interface #}
+{% set usebr0 = salt['pillar.get']('usebr0', True) %}
+
+{% if role in ['so-hypervisor','so-managerhype'] and usebr0 %}
 {%   set interface = 'br0' %}
 {% else %}
 {%   set interface = pillar.host.mainint %}

salt/salt/mine_functions.sls

@@ -3,7 +3,7 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-# this state was seperated from salt.minion state since it is called during setup
+# this state was separated from salt.minion state since it is called during setup
 # GLOBALS are imported in the salt.minion state and that is not available at that point in setup
 # this state is included in the salt.minion state
 

salt/salt/minion/init.sls

@@ -1,18 +1,22 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
 {% from 'vars/globals.map.jinja' import GLOBALS %}
 {% from 'salt/map.jinja' import UPGRADECOMMAND with context %}
 {% from 'salt/map.jinja' import SALTVERSION %}
 {% from 'salt/map.jinja' import INSTALLEDSALTVERSION %}
 {% from 'salt/map.jinja' import SALTPACKAGES %}
-{% from 'salt/map.jinja' import SYSTEMD_UNIT_FILE %}
 {% import_yaml 'salt/minion.defaults.yaml' as SALTMINION %}
 
 include:
   - salt.python_modules
   - salt.patch.x509_v2
   - salt
-  - systemd.reload
   - repo.client
   - salt.mine_functions
+  - salt.minion.service_file
 {% if GLOBALS.role in GLOBALS.manager_roles %}
   - ca
 {% endif %}
@@ -94,17 +98,6 @@ enable_startup_states:
     - regex: '^startup_states: highstate$'
     - unless: pgrep so-setup
 
-# prior to 2.4.30 this managed file would restart the salt-minion service when updated
-# since this file is currently only adding a delay service start
-# it is not required to restart the service
-salt_minion_service_unit_file:
-  file.managed:
-    - name: {{ SYSTEMD_UNIT_FILE }}
-    - source: salt://salt/service/salt-minion.service.jinja
-    - template: jinja
-    - onchanges_in:
-      - module: systemd_reload
-
 {% endif %}
 
 # this has to be outside the if statement above since there are <requisite>_in calls to this state

salt/salt/minion/service_file.sls

@@ -0,0 +1,26 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+{% from 'salt/map.jinja' import SALTVERSION %}
+{% from 'salt/map.jinja' import INSTALLEDSALTVERSION %}
+{% from 'salt/map.jinja' import SYSTEMD_UNIT_FILE %}
+
+include:
+  - systemd.reload
+
+{% if INSTALLEDSALTVERSION|string == SALTVERSION|string %}
+
+# prior to 2.4.30 this managed file would restart the salt-minion service when updated
+# since this file is currently only adding a delay service start
+# it is not required to restart the service
+salt_minion_service_unit_file:
+  file.managed:
+    - name: {{ SYSTEMD_UNIT_FILE }}
+    - source: salt://salt/service/salt-minion.service.jinja
+    - template: jinja
+    - onchanges_in:
+      - module: systemd_reload
+
+{% endif %}

salt/sensoroni/defaults.yaml

@@ -5,6 +5,12 @@ sensoroni:
       enabled: False
       timeout_ms: 900000
       parallel_limit: 5
+    export:
+      timeout_ms: 1200000
+      cache_refresh_interval_ms: 10000
+      export_metric_limit: 10000
+      export_event_limit: 10000
+      csv_separator: ','
     node_checkin_interval_ms: 10000
     sensoronikey:
     soc_host:

salt/sensoroni/files/sensoroni.json

@@ -21,7 +21,13 @@
       },
 {%- endif %}
       "importer": {},
-      "export": {},
+      "export": {
+        "timeoutMs": {{ SENSORONIMERGED.config.export.timeout_ms }},
+        "cacheRefreshIntervalMs": {{ SENSORONIMERGED.config.export.cache_refresh_interval_ms }},
+        "exportMetricLimit": {{ SENSORONIMERGED.config.export.export_metric_limit }},
+        "exportEventLimit": {{ SENSORONIMERGED.config.export.export_event_limit }},
+        "csvSeparator": "{{ SENSORONIMERGED.config.export.csv_separator }}"
+      },
       "statickeyauth": {
         "apiKey": "{{ GLOBALS.sensoroni_key }}"
 {%  if GLOBALS.is_sensor %}

salt/sensoroni/soc_sensoroni.yaml

@@ -17,6 +17,27 @@ sensoroni:
         description: Parallel limit for the analyzer.
         advanced: True
         helpLink: cases.html
+    export:
+      timeout_ms:
+        description: Timeout period for the exporter to finish export-related tasks.
+        advanced: True
+        helpLink: reports.html
+      cache_refresh_interval_ms:
+        description: Refresh interval for cache updates. Longer intervals result in less compute usage but risks stale data included in reports.
+        advanced: True
+        helpLink: reports.html
+      export_metric_limit:
+        description: Maximum number of metric values to include in each metric aggregation group.
+        advanced: True
+        helpLink: reports.html
+      export_event_limit:
+        description: Maximum number of events to include per event list.
+        advanced: True
+        helpLink: reports.html
+      csv_separator:
+        description: Separator character to use for CSV exports.
+        advanced: False
+        helpLink: reports.html
     node_checkin_interval_ms:
       description: Interval in ms to checkin to the soc_host.
       advanced: True

salt/soc/defaults.yaml

@@ -1493,6 +1493,9 @@ soc:
                 folder: securityonion-normalized
         assistant:
           apiUrl: https://onionai.securityonion.net
+          healthTimeoutSeconds: 3
+          systemPromptAddendum: ""
+          systemPromptAddendumMaxLength: 50000
         salt:
           queueDir: /opt/sensoroni/queue
           timeoutMs: 45000
@@ -1635,6 +1638,9 @@ soc:
             - name: socExcludeToggle
               filter: 'NOT event.module:"soc"'
               enabled: true
+            - name: onionaiExcludeToggle
+              filter: 'NOT _index:"*:so-assistant-*"'
+              enabled: true
           queries:
             - name: Default Query
               description: Show all events grouped by the observer host
@@ -2545,7 +2551,7 @@ soc:
               level: 'high'  # info | low | medium | high | critical
         assistant:
           enabled: false
-          investigationPrompt: Investigate Alert ID {socid}
+          investigationPrompt: Investigate Alert ID {socId}
           contextLimitSmall: 200000
           contextLimitLarge: 1000000
           thresholdColorRatioLow: 0.5

salt/soc/dyanno/hypervisor/hypervisor.yaml

@@ -63,18 +63,22 @@ hypervisor:
         required: true
         readonly: true
         forcedType: int
+      - field: nsm_size
+        label: "Size of virtual disk to create and use for /nsm, in GB. Only applicable if no pass-through disk."
+        forcedType: int
+        readonly: true
       - field: disk
-        label: "Disk(s) for passthrough. Free: FREE | Total: TOTAL"
+        label: "Disk(s) to pass through for /nsm. Free: FREE | Total: TOTAL"
         readonly: true
         options: []
         forcedType: '[]int'
       - field: copper
-        label: "Copper port(s) for passthrough. Free: FREE | Total: TOTAL"
+        label: "Copper port(s) to pass through. Free: FREE | Total: TOTAL"
         readonly: true
         options: []
         forcedType: '[]int'
       - field: sfp
-        label: "SFP port(s) for passthrough. Free: FREE | Total: TOTAL"
+        label: "SFP port(s) to pass through. Free: FREE | Total: TOTAL"
         readonly: true
         options: []
         forcedType: '[]int'

salt/soc/dyanno/hypervisor/map.jinja

@@ -3,11 +3,14 @@
 {# Define the list of process steps in order (case-sensitive) #}
 {% set PROCESS_STEPS = [
     'Processing',
+    'Hypervisor NSM Disk Full',
     'IP Configuration',
     'Starting Create',
     'Executing Deploy Script',
     'Initialize Minion Pillars',
     'Created Instance',
+    'Volume Creation',
+    'Volume Configuration',
     'Hardware Configuration',
     'Highstate Initiated',
     'Destroyed Instance'

salt/soc/dyanno/hypervisor/remove_failed_vm.sls

@@ -0,0 +1,51 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+#
+# Note: Per the Elastic License 2.0, the second limitation states:
+#
+#   "You may not move, change, disable, or circumvent the license key functionality
+#    in the software, and you may not remove or obscure any functionality in the
+#    software that is protected by the license key."
+
+{% if 'vrt' in salt['pillar.get']('features', []) %}
+
+{% do salt.log.info('soc/dyanno/hypervisor/remove_failed_vm: Running') %}
+{% set vm_name = pillar.get('vm_name') %}
+{% set hypervisor = pillar.get('hypervisor') %}
+
+{% if vm_name and hypervisor %}
+{%   set vm_parts = vm_name.split('_') %}
+{%   if vm_parts | length >= 2 %}
+{%     set vm_role = vm_parts[-1] %}
+{%     set vm_hostname = '_'.join(vm_parts[:-1]) %}
+{%     set vms_file = '/opt/so/saltstack/local/salt/hypervisor/hosts/' ~ hypervisor ~ 'VMs' %}
+
+{%     do salt.log.info('soc/dyanno/hypervisor/remove_failed_vm: Removing VM ' ~ vm_name ~ ' from ' ~ vms_file) %}
+
+remove_vm_{{ vm_name }}_from_vms_file:
+  module.run:
+    - name: hypervisor.remove_vm_from_vms_file
+    - vms_file_path: {{ vms_file }}
+    - vm_hostname: {{ vm_hostname }}
+    - vm_role: {{ vm_role }}
+
+{%   else %}
+{%     do salt.log.error('soc/dyanno/hypervisor/remove_failed_vm: Invalid vm_name format: ' ~ vm_name) %}
+{%   endif %}
+{% else %}
+{%   do salt.log.error('soc/dyanno/hypervisor/remove_failed_vm: Missing required pillar data (vm_name or hypervisor)') %}
+{% endif %}
+
+{% do salt.log.info('soc/dyanno/hypervisor/remove_failed_vm: Completed') %}
+
+{% else %}
+
+{% do salt.log.error(
+  'Hypervisor nodes are a feature supported only for customers with a valid license. '
+  'Contact Security Onion Solutions, LLC via our website at https://securityonionsolutions.com '
+  'for more information about purchasing a license to enable this feature.'
+) %}
+
+{% endif %}

salt/soc/dyanno/hypervisor/soc_hypervisor.yaml.jinja

@@ -13,7 +13,6 @@
 
 {%- import_yaml 'soc/dyanno/hypervisor/hypervisor.yaml' as ANNOTATION -%}
 {%- from 'hypervisor/map.jinja' import HYPERVISORS -%}
-{%- from 'soc/dyanno/hypervisor/map.jinja' import PROCESS_STEPS -%}
 
 {%- set TEMPLATE = ANNOTATION.hypervisor.hosts.pop('defaultHost') -%}
 
@@ -27,7 +26,6 @@
 {%- if baseDomainStatus == 'Initialized' %}
 {%-   if vm_list %}
 #### Virtual Machines
-Status values: {% for step in PROCESS_STEPS %}{{ step }}{% if not loop.last %}, {% endif %}{% endfor %}. "Last Updated" shows when status changed. After "Highstate Initiated", only "Destroyed Instance" updates the timestamp.
 
 | Name               | Status             | CPU Cores | Memory (GB)| Disk | Copper | SFP  | Last Updated        |
 |--------------------|--------------------|-----------|------------|------|--------|------|---------------------|
@@ -42,7 +40,6 @@ Status values: {% for step in PROCESS_STEPS %}{{ step }}{% if not loop.last %},
 {%-     endfor %}
 {%-   else %}
 #### Virtual Machines
-Status values: {% for step in PROCESS_STEPS %}{{ step }}{% if not loop.last %}, {% endif %}{% endfor %}. "Last Updated" shows when status changed. After "Highstate Initiated", only "Destroyed Instance" updates the timestamp.
 
 No Virtual Machines Found
 {%-   endif %}
@@ -96,9 +93,21 @@ Base domain has not been initialized.
 {%-       endif -%}
 {%-     endfor -%}
 
-{# Calculate available resources #}
-{%-     set cpu_free = hw_config.cpu - ns.used_cpu -%}
-{%-     set mem_free = hw_config.memory - ns.used_memory -%}
+{# Determine host OS overhead based on role #}
+{%-     if role == 'hypervisor' -%}
+{%-       set host_os_cpu = 8 -%}
+{%-       set host_os_memory = 16 -%}
+{%-     elif role == 'managerhype' -%}
+{%-       set host_os_cpu = 16 -%}
+{%-       set host_os_memory = 32 -%}
+{%-     else -%}
+{%-       set host_os_cpu = 0 -%}
+{%-       set host_os_memory = 0 -%}
+{%-     endif -%}
+
+{# Calculate available resources (subtract both VM usage and host OS overhead) #}
+{%-     set cpu_free = hw_config.cpu - ns.used_cpu - host_os_cpu -%}
+{%-     set mem_free = hw_config.memory - ns.used_memory - host_os_memory -%}
 
 {# Get used PCI indices #}
 {%-     set used_disk = [] -%}

salt/soc/files/bin/salt-relay.sh

@@ -237,10 +237,22 @@ function manage_salt() {
 
   case "$op" in
     state)
-      log "Performing '$op' for '$state' on minion '$minion'"
       state=$(echo "$request" | jq -r .state)
-      response=$(salt --async "$minion" state.apply "$state" queue=2)
+      async=$(echo "$request" | jq -r .async)
+      if [[ $async == "true" ]]; then
+        log "Performing async '$op' on minion $minion with state '$state'"
+        response=$(salt --async "$minion" state.apply "$state" queue=2)
+      else
+        log "Performing '$op' on minion $minion with state '$state'"
+        response=$(salt "$minion" state.apply "$state")
+      fi
+     
       exit_code=$?
+      if [[ $exit_code -ne 0 && "$response" =~ "is running as PID" ]]; then
+        log "Salt already running: $response ($exit_code)"
+        respond "$id" "ERROR_SALT_ALREADY_RUNNING"
+        return
+      fi
       ;;
     highstate)
       log "Performing '$op' on minion $minion"
@@ -259,7 +271,7 @@ function manage_salt() {
       ;;
   esac
 
-  if [[ exit_code -eq 0 ]]; then
+  if [[ $exit_code -eq 0 ]]; then
     log "Successful command execution: $response"
     respond "$id" "true"
   else

salt/soc/soc_soc.yaml

@@ -585,6 +585,19 @@ soc:
             description: The URL of the AI gateway.
             advanced: True
             global: True
+          healthTimeoutSeconds:
+            description: Timeout in seconds for the Onion AI health check.
+            global: True
+            advanced: True
+          systemPromptAddendum:
+            description: Additional context to provide to the AI assistant about this SOC deployment. This can include information about your environment, policies, or any other relevant details that can help the AI provide more accurate and tailored assistance. Long prompts may be shortened.
+            global: True
+            advanced: False
+            multiline: True
+          systemPromptAddendumMaxLength:
+            description: Maximum length of the system prompt addendum. Longer prompts will be truncated.
+            global: True
+            advanced: True
       client:
         assistant:
           enabled:
@@ -615,6 +628,7 @@ soc:
             advanced: True 
           lowBalanceColorAlert:
             description: Onion AI credit amount at which balance turns red.
+            global: True
             advanced: True
         apiTimeoutMs:
           description: Duration (in milliseconds) to wait for a response from the SOC server API before giving up and showing an error on the SOC UI.

salt/storage/init.sls

@@ -4,10 +4,17 @@
 # Elastic License 2.0.
 
 
-{% set nvme_devices = salt['cmd.shell']("find /dev -name 'nvme*n1' 2>/dev/null") %}
+{% set nvme_devices = salt['cmd.shell']("ls /dev/nvme*n1 2>/dev/null || echo ''") %}
+{% set virtio_devices = salt['cmd.shell']("test -b /dev/vdb && echo '/dev/vdb' || echo ''") %}
+
 {% if nvme_devices %}
 
 include:
-  - storage.nsm_mount
+  - storage.nsm_mount_nvme
+
+{% elif virtio_devices %}
+
+include:
+  - storage.nsm_mount_virtio
 
 {% endif %}

salt/storage/nsm_mount_nvme.sls

@@ -22,8 +22,8 @@ storage_nsm_mount_logdir:
 # Install the NSM mount script
 storage_nsm_mount_script:
   file.managed:
-    - name: /usr/sbin/so-nsm-mount
-    - source: salt://storage/tools/sbin/so-nsm-mount
+    - name: /usr/sbin/so-nsm-mount-nvme
+    - source: salt://storage/tools/sbin/so-nsm-mount-nvme
     - mode: 755
     - user: root
     - group: root
@@ -34,7 +34,7 @@ storage_nsm_mount_script:
 # Execute the mount script if not already mounted
 storage_nsm_mount_execute:
   cmd.run:
-    - name: /usr/sbin/so-nsm-mount
+    - name: /usr/sbin/so-nsm-mount-nvme
     - unless: mountpoint -q /nsm
     - require:
       - file: storage_nsm_mount_script

salt/storage/nsm_mount_virtio.sls

@@ -0,0 +1,39 @@
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+# Install required packages
+storage_nsm_mount_virtio_packages:
+  pkg.installed:
+    - pkgs:
+      - xfsprogs
+
+# Ensure log directory exists
+storage_nsm_mount_virtio_logdir:
+  file.directory:
+    - name: /opt/so/log
+    - makedirs: True
+    - user: root
+    - group: root
+    - mode: 755
+
+# Install the NSM mount script
+storage_nsm_mount_virtio_script:
+  file.managed:
+    - name: /usr/sbin/so-nsm-mount-virtio
+    - source: salt://storage/tools/sbin/so-nsm-mount-virtio
+    - mode: 755
+    - user: root
+    - group: root
+    - require:
+      - pkg: storage_nsm_mount_virtio_packages
+      - file: storage_nsm_mount_virtio_logdir
+
+# Execute the mount script if not already mounted
+storage_nsm_mount_virtio_execute:
+  cmd.run:
+    - name: /usr/sbin/so-nsm-mount-virtio
+    - unless: mountpoint -q /nsm
+    - require:
+      - file: storage_nsm_mount_virtio_script

salt/storage/tools/sbin/so-nsm-mount-nvme

@@ -81,7 +81,7 @@
 
 set -e
 
-LOG_FILE="/opt/so/log/so-nsm-mount.log"
+LOG_FILE="/opt/so/log/so-nsm-mount-nvme"
 VG_NAME=""
 LV_NAME="nsm"
 MOUNT_POINT="/nsm"

salt/storage/tools/sbin/so-nsm-mount-virtio

@@ -0,0 +1,171 @@
+#!/bin/bash
+
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+# Usage:
+#     so-nsm-mount-virtio
+#
+# Options:
+#     None - script automatically configures /dev/vdb
+#
+# Examples:
+#     1. Configure and mount virtio-blk device:
+#         ```bash
+#         sudo so-nsm-mount-virtio
+#         ```
+#
+# Notes:
+#     - Requires root privileges
+#     - Mounts /dev/vdb as /nsm
+#     - Creates XFS filesystem if needed
+#     - Configures persistent mount via /etc/fstab
+#     - Safe to run multiple times
+#
+# Description:
+#     This script automates the configuration and mounting of virtio-blk devices
+#     as /nsm in Security Onion virtual machines. It performs these steps:
+#
+# Dependencies:
+#     - xfsprogs: Required for XFS filesystem operations
+#
+#     1. Safety Checks:
+#        - Verifies root privileges
+#        - Checks if /nsm is already mounted
+#        - Verifies /dev/vdb exists
+#
+#     2. Filesystem Creation:
+#        - Creates XFS filesystem on /dev/vdb if not already formatted
+#
+#     3. Mount Configuration:
+#        - Creates /nsm directory if needed
+#        - Adds entry to /etc/fstab for persistence
+#        - Mounts the filesystem as /nsm
+#
+# Exit Codes:
+#     0: Success conditions:
+#        - Device configured and mounted
+#        - Already properly mounted
+#     1: Error conditions:
+#        - Must be run as root
+#        - Device /dev/vdb not found
+#        - Filesystem creation failed
+#        - Mount operation failed
+#
+# Logging:
+#     - All operations logged to /opt/so/log/so-nsm-mount-virtio
+
+set -e
+
+LOG_FILE="/opt/so/log/so-nsm-mount-virtio"
+DEVICE="/dev/vdb"
+MOUNT_POINT="/nsm"
+
+# Function to log messages
+log() {
+    echo "$(date '+%Y-%m-%d %H:%M:%S') $1" | tee -a "$LOG_FILE"
+}
+
+# Function to log errors
+log_error() {
+    echo "$(date '+%Y-%m-%d %H:%M:%S') ERROR: $1" | tee -a "$LOG_FILE" >&2
+}
+
+# Function to check if running as root
+check_root() {
+    if [ "$EUID" -ne 0 ]; then
+        log_error "Must be run as root"
+        exit 1
+    fi
+}
+
+# Main execution
+main() {
+    log "=========================================="
+    log "Starting virtio-blk NSM mount process"
+    log "=========================================="
+    
+    # Check root privileges
+    check_root
+    
+    # Check if already mounted
+    if mountpoint -q "$MOUNT_POINT"; then
+        log "$MOUNT_POINT is already mounted"
+        log "=========================================="
+        exit 0
+    fi
+    
+    # Check if device exists
+    if [ ! -b "$DEVICE" ]; then
+        log_error "Device $DEVICE not found"
+        log "=========================================="
+        exit 1
+    fi
+    
+    log "Found device: $DEVICE"
+    
+    # Get device size
+    local size=$(lsblk -dbn -o SIZE "$DEVICE" 2>/dev/null | numfmt --to=iec)
+    log "Device size: $size"
+    
+    # Check if device has filesystem
+    if ! blkid "$DEVICE" | grep -q 'TYPE="xfs"'; then
+        log "Creating XFS filesystem on $DEVICE"
+        if ! mkfs.xfs -f "$DEVICE" 2>&1 | tee -a "$LOG_FILE"; then
+            log_error "Failed to create filesystem"
+            log "=========================================="
+            exit 1
+        fi
+        log "Filesystem created successfully"
+    else
+        log "Device already has XFS filesystem"
+    fi
+    
+    # Create mount point
+    if [ ! -d "$MOUNT_POINT" ]; then
+        log "Creating mount point $MOUNT_POINT"
+        mkdir -p "$MOUNT_POINT"
+    fi
+    
+    # Add to fstab if not present
+    if ! grep -q "$DEVICE.*$MOUNT_POINT" /etc/fstab; then
+        log "Adding entry to /etc/fstab"
+        echo "$DEVICE $MOUNT_POINT xfs defaults 0 0" >> /etc/fstab
+        log "Entry added to /etc/fstab"
+    else
+        log "Entry already exists in /etc/fstab"
+    fi
+    
+    # Mount the filesystem
+    log "Mounting $DEVICE to $MOUNT_POINT"
+    if mount "$MOUNT_POINT" 2>&1 | tee -a "$LOG_FILE"; then
+        log "Successfully mounted $DEVICE to $MOUNT_POINT"
+        
+        # Verify mount
+        if mountpoint -q "$MOUNT_POINT"; then
+            log "Mount verified successfully"
+            
+            # Display mount information
+            log "Mount details:"
+            df -h "$MOUNT_POINT" | tail -n 1 | tee -a "$LOG_FILE"
+        else
+            log_error "Mount verification failed"
+            log "=========================================="
+            exit 1
+        fi
+    else
+        log_error "Failed to mount $DEVICE"
+        log "=========================================="
+        exit 1
+    fi
+    
+    log "=========================================="
+    log "Virtio-blk NSM mount process completed successfully"
+    log "=========================================="
+    exit 0
+}
+
+# Run main function
+main

salt/zeek/policy/custom/filters/dns

@@ -0,0 +1,30 @@
+hook DNS::log_policy(rec: DNS::Info, id: Log::ID, filter: Log::Filter)
+    {
+       # Only put a single name per line otherwise there will be memory issues!
+       # If the query comes back blank don't log
+       if (!rec?$query)
+          break;
+
+       # If the query comes back with one of these don't log
+       if (rec?$query && /google.com$/ in rec$query)
+           break;
+
+       # If the query comes back with one of these don't log
+       if (rec?$query && /.apple.com$/ in rec$query)
+           break;
+
+       # Don't log reverse lookups
+       if (rec?$query && /.in-addr.arpa/ in to_lower(rec$query))
+           break;
+
+       # Don't log netbios lookups. This generates a cray amount of logs
+       if (rec?$qtype_name && /NB/ in rec$qtype_name)
+           break;
+    }
+
+event zeek_init()
+{
+    Log::remove_default_filter(DNS::LOG);
+    local filter: Log::Filter = [$name="dns-filter"];
+    Log::add_filter(DNS::LOG, filter);
+}

salt/zeek/policy/custom/filters/files

@@ -0,0 +1,13 @@
+hook Files::log_policy(rec: Files::Info, id: Log::ID, filter: Log::Filter)
+    {
+       # Turn off a specific mimetype
+           if (rec?$mime_type && ( /soap+xml/ | /json/ | /xml/ | /x509/ )in rec$mime_type)
+               break;
+    }
+
+event zeek_init()
+{
+    Log::remove_default_filter(Files::LOG);
+    local filter: Log::Filter = [$name="files-filter"];
+    Log::add_filter(Files::LOG, filter);
+}

salt/zeek/policy/custom/filters/httphost

@@ -0,0 +1,20 @@
+### HTTP filter by host entries by string #####
+ 
+module Filterhttp;
+ 
+export {
+    global remove_host_entries: set[string] = {"www.genevalab.com", "www.google.com"};
+ }
+ 
+hook HTTP::log_policy(rec: HTTP::Info, id: Log::ID, filter: Log::Filter)
+   {
+   # Remove HTTP host entries
+ if ( ! rec?$host || rec$host in remove_host_entries )
+       break;
+   }
+event zeek_init()
+{
+   Log::remove_default_filter(HTTP::LOG);
+   local filter: Log::Filter = [$name="http-filter"];
+   Log::add_filter(HTTP::LOG, filter);
+}

salt/zeek/policy/custom/filters/httpuri

@@ -0,0 +1,14 @@
+### HTTP filter by uri using pattern ####
+ 
+hook HTTP::log_policy(rec: HTTP::Info, id: Log::ID, filter: Log::Filter)
+   {
+   # Remove HTTP uri entries by regex
+ if ( rec?$uri && /^\/kratos\// in rec$uri )
+       break;
+   }
+event zeek_init()
+{
+   Log::remove_default_filter(HTTP::LOG);
+   local filter: Log::Filter = [$name="http-filter"];
+   Log::add_filter(HTTP::LOG, filter);
+}

salt/zeek/policy/custom/filters/ssl

@@ -0,0 +1,29 @@
+### Log filter by JA3S md5 hash:
+hook SSL::log_policy(rec: SSL::Info, id: Log::ID, filter: Log::Filter)
+    {
+       # SSL log filter Ja3s by md5           
+           if (rec?c$ssl$ja3s_cipher && ( /623de93db17d313345d7ea481e7443cf/ )in rec$c$ssl$ja3s_cipher)
+               break;
+    }
+
+event zeek_init()
+{
+    Log::remove_default_filter(SSL::LOG);
+    local filter: Log::Filter = [$name="ssl-filter"];
+    Log::add_filter(SSL::LOG, filter);
+}
+
+### Log filter by server name:
+hook SSL::log_policy(rec: SSL::Info, id: Log::ID, filter: Log::Filter)
+  {
+    # SSL log filter by server name
+    if (rec?$server_name && ( /api.github.com$/ ) in rec$server_name)
+       break;
+  }
+
+event zeek_init()
+{
+   Log::remove_default_filter(SSL::LOG);
+   local filter: Log::Filter = [$name="ssl-filter"];
+   Log::add_filter(SSL::LOG, filter);
+}

salt/zeek/policy/custom/filters/tunnel

@@ -0,0 +1,17 @@
+global tunnel_subnet: set[subnet]={
+									
+	10.19.0.0/24
+			
+};
+
+hook Tunnel::log_policy(rec: Tunnel::Info, id: Log::ID, Filter: Log::Filter)
+	{
+	if (rec$id$orig_h in tunnel_subnet || rec$id$resp_h in tunnel_subnet)
+		break;
+	}
+event zeek_init()
+{
+    Log::remove_default_filter(Tunnel::LOG);
+    local filter: Log::Filter = [$name="tunnel-filter"];
+    Log::add_filter(Tunnel::LOG, filter);
+}

salt/zeek/soc_zeek.yaml

@@ -61,6 +61,48 @@ zeek:
           global: True
           advanced: True
           duplicates: True
+        dns:
+          description: DNS Filter for Zeek. This is an advanced setting and will take further action to enable.
+          helpLink: zeek.html
+          file: True
+          global: True
+          advanced: True
+          duplicates: True
+        files:
+          description: Files Filter for Zeek. This is an advanced setting and will take further action to enable.
+          helpLink: zeek.html
+          file: True
+          global: True
+          advanced: True
+          duplicates: True
+        httphost:
+          description: HTTP Hosts Filter for Zeek. This is an advanced setting and will take further action to enable.
+          helpLink: zeek.html
+          file: True
+          global: True
+          advanced: True
+          duplicates: True
+        httpuri:
+          description: HTTP URI Filter for Zeek. This is an advanced setting and will take further action to enable.
+          helpLink: zeek.html
+          file: True
+          global: True
+          advanced: True
+          duplicates: True
+        ssl:
+          description: SSL Filter for Zeek. This is an advanced setting and will take further action to enable.
+          helpLink: zeek.html
+          file: True
+          global: True
+          advanced: True
+          duplicates: True
+        tunnel:
+          description: Tunnel Filter for Zeek. This is an advanced setting and will take further action to enable.
+          helpLink: zeek.html
+          file: True
+          global: True
+          advanced: True
+          duplicates: True
   file_extraction:
     description: Contains a list of file or MIME types Zeek will extract from the network streams. Values must adhere to the following format - {"MIME_TYPE":"FILE_EXTENSION"}
     forcedType: "[]{}"

setup/so-functions

@@ -541,8 +541,15 @@ configure_minion() {
 		"log_file: /opt/so/log/salt/minion"\
 		"#startup_states: highstate" >> "$minion_config"
 
-	info "Running: salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar='{"host": {"mainint": "$MNIC"}}'"
-	salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar="{'host': {'mainint': $MNIC}}"
+	# At the time the so-managerhype node does not yet have the bridge configured.
+	# The so-hypervisor node doesn't either, but it doesn't cause issues here.
+	local usebr0=false
+	if [ "$minion_type" == 'hypervisor' ]; then
+    	usebr0=true
+	fi
+	local pillar_json="{\"host\": {\"mainint\": \"$MNIC\"}, \"usebr0\": $usebr0}"
+	info "Running: salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar='$pillar_json'"
+	salt-call state.apply salt.mine_functions --local --file-root=../salt/ -l info pillar="$pillar_json"
 
 	{
 		logCmd "systemctl enable salt-minion";
@@ -1194,10 +1201,7 @@ hypervisor_local_states() {
         info "Running libvirt states for hypervisor"
         logCmd "salt-call state.apply libvirt.64962 --local --file-root=../salt/ -l info queue=True"
         info "Setting up bridge for $MNIC"
-		    salt-call state.apply libvirt.bridge --local --file-root=../salt/ -l info pillar='{"host": {"mainint": "'$MNIC'"}}' queue=True
-		    if [ $is_managerhype ]; then
-			    logCmd "salt-call state.apply salt.minion queue=True"
-		    fi
+		salt-call state.apply libvirt.bridge --local --file-root=../salt/ -l info pillar='{"host": {"mainint": "'$MNIC'"}}' queue=True
     fi
 }
 
@@ -2301,7 +2305,7 @@ set_redirect() {
 
 set_timezone() {
 
-	logCmd "timedatectl set-timezone Etc/UTC"
+	timedatectl set-timezone Etc/UTC
 
 }
 

setup/so-setup

@@ -762,6 +762,7 @@ if ! [[ -f $install_opt_file ]]; then
 		fi
 		logCmd "salt-call state.apply common.packages"
 		logCmd "salt-call state.apply common"
+		hypervisor_local_states
 		# this will apply the salt.minion state first since salt.master includes salt.minion
 		logCmd "salt-call state.apply salt.master"
 		# wait here until we get a response from the salt-master since it may have just restarted
@@ -826,7 +827,6 @@ if ! [[ -f $install_opt_file ]]; then
 		checkin_at_boot
 		set_initial_firewall_access
 		logCmd "salt-call schedule.enable -linfo --local"
-		hypervisor_local_states
 		verify_setup
 	else
 		touch /root/accept_changes

setup/so-verify

@@ -68,6 +68,7 @@ log_has_errors() {
         grep -vE "Command failed with exit code" | \
         grep -vE "Running scope as unit" | \
         grep -vE "securityonion-resources/sigma/stable" | \
+        grep -vE "remove_failed_vm.sls" | \
         grep -vE "log-.*-pipeline_failed_attempts" &> "$error_log"
     
     if [[ $? -eq 0 ]]; then