Merge pull request #15241 from Security-Onion-Solutions/reyesj2/advilm

FEATURE: Advanced ILM actions via SOC UI

.github/DISCUSSION_TEMPLATE/2-4.yml

@@ -30,6 +30,9 @@ body:
         - 2.4.150
         - 2.4.160
         - 2.4.170
+        - 2.4.180
+        - 2.4.190
+        - 2.4.200
         - Other (please provide detail below)
     validations:
       required: true

.github/workflows/pythontest.yml

@@ -4,7 +4,7 @@ on:
   pull_request:
     paths:
       - "salt/sensoroni/files/analyzers/**"
-      - "salt/manager/tools/sbin"
+      - "salt/manager/tools/sbin/**"
 
 jobs:
   build:

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 2.4.170-20250812 ISO image released on 2025/08/12
+### 2.4.190-20251024 ISO image released on 2025/10/24
 
 
 ### Download and Verify
 
-2.4.170-20250812 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-2.4.170-20250812.iso
+2.4.190-20251024 ISO image:  
+https://download.securityonion.net/file/securityonion/securityonion-2.4.190-20251024.iso
  
-MD5: 50ECAAD05736298452DECEAE074FA773  
-SHA1: 1B1EB520DE61ECC4BF34E512DAFE307317D7666A  
-SHA256: 87D176A48A58BAD1C2D57196F999BED23DE9B526226E3754F0C166C866CCDC1A  
+MD5: 25358481FB876226499C011FC0710358  
+SHA1: 0B26173C0CE136F2CA40A15046D1DFB78BCA1165  
+SHA256: 4FD9F62EDA672408828B3C0C446FE5EA9FF3C4EE8488A7AB1101544A3C487872  
 
 Signature for ISO image:  
-https://github.com/Security-Onion-Solutions/securityonion/raw/2.4/main/sigs/securityonion-2.4.170-20250812.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-2.4.170-20250812.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-2.4.170-20250812.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-2.4.170-20250812.iso.sig securityonion-2.4.170-20250812.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 Fri 08 Aug 2025 06:24:56 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 @@
-2.4.170
+2.4.200

pillar/top.sls

@@ -262,6 +262,9 @@ base:
     - minions.adv_{{ grains.id }}
     - kafka.nodes
     - kafka.soc_kafka
+    - stig.soc_stig
+    - elasticfleet.soc_elasticfleet
+    - elasticfleet.adv_elasticfleet
 
   '*_import':
     - node_data.ips
@@ -319,10 +322,12 @@ base:
     - elasticfleet.adv_elasticfleet
     - minions.{{ grains.id }}
     - minions.adv_{{ grains.id }}
+    - stig.soc_stig
 
   '*_hypervisor':
     - minions.{{ grains.id }}
     - minions.adv_{{ grains.id }}
+    - stig.soc_stig
 
   '*_desktop':
     - minions.{{ grains.id }}

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/_runners/setup_hypervisor.py

@@ -172,7 +172,15 @@ MANAGER_HOSTNAME = socket.gethostname()
 
 def _download_image():
     """
-    Download and validate the Oracle Linux KVM image.
+    Download and validate the Oracle Linux KVM image with retry logic and progress monitoring.
+    
+    Features:
+    - Detects stalled downloads (no progress for 30 seconds)
+    - Retries up to 3 times on failure
+    - Connection timeout of 30 seconds
+    - Read timeout of 60 seconds
+    - Cleans up partial downloads on failure
+    
     Returns:
         bool: True if successful or file exists with valid checksum, False on error
     """
@@ -185,45 +193,107 @@ def _download_image():
             os.unlink(IMAGE_PATH)
     
     log.info("Starting image download process")
+    
+    # Retry configuration
+    max_attempts = 3
+    retry_delay = 5  # seconds to wait between retry attempts
+    stall_timeout = 30  # seconds without progress before considering download stalled
+    connection_timeout = 30  # seconds to establish connection
+    read_timeout = 60  # seconds to wait for data chunks
+    
+    for attempt in range(1, max_attempts + 1):
+        log.info("Download attempt %d of %d", attempt, max_attempts)
+        
+        try:
+            # Download file with timeouts
+            log.info("Downloading Oracle Linux KVM image from %s to %s", IMAGE_URL, IMAGE_PATH)
+            response = requests.get(
+                IMAGE_URL,
+                stream=True,
+                timeout=(connection_timeout, read_timeout)
+            )
+            response.raise_for_status()
 
-    try:
-        # Download file
-        log.info("Downloading Oracle Linux KVM image from %s to %s", IMAGE_URL, IMAGE_PATH)
-        response = requests.get(IMAGE_URL, stream=True)
-        response.raise_for_status()
+            # Get total file size for progress tracking
+            total_size = int(response.headers.get('content-length', 0))
+            downloaded_size = 0
+            last_log_time = 0
+            last_progress_time = time.time()
+            last_downloaded_size = 0
 
-        # Get total file size for progress tracking
-        total_size = int(response.headers.get('content-length', 0))
-        downloaded_size = 0
-        last_log_time = 0
+            # Save file with progress logging and stall detection
+            with salt.utils.files.fopen(IMAGE_PATH, 'wb') as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    if chunk:  # filter out keep-alive new chunks
+                        f.write(chunk)
+                        downloaded_size += len(chunk)
+                        current_time = time.time()
+                        
+                        # Check for stalled download
+                        if downloaded_size > last_downloaded_size:
+                            # Progress made, reset stall timer
+                            last_progress_time = current_time
+                            last_downloaded_size = downloaded_size
+                        elif current_time - last_progress_time > stall_timeout:
+                            # No progress for stall_timeout seconds
+                            raise Exception(
+                                f"Download stalled: no progress for {stall_timeout} seconds "
+                                f"at {downloaded_size}/{total_size} bytes"
+                            )
+                        
+                        # Log progress every second
+                        if current_time - last_log_time >= 1:
+                            progress = (downloaded_size / total_size) * 100 if total_size > 0 else 0
+                            log.info("Progress - %.1f%% (%d/%d bytes)",
+                                    progress, downloaded_size, total_size)
+                            last_log_time = current_time
 
-        # Save file with progress logging
-        with salt.utils.files.fopen(IMAGE_PATH, 'wb') as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-                downloaded_size += len(chunk)
+            # Validate downloaded file
+            log.info("Download complete, validating checksum...")
+            if not _validate_image_checksum(IMAGE_PATH, IMAGE_SHA256):
+                log.error("Checksum validation failed on attempt %d", attempt)
+                os.unlink(IMAGE_PATH)
+                if attempt < max_attempts:
+                    log.info("Will retry download...")
+                    continue
+                else:
+                    log.error("All download attempts failed due to checksum mismatch")
+                    return False
+
+            log.info("Successfully downloaded and validated Oracle Linux KVM image")
+            return True
+
+        except requests.exceptions.Timeout as e:
+            log.error("Download attempt %d failed: Timeout - %s", attempt, str(e))
+            if os.path.exists(IMAGE_PATH):
+                os.unlink(IMAGE_PATH)
+            if attempt < max_attempts:
+                log.info("Will retry download in %d seconds...", retry_delay)
+                time.sleep(retry_delay)
+            else:
+                log.error("All download attempts failed due to timeout")
                 
-                # Log progress every second
-                current_time = time.time()
-                if current_time - last_log_time >= 1:
-                    progress = (downloaded_size / total_size) * 100 if total_size > 0 else 0
-                    log.info("Progress - %.1f%% (%d/%d bytes)", 
-                            progress, downloaded_size, total_size)
-                    last_log_time = current_time
-
-        # Validate downloaded file
-        if not _validate_image_checksum(IMAGE_PATH, IMAGE_SHA256):
-            os.unlink(IMAGE_PATH)
-            return False
-
-        log.info("Successfully downloaded and validated Oracle Linux KVM image")
-        return True
-
-    except Exception as e:
-        log.error("Error downloading hypervisor image: %s", str(e))
-        if os.path.exists(IMAGE_PATH):
-            os.unlink(IMAGE_PATH)
-        return False
+        except requests.exceptions.RequestException as e:
+            log.error("Download attempt %d failed: Network error - %s", attempt, str(e))
+            if os.path.exists(IMAGE_PATH):
+                os.unlink(IMAGE_PATH)
+            if attempt < max_attempts:
+                log.info("Will retry download in %d seconds...", retry_delay)
+                time.sleep(retry_delay)
+            else:
+                log.error("All download attempts failed due to network errors")
+                
+        except Exception as e:
+            log.error("Download attempt %d failed: %s", attempt, str(e))
+            if os.path.exists(IMAGE_PATH):
+                os.unlink(IMAGE_PATH)
+            if attempt < max_attempts:
+                log.info("Will retry download in %d seconds...", retry_delay)
+                time.sleep(retry_delay)
+            else:
+                log.error("All download attempts failed")
+    
+    return False
 
 def _check_ssh_keys_exist():
     """
@@ -419,25 +489,28 @@ def _ensure_hypervisor_host_dir(minion_id: str = None):
         log.error(f"Error creating hypervisor host directory: {str(e)}")
         return False
 
-def _apply_dyanno_hypervisor_state():
+def _apply_dyanno_hypervisor_state(status):
     """
     Apply the soc.dyanno.hypervisor state on the salt master.
     
     This function applies the soc.dyanno.hypervisor state on the salt master
     to update the hypervisor annotation and ensure all hypervisor host directories exist.
     
+    Args:
+        status: Status passed to the hypervisor annotation state
+    
     Returns:
         bool: True if state was applied successfully, False otherwise
     """
     try:
-        log.info("Applying soc.dyanno.hypervisor state on salt master")
+        log.info(f"Applying soc.dyanno.hypervisor state on salt master with status: {status}")
         
         # Initialize the LocalClient
         local = salt.client.LocalClient()
         
         # Target the salt master to apply the soc.dyanno.hypervisor state
         target = MANAGER_HOSTNAME + '_*'
-        state_result = local.cmd(target, 'state.apply', ['soc.dyanno.hypervisor', "pillar={'baseDomain': {'status': 'PreInit'}}", 'concurrent=True'], tgt_type='glob')
+        state_result = local.cmd(target, 'state.apply', ['soc.dyanno.hypervisor', f"pillar={{'baseDomain': {{'status': '{status}'}}}}", 'concurrent=True'], tgt_type='glob')
         log.debug(f"state_result: {state_result}")
         # Check if state was applied successfully
         if state_result:
@@ -454,17 +527,17 @@ def _apply_dyanno_hypervisor_state():
                         success = False
             
             if success:
-                log.info("Successfully applied soc.dyanno.hypervisor state")
+                log.info(f"Successfully applied soc.dyanno.hypervisor state with status: {status}")
                 return True
             else:
-                log.error("Failed to apply soc.dyanno.hypervisor state")
+                log.error(f"Failed to apply soc.dyanno.hypervisor state with status: {status}")
                 return False
         else:
-            log.error("No response from salt master when applying soc.dyanno.hypervisor state")
+            log.error(f"No response from salt master when applying soc.dyanno.hypervisor state with status: {status}")
             return False
             
     except Exception as e:
-        log.error(f"Error applying soc.dyanno.hypervisor state: {str(e)}")
+        log.error(f"Error applying soc.dyanno.hypervisor state with status: {status}: {str(e)}")
         return False
 
 def _apply_cloud_config_state():
@@ -598,11 +671,6 @@ def setup_environment(vm_name: str = 'sool9', disk_size: str = '220G', minion_id
         log.warning("Failed to apply salt.cloud.config state, continuing with setup")
         # We don't return an error here as we want to continue with the setup process
 
-    # Apply the soc.dyanno.hypervisor state on the salt master
-    if not _apply_dyanno_hypervisor_state():
-        log.warning("Failed to apply soc.dyanno.hypervisor state, continuing with setup")
-        # We don't return an error here as we want to continue with the setup process
-
     log.info("Starting setup_environment in setup_hypervisor runner")
     
     # Check if environment is already set up
@@ -616,9 +684,12 @@ def setup_environment(vm_name: str = 'sool9', disk_size: str = '220G', minion_id
     
     # Handle image setup if needed
     if not image_valid:
+        _apply_dyanno_hypervisor_state('ImageDownloadStart')
         log.info("Starting image download/validation process")
         if not _download_image():
             log.error("Image download failed")
+            # Update hypervisor annotation with failure status
+            _apply_dyanno_hypervisor_state('ImageDownloadFailed')
             return {
                 'success': False,
                 'error': 'Image download failed',
@@ -631,6 +702,8 @@ def setup_environment(vm_name: str = 'sool9', disk_size: str = '220G', minion_id
         log.info("Setting up SSH keys")
         if not _setup_ssh_keys():
             log.error("SSH key setup failed")
+            # Update hypervisor annotation with failure status
+            _apply_dyanno_hypervisor_state('SSHKeySetupFailed')
             return {
                 'success': False,
                 'error': 'SSH key setup failed',
@@ -655,6 +728,12 @@ def setup_environment(vm_name: str = 'sool9', disk_size: str = '220G', minion_id
     success = vm_result.get('success', False)
     log.info("Setup environment completed with status: %s", "SUCCESS" if success else "FAILED")
     
+    # Update hypervisor annotation with success status
+    if success:
+        _apply_dyanno_hypervisor_state('PreInit')
+    else:
+        _apply_dyanno_hypervisor_state('SetupFailed')
+    
     # If setup was successful and we have a minion_id, run highstate
     if success and minion_id:
         log.info("Running highstate on hypervisor %s", minion_id)

salt/allowed_states.map.jinja

@@ -143,6 +143,7 @@
         ),
         'so-fleet': (
             ssl_states +
+            stig_states +
             ['logstash', 'nginx', 'healthcheck', 'elasticfleet']
         ),
         'so-receiver': (

salt/bpf/pcap.map.jinja

@@ -1,4 +1,7 @@
 {% from 'vars/globals.map.jinja' import GLOBALS %}
+{% set PCAP_BPF_STATUS = 0  %}
+{% set STENO_BPF_COMPILED = "" %}
+
 {% if GLOBALS.pcap_engine == "TRANSITION" %}
 {%   set PCAPBPF = ["ip and host 255.255.255.1 and port 1"] %}
 {% else %}
@@ -8,3 +11,11 @@
 {{   MACROS.remove_comments(BPFMERGED, 'pcap') }}
 {%   set PCAPBPF = BPFMERGED.pcap %}
 {% endif %}
+
+{% if PCAPBPF %}
+   {% set PCAP_BPF_CALC = salt['cmd.run_all']('/usr/sbin/so-bpf-compile ' ~ GLOBALS.sensor.interface ~ ' ' ~ PCAPBPF|join(" "), cwd='/root') %}
+   {% if PCAP_BPF_CALC['retcode'] == 0 %}
+      {% set PCAP_BPF_STATUS = 1 %}
+      {% set STENO_BPF_COMPILED =  ",\\\"--filter=" + PCAP_BPF_CALC['stdout'] + "\\\""  %}
+   {% endif %}
+{% endif %}

salt/bpf/soc_bpf.yaml

@@ -1,11 +1,11 @@
 bpf:
   pcap:
-    description: List of BPF filters to apply to Stenographer.
+    description: List of BPF filters to apply to the PCAP engine.
     multiline: True
     forcedType: "[]string"
     helpLink: bpf.html
   suricata:
-    description: List of BPF filters to apply to Suricata.
+    description: List of BPF filters to apply to Suricata. This will apply to alerts and, if enabled, to metadata and PCAP logs generated by Suricata.
     multiline: True
     forcedType: "[]string"
     helpLink: bpf.html

salt/bpf/suricata.map.jinja

@@ -1,7 +1,16 @@
+{% from 'vars/globals.map.jinja' import GLOBALS %}
 {% import_yaml 'bpf/defaults.yaml' as BPFDEFAULTS %}
 {% set BPFMERGED = salt['pillar.get']('bpf', BPFDEFAULTS.bpf, merge=True) %}
+{% set SURICATA_BPF_STATUS = 0 %}
 {% import 'bpf/macros.jinja' as MACROS %}
 
 {{ MACROS.remove_comments(BPFMERGED, 'suricata') }}
 
 {% set SURICATABPF = BPFMERGED.suricata %}
+
+{% if SURICATABPF %}
+   {% set SURICATA_BPF_CALC = salt['cmd.run_all']('/usr/sbin/so-bpf-compile ' ~ GLOBALS.sensor.interface ~ ' ' ~ SURICATABPF|join(" "), cwd='/root') %}
+   {% if SURICATA_BPF_CALC['retcode'] == 0 %}
+      {% set SURICATA_BPF_STATUS = 1 %}
+   {% endif %}
+{% endif %}

salt/bpf/zeek.map.jinja

@@ -1,7 +1,16 @@
+{% from 'vars/globals.map.jinja' import GLOBALS %}
 {% import_yaml 'bpf/defaults.yaml' as BPFDEFAULTS %}
 {% set BPFMERGED = salt['pillar.get']('bpf', BPFDEFAULTS.bpf, merge=True) %}
+{% set ZEEK_BPF_STATUS = 0 %}
 {% import 'bpf/macros.jinja' as MACROS %}
 
 {{ MACROS.remove_comments(BPFMERGED, 'zeek') }}
 
 {% set ZEEKBPF = BPFMERGED.zeek %}
+
+{% if ZEEKBPF %}
+   {% set ZEEK_BPF_CALC = salt['cmd.run_all']('/usr/sbin/so-bpf-compile ' ~ GLOBALS.sensor.interface ~ ' ' ~ ZEEKBPF|join(" "), cwd='/root') %}
+   {% if ZEEK_BPF_CALC['retcode'] == 0 %}
+      {% set ZEEK_BPF_STATUS = 1 %}
+   {% endif %}
+{% endif %}

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-bpf-compile

@@ -29,9 +29,26 @@ fi
 
 interface="$1"
 shift
-tcpdump -i $interface -ddd $@ | tail -n+2 |
-while read line; do
+
+# Capture tcpdump output and exit code
+tcpdump_output=$(tcpdump -i "$interface" -ddd "$@" 2>&1)
+tcpdump_exit=$?
+
+if [ $tcpdump_exit -ne 0 ]; then
+  echo "$tcpdump_output" >&2
+  exit $tcpdump_exit
+fi
+
+# Process the output, skipping the first line
+echo "$tcpdump_output" | tail -n+2 | while read -r line; do
   cols=( $line )
-  printf "%04x%02x%02x%08x" ${cols[0]} ${cols[1]} ${cols[2]} ${cols[3]}
+  printf "%04x%02x%02x%08x" "${cols[0]}" "${cols[1]}" "${cols[2]}" "${cols[3]}"
 done
+
+# Check if the pipeline succeeded
+if [ "${PIPESTATUS[0]}" -ne 0 ]; then
+  exit 1
+fi
+
 echo ""
+exit 0

salt/common/tools/sbin/so-common

@@ -220,12 +220,22 @@ compare_es_versions() {
 }
 
 copy_new_files() {
+  # Define files to exclude from deletion (relative to their respective base directories)
+  local EXCLUDE_FILES=(
+    "salt/hypervisor/soc_hypervisor.yaml"
+  )
+  
+  # Build rsync exclude arguments
+  local EXCLUDE_ARGS=()
+  for file in "${EXCLUDE_FILES[@]}"; do
+    EXCLUDE_ARGS+=(--exclude="$file")
+  done
+  
   # Copy new files over to the salt dir
   cd $UPDATE_DIR
-  rsync -a salt $DEFAULT_SALT_DIR/ --delete
-  rsync -a pillar $DEFAULT_SALT_DIR/ --delete
+  rsync -a salt $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
+  rsync -a pillar $DEFAULT_SALT_DIR/ --delete "${EXCLUDE_ARGS[@]}"
   chown -R socore:socore $DEFAULT_SALT_DIR/
-  chmod 755 $DEFAULT_SALT_DIR/pillar/firewall/addfirewall.sh
   cd /tmp
 }
 
@@ -385,7 +395,7 @@ is_manager_node() {
 }
 
 is_sensor_node() {
-	# Check to see if this is a sensor (forward) node
+	# Check to see if this is a sensor node
 	is_single_node_grid && return 0
 	grep "role: so-" /etc/salt/grains | grep -E "sensor|heavynode" &> /dev/null
 }
@@ -441,8 +451,7 @@ 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-image-common

@@ -62,8 +62,6 @@ container_list() {
       "so-soc"
       "so-steno"
       "so-strelka-backend"
-      "so-strelka-filestream"
-      "so-strelka-frontend"
       "so-strelka-manager"
       "so-suricata"
       "so-telegraf"

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/artifact_registry.sls

@@ -9,3 +9,6 @@ fleetartifactdir:
     - user: 947
     - group: 939
     - makedirs: True
+    - recurse:
+      - user
+      - group

salt/elasticfleet/config.map.jinja

@@ -0,0 +1,34 @@
+{# 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 'elasticfleet/map.jinja' import ELASTICFLEETMERGED %}
+
+{# advanced config_yaml options for elasticfleet logstash output #}
+{% set ADV_OUTPUT_LOGSTASH_RAW = ELASTICFLEETMERGED.config.outputs.logstash %}
+{% set ADV_OUTPUT_LOGSTASH = {} %}
+{% for k, v in ADV_OUTPUT_LOGSTASH_RAW.items() %}
+{%   if v != "" and v is not none %}
+{%     if k == 'queue_mem_events' %}
+{#       rename queue_mem_events queue.mem.events #}
+{%       do ADV_OUTPUT_LOGSTASH.update({'queue.mem.events':v}) %}
+{%     elif k == 'loadbalance' %}
+{%       if v %}
+{#         only include loadbalance config when its True #}
+{%         do ADV_OUTPUT_LOGSTASH.update({k:v}) %}
+{%       endif %}
+{%     else %}
+{%       do ADV_OUTPUT_LOGSTASH.update({k:v}) %}
+{%     endif %}
+{%   endif %}
+{% endfor %}
+
+{% set LOGSTASH_CONFIG_YAML_RAW = [] %}
+{% if ADV_OUTPUT_LOGSTASH %}
+{%   for k, v in ADV_OUTPUT_LOGSTASH.items() %}
+{%     do LOGSTASH_CONFIG_YAML_RAW.append(k ~ ': ' ~ v) %}
+{%   endfor %}
+{% endif %}
+
+{% set LOGSTASH_CONFIG_YAML = LOGSTASH_CONFIG_YAML_RAW | join('\\n') if LOGSTASH_CONFIG_YAML_RAW else '' %}

salt/elasticfleet/config.sls

@@ -9,6 +9,9 @@
 {% from 'elasticfleet/map.jinja' import ELASTICFLEETMERGED %}
 {% set node_data = salt['pillar.get']('node_data') %}
 
+include:
+  - elasticfleet.artifact_registry
+
 # Add EA Group
 elasticfleetgroup:
   group.present:

salt/elasticfleet/defaults.yaml

@@ -10,12 +10,19 @@ elasticfleet:
       grid_enrollment: ''
     defend_filters:
       enable_auto_configuration: False
+    outputs:
+      logstash:
+        bulk_max_size: ''
+        worker: ''
+        queue_mem_events: ''
+        timeout: ''
+        loadbalance: False
+        compression_level: ''
     subscription_integrations: False
     auto_upgrade_integrations: False
   logging:
     zeek:
       excluded:
-        - analyzer
         - broker
         - capture_loss
         - cluster
@@ -38,6 +45,7 @@ elasticfleet:
     - elasticsearch
     - endpoint
     - fleet_server
+    - filestream
     - http_endpoint
     - httpjson
     - log

salt/elasticfleet/enabled.sls

@@ -32,6 +32,17 @@ so-elastic-fleet-auto-configure-logstash-outputs:
     - retry:
         attempts: 4
         interval: 30
+
+{# Separate from above in order to catch elasticfleet-logstash.crt changes and force update to fleet output policy #}
+so-elastic-fleet-auto-configure-logstash-outputs-force:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-outputs-update --certs
+    - retry:
+        attempts: 4
+        interval: 30
+    - onchanges:
+        - x509: etc_elasticfleet_logstash_crt
+        - x509: elasticfleet_kafka_crt
 {% endif %}
 
 # If enabled, automatically update Fleet Server URLs & ES Connection
@@ -67,6 +78,8 @@ so-elastic-fleet-auto-configure-artifact-urls:
 elasticagent_syncartifacts:
   file.recurse:
     - name: /nsm/elastic-fleet/artifacts/beats
+    - user: 947
+    - group: 947
     - source: salt://beats
 {% endif %}
 
@@ -133,12 +146,18 @@ 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:
@@ -150,7 +169,11 @@ 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/elastic-agent-monitor.json

@@ -0,0 +1,48 @@
+{
+  "package": {
+    "name": "filestream",
+    "version": ""
+  },
+  "name": "agent-monitor",
+  "namespace": "",
+  "description": "",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "output_id": null,
+  "vars": {},
+  "inputs": {
+    "filestream-filestream": {
+      "enabled": true,
+      "streams": {
+        "filestream.generic": {
+          "enabled": true,
+          "vars": {
+            "paths": [
+              "/opt/so/log/agents/agent-monitor.log"
+            ],
+            "data_stream.dataset": "agentmonitor",
+            "pipeline": "elasticagent.monitor",
+            "parsers": "",
+            "exclude_files": [
+              "\\.gz$"
+            ],
+            "include_files": [],
+            "processors": "- decode_json_fields:\n    fields: [\"message\"]\n    target: \"\"\n- add_fields:\n    target: event\n    fields:\n        module: gridmetrics",
+            "tags": [],
+            "recursive_glob": true,
+            "ignore_older": "72h",
+            "clean_inactive": -1,
+            "harvester_limit": 0,
+            "fingerprint": true,
+            "fingerprint_offset": 0,
+            "fingerprint_length": 64,
+            "file_identity_native": false,
+            "exclude_lines": [],
+            "include_lines": []
+          }
+        }
+      }
+    }
+  }
+}

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-2.3.3\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-3.1.0\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-2.3.3\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-2.3.3\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-3.1.0\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/install_agent_grid.sls

@@ -2,26 +2,30 @@
 # or more contributor license agreements. Licensed under the Elastic License 2.0; you may not use
 # this file except in compliance with the Elastic License 2.0.
 
-{%- set GRIDNODETOKENGENERAL = salt['pillar.get']('global:fleet_grid_enrollment_token_general') -%}
-{%- set GRIDNODETOKENHEAVY = salt['pillar.get']('global:fleet_grid_enrollment_token_heavy') -%}
+{% set GRIDNODETOKEN = salt['pillar.get']('global:fleet_grid_enrollment_token_general') -%}
+{% if grains.role == 'so-heavynode' %}
+{%   set GRIDNODETOKEN = salt['pillar.get']('global:fleet_grid_enrollment_token_heavy') -%}
+{% endif %}
 
 {% set AGENT_STATUS = salt['service.available']('elastic-agent') %}
 {% if not AGENT_STATUS  %}
 
-{% if grains.role not in ['so-heavynode'] %}
-run_installer:
-  cmd.script:
-    - name: salt://elasticfleet/files/so_agent-installers/so-elastic-agent_linux_amd64
-    - cwd: /opt/so
-    - args: -token={{ GRIDNODETOKENGENERAL }}
-    - retry: True
-{% else %} 
-run_installer:
-  cmd.script:
-    - name: salt://elasticfleet/files/so_agent-installers/so-elastic-agent_linux_amd64
-    - cwd: /opt/so
-    - args: -token={{ GRIDNODETOKENHEAVY }}
-    - retry: True
-{% endif %}  
+pull_agent_installer:
+  file.managed:
+    - name: /opt/so/so-elastic-agent_linux_amd64
+    - source: salt://elasticfleet/files/so_agent-installers/so-elastic-agent_linux_amd64
+    - mode: 755
+    - makedirs: True
 
+run_installer:
+  cmd.run:
+    - name: ./so-elastic-agent_linux_amd64 -token={{ GRIDNODETOKEN }}
+    - cwd: /opt/so
+    - retry:
+        attempts: 3
+        interval: 20
+
+cleanup_agent_installer:
+  file.absent:
+    - name: /opt/so/so-elastic-agent_linux_amd64
 {% endif %}

salt/elasticfleet/integration-defaults.map.jinja

@@ -121,6 +121,9 @@
                  "phases": {
                    "cold": {
                      "actions": {
+                        "allocate":{
+                          "number_of_replicas": ""
+                        },
                        "set_priority": {"priority": 0}
                      },
                      "min_age": "60d"
@@ -137,12 +140,31 @@
                          "max_age": "30d",
                          "max_primary_shard_size": "50gb"
                        },
+                       "forcemerge":{
+                         "max_num_segments": ""
+                       },
+                       "shrink":{
+                         "max_primary_shard_size": "",
+                         "method": "COUNT",
+                         "number_of_shards": ""
+                       },
                        "set_priority": {"priority": 100}
                       },
                       "min_age": "0ms"
                    },
                    "warm": {
                      "actions": {
+                        "allocate": {
+                          "number_of_replicas": ""
+                        },
+                        "forcemerge": {
+                          "max_num_segments": ""
+                        },
+                        "shrink":{
+                          "max_primary_shard_size": "",
+                          "method": "COUNT",
+                          "number_of_shards": ""
+                        },
                        "set_priority": {"priority": 50}
                      },
                      "min_age": "30d"

salt/elasticfleet/soc_elasticfleet.yaml

@@ -50,6 +50,46 @@ elasticfleet:
       global: True
       forcedType: bool
       helpLink: elastic-fleet.html
+    outputs:
+      logstash:
+        bulk_max_size:
+          description: The maximum number of events to bulk in a single Logstash request.
+          global: True
+          forcedType: int
+          advanced: True
+          helpLink: elastic-fleet.html
+        worker:
+          description: The number of workers per configured host publishing events.
+          global: True
+          forcedType: int
+          advanced: true
+          helpLink: elastic-fleet.html
+        queue_mem_events:
+          title: queued events
+          description: The number of events the queue can store. This value should be evenly divisible by the smaller of 'bulk_max_size' to avoid sending partial batches to the output.
+          global: True
+          forcedType: int
+          advanced: True
+          helpLink: elastic-fleet.html
+        timeout:
+          description: The number of seconds to wait for responses from the Logstash server before timing out. Eg 30s
+          regex: ^[0-9]+s$
+          advanced: True
+          global: True
+          helpLink: elastic-fleet.html
+        loadbalance:
+          description: If true and multiple Logstash hosts are configured, the output plugin load balances published events onto all Logstash hosts. If false, the output plugin sends all events to one host (determined at random) and switches to another host if the selected one becomes unresponsive.
+          forcedType: bool
+          advanced: True
+          global: True
+          helpLink: elastic-fleet.html
+        compression_level:
+          description: The gzip compression level. The compression level must be in the range of 1 (best speed) to 9 (best compression).
+          regex: ^[1-9]$
+          forcedType: int
+          advanced: True
+          global: True
+          helpLink: elastic-fleet.html
     server:
       custom_fqdn:
         description: Custom FQDN for Agents to connect to. One per line.

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

@@ -3,11 +3,36 @@
 # 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; you may not use
 # this file except in compliance with the Elastic License 2.0.
-{% from 'vars/globals.map.jinja' import GLOBALS %}
-{% from 'elasticfleet/map.jinja' import ELASTICFLEETMERGED %}
+{%- from 'vars/globals.map.jinja' import GLOBALS %}
+{%- from 'elasticfleet/map.jinja' import ELASTICFLEETMERGED %}
+{%- from 'elasticfleet/config.map.jinja' import LOGSTASH_CONFIG_YAML %}
 
 . /usr/sbin/so-common
 
+FORCE_UPDATE=false
+UPDATE_CERTS=false
+LOGSTASH_PILLAR_CONFIG_YAML="{{ LOGSTASH_CONFIG_YAML }}"
+LOGSTASH_PILLAR_STATE_FILE="/opt/so/state/esfleet_logstash_config_pillar"
+
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    -f|--force)
+      FORCE_UPDATE=true
+      shift
+      ;;
+    -c| --certs)
+      UPDATE_CERTS=true
+      FORCE_UPDATE=true
+      shift
+      ;;
+    *)
+      echo "Unknown option $1"
+      echo "Usage: $0 [-f|--force] [-c|--certs]"
+      exit 1
+      ;;
+  esac
+done
+
 # Only run on Managers
 if ! is_manager_node; then
     printf "Not a Manager Node... Exiting"
@@ -15,22 +40,104 @@ 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')
+        LOGSTASHKEY=$(openssl rsa -in  /etc/pki/elasticfleet-logstash.key)
+        LOGSTASHCRT=$(openssl x509 -in /etc/pki/elasticfleet-logstash.crt)
+        LOGSTASHCA=$(openssl x509 -in  /etc/pki/tls/certs/intca.crt)
+        # Revert escaped \\n to \n for jq
+        LOGSTASH_PILLAR_CONFIG_YAML=$(printf '%b' "$LOGSTASH_PILLAR_CONFIG_YAML")
+
+        if SECRETS=$(echo "$logstash_policy" | jq -er '.item.secrets' 2>/dev/null); then
+            if [[ "$UPDATE_CERTS" != "true"  ]]; then
+                # Reuse existing secret
+                JSON_STRING=$(jq -n \
+                    --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                    --arg CONFIG_YAML "$LOGSTASH_PILLAR_CONFIG_YAML" \
+                    --argjson SECRETS "$SECRETS" \
+                    --argjson SSL_CONFIG "$SSL_CONFIG" \
+                    '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":$CONFIG_YAML,"ssl": $SSL_CONFIG,"secrets": $SECRETS}')
+            else
+                # Update certs, creating new secret
+                JSON_STRING=$(jq -n \
+                    --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                    --arg CONFIG_YAML "$LOGSTASH_PILLAR_CONFIG_YAML" \
+                    --arg LOGSTASHKEY "$LOGSTASHKEY" \
+                    --arg LOGSTASHCRT "$LOGSTASHCRT" \
+                    --arg LOGSTASHCA "$LOGSTASHCA" \
+                    '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":$CONFIG_YAML,"ssl": {"certificate": $LOGSTASHCRT,"certificate_authorities":[ $LOGSTASHCA ]},"secrets": {"ssl":{"key": $LOGSTASHKEY }}}')
+            fi
+        else
+            if [[ "$UPDATE_CERTS" != "true" ]]; then
+                # Reuse existing ssl config
+                JSON_STRING=$(jq -n \
+                    --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                    --arg CONFIG_YAML "$LOGSTASH_PILLAR_CONFIG_YAML" \
+                    --argjson SSL_CONFIG "$SSL_CONFIG" \
+                    '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":$CONFIG_YAML,"ssl": $SSL_CONFIG}')
+            else
+                # Update ssl config
+                JSON_STRING=$(jq -n \
+                    --arg UPDATEDLIST "$NEW_LIST_JSON" \
+                    --arg CONFIG_YAML "$LOGSTASH_PILLAR_CONFIG_YAML" \
+                    --arg LOGSTASHKEY "$LOGSTASHKEY" \
+                    --arg LOGSTASHCRT "$LOGSTASHCRT" \
+                    --arg LOGSTASHCA "$LOGSTASHCA" \
+                    '{"name":"grid-logstash","type":"logstash","hosts": $UPDATEDLIST,"is_default":true,"is_default_monitoring":true,"config_yaml":$CONFIG_YAML,"ssl": {"certificate": $LOGSTASHCRT,"key": $LOGSTASHKEY,"certificate_authorities":[ $LOGSTASHCA ]}}')
+            fi
+        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 "$JSON_STRING" | jq
 }
 function update_kafka_outputs() {
   # Make sure SSL configuration is included in policy updates for Kafka output. SSL is configured in so-elastic-fleet-setup
-  SSL_CONFIG=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_kafka" | jq -r '.item.ssl')
-
-  JSON_STRING=$(jq -n \
-    --arg UPDATEDLIST "$NEW_LIST_JSON" \
-    --argjson SSL_CONFIG "$SSL_CONFIG" \
-    '{"name": "grid-kafka","type": "kafka","hosts": $UPDATEDLIST,"is_default": true,"is_default_monitoring": true,"config_yaml": "","ssl": $SSL_CONFIG}')
-  # Update Kafka outputs
-  curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_kafka" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" | jq
+  if kafka_policy=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_kafka" --fail 2>/dev/null); then
+    SSL_CONFIG=$(echo "$kafka_policy" | jq -r '.item.ssl')
+    KAFKAKEY=$(openssl rsa -in  /etc/pki/elasticfleet-kafka.key)
+    KAFKACRT=$(openssl x509 -in /etc/pki/elasticfleet-kafka.crt)
+    KAFKACA=$(openssl x509 -in  /etc/pki/tls/certs/intca.crt)
+    if SECRETS=$(echo "$kafka_policy" | jq -er '.item.secrets' 2>/dev/null); then
+        if [[ "$UPDATE_CERTS" != "true" ]]; then
+            # Update policy when fleet has secrets enabled
+            JSON_STRING=$(jq -n \
+              --arg UPDATEDLIST "$NEW_LIST_JSON" \
+              --argjson SSL_CONFIG "$SSL_CONFIG" \
+              --argjson SECRETS "$SECRETS" \
+              '{"name": "grid-kafka","type": "kafka","hosts": $UPDATEDLIST,"is_default": true,"is_default_monitoring": true,"config_yaml": "","ssl": $SSL_CONFIG,"secrets": $SECRETS}')
+        else
+            # Update certs, creating new secret
+            JSON_STRING=$(jq -n \
+              --arg UPDATEDLIST "$NEW_LIST_JSON" \
+              --arg KAFKAKEY "$KAFKAKEY" \
+              --arg KAFKACRT "$KAFKACRT" \
+              --arg KAFKACA "$KAFKACA" \
+              '{"name": "grid-kafka","type": "kafka","hosts": $UPDATEDLIST,"is_default": true,"is_default_monitoring": true,"config_yaml": "","ssl": {"certificate_authorities":[ $KAFKACA ],"certificate": $KAFKACRT ,"key":"","verification_mode":"full"},"secrets": {"ssl":{"key": $KAFKAKEY }}}')
+        fi
+    else
+        if [[ "$UPDATE_CERTS" != "true" ]]; then
+            # Update policy when fleet has secrets disabled or policy hasn't been force updated
+            JSON_STRING=$(jq -n \
+              --arg UPDATEDLIST "$NEW_LIST_JSON" \
+              --argjson SSL_CONFIG "$SSL_CONFIG" \
+              '{"name": "grid-kafka","type": "kafka","hosts": $UPDATEDLIST,"is_default": true,"is_default_monitoring": true,"config_yaml": "","ssl": $SSL_CONFIG}')
+        else
+            # Update ssl config
+            JSON_STRING=$(jq -n \
+              --arg UPDATEDLIST "$NEW_LIST_JSON" \
+              --arg KAFKAKEY "$KAFKAKEY" \
+              --arg KAFKACRT "$KAFKACRT" \
+              --arg KAFKACA "$KAFKACA" \
+              '{"name": "grid-kafka","type": "kafka","hosts": $UPDATEDLIST,"is_default": true,"is_default_monitoring": true,"config_yaml": "","ssl": { "certificate_authorities": [ $KAFKACA ], "certificate": $KAFKACRT, "key": $KAFKAKEY, "verification_mode": "full" }}')
+        fi
+    fi
+    # Update Kafka outputs
+    curl -K /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_kafka" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" | jq
+  else
+    printf "Failed to get current Kafka output policy..."
+    exit 1
+  fi
 }
 
 {% if GLOBALS.pipeline == "KAFKA" %}
@@ -46,7 +153,7 @@ function update_kafka_outputs() {
 
   # Get the current list of kafka outputs & hash them
   CURRENT_LIST=$(jq -c -r '.item.hosts' <<<  "$RAW_JSON")
-  CURRENT_HASH=$(sha1sum <<< "$CURRENT_LIST" | awk '{print $1}')
+  CURRENT_HASH=$(sha256sum <<< "$CURRENT_LIST" | awk '{print $1}')
 
   declare -a NEW_LIST=()
 
@@ -69,10 +176,19 @@ function update_kafka_outputs() {
    printf "Failed to query for current Logstash Outputs..."
    exit 1
   fi
+  # logstash adv config - compare pillar to last state file value
+  if [[ -f "$LOGSTASH_PILLAR_STATE_FILE" ]]; then
+    PREVIOUS_LOGSTASH_PILLAR_CONFIG_YAML=$(cat "$LOGSTASH_PILLAR_STATE_FILE")
+    if [[ "$LOGSTASH_PILLAR_CONFIG_YAML" != "$PREVIOUS_LOGSTASH_PILLAR_CONFIG_YAML" ]]; then
+      echo "Logstash pillar config has changed - forcing update"
+      FORCE_UPDATE=true
+    fi
+    echo "$LOGSTASH_PILLAR_CONFIG_YAML" > "$LOGSTASH_PILLAR_STATE_FILE"
+  fi
 
   # Get the current list of Logstash outputs & hash them
   CURRENT_LIST=$(jq -c -r '.item.hosts' <<<  "$RAW_JSON")
-  CURRENT_HASH=$(sha1sum <<< "$CURRENT_LIST" | awk '{print $1}')
+  CURRENT_HASH=$(sha256sum <<< "$CURRENT_LIST" | awk '{print $1}')
 
   declare -a NEW_LIST=()
 
@@ -121,10 +237,10 @@ function update_kafka_outputs() {
 
 # Sort & hash the new list of Logstash Outputs
 NEW_LIST_JSON=$(jq --compact-output --null-input '$ARGS.positional' --args -- "${NEW_LIST[@]}")
-NEW_HASH=$(sha1sum <<< "$NEW_LIST_JSON" | awk '{print $1}')
+NEW_HASH=$(sha256sum <<< "$NEW_LIST_JSON" | awk '{print $1}')
 
 # Compare the current & new list of outputs - if different, update the Logstash outputs
-if [ "$NEW_HASH" = "$CURRENT_HASH" ]; then
+if [[ "$NEW_HASH" = "$CURRENT_HASH" ]] && [[ "$FORCE_UPDATE" != "true" ]]; then
     printf "\nHashes match - no update needed.\n"
     printf "Current List: $CURRENT_LIST\nNew List: $NEW_LIST_JSON\n"
 

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/elasticfleet/tools/sbin_jinja/so-kafka-fleet-output-policy

@@ -5,46 +5,78 @@
 # Elastic License 2.0.
 
 {% from 'vars/globals.map.jinja' import GLOBALS %}
-{% if GLOBALS.role in ['so-manager', 'so-standalone', 'so-managersearch'] %}
+{% if GLOBALS.role in ['so-manager', 'so-standalone', 'so-managersearch', 'so-managerhype'] %}
 
 . /usr/sbin/so-common
 
+force=false
+while [[ $# -gt 0 ]]; do
+  case $1 in
+    -f|--force)
+      force=true
+      shift
+      ;;
+    *)
+      echo "Unknown option $1"
+      echo "Usage: $0 [-f|--force]"
+      exit 1
+      ;;
+  esac
+done
+
 # Check to make sure that Kibana API is up & ready
 RETURN_CODE=0
 wait_for_web_response "http://localhost:5601/api/fleet/settings" "fleet" 300 "curl -K /opt/so/conf/elasticsearch/curl.config"
 RETURN_CODE=$?
 
 if [[ "$RETURN_CODE" != "0" ]]; then
-    printf "Kibana API not accessible, can't setup Elastic Fleet output policy for Kafka..."
-    exit 1
+  echo -e "\nKibana API not accessible, can't setup Elastic Fleet output policy for Kafka...\n"
+  exit 1
 fi
 
-output=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs" | jq -r .items[].id)
+KAFKACRT=$(openssl x509 -in /etc/pki/elasticfleet-kafka.crt)
+KAFKAKEY=$(openssl rsa -in  /etc/pki/elasticfleet-kafka.key)
+KAFKACA=$(openssl x509 -in  /etc/pki/tls/certs/intca.crt)
+KAFKA_OUTPUT_VERSION="2.6.0"
 
-if ! echo "$output" | grep -q "so-manager_kafka"; then
-  KAFKACRT=$(openssl x509 -in /etc/pki/elasticfleet-kafka.crt)
-  KAFKAKEY=$(openssl rsa -in  /etc/pki/elasticfleet-kafka.key)
-  KAFKACA=$(openssl x509 -in  /etc/pki/tls/certs/intca.crt)
-  KAFKA_OUTPUT_VERSION="2.6.0"
+if ! kafka_output=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_kafka" --fail 2>/dev/null); then
+  # Create a new output policy for Kafka. Default is disabled 'is_default: false & is_default_monitoring: false'
   JSON_STRING=$( jq -n \
-                --arg KAFKACRT "$KAFKACRT" \
-                --arg KAFKAKEY "$KAFKAKEY" \
-                --arg KAFKACA "$KAFKACA" \
-                --arg MANAGER_IP "{{ GLOBALS.manager_ip }}:9092" \
-                --arg KAFKA_OUTPUT_VERSION "$KAFKA_OUTPUT_VERSION" \
-                    '{ "name": "grid-kafka", "id": "so-manager_kafka", "type": "kafka", "hosts": [ $MANAGER_IP ], "is_default": false, "is_default_monitoring": false, "config_yaml": "", "ssl": { "certificate_authorities": [ $KAFKACA ], "certificate": $KAFKACRT, "key": $KAFKAKEY, "verification_mode": "full" }, "proxy_id": null, "client_id": "Elastic", "version": $KAFKA_OUTPUT_VERSION, "compression": "none", "auth_type": "ssl", "partition": "round_robin", "round_robin": { "group_events": 10 }, "topics":[{"topic":"default-securityonion"}], "headers": [ { "key": "", "value": "" } ], "timeout": 30, "broker_timeout": 30, "required_acks": 1 }'
-                )
-  curl -sK /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/outputs" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" -o /dev/null
-  refresh_output=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs" | jq -r .items[].id)
-
-  if ! echo "$refresh_output" | grep -q "so-manager_kafka"; then
-    echo -e "\nFailed to setup Elastic Fleet output policy for Kafka...\n"
+    --arg KAFKACRT "$KAFKACRT" \
+    --arg KAFKAKEY "$KAFKAKEY" \
+    --arg KAFKACA "$KAFKACA" \
+    --arg MANAGER_IP "{{ GLOBALS.manager_ip }}:9092" \
+    --arg KAFKA_OUTPUT_VERSION "$KAFKA_OUTPUT_VERSION" \
+      '{"name":"grid-kafka", "id":"so-manager_kafka","type":"kafka","hosts":[ $MANAGER_IP ],"is_default":false,"is_default_monitoring":false,"config_yaml":"","ssl":{"certificate_authorities":[ $KAFKACA ],"certificate": $KAFKACRT ,"key":"","verification_mode":"full"},"proxy_id":null,"client_id":"Elastic","version": $KAFKA_OUTPUT_VERSION ,"compression":"none","auth_type":"ssl","partition":"round_robin","round_robin":{"group_events":10},"topics":[{"topic":"default-securityonion"}],"headers":[{"key":"","value":""}],"timeout":30,"broker_timeout":30,"required_acks":1,"secrets":{"ssl":{"key": $KAFKAKEY }}}'
+    )
+    if ! response=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L -X POST "localhost:5601/api/fleet/outputs" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" --fail 2>/dev/null); then
+      echo -e "\nFailed to setup Elastic Fleet output policy for Kafka...\n"
+      exit 1
+    else
+      echo -e "\nSuccessfully setup Elastic Fleet output policy for Kafka...\n"
+      exit 0
+    fi
+elif kafka_output=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/outputs/so-manager_kafka" --fail 2>/dev/null) && [[ "$force" == "true" ]]; then
+  # force an update to Kafka policy. Keep the current value of Kafka output policy (enabled/disabled).
+  ENABLED_DISABLED=$(echo "$kafka_output" | jq -e .item.is_default)
+  HOSTS=$(echo "$kafka_output" | jq -r '.item.hosts')
+  JSON_STRING=$( jq -n \
+    --arg KAFKACRT "$KAFKACRT" \
+    --arg KAFKAKEY "$KAFKAKEY" \
+    --arg KAFKACA "$KAFKACA" \
+    --arg ENABLED_DISABLED "$ENABLED_DISABLED"\
+    --arg KAFKA_OUTPUT_VERSION "$KAFKA_OUTPUT_VERSION" \
+    --argjson HOSTS "$HOSTS" \
+      '{"name":"grid-kafka","type":"kafka","hosts":$HOSTS,"is_default":$ENABLED_DISABLED,"is_default_monitoring":$ENABLED_DISABLED,"config_yaml":"","ssl":{"certificate_authorities":[ $KAFKACA ],"certificate": $KAFKACRT ,"key":"","verification_mode":"full"},"proxy_id":null,"client_id":"Elastic","version": $KAFKA_OUTPUT_VERSION ,"compression":"none","auth_type":"ssl","partition":"round_robin","round_robin":{"group_events":10},"topics":[{"topic":"default-securityonion"}],"headers":[{"key":"","value":""}],"timeout":30,"broker_timeout":30,"required_acks":1,"secrets":{"ssl":{"key": $KAFKAKEY }}}'
+    )
+  if ! response=$(curl -sK /opt/so/conf/elasticsearch/curl.config -L -X PUT "localhost:5601/api/fleet/outputs/so-manager_kafka" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING" --fail 2>/dev/null); then
+    echo -e "\nFailed to force update to Elastic Fleet output policy for Kafka...\n"
     exit 1
-  elif echo "$refresh_output" | grep -q "so-manager_kafka"; then
-    echo -e "\nSuccessfully setup Elastic Fleet output policy for Kafka...\n"
+  else
+    echo -e "\nForced update to Elastic Fleet output policy for Kafka...\n"
   fi
 
-elif echo "$output" | grep -q "so-manager_kafka"; then
+else
   echo -e "\nElastic Fleet output policy for Kafka already exists...\n"
 fi
 {% else %}

salt/elasticsearch/defaults.yaml

@@ -1,6 +1,6 @@
 elasticsearch:
   enabled: false
-  version: 8.18.4
+  version: 8.18.8
   index_clean: true
   config:
     action:
@@ -72,6 +72,8 @@ elasticsearch:
             actions:
               set_priority:
                 priority: 0
+              allocate:
+                number_of_replicas: ""
             min_age: 60d
           delete:
             actions:
@@ -84,11 +86,25 @@ elasticsearch:
                 max_primary_shard_size: 50gb
               set_priority:
                 priority: 100
+              forcemerge:
+                max_num_segments: ""
+              shrink:
+                max_primary_shard_size: ""
+                method: COUNT
+                number_of_shards: ""
             min_age: 0ms
           warm:
             actions:
               set_priority:
                 priority: 50
+              forcemerge:
+                max_num_segments: ""
+              shrink:
+                max_primary_shard_size: ""
+                method: COUNT
+                number_of_shards: ""
+              allocate:
+                number_of_replicas: ""
             min_age: 30d
     so-case:
       index_sorting: false
@@ -245,7 +261,6 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
-      warm: 7
     so-detection:
       index_sorting: false
       index_template:
@@ -284,6 +299,86 @@ elasticsearch:
           hot:
             actions: {}
             min_age: 0ms
+    so-assistant-chat:
+      index_sorting: false
+      index_template:
+        composed_of:
+        - assistant-chat-mappings
+        - assistant-chat-settings
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates: []
+        index_patterns:
+        - so-assistant-chat*
+        priority: 501
+        template:
+          mappings:
+            date_detection: false
+            dynamic_templates:
+            - strings_as_keyword:
+                mapping:
+                  ignore_above: 1024
+                  type: keyword
+                match_mapping_type: string
+          settings:
+            index:
+              lifecycle:
+                name: so-assistant-chat-logs
+              mapping:
+                total_fields:
+                  limit: 1500
+              number_of_replicas: 0
+              number_of_shards: 1
+              refresh_interval: 1s
+              sort:
+                field: '@timestamp'
+                order: desc
+      policy:
+        phases:
+          hot:
+            actions: {}
+            min_age: 0ms
+    so-assistant-session:
+      index_sorting: false
+      index_template:
+        composed_of:
+        - assistant-session-mappings
+        - assistant-session-settings
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        ignore_missing_component_templates: []
+        index_patterns:
+        - so-assistant-session*
+        priority: 501
+        template:
+          mappings:
+            date_detection: false
+            dynamic_templates:
+            - strings_as_keyword:
+                mapping:
+                  ignore_above: 1024
+                  type: keyword
+                match_mapping_type: string
+          settings:
+            index:
+              lifecycle:
+                name: so-assistant-session-logs
+              mapping:
+                total_fields:
+                  limit: 1500
+              number_of_replicas: 0
+              number_of_shards: 1
+              refresh_interval: 1s
+              sort:
+                field: '@timestamp'
+                order: desc
+      policy:
+        phases:
+          hot:
+            actions: {}
+            min_age: 0ms
     so-endgame:
       index_sorting: false
       index_template:
@@ -504,7 +599,6 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
-      warm: 7
     so-import:
       index_sorting: false
       index_template:
@@ -852,7 +946,6 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
-      warm: 7
     so-hydra:
       close: 30
       delete: 365
@@ -963,7 +1056,6 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
-      warm: 7
     so-lists:
       index_sorting: false
       index_template:
@@ -1047,6 +1139,8 @@ elasticsearch:
             actions:
               set_priority:
                 priority: 0
+              allocate:
+                number_of_replicas: ""
             min_age: 60d
           delete:
             actions:
@@ -1059,11 +1153,25 @@ elasticsearch:
                 max_primary_shard_size: 50gb
               set_priority:
                 priority: 100
+              forcemerge:
+                max_num_segments: ""
+              shrink:
+                max_primary_shard_size: ""
+                method: COUNT
+                number_of_shards: ""
             min_age: 0ms
           warm:
             actions:
               set_priority:
                 priority: 50
+              allocate:
+                number_of_replicas: ""
+              forcemerge:
+                max_num_segments: ""
+              shrink:
+                max_primary_shard_size: ""
+                method: COUNT
+                number_of_shards: ""
             min_age: 30d
     so-logs-detections_x_alerts:
       index_sorting: false
@@ -1243,6 +1351,68 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
+    so-elastic-agent-monitor:
+      index_sorting: false
+      index_template:
+        composed_of:
+        - event-mappings
+        - so-elastic-agent-monitor
+        - so-fleet_integrations.ip_mappings-1
+        - so-fleet_globals-1
+        - so-fleet_agent_id_verification-1
+        data_stream:
+          allow_custom_routing: false
+          hidden: false
+        index_patterns:
+        - logs-agentmonitor-*
+        priority: 501
+        template:
+          mappings:
+            _meta:
+              managed: true
+              managed_by: security_onion
+              package:
+                name: elastic_agent
+          settings:
+            index:
+              lifecycle:
+                name: so-elastic-agent-monitor-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-elastic_agent_x_apm_server:
       index_sorting: false
       index_template:
@@ -1849,6 +2019,70 @@ 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:
@@ -2917,7 +3151,6 @@ elasticsearch:
               set_priority:
                 priority: 50
             min_age: 30d
-      warm: 7
     so-logs-system_x_application:
       index_sorting: false
       index_template:
@@ -4031,7 +4264,7 @@ elasticsearch:
           hot:
             actions:
               rollover:
-                max_age: 1d
+                max_age: 30d
                 max_primary_shard_size: 50gb
               set_priority:
                 priority: 100

salt/elasticsearch/files/ingest/common.ip_validation

@@ -0,0 +1,22 @@
+{
+  "processors": [
+    {
+      "convert": {
+        "field": "_ingest._value",
+        "type": "ip",
+        "target_field": "_ingest._temp_ip",
+        "ignore_failure": true
+      }
+    },
+    {
+      "append": {
+        "field": "temp._valid_ips",
+        "allow_duplicates": false,
+        "value": [
+          "{{{_ingest._temp_ip}}}"
+        ],
+        "ignore_failure": true
+      }
+    }
+  ]
+}

salt/elasticsearch/files/ingest/elasticagent.monitor

@@ -0,0 +1,36 @@
+{
+  "processors": [
+    {
+      "set": {
+        "field": "event.dataset",
+        "value": "gridmetrics.agents",
+        "ignore_failure": true
+      }
+    },
+    {
+      "set": {
+        "field": "event.module",
+        "value": "gridmetrics",
+        "ignore_failure": true
+      }
+    },
+    {
+      "remove": {
+        "field": [
+          "host",
+          "elastic_agent",
+          "agent"
+        ],
+        "ignore_missing": true,
+        "ignore_failure": true
+      }
+    },
+    {
+      "json": {
+        "field": "message",
+        "add_to_root": true,
+        "ignore_failure": true
+      }
+    }
+  ]
+}

salt/elasticsearch/files/ingest/global@custom

@@ -23,8 +23,9 @@
     { "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'","description":"Extract IPs from Elastic Agent events (host.ip) and adds them to related.ip"}},
+    {"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/ingest/logs-pfsense.log-1.23.1

@@ -107,61 +107,61 @@
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-firewall",
+        "name": "logs-pfsense.log-1.23.1-firewall",
         "if": "ctx.event.provider == 'filterlog'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-openvpn",
+        "name": "logs-pfsense.log-1.23.1-openvpn",
         "if": "ctx.event.provider == 'openvpn'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-ipsec",
+        "name": "logs-pfsense.log-1.23.1-ipsec",
         "if": "ctx.event.provider == 'charon'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-dhcp",
+        "name": "logs-pfsense.log-1.23.1-dhcp",
         "if": "[\"dhcpd\", \"dhclient\", \"dhcp6c\"].contains(ctx.event.provider)"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-unbound",
+        "name": "logs-pfsense.log-1.23.1-unbound",
         "if": "ctx.event.provider == 'unbound'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-haproxy",
+        "name": "logs-pfsense.log-1.23.1-haproxy",
         "if": "ctx.event.provider == 'haproxy'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-php-fpm",
+        "name": "logs-pfsense.log-1.23.1-php-fpm",
         "if": "ctx.event.provider == 'php-fpm'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-squid",
+        "name": "logs-pfsense.log-1.23.1-squid",
         "if": "ctx.event.provider == 'squid'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-snort",
+        "name": "logs-pfsense.log-1.23.1-snort",
         "if": "ctx.event.provider == 'snort'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.0-suricata",
+        "name": "logs-pfsense.log-1.23.1-suricata",
         "if": "ctx.event.provider == 'suricata'"
       }
     },

salt/elasticsearch/files/ingest/suricata.alert

@@ -1,15 +1,79 @@
 {
-  "description" : "suricata.alert",
-  "processors" : [
-    { "set":   { "if": "ctx.event?.imported != true", "field": "_index", "value": "logs-suricata.alerts-so" } },
-    { "set":   { "field": "tags","value": "alert" }},
-    { "rename":{ "field": "message2.alert",	"target_field": "rule",	"ignore_failure": true 	} },
-    { "rename":{ "field": "rule.signature",     "target_field": "rule.name", "ignore_failure": true  } },
-    { "rename":{ "field": "rule.ref",     "target_field": "rule.version", "ignore_failure": true  } },
-    { "rename":{ "field": "rule.signature_id",     "target_field": "rule.uuid", "ignore_failure": true  } },
-    { "rename":{ "field": "rule.signature_id",     "target_field": "rule.signature", "ignore_failure": true  } },
-    { "rename":{ "field": "message2.payload_printable",     "target_field": "network.data.decoded", "ignore_failure": true  } },
-    { "dissect": { "field": "rule.rule", "pattern": "%{?prefix}content:\"%{dns.query_name}\"%{?remainder}", "ignore_missing": true, "ignore_failure": true } },
-    { "pipeline": { "name": "common.nids" } }
-  ]
+    "description": "suricata.alert",
+    "processors": [
+        {
+            "set": {
+                "if": "ctx.event?.imported != true",
+                "field": "_index",
+                "value": "logs-suricata.alerts-so"
+            }
+        },
+        {
+            "set": {
+                "field": "tags",
+                "value": "alert"
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.alert",
+                "target_field": "rule",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "rule.signature",
+                "target_field": "rule.name",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "rule.ref",
+                "target_field": "rule.version",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "rule.signature_id",
+                "target_field": "rule.uuid",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "rule.signature_id",
+                "target_field": "rule.signature",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.payload_printable",
+                "target_field": "network.data.decoded",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "dissect": {
+                "field": "rule.rule",
+                "pattern": "%{?prefix}content:\"%{dns.query_name}\"%{?remainder}",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "pipeline": {
+                "name": "common.nids"
+            }
+        }
+    ]
 }

salt/elasticsearch/files/ingest/suricata.common

@@ -1,30 +1,155 @@
 {
-  "description" : "suricata.common",
-  "processors" : [
-    { "json":   { "field": "message",                   "target_field": "message2",             "ignore_failure": true  } },
-    { "rename": { "field": "message2.pkt_src",          "target_field": "network.packet_source","ignore_failure": true  } },
-    { "rename": { "field": "message2.proto",            "target_field": "network.transport",    "ignore_failure": true  } },
-    { "rename": { "field": "message2.in_iface",         "target_field": "observer.ingress.interface.name",    "ignore_failure": true  } },
-    { "rename": { "field": "message2.flow_id",          "target_field": "log.id.uid",           "ignore_failure": true  } },
-    { "rename": { "field": "message2.src_ip",           "target_field": "source.ip",            "ignore_failure": true  } },
-    { "rename": { "field": "message2.src_port",         "target_field": "source.port",          "ignore_failure": true  } },
-    { "rename": { "field": "message2.dest_ip",          "target_field": "destination.ip",       "ignore_failure": true  } },
-    { "rename": { "field": "message2.dest_port",        "target_field": "destination.port",     "ignore_failure": true  } },
-    { "rename": { "field": "message2.vlan",             "target_field": "network.vlan.id",      "ignore_failure": true  } },
-    { "rename": { "field": "message2.community_id",     "target_field": "network.community_id", "ignore_missing": true  } },
-    { "rename": { "field": "message2.xff",              "target_field": "xff.ip",               "ignore_missing": true  } },
-    { "set":    { "field": "event.dataset",             "value": "{{ message2.event_type }}"                            } },
-    { "set":    { "field": "observer.name",             "value": "{{agent.name}}"                                       } },
-    { "set":    { "field": "event.ingested",            "value": "{{@timestamp}}"                                       } },
-    { "date": { "field": "message2.timestamp", "target_field": "@timestamp", "formats": ["ISO8601", "UNIX"], "timezone": "UTC", "ignore_failure": true } },
-    { "remove":{ "field": "agent",                                                              "ignore_failure": true  } },
-    {"append":{"field":"related.ip","value":["{{source.ip}}","{{destination.ip}}"],"allow_duplicates":false,"ignore_failure":true}},
-    {
-      "script": {
-        "source": "boolean isPrivate(def ip) { if (ip == null) return false; int dot1 = ip.indexOf('.'); if (dot1 == -1) return false; int dot2 = ip.indexOf('.', dot1 + 1); if (dot2 == -1) return false; int first = Integer.parseInt(ip.substring(0, dot1)); if (first == 10) return true; if (first == 192 && ip.startsWith('168.', dot1 + 1)) return true; if (first == 172) { int second = Integer.parseInt(ip.substring(dot1 + 1, dot2)); return second >= 16 && second <= 31; } return false; } String[] fields = new String[] {\"source\", \"destination\"}; for (int i = 0; i < fields.length; i++) { def field = fields[i]; def ip = ctx[field]?.ip; if (ip != null) { if (ctx.network == null) ctx.network = new HashMap(); if (isPrivate(ip)) { if (ctx.network.private_ip == null) ctx.network.private_ip = new ArrayList(); if (!ctx.network.private_ip.contains(ip)) ctx.network.private_ip.add(ip); } else { if (ctx.network.public_ip == null) ctx.network.public_ip = new ArrayList(); if (!ctx.network.public_ip.contains(ip)) ctx.network.public_ip.add(ip); } } }",
-        "ignore_failure": false
-      }
-    },
-    { "pipeline": { "if": "ctx?.event?.dataset != null", "name": "suricata.{{event.dataset}}" } }
-  ]
-}
+    "description": "suricata.common",
+    "processors": [
+        {
+            "json": {
+                "field": "message",
+                "target_field": "message2",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.pkt_src",
+                "target_field": "network.packet_source",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.proto",
+                "target_field": "network.transport",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.in_iface",
+                "target_field": "observer.ingress.interface.name",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.flow_id",
+                "target_field": "log.id.uid",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.src_ip",
+                "target_field": "source.ip",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.src_port",
+                "target_field": "source.port",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dest_ip",
+                "target_field": "destination.ip",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dest_port",
+                "target_field": "destination.port",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.vlan",
+                "target_field": "network.vlan.id",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.community_id",
+                "target_field": "network.community_id",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.xff",
+                "target_field": "xff.ip",
+                "ignore_missing": true
+            }
+        },
+        {
+            "set": {
+                "field": "event.dataset",
+                "value": "{{ message2.event_type }}"
+            }
+        },
+        {
+            "set": {
+                "field": "observer.name",
+                "value": "{{agent.name}}"
+            }
+        },
+        {
+            "set": {
+                "field": "event.ingested",
+                "value": "{{@timestamp}}"
+            }
+        },
+        {
+            "date": {
+                "field": "message2.timestamp",
+                "target_field": "@timestamp",
+                "formats": [
+                    "ISO8601",
+                    "UNIX"
+                ],
+                "timezone": "UTC",
+                "ignore_failure": true
+            }
+        },
+        {
+            "remove": {
+                "field": "agent",
+                "ignore_failure": true
+            }
+        },
+        {
+            "append": {
+                "field": "related.ip",
+                "value": [
+                    "{{source.ip}}",
+                    "{{destination.ip}}"
+                ],
+                "allow_duplicates": false,
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "boolean isPrivate(def ip) { if (ip == null) return false; int dot1 = ip.indexOf('.'); if (dot1 == -1) return false; int dot2 = ip.indexOf('.', dot1 + 1); if (dot2 == -1) return false; int first = Integer.parseInt(ip.substring(0, dot1)); if (first == 10) return true; if (first == 192 && ip.startsWith('168.', dot1 + 1)) return true; if (first == 172) { int second = Integer.parseInt(ip.substring(dot1 + 1, dot2)); return second >= 16 && second <= 31; } return false; } String[] fields = new String[] {\"source\", \"destination\"}; for (int i = 0; i < fields.length; i++) { def field = fields[i]; def ip = ctx[field]?.ip; if (ip != null) { if (ctx.network == null) ctx.network = new HashMap(); if (isPrivate(ip)) { if (ctx.network.private_ip == null) ctx.network.private_ip = new ArrayList(); if (!ctx.network.private_ip.contains(ip)) ctx.network.private_ip.add(ip); } else { if (ctx.network.public_ip == null) ctx.network.public_ip = new ArrayList(); if (!ctx.network.public_ip.contains(ip)) ctx.network.public_ip.add(ip); } } }",
+                "ignore_failure": false
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.capture_file",
+                "target_field": "suricata.capture_file",
+                "ignore_missing": true
+            }
+        },
+        {
+            "pipeline": {
+                "if": "ctx?.event?.dataset != null",
+                "name": "suricata.{{event.dataset}}"
+            }
+        }
+    ]
+}

salt/elasticsearch/files/ingest/suricata.dns

@@ -1,21 +1,136 @@
 {
-  "description" : "suricata.dns",
-  "processors" : [
-    { "rename": 	{ "field": "message2.proto", 			"target_field": "network.transport",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.app_proto", 		"target_field": "network.protocol",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.type", 		"target_field": "dns.query.type",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.tx_id",		"target_field": "dns.id",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.version", 		"target_field": "dns.version",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.rrname", 		"target_field": "dns.query.name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.rrtype", 		"target_field": "dns.query.type_name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.flags", 		"target_field": "dns.flags",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.qr", 			"target_field": "dns.qr",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.rd", 			"target_field": "dns.recursion.desired",	"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.ra", 			"target_field": "dns.recursion.available",	"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.dns.rcode", 		"target_field": "dns.response.code_name",	"ignore_missing": true 	} },
-    { "rename":		{ "field": "message2.dns.grouped.A", 		"target_field": "dns.answers.data",		"ignore_missing": true 	} },
-    { "rename":		{ "field": "message2.dns.grouped.CNAME",	"target_field": "dns.answers.name",		"ignore_missing": true 	} },
-    { "pipeline":	{ "if": "ctx.dns.query?.name != null && ctx.dns.query.name.contains('.')", "name": "dns.tld"				} },
-    { "pipeline": 	{ "name": "common"													} }
-  ]
-}
+    "description": "suricata.dns",
+    "processors": [
+        {
+            "rename": {
+                "field": "message2.proto",
+                "target_field": "network.transport",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.app_proto",
+                "target_field": "network.protocol",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.type",
+                "target_field": "dns.query.type",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.tx_id",
+                "target_field": "dns.tx_id",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.id",
+                "target_field": "dns.id",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.version",
+                "target_field": "dns.version",
+                "ignore_missing": true
+            }
+        },
+        {
+            "pipeline": {
+                "name": "suricata.dnsv3",
+                "ignore_missing_pipeline": true,
+                "if": "ctx?.dns?.version != null && ctx?.dns?.version == 3",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.rrname",
+                "target_field": "dns.query.name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.rrtype",
+                "target_field": "dns.query.type_name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.flags",
+                "target_field": "dns.flags",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.qr",
+                "target_field": "dns.qr",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.rd",
+                "target_field": "dns.recursion.desired",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.ra",
+                "target_field": "dns.recursion.available",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.opcode",
+                "target_field": "dns.opcode",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.rcode",
+                "target_field": "dns.response.code_name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.grouped.A",
+                "target_field": "dns.answers.data",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.dns.grouped.CNAME",
+                "target_field": "dns.answers.name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "pipeline": {
+                "if": "ctx.dns.query?.name != null && ctx.dns.query.name.contains('.')",
+                "name": "dns.tld"
+            }
+        },
+        {
+            "pipeline": {
+                "name": "common"
+            }
+        }
+    ]
+}

salt/elasticsearch/files/ingest/suricata.dnsv3

@@ -0,0 +1,56 @@
+{
+  "processors": [
+    {
+      "rename": {
+        "field": "message2.dns.queries",
+        "target_field": "dns.queries",
+        "ignore_missing": true,
+        "ignore_failure": true
+      }
+    },
+    {
+      "script": {
+        "source": "if (ctx?.dns?.queries != null && ctx?.dns?.queries.length > 0) {\n    if (ctx.dns == null) {\n      ctx.dns = new HashMap();\n    }\n    if (ctx.dns.query == null) {\n      ctx.dns.query = new HashMap();\n    }\n    ctx.dns.query.name = ctx?.dns?.queries[0].rrname;\n}"
+      }
+    },
+    {
+      "script": {
+        "source": "if (ctx?.dns?.queries != null && ctx?.dns?.queries.length > 0) {\n    if (ctx.dns == null) {\n      ctx.dns = new HashMap();\n    }\n    if (ctx.dns.query == null) {\n      ctx.dns.query = new HashMap();\n    }\n    ctx.dns.query.type_name = ctx?.dns?.queries[0].rrtype;\n}"
+      }
+    },
+    {
+      "foreach": {
+        "field": "dns.queries",
+        "processor": {
+          "rename": {
+            "field": "_ingest._value.rrname",
+            "target_field": "_ingest._value.name",
+            "ignore_missing": true
+          }
+        },
+        "ignore_failure": true
+      }
+    },
+    {
+      "foreach": {
+        "field": "dns.queries",
+        "processor": {
+          "rename": {
+            "field": "_ingest._value.rrtype",
+            "target_field": "_ingest._value.type_name",
+            "ignore_missing": true
+          }
+        },
+        "ignore_failure": true
+      }
+    },
+    {
+      "pipeline": {
+        "name": "suricata.tld",
+        "ignore_missing_pipeline": true,
+        "if": "ctx?.dns?.queries != null && ctx?.dns?.queries.length > 0",
+        "ignore_failure": true
+      }
+    }
+  ]
+}

salt/elasticsearch/files/ingest/suricata.tld

@@ -0,0 +1,52 @@
+{
+    "processors": [
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    if (q.name != null && q.name.contains('.')) {\n      q.top_level_domain = q.name.substring(q.name.lastIndexOf('.') + 1);\n    }\n  }\n}",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    if (q.name != null && q.name.contains('.')) {\n      q.query_without_tld = q.name.substring(0, q.name.lastIndexOf('.'));\n    }\n  }\n}",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    if (q.query_without_tld != null && q.query_without_tld.contains('.')) {\n      q.parent_domain = q.query_without_tld.substring(q.query_without_tld.lastIndexOf('.') + 1);\n    }\n  }\n}",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    if (q.query_without_tld != null && q.query_without_tld.contains('.')) {\n      q.subdomain = q.query_without_tld.substring(0, q.query_without_tld.lastIndexOf('.'));\n    }\n  }\n}",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    if (q.parent_domain != null && q.top_level_domain != null) {\n      q.highest_registered_domain = q.parent_domain + \".\" + q.top_level_domain;\n    }\n  }\n}",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    if (q.subdomain != null) {\n      q.subdomain_length = q.subdomain.length();\n    }\n  }\n}",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    if (q.parent_domain != null) {\n      q.parent_domain_length = q.parent_domain.length();\n    }\n  }\n}",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns != null && ctx.dns.queries != null) {\n  for (def q : ctx.dns.queries) {\n    q.remove('query_without_tld');\n  }\n}",
+                "ignore_failure": true
+            }
+        }
+    ]
+}

salt/elasticsearch/files/ingest/zeek.analyzer

@@ -0,0 +1,61 @@
+{
+    "description": "zeek.analyzer",
+    "processors": [
+        {
+            "set": {
+                "field": "event.dataset",
+                "value": "analyzer"
+            }
+        },
+        {
+            "remove": {
+                "field": [
+                    "host"
+                ],
+                "ignore_failure": true
+            }
+        },
+        {
+            "json": {
+                "field": "message",
+                "target_field": "message2",
+                "ignore_failure": true
+            }
+        },
+        {
+            "set": {
+                "field": "network.protocol",
+                "copy_from": "message2.analyzer_name",
+                "ignore_empty_value": true,
+                "if": "ctx?.message2?.analyzer_kind == 'protocol'"
+            }
+        },
+        {
+            "set": {
+                "field": "network.protocol",
+                "ignore_empty_value": true,
+                "if": "ctx?.message2?.analyzer_kind != 'protocol'",
+                "copy_from": "message2.proto"
+            }
+        },
+        {
+            "lowercase": {
+                "field": "network.protocol",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.failure_reason",
+                "target_field": "error.reason",
+                "ignore_missing": true
+            }
+        },
+        {
+            "pipeline": {
+                "name": "zeek.common"
+            }
+        }
+    ]
+}

salt/elasticsearch/files/ingest/zeek.dns

@@ -1,32 +1,227 @@
 {
-  "description" : "zeek.dns",
-  "processors" : [
-    { "set": { "field": "event.dataset", "value": "dns" } },
-    { "remove":         { "field": ["host"],     "ignore_failure": true                                                                  } },
-    { "json":		{ "field": "message",			"target_field": "message2",		"ignore_failure": true	} },
-    { "dot_expander": 	{ "field": "id.orig_h", 		"path": "message2", 			"ignore_failure": true 	} },
-    { "rename": 	{ "field": "message2.proto", 		"target_field": "network.transport",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.trans_id",		"target_field": "dns.id",	"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.rtt",	 	"target_field": "event.duration",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.query", 		"target_field": "dns.query.name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.qclass", 		"target_field": "dns.query.class",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.qclass_name", 	"target_field": "dns.query.class_name",	"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.qtype", 		"target_field": "dns.query.type",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.qtype_name", 	"target_field": "dns.query.type_name",	"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.rcode",	 	"target_field": "dns.response.code",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.rcode_name", 	"target_field": "dns.response.code_name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.AA", 		"target_field": "dns.authoritative",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.TC", 		"target_field": "dns.truncated",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.RD", 		"target_field": "dns.recursion.desired",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.RA", 		"target_field": "dns.recursion.available",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.Z",		"target_field": "dns.reserved",			"ignore_missing": true 	} },
-    { "rename":  	{ "field": "message2.answers", 		"target_field": "dns.answers.name", 		"ignore_missing": true  	} },
-    { "script": { "lang": "painless", "if": "ctx.dns != null && ctx.dns.answers != null && ctx.dns.answers.name != null", "source": "def ips = []; for (item in ctx.dns.answers.name) { if (item =~ /^(?:[0-9]{1,3}\\.){3}[0-9]{1,3}$/ || item =~ /^([a-fA-F0-9:]+:+)+[a-fA-F0-9]+$/) { ips.add(item); } } ctx.dns.resolved_ip = ips;" } },
-    { "rename": 	{ "field": "message2.TTLs", 		"target_field": "dns.ttls",			"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.rejected", 	"target_field": "dns.query.rejected",		"ignore_missing": true 	} },
-    { "script": 	{ "lang": "painless", "source": "ctx.dns.query.length = ctx.dns.query.name.length()",	"ignore_failure": true  } },
-    { "set":      { "if": "ctx._index == 'so-zeek'", "field": "_index",      "value": "so-zeek_dns", "override": true   } },
-    { "pipeline": { "if": "ctx.dns?.query?.name != null && ctx.dns.query.name.contains('.')", "name": "dns.tld" } },
-    { "pipeline":       { "name": "zeek.common"											} }
-  ]
+    "description": "zeek.dns",
+    "processors": [
+        {
+            "set": {
+                "field": "event.dataset",
+                "value": "dns"
+            }
+        },
+        {
+            "remove": {
+                "field": [
+                    "host"
+                ],
+                "ignore_failure": true
+            }
+        },
+        {
+            "json": {
+                "field": "message",
+                "target_field": "message2",
+                "ignore_failure": true
+            }
+        },
+        {
+            "dot_expander": {
+                "field": "id.orig_h",
+                "path": "message2",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.proto",
+                "target_field": "network.transport",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.trans_id",
+                "target_field": "dns.id",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.rtt",
+                "target_field": "event.duration",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.query",
+                "target_field": "dns.query.name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.qclass",
+                "target_field": "dns.query.class",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.qclass_name",
+                "target_field": "dns.query.class_name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.qtype",
+                "target_field": "dns.query.type",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.qtype_name",
+                "target_field": "dns.query.type_name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.rcode",
+                "target_field": "dns.response.code",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.rcode_name",
+                "target_field": "dns.response.code_name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.AA",
+                "target_field": "dns.authoritative",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.TC",
+                "target_field": "dns.truncated",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.RD",
+                "target_field": "dns.recursion.desired",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.RA",
+                "target_field": "dns.recursion.available",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.Z",
+                "target_field": "dns.reserved",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.answers",
+                "target_field": "dns.answers.name",
+                "ignore_missing": true
+            }
+        },
+        {
+            "foreach": {
+                "field": "dns.answers.name",
+                "processor": {
+                    "pipeline": {
+                        "name": "common.ip_validation"
+                    }
+                },
+                "if": "ctx.dns != null && ctx.dns.answers != null && ctx.dns.answers.name != null",
+                "ignore_failure": true
+            }
+        },
+        {
+            "foreach": {
+                "field": "temp._valid_ips",
+                "processor": {
+                    "append": {
+                        "field": "dns.resolved_ip",
+                        "allow_duplicates": false,
+                        "value": "{{{_ingest._value}}}",
+                        "ignore_failure": true
+                    }
+                },
+                "if": "ctx.dns != null && ctx.dns.answers != null && ctx.dns.answers.name != null",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "source": "if (ctx.dns.resolved_ip != null && ctx.dns.resolved_ip instanceof List) {\n        ctx.dns.resolved_ip.removeIf(item -> item == null || item.toString().trim().isEmpty());\n      }",
+                "ignore_failure": true
+            }
+        },
+        {
+            "remove": {
+                "field": [
+                    "temp"
+                ],
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.TTLs",
+                "target_field": "dns.ttls",
+                "ignore_missing": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.rejected",
+                "target_field": "dns.query.rejected",
+                "ignore_missing": true
+            }
+        },
+        {
+            "script": {
+                "lang": "painless",
+                "source": "ctx.dns.query.length = ctx.dns.query.name.length()",
+                "ignore_failure": true
+            }
+        },
+        {
+            "set": {
+                "if": "ctx._index == 'so-zeek'",
+                "field": "_index",
+                "value": "so-zeek_dns",
+                "override": true
+            }
+        },
+        {
+            "pipeline": {
+                "if": "ctx.dns?.query?.name != null && ctx.dns.query.name.contains('.')",
+                "name": "dns.tld"
+            }
+        },
+        {
+            "pipeline": {
+                "name": "zeek.common"
+            }
+        }
+    ]
 }

salt/elasticsearch/files/ingest/zeek.dpd

@@ -1,20 +0,0 @@
-{
-  "description" : "zeek.dpd",
-  "processors" : [
-    { "set": { "field": "event.dataset", "value": "dpd" } },
-    { "remove":         { "field": ["host"],     "ignore_failure": true                                                                  } },
-    { "json":		{ "field": "message",			"target_field": "message2",		"ignore_failure": true	} },
-    { "dot_expander": 	{ "field": "id.orig_h", 		"path": "message2", 			"ignore_failure": true 	} },
-    { "rename": 	{ "field": "message2.id.orig_h", 	"target_field": "source.ip",		"ignore_missing": true 	} },
-    { "dot_expander": 	{ "field": "id.orig_p", 		"path": "message2",			"ignore_failure": true 	} },
-    { "rename": 	{ "field": "message2.id.orig_p", 	"target_field": "source.port",		"ignore_missing": true 	} },
-    { "dot_expander": 	{ "field": "id.resp_h", 		"path": "message2",			"ignore_failure": true 	} },
-    { "rename": 	{ "field": "message2.id.resp_h", 	"target_field": "destination.ip",	"ignore_missing": true 	} },
-    { "dot_expander": 	{ "field": "id.resp_p", 		"path": "message2",			"ignore_failure": true 	} },
-    { "rename": 	{ "field": "message2.id.resp_p", 	"target_field": "destination.port",	"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.proto", 		"target_field": "network.protocol",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.analyzer", 	"target_field": "observer.analyzer",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.failure_reason", 	"target_field": "error.reason",	"ignore_missing": true 	} },
-    { "pipeline":       { "name": "zeek.common"                                                                                   } }
-  ]
-}

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

@@ -131,6 +131,47 @@ elasticsearch:
                   description: Maximum primary shard size. Once an index reaches this limit, it will be rolled over into a new index.
                   global: True
                   helpLink: elasticsearch.html
+              shrink:
+                method:
+                  description: Shrink the index to a new index with fewer primary shards. Shrink operation is by count or size.
+                  options:
+                  - COUNT
+                  - SIZE
+                  global: True
+                  advanced: True
+                  forcedType: string
+                number_of_shards:
+                  title: shard count
+                  description: Desired shard count. Note that this value is only used when the shrink method selected is 'COUNT'.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                max_primary_shard_size:
+                  title: max shard size
+                  description: Desired shard size in gb/tb/pb eg. 100gb. Note that this value is only used when the shrink method selected is 'SIZE'.
+                  regex: ^[0-9]+(?:gb|tb|pb)$
+                  global: True
+                  forcedType: string
+                  advanced: True
+                allow_write_after_shrink:
+                  description: Allow writes after shrink.
+                  global: True
+                  forcedType: bool
+                  default: False
+                  advanced: True
+              forcemerge:
+                max_num_segments:
+                  description: Reduce the number of segments in each index shard and clean up deleted documents.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                index_codec:
+                  title: compression
+                  description: Use higher compression for stored fields at the cost of slower performance.
+                  forcedType: bool
+                  global: True
+                  default: False
+                  advanced: True
           cold:
             min_age:
               description: Minimum age of index. ex. 60d - This determines when the index should be moved to the cold tier. While still searchable, this tier is typically optimized for lower storage costs rather than search speed. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and cold min_age set to 60 then there will be 30 days from index creation to rollover and then an additional 60 days before moving to cold tier.
@@ -144,6 +185,12 @@ elasticsearch:
                   description: Used for index recovery after a node restart. Indices with higher priorities are recovered before indices with lower priorities.
                   global: True
                   helpLink: elasticsearch.html
+              allocate:
+                number_of_replicas:
+                  description: Set the number of replicas. Remains the same as the previous phase by default.
+                  forcedType: int
+                  global: True
+                  advanced: True
           warm:
             min_age: 
               description: Minimum age of index. ex. 30d - This determines when the index should be moved to the warm tier. Nodes in the warm tier generally don’t need to be as fast as those in the hot tier. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and warm min_age set to 30 then there will be 30 days from index creation to rollover and then an additional 30 days before moving to warm tier.
@@ -158,6 +205,52 @@ elasticsearch:
                   forcedType: int
                   global: True
                   helpLink: elasticsearch.html
+              shrink:
+                method:
+                  description: Shrink the index to a new index with fewer primary shards. Shrink operation is by count or size.
+                  options:
+                  - COUNT
+                  - SIZE
+                  global: True
+                  advanced: True
+                number_of_shards:
+                  title: shard count
+                  description: Desired shard count. Note that this value is only used when the shrink method selected is 'COUNT'.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                max_primary_shard_size:
+                  title: max shard size
+                  description: Desired shard size in gb/tb/pb eg. 100gb. Note that this value is only used when the shrink method selected is 'SIZE'.
+                  regex: ^[0-9]+(?:gb|tb|pb)$
+                  global: True
+                  forcedType: string
+                  advanced: True
+                allow_write_after_shrink:
+                  description: Allow writes after shrink.
+                  global: True
+                  forcedType: bool
+                  default: False
+                  advanced: True
+              forcemerge:
+                max_num_segments:
+                  description: Reduce the number of segments in each index shard and clean up deleted documents.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                index_codec:
+                  title: compression
+                  description: Use higher compression for stored fields at the cost of slower performance.
+                  forcedType: bool
+                  global: True
+                  default: False
+                  advanced: True
+              allocate:
+                number_of_replicas:
+                  description: Set the number of replicas. Remains the same as the previous phase by default.
+                  forcedType: int
+                  global: True
+                  advanced: True
           delete:
             min_age:
               description: Minimum age of index. ex. 90d - This determines when the index should be deleted. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and delete min_age set to 90 then there will be 30 days from index creation to rollover and then an additional 90 days before deletion.
@@ -287,6 +380,47 @@ elasticsearch:
                   global: True
                   advanced: True
                   helpLink: elasticsearch.html
+              shrink:
+                method:
+                  description: Shrink the index to a new index with fewer primary shards. Shrink operation is by count or size.
+                  options:
+                  - COUNT
+                  - SIZE
+                  global: True
+                  advanced: True
+                  forcedType: string
+                number_of_shards:
+                  title: shard count
+                  description: Desired shard count. Note that this value is only used when the shrink method selected is 'COUNT'.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                max_primary_shard_size:
+                  title: max shard size
+                  description: Desired shard size in gb/tb/pb eg. 100gb. Note that this value is only used when the shrink method selected is 'SIZE'.
+                  regex: ^[0-9]+(?:gb|tb|pb)$
+                  global: True
+                  forcedType: string
+                  advanced: True
+                allow_write_after_shrink:
+                  description: Allow writes after shrink.
+                  global: True
+                  forcedType: bool
+                  default: False
+                  advanced: True
+              forcemerge:
+                max_num_segments:
+                  description: Reduce the number of segments in each index shard and clean up deleted documents.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                index_codec:
+                  title: compression
+                  description: Use higher compression for stored fields at the cost of slower performance.
+                  forcedType: bool
+                  global: True
+                  default: False
+                  advanced: True
           warm:
             min_age:
               description: Minimum age of index. ex. 30d - This determines when the index should be moved to the warm tier. Nodes in the warm tier generally don’t need to be as fast as those in the hot tier. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and warm min_age set to 30 then there will be 30 days from index creation to rollover and then an additional 30 days before moving to warm tier.
@@ -314,6 +448,52 @@ elasticsearch:
                   global: True
                   advanced: True
                   helpLink: elasticsearch.html
+              shrink:
+                method:
+                  description: Shrink the index to a new index with fewer primary shards. Shrink operation is by count or size.
+                  options:
+                  - COUNT
+                  - SIZE
+                  global: True
+                  advanced: True
+                number_of_shards:
+                  title: shard count
+                  description: Desired shard count. Note that this value is only used when the shrink method selected is 'COUNT'.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                max_primary_shard_size:
+                  title: max shard size
+                  description: Desired shard size in gb/tb/pb eg. 100gb. Note that this value is only used when the shrink method selected is 'SIZE'.
+                  regex: ^[0-9]+(?:gb|tb|pb)$
+                  global: True
+                  forcedType: string
+                  advanced: True
+                allow_write_after_shrink:
+                  description: Allow writes after shrink.
+                  global: True
+                  forcedType: bool
+                  default: False
+                  advanced: True
+              forcemerge:
+                max_num_segments:
+                  description: Reduce the number of segments in each index shard and clean up deleted documents.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                index_codec:
+                  title: compression
+                  description: Use higher compression for stored fields at the cost of slower performance.
+                  forcedType: bool
+                  global: True
+                  default: False
+                  advanced: True
+              allocate:
+                number_of_replicas:
+                  description: Set the number of replicas. Remains the same as the previous phase by default.
+                  forcedType: int
+                  global: True
+                  advanced: True
           cold:
             min_age:
               description: Minimum age of index. ex. 60d - This determines when the index should be moved to the cold tier.  While still searchable, this tier is typically optimized for lower storage costs rather than search speed. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and cold min_age set to 60 then there will be 30 days from index creation to rollover and then an additional 60 days before moving to cold tier.
@@ -330,6 +510,12 @@ elasticsearch:
                   global: True
                   advanced: True
                   helpLink: elasticsearch.html
+              allocate:
+                number_of_replicas:
+                  description: Set the number of replicas. Remains the same as the previous phase by default.
+                  forcedType: int
+                  global: True
+                  advanced: True
           delete:
             min_age:
               description: Minimum age of index. ex. 90d - This determines when the index should be deleted. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and delete min_age set to 90 then there will be 30 days from index creation to rollover and then an additional 90 days before deletion.
@@ -392,6 +578,7 @@ 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/elasticsearch/template.map.jinja

@@ -61,5 +61,55 @@
 {%       do settings.index_template.template.settings.index.pop('sort') %}
 {%     endif %}
 {%   endif %}
+
+{# advanced ilm actions #}
+{%   if settings.policy is defined and settings.policy.phases is defined %}
+{%     set PHASE_NAMES = ["hot", "warm", "cold"] %}
+{%     for P in PHASE_NAMES %}
+{%       if settings.policy.phases[P] is defined and settings.policy.phases[P].actions is defined %}
+{%         set PHASE = settings.policy.phases[P].actions %}
+{#         remove allocate action if number_of_replicas isn't configured #}
+{%         if PHASE.allocate is defined %}
+{%           if PHASE.allocate.number_of_replicas is not defined or PHASE.allocate.number_of_replicas == "" %}
+{%             do PHASE.pop('allocate', none) %}
+{%           endif %}
+{%         endif %}
+{#         start shrink action #}
+{%         if PHASE.shrink is defined %}
+{%           if PHASE.shrink.method is defined %}
+{%             if PHASE.shrink.method == 'COUNT' and PHASE.shrink.number_of_shards is defined and PHASE.shrink.number_of_shards %}
+{#               remove max_primary_shard_size value when doing shrink operation by count vs size #}
+{%               do PHASE.shrink.pop('max_primary_shard_size', none) %}
+{%             elif PHASE.shrink.method == 'SIZE' and PHASE.shrink.max_primary_shard_size is defined and PHASE.shrink.max_primary_shard_size %}
+{#               remove number_of_shards value when doing shrink operation by size vs count #}
+{%               do PHASE.shrink.pop('number_of_shards', none) %}
+{%             else %}
+{#               method isn't defined or missing a required config number_of_shards/max_primary_shard_size #}
+{%               do PHASE.pop('shrink', none) %}
+{%             endif %}
+{%           endif %}
+{%         endif %}
+{#         always remove shrink method since its only used for SOC config, not in the actual ilm policy #}
+{%         if PHASE.shrink is defined %}
+{%            do PHASE.shrink.pop('method', none) %}
+{%         endif %}
+{#         end shrink action #}
+{#         start force merge #}
+{%         if PHASE.forcemerge is defined %}
+{%           if PHASE.forcemerge.index_codec is defined and PHASE.forcemerge.index_codec %}
+{%             do PHASE.forcemerge.update({'index_codec': 'best_compression'}) %}
+{%           else %}
+{%             do PHASE.forcemerge.pop('index_codec', none) %}
+{%           endif %}
+{%           if PHASE.forcemerge.max_num_segments is not defined or not PHASE.forcemerge.max_num_segments %}
+{#             max_num_segments is empty, drop it #}
+{%             do PHASE.pop('forcemerge', none) %}
+{%           endif %}
+{%         endif %}
+{#         end force merge #}
+{%       endif %}
+{%     endfor %}
+{%   endif %}
+
 {%   do ES_INDEX_SETTINGS.update({index | replace("_x_", "."): ES_INDEX_SETTINGS_GLOBAL_OVERRIDES[index]}) %}
 {% endfor %}

salt/elasticsearch/templates/component/ecs/suricata.json

@@ -841,6 +841,10 @@
                   "type": "long"
                 }
               }
+            },
+            "capture_file": {
+                "type": "keyword",
+                "ignore_above": 1024
             }
           }
         }

salt/elasticsearch/templates/component/elastic-agent/so-elastic-agent-monitor.json

@@ -0,0 +1,43 @@
+{
+  "template": {
+    "mappings": {
+      "properties": {
+        "agent": {
+          "type": "object",
+          "properties": {
+            "hostname": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "id": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "last_checkin_status": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "last_checkin": {
+              "type": "date"
+            },
+            "name": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "offline_duration_hours": {
+              "type": "integer"
+            },
+            "policy_id": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            },
+            "status": {
+              "ignore_above": 1024,
+              "type": "keyword"
+            }
+          }
+        }
+      }
+    }
+  }
+}

salt/elasticsearch/templates/component/so/assistant-chat-mappings.json

@@ -0,0 +1,104 @@
+{
+	"template": {
+		"mappings": {
+			"properties": {
+				"@timestamp": {
+					"type": "date"
+				},
+				"so_kind": {
+					"ignore_above": 1024,
+					"type": "keyword"
+				},
+				"so_operation": {
+					"ignore_above": 1024,
+					"type": "keyword"
+				},
+				"so_chat": {
+					"properties": {
+						"role": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"content": {
+							"type": "object",
+							"enabled": false
+						},
+						"sessionId": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"createTime": {
+							"type": "date"
+						},
+						"deletedAt": {
+							"type": "date"
+						},
+						"tags": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"tool_use_id": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"userId": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"message": {
+							"properties": {
+								"id": {
+									"ignore_above": 1024,
+									"type": "keyword"
+								},
+								"type": {
+									"ignore_above": 1024,
+									"type": "keyword"
+								},
+								"role": {
+									"ignore_above": 1024,
+									"type": "keyword"
+								},
+								"model": {
+									"ignore_above": 1024,
+									"type": "keyword"
+								},
+								"contentStr": {
+									"type": "text"
+								},
+								"contentBlocks": {
+									"type": "nested",
+									"enabled": false
+								},
+								"stopReason": {
+									"ignore_above": 1024,
+									"type": "keyword"
+								},
+								"stopSequence": {
+									"ignore_above": 1024,
+									"type": "keyword"
+								},
+								"usage": {
+									"properties": {
+										"input_tokens": {
+											"type": "long"
+										},
+										"output_tokens": {
+											"type": "long"
+										},
+										"credits": {
+											"type": "long"
+										}
+									}
+								}
+							}
+						}
+					}
+				}
+			}
+		}
+	},
+	"_meta": {
+		"ecs_version": "1.12.2"
+	}
+}

salt/elasticsearch/templates/component/so/assistant-chat-settings.json

@@ -0,0 +1,7 @@
+{
+	"template": {},
+	"version": 1,
+	"_meta": {
+		"description": "default settings for common Security Onion Assistant indices"
+	}
+}

salt/elasticsearch/templates/component/so/assistant-session-mappings.json

@@ -0,0 +1,44 @@
+{
+	"template": {
+		"mappings": {
+			"properties": {
+				"@timestamp": {
+					"type": "date"
+				},
+				"so_kind": {
+					"ignore_above": 1024,
+					"type": "keyword"
+				},
+				"so_session": {
+					"properties": {
+						"title": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"sessionId": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"createTime": {
+							"type": "date"
+						},
+						"deleteTime": {
+							"type": "date"
+						},
+						"tags": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						},
+						"userId": {
+							"ignore_above": 1024,
+							"type": "keyword"
+						}
+					}
+				}
+			}
+		}
+	},
+	"_meta": {
+		"ecs_version": "1.12.2"
+	}
+}

salt/elasticsearch/templates/component/so/assistant-session-settings.json

@@ -0,0 +1,7 @@
+{
+	"template": {},
+	"version": 1,
+	"_meta": {
+		"description": "default settings for common Security Onion Assistant indices"
+	}
+}

salt/firewall/defaults.yaml

@@ -909,6 +909,15 @@ firewall:
                 - elastic_agent_control
                 - elastic_agent_data
                 - elastic_agent_update
+            hypervisor:
+              portgroups:
+                - yum
+                - docker_registry
+                - influxdb
+                - elastic_agent_control
+                - elastic_agent_data
+                - elastic_agent_update
+                - sensoroni
             customhostgroup0:
               portgroups: []
             customhostgroup1:
@@ -961,6 +970,9 @@ firewall:
             desktop:
               portgroups:
                 - salt_manager
+            hypervisor:
+              portgroups:
+                - salt_manager
             self:
               portgroups:
                 - syslog
@@ -1113,6 +1125,15 @@ firewall:
                 - elastic_agent_control
                 - elastic_agent_data
                 - elastic_agent_update
+            hypervisor:
+              portgroups:
+                - yum
+                - docker_registry
+                - influxdb
+                - elastic_agent_control
+                - elastic_agent_data
+                - elastic_agent_update
+                - sensoroni
             customhostgroup0:
               portgroups: []
             customhostgroup1:
@@ -1168,6 +1189,9 @@ firewall:
             desktop:
               portgroups:
                 - salt_manager
+            hypervisor:
+              portgroups:
+                - salt_manager
             self:
               portgroups:
                 - syslog
@@ -1206,6 +1230,10 @@ firewall:
               portgroups:
                 - elasticsearch_node
                 - elasticsearch_rest
+            managerhype:
+              portgroups:
+                - elasticsearch_node
+                - elasticsearch_rest
             standalone:
               portgroups:
                 - elasticsearch_node
@@ -1353,6 +1381,10 @@ firewall:
               portgroups:
                 - elasticsearch_node
                 - elasticsearch_rest
+            managerhype:
+              portgroups:
+                - elasticsearch_node
+                - elasticsearch_rest
             standalone:
               portgroups:
                 - elasticsearch_node
@@ -1555,6 +1587,9 @@ firewall:
               portgroups:
                 - redis
                 - elastic_agent_data
+            managerhype:
+              portgroups:
+                - elastic_agent_data
             self:
               portgroups:
                 - redis
@@ -1672,6 +1707,9 @@ firewall:
             managersearch:
               portgroups:
                 - openssh
+            managerhype:
+              portgroups:
+                - openssh
             standalone:
               portgroups:
                 - openssh
@@ -1734,6 +1772,8 @@ firewall:
               portgroups: []
             managersearch:
               portgroups: []
+            managerhype:
+              portgroups: []
             standalone:
               portgroups: []
             customhostgroup0:

salt/firewall/iptables.jinja

@@ -91,7 +91,7 @@ COMMIT
 -A INPUT -m conntrack --ctstate INVALID -j DROP
 -A INPUT -p icmp -j ACCEPT
 -A INPUT -j LOGGING
-{% if GLOBALS.role in ['so-hypervisor', 'so-managerhyper'] -%}
+{% if GLOBALS.role in ['so-hypervisor', 'so-managerhype'] -%}
 -A FORWARD -m state --state RELATED,ESTABLISHED -j ACCEPT
 -A FORWARD -i br0 -o br0 -j ACCEPT
 {%- endif %}

salt/firewall/map.jinja

@@ -25,7 +25,7 @@
 {%   set KAFKA_EXTERNAL_ACCESS = salt['pillar.get']('kafka:config:external_access:enabled', default=False) %}
 {%   set kafka_node_type = salt['pillar.get']('kafka:nodes:'+ GLOBALS.hostname + ':role') %}
 
-{%   if role in ['manager', 'managersearch', 'standalone'] %}
+{%   if role.startswith('manager') or role == 'standalone' %}
 {%     do FIREWALL_DEFAULT.firewall.role[role].chain["DOCKER-USER"].hostgroups[role].portgroups.append('kafka_controller') %}
 {%     do FIREWALL_DEFAULT.firewall.role[role].chain["DOCKER-USER"].hostgroups.receiver.portgroups.append('kafka_controller') %}
 {%   endif %}
@@ -38,8 +38,8 @@
 {%     do FIREWALL_DEFAULT.firewall.role[role].chain["DOCKER-USER"].hostgroups.receiver.portgroups.append('kafka_controller') %}
 {%   endif %}
 
-{%   if role in ['manager', 'managersearch', 'standalone', 'receiver'] %}
-{%     for r in ['manager', 'managersearch', 'standalone', 'receiver', 'fleet', 'idh', 'sensor', 'searchnode','heavynode', 'elastic_agent_endpoint', 'desktop'] %}
+{%   if role.startswith('manager') or role in ['standalone', 'receiver'] %}
+{%     for r in ['manager', 'managersearch', 'managerhype', 'standalone', 'receiver', 'fleet', 'idh', 'sensor', 'searchnode','heavynode', 'elastic_agent_endpoint', 'desktop'] %}
 {%       if FIREWALL_DEFAULT.firewall.role[role].chain["DOCKER-USER"].hostgroups[r] is defined %}
 {%         do FIREWALL_DEFAULT.firewall.role[role].chain["DOCKER-USER"].hostgroups[r].portgroups.append('kafka_data') %}
 {%       endif %}
@@ -48,11 +48,11 @@
 
 {%   if KAFKA_EXTERNAL_ACCESS %}
 {#     Kafka external access only applies for Kafka nodes with the broker role. #}
-{%     if role in ['manager', 'managersearch', 'standalone', 'receiver'] and 'broker' in kafka_node_type %}
+{%     if role.startswith('manager') or role in ['standalone', 'receiver'] and 'broker' in kafka_node_type %}
 {%       do FIREWALL_DEFAULT.firewall.role[role].chain["DOCKER-USER"].hostgroups.external_kafka.portgroups.append('kafka_external_access') %}
 {%     endif %}
 {%   endif %}
 
 {% endif %}
 
-{% set FIREWALL_MERGED = salt['pillar.get']('firewall', FIREWALL_DEFAULT.firewall, merge=True) %}
+{% set FIREWALL_MERGED = salt['pillar.get']('firewall', FIREWALL_DEFAULT.firewall, merge=True) %}

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 +1,591 @@
+#!/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-<epoch_timestamp>.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-<epoch_timestamp>.img`.
+- The epoch timestamp ensures unique volume names and prevents conflicts.
+- 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 time
+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
+    """
+    # Generate epoch timestamp for unique volume naming
+    epoch_timestamp = int(time.time())
+    
+    # Define volume path with epoch timestamp for uniqueness
+    volume_path = os.path.join(VOLUME_DIR, f"{vm_name}-nsm-{epoch_timestamp}.img")
+    
+    # Check if volume already exists (shouldn't be possible with timestamp)
+    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: "8.18.4"
+      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

@@ -3,8 +3,10 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-{%  from 'libvirt/map.jinja' import LIBVIRTMERGED %}
-{%  from 'salt/map.jinja' import SYSTEMD_UNIT_FILE %}
+# 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:
@@ -29,21 +31,14 @@ wait_for_br0_ip:
     - timeout: 95
     - onchanges:
       - cmd: down_original_mgmt_interface
-
-update_mine_functions:
-  file.managed:
-    - name: /etc/salt/minion.d/mine_functions.conf
-    - contents: |
-        mine_interval: 25
-        mine_functions:
-          network.ip_addrs:
-            - interface: br0
-    - 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
+      - file: salt_minion_service_unit_file
+      - file: mine_functions

salt/libvirt/init.sls

@@ -31,6 +31,19 @@ libvirt_conf_dir:
     - group: 939
     - makedirs: True
 
+libvirt_volumes:
+  file.directory:
+    - name: /nsm/libvirt/volumes
+    - user: qemu
+    - group: qemu
+    - dir_mode: 755
+    - file_mode: 640
+    - recurse:
+      - user
+      - group
+      - mode
+    - makedirs: True
+
 libvirt_config:
   file.managed:
     - name: /opt/so/conf/libvirt/libvirtd.conf

salt/logrotate/defaults.yaml

@@ -268,3 +268,12 @@ logrotate:
       - nocompress
       - create
       - sharedscripts
+    /opt/so/log/agents/agent-monitor*_x_log:
+      - daily
+      - rotate 14
+      - missingok
+      - compress
+      - create
+      - extension .log
+      - dateext
+      - dateyesterday

salt/logrotate/soc_logrotate.yaml

@@ -175,3 +175,10 @@ logrotate:
       multiline: True
       global: True
       forcedType: "[]string"
+    "/opt/so/log/agents/agent-monitor*_x_log":
+      description: List of logrotate options for this file.
+      title: /opt/so/log/agents/agent-monitor*.log
+      advanced: True
+      multiline: True
+      global: True
+      forcedType: "[]string"

salt/logstash/map.jinja

@@ -17,7 +17,7 @@
 
 {% for node_type, node_details in redis_node_data.items() | sort %}
 {%   if GLOBALS.role in ['so-searchnode', 'so-standalone', 'so-managersearch', 'so-fleet'] %}
-{%     if node_type in ['manager', 'managersearch', 'standalone', 'receiver' ] %}
+{%     if node_type.startswith('manager') or node_type in ['standalone', 'receiver'] %}
 {%       for hostname in redis_node_data[node_type].keys() %}
 {%         do LOGSTASH_REDIS_NODES.append({hostname:node_details[hostname].ip}) %}
 {%       endfor %}
@@ -47,7 +47,7 @@
 {%   endif %}
 {# Disable logstash on manager & receiver nodes unless it has an override configured #}
 {%   if not KAFKA_LOGSTASH %}
-{%     if GLOBALS.role in ['so-manager', 'so-receiver'] and GLOBALS.hostname not in KAFKA_LOGSTASH %}
+{%     if GLOBALS.role in ['so-manager', 'so-managerhype', 'so-receiver'] and GLOBALS.hostname not in KAFKA_LOGSTASH %}
 {%       do LOGSTASH_MERGED.update({'enabled': False}) %}
 {%     endif %}
 {%   endif %}

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/defaults.yaml

@@ -5,3 +5,12 @@ manager:
     minute: 0
   additionalCA: ''
   insecureSkipVerify: False
+  agent_monitoring:
+    enabled: False
+    config:
+      critical_agents: []
+      custom_kquery:
+      offline_threshold: 5
+      realert_threshold: 5
+      page_size: 250
+      run_interval: 5

salt/manager/init.sls

@@ -34,6 +34,26 @@ agents_log_dir:
       - user
       - group
 
+agents_conf_dir:
+  file.directory:
+    - name: /opt/so/conf/agents
+    - user: root
+    - group: root
+    - recurse:
+      - user
+      - group
+
+{% if MANAGERMERGED.agent_monitoring.config.critical_agents | length > 0 %}
+critical_agents_patterns:
+  file.managed:
+    - name: /opt/so/conf/agents/critical-agents.txt
+    - contents: {{ MANAGERMERGED.agent_monitoring.config.critical_agents }}
+{% else %}
+remove_critical_agents_config:
+  file.absent:
+    - name: /opt/so/conf/agents/critical-agents.txt
+{% endif %}
+
 yara_log_dir:
   file.directory:
     - name: /opt/so/log/yarasync
@@ -127,6 +147,21 @@ so_fleetagent_status:
     - month: '*'
     - dayweek: '*'
 
+so_fleetagent_monitor:
+{% if MANAGERMERGED.agent_monitoring.enabled %}
+  cron.present:
+{% else %}
+  cron.absent:
+{% endif %}
+  - name: /bin/flock -n /opt/so/log/agents/agent-monitor.lock /usr/sbin/so-elastic-agent-monitor
+  - identifier: so_fleetagent_monitor
+  - user: root
+  - minute: '*/{{ MANAGERMERGED.agent_monitoring.config.run_interval }}'
+  - hour: '*'
+  - daymonth: '*'
+  - month: '*'
+  - dayweek: '*'
+
 socore_own_saltstack_default:
   file.directory:
     - name: /opt/so/saltstack/default

salt/manager/managed_soc_annotations.sls

@@ -25,13 +25,11 @@
            {% set index_settings = es.get('index_settings', {}) %}
            {% set input = index_settings.get('so-logs', {}) %}
            {% for k in matched_integration_names %}
-           {%   if k not in index_settings %}
-           {%     set _ = index_settings.update({k: input}) %}
-           {%   endif %}
+           {%   do index_settings.update({k: input}) %}
            {% endfor %}
            {% for k in addon_integration_keys %}
            {%   if k not in matched_integration_names and k in index_settings %}
-           {%     set _ = index_settings.pop(k) %}
+           {%     do index_settings.pop(k) %}
            {%   endif %}
            {% endfor %}
            {{ data }}
@@ -45,14 +43,12 @@
            {% set es = data.get('elasticsearch', {}) %}
            {% set index_settings = es.get('index_settings', {}) %}
            {% for k in matched_integration_names %}
-           {%   if k not in index_settings %}
-           {%     set input = ADDON_INTEGRATION_DEFAULTS[k] %}
-           {%     set _ = index_settings.update({k: input})%}
-           {%   endif %}
+           {%   set input = ADDON_INTEGRATION_DEFAULTS[k] %}
+           {%     do index_settings.update({k: input})%}
            {% endfor %}
            {% for k in addon_integration_keys %}
            {%   if k not in matched_integration_names and k in index_settings %}
-           {%     set _ = index_settings.pop(k) %}
+           {%     do index_settings.pop(k) %}
            {%   endif %}
            {% endfor %}
            {{ data }}

salt/manager/soc_manager.yaml

@@ -37,3 +37,44 @@ manager:
     forcedType: bool
     global: True
     helpLink: proxy.html
+  agent_monitoring:
+    enabled:
+      description: Enable monitoring elastic agents for health issues. Can be used to trigger an alert when a 'critical' agent hasn't checked in with fleet for longer than the configured offline threshold.
+      global: True
+      helpLink: elastic-fleet.html
+      forcedType: bool
+    config:
+      critical_agents:
+        description: List of 'critical' agents to log when they haven't checked in longer than the maximum allowed time. If there are no 'critical' agents specified all offline agents will be logged once they reach the offline threshold.
+        global: True
+        multiline: True
+        helpLink: elastic-fleet.html
+        forcedType: "[]string"
+      custom_kquery:
+        description: For more granular control over what agents to monitor for offline|degraded status add a kquery here. It is recommended to create & test within Elastic Fleet first to ensure your agents are targeted correctly using the query. eg 'status:offline AND tags:INFRA'
+        global: True
+        helpLink: elastic-fleet.html
+        forcedType: string
+        advanced: True
+      offline_threshold:
+        description: The maximum allowed time in hours a 'critical' agent has been offline before being logged.
+        global: True
+        helpLink: elastic-fleet.html
+        forcedType: int
+      realert_threshold:
+        description: The time to pass before another alert for an offline agent exceeding the offline_threshold is generated.
+        global: True
+        helpLink: elastic-fleet.html
+        forcedType: int
+      page_size:
+        description: The amount of agents that can be processed per API request to fleet.
+        global: True
+        helpLink: elastic-fleet.html
+        forcedType: int
+        advanced: True
+      run_interval:
+        description: The time in minutes between checking fleet agent statuses.
+        global: True
+        advanced: True
+        helpLink: elastic-fleet.html
+        forcedType: int

salt/manager/tools/sbin/so-minion

@@ -454,6 +454,7 @@ function add_sensor_to_minion() {
         echo "sensor:"
         echo "  interface: '$INTERFACE'"
         echo "  mtu: 9000"
+		echo "  channels: 1"
         echo "zeek:"
         echo "  enabled: True"
         echo "  config:"

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/so-yaml.py

@@ -17,6 +17,7 @@ def showUsage(args):
     print('Usage: {} <COMMAND> <YAML_FILE> [ARGS...]'.format(sys.argv[0]), file=sys.stderr)
     print('  General commands:', file=sys.stderr)
     print('    append         - Append a list item to a yaml key, if it exists and is a list. Requires KEY and LISTITEM args.', file=sys.stderr)
+    print('    removelistitem - Remove a list item from a yaml key, if it exists and is a list. Requires KEY and LISTITEM args.', file=sys.stderr)
     print('    add            - Add a new key and set its value. Fails if key already exists. Requires KEY and VALUE args.', file=sys.stderr)
     print('    get            - Displays (to stdout) the value stored in the given key. Requires KEY arg.', file=sys.stderr)
     print('    remove         - Removes a yaml key, if it exists. Requires KEY arg.', file=sys.stderr)
@@ -26,8 +27,8 @@ def showUsage(args):
     print('  Where:', file=sys.stderr)
     print('   YAML_FILE       - Path to the file that will be modified. Ex: /opt/so/conf/service/conf.yaml', file=sys.stderr)
     print('   KEY             - YAML key, does not support \' or " characters at this time. Ex: level1.level2', file=sys.stderr)
-    print('   VALUE           - Value to set for a given key', file=sys.stderr)
-    print('   LISTITEM        - Item to append to a given key\'s list value', file=sys.stderr)
+    print('   VALUE           - Value to set for a given key. Can be a literal value or file:<path> to load from a YAML file.', file=sys.stderr)
+    print('   LISTITEM        - Item to append to a given key\'s list value. Can be a literal value or file:<path> to load from a YAML file.', file=sys.stderr)
     sys.exit(1)
 
 
@@ -57,8 +58,32 @@ def appendItem(content, key, listItem):
             return 1
 
 
+def removeListItem(content, key, listItem):
+    pieces = key.split(".", 1)
+    if len(pieces) > 1:
+        removeListItem(content[pieces[0]], pieces[1], listItem)
+    else:
+        try:
+            if not isinstance(content[key], list):
+                raise AttributeError("Value is not a list")
+            if listItem in content[key]:
+                content[key].remove(listItem)
+        except (AttributeError, TypeError):
+            print("The existing value for the given key is not a list. No action was taken on the file.", file=sys.stderr)
+            return 1
+        except KeyError:
+            print("The key provided does not exist. No action was taken on the file.", file=sys.stderr)
+            return 1
+
+
 def convertType(value):
-    if isinstance(value, str) and len(value) > 0 and (not value.startswith("0") or len(value) == 1):
+    if isinstance(value, str) and value.startswith("file:"):
+        path = value[5:]  # Remove "file:" prefix
+        if not os.path.exists(path):
+            print(f"File '{path}' does not exist.", file=sys.stderr)
+            sys.exit(1)
+        return loadYaml(path)
+    elif isinstance(value, str) and len(value) > 0 and (not value.startswith("0") or len(value) == 1):
         if "." in value:
             try:
                 value = float(value)
@@ -97,6 +122,23 @@ def append(args):
     return 0
 
 
+def removelistitem(args):
+    if len(args) != 3:
+        print('Missing filename, key arg, or list item to remove', file=sys.stderr)
+        showUsage(None)
+        return 1
+
+    filename = args[0]
+    key = args[1]
+    listItem = args[2]
+
+    content = loadYaml(filename)
+    removeListItem(content, key, convertType(listItem))
+    writeYaml(filename, content)
+
+    return 0
+
+
 def addKey(content, key, value):
     pieces = key.split(".", 1)
     if len(pieces) > 1:
@@ -205,6 +247,7 @@ def main():
         "help": showUsage,
         "add": add,
         "append": append,
+        "removelistitem": removelistitem,
         "get": get,
         "remove": remove,
         "replace": replace,

salt/manager/tools/sbin/so-yaml_test.py

@@ -361,6 +361,29 @@ class TestRemove(unittest.TestCase):
         self.assertEqual(soyaml.convertType("FALSE"), False)
         self.assertEqual(soyaml.convertType(""), "")
 
+    def test_convert_file(self):
+        import tempfile
+        import os
+
+        # Create a temporary YAML file
+        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
+            f.write("test:\n  - name: hi\n    color: blue\n")
+            temp_file = f.name
+
+        try:
+            result = soyaml.convertType(f"file:{temp_file}")
+            expected = {"test": [{"name": "hi", "color": "blue"}]}
+            self.assertEqual(result, expected)
+        finally:
+            os.unlink(temp_file)
+
+    def test_convert_file_nonexistent(self):
+        with self.assertRaises(SystemExit) as cm:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                soyaml.convertType("file:/nonexistent/file.yaml")
+                self.assertEqual(cm.exception.code, 1)
+                self.assertIn("File '/nonexistent/file.yaml' does not exist.", mock_stderr.getvalue())
+
     def test_get_int(self):
         with patch('sys.stdout', new=StringIO()) as mock_stdout:
             filename = "/tmp/so-yaml_test-get.yaml"
@@ -434,3 +457,126 @@ class TestRemove(unittest.TestCase):
                 self.assertEqual(result, 1)
                 self.assertIn("Missing filename or key arg", mock_stderr.getvalue())
                 sysmock.assert_called_once_with(1)
+
+
+class TestRemoveListItem(unittest.TestCase):
+
+    def test_removelistitem_missing_arg(self):
+        with patch('sys.exit', new=MagicMock()) as sysmock:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                sys.argv = ["cmd", "help"]
+                soyaml.removelistitem(["file", "key"])
+                sysmock.assert_called()
+                self.assertIn("Missing filename, key arg, or list item to remove", mock_stderr.getvalue())
+
+    def test_removelistitem(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: { child1: 123, child2: abc }, key2: false, key3: [a,b,c]}")
+        file.close()
+
+        soyaml.removelistitem([filename, "key3", "b"])
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "key1:\n  child1: 123\n  child2: abc\nkey2: false\nkey3:\n- a\n- c\n"
+        self.assertEqual(actual, expected)
+
+    def test_removelistitem_nested(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: { child1: 123, child2: [a,b,c] }, key2: false, key3: [e,f,g]}")
+        file.close()
+
+        soyaml.removelistitem([filename, "key1.child2", "b"])
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "key1:\n  child1: 123\n  child2:\n  - a\n  - c\nkey2: false\nkey3:\n- e\n- f\n- g\n"
+        self.assertEqual(actual, expected)
+
+    def test_removelistitem_nested_deep(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: { child1: 123, child2: { deep1: 45, deep2: [a,b,c] } }, key2: false, key3: [e,f,g]}")
+        file.close()
+
+        soyaml.removelistitem([filename, "key1.child2.deep2", "b"])
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "key1:\n  child1: 123\n  child2:\n    deep1: 45\n    deep2:\n    - a\n    - c\nkey2: false\nkey3:\n- e\n- f\n- g\n"
+        self.assertEqual(actual, expected)
+
+    def test_removelistitem_item_not_in_list(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: [a,b,c]}")
+        file.close()
+
+        soyaml.removelistitem([filename, "key1", "d"])
+
+        file = open(filename, "r")
+        actual = file.read()
+        file.close()
+
+        expected = "key1:\n- a\n- b\n- c\n"
+        self.assertEqual(actual, expected)
+
+    def test_removelistitem_key_noexist(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: { child1: 123, child2: { deep1: 45, deep2: [a,b,c] } }, key2: false, key3: [e,f,g]}")
+        file.close()
+
+        with patch('sys.exit', new=MagicMock()) as sysmock:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                sys.argv = ["cmd", "removelistitem", filename, "key4", "h"]
+                soyaml.main()
+                sysmock.assert_called()
+                self.assertEqual("The key provided does not exist. No action was taken on the file.\n", mock_stderr.getvalue())
+
+    def test_removelistitem_key_noexist_deep(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: { child1: 123, child2: { deep1: 45, deep2: [a,b,c] } }, key2: false, key3: [e,f,g]}")
+        file.close()
+
+        with patch('sys.exit', new=MagicMock()) as sysmock:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                sys.argv = ["cmd", "removelistitem", filename, "key1.child2.deep3", "h"]
+                soyaml.main()
+                sysmock.assert_called()
+                self.assertEqual("The key provided does not exist. No action was taken on the file.\n", mock_stderr.getvalue())
+
+    def test_removelistitem_key_nonlist(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: { child1: 123, child2: { deep1: 45, deep2: [a,b,c] } }, key2: false, key3: [e,f,g]}")
+        file.close()
+
+        with patch('sys.exit', new=MagicMock()) as sysmock:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                sys.argv = ["cmd", "removelistitem", filename, "key1", "h"]
+                soyaml.main()
+                sysmock.assert_called()
+                self.assertEqual("The existing value for the given key is not a list. No action was taken on the file.\n", mock_stderr.getvalue())
+
+    def test_removelistitem_key_nonlist_deep(self):
+        filename = "/tmp/so-yaml_test-removelistitem.yaml"
+        file = open(filename, "w")
+        file.write("{key1: { child1: 123, child2: { deep1: 45, deep2: [a,b,c] } }, key2: false, key3: [e,f,g]}")
+        file.close()
+
+        with patch('sys.exit', new=MagicMock()) as sysmock:
+            with patch('sys.stderr', new=StringIO()) as mock_stderr:
+                sys.argv = ["cmd", "removelistitem", filename, "key1.child2.deep1", "h"]
+                soyaml.main()
+                sysmock.assert_called()
+                self.assertEqual("The existing value for the given key is not a list. No action was taken on the file.\n", mock_stderr.getvalue())

salt/manager/tools/sbin/soup

@@ -21,6 +21,9 @@ whiptail_title='Security Onion UPdater'
 NOTIFYCUSTOMELASTICCONFIG=false
 TOPFILE=/opt/so/saltstack/default/salt/top.sls
 BACKUPTOPFILE=/opt/so/saltstack/default/salt/top.sls.backup
+SALTUPGRADED=false
+SALT_CLOUD_INSTALLED=false
+SALT_CLOUD_CONFIGURED=false
 # used to display messages to the user at the end of soup
 declare -a FINAL_MESSAGE_QUEUE=()
 
@@ -169,6 +172,8 @@ 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
 }
@@ -269,7 +274,7 @@ check_os_updates() {
         if [[ "$confirm" == [cC] ]]; then
           echo "Continuing without updating packages"
         elif [[ "$confirm" == [uU] ]]; then
-          echo "Applying Grid Updates"
+          echo "Applying Grid Updates. The following patch.os salt state may take a while depending on how many packages need to be updated."
           update_flag=true
         else
           echo "Exiting soup"
@@ -419,6 +424,9 @@ preupgrade_changes() {
     [[ "$INSTALLEDVERSION" == 2.4.141 ]] && up_to_2.4.150
     [[ "$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
+    [[ "$INSTALLEDVERSION" == 2.4.180 ]] && up_to_2.4.190
+    [[ "$INSTALLEDVERSION" == 2.4.190 ]] && up_to_2.4.200
     true
 }
 
@@ -448,6 +456,9 @@ postupgrade_changes() {
     [[ "$POSTVERSION"  == 2.4.141 ]] && post_to_2.4.150
     [[ "$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
+    [[ "$POSTVERSION"  == 2.4.180 ]] && post_to_2.4.190
+    [[ "$POSTVERSION"  == 2.4.190 ]] && post_to_2.4.200
     true
 }
 
@@ -588,9 +599,6 @@ post_to_2.4.160() {
 }
 
 post_to_2.4.170() {
-  echo "Regenerating Elastic Agent Installers"
-  /sbin/so-elastic-agent-gen-installers
-
   # Update kibana default space
   salt-call state.apply kibana.config queue=True
   echo "Updating Kibana default space"
@@ -599,6 +607,42 @@ post_to_2.4.170() {
   POSTVERSION=2.4.170
 }
 
+post_to_2.4.180() {
+  # 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" ]] || [[ "$pipeline" == "REDIS" ]]; then
+        # Check if this grid is currently affected by corrupt fleet output policy
+        if elastic-agent status | grep "config: key file not configured" > /dev/null 2>&1; then
+            echo "Elastic Agent shows an ssl error connecting to logstash output. Updating output policy..."
+            update_default_logstash_output
+        fi
+    fi
+    # Apply new elasticsearch.server index template
+    rollover_index "logs-elasticsearch.server-default"
+
+  POSTVERSION=2.4.190
+}
+
+post_to_2.4.200() {
+  echo "Nothing to apply"
+  POSTVERSION=2.4.200
+}
+
 repo_sync() {
   echo "Sync the local repo."
   su socore -c '/usr/sbin/so-repo-sync' || fail "Unable to complete so-repo-sync."
@@ -850,10 +894,26 @@ up_to_2.4.170() {
     touch /opt/so/saltstack/local/pillar/$state/adv_$state.sls /opt/so/saltstack/local/pillar/$state/soc_$state.sls
   done
 
+
+  INSTALLEDVERSION=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=2.4.170
+  INSTALLEDVERSION=2.4.190
+}
+
+up_to_2.4.200() {
+  touch /opt/so/state/esfleet_logstash_config_pillar
+
+  INSTALLEDVERSION=2.4.200
 }
 
 add_hydra_pillars() {
@@ -1129,6 +1189,44 @@ 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
@@ -1178,24 +1276,43 @@ upgrade_check_salt() {
 }
 
 upgrade_salt() {
-  SALTUPGRADED=True
   echo "Performing upgrade of Salt from $INSTALLEDSALTVERSION to $NEWSALTVERSION."
   echo ""
   # If rhel family
   if [[ $is_rpm ]]; then
+    # Check if salt-cloud is installed
+    if rpm -q salt-cloud &>/dev/null; then
+      SALT_CLOUD_INSTALLED=true
+    fi
+    # Check if salt-cloud is configured
+    if [[ -f /etc/salt/cloud.profiles.d/socloud.conf ]]; then
+      SALT_CLOUD_CONFIGURED=true
+    fi
+    
     echo "Removing yum versionlock for Salt."
     echo ""
     yum versionlock delete "salt"
     yum versionlock delete "salt-minion"
     yum versionlock delete "salt-master"
+    # Remove salt-cloud versionlock if installed
+    if [[ $SALT_CLOUD_INSTALLED == true ]]; then
+      yum versionlock delete "salt-cloud"
+    fi
     echo "Updating Salt packages."
     echo ""
     set +e
     # if oracle run with -r to ignore repos set by bootstrap
     if [[ $OS == 'oracle' ]]; then
-      run_check_net_err \
-      "sh $UPDATE_DIR/salt/salt/scripts/bootstrap-salt.sh -X -r -F -M stable \"$NEWSALTVERSION\"" \
-      "Could not update salt, please check $SOUP_LOG for details."
+      # Add -L flag only if salt-cloud is already installed
+      if [[ $SALT_CLOUD_INSTALLED == true ]]; then
+        run_check_net_err \
+        "sh $UPDATE_DIR/salt/salt/scripts/bootstrap-salt.sh -X -r -L -F -M stable \"$NEWSALTVERSION\"" \
+        "Could not update salt, please check $SOUP_LOG for details."
+      else
+        run_check_net_err \
+        "sh $UPDATE_DIR/salt/salt/scripts/bootstrap-salt.sh -X -r -F -M stable \"$NEWSALTVERSION\"" \
+        "Could not update salt, please check $SOUP_LOG for details."
+      fi
     # if another rhel family variant we want to run without -r to allow the bootstrap script to manage repos
     else
       run_check_net_err \
@@ -1208,8 +1325,14 @@ upgrade_salt() {
     yum versionlock add "salt-0:$NEWSALTVERSION-0.*"
     yum versionlock add "salt-minion-0:$NEWSALTVERSION-0.*"
     yum versionlock add "salt-master-0:$NEWSALTVERSION-0.*"
+    # Add salt-cloud versionlock if installed
+    if [[ $SALT_CLOUD_INSTALLED == true ]]; then
+      yum versionlock add "salt-cloud-0:$NEWSALTVERSION-0.*"
+    fi
   # Else do Ubuntu things
   elif [[ $is_deb ]]; then
+    # ensure these files don't exist when upgrading from 3006.9 to 3006.16
+    rm -f /etc/apt/keyrings/salt-archive-keyring-2023.pgp /etc/apt/sources.list.d/salt.list
     echo "Removing apt hold for Salt."
     echo ""
     apt-mark unhold "salt-common"
@@ -1240,6 +1363,7 @@ upgrade_salt() {
     echo ""
     exit 1
   else
+    SALTUPGRADED=true
     echo "Salt upgrade success."
     echo ""
   fi
@@ -1345,6 +1469,7 @@ main() {
   fi
 
   set_minionid
+  MINION_ROLE=$(lookup_role)
   echo "Found that Security Onion $INSTALLEDVERSION is currently installed."
   echo ""
   if [[ $is_airgap -eq 0 ]]; then
@@ -1387,7 +1512,7 @@ main() {
   if [ "$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
@@ -1450,7 +1575,7 @@ 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
@@ -1482,6 +1607,11 @@ main() {
     # ensure the mine is updated and populated before highstates run, following the salt-master restart
     update_salt_mine
 
+    if [[ $SALT_CLOUD_CONFIGURED == true && $SALTUPGRADED == true ]]; then
+      echo "Updating salt-cloud config to use the new Salt version"
+      salt-call state.apply salt.cloud.config concurrent=True
+    fi
+
     enable_highstate
 
     echo ""
@@ -1564,7 +1694,7 @@ This appears to be a distributed deployment. Other nodes should update themselve
 
 Each minion is on a random 15 minute check-in period and things like network bandwidth can be a factor in how long the actual upgrade takes. If you have a heavy node on a slow link, it is going to take a while to get the containers to it. Depending on what changes happened between the versions, Elasticsearch might not be able to talk to said heavy node until the update is complete.
 
-If it looks like you’re missing data after the upgrade, please avoid restarting services and instead make sure at least one search node has completed its upgrade. The best way to do this is to run 'sudo salt-call state.highstate' from a search node and make sure there are no errors. Typically if it works on one node it will work on the rest. Forward nodes are less complex and will update as they check in so you can monitor those from the Grid section of SOC.
+If it looks like you’re missing data after the upgrade, please avoid restarting services and instead make sure at least one search node has completed its upgrade. The best way to do this is to run 'sudo salt-call state.highstate' from a search node and make sure there are no errors. Typically if it works on one node it will work on the rest. Sensor nodes are less complex and will update as they check in so you can monitor those from the Grid section of SOC.
 
 For more information, please see $DOC_BASE_URL/soup.html#distributed-deployments.
 

salt/manager/tools/sbin_jinja/so-elastic-agent-monitor

@@ -0,0 +1,254 @@
+{%- from 'manager/map.jinja' import MANAGERMERGED -%}
+{%- set OFFLINE_THRESHOLD_HOURS = MANAGERMERGED.agent_monitoring.config.offline_threshold -%}
+{%- set PAGE_SIZE = MANAGERMERGED.agent_monitoring.config.page_size -%}
+{%- set CUSTOM_KQUERY = MANAGERMERGED.agent_monitoring.config.custom_kquery -%}
+{%- set REALERT_THRESHOLD = MANAGERMERGED.agent_monitoring.config.realert_threshold -%}
+#!/bin/bash
+
+set -euo pipefail
+
+LOG_DIR="/opt/so/log/agents"
+LOG_FILE="$LOG_DIR/agent-monitor.log"
+CURL_CONFIG="/opt/so/conf/elasticsearch/curl.config"
+FLEET_API="http://localhost:5601/api/fleet/agents"
+{#- When using custom kquery ignore critical agents patterns. Since we want all the results of custom query logged #}
+{%- if CUSTOM_KQUERY != None and CUSTOM_KQUERY | length > 0 %}
+CRITICAL_AGENTS_FILE="/dev/null"
+{%- else %}
+CRITICAL_AGENTS_FILE="/opt/so/conf/agents/critical-agents.txt"
+{%- endif %}
+OFFLINE_THRESHOLD_HOURS={{ OFFLINE_THRESHOLD_HOURS }}
+REALERT_THRESHOLD={{ REALERT_THRESHOLD }}
+PAGE_SIZE="{{ PAGE_SIZE }}"
+
+log_message() {
+    local level="$1"
+    local message="$2"
+    echo "$(date -u +"%Y-%m-%dT%H:%M:%SZ") [$level] $message" >&2
+}
+
+matches_critical_pattern() {
+    local hostname="$1"
+    local pattern_file="$2"
+    
+    # If critical agents file doesn't exist or is empty, match all
+    if [ ! -f "$pattern_file" ] || [ ! -s "$pattern_file" ]; then
+        return 0
+    fi
+    
+    local hostname_lower=$(echo "$hostname" | tr '[:upper:]' '[:lower:]')
+    
+    while IFS= read -r pattern || [ -n "$pattern" ]; do
+        # empty lines and comments
+        [[ -z "$pattern" || "$pattern" =~ ^[[:space:]]*# ]] && continue
+        
+        # cut whitespace
+        pattern=$(echo "$pattern" | xargs)
+        
+        local pattern_lower=$(echo "$pattern" | tr '[:upper:]' '[:lower:]')
+        
+        # Replace * with bash wildcard
+        local bash_pattern="${pattern_lower//\*/.*}"
+        
+        # Check if hostname matches the pattern
+        if [[ "$hostname_lower" =~ ^${bash_pattern}$ ]]; then
+            return 0
+        fi
+    done < "$pattern_file"
+    
+    return 1
+}
+
+calculate_offline_hours() {
+    local last_checkin="$1"
+    local current_time=$(date +%s)
+    local checkin_time=$(date -d "$last_checkin" +%s 2>/dev/null || echo "0")
+    
+    if [ "$checkin_time" -eq "0" ]; then
+        echo "0"
+        return
+    fi
+    
+    local diff=$((current_time - checkin_time))
+    echo $((diff / 3600))
+}
+
+check_recent_log_entries() {
+    local agent_hostname="$1"
+
+    if [ ! -f "$LOG_FILE" ]; then
+        return 1
+    fi
+
+    local current_time=$(date +%s)
+    local threshold_seconds=$((REALERT_THRESHOLD * 3600))
+    local agent_hostname_lower=$(echo "$agent_hostname" | tr '[:upper:]' '[:lower:]')
+    local most_recent_timestamp=""
+
+    while IFS= read -r line; do
+        [ -z "$line" ] && continue
+
+        local logged_hostname=$(echo "$line" | jq -r '.["agent.hostname"] // empty' 2>/dev/null)
+        local logged_timestamp=$(echo "$line" | jq -r '.["@timestamp"] // empty' 2>/dev/null)
+
+        [ -z "$logged_hostname" ] || [ -z "$logged_timestamp" ] && continue
+
+        local logged_hostname_lower=$(echo "$logged_hostname" | tr '[:upper:]' '[:lower:]')
+
+        if [ "$logged_hostname_lower" = "$agent_hostname_lower" ]; then
+            most_recent_timestamp="$logged_timestamp"
+        fi
+    done < <(tail -n 1000 "$LOG_FILE" 2>/dev/null)
+
+    # If there is agent entry (within last 1000), check the time difference
+    if [ -n "$most_recent_timestamp" ]; then
+        local logged_time=$(date -d "$most_recent_timestamp" +%s 2>/dev/null || echo "0")
+
+        if [ "$logged_time" -ne "0" ]; then
+            local time_diff=$((current_time - logged_time))
+            local hours_diff=$((time_diff / 3600))
+
+            # Skip if last agent timestamp was more recent than realert threshold
+            if ((hours_diff < REALERT_THRESHOLD)); then
+                return 0
+            fi
+        fi
+    fi
+
+    # Agent has not been logged within realert threshold
+    return 1
+}
+
+main() {
+    log_message "INFO" "Starting Fleet agent status check"
+
+    # Check if critical agents file is configured
+    if [ -f "$CRITICAL_AGENTS_FILE" ] && [ -s "$CRITICAL_AGENTS_FILE" ]; then
+        log_message "INFO" "Using critical agents filter from: $CRITICAL_AGENTS_FILE"
+        log_message "INFO" "Patterns: $(grep -v '^#' "$CRITICAL_AGENTS_FILE" 2>/dev/null | xargs | tr ' ' ',')"
+    else
+        log_message "INFO" "No critical agents filter found, monitoring all agents"
+    fi
+
+    log_message "INFO" "Querying Fleet API"
+
+    local page=1
+    local total_agents=0
+    local processed_agents=0
+    local current_timestamp=$(date -u +"%Y-%m-%dT%H:%M:%SZ")
+
+    {%- if CUSTOM_KQUERY != None and CUSTOM_KQUERY | length > 0 %}
+    log_message "INFO" "Using custom kquery: {{ CUSTOM_KQUERY }}"
+    FLEET_QUERY="${FLEET_API}?kuery={{ CUSTOM_KQUERY | urlencode }}&perPage=${PAGE_SIZE}&page=${page}"
+    {%- else %}
+    log_message "INFO" "Using default query (all offline or degraded agents)"
+    FLEET_QUERY="${FLEET_API}?kuery=status%3Aoffline%20OR%20status%3Adegraded&perPage=${PAGE_SIZE}&page=${page}"
+    {%- endif %}
+
+    while true; do
+        log_message "INFO" "Fetching page $page (${PAGE_SIZE} agents per page)"
+
+        if ! response_body=$(curl -K "$CURL_CONFIG" \
+            -s --fail \
+            "$FLEET_QUERY" \
+            -H 'kbn-xsrf: true' 2>/dev/null); then
+            log_message "ERROR" "Failed to query Fleet API (page $page)"
+            exit 1
+        fi
+
+        # pagination info
+        current_total=$(echo "$response_body" | jq -r '.total // 0')
+        current_page=$(echo "$response_body" | jq -r '.page // 1')
+        agents_in_page=$(echo "$response_body" | jq -r '.list | length')
+
+        # Update total
+        if [ "$page" -eq 1 ]; then
+            total_agents="$current_total"
+            log_message "INFO" "Found $total_agents total agents across all pages"
+        fi
+
+        log_message "INFO" "Processing page $current_page with $agents_in_page agents"
+
+        # Process agents from current page
+        mapfile -t agents < <(echo "$response_body" | jq -c '.list[]')
+
+        for agent in "${agents[@]}"; do
+            # Grab agent details
+            agent_id=$(echo "$agent" | jq -r '.id // "unknown"')
+            agent_hostname=$(echo "$agent" | jq -r '.local_metadata.host.hostname // "unknown"')
+            agent_name=$(echo "$agent" | jq -r '.local_metadata.host.name // "unknown"')
+            agent_status=$(echo "$agent" | jq -r '.status // "unknown"')
+            last_checkin=$(echo "$agent" | jq -r '.last_checkin // ""')
+            last_checkin_status=$(echo "$agent" | jq -r '.last_checkin_status // "unknown"')
+            policy_id=$(echo "$agent" | jq -r '.policy_id // "unknown"')
+
+            # Only log agents that are offline or degraded (skip inactive agents)
+            # Fleetserver agents can show multiple versions as 'inactive'
+            if [ "$agent_status" = "offline" ] || [ "$agent_status" = "degraded" ]; then
+                # Check if agent matches critical agent patterns (if configured)
+                if ! matches_critical_pattern "$agent_hostname" "$CRITICAL_AGENTS_FILE"; then
+                    log_message "WARN" "${agent_hostname^^} is ${agent_status^^}, but does not match configured critical agents patterns. Not logging ${agent_status^^} agent"
+                    continue  # Skip this agent if it doesn't match any critical agent pattern
+                fi
+
+                offline_hours=$(calculate_offline_hours "$last_checkin")
+
+                if [ "$offline_hours" -lt "$OFFLINE_THRESHOLD_HOURS" ]; then
+                    log_message "INFO" "${agent_hostname^^} has been offline for ${offline_hours}h (threshold: ${OFFLINE_THRESHOLD_HOURS}h). Not logging ${agent_status^^} agent until it reaches threshold"
+                    continue
+                fi
+
+                # Check if this agent was already logged within the realert_threshold
+                if check_recent_log_entries "$agent_hostname"; then
+                    log_message "INFO" "Skipping $agent_hostname (status: $agent_status) - already logged within last ${REALERT_THRESHOLD}h"
+                    continue
+                fi
+
+                log_entry=$(echo 'null' | jq -c \
+                    --arg ts "$current_timestamp" \
+                    --arg id "$agent_id" \
+                    --arg hostname "$agent_hostname" \
+                    --arg name "$agent_name" \
+                    --arg status "$agent_status" \
+                    --arg last_checkin "$last_checkin" \
+                    --arg last_checkin_status "$last_checkin_status" \
+                    --arg policy_id "$policy_id" \
+                    --arg offline_hours "$offline_hours" \
+                    '{
+                        "@timestamp": $ts,
+                        "agent.id": $id,
+                        "agent.hostname": $hostname,
+                        "agent.name": $name,
+                        "agent.status": $status,
+                        "agent.last_checkin": $last_checkin,
+                        "agent.last_checkin_status": $last_checkin_status,
+                        "agent.policy_id": $policy_id,
+                        "agent.offline_duration_hours": ($offline_hours | tonumber)
+                    }')
+
+                echo "$log_entry" >> "$LOG_FILE"
+
+                log_message "INFO" "Logged offline agent: $agent_hostname (status: $agent_status, offline: ${offline_hours}h)"
+            fi
+        done
+
+        processed_agents=$((processed_agents + agents_in_page))
+
+        if [ "$agents_in_page" -eq 0 ] || [ "$processed_agents" -ge "$total_agents" ]; then
+            log_message "INFO" "Completed processing all pages. Total processed: $processed_agents agents"
+            break
+        fi
+
+        page=$((page + 1))
+
+        # Limit pagination loops incase of any issues. If agent count is high enough increase page_size in SOC manager.agent_monitoring.config.page_size
+        if [ "$page" -gt 100 ]; then
+            log_message "ERROR" "Reached maximum page limit (100). Issue with script or extremely large fleet deployment. Consider increasing page_size in SOC -> manager.agent_monitoring.config.page_size"
+            break
+        fi
+    done
+
+    log_message "INFO" "Fleet agent status check completed. Processed $processed_agents out of $total_agents agents"
+}
+
+main "$@"

salt/manager/tools/sbin_jinja/so-elastic-fleet-reset

@@ -15,6 +15,7 @@ require_manager
 echo
 echo "This script will remove the current Elastic Fleet install and all of its data and then rerun Elastic Fleet setup."
 echo "Deployed Elastic Agents will no longer be enrolled and will need to be reinstalled."
+echo "Only the Elastic Fleet instance on the Manager will be reinstalled - dedicated Fleet node config will removed and will need to be reinstalled."
 echo "This script should only be used as a last resort to reinstall Elastic Fleet." 
 echo
 echo "If you would like to proceed, then type AGREE and press ENTER."

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/nginx/etc/nginx.conf

@@ -196,19 +196,23 @@ http {
 		}
 
 		location / {
-			auth_request          /auth/sessions/whoami;
-			auth_request_set      $userid $upstream_http_x_kratos_authenticated_identity_id;
-			proxy_set_header      x-user-id $userid;
-			proxy_pass            http://{{ GLOBALS.manager }}:9822/;
-			proxy_read_timeout    300;
-			proxy_connect_timeout 300;
-			proxy_set_header      Host $host;
-			proxy_set_header      X-Real-IP $remote_addr;
-			proxy_set_header      X-Forwarded-For $proxy_add_x_forwarded_for;
-			proxy_set_header      Proxy "";
-			proxy_set_header      Upgrade $http_upgrade;
-			proxy_set_header      Connection "Upgrade";
-			proxy_set_header      X-Forwarded-Proto $scheme;
+			auth_request            /auth/sessions/whoami;
+			auth_request_set        $userid $upstream_http_x_kratos_authenticated_identity_id;
+			proxy_set_header        x-user-id $userid;
+			proxy_pass              http://{{ GLOBALS.manager }}:9822/;
+			proxy_read_timeout      300;
+			proxy_connect_timeout   300;
+			proxy_set_header        Host $host;
+			proxy_set_header        X-Real-IP $remote_addr;
+			proxy_set_header        X-Forwarded-For $proxy_add_x_forwarded_for;
+			proxy_set_header        Proxy "";
+			proxy_set_header        Upgrade $http_upgrade;
+			proxy_set_header        Connection "Upgrade";
+			proxy_set_header        X-Forwarded-Proto $scheme;
+
+			proxy_buffering         off;
+			proxy_cache             off;
+			proxy_request_buffering off;
 		}
 
 		location ~ ^/auth/.*?(login|oidc/callback) {

salt/ntp/chrony.conf

@@ -1,7 +1,7 @@
 
 # NTP server list
 {%- for SERVER in NTPCONFIG.servers %}
-server {{ SERVER }} iburst
+server {{ SERVER }} iburst maxpoll 10
 {%- endfor %}
 
 # Config options
@@ -9,3 +9,5 @@ driftfile /var/lib/chrony/drift
 makestep 1.0 3
 rtcsync
 logdir /var/log/chrony
+port 0
+cmdport 0

salt/pcap/config.sls

@@ -8,12 +8,9 @@
 
 {% from 'vars/globals.map.jinja' import GLOBALS %}
 {% from "pcap/config.map.jinja" import PCAPMERGED %}
-{% from 'bpf/pcap.map.jinja' import PCAPBPF %}
-
-{% set BPF_COMPILED = "" %}
+{% from 'bpf/pcap.map.jinja' import PCAPBPF, PCAP_BPF_STATUS, PCAP_BPF_CALC, STENO_BPF_COMPILED %}
 
 # PCAP Section
-
 stenographergroup:
   group.present:
     - name: stenographer
@@ -40,18 +37,12 @@ pcap_sbin:
     - group: 939
     - file_mode: 755
 
-{% if PCAPBPF %}
-   {% set BPF_CALC = salt['cmd.script']('salt://common/tools/sbin/so-bpf-compile', GLOBALS.sensor.interface + ' ' + PCAPBPF|join(" "),cwd='/root') %}
-   {% if BPF_CALC['stderr'] == "" %}
-      {% set BPF_COMPILED =  ",\\\"--filter=" + BPF_CALC['stdout'] + "\\\""  %}
-   {% else  %}
-
-bpfcompilationfailure:
+{% if PCAPBPF and not PCAP_BPF_STATUS %}
+stenoPCAPbpfcompilationfailure:
   test.configurable_test_state:
    - changes: False
    - result: False
-   - comment: "BPF Compilation Failed - Discarding Specified BPF"
-   {% endif %}
+  - comment: "BPF Syntax Error - Discarding Specified BPF. Error: {{ PCAP_BPF_CALC['stderr'] }}"
 {% endif %}
 
 stenoconf:
@@ -64,7 +55,7 @@ stenoconf:
     - template: jinja
     - defaults:
         PCAPMERGED: {{ PCAPMERGED }}
-        BPF_COMPILED: "{{ BPF_COMPILED }}"
+        STENO_BPF_COMPILED: "{{ STENO_BPF_COMPILED }}"
 
 stenoca:
   file.directory:

salt/pcap/files/config.jinja

@@ -6,6 +6,6 @@
   , "Interface": "{{ pillar.sensor.interface }}"
   , "Port": 1234
   , "Host": "127.0.0.1"
-  , "Flags": ["-v", "--blocks={{ PCAPMERGED.config.blocks }}", "--preallocate_file_mb={{ PCAPMERGED.config.preallocate_file_mb }}", "--aiops={{ PCAPMERGED.config.aiops }}", "--uid=stenographer", "--gid=stenographer"{{ BPF_COMPILED }}]
+  , "Flags": ["-v", "--blocks={{ PCAPMERGED.config.blocks }}", "--preallocate_file_mb={{ PCAPMERGED.config.preallocate_file_mb }}", "--aiops={{ PCAPMERGED.config.aiops }}", "--uid=stenographer", "--gid=stenographer"{{ STENO_BPF_COMPILED }}]
   , "CertPath": "/etc/stenographer/certs"
 }