Move pipeline fix

update tick interval desc

.github/DISCUSSION_TEMPLATE/3-0.yml

@@ -11,6 +11,9 @@ body:
         -
         - 3.0.0
         - 3.1.0
+        - 3.2.0
+        - 3.3.0
+        - 3.4.0
         - Other (please provide detail below)
     validations:
       required: true

.github/workflows/pythontest.yml

@@ -5,6 +5,11 @@ on:
     paths:
       - "salt/sensoroni/files/analyzers/**"
       - "salt/manager/tools/sbin/**"
+      - "salt/_beacons/**"
+      - "salt/elastalert/files/modules/**"
+      - "salt/telegraf/tools/sbin_jinja/**"
+      - "salt/telegraf/defaults.yaml"
+      - "salt/telegraf/soc_telegraf.yaml"
 
 jobs:
   build:
@@ -14,7 +19,7 @@ jobs:
       fail-fast: false
       matrix:
         python-version: ["3.14"]
-        python-code-path: ["salt/sensoroni/files/analyzers", "salt/manager/tools/sbin"]
+        python-code-path: ["salt/sensoroni/files/analyzers", "salt/manager/tools/sbin", "salt/_beacons", "salt/elastalert/files/modules/so"]
 
     steps:
     - uses: actions/checkout@v3
@@ -33,3 +38,25 @@ jobs:
     - name: Test with pytest
       run: |
         PYTHONPATH=${{ matrix.python-code-path }} pytest ${{ matrix.python-code-path }} --cov=${{ matrix.python-code-path }} --doctest-modules --cov-report=term --cov-fail-under=100 --cov-config=pytest.ini
+
+  telegraf-collector:
+    # so-container-stats is a jinja template rather than an importable module, so it gets its
+    # own job: the test renders it the way salt does, then drives it with a faked docker engine
+    # and cgroup tree. No container runtime is needed.
+    runs-on: ubuntu-latest
+    steps:
+    - uses: actions/checkout@v3
+    - name: Set up Python
+      uses: actions/setup-python@v3
+      with:
+        python-version: "3.14"
+    - name: Install dependencies
+      run: |
+        python -m pip install --upgrade pip
+        python -m pip install flake8 pytest jinja2 pyyaml
+    - name: Lint with flake8
+      run: |
+        flake8 salt/telegraf/tools/sbin_jinja/so-container-stats_test.py --config=pytest.ini
+    - name: Test with pytest
+      run: |
+        pytest salt/telegraf/tools/sbin_jinja/so-container-stats_test.py -v

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 3.0.0-20260331 ISO image released on 2026/03/31
+### 3.3.0-20260911 ISO image released on 2026/09/11
 
 
 ### Download and Verify
 
-3.0.0-20260331 ISO image:  
+3.3.0-20260911 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-3.0.0-20260331.iso
+https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
  
-MD5: ECD318A1662A6FDE0EF213F5A9BD4B07  
+MD5: 12B18433D3A2198A185892FF79CF638F  
-SHA1: E55BE314440CCF3392DC0B06BC5E270B43176D9C  
+SHA1: 2B3C2E1FA7A78ED1F956E7EDCC12E32593C14EEE  
-SHA256: 7FC47405E335CBE5C2B6C51FE7AC60248F35CBE504907B8B5A33822B23F8F4D5  
+SHA256: 0938C73B76CE30EC9E4394D312C79EA7CAC721B6818541697279A6221F7D870D  
 
 Signature for ISO image:  
-https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.0.0-20260331.iso.sig
+https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 
 Signing key:  
 https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/main/KEYS  
@@ -25,22 +25,22 @@ wget https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/
 
 Download the signature file for the ISO:  
 ```
-wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.0.0-20260331.iso.sig
+wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.3.0-20260911.iso.sig
 ```
 
 Download the ISO image:  
 ```
-wget https://download.securityonion.net/file/securityonion/securityonion-3.0.0-20260331.iso
+wget https://download.securityonion.net/file/securityonion/securityonion-3.3.0-20260911.iso
 ```
 
 Verify the downloaded ISO image using the signature file:  
 ```
-gpg --verify securityonion-3.0.0-20260331.iso.sig securityonion-3.0.0-20260331.iso
+gpg --verify securityonion-3.3.0-20260911.iso.sig securityonion-3.3.0-20260911.iso
 ```
 
 The output should show "Good signature" and the Primary key fingerprint should match what's shown below:
 ```
-gpg: Signature made Mon 30 Mar 2026 06:22:14 PM EDT using RSA key ID FE507013
+gpg: Signature made Fri 11 Sep 2026 11:23:56 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.

HOTFIX

@@ -0,0 +1 @@
+

VERSION

@@ -1 +1 @@
-3.1.0
+3.4.0

pillar/data/addtotab.sh

@@ -1,59 +0,0 @@
-#!/usr/bin/env bash
-
-# This script adds sensors/nodes/etc to the nodes tab
-default_salt_dir=/opt/so/saltstack/default
-local_salt_dir=/opt/so/saltstack/local
-TYPE=$1
-NAME=$2
-IPADDRESS=$3
-CPUS=$4
-GUID=$5
-MANINT=$6
-ROOTFS=$7
-NSM=$8
-MONINT=$9
-#NODETYPE=$10
-#HOTNAME=$11
-
-echo "Seeing if this host is already in here. If so delete it"
-if grep -q $NAME "$local_salt_dir/pillar/data/$TYPE.sls"; then
-  echo "Node Already Present - Let's re-add it"
-  awk -v blah="  $NAME:" 'BEGIN{ print_flag=1 }
-{
-    if( $0 ~ blah )
-    {
-       print_flag=0;
-       next
-    }
-    if( $0 ~ /^  [a-zA-Z0-9]+:$/ )
-    {
-        print_flag=1;
-    }
-    if ( print_flag == 1 )
-        print $0
-
-} ' $local_salt_dir/pillar/data/$TYPE.sls > $local_salt_dir/pillar/data/tmp.$TYPE.sls
-mv $local_salt_dir/pillar/data/tmp.$TYPE.sls $local_salt_dir/pillar/data/$TYPE.sls
-echo "Deleted $NAME from the tab. Now adding it in again with updated info"
-fi
-echo "  $NAME:" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    ip: $IPADDRESS" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    manint: $MANINT" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    totalcpus: $CPUS" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    guid: $GUID" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    rootfs: $ROOTFS" >> $local_salt_dir/pillar/data/$TYPE.sls
-echo "    nsmfs: $NSM" >> $local_salt_dir/pillar/data/$TYPE.sls
-if [ $TYPE == 'sensorstab' ]; then
-  echo "    monint: bond0" >> $local_salt_dir/pillar/data/$TYPE.sls
-fi
-if [ $TYPE == 'evaltab' ] || [ $TYPE == 'standalonetab' ]; then
-  echo "    monint: bond0" >> $local_salt_dir/pillar/data/$TYPE.sls
-  if [ ! $10 ]; then
-    salt-call state.apply utility queue=True
-  fi
-fi
-if [ $TYPE == 'nodestab' ]; then
-  salt-call state.apply elasticsearch queue=True
-#  echo "    nodetype: $NODETYPE" >> $local_salt_dir/pillar/data/$TYPE.sls
-#  echo "    hotname: $HOTNAME" >> $local_salt_dir/pillar/data/$TYPE.sls
-fi

pillar/elasticsearch/index_templates.sls

@@ -1,2 +0,0 @@
-elasticsearch:
-  index_settings:

pillar/telegraf/creds.sls

@@ -0,0 +1,12 @@
+# 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.
+
+# Per-minion Telegraf Postgres credentials. so-telegraf-cred on the manager is
+# the single writer; it mutates /opt/so/saltstack/local/pillar/telegraf/creds.sls
+# under flock. Pillar_roots order (local before default) means the populated
+# copy shadows this default on any real grid; this file exists so the pillar
+# key is always defined on fresh installs and when no minions have creds yet.
+telegraf:
+  postgres_creds: {}

pillar/top.sls

@@ -3,6 +3,8 @@ base:
     - ca
     - global.soc_global
     - global.adv_global
+    - salt.soc_salt
+    - salt.adv_salt
     - docker.soc_docker
     - docker.adv_docker
     - influxdb.token
@@ -17,6 +19,7 @@ base:
     - sensoroni.adv_sensoroni
     - telegraf.soc_telegraf
     - telegraf.adv_telegraf
+    - telegraf.creds
     - versionlock.soc_versionlock
     - versionlock.adv_versionlock
     - soc.license
@@ -38,6 +41,9 @@ base:
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/elasticsearch/auth.sls') %}
     - elasticsearch.auth
     {% endif %}
+    {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/postgres/auth.sls') %}
+    - postgres.auth
+    {% endif %}
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/kibana/secrets.sls') %}
     - kibana.secrets
     {% endif %}
@@ -60,6 +66,8 @@ base:
     - redis.adv_redis
     - influxdb.soc_influxdb
     - influxdb.adv_influxdb
+    - postgres.soc_postgres
+    - postgres.adv_postgres
     - elasticsearch.nodes
     - elasticsearch.soc_elasticsearch
     - elasticsearch.adv_elasticsearch
@@ -97,10 +105,12 @@ base:
     - node_data.ips
     - secrets
     - healthcheck.eval
-    - elasticsearch.index_templates
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/elasticsearch/auth.sls') %}
     - elasticsearch.auth
     {% endif %}
+    {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/postgres/auth.sls') %}
+    - postgres.auth
+    {% endif %}
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/kibana/secrets.sls') %}
     - kibana.secrets
     {% endif %}
@@ -126,6 +136,8 @@ base:
     - redis.adv_redis
     - influxdb.soc_influxdb
     - influxdb.adv_influxdb
+    - postgres.soc_postgres
+    - postgres.adv_postgres
     - backup.soc_backup
     - backup.adv_backup
     - zeek.soc_zeek
@@ -142,10 +154,12 @@ base:
     - logstash.nodes
     - logstash.soc_logstash
     - logstash.adv_logstash
-    - elasticsearch.index_templates
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/elasticsearch/auth.sls') %}
     - elasticsearch.auth
     {% endif %}
+    {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/postgres/auth.sls') %}
+    - postgres.auth
+    {% endif %}
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/kibana/secrets.sls') %}
     - kibana.secrets
     {% endif %}
@@ -160,6 +174,8 @@ base:
     - redis.adv_redis
     - influxdb.soc_influxdb
     - influxdb.adv_influxdb
+    - postgres.soc_postgres
+    - postgres.adv_postgres
     - elasticsearch.nodes
     - elasticsearch.soc_elasticsearch
     - elasticsearch.adv_elasticsearch
@@ -256,10 +272,12 @@ base:
   '*_import':
     - node_data.ips
     - secrets
-    - elasticsearch.index_templates
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/elasticsearch/auth.sls') %}
     - elasticsearch.auth
     {% endif %}
+    {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/postgres/auth.sls') %}
+    - postgres.auth
+    {% endif %}
     {% if salt['file.file_exists']('/opt/so/saltstack/local/pillar/kibana/secrets.sls') %}
     - kibana.secrets
     {% endif %}
@@ -285,6 +303,8 @@ base:
     - redis.adv_redis
     - influxdb.soc_influxdb
     - influxdb.adv_influxdb
+    - postgres.soc_postgres
+    - postgres.adv_postgres
     - zeek.soc_zeek
     - zeek.adv_zeek
     - bpf.soc_bpf

salt/_beacons/local_files_beacon.py

@@ -0,0 +1,145 @@
+# 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.
+
+# Custom salt beacon that watches hand-edited directories under
+# /opt/so/saltstack/local/salt/ for changes and emits a beacon event per changed
+# directory. This replaces the stock salt `inotify` beacon, which leaks a kernel
+# inotify instance every time the minion rebuilds the beacon loader's __context__
+# (orphaning the old pyinotify.Notifier without closing it) until
+# fs.inotify.max_user_instances is exhausted and the beacon dies with EMFILE.
+# Polling holds zero inotify instances, so the leak is impossible, and it keeps
+# firing during state runs (no blackout).
+#
+# Detection is poll-based with a per-directory fingerprint persisted to
+# WATERMARK_DIR: each pass walks the directory and hashes every file's
+# (relpath, st_mtime_ns, st_size), which catches content writes, additions,
+# moves, and deletions. A change in the digest emits one event; an unchanged
+# digest emits nothing. This makes it self-healing (a missed poll simply catches
+# up on the next one).
+#
+# Each emitted event carries the watched directory path under the configured tag
+# (e.g. salt/beacon/<minion>/local_files_beacon/zeek); the push_files reactor
+# looks the tag up in salt/reactor/pillar_push_map.yaml and writes a push intent,
+# after which the existing so-push-drainer / orch.push_batch pipeline takes over
+# unchanged.
+
+import hashlib
+import logging
+import os
+import re
+
+log = logging.getLogger(__name__)
+
+WATERMARK_DIR = '/opt/so/state'
+
+# Temp/editor files that should not trigger a push. Mirrors the exclude regexes
+# the inotify beacon used. Matched against the full pathname.
+EXCLUDES = [
+    re.compile(r'\.sw[a-z]$'),
+    re.compile(r'~$'),
+    re.compile(r'/4913$'),
+    re.compile(r'/\.#'),
+]
+
+
+def __virtual__():
+    return True
+
+
+def validate(config):
+    return True, 'valid'
+
+
+def _paths_from_config(config):
+    # The beacon config arrives as a list of single-key dicts (salt beacon style).
+    # Merge it and return the {dir: tag} mapping under the 'paths' key.
+    merged = {}
+    if isinstance(config, list):
+        for item in config:
+            if isinstance(item, dict):
+                merged.update(item)
+    elif isinstance(config, dict):
+        merged = config
+    paths = merged.get('paths', {})
+    return paths if isinstance(paths, dict) else {}
+
+
+def _excluded(pathname):
+    for pattern in EXCLUDES:
+        if pattern.search(pathname):
+            return True
+    return False
+
+
+def _fingerprint(directory):
+    # Stat-only walk; hash each file's (relpath, mtime_ns, size). Returns a hex
+    # digest, or the digest of an empty tree if the directory does not exist.
+    h = hashlib.sha1()
+    if os.path.isdir(directory):
+        entries = []
+        for root, dirs, files in os.walk(directory):
+            # zkg packages are git clones; .git churn would fire a state apply on its own.
+            dirs[:] = [d for d in dirs if d != '.git']
+            for name in files:
+                full = os.path.join(root, name)
+                if _excluded(full):
+                    continue
+                try:
+                    st = os.stat(full)
+                except OSError:
+                    continue
+                rel = os.path.relpath(full, directory)
+                entries.append('%s\0%d\0%d' % (rel, st.st_mtime_ns, st.st_size))
+        for line in sorted(entries):
+            h.update(line.encode('utf-8', 'surrogateescape'))
+            h.update(b'\n')
+    return h.hexdigest()
+
+
+def _watermark_file(tag, directory):
+    # Keyed by directory: zeek/policy and zeek/zkg share the tag `zeek`.
+    scope = hashlib.sha1(directory.encode('utf-8', 'surrogateescape')).hexdigest()[:12]
+    return os.path.join(WATERMARK_DIR, 'local_files_beacon_%s_%s.hash' % (tag, scope))
+
+
+def _read_watermark(tag, directory):
+    try:
+        with open(_watermark_file(tag, directory), 'r') as f:
+            return (f.read() or '').strip() or None
+    except IOError:
+        return None
+
+
+def _write_watermark(tag, directory, digest):
+    path = _watermark_file(tag, directory)
+    try:
+        os.makedirs(WATERMARK_DIR, exist_ok=True)
+        tmp = path + '.tmp'
+        with open(tmp, 'w') as f:
+            f.write(digest)
+        os.rename(tmp, path)
+    except OSError:
+        log.exception('local_files_beacon: failed to persist watermark to %s', path)
+
+
+def beacon(config):
+    retval = []
+
+    for directory, tag in _paths_from_config(config).items():
+        digest = _fingerprint(directory)
+        previous = _read_watermark(tag, directory)
+
+        # First run / missing watermark: seed the digest and emit nothing so a
+        # fresh host does not fire a spurious fleetwide push.
+        if previous is None:
+            _write_watermark(tag, directory, digest)
+            continue
+
+        if digest != previous:
+            _write_watermark(tag, directory, digest)
+            retval.append({'tag': tag, 'path': directory})
+            log.info('local_files_beacon: change detected in %s, emitting %s', directory, tag)
+
+    return retval

salt/_beacons/local_files_beacon_test.py

@@ -0,0 +1,221 @@
+# 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.
+
+import hashlib
+import os
+import shutil
+import tempfile
+import unittest
+from unittest.mock import patch
+
+import local_files_beacon
+
+
+class TestRulesBeacon(unittest.TestCase):
+
+    def setUp(self):
+        # Isolate all on-disk state (watermarks and the dirs we fingerprint) in a
+        # throwaway tree, and point WATERMARK_DIR at it so the real read/write
+        # helpers run against actual files.
+        self.tmpdir = tempfile.mkdtemp()
+        self.state = os.path.join(self.tmpdir, 'state')
+        patcher = patch.object(local_files_beacon, 'WATERMARK_DIR', self.state)
+        patcher.start()
+        self.addCleanup(patcher.stop)
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    def _make_dir(self, name, files=None):
+        path = os.path.join(self.tmpdir, name)
+        os.makedirs(path, exist_ok=True)
+        for fname, content in (files or {}).items():
+            with open(os.path.join(path, fname), 'w') as f:
+                f.write(content)
+        return path
+
+    # -- trivial contract -------------------------------------------------
+
+    def test_virtual_returns_true(self):
+        self.assertTrue(local_files_beacon.__virtual__())
+
+    def test_validate_returns_valid(self):
+        self.assertEqual(local_files_beacon.validate({}), (True, 'valid'))
+
+    # -- _paths_from_config -----------------------------------------------
+
+    def test_paths_from_config_list_of_dicts(self):
+        config = [{'interval': 10}, {'paths': {'/a': 'suricata', '/b': 'strelka'}}]
+        self.assertEqual(
+            local_files_beacon._paths_from_config(config),
+            {'/a': 'suricata', '/b': 'strelka'},
+        )
+
+    def test_paths_from_config_plain_dict(self):
+        self.assertEqual(
+            local_files_beacon._paths_from_config({'paths': {'/a': 'suricata'}}),
+            {'/a': 'suricata'},
+        )
+
+    def test_paths_from_config_skips_non_dict_items(self):
+        self.assertEqual(local_files_beacon._paths_from_config(['bogus', 42]), {})
+
+    def test_paths_from_config_paths_not_a_dict(self):
+        self.assertEqual(local_files_beacon._paths_from_config({'paths': 'nope'}), {})
+
+    def test_paths_from_config_unexpected_type(self):
+        self.assertEqual(local_files_beacon._paths_from_config('nonsense'), {})
+
+    # -- _excluded --------------------------------------------------------
+
+    def test_excluded_matches_temp_and_editor_files(self):
+        for pathname in ('/rules/foo.swp', '/rules/foo~', '/rules/4913', '/rules/.#foo'):
+            self.assertTrue(local_files_beacon._excluded(pathname), pathname)
+
+    def test_excluded_allows_real_rule_files(self):
+        self.assertFalse(local_files_beacon._excluded('/rules/suricata.rules'))
+
+    # -- _fingerprint -----------------------------------------------------
+
+    def test_fingerprint_missing_dir_is_empty_tree_digest(self):
+        missing = os.path.join(self.tmpdir, 'does-not-exist')
+        self.assertEqual(local_files_beacon._fingerprint(missing), hashlib.sha1().hexdigest())
+
+    def test_fingerprint_changes_when_content_changes(self):
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'a.rules'), 'w') as f:
+            f.write('alert tcp any any -> any any')  # different size
+        self.assertNotEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_ignores_excluded_files(self):
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'a.rules.swp'), 'w') as f:
+            f.write('editor swap')
+        self.assertEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_skips_unstatable_entries(self):
+        # A dangling symlink appears in os.walk's file list but os.stat raises
+        # OSError, exercising the except-continue path.
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        good = local_files_beacon._fingerprint(d)
+        os.symlink(os.path.join(d, 'missing-target'), os.path.join(d, 'broken.link'))
+        self.assertEqual(local_files_beacon._fingerprint(d), good)
+
+    def test_fingerprint_prunes_git_metadata(self):
+        # zkg packages are git clones, so the watched tree carries .git.
+        d = self._make_dir('zkg', {'pkg.zeek': 'print 1;'})
+        before = local_files_beacon._fingerprint(d)
+        git_dir = os.path.join(d, 'pkg', '.git', 'refs', 'heads')
+        os.makedirs(git_dir)
+        with open(os.path.join(git_dir, 'main'), 'w') as f:
+            f.write('0' * 40)
+        self.assertEqual(local_files_beacon._fingerprint(d), before)
+
+    def test_fingerprint_still_sees_worktree_next_to_git(self):
+        d = self._make_dir('zkg', {'pkg.zeek': 'print 1;'})
+        os.makedirs(os.path.join(d, 'pkg', '.git'))
+        before = local_files_beacon._fingerprint(d)
+        with open(os.path.join(d, 'pkg', 'scripts.zeek'), 'w') as f:
+            f.write('print 2;')
+        self.assertNotEqual(local_files_beacon._fingerprint(d), before)
+
+    # -- _read_watermark / _write_watermark -------------------------------
+
+    def test_watermark_round_trip(self):
+        local_files_beacon._write_watermark('suricata', '/rules/suricata', 'deadbeef')
+        self.assertEqual(
+            local_files_beacon._read_watermark('suricata', '/rules/suricata'), 'deadbeef')
+
+    def test_read_watermark_missing_returns_none(self):
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_read_watermark_empty_file_returns_none(self):
+        os.makedirs(self.state, exist_ok=True)
+        with open(local_files_beacon._watermark_file('suricata', '/rules/suricata'), 'w') as f:
+            f.write('')
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_write_watermark_swallows_oserror(self):
+        with patch.object(local_files_beacon.os, 'makedirs', side_effect=OSError):
+            local_files_beacon._write_watermark('suricata', '/rules/suricata', 'deadbeef')
+        self.assertIsNone(local_files_beacon._read_watermark('suricata', '/rules/suricata'))
+
+    def test_watermark_file_differs_per_directory_within_one_tag(self):
+        # zeek/policy and zeek/zkg share the tag 'zeek'.
+        self.assertNotEqual(
+            local_files_beacon._watermark_file('zeek', '/local/zeek/policy'),
+            local_files_beacon._watermark_file('zeek', '/local/zeek/zkg'),
+        )
+
+    def test_watermarks_are_independent_within_one_tag(self):
+        local_files_beacon._write_watermark('zeek', '/local/zeek/policy', 'policyhash')
+        local_files_beacon._write_watermark('zeek', '/local/zeek/zkg', 'zkghash')
+        self.assertEqual(
+            local_files_beacon._read_watermark('zeek', '/local/zeek/policy'), 'policyhash')
+        self.assertEqual(
+            local_files_beacon._read_watermark('zeek', '/local/zeek/zkg'), 'zkghash')
+
+    # -- beacon -----------------------------------------------------------
+
+    def _config(self, mapping):
+        return [{'paths': mapping}]
+
+    def test_beacon_seeds_first_run_and_emits_nothing(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='hash1'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value=None), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [])
+        mock_write.assert_called_once_with('suricata', '/rules/suricata', 'hash1')
+
+    def test_beacon_emits_on_change(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='newhash'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value='oldhash'), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [{'tag': 'suricata', 'path': '/rules/suricata'}])
+        mock_write.assert_called_once_with('suricata', '/rules/suricata', 'newhash')
+
+    def test_beacon_no_change_emits_nothing(self):
+        with patch.object(local_files_beacon, '_fingerprint', return_value='samehash'), \
+             patch.object(local_files_beacon, '_read_watermark', return_value='samehash'), \
+             patch.object(local_files_beacon, '_write_watermark') as mock_write:
+            result = local_files_beacon.beacon(self._config({'/rules/suricata': 'suricata'}))
+        self.assertEqual(result, [])
+        mock_write.assert_not_called()
+
+    def test_beacon_end_to_end_with_real_files(self):
+        # Exercise the full stack (real fingerprint + real watermark files) across
+        # two poll passes: first seeds silently, second fires after a write.
+        d = self._make_dir('rules', {'a.rules': 'alert'})
+        config = self._config({d: 'suricata'})
+
+        self.assertEqual(local_files_beacon.beacon(config), [])  # seed pass
+        self.assertEqual(local_files_beacon.beacon(config), [])  # unchanged pass
+
+        with open(os.path.join(d, 'b.rules'), 'w') as f:
+            f.write('alert tcp any any -> any any')
+        self.assertEqual(local_files_beacon.beacon(config), [{'tag': 'suricata', 'path': d}])
+
+    def test_beacon_two_dirs_one_tag_do_not_flap(self):
+        # Tag-keyed watermarks would clobber each other and emit on every pass.
+        policy = self._make_dir('zeek/policy', {'intel.dat': '#fields\tindicator'})
+        zkg = self._make_dir('zeek/zkg', {'README': 'place packages here'})
+        config = self._config({policy: 'zeek', zkg: 'zeek'})
+
+        self.assertEqual(local_files_beacon.beacon(config), [])  # seed pass
+        self.assertEqual(local_files_beacon.beacon(config), [])  # idle
+        self.assertEqual(local_files_beacon.beacon(config), [])  # still idle
+
+        with open(os.path.join(policy, 'intel.dat'), 'a') as f:
+            f.write('\nevil.com\tIntel::DOMAIN\tsource\n')
+        self.assertEqual(local_files_beacon.beacon(config), [{'tag': 'zeek', 'path': policy}])
+        self.assertEqual(local_files_beacon.beacon(config), [])  # quiet again
+
+
+if __name__ == '__main__':
+    unittest.main()

salt/_beacons/postgres_pillar_beacon.py

@@ -0,0 +1,142 @@
+# 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.
+
+# Custom salt beacon that watches the SOC audit_settings table in postgres for
+# new settings changes and emits a beacon event per new row. This replaces the
+# inotify watch on /opt/so/saltstack/local/pillar -- instead of monitoring pillar
+# files on disk, we monitor the securityonion.audit_settings table that SOC writes to.
+#
+# Detection is poll-based with a monotonic `id` watermark persisted to
+# WATERMARK_FILE: each pass selects rows with id greater than the last id seen,
+# which makes it self-healing (a missed poll simply catches up on the next one).
+#
+# Each emitted event carries setting_id and node_id; the push_pillar reactor maps
+# setting_id -> app via pillar_push_map.yaml and writes a push intent, after which
+# the existing so-push-drainer / orch.push_batch pipeline takes over unchanged.
+
+import logging
+import os
+import subprocess
+
+log = logging.getLogger(__name__)
+
+WATERMARK_FILE = '/opt/so/state/postgres_pillar_beacon_watch.id'
+CONTAINER = 'so-postgres'
+DATABASE = 'securityonion'
+
+# Unaligned, tuples-only psql output with a field separator that cannot appear in
+# an id/setting_id/node_id, so we can split each row reliably.
+FIELD_SEP = '\x1f'
+
+
+def __virtual__():
+    return True
+
+
+def validate(config):
+    return True, 'valid'
+
+
+def _read_watermark():
+    # Returns the last processed id, or None if the watermark has not been seeded.
+    try:
+        with open(WATERMARK_FILE, 'r') as f:
+            return int((f.read() or '').strip())
+    except (IOError, ValueError):
+        return None
+
+
+def _write_watermark(value):
+    try:
+        os.makedirs(os.path.dirname(WATERMARK_FILE), exist_ok=True)
+        tmp = WATERMARK_FILE + '.tmp'
+        with open(tmp, 'w') as f:
+            f.write(str(int(value)))
+        os.rename(tmp, WATERMARK_FILE)
+    except OSError:
+        log.exception('postgres_pillar_beacon: failed to persist watermark to %s', WATERMARK_FILE)
+
+
+def _query(sql):
+    # Run a query against securityonion inside the so-postgres container over the unix
+    # socket (trust auth, no password). Returns stdout on success, or None on any
+    # failure so the caller can no-op and retry on the next interval.
+    cmd = [
+        'docker', 'exec', CONTAINER,
+        'psql', '-U', 'postgres', '-d', DATABASE,
+        '-tA', '-F', FIELD_SEP, '-c', sql,
+    ]
+    try:
+        result = subprocess.run(cmd, capture_output=True, text=True, timeout=30)
+    except subprocess.TimeoutExpired:
+        log.warning('postgres_pillar_beacon: psql timed out')
+        return None
+    except Exception:
+        log.exception('postgres_pillar_beacon: failed to exec psql')
+        return None
+    if result.returncode != 0:
+        log.warning('postgres_pillar_beacon: psql failed (rc=%s): %s',
+                    result.returncode, (result.stderr or '').strip())
+        return None
+    return result.stdout
+
+
+def beacon(config):  # noqa: C901
+    retval = []
+
+    watermark = _read_watermark()
+
+    # First run / missing watermark: seed to the current MAX(id) and emit nothing
+    # so we never replay the entire settings history into a fleetwide push.
+    if watermark is None:
+        seed = _query('SELECT COALESCE(MAX(id), 0) FROM audit_settings;')
+        if seed is None:
+            return retval  # postgres not ready yet; retry next interval
+        try:
+            _write_watermark(int((seed or '0').strip() or 0))
+        except ValueError:
+            log.warning('postgres_pillar_beacon: could not parse MAX(id) seed: %r', seed)
+        return retval
+
+    rows = _query(
+        "SELECT id, setting_id, COALESCE(node_id, '') FROM audit_settings "
+        "WHERE id > %d ORDER BY id;" % watermark
+    )
+    if rows is None:
+        return retval
+
+    max_id = watermark
+    for line in rows.splitlines():
+        # Do NOT str.strip() the whole line: Python treats the \x1f field
+        # separator (and \x1c-\x1e) as whitespace, so stripping would eat an
+        # empty trailing node_id field and make the row look malformed.
+        if not line.strip():
+            continue
+        parts = line.split(FIELD_SEP)
+        if len(parts) < 3:
+            log.warning('postgres_pillar_beacon: skipping malformed row: %r', line)
+            continue
+        try:
+            row_id = int(parts[0])
+        except ValueError:
+            log.warning('postgres_pillar_beacon: skipping row with non-int id: %r', line)
+            continue
+        setting_id = parts[1]
+        node_id = parts[2]
+        retval.append({
+            'tag': 'audit_settings',
+            'id': row_id,
+            'setting_id': setting_id,
+            'node_id': node_id,
+        })
+        if row_id > max_id:
+            max_id = row_id
+
+    if max_id > watermark:
+        _write_watermark(max_id)
+        log.info('postgres_pillar_beacon: emitted %d change(s), watermark %d -> %d',
+                 len(retval), watermark, max_id)
+
+    return retval

salt/_beacons/postgres_pillar_beacon_test.py

@@ -0,0 +1,165 @@
+# 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.
+
+import os
+import shutil
+import subprocess
+import tempfile
+import unittest
+from unittest.mock import patch
+
+import postgres_pillar_beacon
+
+
+class TestPostgresPillarBeacon(unittest.TestCase):
+
+    def setUp(self):
+        # Point WATERMARK_FILE at a throwaway dir so the real read/write helpers
+        # (and their os.makedirs/os.rename) run against actual files, then clean
+        # it all up in tearDown.
+        self.tmpdir = tempfile.mkdtemp()
+        self.watermark = os.path.join(self.tmpdir, 'state', 'watch.id')
+        patcher = patch.object(postgres_pillar_beacon, 'WATERMARK_FILE', self.watermark)
+        patcher.start()
+        self.addCleanup(patcher.stop)
+
+    def tearDown(self):
+        shutil.rmtree(self.tmpdir, ignore_errors=True)
+
+    # -- trivial contract -------------------------------------------------
+
+    def test_virtual_returns_true(self):
+        self.assertTrue(postgres_pillar_beacon.__virtual__())
+
+    def test_validate_returns_valid(self):
+        self.assertEqual(postgres_pillar_beacon.validate({}), (True, 'valid'))
+
+    # -- _read_watermark --------------------------------------------------
+
+    def test_read_watermark_valid(self):
+        postgres_pillar_beacon._write_watermark(42)
+        self.assertEqual(postgres_pillar_beacon._read_watermark(), 42)
+
+    def test_read_watermark_missing_file_returns_none(self):
+        # tmp watermark file was never created
+        self.assertIsNone(postgres_pillar_beacon._read_watermark())
+
+    def test_read_watermark_garbage_returns_none(self):
+        os.makedirs(os.path.dirname(self.watermark), exist_ok=True)
+        with open(self.watermark, 'w') as f:
+            f.write('nope')
+        self.assertIsNone(postgres_pillar_beacon._read_watermark())
+
+    # -- _write_watermark -------------------------------------------------
+
+    def test_write_watermark_round_trip(self):
+        postgres_pillar_beacon._write_watermark(7)
+        with open(self.watermark) as f:
+            self.assertEqual(f.read(), '7')
+
+    def test_write_watermark_swallows_oserror(self):
+        with patch.object(postgres_pillar_beacon.os, 'makedirs', side_effect=OSError):
+            # Must not raise; failure is logged and the beacon retries next pass.
+            postgres_pillar_beacon._write_watermark(5)
+        self.assertFalse(os.path.exists(self.watermark))
+
+    # -- _query -----------------------------------------------------------
+
+    def test_query_success_returns_stdout_and_builds_argv(self):
+        completed = subprocess.CompletedProcess(args=[], returncode=0, stdout='rows', stderr='')
+        with patch.object(postgres_pillar_beacon.subprocess, 'run', return_value=completed) as mock_run:
+            result = postgres_pillar_beacon._query('SELECT 1;')
+        self.assertEqual(result, 'rows')
+        argv = mock_run.call_args[0][0]
+        self.assertEqual(argv[:5], ['docker', 'exec', 'so-postgres', 'psql', '-U'])
+        self.assertIn('SELECT 1;', argv)
+        self.assertFalse(mock_run.call_args[1].get('shell', False))
+
+    def test_query_timeout_returns_none(self):
+        with patch.object(postgres_pillar_beacon.subprocess, 'run',
+                          side_effect=subprocess.TimeoutExpired(cmd='psql', timeout=30)):
+            self.assertIsNone(postgres_pillar_beacon._query('SELECT 1;'))
+
+    def test_query_generic_exception_returns_none(self):
+        with patch.object(postgres_pillar_beacon.subprocess, 'run', side_effect=Exception('boom')):
+            self.assertIsNone(postgres_pillar_beacon._query('SELECT 1;'))
+
+    def test_query_nonzero_returncode_returns_none(self):
+        completed = subprocess.CompletedProcess(args=[], returncode=1, stdout='', stderr='bad')
+        with patch.object(postgres_pillar_beacon.subprocess, 'run', return_value=completed):
+            self.assertIsNone(postgres_pillar_beacon._query('SELECT 1;'))
+
+    # -- beacon: first run / seeding --------------------------------------
+
+    def test_beacon_seeds_when_postgres_not_ready(self):
+        with patch.object(postgres_pillar_beacon, '_read_watermark', return_value=None), \
+             patch.object(postgres_pillar_beacon, '_query', return_value=None), \
+             patch.object(postgres_pillar_beacon, '_write_watermark') as mock_write:
+            self.assertEqual(postgres_pillar_beacon.beacon({}), [])
+        mock_write.assert_not_called()
+
+    def test_beacon_seeds_to_max_id_and_emits_nothing(self):
+        with patch.object(postgres_pillar_beacon, '_read_watermark', return_value=None), \
+             patch.object(postgres_pillar_beacon, '_query', return_value='7\n'), \
+             patch.object(postgres_pillar_beacon, '_write_watermark') as mock_write:
+            self.assertEqual(postgres_pillar_beacon.beacon({}), [])
+        mock_write.assert_called_once_with(7)
+
+    def test_beacon_seed_unparseable_is_swallowed(self):
+        with patch.object(postgres_pillar_beacon, '_read_watermark', return_value=None), \
+             patch.object(postgres_pillar_beacon, '_query', return_value='abc'), \
+             patch.object(postgres_pillar_beacon, '_write_watermark') as mock_write:
+            self.assertEqual(postgres_pillar_beacon.beacon({}), [])
+        mock_write.assert_not_called()
+
+    # -- beacon: steady state ---------------------------------------------
+
+    def test_beacon_query_failure_returns_empty(self):
+        with patch.object(postgres_pillar_beacon, '_read_watermark', return_value=10), \
+             patch.object(postgres_pillar_beacon, '_query', return_value=None), \
+             patch.object(postgres_pillar_beacon, '_write_watermark') as mock_write:
+            self.assertEqual(postgres_pillar_beacon.beacon({}), [])
+        mock_write.assert_not_called()
+
+    def test_beacon_emits_events_and_advances_watermark(self):
+        sep = postgres_pillar_beacon.FIELD_SEP
+        rows = '11%s5%snode1\n12%s6%s\n' % (sep, sep, sep, sep)
+        with patch.object(postgres_pillar_beacon, '_read_watermark', return_value=10), \
+             patch.object(postgres_pillar_beacon, '_query', return_value=rows), \
+             patch.object(postgres_pillar_beacon, '_write_watermark') as mock_write:
+            result = postgres_pillar_beacon.beacon({})
+        self.assertEqual(result, [
+            {'tag': 'audit_settings', 'id': 11, 'setting_id': '5', 'node_id': 'node1'},
+            {'tag': 'audit_settings', 'id': 12, 'setting_id': '6', 'node_id': ''},
+        ])
+        mock_write.assert_called_once_with(12)
+
+    def test_beacon_skips_malformed_blank_and_noninteger_rows(self):
+        sep = postgres_pillar_beacon.FIELD_SEP
+        rows = (
+            '\n'                       # blank line -> skipped
+            '13%s7\n'                  # too few fields -> skipped
+            'abc%s8%snodeX\n'          # non-integer id -> skipped
+            '14%s9%snodeY\n'           # the one good row
+        ) % (sep, sep, sep, sep, sep)
+        with patch.object(postgres_pillar_beacon, '_read_watermark', return_value=10), \
+             patch.object(postgres_pillar_beacon, '_query', return_value=rows), \
+             patch.object(postgres_pillar_beacon, '_write_watermark') as mock_write:
+            result = postgres_pillar_beacon.beacon({})
+        self.assertEqual(result, [
+            {'tag': 'audit_settings', 'id': 14, 'setting_id': '9', 'node_id': 'nodeY'},
+        ])
+        mock_write.assert_called_once_with(14)
+
+    def test_beacon_no_new_rows_does_not_advance_watermark(self):
+        with patch.object(postgres_pillar_beacon, '_read_watermark', return_value=10), \
+             patch.object(postgres_pillar_beacon, '_query', return_value=''), \
+             patch.object(postgres_pillar_beacon, '_write_watermark') as mock_write:
+            self.assertEqual(postgres_pillar_beacon.beacon({}), [])
+        mock_write.assert_not_called()
+
+
+if __name__ == '__main__':
+    unittest.main()

salt/_beacons/zeek.py

@@ -3,31 +3,30 @@ import logging
 
 def status():
 
- cmd = "runuser -l zeek -c '/opt/zeek/bin/zeekctl status'"
+    cmd = "runuser -l zeek -c '/opt/zeek/bin/zeekctl status'"
- retval = __salt__['docker.run']('so-zeek', cmd)
+    retval = __salt__['docker.run']('so-zeek', cmd)  # noqa: F821
- logging.info('zeekctl_module: zeekctl.status retval: %s' % retval)
+    logging.info('zeekctl_module: zeekctl.status retval: %s' % retval)
 
- return retval
+    return retval
 
 
 def beacon(config):
 
-  retval = []
+    retval = []
 
-  is_enabled = __salt__['healthcheck.is_enabled']()
+    is_enabled = __salt__['healthcheck.is_enabled']()  # noqa: F821
-  logging.info('zeek_beacon: healthcheck_is_enabled: %s' % is_enabled)
+    logging.info('zeek_beacon: healthcheck_is_enabled: %s' % is_enabled)
 
-  if is_enabled:
+    if is_enabled:
-    zeekstatus = status().lower().split(' ')
+        zeekstatus = status().lower().split(' ')
-    logging.info('zeek_beacon: zeekctl.status: %s' % str(zeekstatus))
+        logging.info('zeek_beacon: zeekctl.status: %s' % str(zeekstatus))
-    if 'stopped' in zeekstatus or 'crashed' in zeekstatus or 'error' in zeekstatus or 'error:' in zeekstatus:
+        if 'stopped' in zeekstatus or 'crashed' in zeekstatus or 'error' in zeekstatus or 'error:' in zeekstatus:
-     zeek_restart = True
+            zeek_restart = True
-    else:
+        else:
-     zeek_restart = False
+            zeek_restart = False
 
-    __salt__['telegraf.send']('healthcheck zeek_restart=%s' % str(zeek_restart))
+        __salt__['telegraf.send']('healthcheck zeek_restart=%s' % str(zeek_restart))  # noqa: F821
-    retval.append({'zeek_restart': zeek_restart})
+        retval.append({'zeek_restart': zeek_restart})
-    logging.info('zeek_beacon: retval: %s' % str(retval))
+        logging.info('zeek_beacon: retval: %s' % str(retval))
-
-  return retval
 
+    return retval

salt/_beacons/zeek_test.py

@@ -0,0 +1,59 @@
+# 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.
+
+import unittest
+from unittest.mock import MagicMock
+
+import zeek
+
+ZEEKCTL_CMD = "runuser -l zeek -c '/opt/zeek/bin/zeekctl status'"
+
+
+class TestZeekBeacon(unittest.TestCase):
+
+    def setUp(self):
+        # zeek.py relies on the __salt__ dunder that Salt injects at load time.
+        # Nothing defines it under test, so we attach a dict of mock loader
+        # functions to the module and remove it again afterwards.
+        self.salt = {
+            'docker.run': MagicMock(return_value='Zeek is running'),
+            'healthcheck.is_enabled': MagicMock(return_value=True),
+            'telegraf.send': MagicMock(),
+        }
+        zeek.__salt__ = self.salt
+        self.addCleanup(lambda: delattr(zeek, '__salt__'))
+
+    # -- status -----------------------------------------------------------
+
+    def test_status_runs_zeekctl_and_returns_output(self):
+        self.salt['docker.run'].return_value = 'Zeek is running'
+        result = zeek.status()
+        self.assertEqual(result, 'Zeek is running')
+        self.salt['docker.run'].assert_called_once_with('so-zeek', ZEEKCTL_CMD)
+
+    # -- beacon -----------------------------------------------------------
+
+    def test_beacon_disabled_returns_empty_and_skips_telegraf(self):
+        self.salt['healthcheck.is_enabled'].return_value = False
+        self.assertEqual(zeek.beacon({}), [])
+        self.salt['telegraf.send'].assert_not_called()
+
+    def test_beacon_running_reports_no_restart(self):
+        self.salt['docker.run'].return_value = 'Zeek is running'
+        self.assertEqual(zeek.beacon({}), [{'zeek_restart': False}])
+        self.salt['telegraf.send'].assert_called_once_with('healthcheck zeek_restart=False')
+
+    def test_beacon_unhealthy_status_triggers_restart(self):
+        # Each of these status tokens should flag a restart (the or-chain in beacon).
+        for status_text in ('Zeek is stopped', 'Zeek crashed', 'Zeek error state', 'Zeek error:'):
+            with self.subTest(status=status_text):
+                self.salt['docker.run'].return_value = status_text
+                self.salt['telegraf.send'].reset_mock()
+                self.assertEqual(zeek.beacon({}), [{'zeek_restart': True}])
+                self.salt['telegraf.send'].assert_called_once_with('healthcheck zeek_restart=True')
+
+
+if __name__ == '__main__':
+    unittest.main()

salt/allowed_states.map.jinja

@@ -29,19 +29,23 @@
     'manager',
     'nginx',
     'influxdb',
+    'postgres',
+    'postgres.auth',
     'soc',
     'kratos',
     'hydra',
     'elasticfleet',
-    'elastic-fleet-package-registry',
+    'elasticfleet.manager',
-    'utility'
+    'elasticsearch.cluster',
+    'elastic-fleet-package-registry'
 ] %}
 
 {% set sensor_states = [
     'suricata',
     'healthcheck',
     'tcpreplay',
-    'zeek'
+    'zeek',
+    'strelka'
 ] %}
 
 {% set kafka_states = [
@@ -76,33 +80,33 @@
         ),
         'so-heavynode': (
             sensor_states +
-            ['elasticagent', 'elasticsearch', 'logstash', 'redis', 'nginx']
+            ['elasticagent', 'elasticsearch', 'elasticsearch.cluster', 'logstash', 'redis', 'nginx']
         ),
         'so-idh': (
             ['idh']
         ),
         'so-import': (
             manager_states +
-            sensor_states | reject('equalto', 'healthcheck') | list +
+            sensor_states | reject('equalto', 'strelka') | reject('equalto', 'healthcheck') | list +
-            ['elasticsearch', 'elasticsearch.auth', 'kibana', 'kibana.secrets', 'logstash.ssl']
+            ['elasticsearch', 'elasticsearch.auth', 'kibana', 'kibana.secrets', 'logstash.ssl', 'strelka.manager']
         ),
         'so-manager': (
             manager_states +
-            ['salt.cloud', 'libvirt.packages', 'libvirt.ssh.users'] +
+            ['salt.cloud', 'libvirt.packages', 'libvirt.ssh.users', 'strelka.manager'] +
             stig_states +
             kafka_states +
             elastic_stack_states
         ),
         'so-managerhype': (
             manager_states +
-            ['salt.cloud', 'hypervisor', 'libvirt'] +
+            ['salt.cloud', 'strelka.manager', 'hypervisor', 'libvirt'] +
             stig_states +
             kafka_states +
             elastic_stack_states
         ),
         'so-managersearch': (
             manager_states +
-            ['salt.cloud', 'libvirt.packages', 'libvirt.ssh.users'] +
+            ['salt.cloud', 'libvirt.packages', 'libvirt.ssh.users', 'strelka.manager'] +
             stig_states +
             kafka_states +
             elastic_stack_states

salt/backup/config_backup.sls

@@ -32,3 +32,4 @@ so_config_backup:
     - daymonth: '*'
     - month: '*'
     - dayweek: '*'
+

salt/backup/tools/sbin/so-config-backup.jinja

@@ -25,9 +25,11 @@ if [ ! -f $BACKUPFILE ]; then
   # Create empty backup file
   tar -cf $BACKUPFILE -T /dev/null
 
-  # Loop through all paths defined in global.sls, and append them to backup file
+  # Loop through all paths defined in global.sls, and append them to backup file if they exist
   {%- for LOCATION in BACKUPLOCATIONS %}
-  tar -rf $BACKUPFILE "${EXCLUSIONS[@]}" {{ LOCATION }}
+  if [[ -d {{ LOCATION }} || -f {{ LOCATION }} ]]; then
+    tar -rf $BACKUPFILE "${EXCLUSIONS[@]}" {{ LOCATION }}
+  fi
   {%- endfor %}
 
 fi

salt/ca/files/signing_policies.conf

@@ -54,6 +54,20 @@ x509_signing_policies:
     - extendedKeyUsage: serverAuth
     - days_valid: 820
     - copypath: /etc/pki/issued_certs/
+  postgres:
+    - minions: '*'
+    - signing_private_key: /etc/pki/ca.key
+    - signing_cert: /etc/pki/ca.crt
+    - C: US
+    - ST: Utah
+    - L: Salt Lake City
+    - basicConstraints: "critical CA:false"
+    - keyUsage: "critical keyEncipherment"
+    - subjectKeyIdentifier: hash
+    - authorityKeyIdentifier: keyid,issuer:always
+    - extendedKeyUsage: serverAuth
+    - days_valid: 820
+    - copypath: /etc/pki/issued_certs/
   elasticfleet:
     - minions: '*'
     - signing_private_key: /etc/pki/ca.key

salt/common/init.sls

@@ -117,25 +117,61 @@ elastic_curl_config:
 {% endif %}
 
 
+# A non-root owner here can chmod the directory and replace any script in it, including
+# the root-owned ones. 555 is the mode the filesystem RPM ships; root ignores it anyway.
+usr_sbin_perms:
+  file.directory:
+    - name: /usr/sbin
+    - user: root
+    - group: root
+    - mode: 555
+
 common_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin
-    - user: 939
+    - user: root
-    - group: 939
+    - group: root
     - file_mode: 755
     - show_changes: False
+    - require:
+      - file: usr_sbin_perms
 {% if GLOBALS.role == 'so-heavynode' %}
     - exclude_pat:
       - so-pcap-import
 {% endif %}
 
+# Pin physical NIC names by MAC (run-once) so a kernel upgrade can't renumber the
+# interfaces SO binds by name. The marker keeps it a one-time setup; an admin can
+# pre-create the marker to opt out.
+pin_nic_names:
+  cmd.run:
+    - name: /usr/sbin/so-nic-pin
+    - unless: 'test -e /opt/so/state/nic_names_pinned'
+    - require:
+      - file: common_sbin
+      - file: statedir
+
+# Once a node is actually running UEK8, the stock EL9 (RHCK) kernel packages are dead weight.
+# They can't be removed any earlier -- dnf protects the running kernel -- so the cleanup waits
+# for the reboot, which makes the highstate the natural place to catch it: fresh installs
+# reboot at the end of setup, and upgraded nodes reboot whenever the admin schedules it.
+# so-kernel-upgrade --cleanup checks rpm before touching dnf, so this costs an rpm query on
+# every highstate after the first pass. The package list lives in the script only, so there
+# is nothing here to drift out of sync with it.
+remove_stock_kernel:
+  cmd.run:
+    - name: /usr/sbin/so-kernel-upgrade --cleanup
+    - onlyif: 'uname -r | grep -qE "^6\.[0-9]+.*uek"'
+    - require:
+      - file: common_sbin
+
 common_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://common/tools/sbin_jinja
-    - user: 939
+    - user: root
-    - group: 939 
+    - group: root
     - file_mode: 755
     - template: jinja
     - show_changes: False
@@ -148,6 +184,8 @@ so-status_script:
   file.managed:
     - name: /usr/sbin/so-status
     - source: salt://common/tools/sbin/so-status
+    - user: root
+    - group: root
     - mode: 755
 
 {% if GLOBALS.is_sensor %}
@@ -179,9 +217,11 @@ sostatus_log:
     - replace: False
 
 # Install sostatus check cron. This is used to populate Grid.
+# telegraf reads status.log on the same minute boundary this runs, so write aside and rename
+# rather than truncating the file it is reading
 so-status_check_cron:
   cron.present:
-    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log 2>&1'
+    - name: '/usr/sbin/so-status -j > /opt/so/log/sostatus/status.log.tmp 2>&1; mv -f /opt/so/log/sostatus/status.log.tmp /opt/so/log/sostatus/status.log'
     - identifier: so-status_check_cron
     - user: root
     - minute: '*/1'

salt/common/soup_scripts.sls

@@ -18,47 +18,61 @@ copy_so-common_common_tools_sbin:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_common_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/common/tools/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/manager/tools/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_manager_tools_sbin:
   file.copy:
     - name: /opt/so/saltstack/default/salt/salt/scripts/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 644
 
 # This section is used to put the new script in place so that it can be called during soup.
 # It is faster than calling the states that normally manage them to put them in place.
@@ -67,46 +81,60 @@ copy_so-common_sbin:
     - name: /usr/sbin/so-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-image-common_sbin:
   file.copy:
     - name: /usr/sbin/so-image-common
     - source: {{UPDATE_DIR}}/salt/common/tools/sbin/so-image-common
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_soup_sbin:
   file.copy:
     - name: /usr/sbin/soup
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/soup
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-firewall_sbin:
   file.copy:
     - name: /usr/sbin/so-firewall
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-firewall
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-yaml_sbin:
   file.copy:
     - name: /usr/sbin/so-yaml.py
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-yaml.py
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_so-repo-sync_sbin:
   file.copy:
     - name: /usr/sbin/so-repo-sync
     - source: {{UPDATE_DIR}}/salt/manager/tools/sbin/so-repo-sync
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755
 
 copy_bootstrap-salt_sbin:
   file.copy:
     - name: /usr/sbin/bootstrap-salt.sh
     - source: {{UPDATE_DIR}}/salt/salt/scripts/bootstrap-salt.sh
     - force: True
-    - preserve: True
+    - user: root
+    - group: root
+    - mode: 755

salt/common/tools/sbin/so-common

@@ -142,6 +142,11 @@ check_elastic_license() {
 	fi  
 }
 
+check_elasticsearch_responsive() {
+    retry 3 15 "so-elasticsearch-query / --output /dev/null --fail" ||
+        fail "Elasticsearch is not responding. Please review Elasticsearch logs /opt/so/log/elasticsearch/securityonion.log for more details. Additionally, consider running so-elasticsearch-troubleshoot."
+}
+
 check_salt_master_status() {
 	local count=0
     local attempts="${1:- 10}"
@@ -235,7 +240,8 @@ copy_new_files() {
   cd $UPDATE_DIR
   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/
+  # Root-executed code; SOC only needs to read it. Local dirs stay socore-owned.
+  chown -R root:root $DEFAULT_SALT_DIR/
   cd /tmp
 }
 
@@ -286,6 +292,20 @@ download_and_verify() {
 	fi
 }
 
+# check if container with name is running and optionally stop it
+docker_check_running() {
+    # show running containers, only names
+    if docker ps --format '{{.Names}}' | grep -q "^so-${1}$"; then
+        if [[ "$2" == "--stop" ]]; then
+            docker stop "so-${1}"
+        fi
+
+        return 0
+    else
+        return 1
+    fi
+}
+
 elastic_license() {
 
 read -r -d '' message <<- EOM
@@ -399,6 +419,19 @@ is_single_node_grid() {
 	grep "role: so-" /etc/salt/grains | grep -E "eval|standalone|import" &> /dev/null
 }
 
+remove_elasticsearch_index_template() {
+  local template_name=$1
+  local reason=${2:-"Removing index template for upgrade"}
+
+  # check if template exists
+  if so-elasticsearch-query "_index_template/$template_name" --fail --retry 3 --retry-delay 5 >/dev/null 2>&1; then
+    echo "Removing Elasticsearch index template: $template_name ($reason)"
+    if ! so-elasticsearch-query "_index_template/$template_name" -XDELETE --fail --retry 3 --retry-delay 5; then
+      return 1
+    fi
+  fi
+}
+
 initialize_elasticsearch_indices() {
     local index_names=$1
     local default_entry=${2:-'{"@timestamp":"0"}'}
@@ -583,42 +616,6 @@ run_check_net_err() {
 	fi
 }
 
-wait_for_salt_minion() {
-    local minion="$1"
-    local max_wait="${2:-30}"
-    local interval="${3:-2}"
-    local logfile="${4:-'/dev/stdout'}"
-    local elapsed=0
-
-	echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - Waiting for salt-minion '$minion' to be ready..."
-
-    while [ $elapsed -lt $max_wait ]; do
-        # Check if service is running
-		echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - Check if salt-minion service is running"
-        if ! systemctl is-active --quiet salt-minion; then
-            echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - salt-minion service not running (elapsed: ${elapsed}s)"
-            sleep $interval
-            elapsed=$((elapsed + interval))
-            continue
-        fi
-		echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - salt-minion service is running"
-
-        # Check if minion responds to ping
-		echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - Check if $minion responds to ping"
-        if salt "$minion" test.ping --timeout=3 --out=json 2>> "$logfile" | grep -q "true"; then
-            echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - salt-minion '$minion' is connected and ready!"
-            return 0
-        fi
-        
-        echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - Waiting... (${elapsed}s / ${max_wait}s)"
-        sleep $interval
-        elapsed=$((elapsed + interval))
-    done
-
-    echo "$(date '+%a %d %b %Y %H:%M:%S.%6N') - ERROR: salt-minion '$minion' not ready after $max_wait seconds"
-    return 1
-}
-
 salt_minion_count() {
 	local MINIONDIR="/opt/so/saltstack/local/pillar/minions"
 	MINIONCOUNT=$(ls -la $MINIONDIR/*.sls | grep -v adv_ | wc -l)
@@ -683,7 +680,7 @@ systemctl_func() {
 
 	echo ""
 	echo "${echo_action^}ing $service_name service at $(date +"%T.%6N")"
-    systemctl $action $service_name && echo "Successfully ${echo_action}ed $service_name." || echo "Failed to $action $service_name."
+    systemctl $action $service_name && echo "Successfully ${echo_action}ed $service_name at $(date +"%T.%6N")." || echo "Failed to $action $service_name at $(date +"%T.%6N")."
 	echo ""
 }
 

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

@@ -9,6 +9,7 @@ import sys
 import subprocess
 import os
 import json
+import tempfile
 
 sys.path.append('/opt/saltstack/salt/lib/python3.10/site-packages/')
 import salt.config
@@ -17,6 +18,21 @@ import salt.loader
 __opts__ = salt.config.minion_config('/etc/salt/minion')
 __grains__ = salt.loader.grains(__opts__)
 
+def write_atomic(path, value):
+  # telegraf reads these files on its own schedule; replacing them by rename means it never
+  # reads a truncated file and reports an empty value as if it were real
+  directory = os.path.dirname(path)
+  handle, temp = tempfile.mkstemp(dir=directory)
+  try:
+    with os.fdopen(handle, 'w') as f:
+      f.write(str(value))
+    os.chmod(temp, 0o644)
+    os.replace(temp, path)
+  except Exception:
+    os.path.exists(temp) and os.unlink(temp)
+    raise
+
+
 def check_needs_restarted():
   osfam = __grains__['os_family']
   val = '0'
@@ -34,8 +50,7 @@ def check_needs_restarted():
   else:
     fail("Unsupported OS")
 
-  with open(outfile, 'w') as f:
+  write_atomic(outfile, val)
-    f.write(val)
 
 def check_for_fps():
     feat = 'fps'
@@ -56,8 +71,7 @@ def check_for_fps():
           # Unknown, so assume 0
           fps = 0
 
-    with open('/opt/so/log/sostatus/fps_enabled', 'w') as f:
+    write_atomic('/opt/so/log/sostatus/fps_enabled', fps)
-       f.write(str(fps))
 
 def check_for_lks():
     feat = 'Lks'
@@ -80,8 +94,7 @@ def check_for_lks():
                                 lks = 1
         if lks:
             break
-    with open('/opt/so/log/sostatus/lks_enabled', 'w') as f:
+    write_atomic('/opt/so/log/sostatus/lks_enabled', lks)
-       f.write(str(lks))
 
 def fail(msg):
   print(msg, file=sys.stderr)

salt/common/tools/sbin/so-image-common

@@ -31,6 +31,7 @@ container_list() {
       "so-hydra"
       "so-nginx"
       "so-pcaptools"
+      "so-postgres"
       "so-soc"
       "so-suricata"
       "so-telegraf"
@@ -55,8 +56,11 @@ container_list() {
       "so-logstash"
       "so-nginx"
       "so-pcaptools"
+      "so-postgres"
       "so-redis"
       "so-soc"
+      "so-strelka-backend"
+      "so-strelka-manager"
       "so-suricata"
       "so-telegraf"
       "so-zeek"
@@ -184,8 +188,27 @@ update_docker_containers() {
         if [ -z "$HOSTNAME" ]; then
           HOSTNAME=$(hostname)
         fi
-        docker tag $CONTAINER_REGISTRY/$IMAGEREPO/$image $HOSTNAME:5000/$IMAGEREPO/$image >> "$LOG_FILE" 2>&1 
+        docker tag $CONTAINER_REGISTRY/$IMAGEREPO/$image $HOSTNAME:5000/$IMAGEREPO/$image >> "$LOG_FILE" 2>&1 || {
-        docker push $HOSTNAME:5000/$IMAGEREPO/$image >> "$LOG_FILE" 2>&1 
+          echo "Unable to tag $image" >> "$LOG_FILE" 2>&1
+          exit 1
+        }
+        # Push to the embedded registry via a registry-to-registry copy. Avoids
+        # `docker push`, which on Docker 29.x with the containerd image store
+        # represents freshly-pulled images as an index whose layer content
+        # isn't reachable through the push path. The local `docker tag` above
+        # is preserved so so-image-pull's `:5000` existence check still works.
+        # Pin to the digest already gpg-verified above so we copy exactly the
+        # bytes we approved.
+        local VERIFIED_REF
+        VERIFIED_REF=$(echo "$DOCKERINSPECT" | jq -r ".[0].RepoDigests[] | select(. | contains(\"$CONTAINER_REGISTRY\"))" | head -n 1)
+        if [ -z "$VERIFIED_REF" ] || [ "$VERIFIED_REF" = "null" ]; then
+          echo "Unable to determine verified digest for $image" >> "$LOG_FILE" 2>&1
+          exit 1
+        fi
+        docker buildx imagetools create --tag $HOSTNAME:5000/$IMAGEREPO/$image "$VERIFIED_REF" >> "$LOG_FILE" 2>&1 || {
+          echo "Unable to copy $image to embedded registry" >> "$LOG_FILE" 2>&1
+          exit 1
+        }
       fi
     else
       echo "There is a problem downloading the $image image. Details: " >> "$LOG_FILE" 2>&1 

salt/common/tools/sbin/so-kernel-upgrade

@@ -0,0 +1,317 @@
+#!/bin/bash
+#
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+#
+# so-kernel-upgrade — install the UEK8 (6.x) kernel, make it the boot default, and once the
+# node is running it, remove the stock EL9 kernel.
+#
+# Security Onion is moving off the EL9 stock kernel (RHCK, 5.14) and UEK7 (5.15) onto UEK8
+# (6.x). Four things have to happen, and the tool has to drive each one:
+#
+#   1. Populate. The manager mirrors the UEK8 packages into /nsm/kernelrepo via so-repo-sync,
+#      and serves them to the grid over https://<manager>/kernelrepo. Until that sync runs the
+#      repo is valid but EMPTY -- dnf resolves it happily and installs nothing, with no error.
+#   2. Install. A node on RHCK has no kernel-uek* package at all, so there is nothing for
+#      'dnf update' to upgrade. A node on UEK7 does have kernel-uek installed, so
+#      'dnf install kernel-uek' reports "Nothing to do" and exits 0 without installing 6.x.
+#      Both cases need an explicit install of the UEK8 NEVRA.
+#   3. Boot it. Whether a newly installed UEK8 kernel becomes the boot default depends on the
+#      RUNNING kernel's flavor. kernel-install/grubby (with UPDATEDEFAULT=yes) only auto-promote
+#      within the running kernel's flavor lineage:
+#        - From UEK7 (5.x, kernel-uek) the install stays in the kernel-uek lineage and IS
+#          auto-promoted, so no grubby change is needed -- just make sure the repo is populated
+#          and install UEK8.
+#        - From the stock EL9 kernel (RHCK, 5.14, no UEK) it is a flavor CROSS that is NOT
+#          auto-promoted, so the box keeps booting RHCK until grubby is told otherwise.
+#      This tool inspects the running kernel and only runs 'grubby --set-default' for RHCK.
+#   4. Clean up. Once the node is actually RUNNING UEK8 the stock kernel packages are dead
+#      weight -- disk in /boot and a stale GRUB entry. They cannot come off any earlier:
+#      dnf's protect_running_kernel refuses to erase the booted kernel-core, so the removal
+#      has to wait for the reboot. Waiting is also the safer sequencing on its own terms --
+#      the node has proven it comes up on UEK8 before its fallback is deleted. That is why
+#      the removal does not happen in the uek7 branch either, where dnf would allow it.
+#
+# Every one of those failure modes is silent by default. This tool handles each case and fails
+# loudly when it cannot, rather than reporting success while changing nothing.
+#
+# Invocation: with no arguments it drives the whole sequence for whatever kernel the node is
+# on. With --cleanup it does the step 4 removal ONLY, and no-ops on a node that isn't running
+# UEK8 yet -- that is the form the common highstate calls (remove_stock_kernel in
+# salt/common/init.sls) so the cleanup lands grid-wide after each node reboots.
+#
+# Manager vs minion: only the manager owns /nsm/kernelrepo, so only the manager can populate
+# it. If the repo is empty here, a manager runs so-repo-sync itself; a minion has no way to
+# fix it and exits non-zero telling the admin to sync the manager first.
+#
+# Idempotent: an already-installed, already-default UEK8 kernel is left alone. It only sets
+# the boot default; it does NOT reboot -- the admin reboots the node on their own schedule.
+
+. /usr/sbin/so-common
+
+# Client-side repo id (what dnf enables on this node, from repo/client/oracle.sls) vs the
+# reposync-side section in repodownload.conf that the manager mirrors from (mirrors the
+# securityonion/securityonionsync split for the main repo).
+KERNEL_REPO="securityonionkernel"
+KERNEL_REPO_SYNC="securityonionkernelsync"
+KERNEL_PKG="kernel-uek"
+KERNEL_REPO_DIR="/nsm/kernelrepo"
+REPOSYNC_CONF="/opt/so/conf/reposync/repodownload.conf"
+GLOBAL_PILLAR="/opt/so/saltstack/local/pillar/global/soc_global.sls"
+
+# Stock EL9 (RHCK) kernel packages, removed only once the node is running UEK8 (see step 4
+# in the header). Left deliberately narrow: UEK7 kernel-uek builds age out on their own via
+# installonly_limit=3, and kernel-devel/kernel-headers are not touched.
+RHCK_PKGS="kernel kernel-core kernel-modules kernel-modules-core kernel-tools kernel-tools-libs"
+
+log() { echo "[so-kernel-upgrade] $*"; }
+die() { echo "[so-kernel-upgrade] ERROR: $*" >&2; exit 1; }
+
+command -v grubby >/dev/null 2>&1 || die "grubby not found"
+command -v dnf >/dev/null 2>&1 || die "dnf not found"
+
+ARCH="$(rpm -E '%{_arch}')"
+
+is_airgap() {
+    [ -f "$GLOBAL_PILLAR" ] && grep -q 'airgap: *[Tt]rue' "$GLOBAL_PILLAR"
+}
+
+# Newest installed UEK8 (6.x) kernel known to the bootloader. UEK8 vmlinuz paths look like
+# /boot/vmlinuz-6.12.0-204.92.4.2.el9uek.x86_64; UEK7 (5.15) and RHCK (5.14) won't match.
+find_uek8() {
+    grubby --info=ALL 2>/dev/null \
+        | sed -n 's/^kernel="\(.*\)"$/\1/p' \
+        | grep -E '/vmlinuz-6\.[0-9]+.*uek' \
+        | sort -V | tail -1
+}
+
+# Classify the RUNNING kernel (uname -r) -- this, not what's installed, is what decides whether
+# a UEK8 install auto-promotes to the boot default:
+#   uek8  6.x UEK    already on the target line; nothing to do
+#   uek7  5.x UEK    a UEK8 install stays in the kernel-uek lineage and auto-promotes (no grubby)
+#   rhck  5.14 EL9   crossing into the UEK flavor does NOT auto-promote (needs grubby --set-default)
+running_flavor() {
+    case "$(uname -r)" in
+        6.*uek*) echo uek8 ;;
+        *uek*)   echo uek7 ;;
+        *)       echo rhck ;;
+    esac
+}
+
+# Newest UEK8 kernel-uek NEVRA offered by the kernel repo, empty if the repo has none.
+# Restricted to the kernel repo so a UEK7 kernel-uek in the main repo can't be picked up,
+# and filtered to 6.x so we never "succeed" by reinstalling the 5.15 we already have.
+uek8_available() {
+    dnf -q repoquery --disablerepo='*' --enablerepo="$KERNEL_REPO" \
+        --arch="$ARCH" --latest-limit=1 \
+        --qf '%{name}-%{evr}.%{arch}\n' "$KERNEL_PKG" 2>/dev/null \
+        | grep -E "^${KERNEL_PKG}-6\." | tail -1
+}
+
+kernelrepo_rpm_count() {
+    find "$KERNEL_REPO_DIR" -maxdepth 1 -name '*.rpm' 2>/dev/null | wc -l
+}
+
+# The kernel repo starts life as valid-but-empty (kernelrepo_init_empty in
+# salt/manager/init.sls) and is filled by so-repo-sync. During a soup, so-repo-sync runs
+# BEFORE the highstate deploys the [securityonionkernelsync] section into repodownload.conf, so
+# the first kernel-aware soup leaves the repo empty until the next nightly sync.
+sync_kernel_repo() {
+    if is_airgap; then
+        log "airgap install: $KERNEL_REPO_DIR is populated from the airgap ISO, not by so-repo-sync."
+        return 1
+    fi
+    if ! grep -q "^\[${KERNEL_REPO_SYNC}\]" "$REPOSYNC_CONF" 2>/dev/null; then
+        log "$REPOSYNC_CONF has no [${KERNEL_REPO_SYNC}] section -- run a highstate to deploy it."
+        return 1
+    fi
+
+    log "populating $KERNEL_REPO_DIR with so-repo-sync (mirrors upstream; can take several minutes)"
+    su socore -c '/usr/sbin/so-repo-sync' || { log "so-repo-sync failed"; return 1; }
+
+    dnf -q clean expire-cache >/dev/null 2>&1
+    return 0
+}
+
+# Make the kernel repo actually able to serve a UEK8 package, or fail trying.
+ensure_kernel_repo() {
+    # The repo is assigned by the repo.client highstate, and only once NICs are pinned by MAC
+    # (/opt/so/state/nic_names_pinned) so the kernel swap can't renumber interfaces SO binds
+    # by name. skip_if_unavailable=1 means a broken repo is silently ignored, so check first.
+    if ! dnf -q repolist --enabled 2>/dev/null | awk '{print $1}' | grep -qx "$KERNEL_REPO"; then
+        log "repo '$KERNEL_REPO' is not enabled on this node."
+        log "Run a highstate first; the repo is skipped until /opt/so/state/nic_names_pinned"
+        log "exists (run so-nic-pin) and this node's salt matches the version this release ships."
+        die "kernel repo unavailable"
+    fi
+
+    [ -n "$(uek8_available)" ] && return 0
+
+    log "repo '$KERNEL_REPO' is enabled but offers no UEK8 $KERNEL_PKG package"
+
+    if ! is_manager_node; then
+        log "This is a minion; it consumes the kernel repo from the manager and cannot populate it."
+        log "On the manager, run:  su socore -c /usr/sbin/so-repo-sync"
+        log "then re-run this script here."
+        die "manager's kernel repo is empty"
+    fi
+
+    log "this is a manager and $KERNEL_REPO_DIR holds $(kernelrepo_rpm_count) rpm(s)"
+    sync_kernel_repo || die "could not populate $KERNEL_REPO_DIR"
+
+    [ -n "$(uek8_available)" ] \
+        || die "so-repo-sync completed but $KERNEL_REPO still offers no UEK8 $KERNEL_PKG"
+}
+
+reboot_notice() {
+    [ "$(uname -r)" = "$(basename "$1" | sed 's/^vmlinuz-//')" ] && return 0
+    log "REBOOT REQUIRED to start using the UEK8 kernel (currently running $(uname -r))."
+    # The stock kernel can't be removed until it stops being the running one, so say when
+    # that will happen rather than leaving the admin to wonder if it was missed.
+    [ -n "$(rhck_installed)" ] \
+        && log "The stock EL9 kernel is left in place until then; it is removed by the next highstate after the reboot."
+    return 0
+}
+
+# Keep future kernel updates on the UEK line rather than falling back to RHCK. Oracle ships
+# /etc/sysconfig/kernel; only rewrite it when it's actually pointing somewhere else.
+set_default_kernel_conf() {
+    if [ -f /etc/sysconfig/kernel ] && ! grep -q '^DEFAULTKERNEL=kernel-uek-core$' /etc/sysconfig/kernel; then
+        log "setting DEFAULTKERNEL=kernel-uek-core in /etc/sysconfig/kernel"
+        sed -i 's/^DEFAULTKERNEL=.*/DEFAULTKERNEL=kernel-uek-core/' /etc/sysconfig/kernel
+    fi
+}
+
+# Which of RHCK_PKGS are actually installed, one per line. rpm -qa treats each argument as a
+# name glob and prints only what it finds, so a package that was never installed (or is
+# already gone) simply doesn't appear -- no "not installed" noise and no non-zero exit.
+rhck_installed() {
+    rpm -qa $RHCK_PKGS 2>/dev/null
+}
+
+# Remove the stock EL9 kernel. Only ever called once the running kernel is UEK8. The rpm
+# check above is the idempotency guard, so this is a cheap no-op on every highstate after
+# the first one -- it costs an rpm query, not a dnf transaction.
+remove_rhck() {
+    local installed; installed="$(rhck_installed)"
+    if [ -z "$installed" ]; then
+        log "no stock EL9 (RHCK) kernel packages installed; nothing to remove."
+        return 0
+    fi
+
+    log "running UEK8; removing the stock EL9 (RHCK) kernel packages:"
+    echo "$installed" | sed 's/^/[so-kernel-upgrade]   /'
+    dnf -y remove $RHCK_PKGS || die "failed to remove the stock EL9 kernel packages"
+
+    installed="$(rhck_installed)"
+    [ -z "$installed" ] || die "dnf reported success but these remain: $(echo $installed)"
+    log "stock EL9 kernel packages removed."
+}
+
+# Make sure a UEK8 kernel is installed, leaving its boot entry in INSTALLED_UEK8. If one is
+# already present we leave the repo alone -- it may be disabled or empty and we don't need it
+# just to flip the boot default. Otherwise install the explicit NEVRA, not the bare package
+# name: on a UEK7 node 'dnf install kernel-uek' sees 5.15 already present, prints "Nothing to
+# do" and exits 0 without installing 6.x.
+ensure_uek8_installed() {
+    INSTALLED_UEK8="$(find_uek8)"
+    if [ -n "$INSTALLED_UEK8" ]; then
+        log "UEK8 kernel already installed: $INSTALLED_UEK8"
+        return 0
+    fi
+
+    ensure_kernel_repo
+    local nevra; nevra="$(uek8_available)"
+    log "installing $nevra from $KERNEL_REPO"
+    dnf -y install "$nevra" || die "failed to install $nevra"
+
+    INSTALLED_UEK8="$(find_uek8)"
+    [ -n "$INSTALLED_UEK8" ] || die "$nevra installed but no 6.x UEK boot entry appeared -- check 'grubby --info=ALL'"
+    log "installed UEK8 kernel: $INSTALLED_UEK8"
+}
+
+# --cleanup does step 4 and nothing else. It exits 0 rather than failing on a node that
+# isn't on UEK8 yet: the highstate gates on 'uname -r' before calling this, and a state that
+# fails whenever that gate races would be worse than one that says what it's waiting for.
+case "$1" in
+"")
+    ;;
+--cleanup)
+    if [ "$(running_flavor)" != uek8 ]; then
+        log "not running a UEK8 kernel yet (currently $(uname -r)); leaving the stock EL9 kernel in place."
+        log "Run so-kernel-upgrade with no arguments to install UEK8, then reboot."
+        exit 0
+    fi
+    set_default_kernel_conf
+    remove_rhck
+    exit 0
+    ;;
+*)
+    echo "Usage: so-kernel-upgrade [--cleanup]" >&2
+    echo "  (no arguments)  install UEK8, make it the boot default, clean up once it's running" >&2
+    echo "  --cleanup       remove the stock EL9 kernel; no-op unless already running UEK8" >&2
+    exit 1
+    ;;
+esac
+
+case "$(running_flavor)" in
+uek8)
+    # Already on the 6.x UEK line. A plain 'dnf update' keeps this node current within the
+    # lineage and auto-promotes newer builds, so there is no install or grubby work left --
+    # only the step 4 cleanup, which this is the first point in the sequence that can run it.
+    log "already running a UEK8 kernel ($(uname -r)); no kernel install needed."
+    set_default_kernel_conf
+    remove_rhck
+    ;;
+
+uek7)
+    # On a 5.x UEK kernel. Installing UEK8 stays inside the kernel-uek lineage, so dnf/grubby
+    # (UPDATEDEFAULT=yes) auto-promote it and we do NOT touch grubby. A node still on UEK7
+    # usually means the kernel repo was empty when it last updated, so populate it and install.
+    log "running UEK7 kernel ($(uname -r)); the kernel repo was likely not yet populated when"
+    log "this node last updated. Populating it and installing UEK8 -- the update stays on the"
+    log "kernel-uek line, so it becomes the boot default automatically (no grubby change needed)."
+    set_default_kernel_conf
+    ensure_uek8_installed
+
+    now="$(grubby --default-kernel 2>/dev/null)"
+    if [ "$now" = "$INSTALLED_UEK8" ]; then
+        log "boot default auto-promoted to UEK8 kernel: $INSTALLED_UEK8"
+    else
+        log "WARNING: expected the UEK8 kernel to auto-promote but the default is still"
+        log "'${now:-unknown}'. Run 'grubby --set-default=$INSTALLED_UEK8' to force it."
+    fi
+    reboot_notice "$INSTALLED_UEK8"
+    ;;
+
+rhck)
+    # On the stock EL9 kernel (5.14, no UEK installed). Crossing from RHCK into the UEK flavor
+    # does NOT auto-promote -- kernel-install/grubby only auto-promote within the running
+    # kernel's flavor lineage -- so after installing we must set the boot default explicitly.
+    log "running stock EL9 (RHCK) kernel ($(uname -r)); installing UEK8 and setting it as the"
+    log "boot default explicitly (a RHCK->UEK flavor change does not auto-promote)."
+    set_default_kernel_conf
+    ensure_uek8_installed
+    target="$INSTALLED_UEK8"
+
+    current="$(grubby --default-kernel 2>/dev/null)"
+    if [ "$current" = "$target" ]; then
+        log "UEK8 kernel is already the boot default: $target"
+        reboot_notice "$target"
+        exit 0
+    fi
+
+    log "current default kernel: ${current:-unknown}"
+    log "switching boot default to UEK8 kernel: $target"
+    grubby --set-default="$target" || die "grubby --set-default failed for $target"
+
+    # Verify the change actually took before claiming success.
+    now="$(grubby --default-kernel 2>/dev/null)"
+    [ "$now" = "$target" ] || die "default kernel is still '${now:-unknown}' after set-default"
+
+    log "boot default is now $target"
+    reboot_notice "$target"
+    ;;
+esac

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

@@ -132,6 +132,9 @@ if [[ $EXCLUDE_STARTUP_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|HTTP 404: Not Found"          # Salt loops until Kratos returns 200, during startup Kratos may not be ready
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Cancelling deferred write event maybeFenceReplicas because the event queue is now closed" # Kafka controller log during shutdown/restart
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Redis may have been restarted" # Redis likely restarted by salt
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|file already closed"          # Go logging race condition during container restart
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|relation \"audit_settings\" does not exist" # salt checking for changes before SOC starts
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Error in plugin: elasticsearch: Unable to retrieve master node information" # expected error while ES is upgrading/electing a master 
 fi
 
 if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
@@ -152,6 +155,8 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|id.orig_h"                    # false positive (zeek test data)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|emerging-all.rules"           # false positive (error in rulename)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|invalid query input"          # false positive (Invalid user input in hunt query)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|no data available for the requested dates" # false positive (pcap cypress test submits a job with an empty time frame)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|no job processor"             # false positive (same empty-time-frame job on import nodes, where no pcap processor runs)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|example"                      # false positive (example test data)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|status 200"                   # false positive (request successful, contained error string in content)
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|app_layer.error"              # false positive (suricata 7) in stats.log e.g. app_layer.error.imap.parser | Total | 0
@@ -165,6 +170,14 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|upgrading component template"  # false positive (elasticsearch index or template names contain 'error')
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|upgrading composable template" # false positive (elasticsearch composable template names contain 'error')
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Error while parsing document for index \[.ds-logs-kratos-so-.*object mapping for \[file\]" # false positive (mapping error occuring BEFORE kratos index has rolled over in 2.4.210)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|No such container"            # false positive (telegraf trying to run stats on an old container)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|passwords do not match"       # false positive (automated hydra test)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Request did not pass preprocessing" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Missing or invalid authorization header for bearer token" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Unexpected authorization header" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Missing ory_kratos_session cookie" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Static assets preprocessor only supports GET and HEAD requests" # expected WARN log lines indicating invalid auth header
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|respondError"                 # respondError is a function name, output via http middleware as standard request logging
 fi
 
 if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
@@ -227,8 +240,9 @@ if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$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
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|TransformTask\] \[logs-(tychon|aws_billing|microsoft_defender_endpoint).*user so_kibana lacks the required permissions \[logs-\1" # Known issue with 3 integrations using kibana_system role vs creating unique api creds with proper permissions.
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|TransformTask\] \[logs-.*user so_kibana lacks the required permissions" # Known issue with integrations starting transform jobs that are explicitly not allowed to start as a system user
-    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # appears in so-dockerregistry log for so-tcpreplay following docker upgrade to 29.2.1-1
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|manifest unknown"             # so-dockerregistry logs a tag lookup miss during image copy; not tied to one docker version
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Could not index event to Elasticsearch.*\"version\" => \"9.0.8\"" # Expected during Elastic upgrade temporarily, as policies referencing older pipelines are updated
 fi
 
 RESULT=0

salt/common/tools/sbin/so-nic-pin

@@ -0,0 +1,76 @@
+#!/bin/bash
+#
+# so-nic-pin — pin physical NIC names by permanent MAC via classic by-MAC udev
+#              rules, so a kernel upgrade can't renumber them.
+#
+# Security Onion binds its management and monitor interfaces BY NAME in pillar
+# (host:mainint, sensor:mainint, and bond0 is built on a specific physical NIC).
+# A kernel upgrade can change the kernel/systemd-udevd predictable-naming output
+# and renumber those NICs (e.g. enp1s0 -> enp2s0), which breaks the grid: the
+# pillar references a name that no longer exists and bond/bridge bring-up fails.
+#
+# This writes /etc/udev/rules.d/70-persistent-net.rules pinning each PHYSICAL NIC
+# to its CURRENT name by its PERMANENT MAC, freezing the names across future kernel
+# changes. It only writes the rules file; it does NOT live-trigger a rename (the
+# rules apply on the next boot/kernel, and a live rename would be disruptive).
+#
+# Run-once: gated by the drop file /opt/so/state/nic_names_pinned. If the marker is
+# present the script does nothing, so an admin can pre-create it to opt out. Invoked
+# from the common state on every highstate; the marker keeps it a one-time setup.
+
+NET_RULES_FILE="/etc/udev/rules.d/70-persistent-net.rules"
+MARKER="/opt/so/state/nic_names_pinned"
+
+log() { echo -e "[so-nic-pin] $*"; }
+
+# Echo "<name> <permanent-mac>" for every PHYSICAL NIC. A physical NIC is backed by a
+# real device (has device/driver), which excludes bond0/sobridge/docker0/veth*/lo whose
+# MACs are dynamic and must never be pinned. The PERMANENT MAC is used (ethtool -P, with
+# fallbacks), not the current one: an enslaved bond member's current MAC is rewritten to
+# the bond's, so matching on it would be wrong/ambiguous.
+physical_nics() {
+    local path n mac
+    for path in /sys/class/net/*; do
+        n="${path##*/}"
+        [ "$n" = "lo" ] && continue
+        [ -e "${path}/device/driver" ] || continue          # real device only
+        mac="$(ethtool -P "$n" 2>/dev/null | awk '/Permanent address/{print $NF}')"
+        case "$mac" in ""|00:00:00:00:00:00) mac="$(cat "${path}/bonding_slave/perm_hwaddr" 2>/dev/null)" ;; esac
+        case "$mac" in ""|00:00:00:00:00:00) mac="$(cat "${path}/address" 2>/dev/null)" ;; esac
+        case "$mac" in ""|00:00:00:00:00:00) continue ;; esac
+        echo "$n $mac"
+    done
+}
+
+# Turn "<name> <mac>" lines on stdin into classic by-MAC persistent-net udev rules.
+render_net_rules() {
+    echo "# Generated by so-nic-pin: pin NIC names by MAC so kernel upgrades can't renumber them."
+    echo "# Security Onion binds its management/monitor interfaces by name; do not hand-edit."
+    local n mac
+    while read -r n mac; do
+        [ -n "$n" ] || continue
+        printf 'SUBSYSTEM=="net", ACTION=="add", DRIVERS=="?*", ATTR{address}=="%s", NAME="%s"\n' \
+            "$mac" "$n"
+    done
+}
+
+[ "$(id -u)" -eq 0 ] || exit 0                   # salt runs us as root; bail quietly otherwise
+[ -e "${MARKER}" ] && exit 0                      # run-once guard (mirrors the state's unless)
+
+nics="$(physical_nics)"
+if [ -z "${nics}" ]; then
+    log "no physical NICs detected — nothing to pin (will retry on next highstate)"
+    exit 0                                         # do NOT drop the marker; let it retry later
+fi
+
+log "pinning physical NICs by permanent MAC:"
+echo "${nics}" | sed 's/^/    /'
+
+[ -f "${NET_RULES_FILE}" ] && cp -f "${NET_RULES_FILE}" "${NET_RULES_FILE}.bak"
+echo "${nics}" | render_net_rules > "${NET_RULES_FILE}" || {
+    log "ERROR: failed to write ${NET_RULES_FILE}"
+    exit 1
+}
+
+mkdir -p "$(dirname "${MARKER}")" && touch "${MARKER}"
+log "wrote ${NET_RULES_FILE} ($(grep -c '^SUBSYSTEM' "${NET_RULES_FILE}") NIC(s) pinned); dropped ${MARKER}"

salt/common/tools/sbin/so-restart

@@ -5,27 +5,41 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
-
-# Usage: so-restart  kibana | playbook 
-
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
+usage() {
+    echo "Usage: $0 <component> [args]"
+    echo ""
+    echo "Supported args:"
+    echo "  --force | -f          Force stop all Salt jobs before starting component."
+    echo ""
+    echo "Examples:"
+    echo "  $0 kibana             Restart Kibana"
+    echo "  $0 kibana --force     Force stop all Salt jobs before restarting Kibana"
+    exit 1
+}
 
-        echo $banner
+if [[ $# -lt 1 ]]; then
-        printf "Restarting $1...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n"
+    usage
-        echo $banner
-
-        if [ "$2" = "--force" ]; then
-                printf "\nForce-stopping all Salt jobs before proceeding\n\n"
-                salt-call saltutil.kill_all_jobs
-        fi
-
-        case $1 in
-                "elastic-fleet") docker stop so-elastic-fleet && docker rm so-elastic-fleet && salt-call state.apply elasticfleet queue=True;;
-                *)  docker stop so-$1 ; docker rm so-$1 ; salt-call state.apply $1 queue=True;;
-        esac
-else
-        echo -e "\nPlease provide an argument by running like so-restart $component, or by using the component-specific script.\nEx. so-restart logstash, or so-logstash-restart\n"
 fi
+
+#shellcheck disable=SC2154
+echo "$banner"
+printf "Restarting %s...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n" "$1"
+echo "$banner"
+if [[ "$2" = "--force" ]] || [[ "$2" = "-f" ]]; then
+    printf "\nForce-stopping all Salt jobs before proceeding\n\n"
+    salt-call saltutil.kill_all_jobs
+fi
+case $1 in
+    "elastic-fleet"|"elasticfleet")
+        docker_check_running "elastic-fleet" "--stop"
+        docker rm "so-elastic-fleet" 2> /dev/null
+        salt-call state.apply elasticfleet queue=True
+        ;;
+    *)
+        docker_check_running "$1" "--stop"
+        docker rm "so-${1}" 2> /dev/null
+        salt-call state.apply "$1" queue=True
+        ;;
+esac

salt/common/tools/sbin/so-sensor-clean

@@ -8,21 +8,37 @@
 # Elastic License 2.0.
 
 
-SENSOR_DIR='/nsm'
+SENSOR_DIR="${SENSOR_DIR:-/nsm}"
 CRIT_DISK_USAGE=90
-CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
+LOG="${LOG:-/opt/so/log/sensor_clean.log}"
-LOG="/opt/so/log/sensor_clean.log"
+LOCK="${LOCK:-/var/tmp/so-sensor-clean.lock}"
-TODAY=$(date -u "+%Y-%m-%d")
+MAX_PASSES=100
 
+ZEEK_LOGS="$SENSOR_DIR/zeek/logs"
+STRELKA_FILES="$SENSOR_DIR/strelka/processed"
+SURICATA_LOGS="$SENSOR_DIR/suricata"
+PCAPS="$SENSOR_DIR/pcapout"
+
+log() {
+	echo "$(date) - $*" >>"$LOG"
+}
+
+disk_usage() {
+	df -P "$SENSOR_DIR" | tail -1 | awk '{print $5}' | tr -d %
+}
+
+disk_avail() {
+	df -P "$SENSOR_DIR" | tail -1 | awk '{print $4}'
+}
+
+# sets REMOVED=1 if anything was actually deleted
 clean() {
 	## find the oldest Zeek logs directory
-	OLDEST_DIR=$(ls /nsm/zeek/logs/ | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
+	OLDEST_DIR=$(ls "$ZEEK_LOGS" 2>/dev/null | grep -v "current" | grep -v "stats" | grep -v "packetloss" | grep -v "zeek_clean" | sort | head -n 1)
-	if [ -z "$OLDEST_DIR" -o "$OLDEST_DIR" == ".." -o "$OLDEST_DIR" == "." ]; then
+	if [ -n "$OLDEST_DIR" ]; then
-		echo "$(date) - No old Zeek logs available to clean up in /nsm/zeek/logs/" >>$LOG
+		log "Removing directory: $ZEEK_LOGS/$OLDEST_DIR"
-		#exit 0
+		rm -rf "$ZEEK_LOGS/$OLDEST_DIR"
-	else
+		REMOVED=1
-		echo "$(date) - Removing directory: /nsm/zeek/logs/$OLDEST_DIR" >>$LOG
-		rm -rf /nsm/zeek/logs/"$OLDEST_DIR"
 	fi
 
 	## Remarking for now, as we are moving extracted files to /nsm/strelka/processed
@@ -42,44 +58,74 @@ clean() {
 	#        done
 	#fi
 
+	## Clean up Zeek extracted files processed by Strelka
+	OLDEST_STRELKA=$(find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
+	if [ -n "$OLDEST_STRELKA" ]; then
+		OLDEST_STRELKA_DATE=$(echo $OLDEST_STRELKA | awk '{print $1}' | cut -d+ -f1)
+		log "Removing extracted files for $OLDEST_STRELKA_DATE"
+		REMOVED=1
+		find "$STRELKA_FILES" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_STRELKA_DATE | awk '{print $2}' | while read FILE; do
+			log "Removing file: $FILE"
+			rm -f "$FILE"
+		done
+	fi
+
 	## Clean up Suricata log files
-	SURICATA_LOGS='/nsm/suricata'
+	OLDEST_SURICATA=$(find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
-	OLDEST_SURICATA=$(find $SURICATA_LOGS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
+	if [ -n "$OLDEST_SURICATA" ]; then
-	if [[ -z "$OLDEST_SURICATA" ]] || [[ "$OLDEST_SURICATA" == ".." ]] || [[ "$OLDEST_SURICATA" == "." ]]; then
-		echo "$(date) - No old files available to clean up in $SURICATA_LOGS" >>$LOG
-	else
 		OLDEST_SURICATA_DATE=$(echo $OLDEST_SURICATA | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_SURICATA_FILE=$(echo $OLDEST_SURICATA | awk '{print $2}')
+		log "Removing logs for $OLDEST_SURICATA_DATE"
-		echo "$(date) - Removing logs for $OLDEST_SURICATA_DATE" >>$LOG
+		REMOVED=1
-		find $SURICATA_LOGS -type f -printf '%T+ %p\n' | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
+		find "$SURICATA_LOGS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_SURICATA_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 
 	## Clean up extracted pcaps
-	PCAPS='/nsm/pcapout'
+	OLDEST_PCAP=$(find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | sort -n | head -n 1)
-	OLDEST_PCAP=$(find $PCAPS -type f -printf '%T+ %p\n' | sort -n | head -n 1)
+	if [ -n "$OLDEST_PCAP" ]; then
-	if [ -z "$OLDEST_PCAP" -o "$OLDEST_PCAP" == ".." -o "$OLDEST_PCAP" == "." ]; then
-		echo "$(date) - No old files available to clean up in $PCAPS" >>$LOG
-	else
 		OLDEST_PCAP_DATE=$(echo $OLDEST_PCAP | awk '{print $1}' | cut -d+ -f1)
-		OLDEST_PCAP_FILE=$(echo $OLDEST_PCAP | awk '{print $2}')
+		log "Removing extracted files for $OLDEST_PCAP_DATE"
-		echo "$(date) - Removing extracted files for $OLDEST_PCAP_DATE" >>$LOG
+		REMOVED=1
-		find $PCAPS -type f -printf '%T+ %p\n' | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
+		find "$PCAPS" -type f -printf '%T+ %p\n' 2>/dev/null | grep $OLDEST_PCAP_DATE | awk '{print $2}' | while read FILE; do
-			echo "$(date) - Removing file: $FILE" >>$LOG
+			log "Removing file: $FILE"
 			rm -f "$FILE"
 		done
 	fi
 }
 
-# Check to see if we are already running
+# Only one instance at a time; the lock is the fd, so it releases on any exit
-NUM_RUNNING=$(pgrep -cf "/bin/bash /usr/sbin/so-sensor-clean")
+exec 9>"$LOCK" || exit 1
-[ "$NUM_RUNNING" -gt 1 ] && echo "$(date) - $NUM_RUNNING sensor clean script processes running...exiting." >>$LOG && exit 0
+if ! flock -n 9; then
-
+	log "another so-sensor-clean is already running (lock $LOCK held); exiting"
-if [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; then
+	exit 0
-	while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
-		clean
-		CUR_USAGE=$(df -P $SENSOR_DIR | tail -1 | awk '{print $5}' | tr -d %)
-	done
 fi
+
+CUR_USAGE=$(disk_usage)
+[ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ] || exit 0
+
+log "$SENSOR_DIR at ${CUR_USAGE}% (threshold ${CRIT_DISK_USAGE}%); starting cleanup"
+
+PASS=0
+while [ "$CUR_USAGE" -gt "$CRIT_DISK_USAGE" ]; do
+	PASS=$((PASS + 1))
+	if [ "$PASS" -gt "$MAX_PASSES" ]; then
+		log "stopping after $MAX_PASSES passes; $SENSOR_DIR still at ${CUR_USAGE}%"
+		break
+	fi
+
+	REMOVED=0
+	BEFORE=$(disk_avail)
+	clean
+	CUR_USAGE=$(disk_usage)
+
+	if [ "$REMOVED" -eq 0 ]; then
+		log "nothing left to remove in $ZEEK_LOGS, $STRELKA_FILES, $SURICATA_LOGS, $PCAPS; $SENSOR_DIR still at ${CUR_USAGE}% - space is consumed outside of NSM cleanup scope"
+		break
+	fi
+	if [ "$(disk_avail)" -le "$BEFORE" ]; then
+		log "pass $PASS freed no space; $SENSOR_DIR still at ${CUR_USAGE}% - stopping until next run"
+		break
+	fi
+done

salt/common/tools/sbin/so-start

@@ -5,27 +5,54 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
+# shellcheck disable=SC1091
-
-# Usage: so-start  all | kibana | playbook 
-
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
+usage() {
-	echo $banner
+    echo "Usage: $0 <component> [args]"
-	printf "Starting $1...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n"
+    echo ""
-	echo $banner
+    echo "Supported args:"
+    echo "  --force | -f          Force stop all Salt jobs before starting component."
+    echo ""
+    echo "Examples:"
+    echo "  $0 kibana             Start Kibana"
+    echo "  $0 kibana --force     Force stop all Salt jobs before starting Kibana"
+    exit 1
+}
 
-	if [ "$2" = "--force" ]; then
+if [[ $# -lt 1 ]]; then
-   		printf "\nForce-stopping all Salt jobs before proceeding\n\n"
+    usage
-   		salt-call saltutil.kill_all_jobs
-	fi
-
-	case $1 in
-   		"all") salt-call state.highstate queue=True;;
-   		"elastic-fleet") if docker ps | grep -q so-$1; then printf "\n$1 is already running!\n\n"; else docker rm so-$1 >/dev/null 2>&1 ; salt-call state.apply elasticfleet queue=True; fi ;; 
-   		*) if docker ps | grep -E -q '^so-$1$'; then printf "\n$1 is already running\n\n"; else docker rm so-$1 >/dev/null 2>&1 ; salt-call state.apply $1 queue=True; fi ;; 
-	esac
-else
-	echo -e "\nPlease provide an argument by running like so-start $component, or by using the component-specific script.\nEx. so-start logstash, or so-logstash-start\n"	
 fi
+
+#shellcheck disable=SC2154
+echo "$banner"
+printf "Starting %s...\n\nThis could take a while if another Salt job is running. \nRun this command with --force to stop all Salt jobs before proceeding.\n" "$1"
+echo "$banner"
+if [[ "$2" = "--force" ]] || [[ "$2" == "-f" ]]; then
+	printf "\nForce-stopping all Salt jobs before proceeding\n\n"
+	salt-call saltutil.kill_all_jobs
+fi
+
+case "$1" in
+    "all")
+        salt-call state.highstate queue=True
+        ;;
+   	"elastic-fleet"|"elasticfleet")
+        if docker_check_running "elastic-fleet"; then
+            printf "\nso-%s is already running!\n\n" "elastic-fleet"
+            /usr/sbin/so-status
+        else
+            docker rm "so-elastic-fleet" 2> /dev/null
+            salt-call state.apply elasticfleet queue=True
+        fi
+        ;;
+   	*)
+        if docker_check_running "$1"; then
+            printf "\nso-%s is already running\n\n" "$1"
+            /usr/sbin/so-status
+        else
+            docker rm "so-${1}" 2> /dev/null
+            salt-call state.apply "$1" queue=True
+        fi
+        ;;
+esac

salt/common/tools/sbin/so-status

@@ -74,13 +74,13 @@ def output(options, console, code, data):
     summary = { "status_code": code, "containers": data }
     print(json.dumps(summary))
   elif "-q" not in options:
-    if code == 2:
+    if code == 99:
-      console.print(" [bold yellow]:hourglass: [bold white]System appears to be starting. No highstate has completed since the system was restarted.")
-    elif code == 99:
       console.print(" [bold red]:exclamation: [bold white]Installation does not appear to be complete. A highstate has not fully completed.")
     elif code == 100:
       console.print(" [bold red]:exclamation: [bold white]Installation encountered errors.")
     else:
+      if code == 2:
+        console.print(" [bold yellow]:hourglass: [bold white]System appears to be starting. No highstate has completed since the system was restarted. Container status is shown below.")
       table = Table(title = "Security Onion Status", show_edge = False, safe_box = True, box = box.MINIMAL)
       table.add_column("Container", justify="right", style="white", no_wrap=True)
       table.add_column("Status", justify="left", style="green", no_wrap=True)
@@ -154,8 +154,14 @@ def check_status(options, console):
   code = check_installation_status(options, console)
   if code == 0:
     code = check_system_status(options, console)
-  if code == 0:
+  # Containers now start on boot without a highstate, so gather/display their
-    code, container_list = check_container_status(options, console)
+  # status even when the system is still "starting" (code 2). Keep the starting
+  # code as the exit/status_code so SOC keeps showing the "restarting" message
+  # on the Grid until a highstate completes.
+  if code == 0 or code == 2:
+    container_code, container_list = check_container_status(options, console)
+    if code == 0:
+      code = container_code
   output(options, console, code, container_list)
   return code
 
@@ -180,4 +186,3 @@ def main():
 
 if __name__ == "__main__":
   main()
-

salt/common/tools/sbin/so-stop

@@ -5,21 +5,33 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
+# shellcheck disable=SC1091
-
-# Usage: so-stop kibana | playbook | thehive
-
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
+usage() {
-	echo $banner
+    echo "Usage: $0 <component>"
-	printf "Stopping $1...\n"
+    echo ""
-	echo $banner
+    echo "Examples:"
+    echo "  $0 kibana             Stop Kibana"
+    exit 1
+}
 
-	case $1 in
+if [[ $# -lt 1 ]]; then
-    		*) docker stop so-$1 ; docker rm so-$1 ;;
+    usage
-	esac
-else
-	echo -e "\nPlease provide an argument by running like so-stop $component, or by using the component-specific script.\nEx. so-stop logstash, or so-logstash-stop\n"	
 fi
 
+
+#shellcheck disable=SC2154
+echo "$banner"
+printf "Stopping %s...\n" "$1"
+echo "$banner"
+case $1 in
+	"elasticfleet"|"elastic-fleet")
+        docker_check_running "elastic-fleet" "--stop"
+        docker rm "so-elastic-fleet" 2> /dev/null
+        ;;
+    *)
+        docker_check_running "$1" "--stop"
+        docker rm "so-${1}" 2> /dev/null
+    ;;
+esac

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

@@ -63,7 +63,8 @@ function status {
 function pcapinfo() {
   PCAP=$1
   ARGS=$2
-  docker run --rm -v "$PCAP:/input.pcap" --entrypoint capinfos {{ MANAGER }}:5000/{{ IMAGEREPO }}/so-pcaptools:{{ VERSION }} /input.pcap -ae $ARGS
+  docker run --rm -v "$PCAP:/input.pcap" --entrypoint capinfos {{ MANAGER }}:5000/{{ IMAGEREPO }}/so-pcaptools:{{ VERSION }} /input.pcap -ae $ARGS |\
+    sed 's/First packet/Earliest packet/g' | sed 's/Last packet/Latest packet/g'
 }
 
 function pcapfix() {

salt/common/tools/sbin_jinja/so-raid-status

@@ -9,7 +9,7 @@
 
 . /usr/sbin/so-common
 
-software_raid=("SOSMN" "SOSMN-DE02" "SOSSNNV" "SOSSNNV-DE02" "SOS10k-DE02" "SOS10KNV" "SOS10KNV-DE02" "SOS10KNV-DE02" "SOS2000-DE02" "SOS-GOFAST-LT-DE02" "SOS-GOFAST-MD-DE02" "SOS-GOFAST-HV-DE02")
+software_raid=("SOSMN" "SOSMN-DE02" "SOSSNNV" "SOSSNNV-DE02" "SOS10k-DE02" "SOS10KNV" "SOS10KNV-DE02" "SOS10KNV-DE02" "SOS2000-DE02" "SOS-GOFAST-LT-DE02" "SOS-GOFAST-MD-DE02" "SOS-GOFAST-HV-DE02" "HVGUEST")
 hardware_raid=("SOS1000" "SOS1000F" "SOSSN7200" "SOS5000" "SOS4000")
 
 {%- if salt['grains.get']('sosmodel', '') %}
@@ -87,6 +87,11 @@ check_boss_raid() {
 }
 
 check_software_raid() {
+  if [[ ! -f /proc/mdstat ]]; then
+    SWRAID=0
+    return
+  fi
+
   SWRC=$(grep "_" /proc/mdstat)
   if [[ -n $SWRC ]]; then
       # RAID is failed in some way
@@ -107,7 +112,9 @@ if [[ "$is_hwraid" == "true" ]]; then
 fi
 if [[ "$is_softwareraid" == "true" ]]; then
 	check_software_raid
-  check_boss_raid
+  if [ "$model" != "HVGUEST" ]; then
+    check_boss_raid
+  fi
 fi
 
 sum=$(($SWRAID + $BOSSRAID + $HWRAID))
@@ -118,4 +125,6 @@ else
   RAIDSTATUS=1
 fi
 
-echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log
+# telegraf reads this file; write aside and rename so it never sees a half-written file
+echo "nsmraid=$RAIDSTATUS" > /opt/so/log/raid/status.log.tmp
+mv -f /opt/so/log/raid/status.log.tmp /opt/so/log/raid/status.log

salt/common/tools/sbin_jinja/so-salt-minion-check

@@ -1,5 +1,3 @@
-{% import_yaml 'salt/minion.defaults.yaml' as SALT_MINION_DEFAULTS -%}
-
 #!/bin/bash
 #
 # Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
@@ -7,7 +5,7 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
+{% from 'salt/schedule.map.jinja' import SCHEDULEMERGED %}
 
 # this script checks the time the file /opt/so/log/salt/state-apply-test was last modified and restarts the salt-minion service if it is outside a threshold date/time
 # the file is modified via file.touch using a scheduled job healthcheck.salt-minion.state-apply-test that runs a state.apply. 
@@ -20,12 +18,14 @@
 
 QUIET=false
 UPTIME_REQ=1800 #in seconds, how long the box has to be up before considering restarting salt-minion due to /opt/so/log/salt/state-apply-test not being touched
+HIGHSTATE_UPTIME_REQ=900 #in seconds; if the box has been up this long and no highstate has completed since boot, force one
 CURRENT_TIME=$(date +%s)
 SYSTEM_START_TIME=$(date -d "$(</proc/uptime awk '{print $1}') seconds ago" +%s)
 LAST_HIGHSTATE_END=$([ -e "/opt/so/log/salt/lasthighstate" ] && date -r /opt/so/log/salt/lasthighstate +%s || echo 0)
 LAST_HEALTHCHECK_STATE_APPLY=$([ -e "/opt/so/log/salt/state-apply-test" ] && date -r /opt/so/log/salt/state-apply-test +%s || echo 0)
 # SETTING THRESHOLD TO ANYTHING UNDER 600 seconds may cause a lot of salt-minion restarts since the job to touch the file occurs every 5-8 minutes by default
-THRESHOLD={{SALT_MINION_DEFAULTS.salt.minion.check_threshold}} #within how many seconds the file /opt/so/log/salt/state-apply-test must have been touched/modified before the salt minion is restarted
+# THRESHOLD is derived from the salt schedule highstate interval + 1 hour, so the minion-check grace period tracks the schedule automatically.
+THRESHOLD=$(( ({{ SCHEDULEMERGED.highstate_interval_minutes }} + 60) * 60 )) #within how many seconds the file /opt/so/log/salt/state-apply-test must have been touched/modified before the salt minion is restarted
 THRESHOLD_DATE=$((LAST_HEALTHCHECK_STATE_APPLY+THRESHOLD))
 
 logCmd() {
@@ -77,24 +77,50 @@ done
 
 log "running so-salt-minion-check"
 
+RESTARTED=false
+
+# Check 1 (minion-restart-check): if the minion has stopped applying states (the
+# state-apply-test healthcheck file has gone stale), restart the salt-minion service.
 if [ $CURRENT_TIME -ge $((SYSTEM_START_TIME+$UPTIME_REQ))  ]; then
   if [ $THRESHOLD_DATE -le $CURRENT_TIME ]; then
-    log "salt-minion is unable to apply states" E
+    log "[minion-restart-check] salt-minion is unable to apply states; restarting salt-minion" E
-    log "/opt/so/log/salt/healthcheck-state-apply not touched by required date: `date -d @$THRESHOLD_DATE`, last touched: `date -d @$LAST_HEALTHCHECK_STATE_APPLY`" I
+    log "[minion-restart-check] state-apply-test not touched by required date `date -d @$THRESHOLD_DATE`, last touched `date -d @$LAST_HEALTHCHECK_STATE_APPLY`" I
-    log "last highstate completed at `date -d @$LAST_HIGHSTATE_END`" I
+    log "[minion-restart-check] last highstate completed at `date -d @$LAST_HIGHSTATE_END`" I
-    log "checking if any jobs are running" I
+    log "[minion-restart-check] checking if any jobs are running" I
     logCmd "salt-call --local saltutil.running" I
-    log "ensure salt.minion-state-apply-test is enabled" I
+    log "[minion-restart-check] ensure salt.minion-state-apply-test is enabled" I
     logCmd "salt-call state.enable salt.minion-state-apply-test" I
-    log "ensure highstate is enabled" I
+    log "[minion-restart-check] ensure highstate is enabled" I
     logCmd "salt-call state.enable highstate" I
-    log "killing all salt-minion processes" I
+    log "[minion-restart-check] killing all salt-minion processes" I
     logCmd "pkill -9 -ef /usr/bin/salt-minion" I
-    log "starting salt-minion service" I
+    log "[minion-restart-check] starting salt-minion service" I
     logCmd "systemctl start salt-minion" I
+    log "[minion-restart-check] waiting for salt-minion to become ready, then applying highstate in the background (queued)" I
+    nohup bash -c '/usr/sbin/so-salt-minion-wait; salt-call state.highstate queue=True' >> "/opt/so/log/salt/so-salt-minion-check" 2>&1 &
+    RESTARTED=true
   else
-    log "/opt/so/log/salt/healthcheck-state-apply last touched: `date -d @$LAST_HEALTHCHECK_STATE_APPLY` must be touched by `date -d @$THRESHOLD_DATE` to avoid salt-minion restart" I
+    log "[minion-restart-check] healthy: state-apply-test last touched `date -d @$LAST_HEALTHCHECK_STATE_APPLY`, must go stale past `date -d @$THRESHOLD_DATE` to trigger a salt-minion restart" I
   fi
 else
-  log "system uptime only $((CURRENT_TIME-SYSTEM_START_TIME)) seconds does not meet $UPTIME_REQ second requirement." I
+  log "[minion-restart-check] skipped: system uptime $((CURRENT_TIME-SYSTEM_START_TIME))s is below the ${UPTIME_REQ}s minimum required before a salt-minion restart" I
+fi
+
+# Check 2 (boot-highstate-check): if the host has been up long enough but no highstate
+# has completed since this boot, force one. This recovers a host whose boot highstate
+# (so-boot-highstate.service) failed or was skipped, even while the minion is otherwise
+# healthy (touching state-apply-test). We deliberately do NOT enable highstate here: if
+# soup has disabled it during an upgrade, Salt will refuse the highstate and we avoid
+# forcing one mid-upgrade.
+if $RESTARTED; then
+  log "[boot-highstate-check] skipped: minion-restart-check already queued a highstate this run" I
+elif [ $CURRENT_TIME -lt $((SYSTEM_START_TIME+HIGHSTATE_UPTIME_REQ)) ]; then
+  log "[boot-highstate-check] skipped: system uptime $((CURRENT_TIME-SYSTEM_START_TIME))s is below the ${HIGHSTATE_UPTIME_REQ}s minimum required before forcing a highstate" I
+elif [ $LAST_HIGHSTATE_END -ge $SYSTEM_START_TIME ]; then
+  log "[boot-highstate-check] healthy: a highstate completed at `date -d @$LAST_HIGHSTATE_END`, after this boot at `date -d @$SYSTEM_START_TIME`" I
+elif salt-call --local saltutil.running 2>/dev/null | grep -q 'state.highstate'; then
+  log "[boot-highstate-check] no highstate has completed since boot, but one is already running; skipping" I
+else
+  log "[boot-highstate-check] no highstate has completed since boot after $((CURRENT_TIME-SYSTEM_START_TIME))s uptime; applying highstate" E
+  nohup bash -c 'salt-call state.highstate -l info queue=True' >> "/opt/so/log/salt/so-salt-minion-check" 2>&1 &
 fi

salt/docker/defaults.yaml

@@ -1,6 +1,12 @@
 docker:
   range: '172.17.1.0/24'
   gateway: '172.17.1.1'
+  networks:
+    sobridge: {}
+    soauth:
+      range: '172.17.2.0/24'
+      gateway: '172.17.2.1'
+      manager_only: True
   ulimits:
     - name: nofile
       soft: 1048576
@@ -58,18 +64,18 @@ docker:
       ulimits: []
     'so-kratos':
       final_octet: 28
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4433:4433
-        - 0.0.0.0:4434:4434
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
       ulimits: []
     'so-hydra':
       final_octet: 30
+      networks: ['soauth']
       port_bindings:
         - 0.0.0.0:4444:4444
-        - 0.0.0.0:4445:4445
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
@@ -128,12 +134,55 @@ docker:
       ulimits: []
     'so-soc':
       final_octet: 34
+      networks: ['sobridge', 'soauth']
       port_bindings:
         - 0.0.0.0:9822:9822
       custom_bind_mounts: []
       extra_hosts: []
       extra_env: []
       ulimits: []
+    'so-strelka-backend':
+      final_octet: 36
+      custom_bind_mounts: []
+      extra_hosts: []
+      extra_env: []
+      ulimits: []
+    'so-strelka-filestream':
+      final_octet: 37
+      custom_bind_mounts: []
+      extra_hosts: []
+      extra_env: []
+      ulimits: []
+    'so-strelka-frontend':
+      final_octet: 38
+      port_bindings:
+        - 0.0.0.0:57314:57314
+      custom_bind_mounts: []
+      extra_hosts: []
+      extra_env: []
+      ulimits: []
+    'so-strelka-manager':
+      final_octet: 39
+      custom_bind_mounts: []
+      extra_hosts: []
+      extra_env: []
+      ulimits: []
+    'so-strelka-gatekeeper':
+      final_octet: 40
+      port_bindings:
+        - 0.0.0.0:6381:6379
+      custom_bind_mounts: []
+      extra_hosts: []
+      extra_env: []
+      ulimits: []
+    'so-strelka-coordinator':
+      final_octet: 41
+      port_bindings:
+        - 0.0.0.0:6380:6379
+      custom_bind_mounts: []
+      extra_hosts: []
+      extra_env: []
+      ulimits: []
     'so-elastalert':
       final_octet: 42
       custom_bind_mounts: []
@@ -195,3 +244,11 @@ docker:
       extra_hosts: []
       extra_env: []
       ulimits: []
+    'so-postgres':
+      final_octet: 47
+      port_bindings:
+        - 0.0.0.0:5432:5432
+      custom_bind_mounts: []
+      extra_hosts: []
+      extra_env: []
+      ulimits: []

salt/docker/docker.map.jinja

@@ -1,8 +1,26 @@
 {% import_yaml 'docker/defaults.yaml' as DOCKERDEFAULTS %}
 {% set DOCKERMERGED = salt['pillar.get']('docker', DOCKERDEFAULTS.docker, merge=True) %}
-{% set RANGESPLIT = DOCKERMERGED.range.split('.') %}
+
-{% set FIRSTTHREE = RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.' %}
+{% if DOCKERMERGED.networks.sobridge is not mapping %}
+{%   do DOCKERMERGED.networks.update({'sobridge': {}}) %}
+{% endif %}
+{% do DOCKERMERGED.networks['sobridge'].update({'range': DOCKERMERGED.range, 'gateway': DOCKERMERGED.gateway}) %}
+
+{% for netname, net in DOCKERMERGED.networks.items() %}
+{%   set RANGESPLIT = net.range.split('.') %}
+{%   do net.update({'prefix': RANGESPLIT[0] ~ '.' ~ RANGESPLIT[1] ~ '.' ~ RANGESPLIT[2] ~ '.'}) %}
+{% endfor %}
 
 {% for container, vals in DOCKERMERGED.containers.items() %}
-{%   do DOCKERMERGED.containers[container].update({'ip': FIRSTTHREE ~ DOCKERMERGED.containers[container].final_octet}) %}
+{%   set CONTAINER_NETS = vals.get('networks', ['sobridge']) %}
+{%   set IPS = {} %}
+{%   for netname in CONTAINER_NETS %}
+{%     do IPS.update({netname: DOCKERMERGED.networks[netname].prefix ~ vals.final_octet}) %}
+{%   endfor %}
+{%   do DOCKERMERGED.containers[container].update({
+         'networks': CONTAINER_NETS,
+         'ips': IPS,
+         'network': CONTAINER_NETS[0],
+         'ip': IPS[CONTAINER_NETS[0]]
+       }) %}
 {% endfor %}

salt/docker/init.sls

@@ -18,10 +18,10 @@ dockergroup:
 dockerheldpackages:
   pkg.installed:
     - pkgs:
-      - containerd.io: 2.2.1-1.el9
+      - containerd.io: 2.3.6-1.el9
-      - docker-ce: 3:29.2.1-1.el9
+      - docker-ce: 3:29.8.1-1.el9
-      - docker-ce-cli: 1:29.2.1-1.el9
+      - docker-ce-cli: 1:29.8.1-1.el9
-      - docker-ce-rootless-extras: 29.2.1-1.el9
+      - docker-ce-rootless-extras: 29.8.1-1.el9
     - hold: True
     - update_holds: True
 
@@ -71,15 +71,19 @@ dockerreserveports:
     - source: salt://common/files/99-reserved-ports.conf
     - name: /etc/sysctl.d/99-reserved-ports.conf
 
-sos_docker_net:
+{% for NETNAME, NETWORK in DOCKERMERGED.networks.items() %}
+{% if not NETWORK.get('manager_only') or GLOBALS.get('is_manager', False) %}
+sos_docker_net_{{ NETNAME }}:
   docker_network.present:
-    - name: sobridge
+    - name: {{ NETNAME }}
-    - subnet: {{ DOCKERMERGED.range }}
+    - subnet: {{ NETWORK.range }}
-    - gateway: {{ DOCKERMERGED.gateway }}
+    - gateway: {{ NETWORK.gateway }}
     - options:
-        com.docker.network.bridge.name: 'sobridge'
+        com.docker.network.bridge.name: '{{ NETNAME }}'
         com.docker.network.driver.mtu: '1500'
         com.docker.network.bridge.enable_ip_masquerade: 'true'
         com.docker.network.bridge.enable_icc: 'true'
         com.docker.network.bridge.host_binding_ipv4: '0.0.0.0'
-    - unless: ip l | grep sobridge
+    - unless: ip l | grep {{ NETNAME }}
+{% endif %}
+{% endfor %}

salt/docker/soc_docker.yaml

@@ -7,6 +7,40 @@ docker:
     description: Default docker IP range for containers.
     helpLink: docker
     advanced: True
+  networks:
+    sobridge:
+      description: |
+        The default docker network, carrying most containers. Its range and gateway are taken
+        from the docker.range and docker.gateway settings above rather than set here.
+      helpLink: docker
+      readonly: True
+      advanced: True
+      global: True
+    soauth:
+      range:
+        description: |
+          IP range for the soauth docker network, an isolated network for the authentication
+          services, so that the Kratos and Hydra admin APIs are only reachable from the
+          containers placed on it.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      gateway:
+        description: Gateway for the soauth docker network.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+      manager_only:
+        description: |
+          Limits the soauth network to grid members running the authentication containers,
+          instead of creating it on every node.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: bool
   ulimits:
     description: |
       Default ulimit settings applied to all containers via the Docker daemon. Each entry specifies a resource name (e.g. nofile, memlock, core, nproc) with soft and hard limits. Individual container ulimits override these defaults. Valid resource names include: cpu, fsize, data, stack, core, rss, nproc, nofile, memlock, as, locks, sigpending, msgqueue, nice, rtprio, rttime.
@@ -34,6 +68,16 @@ docker:
         readonly: True
         advanced: True
         global: True
+      networks:
+        description: |
+          Docker networks this container is attached to. The first entry is the container's
+          primary network and determines the address its published ports are forwarded to.
+          Defaults to sobridge when unset.
+        helpLink: docker
+        readonly: True
+        advanced: True
+        global: True
+        forcedType: "[]string"
       port_bindings:
         description: List of port bindings for the container.
         helpLink: docker
@@ -89,6 +133,12 @@ docker:
     so-redis: *dockerOptions
     so-sensoroni: *dockerOptions
     so-soc: *dockerOptions
+    so-strelka-backend: *dockerOptions
+    so-strelka-filestream: *dockerOptions
+    so-strelka-frontend: *dockerOptions
+    so-strelka-manager: *dockerOptions
+    so-strelka-gatekeeper: *dockerOptions
+    so-strelka-coordinator: *dockerOptions
     so-elastalert: *dockerOptions
     so-elastic-fleet-package-registry: *dockerOptions
     so-idh: *dockerOptions

salt/docker_clean/init.sls

@@ -9,7 +9,8 @@
 prune_images:
   cmd.run:
     - name: so-docker-prune
-    - order: last
+    - onlyif: command -v /usr/sbin/so-docker-prune >/dev/null 2>&1
+    - order: 9000
 
 {% else %}
 

salt/elastalert/config.sls

@@ -21,6 +21,7 @@ elastalert:
     - gid: 933
     - home: /opt/so/conf/elastalert
     - createhome: False
+    - shell: /sbin/nologin
 
 elastalogdir:
   file.directory:
@@ -33,8 +34,8 @@ elastalert_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elastalert/tools/sbin
-    - user: 933
+    - user: root
-    - group: 939
+    - group: root
     - file_mode: 755
 
 #elastalert_sbin_jinja:

salt/elastalert/defaults.yaml

@@ -10,7 +10,7 @@ elastalert:
     buffer_time:
       minutes: 10
     old_query_limit:
-      minutes: 5
+      minutes: 1440
     es_port: 9200
     es_conn_timeout: 55
     max_query_size: 5000

salt/elastalert/enabled.sls

@@ -19,6 +19,7 @@ wait_for_elasticsearch:
 so-elastalert:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastalert:{{ GLOBALS.so_version }}
+    - restart_policy: unless-stopped
     - hostname: elastalert
     - name: so-elastalert
     - user: so-elastalert

salt/elastalert/files/modules/so/conftest.py

@@ -0,0 +1,80 @@
+# 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 datetime import datetime
+import json
+import logging
+import sys
+import types
+
+# stand-ins when ElastAlert isn't installed (CI)
+try:
+    import elastalert.alerts  # noqa: F401
+except ImportError:
+
+    class Alerter:
+        def __init__(self, rule):
+            self.rule = rule
+
+    class DateTimeEncoder(json.JSONEncoder):
+        def default(self, obj):
+            return obj.isoformat() if hasattr(obj, 'isoformat') else json.JSONEncoder.default(self, obj)
+
+    class EAException(Exception):
+        pass
+
+    def lookup_es_key(doc, term):
+        for part in term.split('.'):
+            if not isinstance(doc, dict) or part not in doc:
+                return None
+            doc = doc[part]
+        return doc
+
+    def ts_to_dt(value):
+        return value if isinstance(value, datetime) else datetime.fromisoformat(value)
+
+    def elasticsearch_client(conf):
+        return None  # tests set the alerter's client
+
+    alerts = types.ModuleType('elastalert.alerts')
+    alerts.Alerter = Alerter
+    alerts.DateTimeEncoder = DateTimeEncoder
+    util = types.ModuleType('elastalert.util')
+    util.EAException = EAException
+    util.elastalert_logger = logging.getLogger('elastalert')
+    util.lookup_es_key = lookup_es_key
+    util.ts_to_dt = ts_to_dt
+    util.elasticsearch_client = elasticsearch_client
+    package = types.ModuleType('elastalert')
+    package.alerts = alerts
+    package.util = util
+    sys.modules.update({'elastalert': package, 'elastalert.alerts': alerts, 'elastalert.util': util})
+
+# stand-ins when elasticsearch-py isn't installed (CI)
+try:
+    import elasticsearch.exceptions  # noqa: F401
+except ImportError:
+
+    class ElasticsearchException(Exception):
+        pass
+
+    class TransportError(ElasticsearchException):
+        pass
+
+    class ConnectionError(TransportError):
+        pass
+
+    class ConflictError(TransportError):
+        pass
+
+    class RequestError(TransportError):
+        pass
+
+    exceptions = types.ModuleType('elasticsearch.exceptions')
+    for cls in (ElasticsearchException, TransportError, ConnectionError, ConflictError, RequestError):
+        setattr(exceptions, cls.__name__, cls)
+    es_package = types.ModuleType('elasticsearch')
+    es_package.exceptions = exceptions
+    sys.modules.update({'elasticsearch': es_package, 'elasticsearch.exceptions': exceptions})

salt/elastalert/files/modules/so/securityonion-es.py

@@ -5,59 +5,265 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
+from datetime import datetime, timezone
-from time import gmtime, strftime
+import hashlib
-import requests,json
+import ipaddress
-from elastalert.alerts import Alerter
+import json
+import re
+import uuid
 
 import urllib3
+from elasticsearch.exceptions import ConflictError, ElasticsearchException, RequestError
+from elastalert.alerts import Alerter, DateTimeEncoder
+from elastalert.util import EAException, elastalert_logger, elasticsearch_client, lookup_es_key, ts_to_dt
+
+# grid runs verify_certs: false; also quiets ElastAlert's own queries
 urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
 
+ALERT_INDEX = 'logs-detections.alerts-so'
+# ES error text kept in logs and alerts
+ERROR_TEXT_LIMIT = 500
+# a match missing backend columns (window_start, count, @timestamp); the alert is still written
+MATCH_ERRORS = (KeyError, TypeError, ValueError)
+
+
 class SecurityOnionESAlerter(Alerter):
     """
     Use matched data to create alerts in Elasticsearch.
     """
 
-    required_options = set(['detection_title', 'sigma_level'])
+    required_options = {'detection_title', 'sigma_level'}
-    optional_fields = ['sigma_category', 'sigma_product', 'sigma_service']
+    optional_fields = ['sigma_category', 'sigma_product', 'sigma_service', 'sigma_correlation']
+
+    # count column and default summary per type; stored alert data, so not localized
+    CORRELATION_COUNTS = {
+        'event_count': ('event_count', '%count% events'),
+        'value_count': ('value_count', '%count% distinct values'),
+        'temporal': ('event_type_count', '%count% correlated rules matched'),
+        'value_sum': ('value_sum', 'total %count%'),
+        'value_avg': ('value_avg', 'average %count%'),
+        'value_percentile': ('value_percentile', 'percentile %count%'),
+        'value_median': ('value_median', 'median %count%'),
+    }
+    PLACEHOLDER = re.compile(r'%([^%\s]+)%')
+    # group-by fields copied into ECS related.*
+    RELATED_USERS = {'user.name', 'winlog.event_data.TargetUserName', 'winlog.event_data.SubjectUserName'}
+    RELATED_HOSTS = {'host.name', 'host.hostname', 'winlog.computer_name'}
+
+    def __init__(self, rule):
+        super().__init__(rule)
+        # uses the grid's TLS, auth and timeout settings
+        self.es = elasticsearch_client(rule)
+
+    @property
+    def is_correlation(self):
+        return bool(self.rule.get('sigma_correlation'))
+
+    def query_keys(self):
+        """compound_query_key holds the list; query_key is flattened to a string."""
+        if self.rule.get('compound_query_key'):
+            return self.rule['compound_query_key']
+        if self.rule.get('query_key'):
+            return [self.rule['query_key']]
+        return []
+
+    def alert_id(self, match):
+        """Stable id: window end + group values for correlations, source _id otherwise; random without one."""
+        if self.is_correlation:
+            # ungrouped rows have a hashed _id that changes with the count
+            values = ''.join(f"|{lookup_es_key(match, k)}" for k in self.query_keys())
+            key = f"{self.rule['detection_public_id']}|{ts_to_dt(match['@timestamp']).isoformat()}{values}"
+        elif match.get('_id'):
+            key = f"{self.rule['detection_public_id']}|{match['_id']}"
+        else:
+            return uuid.uuid4().hex
+
+        return hashlib.sha256(key.encode('utf-8')).hexdigest()
+
+    def group(self, match):
+        """Group-by values, joined like ElastAlert's realert key."""
+        return ', '.join(str(lookup_es_key(match, k)) for k in self.query_keys())
+
+    def related_bucket(self, key):
+        if key == 'ip' or key.endswith('.ip'):
+            return 'ip'
+        if key in self.RELATED_USERS or key.endswith('.user.name'):
+            return 'user'
+        if key in self.RELATED_HOSTS:
+            return 'hosts'
+        return None
+
+    @staticmethod
+    def valid_ip(value):
+        try:
+            ipaddress.ip_address(value)
+            return True
+        except ValueError:
+            return False
+
+    def related(self, match):
+        """ECS related.* from group-by values; skips invalid IPs."""
+        related = {}
+        for key in self.query_keys():
+            bucket = self.related_bucket(key)
+            if not bucket:
+                continue
+            # original spellings of a lowercased group
+            value = lookup_es_key(match, f"{key}_spellings")
+            if value is None:
+                value = lookup_es_key(match, key)
+            for v in value if isinstance(value, list) else [value]:
+                if v is None or (bucket == 'ip' and not self.valid_ip(str(v))):
+                    continue
+                # dict: ordered and deduped
+                related.setdefault(bucket, {})[str(v)] = None
+        return {bucket: list(values) for bucket, values in related.items()}
+
+    def event_data(self, match):
+        """The match minus the compound query_key field, which ES would map by its last part."""
+        if not self.rule.get('compound_query_key'):
+            return match
+        return {k: v for k, v in match.items() if k != self.rule['query_key']}
+
+    @staticmethod
+    def format_value(value):
+        if isinstance(value, list):
+            shown = ', '.join(str(v) for v in value[:3])
+            return shown if len(value) <= 3 else f"{shown} and {len(value) - 3} more"
+        return str(value)
+
+    @staticmethod
+    def format_count(value):
+        if isinstance(value, float) and not value.is_integer():
+            return f"{value:,.2f}"
+        if isinstance(value, (int, float)):
+            return f"{int(value):,}"
+        return str(value)
+
+    @staticmethod
+    def format_duration(seconds):
+        for unit, size in (('hour', 3600), ('minute', 60)):
+            if seconds >= 2 * size:
+                return f"{seconds // size} {unit}s"
+        return f"{seconds} second{'' if seconds == 1 else 's'}"
+
+    def summary(self, match):
+        """One-line correlation summary."""
+        column, label = self.CORRELATION_COUNTS.get(self.rule['sigma_correlation'], (None, '%count%'))
+        start = ts_to_dt(match['window_start'])
+        end = ts_to_dt(match['@timestamp'])
+        values = {
+            'count': self.format_count(match.get(column)),
+            'start': start.strftime('%Y-%m-%d %H:%M:%S UTC'),
+            'end': end.strftime('%Y-%m-%d %H:%M:%S UTC'),
+            'duration': self.format_duration(int((end - start).total_seconds())),
+        }
+
+        template = self.rule.get('summary_template')
+        if not template:
+            groups = ', '.join(f"{k} %{k}%" for k in self.query_keys())
+            template = f"{label} for {groups} in %duration%" if groups else f"{label} in %duration%"
+
+        def fill(m):
+            if m[1] in values:
+                return values[m[1]]
+            value = lookup_es_key(match, m[1])
+            # unknown placeholders stay visible so typos show
+            return m[0] if value is None else self.format_value(value)
+
+        return self.PLACEHOLDER.sub(fill, template)
 
     def alert(self, matches):
         for match in matches:
-            timestamp = strftime("%Y-%m-%d"'T'"%H:%M:%S"'.000Z', gmtime())
+            try:
-            headers = {"Content-Type": "application/json"}
+                alert_id = self.alert_id(match)
+            except MATCH_ERRORS as e:
+                elastalert_logger.warning("Writing alert for rule %s without a stable id, so a retry may duplicate it: %r",
+                                          self.rule['detection_public_id'], e)
+                alert_id = uuid.uuid4().hex
+            try:
+                self.write(alert_id, self.payload(match))
+            except ElasticsearchException as e:
+                # EAException makes ElastAlert retry
+                raise EAException(f"Unable to write the alert to Elasticsearch: {str(e)[:ERROR_TEXT_LIMIT]}") from e
 
-            creds = None
+    def payload(self, match):
-            if 'es_username' in self.rule and 'es_password' in self.rule:
+        rule_info = {
-                creds = (self.rule['es_username'], self.rule['es_password'])
+            "name": self.rule['detection_title'],
+            "uuid": self.rule['detection_public_id']
+        }
 
-            # Start building the rule dict
+        # Add optional fields if they are present in the rule
-            rule_info = {
+        for field in self.optional_fields:
-                "name": self.rule['detection_title'],
+            rule_key = field.split('_')[-1]  # Assumes field format "sigma_<key>"
-                "uuid": self.rule['detection_public_id']
+            if field in self.rule:
-            }
+                rule_info[rule_key] = self.rule[field]
 
-            # Add optional fields if they are present in the rule
+        event_info = {
-            for field in self.optional_fields:
+            "kind": "alert",
-                rule_key = field.split('_')[-1]  # Assumes field format "sigma_<key>"
+            "severity": self.rule['event.severity'],
-                if field in self.rule:
+            "module": self.rule['event.module'],
-                    rule_info[rule_key] = self.rule[field]
+            "dataset": self.rule['event.dataset'],
+            "severity_label": self.rule['sigma_level']
+        }
 
-            # Construct the payload with the conditional rule_info
+        payload = {
-            payload = {
+            "tags": ["alert"],
-                "tags": "alert",
+            "rule": rule_info,
-                "rule": rule_info,
+            "event": event_info,
-                "event": {
+            "sigma_level": self.rule['sigma_level'],
-                    "severity": self.rule['event.severity'],
+            "event_data": self.event_data(match),
-                    "module": self.rule['event.module'],
+            "@timestamp": datetime.now(timezone.utc).strftime('%Y-%m-%dT%H:%M:%S.000Z')
-                    "dataset": self.rule['event.dataset'],
+        }
-                    "severity_label": self.rule['sigma_level']
+
-                },
+        if self.is_correlation:
-                "sigma_level": self.rule['sigma_level'],
+            keys = self.query_keys()
-                "event_data": match,
+            try:
-                "@timestamp": timestamp
+                # built before any is added, so a failure adds none
-            }
+                reason = self.summary(match)
-            url = f"https://{self.rule['es_host']}:{self.rule['es_port']}/logs-detections.alerts-so/_doc/"
+                labels = {"correlation_group_by": ', '.join(keys), "correlation_group": self.group(match)} if keys else None
-            requests.post(url, data=json.dumps(payload), headers=headers, verify=False, auth=creds)
+                related = self.related(match)
+            except MATCH_ERRORS as e:
+                elastalert_logger.warning("Writing alert for rule %s without its correlation summary: %r",
+                                          self.rule['detection_public_id'], e)
+            else:
+                payload["event"]["reason"] = reason
+                if labels:
+                    payload["labels"] = labels
+                if related:
+                    payload["related"] = related
+
+        return payload
+
+    def write(self, alert_id, payload):
+        try:
+            self.create(alert_id, payload)
+        except RequestError as e:
+            # mapping rejections come from event_data; retry it as text
+            rejection = str(e)[:ERROR_TEXT_LIMIT]
+            try:
+                self.create(alert_id, self.without_event_data(payload, rejection))
+            except RequestError as again:
+                elastalert_logger.error("Dropping alert %s for rule %s, rejected by Elasticsearch even without its event data: %s; first rejection: %s",
+                                        alert_id, self.rule['detection_public_id'], str(again)[:ERROR_TEXT_LIMIT], rejection)
+                return
+            elastalert_logger.warning("Stored alert %s for rule %s with its event data as text, rejected by Elasticsearch: %s",
+                                      alert_id, self.rule['detection_public_id'], rejection)
+
+    def create(self, alert_id, payload):
+        try:
+            self.es.create(index=ALERT_INDEX, id=alert_id, body=payload)
+        except ConflictError:
+            pass  # a repeat id is already stored
+
+    @staticmethod
+    def without_event_data(payload, rejection):
+        """Moves event_data to event.original; the tag keeps Fleet's final pipeline from dropping it."""
+        fallback = {k: v for k, v in payload.items() if k != 'event_data'}
+        fallback['event'] = dict(payload['event'], original=json.dumps(payload['event_data'], cls=DateTimeEncoder))
+        fallback['error'] = {'message': f"event_data rejected by Elasticsearch: {rejection}"}
+        fallback['tags'] = payload['tags'] + ['preserve_original_event']
+        return fallback
 
     def get_info(self):
         return {'type': 'SecurityOnionESAlerter'}

salt/elastalert/files/modules/so/securityonion-es_test.py

@@ -0,0 +1,260 @@
+# 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.
+
+import copy
+from datetime import datetime, timezone
+import importlib.util
+import json
+import os
+import unittest
+from unittest.mock import MagicMock
+
+from elasticsearch.exceptions import ConflictError, ConnectionError, RequestError
+
+spec = importlib.util.spec_from_file_location('securityonion_es', os.path.join(os.path.dirname(__file__), 'securityonion-es.py'))
+es = importlib.util.module_from_spec(spec)
+spec.loader.exec_module(es)
+
+BASE_RULE = {
+    'detection_title': 'Many Failed Network Logons To One Host From One Source',
+    'detection_public_id': '35a42db6-6629-45af-b8aa-e1fa33c28ef5',
+    'sigma_level': 'medium',
+    'sigma_correlation': 'event_count',
+    'event.severity': 3,
+    'event.module': 'sigma',
+    'event.dataset': 'sigma.alert',
+    'summary_template': '%count% failed network logons to %host.name% from %source.ip% in %duration%',
+}
+
+PLAIN_RULE = {k: v for k, v in BASE_RULE.items() if k not in ('sigma_correlation', 'summary_template')}
+
+
+def correlation_match():
+    return {
+        'event_count': 3561,
+        'window_start': '2026-09-30T18:05:10+00:00',
+        '@timestamp': '2026-09-30T18:07:53+00:00',
+        'host': {'name': 'host-01'},
+        'source': {'ip': '192.0.2.10'},
+        '_id': '6d1c',
+        'num_hits': 1,
+        'num_matches': 1,
+    }
+
+
+class TestSecurityOnionESAlerter(unittest.TestCase):
+
+    def creates(self, rule, match, effects=None):
+        """Run alert(); return (body, id) of each create."""
+        alerter = es.SecurityOnionESAlerter(rule)
+        alerter.es = MagicMock()
+        alerter.es.create.side_effect = effects
+        alerter.alert([match])
+        calls = alerter.es.create.call_args_list
+        self.assertTrue(all(c.kwargs['index'] == 'logs-detections.alerts-so' for c in calls))
+        return [(json.loads(json.dumps(c.kwargs['body'], cls=es.DateTimeEncoder)), c.kwargs['id']) for c in calls]
+
+    def send(self, rule, match):
+        """Run alert(); return the payload it wrote and its id."""
+        (payload, alert_id), = self.creates(rule, match)
+        return payload, alert_id
+
+    def test_compound_query_key_left_out_of_event_data(self):
+        rule = dict(BASE_RULE, compound_query_key=['host.name', 'source.ip'], query_key='host.name,source.ip')
+        match = correlation_match()
+        match['host.name,source.ip'] = 'host-01, 192.0.2.10'
+        original = copy.deepcopy(match)
+
+        payload, _ = self.send(rule, match)
+
+        self.assertNotIn('host.name,source.ip', payload['event_data'])
+        self.assertEqual(payload['event_data']['host'], {'name': 'host-01'})
+        self.assertEqual(payload['event_data']['source'], {'ip': '192.0.2.10'})
+        self.assertEqual(payload['rule'], {'name': BASE_RULE['detection_title'], 'uuid': BASE_RULE['detection_public_id'], 'correlation': 'event_count'})
+        self.assertEqual(payload['labels'], {'correlation_group_by': 'host.name, source.ip', 'correlation_group': 'host-01, 192.0.2.10'})
+        self.assertEqual(payload['related'], {'hosts': ['host-01'], 'ip': ['192.0.2.10']})
+        self.assertEqual(payload['event']['kind'], 'alert')
+        self.assertEqual(payload['event']['reason'], '3,561 failed network logons to host-01 from 192.0.2.10 in 2 minutes')
+        # ElastAlert reuses the match
+        self.assertEqual(match, original)
+
+    def test_single_query_key(self):
+        rule = dict(BASE_RULE, query_key='user.name', summary_template='%count% failed SOC logins for %user.name%')
+        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
+                 'user': {'name': 'user@example.invalid'}}
+
+        payload, _ = self.send(rule, match)
+
+        self.assertEqual(payload['labels'], {'correlation_group_by': 'user.name', 'correlation_group': 'user@example.invalid'})
+        self.assertEqual(payload['related'], {'user': ['user@example.invalid']})
+        self.assertEqual(payload['event']['reason'], '3 failed SOC logins for user@example.invalid')
+        self.assertEqual(payload['event_data'], match)
+
+    def test_related_buckets(self):
+        rule = dict(BASE_RULE, compound_query_key=['winlog.event_data.TargetUserName', 'source.ip', 'dns.highest_registered_domain'],
+                    query_key='winlog.event_data.TargetUserName,source.ip,dns.highest_registered_domain')
+        match = correlation_match()
+        match.update({'winlog': {'event_data': {'TargetUserName': ['admin1', 'svc', 'admin1']}},
+                      'source': {'ip': 'not-an-ip'}, 'dns': {'highest_registered_domain': 'example.com'}})
+
+        payload, _ = self.send(rule, match)
+
+        # deduped; invalid IP skipped; domain stays in the group only
+        self.assertEqual(payload['related'], {'user': ['admin1', 'svc']})
+        self.assertEqual(payload['labels']['correlation_group'], "['admin1', 'svc', 'admin1'], not-an-ip, example.com")
+
+        payload, _ = self.send(dict(BASE_RULE, query_key='dns.highest_registered_domain'), match)
+
+        self.assertNotIn('related', payload)
+
+    def test_related_uses_original_spellings(self):
+        rule = dict(BASE_RULE, query_key='user.name', summary_template=None)
+        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
+                 'user': {'name': 'admin', 'name_spellings': ['Admin', 'admin', 'ADMIN']}}
+
+        payload, _ = self.send(rule, match)
+
+        # the group shows the lowercased value; related.user finds every spelling
+        self.assertEqual(payload['labels']['correlation_group'], 'admin')
+        self.assertEqual(payload['related'], {'user': ['Admin', 'admin', 'ADMIN']})
+        self.assertEqual(payload['event']['reason'], '3 events for user.name admin in 8 seconds')
+
+    def test_plain_rule_has_no_correlation_fields(self):
+        # a query_key alone (e.g. from an override) isn't a correlation
+        rule = dict(PLAIN_RULE, query_key='user.name')
+        # ElastAlert parses @timestamp for EQL hits
+        match = {'@timestamp': datetime(2026, 9, 30, 16, 50, tzinfo=timezone.utc), '_id': 'abc',
+                 'process': {'name': 'whoami.exe'}, 'user': {'name': 'user'}}
+
+        payload, alert_id = self.send(rule, match)
+
+        alerter = es.SecurityOnionESAlerter(rule)
+        self.assertEqual(payload['rule'], {'name': PLAIN_RULE['detection_title'], 'uuid': PLAIN_RULE['detection_public_id']})
+        self.assertNotIn('labels', payload)
+        self.assertNotIn('related', payload)
+        self.assertNotIn('reason', payload['event'])
+        self.assertEqual(payload['event']['kind'], 'alert')
+        self.assertEqual(payload['event_data'], dict(match, **{'@timestamp': '2026-09-30T16:50:00+00:00'}))
+        self.assertEqual(alert_id, alerter.alert_id(match))
+        self.assertNotEqual(alerter.alert_id(match), alerter.alert_id(dict(match, _id='abd')))
+        self.assertNotEqual(alerter.alert_id(match), es.SecurityOnionESAlerter(dict(rule, detection_public_id='other')).alert_id(match))
+        # without an _id, never deduplicated
+        self.assertNotEqual(alerter.alert_id({'_id': None}), alerter.alert_id({'_id': None}))
+
+    def test_ungrouped_correlation_id_ignores_row_hash(self):
+        rule = dict(BASE_RULE, summary_template=None)
+        first = {k: v for k, v in correlation_match().items() if k not in ('host', 'source')}
+        # ES|QL hashes the row into _id, so a later count changes it
+        later = dict(first, event_count=3600, _id='9f2a')
+
+        payload, alert_id = self.send(rule, first)
+
+        alerter = es.SecurityOnionESAlerter(rule)
+        self.assertEqual(alerter.alert_id(first), alerter.alert_id(later))
+        self.assertNotEqual(alerter.alert_id(first), alerter.alert_id(dict(first, **{'@timestamp': '2026-09-30T18:09:00+00:00'})))
+        self.assertEqual(alert_id, alerter.alert_id(first))
+        self.assertEqual(payload['event']['reason'], '3,561 events in 2 minutes')
+        self.assertNotIn('labels', payload)
+
+    def test_temporal_count_column(self):
+        rule = dict(BASE_RULE, sigma_correlation='temporal', summary_template=None)
+        match = {'event_type_count': 2, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00'}
+
+        payload, _ = self.send(rule, match)
+
+        self.assertEqual(payload['event']['reason'], '2 correlated rules matched in 8 seconds')
+
+    def test_grouped_correlation_id_unchanged(self):
+        """Ids of alerts already written must not change."""
+        rule = dict(BASE_RULE, compound_query_key=['host.name', 'source.ip'], query_key='host.name,source.ip')
+        key = f"{BASE_RULE['detection_public_id']}|2026-09-30T18:07:53+00:00|host-01|192.0.2.10"
+
+        self.assertEqual(es.SecurityOnionESAlerter(rule).alert_id(correlation_match()), es.hashlib.sha256(key.encode()).hexdigest())
+
+    def test_rejected_event_data_is_kept_as_text(self):
+        rule = dict(BASE_RULE, query_key='user.name', summary_template='%count% failed SOC logins for %user.name%')
+        match = {'event_count': 3, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
+                 'user': {'name': 'user@example.invalid'}}
+        rejected = RequestError(400, 'document_parsing_exception', {})
+
+        (first, _), (second, _) = self.creates(rule, match, [rejected, None])
+
+        self.assertIn('event_data', first)
+        self.assertNotIn('event_data', second)
+        self.assertEqual(json.loads(second['event']['original']), match)
+        self.assertEqual(second['tags'], ['alert', 'preserve_original_event'])
+        self.assertEqual(first['tags'], ['alert'])
+        self.assertTrue(second['error']['message'].startswith('event_data rejected by Elasticsearch: '))
+        self.assertIn('document_parsing_exception', second['error']['message'])
+        # everything else carries over
+        self.assertEqual({k: v for k, v in second['event'].items() if k != 'original'}, first['event'])
+        changed = ('event_data', 'event', 'error', 'tags')
+        self.assertEqual({k: v for k, v in second.items() if k not in changed}, {k: v for k, v in first.items() if k not in changed})
+
+    def test_rejected_dates_are_kept_as_text(self):
+        match = {'@timestamp': datetime(2026, 9, 30, 16, 50, tzinfo=timezone.utc), '_id': 'abc'}
+
+        _, (second, _) = self.creates(PLAIN_RULE, match, [RequestError(400, 'document_parsing_exception', {}), None])
+
+        self.assertEqual(json.loads(second['event']['original']), {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'})
+
+    def test_rejected_twice_is_dropped_without_retry(self):
+        rejected = RequestError(400, 'document_parsing_exception', {})
+        match = {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'}
+
+        with self.assertLogs('elastalert', 'ERROR') as logs:
+            self.assertEqual(len(self.creates(PLAIN_RULE, match, [rejected, rejected])), 2)
+
+        self.assertIn('Dropping alert', logs.output[0])
+
+    def test_write_failure_is_retried(self):
+        match = {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'}
+
+        with self.assertRaisesRegex(es.EAException, 'Unable to write the alert to Elasticsearch'):
+            self.creates(PLAIN_RULE, match, [ConnectionError('N/A', 'refused', None)])
+
+    def test_repeat_id_is_ignored(self):
+        match = {'@timestamp': '2026-09-30T16:50:00+00:00', '_id': 'abc'}
+
+        self.assertEqual(len(self.creates(PLAIN_RULE, match, [ConflictError(409, 'version_conflict_engine_exception', {})])), 1)
+
+    def test_correlation_fields_are_optional(self):
+        rule = dict(BASE_RULE, query_key='source.ip')
+        # no window_start: the summary cannot be built
+        match = {k: v for k, v in correlation_match().items() if k != 'window_start'}
+
+        with self.assertLogs('elastalert', 'WARNING') as logs:
+            payload, _ = self.send(rule, match)
+
+        self.assertIn('without its correlation summary', logs.output[0])
+        self.assertEqual(payload['event']['kind'], 'alert')
+        self.assertNotIn('reason', payload['event'])
+        self.assertNotIn('labels', payload)
+        self.assertNotIn('related', payload)
+
+    def test_unstable_id_still_writes(self):
+        # no @timestamp: the window end is unknown
+        match = {k: v for k, v in correlation_match().items() if k not in ('@timestamp', 'window_start')}
+
+        with self.assertLogs('elastalert', 'WARNING') as logs:
+            payload, alert_id = self.send(BASE_RULE, match)
+
+        self.assertIn('without a stable id', logs.output[0])
+        self.assertEqual(len(alert_id), 32)
+        self.assertEqual(payload['event_data'], match)
+
+    def test_summary_formats_values(self):
+        rule = dict(BASE_RULE, sigma_correlation='value_avg', query_key='source.ip',
+                    summary_template='%count% for %source.ip% to %destination.port% %no.such.field%')
+        match = {'value_avg': 2.5, 'window_start': '2026-09-30T16:49:52+00:00', '@timestamp': '2026-09-30T16:50:00+00:00',
+                 'source': {'ip': '192.0.2.10'}, 'destination': {'port': [22, 80, 443, 8080, 8443]}}
+
+        payload, _ = self.send(rule, match)
+
+        self.assertEqual(payload['event']['reason'], '2.50 for 192.0.2.10 to 22, 80, 443 and 2 more %no.such.field%')
+        self.assertEqual(es.SecurityOnionESAlerter.format_count('n/a'), 'n/a')
+
+    def test_get_info(self):
+        self.assertEqual(es.SecurityOnionESAlerter(PLAIN_RULE).get_info(), {'type': 'SecurityOnionESAlerter'})

salt/elastalert/soc_elastalert.yaml

@@ -120,7 +120,7 @@ elastalert:
         helpLink: elastalert
     old_query_limit:
       minutes:
-        description: Amount of time in minutes between queries to start at the most recently run query.
+        description: How long ElastAlert can be down, in minutes, and still resume each rule where it stopped. After a longer outage, rules restart from now and skip the gap.
         global: True
         helpLink: elastalert
     es_conn_timeout:

salt/elastic-fleet-package-registry/config.sls

@@ -19,6 +19,7 @@ elastic-agent-pr:
     - gid: 948
     - home: /opt/so/conf/elastic-fleet-pr
     - createhome: False
+    - shell: /sbin/nologin
 
 {% else %}
 

salt/elastic-fleet-package-registry/enabled.sls

@@ -15,6 +15,7 @@ include:
 so-elastic-fleet-package-registry:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-fleet-package-registry:{{ GLOBALS.so_version }}
+    - restart_policy: unless-stopped
     - name: so-elastic-fleet-package-registry
     - hostname: Fleet-package-reg-{{ GLOBALS.hostname }}
     - detach: True
@@ -51,6 +52,16 @@ so-elastic-fleet-package-registry:
       - {{ ULIMIT.name }}={{ ULIMIT.soft }}:{{ ULIMIT.hard }}
     {%   endfor %}
     {% endif %}
+
+wait_for_so-elastic-fleet-package-registry:
+  http.wait_for_successful_query:
+    - name: "http://localhost:8080/health"
+    - status: 200
+    - wait_for: 300
+    - request_interval: 15
+    - require:
+      - docker_container: so-elastic-fleet-package-registry
+
 delete_so-elastic-fleet-package-registry_so-status.disabled:
   file.uncomment:
     - name: /opt/so/conf/so-status/so-status.conf

salt/elasticagent/config.sls

@@ -20,6 +20,7 @@ elastic-agent:
     - gid: 949
     - home: /opt/so/conf/elastic-agent
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticagentconfdir:
   file.directory:
@@ -39,8 +40,8 @@ elasticagent_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticagent/tools/sbin_jinja
-    - user: 949
+    - user: root
-    - group: 939
+    - group: root
     - file_mode: 755
     - template: jinja
 

salt/elasticagent/enabled.sls

@@ -16,6 +16,7 @@ include:
 so-elastic-agent:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent:{{ GLOBALS.so_version }}
+    - restart_policy: unless-stopped
     - name: so-elastic-agent
     - hostname: {{ GLOBALS.hostname }}
     - detach: True

salt/elasticfleet/config.sls

@@ -26,13 +26,14 @@ elastic-fleet:
     - gid: 947
     - home: /opt/so/conf/elastic-fleet
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticfleet_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin
-    - user: 947
+    - user: root
-    - group: 939
+    - group: root
     - file_mode: 755
     - show_changes: False
 
@@ -40,8 +41,8 @@ elasticfleet_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticfleet/tools/sbin_jinja
-    - user: 947
+    - user: root
-    - group: 939 
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -81,8 +82,8 @@ eapackageupgrade:
   file.managed:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
     - source: salt://elasticfleet/tools/sbin_jinja/so-elastic-fleet-package-upgrade
-    - user: 947
+    - user: root
-    - group: 939
+    - group: root
     - mode: 755
     - template: jinja
 
@@ -173,7 +174,7 @@ eaoptionalintegrationsdir:
 
 {% for minion in node_data %}
 {% set role = node_data[minion]["role"] %}
-{% if role in [ "eval","fleet","heavynode","import","manager", "managerhype", "managersearch","standalone" ] %}
+{% if role in [ "eval","fleet","import","manager", "managerhype", "managersearch","standalone" ] %}
 {% set optional_integrations = ELASTICFLEETMERGED.optional_integrations %}
 {% set integration_keys = optional_integrations.keys() %}
 fleet_server_integrations_{{ minion }}:

salt/elasticfleet/content-defaults.map.jinja

@@ -0,0 +1,122 @@
+{# 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. #}
+
+
+{% import_json '/opt/so/state/esfleet_content_package_components.json' as ADDON_CONTENT_PACKAGE_COMPONENTS %}
+{% import_json '/opt/so/state/esfleet_component_templates.json' as INSTALLED_COMPONENT_TEMPLATES %}
+{% import_yaml 'elasticfleet/defaults.yaml' as ELASTICFLEETDEFAULTS %}
+
+{% set CORE_ESFLEET_PACKAGES = ELASTICFLEETDEFAULTS.get('elasticfleet', {}).get('packages', {}) %}
+{% set ADDON_CONTENT_INTEGRATION_DEFAULTS = {} %}
+
+{% for pkg in ADDON_CONTENT_PACKAGE_COMPONENTS %}
+{%   if pkg.name in CORE_ESFLEET_PACKAGES %}
+{#     skip core content packages #}
+{%   elif pkg.name not in CORE_ESFLEET_PACKAGES %}
+{#     generate defaults for each content package #}
+{%     if pkg.dataStreams is defined and pkg.dataStreams is not none and pkg.dataStreams | length > 0%}
+{%       for pattern in pkg.dataStreams %}
+{#         in ES 9.3.2 'input' type integrations no longer create default component templates and instead they wait for user input during 'integration' setup (fleet ui config)
+             title: generic is an artifact of that and is not in use #}
+{%         if pattern.title == "generic" %}
+{%           continue %}
+{%         endif %}
+{%         if "metrics-" in pattern.name %}
+{%           set integration_type = "metrics-" %}
+{%         elif "logs-" in pattern.name %}
+{%           set integration_type = "logs-" %}
+{%         else %}
+{%           set integration_type = "" %}
+{%         endif %}
+{#         on content integrations the component name is user defined at the time it is added to an agent policy #}
+{%         set component_name = pattern.title %}
+{%         set index_pattern = pattern.name %}
+{#           component_name_x maintains the functionality of merging local pillar changes with generated 'defaults' via SOC UI #}
+{%           set component_name_x = component_name.replace(".","_x_") %}
+{#           pillar overrides/merge expects the key names to follow the naming in elasticsearch/defaults.yaml eg. so-logs-1password_x_item_usages . The _x_ is replaced later on in elasticsearch/template.map.jinja #}
+{%           set integration_key = "so-" ~ integration_type ~ pkg.name + '_x_' ~ component_name_x %}
+{#           Default integration settings #}
+{%           set integration_defaults = {
+               "index_sorting": false,
+               "index_template": {
+                 "composed_of": [integration_type ~ component_name ~ "@package", integration_type ~ component_name ~ "@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": [integration_type ~ component_name ~ "@custom"],
+                 "index_patterns": [index_pattern],
+                 "priority": 501,
+                 "template": {
+                   "settings": {
+                     "index": {
+                       "lifecycle": {"name": "so-" ~ integration_type ~ component_name ~ "-logs"},
+                         "number_of_replicas": 0
+                     }
+                   }
+                 }
+               },
+               "policy": {
+                 "phases": {
+                   "cold": {
+                     "actions": {
+                        "allocate":{
+                          "number_of_replicas": ""
+                        },
+                       "set_priority": {"priority": 0}
+                     },
+                     "min_age": "60d"
+                   },
+                   "delete": {
+                     "actions": {
+                       "delete": {}
+                     },
+                     "min_age": "365d"
+                   },
+                   "hot": {
+                     "actions": {
+                       "rollover": {
+                         "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"
+                   }
+                 }
+               }
+             } %}
+
+
+{%         do ADDON_CONTENT_INTEGRATION_DEFAULTS.update({integration_key: integration_defaults}) %}
+{%       endfor %}
+{%     else %}
+{%     endif %}
+{%   endif %}
+{% endfor %}

salt/elasticfleet/enabled.sls

@@ -17,65 +17,19 @@ include:
   - logstash.ssl
   - elasticfleet.config
   - elasticfleet.sostatus
+{%- if GLOBALS.role != "so-fleet" %}
+  - elasticfleet.manager
+{%- endif %}
 
-{% if grains.role not in ['so-fleet'] %}
+{% if GLOBALS.role != "so-fleet" %}
 # Wait for Elasticsearch to be ready - no reason to try running Elastic Fleet server if ES is not ready
 wait_for_elasticsearch_elasticfleet:
   cmd.run:
     - name: so-elasticsearch-wait
 {% endif %}
 
-# If enabled, automatically update Fleet Logstash Outputs
+{% if GLOBALS.role == "so-fleet" %}
-{% if ELASTICFLEETMERGED.config.server.enable_auto_configuration and grains.role not in ['so-import', 'so-eval', 'so-fleet'] %}
-so-elastic-fleet-auto-configure-logstash-outputs:
-  cmd.run:
-    - name: /usr/sbin/so-elastic-fleet-outputs-update
-    - 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
-{% if ELASTICFLEETMERGED.config.server.enable_auto_configuration and grains.role not in ['so-fleet'] %}
-so-elastic-fleet-auto-configure-server-urls:
-  cmd.run:
-    - name: /usr/sbin/so-elastic-fleet-urls-update
-    - retry:
-        attempts: 4
-        interval: 30
-{% endif %}
-
-# Automatically update Fleet Server Elasticsearch URLs & Agent Artifact URLs
-{% if grains.role not in ['so-fleet'] %}
-so-elastic-fleet-auto-configure-elasticsearch-urls:
-  cmd.run:
-    - name: /usr/sbin/so-elastic-fleet-es-url-update
-    - retry:
-        attempts: 4
-        interval: 30
-
-so-elastic-fleet-auto-configure-artifact-urls:
-  cmd.run:
-    - name: /usr/sbin/so-elastic-fleet-artifacts-url-update
-    - retry:
-        attempts: 4
-        interval: 30
-
-{% endif %}
-
 # Sync Elastic Agent artifacts to Fleet Node
-{% if grains.role in ['so-fleet'] %}
 elasticagent_syncartifacts:
   file.recurse:
     - name: /nsm/elastic-fleet/artifacts/beats
@@ -88,6 +42,7 @@ elasticagent_syncartifacts:
 so-elastic-fleet:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent:{{ GLOBALS.so_version }}
+    - restart_policy: unless-stopped
     - name: so-elastic-fleet
     - hostname: FleetServer-{{ GLOBALS.hostname }}
     - detach: True
@@ -147,59 +102,19 @@ so-elastic-fleet:
       - file: trusttheca
       - x509: etc_elasticfleet_key
       - x509: etc_elasticfleet_crt
+
+wait_for_so-elastic-fleet:
+  http.wait_for_successful_query:
+    - name: "https://localhost:8220/api/status"
+    - ssl: True
+    - verify_ssl: False
+    - status: 200
+    - wait_for: 300
+    - request_interval: 15
+    - require:
+      - docker_container: so-elastic-fleet
 {%   endif %}
 
-{%  if GLOBALS.role != "so-fleet" %}
-so-elastic-fleet-package-statefile:
-  file.managed:
-    - name: /opt/so/state/elastic_fleet_packages.txt
-    - contents: {{ELASTICFLEETMERGED.packages}}
-
-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:
-    - name: /usr/sbin/so-elastic-agent-grid-upgrade
-    - retry:
-        attempts: 12
-        interval: 5
-
-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
-
-{%   if ELASTICFLEETMERGED.config.defend_filters.enable_auto_configuration %}
-so-elastic-defend-manage-filters-file-watch:
-  cmd.run:
-    - name: python3 /sbin/so-elastic-defend-manage-filters.py -c /opt/so/conf/elasticsearch/curl.config -d /opt/so/conf/elastic-fleet/defend-exclusions/disabled-filters.yaml -i /nsm/securityonion-resources/event_filters/ -i /opt/so/conf/elastic-fleet/defend-exclusions/rulesets/custom-filters/ &>> /opt/so/log/elasticfleet/elastic-defend-manage-filters.log
-    - onchanges:
-      - file: elasticdefendcustom
-      - file: elasticdefenddisabled
-{%    endif %}
-{%  endif %}
-
 delete_so-elastic-fleet_so-status.disabled:
   file.uncomment:
     - name: /opt/so/conf/so-status/so-status.conf

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

@@ -9,16 +9,22 @@
   "namespace": "so",
   "description": "Zeek Import logs",
   "policy_id": "so-grid-nodes_general",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/import/*/zeek/logs/*.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "import",
             "pipeline": "",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -34,7 +40,8 @@
             "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations-dynamic/grid-nodes_general/kratos-logs.json

@@ -15,19 +15,25 @@
     "version": ""
   },
   "name": "kratos-logs",
+  "namespace": "so",
   "description": "Kratos logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/kratos/kratos.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "kratos",
             "pipeline": "kratos",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -48,10 +54,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations-dynamic/grid-nodes_general/zeek-logs.json

@@ -9,16 +9,22 @@
   "namespace": "so",
   "description": "Zeek logs",
   "policy_id": "so-grid-nodes_general",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/zeek/logs/current/*.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "zeek",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
             "exclude_files": ["({%- endraw -%}{{ ELASTICFLEETMERGED.logging.zeek.excluded | join('|') }}{%- raw -%})(\\..+)?\\.log$"],
@@ -30,10 +36,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations/elastic-defend/elastic-defend-endpoints.json

@@ -5,7 +5,7 @@
   "package": {
     "name": "endpoint",
     "title": "Elastic Defend",
-    "version": "9.0.2",
+    "version": "9.4.1",
     "requires_root": true
   },
   "enabled": true,

salt/elasticfleet/files/integrations/grid-nodes_general/elastic-agent-monitor.json

@@ -6,21 +6,23 @@
   "name": "agent-monitor",
   "namespace": "",
   "description": "",
+  "policy_id": "so-grid-nodes_general",
   "policy_ids": [
     "so-grid-nodes_general"
   ],
-  "output_id": null,
   "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/agents/agent-monitor.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "agentmonitor",
             "pipeline": "elasticagent.monitor",
             "parsers": "",
@@ -34,15 +36,16 @@
             "ignore_older": "72h",
             "clean_inactive": -1,
             "harvester_limit": 0,
-            "fingerprint": true,
+            "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": 64,
+            "file_identity_native": true,
-            "file_identity_native": false,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }
     }
-  }
+  },
+  "force": true
 }

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

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "hydra-logs",
+  "namespace": "so",
   "description": "Hydra logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/hydra/hydra.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "hydra",
             "pipeline": "hydra",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -34,10 +40,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

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

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "idh-logs",
+  "namespace": "so",
   "description": "IDH integration",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/idh/opencanary.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "idh",
             "pipeline": "common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -31,10 +37,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

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

@@ -4,26 +4,32 @@
     "version": ""
   },
   "name": "import-evtx-logs",
+  "namespace": "so",
   "description": "Import Windows EVTX logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/import/*/evtx/*.json"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "import",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
             "exclude_files": [
               "\\.gz$"
             ],
             "include_files": [],
-            "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",
+            "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- add_fields:\n    target: event\n    fields:\n      dataset: windows.forwarded\n      module: windows\n      imported: true\n- add_fields:\n    target: \"@metadata\"\n    fields:\n        pipeline: import.evtx\n- if:\n    equals:\n      winlog.channel: 'Security'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.security\n          module: system\n- if:\n    equals:\n      winlog.channel: 'Windows PowerShell'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell\n          module: windows\n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-Sysmon/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.sysmon_operational\n          module: windows\n          imported: true\n- if:\n    equals:\n      winlog.channel: 'Application'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.application\n          module: system\n- if:\n    equals:\n      winlog.channel: 'System'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: system.system\n          module: system\n    \n- if:\n    equals:\n      winlog.channel: 'Microsoft-Windows-PowerShell/Operational'\n  then: \n    - add_fields:\n        target: event\n        fields:\n          dataset: windows.powershell_operational\n          module: windows\n- add_fields:\n    target: data_stream\n    fields:\n        type: logs\n        dataset: import",
             "tags": [
               "import"
             ],
@@ -33,10 +39,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

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

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "import-suricata-logs",
+  "namespace": "so",
   "description": "Import Suricata logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/import/*/suricata/eve*.json"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "import",
             "pipeline": "suricata.common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -32,10 +38,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

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

@@ -4,14 +4,18 @@
     "version": ""
   },
   "name": "rita-logs",
+  "namespace": "so",
   "description": "RITA Logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
@@ -19,6 +23,8 @@
               "/nsm/rita/exploded-dns.csv",
               "/nsm/rita/long-connections.csv"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "rita",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
             "exclude_files": [
@@ -33,10 +39,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations/grid-nodes_general/so-ip-mappings.json

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "so-ip-mappings",
+  "namespace": "so",
   "description": "IP Description mappings",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/custom-mappings/ip-descriptions.csv"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "hostnamemappings",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
             "exclude_files": [
@@ -32,10 +38,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations/grid-nodes_general/soc-auth-sync-logs.json

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "soc-auth-sync-logs",
+  "namespace": "so",
   "description": "Security Onion - Elastic Auth Sync - Logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/soc/sync.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "soc",
             "pipeline": "common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -31,10 +37,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations/grid-nodes_general/soc-detections-logs.json

@@ -4,20 +4,26 @@
     "version": ""
   },
   "name": "soc-detections-logs",
+  "namespace": "so",
   "description": "Security Onion Console - Detections Logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/soc/detections_runtime-status_sigma.log",
               "/opt/so/log/soc/detections_runtime-status_yara.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "soc",
             "pipeline": "common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -35,10 +41,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations/grid-nodes_general/soc-salt-relay-logs.json

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "soc-salt-relay-logs",
+  "namespace": "so",
   "description": "Security Onion - Salt Relay - Logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/soc/salt-relay.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "soc",
             "pipeline": "common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -33,10 +39,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations/grid-nodes_general/soc-sensoroni-logs.json

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "soc-sensoroni-logs",
+  "namespace": "so",
   "description": "Security Onion - Sensoroni - Logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/sensoroni/sensoroni.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "soc",
             "pipeline": "common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -31,10 +37,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/files/integrations/grid-nodes_general/soc-server-logs.json

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "soc-server-logs",
+  "namespace": "so",
   "description": "Security Onion Console Logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/opt/so/log/soc/sensoroni-server.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "soc",
             "pipeline": "common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -33,10 +39,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

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

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "strelka-logs",
+  "namespace": "so",
   "description": "Strelka Logs",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/strelka/log/strelka.log"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "strelka",
             "pipeline": "strelka.file",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -31,10 +37,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

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

@@ -4,19 +4,25 @@
     "version": ""
   },
   "name": "suricata-logs",
+  "namespace": "so",
   "description": "Suricata integration",
   "policy_id": "so-grid-nodes_general",
-  "namespace": "so",
+  "policy_ids": [
+    "so-grid-nodes_general"
+  ],
+  "vars": {},
   "inputs": {
     "filestream-filestream": {
       "enabled": true,
       "streams": {
-        "filestream.generic": {
+        "filestream.filestream": {
           "enabled": true,
           "vars": {
             "paths": [
               "/nsm/suricata/eve*.json"
             ],
+            "compression_gzip": false,
+            "use_logs_stream": false,
             "data_stream.dataset": "suricata",
             "pipeline": "suricata.common",
             "parsers": "#- ndjson:\n#    target: \"\"\n#    message_key: msg\n#- multiline:\n#    type: count\n#    count_lines: 3\n",
@@ -31,10 +37,10 @@
             "harvester_limit": 0,
             "fingerprint": false,
             "fingerprint_offset": 0,
-            "fingerprint_length": "64",
             "file_identity_native": true,
             "exclude_lines": [],
-            "include_lines": []
+            "include_lines": [],
+            "delete_enabled": false
           }
         }
       }

salt/elasticfleet/input-defaults.map.jinja

@@ -0,0 +1,121 @@
+{# 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. #}
+
+
+{% import_json '/opt/so/state/esfleet_input_package_components.json' as ADDON_INPUT_PACKAGE_COMPONENTS %}
+{% import_json '/opt/so/state/esfleet_component_templates.json' as INSTALLED_COMPONENT_TEMPLATES %}
+{% import_yaml 'elasticfleet/defaults.yaml' as ELASTICFLEETDEFAULTS %}
+
+{% set CORE_ESFLEET_PACKAGES = ELASTICFLEETDEFAULTS.get('elasticfleet', {}).get('packages', {}) %}
+{% set ADDON_INPUT_INTEGRATION_DEFAULTS = {} %}
+
+{% for pkg in ADDON_INPUT_PACKAGE_COMPONENTS %}
+{%   if pkg.name in CORE_ESFLEET_PACKAGES %}
+{#     skip core input packages #}
+{%   elif pkg.name not in CORE_ESFLEET_PACKAGES %}
+{#     generate defaults for each input package #}
+{%     if pkg.dataStreams is defined and pkg.dataStreams is not none and pkg.dataStreams | length > 0 %}
+{%       for pattern in pkg.dataStreams %}
+{#         in ES 9.3.2 'input' type integrations no longer create default component templates and instead they wait for user input during 'integration' setup (fleet ui config)
+             title: generic is an artifact of that and is not in use #}
+{%         if pattern.title == "generic" %}
+{%           continue %}
+{%         endif %}
+{%         if "metrics-" in pattern.name %}
+{%           set integration_type = "metrics-" %}
+{%         elif "logs-" in pattern.name %}
+{%           set integration_type = "logs-" %}
+{%         else %}
+{%           set integration_type = "" %}
+{%         endif %}
+{#         on input integrations the component name is user defined at the time it is added to an agent policy #}
+{%         set component_name = pattern.title %}
+{%         set index_pattern = pattern.name %}
+{#           component_name_x maintains the functionality of merging local pillar changes with generated 'defaults' via SOC UI #}
+{%           set component_name_x = component_name.replace(".","_x_") %}
+{#           pillar overrides/merge expects the key names to follow the naming in elasticsearch/defaults.yaml eg. so-logs-1password_x_item_usages . The _x_ is replaced later on in elasticsearch/template.map.jinja #}
+{%           set integration_key = "so-" ~ integration_type ~ pkg.name + '_x_' ~ component_name_x %}
+{#           Default integration settings #}
+{%           set integration_defaults = {
+               "index_sorting": false,
+               "index_template": {
+                 "composed_of": [integration_type ~ component_name ~ "@package", integration_type ~ component_name ~ "@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": [integration_type ~ component_name ~ "@custom"],
+                 "index_patterns": [index_pattern],
+                 "priority": 501,
+                 "template": {
+                   "settings": {
+                     "index": {
+                       "lifecycle": {"name": "so-" ~ integration_type ~ component_name ~ "-logs"},
+                         "number_of_replicas": 0
+                     }
+                   }
+                 }
+               },
+               "policy": {
+                 "phases": {
+                   "cold": {
+                     "actions": {
+                        "allocate":{
+                          "number_of_replicas": ""
+                        },
+                       "set_priority": {"priority": 0}
+                     },
+                     "min_age": "60d"
+                   },
+                   "delete": {
+                     "actions": {
+                       "delete": {}
+                     },
+                     "min_age": "365d"
+                   },
+                   "hot": {
+                     "actions": {
+                       "rollover": {
+                         "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"
+                   }
+                 }
+               }
+             } %}
+
+
+{%         do ADDON_INPUT_INTEGRATION_DEFAULTS.update({integration_key: integration_defaults}) %}
+{%       endfor %}
+{%     endif %}
+{%   endif %}
+{% endfor %}

salt/elasticfleet/install_agent_grid.sls

@@ -10,6 +10,15 @@
 {% set AGENT_STATUS = salt['service.available']('elastic-agent') %}
 {% set AGENT_EXISTS = salt['file.file_exists']('/opt/Elastic/Agent/elastic-agent') %}
 
+so-elastic-agent-install:
+  file.managed:
+    - name: /usr/sbin/so-elastic-agent-install
+    - source: salt://elasticfleet/tools/sbin/so-elastic-agent-install
+    - user: root
+    - group: root
+    - mode: 755
+    - show_changes: False
+
 {% if not AGENT_STATUS or not AGENT_EXISTS %}
 
 pull_agent_installer:
@@ -21,11 +30,9 @@ pull_agent_installer:
 
 run_installer:
   cmd.run:
-    - name: ./so-elastic-agent_linux_amd64 -token={{ GRIDNODETOKEN }} -force
+    - name: /usr/sbin/so-elastic-agent-install "{{ GRIDNODETOKEN }}"
-    - cwd: /opt/so
+    - require:
-    - retry:
+      - file: pull_agent_installer
-        attempts: 3
-        interval: 20
 
 cleanup_agent_installer:
   file.absent:

salt/elasticfleet/integration-defaults.map.jinja

@@ -16,7 +16,6 @@
     'awsfirehose.metrics': 'aws.cloudwatch',
     'cribl.logs': 'cribl',
     'cribl.metrics': 'cribl',
-    'sentinel_one_cloud_funnel.logins': 'sentinel_one_cloud_funnel.login',
     'azure_application_insights.app_insights': 'azure.app_insights',
     'azure_application_insights.app_state': 'azure.app_state',
     'azure_billing.billing': 'azure.billing',
@@ -31,17 +30,14 @@
     'azure_metrics.monitor': 'azure.monitor',
     'azure_metrics.storage_account': 'azure.storage_account',
     'azure_openai.metrics': 'azure.open_ai',
-    'beat.state': 'beats.stack_monitoring.state',
-    'beat.stats': 'beats.stack_monitoring.stats',
-    'enterprisesearch.health': 'enterprisesearch.stack_monitoring.health',
-    'enterprisesearch.stats': 'enterprisesearch.stack_monitoring.stats',
     'kibana.cluster_actions': 'kibana.stack_monitoring.cluster_actions',
     'kibana.cluster_rules': 'kibana.stack_monitoring.cluster_rules',
     'kibana.node_actions': 'kibana.stack_monitoring.node_actions',
     'kibana.node_rules': 'kibana.stack_monitoring.node_rules',
     'kibana.stats': 'kibana.stack_monitoring.stats',
     'kibana.status': 'kibana.stack_monitoring.status',
-    'logstash.node_cel': 'logstash.stack_monitoring.node',
+    'logstash.node': 'logstash.stack_monitoring.node',
+    'logstash.node_cel': 'logstash.node',
     'logstash.node_stats': 'logstash.stack_monitoring.node_stats',
     'synthetics.browser': 'synthetics-browser',
     'synthetics.browser_network': 'synthetics-browser.network',
@@ -59,8 +55,8 @@
 {#     skip core integrations #}
 {%   elif pkg.name not in CORE_ESFLEET_PACKAGES %}
 {#     generate defaults for each integration #}
-{%     if pkg.es_index_patterns is defined and pkg.es_index_patterns is not none %}
+{%     if pkg.dataStreams is defined and pkg.dataStreams is not none and pkg.dataStreams | length > 0 %}
-{%       for pattern in pkg.es_index_patterns %}
+{%       for pattern in pkg.dataStreams %}
 {%         if "metrics-" in pattern.name %}
 {%           set integration_type = "metrics-" %}
 {%         elif "logs-" in pattern.name %}
@@ -75,44 +71,27 @@
 {%         if component_name in WEIRD_INTEGRATIONS %}
 {%           set component_name = WEIRD_INTEGRATIONS[component_name] %}
 {%         endif %}
-
-{#         create duplicate of component_name, so we can split generics from @custom component templates in the index template below and overwrite the default @package when needed
-           eg. having to replace unifiedlogs.generic@package with filestream.generic@package, but keep the ability to customize unifiedlogs.generic@custom and its ILM policy #}
-{%         set custom_component_name = component_name %}
-
-{#         duplicate integration_type to assist with sometimes needing to overwrite component templates with 'logs-filestream.generic@package' (there is no metrics-filestream.generic@package) #}
-{%         set generic_integration_type = integration_type %}
-
 {#           component_name_x maintains the functionality of merging local pillar changes with generated 'defaults' via SOC UI #}
 {%           set component_name_x = component_name.replace(".","_x_") %}
 {#           pillar overrides/merge expects the key names to follow the naming in elasticsearch/defaults.yaml eg. so-logs-1password_x_item_usages . The _x_ is replaced later on in elasticsearch/template.map.jinja #}
 {%           set integration_key = "so-" ~ integration_type ~ component_name_x %}
 
-{#         if its a .generic template make sure that a .generic@package for the integration exists. Else default to logs-filestream.generic@package #}
-{%         if ".generic" in component_name and integration_type ~ component_name ~ "@package" not in INSTALLED_COMPONENT_TEMPLATES %}
-{#           these generic templates by default are directed to index_pattern of 'logs-generic-*', overwrite that here to point to eg gcp_pubsub.generic-* #}
-{%           set index_pattern = integration_type ~ component_name ~ "-*" %}
-{#           includes use of .generic component template, but it doesn't exist in installed component templates. Redirect it to filestream.generic@package #}
-{%           set component_name = "filestream.generic" %}
-{%           set generic_integration_type = "logs-" %}
-{%         endif %}
-
 {#           Default integration settings #}
 {%           set integration_defaults = {
                "index_sorting": false,
                "index_template": {
-                 "composed_of": [generic_integration_type ~ component_name ~ "@package", integration_type ~ custom_component_name ~ "@custom", "so-fleet_integrations.ip_mappings-1", "so-fleet_globals-1", "so-fleet_agent_id_verification-1"],
+                 "composed_of": [integration_type ~ component_name ~ "@package", integration_type ~ component_name ~ "@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": [integration_type ~ custom_component_name ~ "@custom"],
+                 "ignore_missing_component_templates": [integration_type ~ component_name ~ "@custom"],
                  "index_patterns": [index_pattern],
                  "priority": 501,
                  "template": {
                    "settings": {
                      "index": {
-                       "lifecycle": {"name": "so-" ~ integration_type ~ custom_component_name ~ "-logs"},
+                       "lifecycle": {"name": "so-" ~ integration_type ~ component_name ~ "-logs"},
                          "number_of_replicas": 0
                      }
                    }

salt/elasticfleet/manager.sls

@@ -0,0 +1,132 @@
+# 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 'allowed_states.map.jinja' import allowed_states %}
+{% if sls in allowed_states %}
+{%   from 'elasticfleet/map.jinja' import ELASTICFLEETMERGED %}
+
+include:
+  - elasticfleet.config
+  - kibana.enabled
+
+# If enabled, automatically update Fleet Logstash Outputs
+{% if ELASTICFLEETMERGED.config.server.enable_auto_configuration %}
+{%   if grains.role not in ['so-import', 'so-eval']%}
+so-elastic-fleet-auto-configure-logstash-outputs:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-outputs-update
+    - retry:
+        attempts: 4
+        interval: 30
+    - require:
+      - http: wait_for_so-kibana
+{%   endif %}
+
+# If enabled, automatically update Fleet Server URLs & ES Connection
+so-elastic-fleet-auto-configure-server-urls:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-urls-update
+    - retry:
+        attempts: 4
+        interval: 30
+    - require:
+      - http: wait_for_so-kibana
+{% endif %}
+
+# Automatically update Fleet Server Elasticsearch URLs & Agent Artifact URLs
+so-elastic-fleet-auto-configure-elasticsearch-urls:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-es-url-update
+    - retry:
+        attempts: 4
+        interval: 30
+    - require:
+      - http: wait_for_so-kibana
+
+so-elastic-fleet-auto-configure-artifact-urls:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-artifacts-url-update
+    - retry:
+        attempts: 4
+        interval: 30
+    - require:
+      - http: wait_for_so-kibana
+
+so-elastic-fleet-package-statefile:
+  file.managed:
+    - name: /opt/so/state/elastic_fleet_packages.txt
+    - contents: {{ELASTICFLEETMERGED.packages}}
+
+so-elastic-fleet-package-upgrade:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-package-upgrade
+    - retry:
+        attempts: 3
+        interval: 30
+    - require:
+      - http: wait_for_so-kibana
+
+# initial so-elasticsearch-templates run is earlier, but it can skip over templates that have component templates not yet installed to avoid elasticsearch rejecting the template.
+so-elasticsearch-templates-after-fleet-packages:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-templates-load
+    - cwd: /opt/so
+    - unless: test -f /opt/so/state/estemplates.txt
+    - require:
+      - cmd: so-elastic-fleet-package-upgrade
+
+so-elastic-fleet-integration-upgrade:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-integration-upgrade
+    - retry:
+        attempts: 3
+        interval: 10
+    - require:
+      - cmd: so-elastic-fleet-package-upgrade
+
+so-elastic-fleet-integrations:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-fleet-integration-policy-load
+    - retry:
+        attempts: 3
+        interval: 10
+    - require:
+      - http: wait_for_so-kibana
+
+so-elastic-agent-grid-upgrade:
+  cmd.run:
+    - name: /usr/sbin/so-elastic-agent-grid-upgrade
+    - retry:
+        attempts: 12
+        interval: 5
+    - require:
+      - http: wait_for_so-kibana
+
+{# 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
+    - require:
+      - http: wait_for_so-kibana
+      - cmd: so-elasticsearch-templates-after-fleet-packages
+
+{% if ELASTICFLEETMERGED.config.defend_filters.enable_auto_configuration %}
+so-elastic-defend-manage-filters-file-watch:
+  cmd.run:
+    - name: python3 /sbin/so-elastic-defend-manage-filters.py -c /opt/so/conf/elasticsearch/curl.config -d /opt/so/conf/elastic-fleet/defend-exclusions/disabled-filters.yaml -i /nsm/securityonion-resources/event_filters/ -i /opt/so/conf/elastic-fleet/defend-exclusions/rulesets/custom-filters/ &>> /opt/so/log/elasticfleet/elastic-defend-manage-filters.log
+    - require:
+      - http: wait_for_so-kibana
+    - onchanges:
+      - file: elasticdefendcustom
+      - file: elasticdefenddisabled
+{% endif %}
+
+{% else %}
+
+{{sls}}_state_not_allowed:
+  test.fail_without_changes:
+    - name: {{sls}}_state_not_allowed
+
+{% endif %}

salt/elasticfleet/tools/sbin/so-elastic-agent-install

@@ -0,0 +1,100 @@
+#!/bin/bash
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+. /usr/sbin/so-elastic-fleet-common
+
+
+# passed in as arg from elasticfleet/install_agent_grid.sls, else pulled from pillar later
+GRIDNODETOKEN="$1"
+LOGFILE="/opt/so/SO-Elastic-Agent_Installer_Health.log"
+
+check_agent_health() {
+    timeout=300
+    interval=10
+    start=$SECONDS
+
+    while (( SECONDS - start < timeout )); do
+        agent_status=$(elastic-agent status 2>&1)
+        echo -e "\n$(date)\n$agent_status\n" >> "$LOGFILE"
+        if echo "$agent_status" | grep -A1 'elastic-agent$' | grep -q 'status: (HEALTHY)'; then
+            return 0
+        fi
+        echo "The Elastic Agent is not yet healthy. Waiting for ${interval} seconds before checking again..."
+        sleep "$interval"
+    done
+
+    echo "The Elastic Agent did not become healthy within ${timeout} seconds"
+    return 1
+}
+
+uninstall_agent() {
+    if command -v elastic-agent >/dev/null 2>&1; then
+        elastic-agent uninstall -f
+    fi
+}
+
+if [[ -z "$GRIDNODETOKEN" ]]; then
+    noderole=$(so-yaml.py get -r /etc/salt/grains role)
+    if [[ "$noderole" == "so-heavynode" ]]; then
+        GRIDNODETOKEN=$(salt-call pillar.get global:fleet_grid_enrollment_token_heavy --out=newline_values_only)
+    else
+        GRIDNODETOKEN=$(salt-call pillar.get global:fleet_grid_enrollment_token_general --out=newline_values_only)
+    fi
+fi
+
+if [[ -z "$GRIDNODETOKEN" ]]; then
+    echo "Unable to determine Elastic Fleet enrollment token. Exiting."
+
+    exit 1
+fi
+
+if [[ ! -x /opt/so/so-elastic-agent_linux_amd64 ]]; then
+    echo "Downloading so-elastic-agent installer... This could take a while if another Salt job is running."
+
+    # When running outside of elasticfleet/install_agent_grid.sls we need to download the installer independently.
+    #  PYTHONWARNINGS="ignore" to avoid messages like the following when running salt-call:
+    #  '/opt/saltstack/salt/lib/python3.10/site-packages/salt/transport/base.py:129: TransportWarning: Unclosed transport! <salt.transport.zeromq.RequestClient object at 0x7fc5f0ee7a30>
+    #    File "/bin/salt-call", line 12, in <module>
+    #      sys.exit(salt_call())'
+
+    PYTHONWARNINGS="ignore" salt-call state.single file.managed name=/opt/so/so-elastic-agent_linux_amd64 source=salt://elasticfleet/files/so_agent-installers/so-elastic-agent_linux_amd64 mode=755 makedirs=True queue=True
+
+fi
+
+if [[ -x /opt/so/so-elastic-agent_linux_amd64 ]]; then
+    attempts=0
+    cd /opt/so/ || exit 1
+
+    truncate -s 0 "$LOGFILE"
+
+    uninstall_agent
+
+    while [[ $attempts -lt 3 ]]; do
+        if ./so-elastic-agent_linux_amd64 -token="$GRIDNODETOKEN" -force && echo "Verifying Elastic Agent health..." && check_agent_health; then
+            rm -f /opt/so/so-elastic-agent_linux_amd64
+            elastic-agent status
+
+            exit 0
+        fi
+
+        attempts=$((attempts + 1))
+
+        if [[ $attempts -lt 3 ]]; then
+            echo "Unable to verify Elastic Agent health... Retrying in 20 seconds..."
+            sleep 20
+        fi
+    done
+
+    uninstall_agent
+    rm -f /opt/so/so-elastic-agent_linux_amd64
+    echo "The so-elastic-agent installer failed after 3 attempts. Exiting."
+
+    exit 1
+else
+    echo "Unable to locate so-elastic-agent installer. Exiting."
+
+    exit 1
+fi

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

@@ -30,15 +30,151 @@ fleet_api() {
     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_require_agent_policy() {
+    local AGENT_POLICY=$1
+    local POLICY_JSON
+
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY") || [ -z "$POLICY_JSON" ]; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    if ! jq -e '.item.package_policies | type == "array"' <<<"$POLICY_JSON" >/dev/null 2>&1; then
+        echo "Error: Agent policy '$AGENT_POLICY' was not found or is not visible in the current Kibana space." >&2
+        return 1
+    fi
+
+    echo "$POLICY_JSON"
+}
+
+# Print the single active enrollment token for POLICY_ID.
+# Exit 1: retryable (API failure, invalid response, no active token)
+# Exit 2: multiple active tokens - Shouldn't get into this state without manual intervention
+elastic_fleet_active_enrollment_token() {
+    local POLICY_ID=$1
+    local RESP TOKEN_COUNT API_KEY
+
+    if ! RESP=$(fleet_api "enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+        echo "Error: Failed to retrieve enrollment tokens for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if ! jq -e '.list' <<<"$RESP" >/dev/null 2>&1; then
+        echo "Error: Invalid enrollment token response for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    TOKEN_COUNT=$(jq --arg pid "$POLICY_ID" '[.list[] | select(.policy_id == $pid and .active == true)] | length' <<<"$RESP")
+
+    if [ "${TOKEN_COUNT:-0}" -eq 0 ]; then
+        echo "Error: No active enrollment token found for agent policy '$POLICY_ID'." >&2
+        return 1
+    fi
+
+    if [ "$TOKEN_COUNT" -gt 1 ]; then
+        echo "Error: Found $TOKEN_COUNT active enrollment tokens for agent policy '$POLICY_ID'; expected exactly one." >&2
+        return 2
+    fi
+
+    API_KEY=$(jq -r --arg pid "$POLICY_ID" '.list[] | select(.policy_id == $pid and .active == true) | .api_key' <<<"$RESP")
+    echo "$API_KEY"
+}
+
+# Max number of concurrent Fleet write jobs (create/update). Override via env if needed.
+MAX_FLEET_JOBS=${MAX_FLEET_JOBS:-10}
+
+# Block until fewer than MAX_FLEET_JOBS background jobs are running.
+elastic_fleet_throttle() {
+    while (( $(jobs -rp | wc -l) >= MAX_FLEET_JOBS )); do
+        wait -n || true
+    done
+}
+
+# Load every integration JSON in a directory into a single agent policy.
+# The agent policy is fetched ONCE (not per file), and the create/update writes
+# are dispatched as throttled background jobs.
+#   $1 AGENT_POLICY     - the agent policy id/name to load integrations into
+#   $2 DIR              - directory of integration *.json files
+#   $3 LABEL           - human-readable label for log output
+#   $4 SKIP_CREATE_NAME - (optional) integration name to skip when creating (still updated if present)
+# Returns 1 if the policy cannot be fetched or if any integration failed to create/update.
+elastic_fleet_load_integrations_dir() {
+    local AGENT_POLICY=$1
+    local DIR=$2
+    local LABEL=$3
+    local SKIP_CREATE_NAME=$4
+    local POLICY_JSON FAIL_FILE OUT_DIR INTEGRATION NAME ID i
+
+    FAIL_FILE=$(mktemp)
+    # Each job buffers its full output (header + API response) into its own file so the
+    # parent can print them grouped and in submission order after concurrent writes finish.
+    OUT_DIR=$(mktemp -d)
+    i=0
+
+    # Fetch the agent policy a single time; we look up integration ids locally below.
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        rm -f "$FAIL_FILE"
+        rm -rf "$OUT_DIR"
+        return 1
+    fi
+
+    for INTEGRATION in "$DIR"/*.json; do
+        [ -e "$INTEGRATION" ] || continue
+        NAME=$(jq -r .name "$INTEGRATION")
+        ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
+
+        elastic_fleet_throttle
+        {
+            local RESP
+            if [ -n "$ID" ]; then
+                printf "\n\n%s - Updating integration %s\n" "$LABEL" "$NAME"
+                if ! RESP=$(elastic_fleet_integration_update "$ID" "@$INTEGRATION"); then
+                    flock 9; echo "update ${INTEGRATION##*/}" >&9
+                fi
+                printf '%s\n' "$RESP"
+            elif [ -n "$SKIP_CREATE_NAME" ] && [ "$NAME" == "$SKIP_CREATE_NAME" ]; then
+                printf "\n\n%s - Skipping creation of %s\n" "$LABEL" "$NAME"
+            else
+                printf "\n\n%s - Creating integration %s\n" "$LABEL" "$NAME"
+                if ! RESP=$(elastic_fleet_integration_create "@$INTEGRATION"); then
+                    flock 9; echo "create ${INTEGRATION##*/}" >&9
+                fi
+                printf '%s\n' "$RESP"
+            fi
+        } >"$OUT_DIR/$(printf '%03d' "$i")" 9>>"$FAIL_FILE" &
+        i=$((i+1))
+    done
+    wait || true
+
+    # Emit per-integration output grouped and in submission order (glob sorts numerically).
+    cat "$OUT_DIR"/* 2>/dev/null
+    rm -rf "$OUT_DIR"
+
+    local rc=0
+    if [ -s "$FAIL_FILE" ]; then
+        printf "\n%s: failed integrations:\n" "$LABEL"
+        cat "$FAIL_FILE"
+        rc=1
+    fi
+    rm -f "$FAIL_FILE"
+    return $rc
+}
+
 elastic_fleet_integration_check() {
 
     AGENT_POLICY=$1
 
     JSON_STRING=$2
 
-    NAME=$(jq -r .name $JSON_STRING)
+    NAME=$(jq -r .name "$JSON_STRING")
+    INTEGRATION_ID=""
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
 
 }
 
@@ -46,7 +182,9 @@ elastic_fleet_integration_create() {
 
     JSON_STRING=$1
 
-    if ! fleet_api "package_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
+    # --retry-all-errors so transient 409 conflicts (concurrent writes to the same agent
+    # policy) are retried; curl --retry alone does not retry 409.
+    if ! fleet_api "package_policies" --retry-all-errors -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
         return 1
     fi
 }
@@ -58,7 +196,16 @@ elastic_fleet_integration_remove() {
 
     NAME=$2
 
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$AGENT_POLICY" | jq -r '.item.package_policies[] | select(.name=="'"$NAME"'") | .id')
+    local POLICY_JSON
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$AGENT_POLICY"); then
+        return 1
+    fi
+
+    INTEGRATION_ID=$(jq -r --arg n "$NAME" '.item.package_policies[]? | select(.name==$n) | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: Integration '$NAME' was not found in agent policy '$AGENT_POLICY'." >&2
+        return 1
+    fi
 
     JSON_STRING=$( jq -n \
                     --arg INTEGRATIONID "$INTEGRATION_ID" \
@@ -77,7 +224,9 @@ elastic_fleet_integration_update() {
 
     JSON_STRING=$2
 
-    if ! fleet_api "package_policies/$UPDATE_ID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPUT -d "$JSON_STRING"; then
+    # --retry-all-errors so transient 409 conflicts (concurrent writes to the same agent
+    # policy) are retried; curl --retry alone does not retry 409.
+    if ! fleet_api "package_policies/$UPDATE_ID" --retry-all-errors -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPUT -d "$JSON_STRING"; then
         return 1
     fi
 }
@@ -135,9 +284,33 @@ elastic_fleet_bulk_package_install() {
     fi
 }
 
-elastic_fleet_installed_packages() {
+elastic_fleet_get_package_list_by_type() {
-    if ! fleet_api "epm/packages/installed?perPage=500"; then
+    if ! output=$(fleet_api "epm/packages"); then
         return 1
+    else
+        is_integration=$(jq '[.items[] | select(.type=="integration") | .name ]' <<< "$output")
+        is_input=$(jq '[.items[] | select(.type=="input") | .name ]' <<< "$output")
+        is_content=$(jq '[.items[] | select(.type=="content") | .name ]' <<< "$output")
+        jq -n --argjson is_integration "${is_integration:-[]}" \
+              --argjson is_input "${is_input:-[]}" \
+              --argjson is_content "${is_content:-[]}" \
+              '{"integration": $is_integration,"input": $is_input, "content": $is_content}'
+    fi
+}
+elastic_fleet_installed_packages_components() {
+    package_type=${1,,}
+    if [[ "$package_type" != "integration" && "$package_type" != "input" && "$package_type" != "content" ]]; then
+        echo "Error: Invalid package type ${package_type}. Valid types are 'integration', 'input', or 'content'."
+        return 1
+    fi
+
+    packages_by_type=$(elastic_fleet_get_package_list_by_type)
+    packages=$(jq --arg package_type "$package_type" '.[$package_type]' <<< "$packages_by_type")
+
+    if ! output=$(fleet_api "epm/packages/installed?perPage=500"); then
+        return 1
+    else
+        jq -c --argjson packages "$packages" '[.items[] | select(.name | IN($packages[])) | {name: .name, dataStreams: .dataStreams}]' <<< "$output"
     fi
 }
 
@@ -216,7 +389,7 @@ elastic_fleet_policy_create() {
         --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}'
+            '{"name": $NAME,"id":$NAME,"description":$DESC,"namespace":"default","monitoring_enabled":["logs"],"inactivity_timeout":$TIMEOUT,"has_fleet_server":$FLEETSERVER,"advanced_settings":{"agent_logging_level": "warning"}}'
         )
     # Create Fleet Policy
     if ! fleet_api "agent_policies" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then

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

@@ -13,7 +13,10 @@ ERROR=false
 for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/elastic-defend/*.json
 do
   printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
-  elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
+  if ! elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"; then
+    ERROR=true
+    continue
+  fi
   if [ -n "$INTEGRATION_ID" ]; then
       printf "\n\nIntegration $NAME exists - Upgrading integration policy\n"
       if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then

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

@@ -7,20 +7,35 @@
 . /usr/sbin/so-elastic-fleet-common
 
 # Get all the fleet policies
-json_output=$(curl -s -K /opt/so/conf/elasticsearch/curl.config -L -X GET "localhost:5601/api/fleet/agent_policies" -H 'kbn-xsrf: true')
+if ! json_output=$(fleet_api "agent_policies" -H 'kbn-xsrf: true'); then
+    echo "Error: Failed to retrieve Fleet agent policies." >&2
+    exit 1
+fi
+
+if ! jq -e '.items' <<<"$json_output" >/dev/null 2>&1; then
+    echo "Error: Invalid Fleet agent policies response." >&2
+    exit 1
+fi
 
 # Extract the IDs that start with "FleetServer_"
-POLICY=$(echo "$json_output" | jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id')
+POLICY=$(jq -r '.items[] | select(.id | startswith("FleetServer_")) | .id' <<<"$json_output")
 
 # Iterate over each ID in the POLICY variable
 for POLICYNAME in $POLICY; do
     printf "\nUpdating Policy: $POLICYNAME\n"
 
-    # First get the Integration ID
+    if ! POLICY_JSON=$(elastic_fleet_require_agent_policy "$POLICYNAME"); then
-    INTEGRATION_ID=$(/usr/sbin/so-elastic-fleet-agent-policy-view "$POLICYNAME" | jq -r '.item.package_policies[] | select(.package.name == "fleet_server") | .id')  
+        exit 1
+    fi
+
+    INTEGRATION_ID=$(jq -r '.item.package_policies[]? | select(.package.name == "fleet_server") | .id' <<<"$POLICY_JSON")
+    if [ -z "$INTEGRATION_ID" ]; then
+        echo "Error: fleet_server integration was not found in agent policy '$POLICYNAME'." >&2
+        exit 1
+    fi
 
     # Modify the default integration policy to update the policy_id and an with the correct naming
-	UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
+    UPDATED_INTEGRATION_POLICY=$(jq --arg policy_id "$POLICYNAME" --arg name "fleet_server-$POLICYNAME" '
     .policy_id = $policy_id |
     .name = $name' /opt/so/conf/elastic-fleet/integrations/fleet-server/fleet-server.json)
 

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

@@ -9,108 +9,45 @@
 RETURN_CODE=0
 
 if [ ! -f /opt/so/state/eaintegrations.txt ]; then
-  # First, check for any package upgrades
-  /usr/sbin/so-elastic-fleet-package-upgrade
 
-  # Second, update Fleet Server policies
+  # update Fleet Server policies
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server
 
-  # Third, configure Elastic Defend Integration seperately
+  # configure Elastic Defend Integration separately
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-defend
 
+  # Each group fetches its agent policy once and dispatches create/update writes concurrently.
+
   # Initial Endpoints
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/endpoints-initial/*.json; do
+  elastic_fleet_load_integrations_dir "endpoints-initial" \
-    printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
+    /opt/so/conf/elastic-fleet/integrations/endpoints-initial "Initial Endpoints Policy" || RETURN_CODE=1
-    elastic_fleet_integration_check "endpoints-initial" "$INTEGRATION"
-    if [ -n "$INTEGRATION_ID" ]; then
-      printf "\n\nIntegration $NAME exists - Updating integration\n"
-      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
-        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    else
-      printf "\n\nIntegration does not exist - Creating integration\n"
-      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    fi
-  done
 
   # Grid Nodes - General
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_general/*.json; do
+  elastic_fleet_load_integrations_dir "so-grid-nodes_general" \
-    printf "\n\nGrid Nodes Policy_General - Loading $INTEGRATION\n"
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_general "Grid Nodes Policy_General" || RETURN_CODE=1
-    elastic_fleet_integration_check "so-grid-nodes_general" "$INTEGRATION"
-    if [ -n "$INTEGRATION_ID" ]; then
-      printf "\n\nIntegration $NAME exists - Updating integration\n"
-      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
-        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    else
-      printf "\n\nIntegration does not exist - Creating integration\n"
-      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    fi
-  done
 
   # Grid Nodes - Heavy
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy/*.json; do
+  elastic_fleet_load_integrations_dir "so-grid-nodes_heavy" \
-    printf "\n\nGrid Nodes Policy_Heavy - Loading $INTEGRATION\n"
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy "Grid Nodes Policy_Heavy" || RETURN_CODE=1
-    elastic_fleet_integration_check "so-grid-nodes_heavy" "$INTEGRATION"
-    if [ -n "$INTEGRATION_ID" ]; then
-      printf "\n\nIntegration $NAME exists - Updating integration\n"
-      if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
-        echo -e "\nFailed to update integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    else
-      printf "\n\nIntegration does not exist - Creating integration\n"
-      if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-        echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-        RETURN_CODE=1
-        continue
-      fi
-    fi
-  done
 
-  # Fleet Server - Optional integrations
+  # Fleet Server - Optional integrations (adds integration configuration to a given FleetServer_ policy)
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json; do
+  for FLEET_DIR in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/; do
-    if ! [ "$INTEGRATION" == "/opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json" ]; then
+    [ -d "$FLEET_DIR" ] || continue
-      FLEET_POLICY=`echo "$INTEGRATION"| cut -d'/' -f7`
+    INTEGRATIONS=("${FLEET_DIR%/}"/*.json)
-      printf "\n\nFleet Server Policy - Loading $INTEGRATION\n"
+    [ -e "${INTEGRATIONS[0]}" ] || continue
-      elastic_fleet_integration_check "$FLEET_POLICY" "$INTEGRATION"
+
-      if [ -n "$INTEGRATION_ID" ]; then
+    FLEET_POLICY=$(basename "$FLEET_DIR")
-        printf "\n\nIntegration $NAME exists - Updating integration\n"
+    elastic_fleet_load_integrations_dir "$FLEET_POLICY" \
-        if ! elastic_fleet_integration_update "$INTEGRATION_ID" "@$INTEGRATION"; then
+      "${FLEET_DIR%/}" "Fleet Server Policy" "elasticsearch-logs" || RETURN_CODE=1
-          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
-          if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-            echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-            RETURN_CODE=1
-            continue
-          fi
-        fi
-      fi
-    fi
   done
 
   # Only create the state file if all policies were created/updated successfully
-  if [[ "$RETURN_CODE" != "1" ]]; then
+  if [[ $RETURN_CODE -eq 0 ]]; then
     touch /opt/so/state/eaintegrations.txt
+  else
+    exit 1
   fi
 else
-  exit $RETURN_CODE
+  echo "Fleet integration policies already loaded."
+  exit 0
 fi

salt/elasticfleet/tools/sbin_jinja/so-elastic-agent-gen-installers

@@ -22,15 +22,22 @@ NUM_RUNNING=$(pgrep -cf "/bin/bash /sbin/so-elastic-agent-gen-installers")
 
 for i in {1..30}
 do
-   ENROLLMENTOKEN=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "localhost:5601/api/fleet/enrollment_api_keys?perPage=100" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'  | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+   ENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial")
+   TOKEN_RC=$?
+   if [ "$TOKEN_RC" -eq 2 ]; then
+     exit 1
+   fi
    FLEETHOST=$(curl -K /opt/so/conf/elasticsearch/curl.config 'http://localhost:5601/api/fleet/fleet_server_hosts/grid-default' | jq -r  '.item.host_urls[]' | paste -sd ',')
-if [[ $FLEETHOST ]] && [[  $ENROLLMENTOKEN ]]; then break; else sleep 10; fi
+   if [[ -n "$FLEETHOST" ]] && [[ -n "$ENROLLMENTOKEN" ]]; then
+     break
+   fi
+   sleep 10
 done
 
-if [[ -z $FLEETHOST ]] || [[ -z $ENROLLMENTOKEN ]]; then 
+if [[ -z "$FLEETHOST" ]] || [[ -z "$ENROLLMENTOKEN" ]]; then
   printf "\nFleet Host URL, Enrollment Token or Elastic Version empty - exiting..."
   printf "\nFleet Host: $FLEETHOST, Enrollment Token: $ENROLLMENTOKEN\n"
-  exit 
+  exit 1
 fi
 
 OSARCH=( "linux-x86_64" "windows-x86_64" "darwin-x86_64" "darwin-aarch64" )
@@ -62,31 +69,60 @@ do
 done 
 
 GOTARGETOS=( "linux" "windows" "darwin" "darwin/arm64" )
-GOARCH="amd64"
 printf "\n### Generating OS packages using the cleaned up tarballs"
-for GOOS in "${GOTARGETOS[@]}"
+for GOOS in "${GOTARGETOS[@]}"; do
-do
+    GOARCH="amd64"
     if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin" && GOARCH="arm64"; fi
     printf "\n\n### Generating $GOOS/$GOARCH Installer...\n"
-    docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
+    if ! docker run -e CGO_ENABLED=0 -e GOOS=$GOOS -e GOARCH=$GOARCH \
     --mount type=bind,source=/etc/pki/tls/certs/,target=/workspace/files/cert/ \
     --mount type=bind,source=/nsm/elastic-agent-workspace/,target=/workspace/files/elastic-agent/ \
-    --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/,target=/output/ \
+    --mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ \
-    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}
+    {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} go build -ldflags "-X main.fleetHostURLsList=$FLEETHOST -X main.enrollmentToken=$ENROLLMENTOKEN"  -o /output/so-elastic-agent_${GOOS}_${GOARCH}; then
+        printf "\n### ERROR: Failed to generate $GOOS/$GOARCH installer. Exiting...\n"
+        exit 1
+    fi
     printf "\n### $GOOS/$GOARCH Installer Generated...\n"
 done
 
 printf "\n\n### Generating MSI...\n"
-cp /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/so-elastic-agent_windows_amd64.exe
+cp /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64 /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
-docker run \
+if ! docker run \
---mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/,target=/output/ -w /output \
+--mount type=bind,source=/opt/so/saltstack/local/salt/elasticfleet/files/,target=/output/ -w /output \
-{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs
+{{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elastic-agent-builder:{{ GLOBALS.so_version }} wixl -o so-elastic-agent_windows_amd64_msi --arch x64 /workspace/so-elastic-agent.wxs; then
+    printf "\n### ERROR: Failed to generate MSI. Exiting...\n"
+    exit 1
+fi
 printf "\n### MSI Generated...\n"
 
+# Verify installers were created
+for GOOS in "${GOTARGETOS[@]}"; do
+    GOARCH="amd64"
+    if [[ $GOOS == 'darwin/arm64' ]]; then GOOS="darwin"; GOARCH="arm64"; fi
+    if [[ ! -f /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_${GOOS}_${GOARCH} ]]; then
+        printf "\n### ERROR: Installer for %s/%s was not generated. Exiting...\n" "$GOOS" "$GOARCH"
+        exit 1
+    fi
+    # After verifying new installer was generated, move it to so_agent-installers directory
+    mv /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_${GOOS}_${GOARCH} /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/
+done
+
+# Verify MSI installer
+if [[ ! -f /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64_msi ]]; then
+    printf "\n### ERROR: Installer MSI was not generated. Exiting...\n"
+    exit 1
+else
+    # After verifying new installer MSI was generated, move it to so_agent-installers directory
+    mv /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64_msi /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/
+fi
+
 printf "\n### Cleaning up temp files \n"
 rm -rf /nsm/elastic-agent-workspace
-rm -rf /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/so-elastic-agent_windows_amd64.exe
+rm -rf /opt/so/saltstack/local/salt/elasticfleet/files/so-elastic-agent_windows_amd64.exe
 
 printf "\n### Copying so_agent-installers to /nsm/elastic-fleet/ for nginx.\n"
 \cp -vr /opt/so/saltstack/local/salt/elasticfleet/files/so_agent-installers/ /nsm/elastic-fleet/
 chmod 644 /nsm/elastic-fleet/so_agent-installers/*
+
+# if we got here all installers have been generated successfully
+exit 0

salt/elasticfleet/tools/sbin_jinja/so-elastic-agent-grid-upgrade

@@ -5,7 +5,13 @@
 # this file except in compliance with the Elastic License 2.0.
 
 . /usr/sbin/so-common
+. /usr/sbin/so-elastic-fleet-common
 {%- import_yaml 'elasticsearch/defaults.yaml' as ELASTICSEARCHDEFAULTS %}
+{%- import_yaml 'elasticfleet/defaults.yaml' as ELASTICFLEETDEFAULTS %}
+{# Optionally override Elasticsearch version for Elastic Agent patch releases #}
+{%- if ELASTICFLEETDEFAULTS.elasticfleet.patch_version is defined %}
+{%-   do ELASTICSEARCHDEFAULTS.elasticsearch.update({'version': ELASTICFLEETDEFAULTS.elasticfleet.patch_version}) %}
+{%- endif %}
 
 # Only run on Managers
 if ! is_manager_node; then
@@ -14,13 +20,10 @@ if ! is_manager_node; then
 fi
 
 # Get current list of Grid Node Agents that need to be upgraded
-RAW_JSON=$(curl -K /opt/so/conf/elasticsearch/curl.config -L "http://localhost:5601/api/fleet/agents?perPage=20&page=1&kuery=NOT%20agent.version%3A%20{{ELASTICSEARCHDEFAULTS.elasticsearch.version}}%20AND%20policy_id%3A%20so-grid-nodes_%2A&showInactive=false&getStatusSummary=true" --retry 3 --retry-delay 30 --fail 2>/dev/null)
+if ! RAW_JSON=$(fleet_api "agents?perPage=20&page=1&kuery=NOT%20agent.version%3A%20{{ELASTICSEARCHDEFAULTS.elasticsearch.version | urlencode }}%20AND%20policy_id%3A%20so-grid-nodes_%2A&showInactive=false&getStatusSummary=true" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
 
-# Check to make sure that the server responded with good data - else, bail from script
+    printf "Failed to query for current Grid Agents...\n"
-CHECKSUM=$(jq -r '.page' <<< "$RAW_JSON")
+    exit 1
-if [ "$CHECKSUM" -ne 1 ]; then
- printf "Failed to query for current Grid Agents...\n"
- exit 1
 fi
 
 # Generate list of Node Agents that need updates
@@ -31,10 +34,12 @@ if [ "$OUTDATED_LIST" != '[]' ]; then
    printf "Initiating upgrades for $AGENTNUMBERS Agents to Elastic {{ELASTICSEARCHDEFAULTS.elasticsearch.version}}...\n\n"
 
    # Generate updated JSON payload
-   JSON_STRING=$(jq -n --arg ELASTICVERSION {{ELASTICSEARCHDEFAULTS.elasticsearch.version}} --arg UPDATELIST $OUTDATED_LIST '{"version": $ELASTICVERSION,"agents": $UPDATELIST }')
+   JSON_STRING=$(jq -n --arg ELASTICVERSION "{{ELASTICSEARCHDEFAULTS.elasticsearch.version}}" --argjson UPDATELIST "$OUTDATED_LIST" '{"version": $ELASTICVERSION,"agents": $UPDATELIST }')
 
    # Update Node Agents
-   curl -K /opt/so/conf/elasticsearch/curl.config -L -X POST "http://localhost:5601/api/fleet/agents/bulk_upgrade" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"
+   if ! fleet_api "agents/bulk_upgrade" -XPOST -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -d "$JSON_STRING"; then
+       printf "Failed to initiate Agent upgrades...\n"
+   fi
 else
     printf "No Agents need updates... Exiting\n\n"
     exit 0

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

@@ -23,73 +23,90 @@ if [ $? -ne 0 ]; then
 fi
 
 default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.last %} {% endif %}{% endfor %})
+# JSON array of the default packages, used by the jq filter below.
+default_packages_json=$(printf '%s\n' "${default_packages[@]}" | jq -R . | jq -s '.')
+
+# Output lock (serializes concurrent job output) and failure file (one marker line per
+# failed integration). Mirrors the pattern used by elastic_fleet_load_integrations_dir.
+OUTPUT_LOCK=$(mktemp)
+FAIL_FILE=$(mktemp)
+trap 'rm -f "$OUTPUT_LOCK" "$FAIL_FILE"' EXIT
+
+# Cache of package name -> latest available version, so the same package is only looked up
+# once instead of once per (policy, integration).
+declare -A LATEST_VERSION_CACHE
 
-ERROR=false
 for AGENT_POLICY in $agent_policies; do
-    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+    # Fetch the agent policy a single time; package name/version and integration id are all
+    # extracted locally below instead of re-fetching the same policy per integration.
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$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" ]] && ! [[ "$INTEGRATION" == "fleet_server-"* ]]; then
+    # One jq pass emits name/package.name/package.version/id for every eligible integration.
-            # Get package name so we know what package to look for when checking the current and latest available version
+    # The endpoint/fleet_server skips and the default-package gate are applied here in jq.
-            if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+    # $defaults (not $def, a jq reserved keyword) holds the default package list.
+    while IFS=$'\t' read -r INTEGRATION PACKAGE_NAME PACKAGE_VERSION INTEGRATION_ID; do
+        [ -n "$INTEGRATION" ] || continue
+
+        # Look up the latest available version once per package, then memoize it.
+        if [[ -z "${LATEST_VERSION_CACHE[$PACKAGE_NAME]+set}" ]]; then
+            if ! AVAILABLE_VERSION=$(elastic_fleet_package_latest_version_check "$PACKAGE_NAME"); then
+                echo "Error: Failed getting latest version for $PACKAGE_NAME"
                 exit 1
             fi
-            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
+            LATEST_VERSION_CACHE[$PACKAGE_NAME]=$AVAILABLE_VERSION
-            if [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
-            {%- endif %}
-                # Get currently installed version of package
-                attempt=0
-                max_attempts=3
-                while [ $attempt -lt $max_attempts ]; do
-                    if PACKAGE_VERSION=$(elastic_fleet_integration_policy_package_version "$AGENT_POLICY" "$INTEGRATION") && AVAILABLE_VERSION=$(elastic_fleet_package_latest_version_check "$PACKAGE_NAME"); then
-                        break
-                    fi
-                    attempt=$((attempt + 1))
-                done
-                if [ $attempt -eq $max_attempts ]; then
-                    echo "Error: Failed getting $PACKAGE_VERSION or $AVAILABLE_VERSION"
-                    exit 1
-                fi
-
-                # Get integration ID
-                if ! INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION"); then
-                    exit 1
-                fi
-
-                if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
-                    # Dry run of the upgrade
-                    echo ""
-                    echo "Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."
-                    echo "Upgrading $INTEGRATION..."
-                    echo "Starting dry run..."
-                    if ! DRYRUN_OUTPUT=$(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..."
-                        if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
-                            echo "Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."
-                            ERROR=true
-                            continue
-                        fi
-                    else
-                        echo "Errors detected during dry run for $PACKAGE_NAME policy upgrade..."
-                        ERROR=true
-                        continue
-                    fi
-                fi
-            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-            fi
-            {%- endif %}
         fi
-    done
+        AVAILABLE_VERSION=${LATEST_VERSION_CACHE[$PACKAGE_NAME]}
+
+        if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
+            # Dry run, then (if clean) the actual upgrade, dispatched as a throttled background
+            # job. Each job builds its full log into one block, then flushes it under a single
+            # shared lock (OUTPUT_LOCK) so concurrent jobs never interleave on stdout; a failed
+            # job also appends a marker line to FAIL_FILE while holding that same lock.
+            elastic_fleet_throttle
+            {
+                block=$'\n'"Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."$'\n'
+                block+="Upgrading $INTEGRATION..."$'\n'"Starting dry run..."$'\n'
+                fail=""
+                if ! DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID"); then
+                    block+="Error: Failed to complete dry run for '$INTEGRATION_ID'."$'\n'
+                    fail="dryrun $INTEGRATION"
+                elif [[ "$(jq .[].hasErrors <<<"$DRYRUN_OUTPUT")" == "false" ]]; then
+                    block+="No errors detected. Proceeding with upgrade..."$'\n'
+                    if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
+                        block+="Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."$'\n'
+                        fail="upgrade $INTEGRATION"
+                    fi
+                else
+                    block+="Errors detected during dry run for $PACKAGE_NAME policy upgrade..."$'\n'
+                    fail="dryrun-errors $INTEGRATION"
+                fi
+                {
+                    flock 9
+                    printf '%s' "$block"
+                    [ -n "$fail" ] && printf '%s\n' "$fail" >>"$FAIL_FILE"
+                } 9>>"$OUTPUT_LOCK"
+            } &
+        fi
+    done < <(jq -r --argjson defaults "$default_packages_json" '
+        .item.package_policies[]
+        | select(.name != "elastic-defend-endpoints")
+        | select(.name | startswith("fleet_server-") | not)
+        {%- if not AUTO_UPGRADE_INTEGRATIONS %}
+        | select(.package.name | IN($defaults[]))
+        {%- endif %}
+        | [.name, .package.name, .package.version, .id] | @tsv
+    ' <<<"$POLICY_JSON")
 done
-if [[ "$ERROR" == "true" ]]; then
+
+# Barrier: wait for every dispatched dry-run/upgrade job to finish.
+wait
+
+if [ -s "$FAIL_FILE" ]; then
+    printf '\nFailed integration upgrades:\n'
+    cat "$FAIL_FILE"
     exit 1
 fi
 echo

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

@@ -16,9 +16,10 @@
 STATE_FILE_SUCCESS=/opt/so/state/estemplates.txt
 INSTALLED_PACKAGE_LIST=/tmp/esfleet_installed_packages.json
 BULK_INSTALL_PACKAGE_LIST=/tmp/esfleet_bulk_install.json
-BULK_INSTALL_PACKAGE_TMP=/tmp/esfleet_bulk_install_tmp.json
 BULK_INSTALL_OUTPUT=/opt/so/state/esfleet_bulk_install_results.json
-PACKAGE_COMPONENTS=/opt/so/state/esfleet_package_components.json
+INTEGRATION_PACKAGE_COMPONENTS=/opt/so/state/esfleet_package_components.json
+INPUT_PACKAGE_COMPONENTS=/opt/so/state/esfleet_input_package_components.json
+CONTENT_PACKAGE_COMPONENTS=/opt/so/state/esfleet_content_package_components.json
 COMPONENT_TEMPLATES=/opt/so/state/esfleet_component_templates.json
 
 PENDING_UPDATE=false
@@ -27,29 +28,6 @@ PENDING_UPDATE=false
 #   Requiring some level of manual Elastic Stack configuration before installation
 EXCLUDED_INTEGRATIONS=('apm')
 
-version_conversion(){
-    version=$1
-    echo "$version" | awk -F '.' '{ printf("%d%03d%03d\n", $1, $2, $3); }'
-}
-
-compare_versions() {
-    version1=$1
-    version2=$2
-
-    # Convert versions to numbers
-    num1=$(version_conversion "$version1")
-    num2=$(version_conversion "$version2")
-
-    # Compare using bc
-    if (( $(echo "$num1 < $num2" | bc -l) )); then
-        echo "less"
-    elif (( $(echo "$num1 > $num2" | bc -l) )); then
-        echo "greater"
-    else
-        echo "equal"
-    fi
-}
-
 IFS=$'\n'
 agent_policies=$(elastic_fleet_agent_policy_ids)
 if [ $? -ne 0 ]; then
@@ -61,23 +39,23 @@ default_packages=({% for pkg in SUPPORTED_PACKAGES %}"{{ pkg }}"{% if not loop.l
 
 in_use_integrations=()
 
+# Fetch each agent policy once; its package_policies[] already contain both the integration name
+#  and the .package.name, so extract all non-default package names locally in a single jq instead
+#  of re-fetching the same policy per integration.
+default_packages_json=$(printf '%s\n' "${default_packages[@]}" | jq -R . | jq -s '.')
 for AGENT_POLICY in $agent_policies; do
 
-    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
+    if ! policy_json=$(fleet_api "agent_policies/$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 $integrations; do
+    # non-default integrations that are in-use in any policy
-        if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+    while IFS= read -r PACKAGE_NAME; do
-            echo  "Not adding $INTEGRATION, couldn't get package name"
+        [ -n "$PACKAGE_NAME" ] && in_use_integrations+=("$PACKAGE_NAME")
-            continue
+    done < <(jq -r --argjson defaults "$default_packages_json" \
-        fi
+        '.item.package_policies[].package.name | select(. as $n | ($defaults | index($n)) | not)' \
-        # non-default integrations that are in-use in any policy
+        <<<"$policy_json")
-        if ! [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
-            in_use_integrations+=("$PACKAGE_NAME")
-        fi
-    done
 done
 
 if [[ -f $STATE_FILE_SUCCESS  ]]; then
@@ -88,72 +66,55 @@ if [[ -f $STATE_FILE_SUCCESS  ]]; then
         rm -f $INSTALLED_PACKAGE_LIST
         echo $latest_package_list | jq '{packages: [.items[] | {name: .name, latest_version: .version, installed_version: .installationInfo.version, subscription: .conditions.elastic.subscription }]}' >> $INSTALLED_PACKAGE_LIST
 
-        while read -r package; do
+        # Build the bulk install list and the per-package status messages with two jq passes
-            # get package details
+        #  instead of a per-package bash loop. The old loop forked ~10 processes per package
-            package_name=$(echo "$package" | jq -r '.name')
+        #  (5 jq + awk/bc for the version compare) and re-parsed/rewrote a growing JSON file on
-            latest_version=$(echo "$package" | jq -r '.latest_version')
+        #  every add (O(n^2)). Selection and messages below are identical to that logic.
-            installed_version=$(echo "$package" | jq -r '.installed_version')
+        SUB={% if SUB %}true{% else %}false{% endif %}
-            subscription=$(echo "$package" | jq -r '.subscription')
+        AUTOUP={% if AUTO_UPGRADE_INTEGRATIONS %}true{% else %}false{% endif %}
-            bulk_package=$(echo "$package" | jq '{name: .name, version: .latest_version}' )
+        EXCLUDED_JSON=$(printf '%s\n' "${EXCLUDED_INTEGRATIONS[@]}" | jq -R 'select(length>0)' | jq -s '.')
+        INUSE_JSON=$(printf '%s\n' "${in_use_integrations[@]}" | jq -R 'select(length>0)' | jq -s 'unique')
 
-            if [[ ! "${EXCLUDED_INTEGRATIONS[@]}" =~ "$package_name" ]]; then
+        # vnum replicates the previous version_conversion (%d%03d%03d of the first three dotted
-            {% if not SUB %}
+        #  fields); needs() replicates the excluded/subscription/installed/upgrade/in-use logic.
-                if [[ "$subscription" != "basic" && "$subscription" != "null" && -n "$subscription" ]]; then
+        JQ_DECISION='
-                    # pass over integrations that require non-basic elastic license
+def vnum:
-                    echo "$package_name integration requires an Elastic license of $subscription or greater... skipping"
+  [ (split(".")|.[0:3][] | gsub("[^0-9].*";"") | (if .=="" then "0" else . end) | tonumber) ]
-                    continue
+  | (.[0]//0)*1000000 + (.[1]//0)*1000 + (.[2]//0);
-                else
+def needs($sub;$autoup;$excluded;$inuse):
-                    if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
+  .name as $n
-                        echo "$package_name is not installed... Adding to next update."
+  | ($n | IN($excluded[]) | not)
-                        jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
+  and ( $sub or (.subscription==null or .subscription=="basic" or .subscription=="") )
+  and ( (.installed_version==null or .installed_version=="")
+        or ( ((.latest_version|vnum) > (.installed_version|vnum))
+             and ( $autoup or ($n | IN($inuse[]) | not) ) ) );'
 
-                        PENDING_UPDATE=true
+        JQ_ARGS=(--argjson sub "$SUB" --argjson autoup "$AUTOUP" --argjson excluded "$EXCLUDED_JSON" --argjson inuse "$INUSE_JSON")
-                    else
-                        results=$(compare_versions "$latest_version" "$installed_version")
-                        if [ $results == "greater" ]; then
-                            {#- When auto_upgrade_integrations is false, skip upgrading in_use_integrations  #}
-                            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-                            if ! [[ " ${in_use_integrations[@]} " =~ " $package_name " ]]; then
-                            {%- endif %}
-                                echo "$package_name is at version $installed_version latest version is $latest_version... Adding to next update."
-                                jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
 
-                                PENDING_UPDATE=true
+        # (a) Per-package status messages (parity with the previous echo output).
-                            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
+        jq -r "${JQ_ARGS[@]}" "$JQ_DECISION"'
-                            else
+          .packages[]
-                                echo "skipping available upgrade for in use integration - $package_name."
+          | .name as $n
-                            fi
+          | if ($n|IN($excluded[])) then "Skipping \($n)..."
-                            {%- endif %}
+            elif (($sub|not) and (.subscription!=null and .subscription!="basic" and .subscription!="")) then
-                        fi
+                 "\($n) integration requires an Elastic license of \(.subscription) or greater... skipping"
-                    fi
+            elif (.installed_version==null or .installed_version=="") then
-                fi
+                 "\($n) is not installed... Adding to next update."
-            {% else %}
+            elif ((.latest_version|vnum) > (.installed_version|vnum)) then
-                if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
+                 (if ($autoup or ($n|IN($inuse[])|not))
-                    echo "$package_name is not installed... Adding to next update."
+                  then "\($n) is at version \(.installed_version) latest version is \(.latest_version)... Adding to next update."
-                    jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
+                  else "skipping available upgrade for in use integration - \($n)." end)
-                    PENDING_UPDATE=true
+            else empty end
-                else
+        ' "$INSTALLED_PACKAGE_LIST"
-                    results=$(compare_versions "$latest_version" "$installed_version")
+
-                    if [ $results == "greater" ]; then
+        # (b) The bulk install list, built in a single pass.
-                        {#- When auto_upgrade_integrations is false, skip upgrading in_use_integrations  #}
+        jq "${JQ_ARGS[@]}" "$JQ_DECISION"'
-                        {%- if not AUTO_UPGRADE_INTEGRATIONS %}
+          {packages: [ .packages[] | select(needs($sub;$autoup;$excluded;$inuse)) | {name, version: .latest_version} ]}
-                        if ! [[ " ${in_use_integrations[@]} " =~ " $package_name " ]]; then
+        ' "$INSTALLED_PACKAGE_LIST" > "$BULK_INSTALL_PACKAGE_LIST"
-                        {%- endif %}
+
-                            echo "$package_name is at version $installed_version latest version is $latest_version... Adding to next update."
+        if jq -e '.packages | length > 0' "$BULK_INSTALL_PACKAGE_LIST" >/dev/null; then
-                            jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
+            PENDING_UPDATE=true
-                            PENDING_UPDATE=true
+        fi
-                        {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-                        else
-                            echo "skipping available upgrade for in use integration - $package_name."
-                        fi
-                        {%- endif %}
-                    fi
-                fi
-            {% endif %}
-            else
-                echo "Skipping $package_name..."
-            fi
-        done <<< "$(jq -c '.packages[]' "$INSTALLED_PACKAGE_LIST")"
 
         if [ "$PENDING_UPDATE" = true ]; then
             # Run chunked install of packages
@@ -179,10 +140,13 @@ if [[ -f $STATE_FILE_SUCCESS  ]]; then
         else
             echo "Elastic integrations don't appear to need installation/updating..."
         fi
-        # Write out file for generating index/component/ilm templates
+        # Write out file for generating index/component/ilm templates, keeping each package type separate
-        if latest_installed_package_list=$(elastic_fleet_installed_packages); then
+        for package_type in "INTEGRATION" "INPUT" "CONTENT"; do
-            echo $latest_installed_package_list | jq '[.items[] | {name: .name, es_index_patterns: .dataStreams}]' > $PACKAGE_COMPONENTS
+            if latest_installed_package_list=$(elastic_fleet_installed_packages_components "$package_type"); then
-        fi
+                outfile="${package_type}_PACKAGE_COMPONENTS"
+                echo $latest_installed_package_list > "${!outfile}"
+            fi
+        done
         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

@@ -235,6 +235,16 @@ function update_kafka_outputs() {
 
 {% endif %}
 
+# Compare the current Elastic Fleet certificate against what is on disk
+POLICY_CERT_SHA=$(jq -r '.item.ssl.certificate' <<< $RAW_JSON | openssl x509 -noout -sha256 -fingerprint)
+DISK_CERT_SHA=$(openssl x509 -in /etc/pki/elasticfleet-logstash.crt -noout -sha256 -fingerprint)
+
+if [[ "$POLICY_CERT_SHA" != "$DISK_CERT_SHA" ]]; then
+    printf "Certificate on disk doesn't match certificate in policy - forcing update\n"
+    UPDATE_CERTS=true
+    FORCE_UPDATE=true
+fi
+
 # Sort & hash the new list of Logstash Outputs
 NEW_LIST_JSON=$(jq --compact-output --null-input '$ARGS.positional' --args -- "${NEW_LIST[@]}")
 NEW_HASH=$(sha256sum <<< "$NEW_LIST_JSON" | awk '{print $1}')

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

@@ -8,18 +8,74 @@
 
 . /usr/sbin/so-elastic-fleet-common
 
+PKG_LOAD_FAILURES=0
+PKG_LOAD_FAILURES_NAMES=()
+PKG_UPGRADED=0
+
+cleanup_elasticsearch_fleet_transforms() {
+    local transforms transform_id attempt
+    
+    if ! transforms=$(so-elasticsearch-query "_transform/logs-elasticsearch.index_pivot-default-*" --retry 1 --retry-delay 5); then
+        return 0
+    fi
+
+    while IFS= read -r transform_id; do
+        [ -n "$transform_id" ] || continue
+        for attempt in {1..3}; do
+            if so-elasticsearch-query "_transform/$transform_id?force=true" -XDELETE --fail --retry 1 --retry-delay 5; then
+                break
+            fi
+            sleep 5
+        done
+    done < <(jq -r '.transforms[]?.id' <<< "$transforms")
+}
+
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
-echo "Upgrading {{ PACKAGE }} package..."
+if INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
-if VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+
-    if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; then
+    if [ "$INSTALLED_VERSION" == "$LATEST_VERSION" ]; then
-        # exit 1 on failure to upgrade a default package, allow salt to handle retries
+        echo "{{ PACKAGE }} integration version $INSTALLED_VERSION is already at the reported latest version $LATEST_VERSION, skipping upgrade."
-        echo -e "\nERROR: Failed to upgrade $PACKAGE to version: $VERSION"
+    else
-        exit 1
+{%- if PACKAGE == 'elasticsearch' %}
+        cleanup_elasticsearch_fleet_transforms
+{%- endif %}
+        echo "Upgrading {{ PACKAGE }} package from $INSTALLED_VERSION to version $LATEST_VERSION..."
+        if ! elastic_fleet_package_install "{{ PACKAGE }}" "$LATEST_VERSION"; then
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        # check that package has upgraded to the expected version after install command
+        elif ! LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+            echo "ERROR: Failed to get latest version information for integration {{ PACKAGE }} after upgrade attempt"
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        elif INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && [ "$INSTALLED_VERSION" == "$LATEST_VERSION" ]; then
+            echo "{{ PACKAGE }} integration upgraded to version $LATEST_VERSION."
+            PKG_UPGRADED=$((PKG_UPGRADED + 1))
+        else
+            echo "ERROR: {{ PACKAGE }} integration still at ${INSTALLED_VERSION:-unknown}; expected $LATEST_VERSION"
+            PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+            PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
+        fi
     fi
 else
-    echo -e "\nERROR: Failed to get version information for integration $PACKAGE"
+    echo "ERROR: Failed to get version information for integration {{ PACKAGE }}"
+    PKG_LOAD_FAILURES=$((PKG_LOAD_FAILURES + 1))
+    PKG_LOAD_FAILURES_NAMES+=("{{ PACKAGE }}")
 fi
-echo
 {%- endfor %}
-echo
+
-/usr/sbin/so-elasticsearch-templates-load
+if [ $PKG_UPGRADED -gt 0 ]; then
+    echo "Elasticsearch template statefiles cleared after $PKG_UPGRADED package upgrade(s), so templates can reload."
+    rm -f /opt/so/state/estemplates.txt /opt/so/state/addon_estemplates.txt
+fi
+
+if [ $PKG_LOAD_FAILURES -gt 0 ]; then
+    echo "ERROR: Failed to upgrade $PKG_LOAD_FAILURES package(s):"
+    for PKG in "${PKG_LOAD_FAILURES_NAMES[@]}"; do
+        echo " - $PKG"
+    done
+    # exit 1 on failure to upgrade a default package, allow salt to handle retries
+    exit 1
+else
+    echo "Successfully upgraded all packages."
+fi

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

@@ -181,6 +181,9 @@ if ! elastic_fleet_policy_create "so-grid-nodes_heavy" "SO Grid Nodes - Heavy No
     exit 1
 fi
 
+# Check for package upgrades
+so-elastic-fleet-package-upgrade
+
 # Load Integrations for default policies
 so-elastic-fleet-integration-policy-load
 
@@ -199,26 +202,9 @@ fi
 ### Finalization ###
 
 # Query for Enrollment Tokens for default policies
-if ENDPOINTSENROLLMENTOKEN_RAW=$(fleet_api "enrollment_api_keys" -H 'kbn-xsrf: true' -H 'Content-Type: application/json'); then
+ENDPOINTSENROLLMENTOKEN=$(elastic_fleet_active_enrollment_token "endpoints-initial") || exit 1
-    ENDPOINTSENROLLMENTOKEN=$(echo "$ENDPOINTSENROLLMENTOKEN_RAW" | jq .list | jq -r -c '.[] | select(.policy_id | contains("endpoints-initial")) | .api_key')
+GRIDNODESENROLLMENTOKENGENERAL=$(elastic_fleet_active_enrollment_token "so-grid-nodes_general") || exit 1
-else
+GRIDNODESENROLLMENTOKENHEAVY=$(elastic_fleet_active_enrollment_token "so-grid-nodes_heavy") || exit 1
-    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
@@ -241,11 +227,37 @@ printf '%s\n'\
     "" >> "$global_pillar_file"
 
 # Call Elastic-Fleet Salt State
-printf "\nApplying elasticfleet state"
+printf "\nApplying elasticfleet state\n"
-salt-call state.apply elasticfleet queue=True
+for state_attempt in {1..3}; do
+    if salt-call state.apply elasticfleet queue=True; then
+        break
+    elif [[ $state_attempt -lt 3 ]]; then
+        printf "\nElasticfleet state did not complete successfully... Attempt (%s/3). Retrying...\n" "$state_attempt"
+        sleep 10
+    else
+        printf "\nFailure(s) in elasticfleet state... Exiting...\n"
+        exit 1
+    fi
+done
 
+printf "\nRunning so-elastic-agent-gen-installers\n"
 # Generate installers & install Elastic Agent on the node
-so-elastic-agent-gen-installers
+for agent_gen_attempt in {1..3}; do
-printf "\nApplying elasticfleet.install_agent_grid state"
+    if so-elastic-agent-gen-installers; then
-salt-call state.apply elasticfleet.install_agent_grid queue=True
+        break
-exit 0
+    elif [[ $agent_gen_attempt -lt 3 ]]; then
+        printf "\nUnable to generate Elastic Agent installers... Attempt (%s/3). Retrying...\n" "$agent_gen_attempt"
+        sleep 10
+    else
+        printf "\nFailed to generate Elastic Agent installers after 3 attempts. Exiting...\n"
+        exit 1
+    fi
+done
+
+printf "\nApplying elasticfleet.install_agent_grid state\n"
+if ! salt-call state.apply elasticfleet.install_agent_grid queue=True; then
+    printf "\nFailure(s) in elasticfleet.install_agent_grid state... Exiting...\n"
+    exit 1
+fi
+
+printf "\nElastic Fleet setup completed successfully\n"

salt/elasticsearch/cluster.sls

@@ -0,0 +1,201 @@
+# 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 'allowed_states.map.jinja' import allowed_states %}
+{% if sls in allowed_states %}
+{%   from 'vars/globals.map.jinja' import GLOBALS %}
+{%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
+{%   from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS, SO_MANAGED_INDICES %}
+{%   if GLOBALS.role != 'so-heavynode' %}
+{%     from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS, ADDON_INDICES %}
+{%   endif %}
+
+include:
+  - elasticsearch.enabled
+
+escomponenttemplates:
+  file.recurse:
+    - name: /opt/so/conf/elasticsearch/templates/component
+    - source: salt://elasticsearch/templates/component
+    - user: 930
+    - group: 939
+    - clean: True
+    - onchanges_in:
+      - file: so-elasticsearch-templates-reload
+    - show_changes: False
+
+# Clean up legacy and non-SO managed templates from the elasticsearch/templates/index/ directory
+so_index_template_dir:
+  file.directory:
+    - name: /opt/so/conf/elasticsearch/templates/index
+    - clean: True
+    {%- if SO_MANAGED_INDICES %}
+    - require:
+      {%- for index in SO_MANAGED_INDICES %}
+      - file: so_index_template_{{index}}
+      {%- endfor %}
+    {%- endif %}
+
+{%  if GLOBALS.role != "so-heavynode" %}
+# Clean up legacy and non-SO managed templates from the elasticsearch/templates/addon-index/ directory
+addon_index_template_dir:
+  file.directory:
+    - name: /opt/so/conf/elasticsearch/templates/addon-index
+    - clean: True
+    {%- if ADDON_INDICES %}
+    - require:
+      {%- for index in ADDON_INDICES %}
+      - file: addon_index_template_{{index}}
+      {%- endfor %}
+    {%- endif %}
+{%  endif %}
+
+# Auto-generate index templates for SO managed indices (directly defined in elasticsearch/defaults.yaml)
+#   These index templates are for the core SO datasets and are always required
+{%  for index, settings in ES_INDEX_SETTINGS.items() %}
+{%    if settings.index_template is defined %}
+so_index_template_{{index}}:
+  file.managed:
+    - name: /opt/so/conf/elasticsearch/templates/index/{{ index }}-template.json
+    - source: salt://elasticsearch/base-template.json.jinja
+    - defaults:
+        TEMPLATE_CONFIG: {{ settings.index_template }}
+    - template: jinja
+    - onchanges_in:
+      - file: so-elasticsearch-templates-reload
+{%    endif %}
+{%  endfor %}
+
+{%  if GLOBALS.role != "so-heavynode" %}
+# Auto-generate optional index templates for integration | input | content packages
+#   These index templates are not used by default (until user adds package to an agent policy).
+#   Pre-configured with standard defaults, and incorporated into SOC configuration for user customization.
+{%    for index,settings in ALL_ADDON_SETTINGS.items() %}
+{%      if settings.index_template is defined %}
+addon_index_template_{{index}}:
+  file.managed:
+    - name: /opt/so/conf/elasticsearch/templates/addon-index/{{ index }}-template.json
+    - source: salt://elasticsearch/base-template.json.jinja
+    - defaults:
+        TEMPLATE_CONFIG: {{ settings.index_template }}
+    - template: jinja
+    - show_changes: False
+    - onchanges_in:
+      - file: addon-elasticsearch-templates-reload
+{%       endif %}
+{%     endfor %}
+{%   endif %}
+
+{%  if GLOBALS.role in GLOBALS.manager_roles %}
+so-es-cluster-settings:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-cluster-settings
+    - cwd: /opt/so
+    - template: jinja
+    - require:
+      - docker_container: so-elasticsearch
+      - file: elasticsearch_sbin_jinja
+      - http: wait_for_so-elasticsearch
+
+so-elasticsearch-system-indices-patch:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-system-indices-patch
+    - require:
+      - http: wait_for_so-elasticsearch
+      - file: so-elasticsearch-system-indices-patch-script
+{%  endif %}
+
+# heavynodes will only load ILM policies for SO managed indices. (Indicies defined in elasticsearch/defaults.yaml)
+so-elasticsearch-ilm-policy-load:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-ilm-policy-load
+    - cwd: /opt/so
+    - require:
+      - docker_container: so-elasticsearch
+      - file: so-elasticsearch-ilm-policy-load-script
+    - onchanges:
+      - file: so-elasticsearch-ilm-policy-load-script
+
+so-elasticsearch-templates-reload:
+  file.absent:
+    - name: /opt/so/state/estemplates.txt
+
+addon-elasticsearch-templates-reload:
+  file.absent:
+    - name: /opt/so/state/addon_estemplates.txt
+
+# so-elasticsearch-templates-load will have its first successful run during the 'so-elastic-fleet-setup' script
+so-elasticsearch-templates:
+  cmd.run:
+{%-  if GLOBALS.role == "so-heavynode" %}
+    - name: /usr/sbin/so-elasticsearch-templates-load --heavynode
+{%-  else %}
+    - name: /usr/sbin/so-elasticsearch-templates-load
+{%-  endif %}
+    - cwd: /opt/so
+    - template: jinja
+    - require:
+      - docker_container: so-elasticsearch
+      - file: elasticsearch_sbin_jinja
+
+so-elasticsearch-dlm-apply:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-dlm-apply
+    - cwd: /opt/so
+    - require:
+      - docker_container: so-elasticsearch
+      - file: elasticsearch_sbin_jinja
+      - cmd: so-elasticsearch-templates
+    - retry:
+        attempts: 3
+        interval: 10
+
+so-elasticsearch-pipelines:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-pipelines {{ GLOBALS.hostname }}
+    - require:
+      - docker_container: so-elasticsearch
+      - file: so-elasticsearch-pipelines-script
+
+so-elasticsearch-roles-load:
+  cmd.run:
+    - name: /usr/sbin/so-elasticsearch-roles-load
+    - cwd: /opt/so
+    - template: jinja
+    - require:
+      - docker_container: so-elasticsearch
+      - file: elasticsearch_sbin_jinja
+
+{%  if grains.role in ['so-managersearch', 'so-manager', 'so-managerhype'] %}
+{%    set ap = "absent" %}
+{%  endif %}
+{%  if grains.role in ['so-eval', 'so-standalone', 'so-heavynode'] %}
+{#    Remove so-elasticsearch-indices-delete script when using DLM #}
+{%    if ELASTICSEARCHMERGED.index_clean and ELASTICSEARCHMERGED.data_retention_method == "ILM" %}
+{%      set ap = "present" %}
+{%    else %}
+{%      set ap = "absent" %}
+{%    endif %}
+{%  endif %}
+{%  if grains.role in ['so-eval', 'so-standalone', 'so-managersearch', 'so-heavynode', 'so-manager'] %}
+so-elasticsearch-indices-delete:
+  cron.{{ap}}:
+    - name: /usr/sbin/so-elasticsearch-indices-delete > /opt/so/log/elasticsearch/cron-elasticsearch-indices-delete.log 2>&1
+    - identifier: so-elasticsearch-indices-delete
+    - user: root
+    - minute: '*/5'
+    - hour: '*'
+    - daymonth: '*'
+    - month: '*'
+    - dayweek: '*'
+{%  endif %}
+
+{% else %}
+
+{{sls}}_state_not_allowed:
+  test.fail_without_changes:
+    - name: {{sls}}_state_not_allowed
+
+{% endif %}

salt/elasticsearch/config.sls

@@ -32,24 +32,35 @@ elasticsearch:
     - gid: 930
     - home: /opt/so/conf/elasticsearch
     - createhome: False
+    - shell: /sbin/nologin
 
 elasticsearch_sbin:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin
-    - user: 930
+    - user: root
-    - group: 939
+    - group: root
     - file_mode: 755
     - exclude_pat:
       - so-elasticsearch-pipelines # exclude this because we need to watch it for changes, we sync it in another state
+      - so-elasticsearch-system-indices-patch
+    - show_changes: False
+
+so-elasticsearch-system-indices-patch-script:
+  file.managed:
+    - name: /usr/sbin/so-elasticsearch-system-indices-patch
+    - source: salt://elasticsearch/tools/sbin/so-elasticsearch-system-indices-patch
+    - user: root
+    - group: root
+    - mode: 755
     - show_changes: False
 
 elasticsearch_sbin_jinja:
   file.recurse:
     - name: /usr/sbin
     - source: salt://elasticsearch/tools/sbin_jinja
-    - user: 939
+    - user: root
-    - group: 939 
+    - group: root
     - file_mode: 755
     - template: jinja
     - exclude_pat:
@@ -62,18 +73,20 @@ so-elasticsearch-ilm-policy-load-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-ilm-policy-load
     - source: salt://elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load
-    - user: 930
+    - user: root
-    - group: 939
+    - group: root
     - mode: 754
     - template: jinja
+    - defaults:
+        GLOBALS: {{ GLOBALS }}
     - show_changes: False
 
 so-elasticsearch-pipelines-script:
   file.managed:
     - name: /usr/sbin/so-elasticsearch-pipelines
     - source: salt://elasticsearch/tools/sbin/so-elasticsearch-pipelines
-    - user: 930
+    - user: root
-    - group: 939
+    - group: root
     - mode: 754
     - show_changes: False
 
@@ -91,6 +104,13 @@ estemplatedir:
     - group: 939
     - makedirs: True
 
+esaddontemplatedir:
+  file.directory:
+    - name: /opt/so/conf/elasticsearch/templates/addon-index
+    - user: 930
+    - group: 939
+    - makedirs: True
+
 esrolesdir:
   file.directory:
     - name: /opt/so/conf/elasticsearch/roles

salt/elasticsearch/enabled.sls

@@ -10,8 +10,6 @@
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCH_NODES %}
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCH_SEED_HOSTS %}
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
-{%   set TEMPLATES = salt['pillar.get']('elasticsearch:templates', {}) %}
-{%   from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS %}
 
 include:
   - ca
@@ -19,10 +17,14 @@ include:
   - elasticsearch.ssl
   - elasticsearch.config
   - elasticsearch.sostatus
+{%- if GLOBALS.role != "so-searchnode" %}
+  - elasticsearch.cluster
+{%- endif%}
 
 so-elasticsearch:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-elasticsearch:{{ ELASTICSEARCHMERGED.version }}
+    - restart_policy: unless-stopped
     - hostname: elasticsearch
     - name: so-elasticsearch
     - user: elasticsearch
@@ -101,134 +103,24 @@ so-elasticsearch:
       - cmd: auth_users_roles_inode
       - cmd: auth_users_inode
 
+wait_for_so-elasticsearch:
+  http.wait_for_successful_query:
+    - name: "https://localhost:9200/"
+    - username: 'so_elastic'
+    - password: '{{ ELASTICSEARCHMERGED.auth.users.so_elastic_user.pass }}'
+    - ssl: True
+    - verify_ssl: False
+    - status: 200
+    - wait_for: 300
+    - request_interval: 15
+    - require:
+      - docker_container: so-elasticsearch
+
 delete_so-elasticsearch_so-status.disabled:
   file.uncomment:
     - name: /opt/so/conf/so-status/so-status.conf
     - regex: ^so-elasticsearch$
 
-{%   if GLOBALS.role != "so-searchnode" %}
-escomponenttemplates:
-  file.recurse:
-    - name: /opt/so/conf/elasticsearch/templates/component
-    - source: salt://elasticsearch/templates/component
-    - user: 930
-    - group: 939
-    - clean: True
-    - onchanges_in:
-      - file: so-elasticsearch-templates-reload
-    - show_changes: False
-      
-# Auto-generate templates from defaults file
-{%     for index, settings in ES_INDEX_SETTINGS.items() %}
- {%      if settings.index_template is defined %}
-es_index_template_{{index}}:
-  file.managed:
-    - name: /opt/so/conf/elasticsearch/templates/index/{{ index }}-template.json
-    - source: salt://elasticsearch/base-template.json.jinja
-    - defaults:
-      TEMPLATE_CONFIG: {{ settings.index_template }}
-    - template: jinja
-    - show_changes: False
-    - onchanges_in:
-      - file: so-elasticsearch-templates-reload
-{%       endif %}
-{%     endfor %}
-
-{%     if TEMPLATES %}
-# Sync custom templates to /opt/so/conf/elasticsearch/templates
-{%       for TEMPLATE in TEMPLATES %}
-es_template_{{TEMPLATE.split('.')[0] | replace("/","_") }}:
-  file.managed:
-    - source: salt://elasticsearch/templates/index/{{TEMPLATE}}
-{%         if 'jinja' in TEMPLATE.split('.')[-1] %}
-    - name: /opt/so/conf/elasticsearch/templates/index/{{TEMPLATE.split('/')[1] | replace(".jinja", "")}}
-    - template: jinja
-{%         else %}
-    - name: /opt/so/conf/elasticsearch/templates/index/{{TEMPLATE.split('/')[1]}}
-{%         endif %}
-    - user: 930
-    - group: 939
-    - show_changes: False
-    - onchanges_in:
-      - file: so-elasticsearch-templates-reload
-{%       endfor %}
-{%     endif %}
-
-{%     if GLOBALS.role in GLOBALS.manager_roles %}
-so-es-cluster-settings:
-  cmd.run:
-    - name: /usr/sbin/so-elasticsearch-cluster-settings
-    - cwd: /opt/so
-    - template: jinja
-    - require:
-      - docker_container: so-elasticsearch
-      - file: elasticsearch_sbin_jinja
-{%     endif %}
-
-so-elasticsearch-ilm-policy-load:
-  cmd.run:
-    - name: /usr/sbin/so-elasticsearch-ilm-policy-load
-    - cwd: /opt/so
-    - require:
-      - docker_container: so-elasticsearch
-      - file: so-elasticsearch-ilm-policy-load-script
-    - onchanges:
-      - file: so-elasticsearch-ilm-policy-load-script
-
-so-elasticsearch-templates-reload:
-  file.absent:
-    - name: /opt/so/state/estemplates.txt
-
-so-elasticsearch-templates:
-  cmd.run:
-    - name: /usr/sbin/so-elasticsearch-templates-load
-    - cwd: /opt/so
-    - template: jinja
-    - require:
-      - docker_container: so-elasticsearch
-      - file: elasticsearch_sbin_jinja
-
-so-elasticsearch-pipelines:
-  cmd.run:
-    - name: /usr/sbin/so-elasticsearch-pipelines {{ GLOBALS.hostname }}
-    - require:
-      - docker_container: so-elasticsearch
-      - file: so-elasticsearch-pipelines-script
-
-so-elasticsearch-roles-load:
-  cmd.run:
-    - name: /usr/sbin/so-elasticsearch-roles-load
-    - cwd: /opt/so
-    - template: jinja
-    - require:
-      - docker_container: so-elasticsearch
-      - file: elasticsearch_sbin_jinja
-
-{%     if grains.role in ['so-managersearch', 'so-manager', 'so-managerhype'] %}
-{%       set ap = "absent" %}
-{%     endif %}
-{%     if grains.role in ['so-eval', 'so-standalone', 'so-heavynode'] %}
-{%       if ELASTICSEARCHMERGED.index_clean %}
-{%         set ap = "present" %}
-{%       else %}
-{%         set ap = "absent" %}
-{%       endif %}
-{%     endif %}  
-{%     if grains.role in ['so-eval', 'so-standalone', 'so-managersearch', 'so-heavynode', 'so-manager'] %}
-so-elasticsearch-indices-delete:
-  cron.{{ap}}:
-    - name: /usr/sbin/so-elasticsearch-indices-delete > /opt/so/log/elasticsearch/cron-elasticsearch-indices-delete.log 2>&1
-    - identifier: so-elasticsearch-indices-delete
-    - user: root
-    - minute: '*/5'
-    - hour: '*'
-    - daymonth: '*'
-    - month: '*'
-    - dayweek: '*'
-{%     endif %}
-
-{%   endif %}
-
 {% else %}
 
 {{sls}}_state_not_allowed:

salt/elasticsearch/files/ingest/common

@@ -63,7 +63,8 @@
     { "set":             { "if": "ctx.event?.dataset != null && !ctx.event.dataset.contains('.')", "field": "event.dataset", "value": "{{event.module}}.{{event.dataset}}" } },
     { "split":           { "if": "ctx.event?.dataset != null && ctx.event.dataset.contains('.')", "field": "event.dataset", "separator": "\\.", "target_field": "dataset_tag_temp" } },
     { "append":          { "if": "ctx.dataset_tag_temp != null", "field": "tags", "value": "{{dataset_tag_temp.1}}"  } },
-    { "grok":            { "if": "ctx.http?.response?.status_code != null", "field": "http.response.status_code", "patterns": ["%{NUMBER:http.response.status_code:long} %{GREEDYDATA}"]} },
+    { "grok":            { "if": "ctx.http?.response?.status_code instanceof String", "field": "http.response.status_code", "patterns": ["%{NUMBER:http.response.status_code:long}(?:\\s+%{GREEDYDATA})?"], "ignore_failure": true } },
+    { "convert":         { "if": "ctx.http?.response?.status_code != null && !(ctx.http.response.status_code instanceof Number)", "field": "http.response.status_code", "type": "long", "ignore_failure": true } },
     { "set":             { "if": "ctx?.metadata?.kafka != null" , "field": "kafka.id", "value": "{{metadata.kafka.partition}}{{metadata.kafka.offset}}{{metadata.kafka.timestamp}}", "ignore_failure": true } },
     { "remove":          { "field": [ "message2", "type", "fields", "category", "module", "dataset", "dataset_tag_temp", "event.dataset_temp" ], "ignore_missing": true, "ignore_failure": true } },
     { "pipeline": { "name": "global@custom", "ignore_missing_pipeline": true, "description": "[Fleet] Global pipeline for all data streams" } }

salt/elasticsearch/files/ingest/global@custom

@@ -1,5 +1,5 @@
 {
-    "version": 3,
+    "version": 4,
     "_meta": {
         "managed_by": "securityonion",
         "managed": true
@@ -99,7 +99,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import')",
+                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
                 "override": true,
                 "field": "data_stream.dataset",
                 "value": "import"
@@ -107,7 +107,7 @@
         },
         {
             "set": {
-                "if": "ctx.tags != null && ctx.tags.contains('import')",
+                "if": "ctx.tags != null && ctx.tags.contains('import') && ctx._index != null && ctx._index.startsWith('logs-import-')",
                 "override": true,
                 "field": "data_stream.namespace",
                 "value": "so"
@@ -177,12 +177,110 @@
                 "description": "Extract IPs from Elastic Agent events (host.ip) and adds them to related.ip"
             }
         },
+        {
+            "trim": {
+                "if": "ctx.event?.dataset == 'system.auth'",
+                "description": "Grok leaves a leading space on 'invalid user' names (elastic/integrations#12174) and, before 2.23.2, sudo padding",
+                "field": "user.name",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "trim": {
+                "if": "ctx.event?.dataset == 'system.auth'",
+                "description": "Appended from the untrimmed user.name",
+                "field": "related.user",
+                "ignore_missing": true,
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "if": "ctx.event?.dataset == 'system.auth' && ctx.related?.user instanceof List",
+                "description": "Dedupe after trimming",
+                "source": "ctx.related.user = new ArrayList(new LinkedHashSet(ctx.related.user));",
+                "ignore_failure": true
+            }
+        },
+        {
+            "script": {
+                "description": "Snapshot event.ingested into _tmp.event_ingested_pre_fleet before .fleet_final_pipeline-1 overwrites it with ES ingest time",
+                "lang": "painless",
+                "if": "ctx.event?.ingested != null && ctx.event?.created == null",
+                "ignore_failure": true,
+                "source": "ctx.putIfAbsent('_tmp', [:]); ctx._tmp.event_ingested_pre_fleet = ctx.event.ingested;"
+            }
+        },
         {
             "pipeline": {
                 "name": ".fleet_final_pipeline-1",
                 "ignore_missing_pipeline": true
             }
         },
+        {
+            "script": {
+                "description": "Calculate time from Elastic Agent to Logstash.",
+                "lang": "painless",
+                "if": "ctx._tmp?.logstash_from_agent != null",
+                "ignore_failure": true,
+                "source": "ZonedDateTime start = ctx._tmp.event_ingested_pre_fleet != null ? ZonedDateTime.parse(ctx._tmp.event_ingested_pre_fleet) : ZonedDateTime.parse(ctx['@timestamp']); ctx.event.putIfAbsent('ingestion', [:]); ctx.event.ingestion.latency_elasticagent_to_logstash = ChronoUnit.SECONDS.between(start, ZonedDateTime.parse(ctx._tmp.logstash_from_agent));"
+            }
+        },
+        {
+            "script": {
+                "description": "Calculate time from Logstash to Redis",
+                "lang": "painless",
+                "if": "ctx._tmp?.logstash_from_agent != null && ctx._tmp?.logstash_to_redis != null",
+                "ignore_failure": true,
+                "source": "ctx.event.putIfAbsent('ingestion', [:]); ctx.event.ingestion.latency_logstash_to_redis = ChronoUnit.SECONDS.between(ZonedDateTime.parse(ctx._tmp.logstash_from_agent), ZonedDateTime.parse(ctx._tmp.logstash_to_redis));"
+            }
+        },
+        {
+            "script": {
+                "description": "Calculate time message spends in redis queue (logstash delay in pulling event).",
+                "lang": "painless",
+                "if": "ctx._tmp?.logstash_to_redis != null && ctx._tmp?.logstash_from_redis != null",
+                "ignore_failure": true,
+                "source": "ctx.event.putIfAbsent('ingestion', [:]); ctx.event.ingestion.latency_redis_to_logstash = ChronoUnit.SECONDS.between(ZonedDateTime.parse(ctx._tmp.logstash_to_redis), ZonedDateTime.parse(ctx._tmp.logstash_from_redis));"
+            }
+        },
+        {
+            "script": {
+                "description": "Calculate time from Logstash to Elasticsearch (after read from Redis).",
+                "lang": "painless",
+                "if": "ctx._tmp?.logstash_from_redis != null",
+                "ignore_failure": true,
+                "source": "ctx.event.putIfAbsent('ingestion', [:]); ctx.event.ingestion.latency_logstash_to_elasticsearch = ChronoUnit.SECONDS.between(ZonedDateTime.parse(ctx._tmp.logstash_from_redis), metadata().now);"
+            }
+        },
+        {
+            "script": {
+                "description": "Calculate time from Elastic Agent to Kafka.",
+                "lang": "painless",
+                "if": "ctx._tmp?.logstash_from_kafka != null && ctx._tmp?.logstash_from_agent == null",
+                "ignore_failure": true,
+                "source": "ZonedDateTime start = ctx._tmp.event_ingested_pre_fleet != null ? ZonedDateTime.parse(ctx._tmp.event_ingested_pre_fleet) : ZonedDateTime.parse(ctx['@timestamp']); ctx.event.putIfAbsent('ingestion', [:]); ctx.event.ingestion.latency_elasticagent_to_kafka = ChronoUnit.SECONDS.between(start, ZonedDateTime.parse(ctx._tmp.logstash_from_kafka));"
+            }
+        },
+        {
+            "script": {
+                "description": "Calculate time message spends in Kafka queue (logstash delay in pulling event).",
+                "lang": "painless",
+                "if": "ctx._tmp?.logstash_from_kafka != null && ctx.metadata?.kafka?.timestamp != null && ctx._tmp?.logstash_from_agent == null",
+                "ignore_failure": true,
+                "source": "ctx.event.putIfAbsent('ingestion', [:]); ctx.event.ingestion.latency_kafka_queue = ChronoUnit.SECONDS.between(ZonedDateTime.ofInstant(Instant.ofEpochMilli(Long.parseLong(ctx.metadata.kafka.timestamp.toString())), ZoneId.of('UTC')), ZonedDateTime.parse(ctx._tmp.logstash_from_kafka));"
+            }
+        },
+        {
+            "script": {
+                "description": "Calculate time from Logstash to Elasticsearch (after read from Kafka).",
+                "lang": "painless",
+                "if": "ctx._tmp?.logstash_from_kafka != null && ctx._tmp?.logstash_from_agent == null",
+                "ignore_failure": true,
+                "source": "ctx.event.putIfAbsent('ingestion', [:]); ctx.event.ingestion.latency_kafka_to_elasticsearch = ChronoUnit.SECONDS.between(ZonedDateTime.parse(ctx._tmp.logstash_from_kafka), metadata().now);"
+            }
+        },
         {
             "remove": {
                 "field": "event.agent_id_status",
@@ -202,7 +300,8 @@
                     "event.dataset_temp",
                     "dataset_tag_temp",
                     "module_temp",
-                    "datastream_dataset_temp"
+                    "datastream_dataset_temp",
+                    "_tmp"
                 ],
                 "ignore_missing": true,
                 "ignore_failure": true

salt/elasticsearch/files/ingest/import.evtx

@@ -0,0 +1,31 @@
+{
+  "description" : "import.evtx: normalize imported EVTX and reroute to logs-<dataset>-import",
+  "processors" : [
+    { "script":  {
+        "description": "Host from the event, not the importing node",
+        "lang": "painless",
+        "source": "Map host = ['os': ['type': 'windows', 'family': 'windows', 'platform': 'windows']]; def cn = ctx.winlog?.computer_name; if (cn != null && cn.toString().length() > 0) { String name = cn.toString(); int dot = name.indexOf('.'); if (dot > 0) { name = name.substring(0, dot); } host.put('hostname', name); host.put('name', name.toLowerCase()); } ctx.host = host;"
+    } },
+    { "script":  {
+        "description": "String event IDs, as Winlogbeat sends",
+        "lang": "painless",
+        "source": "if (ctx.winlog?.event_id != null) { ctx.winlog.event_id = ctx.winlog.event_id.toString(); } if (ctx.event?.code != null) { ctx.event.code = ctx.event.code.toString(); }"
+    } },
+    { "script":  {
+        "description": "Unnamed <Data> to param1..N, as Winlogbeat",
+        "lang": "painless",
+        "if": "ctx.winlog?.event_data?.Data instanceof Map && ctx.winlog.event_data.Data['#text'] != null",
+        "source": "def t = ctx.winlog.event_data.Data['#text']; List vals = t instanceof List ? t : [t]; for (int i = 0; i < vals.size(); i++) { ctx.winlog.event_data['param' + (i + 1)] = vals.get(i); } ctx.winlog.event_data.remove('Data');"
+    } },
+    { "script":  {
+        "description": "String values and LF line endings, as Winlogbeat",
+        "lang": "painless",
+        "if": "ctx.winlog?.event_data instanceof Map || ctx.winlog?.user_data instanceof Map",
+        "source": "String lf = String.valueOf((char) 10); String crlf = String.valueOf((char) 13) + lf; for (def key : ['event_data', 'user_data']) { def m = ctx.winlog[key]; if (!(m instanceof Map)) { continue; } for (def e : m.entrySet()) { def v = e.getValue(); if (v instanceof String) { e.setValue(v.replace(crlf, lf)); } else if (v instanceof Number || v instanceof Boolean) { e.setValue(v.toString()); } } }"
+    } },
+    { "set":     { "description": "event.kind, as Winlogbeat", "field": "event.kind", "value": "event", "override": false } },
+    { "set":     { "field": "data_stream.dataset", "copy_from": "event.dataset", "override": true, "ignore_empty_value": true } },
+    { "set":     { "field": "data_stream.namespace", "value": "import", "override": true } },
+    { "reroute": { "dataset": "{{data_stream.dataset}}", "namespace": "{{data_stream.namespace}}" } }
+  ]
+}

salt/elasticsearch/files/ingest/logs-pfsense.log-1.25.4

@@ -10,24 +10,28 @@
   "processors": [
     {
       "set": {
+        "tag": "set_ecs_version_f5923549",
         "field": "ecs.version",
         "value": "8.17.0"
       }
     },
     {
       "set": {
+        "tag": "set_observer_vendor_ad9d35cc",
         "field": "observer.vendor",
         "value": "netgate"
       }
     },
     {
       "set": {
+        "tag": "set_observer_type_5dddf3ba",
         "field": "observer.type",
         "value": "firewall"
       }
     },
     {
       "rename": {
+        "tag": "rename_message_to_event_original_56a77271",
         "field": "message",
         "target_field": "event.original",
         "ignore_missing": true,
@@ -36,12 +40,14 @@
     },
     {
       "set": {
+        "tag": "set_event_kind_de80643c",
         "field": "event.kind",
         "value": "event"
       }
     },
     {
       "set": {
+        "tag": "set_event_timezone_4ca44cac",
         "field": "event.timezone",
         "value": "{{{_tmp.tz_offset}}}",
         "if": "ctx._tmp?.tz_offset != null && ctx._tmp?.tz_offset != 'local'"
@@ -49,6 +55,7 @@
     },
     {
       "grok": {
+        "tag": "grok_event_original_27d9c8c7",
         "description": "Parse syslog header",
         "field": "event.original",
         "patterns": [
@@ -72,6 +79,7 @@
     },
     {
       "date": {
+        "tag": "date__tmp_timestamp8601_to_timestamp_6ac9d3ce",
         "if": "ctx._tmp.timestamp8601 != null",
         "field": "_tmp.timestamp8601",
         "target_field": "@timestamp",
@@ -82,6 +90,7 @@
     },
     {
       "date": {
+        "tag": "date__tmp_timestamp_to_timestamp_f21e536e",
         "if": "ctx.event?.timezone != null && ctx._tmp?.timestamp != null",
         "field": "_tmp.timestamp",
         "target_field": "@timestamp",
@@ -95,6 +104,7 @@
     },
     {
       "grok": {
+        "tag": "grok_process_name_cef3d489",
         "description": "Set Event Provider",
         "field": "process.name",
         "patterns": [
@@ -107,71 +117,83 @@
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-firewall",
+        "tag": "pipeline_e16851a7",
+        "name": "logs-pfsense.log-1.25.4-firewall",
         "if": "ctx.event.provider == 'filterlog'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-openvpn",
+        "tag": "pipeline_828590b5",
+        "name": "logs-pfsense.log-1.25.4-openvpn",
         "if": "ctx.event.provider == 'openvpn'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-ipsec",
+        "tag": "pipeline_9d37039c",
+        "name": "logs-pfsense.log-1.25.4-ipsec",
         "if": "ctx.event.provider == 'charon'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-dhcp",
+        "tag": "pipeline_ad56bbca",
-        "if": "[\"dhcpd\", \"dhclient\", \"dhcp6c\"].contains(ctx.event.provider)"
+        "name": "logs-pfsense.log-1.25.4-dhcp",
+        "if": "[\"dhcpd\", \"dhclient\", \"dhcp6c\", \"dnsmasq-dhcp\"].contains(ctx.event.provider)"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-unbound",
+        "tag": "pipeline_dd85553d",
+        "name": "logs-pfsense.log-1.25.4-unbound",
         "if": "ctx.event.provider == 'unbound'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-haproxy",
+        "tag": "pipeline_720ed255",
+        "name": "logs-pfsense.log-1.25.4-haproxy",
         "if": "ctx.event.provider == 'haproxy'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-php-fpm",
+        "tag": "pipeline_456beba5",
+        "name": "logs-pfsense.log-1.25.4-php-fpm",
         "if": "ctx.event.provider == 'php-fpm'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-squid",
+        "tag": "pipeline_a0d89375",
+        "name": "logs-pfsense.log-1.25.4-squid",
         "if": "ctx.event.provider == 'squid'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-snort",
+        "tag": "pipeline_c2f1ed55",
+        "name": "logs-pfsense.log-1.25.4-snort",
         "if": "ctx.event.provider == 'snort'"
       }
     },
     {
       "pipeline": {
-        "name": "logs-pfsense.log-1.23.1-suricata",
+        "tag":"pipeline_33db1c9e",
+        "name": "logs-pfsense.log-1.25.4-suricata",
         "if": "ctx.event.provider == 'suricata'"
       }
     },
     {
       "drop": {
-        "if": "![\"filterlog\", \"openvpn\", \"charon\", \"dhcpd\", \"dhclient\", \"dhcp6c\", \"unbound\", \"haproxy\", \"php-fpm\", \"squid\", \"snort\", \"suricata\"].contains(ctx.event?.provider)"
+        "tag": "drop_9d7c46f8",
+        "if": "![\"filterlog\", \"openvpn\", \"charon\", \"dhcpd\", \"dnsmasq-dhcp\", \"dhclient\", \"dhcp6c\", \"unbound\", \"haproxy\", \"php-fpm\", \"squid\", \"snort\", \"suricata\"].contains(ctx.event?.provider)"
       }
     },
     {
       "append": {
+        "tag": "append_event_category_4780a983",
         "field": "event.category",
         "value": "network",
         "if": "ctx.network != null"
@@ -179,6 +201,7 @@
     },
     {
       "convert": {
+        "tag": "convert_source_address_to_source_ip_f5632a20",
         "field": "source.address",
         "target_field": "source.ip",
         "type": "ip",
@@ -188,6 +211,7 @@
     },
     {
       "convert": {
+        "tag": "convert_destination_address_to_destination_ip_f1388f0c",
         "field": "destination.address",
         "target_field": "destination.ip",
         "type": "ip",
@@ -197,6 +221,7 @@
     },
     {
       "set": {
+        "tag": "set_network_type_1f1d940a",
         "field": "network.type",
         "value": "ipv6",
         "if": "ctx.source?.ip != null && ctx.source.ip.contains(\":\")"
@@ -204,6 +229,7 @@
     },
     {
       "set": {
+        "tag": "set_network_type_69deca38",
         "field": "network.type",
         "value": "ipv4",
         "if": "ctx.source?.ip != null && ctx.source.ip.contains(\".\")"
@@ -211,6 +237,7 @@
     },
     {
       "geoip": {
+        "tag": "geoip_source_ip_to_source_geo_da2e41b2",
         "field": "source.ip",
         "target_field": "source.geo",
         "ignore_missing": true
@@ -218,6 +245,7 @@
     },
     {
       "geoip": {
+        "tag": "geoip_destination_ip_to_destination_geo_ab5e2968",
         "field": "destination.ip",
         "target_field": "destination.geo",
         "ignore_missing": true
@@ -225,6 +253,7 @@
     },
     {
       "geoip": {
+        "tag": "geoip_source_ip_to_source_as_28d69883",
         "ignore_missing": true,
         "database_file": "GeoLite2-ASN.mmdb",
         "field": "source.ip",
@@ -237,6 +266,7 @@
     },
     {
       "geoip": {
+        "tag": "geoip_destination_ip_to_destination_as_8a007787",
         "database_file": "GeoLite2-ASN.mmdb",
         "field": "destination.ip",
         "target_field": "destination.as",
@@ -249,6 +279,7 @@
     },
     {
       "rename": {
+        "tag": "rename_source_as_asn_to_source_as_number_a917047d",
         "field": "source.as.asn",
         "target_field": "source.as.number",
         "ignore_missing": true
@@ -256,6 +287,7 @@
     },
     {
       "rename": {
+        "tag": "rename_source_as_organization_name_to_source_as_organization_name_f1362d0b",
         "field": "source.as.organization_name",
         "target_field": "source.as.organization.name",
         "ignore_missing": true
@@ -263,6 +295,7 @@
     },
     {
       "rename": {
+        "tag": "rename_destination_as_asn_to_destination_as_number_3b459fcd",
         "field": "destination.as.asn",
         "target_field": "destination.as.number",
         "ignore_missing": true
@@ -270,6 +303,7 @@
     },
     {
       "rename": {
+        "tag": "rename_destination_as_organization_name_to_destination_as_organization_name_814bd459",
         "field": "destination.as.organization_name",
         "target_field": "destination.as.organization.name",
         "ignore_missing": true
@@ -277,12 +311,14 @@
     },
     {
       "community_id": {
+        "tag": "community_id_d2308e7a",
         "target_field": "network.community_id",
         "ignore_failure": true
       }
     },
     {
       "grok": {
+        "tag": "grok_observer_ingress_interface_name_968018d3",
         "field": "observer.ingress.interface.name",
         "patterns": [
           "%{DATA}.%{NONNEGINT:observer.ingress.vlan.id}"
@@ -293,6 +329,7 @@
     },
     {
       "set": {
+        "tag": "set_network_vlan_id_efd4d96a",
         "field": "network.vlan.id",
         "copy_from": "observer.ingress.vlan.id",
         "ignore_empty_value": true
@@ -300,6 +337,7 @@
     },
     {
       "append": {
+        "tag": "append_related_ip_c1a6356b",
         "field": "related.ip",
         "value": "{{{destination.ip}}}",
         "allow_duplicates": false,
@@ -308,6 +346,7 @@
     },
     {
       "append": {
+        "tag": "append_related_ip_8121c591",
         "field": "related.ip",
         "value": "{{{source.ip}}}",
         "allow_duplicates": false,
@@ -316,6 +355,7 @@
     },
     {
       "append": {
+        "tag": "append_related_ip_53b62ed8",
         "field": "related.ip",
         "value": "{{{source.nat.ip}}}",
         "allow_duplicates": false,
@@ -324,6 +364,7 @@
     },
     {
       "append": {
+        "tag": "append_related_hosts_6f162628",
         "field": "related.hosts",
         "value": "{{{destination.domain}}}",
         "if": "ctx.destination?.domain != null"
@@ -331,6 +372,7 @@
     },
     {
       "append": {
+        "tag": "append_related_user_c036eec2",
         "field": "related.user",
         "value": "{{{user.name}}}",
         "if": "ctx.user?.name != null"
@@ -338,6 +380,7 @@
     },
     {
       "set": {
+        "tag": "set_network_direction_cb1e3125",
         "field": "network.direction",
         "value": "{{{network.direction}}}bound",
         "if": "ctx.network?.direction != null && ctx.network?.direction =~ /^(in|out)$/"
@@ -345,6 +388,7 @@
     },
     {
       "remove": {
+        "tag": "remove_a82e20f2",
         "field": [
           "_tmp"
         ],
@@ -353,11 +397,21 @@
     },
     {
       "script": {
+        "tag": "script_a7f2c062",
         "lang": "painless",
         "description": "This script processor iterates over the whole document to remove fields with null values.",
         "source": "void handleMap(Map map) {\n  for (def x : map.values()) {\n    if (x instanceof Map) {\n        handleMap(x);\n    } else if (x instanceof List) {\n        handleList(x);\n    }\n  }\n  map.values().removeIf(v -> v == null || (v instanceof String && v == \"-\"));\n}\nvoid handleList(List list) {\n  for (def x : list) {\n      if (x instanceof Map) {\n          handleMap(x);\n      } else if (x instanceof List) {\n          handleList(x);\n      }\n  }\n}\nhandleMap(ctx);\n"
       }
     },
+    {
+      "append": {
+        "tag": "append_preserve_original_event_on_error",
+        "field": "tags",
+        "value": "preserve_original_event",
+        "allow_duplicates": false,
+        "if": "ctx.error?.message != null"
+      }
+    },
     {
       "pipeline": {
         "name": "global@custom",
@@ -405,7 +459,14 @@
     {
       "append": {
         "field": "error.message",
-        "value": "{{{ _ingest.on_failure_message }}}"
+        "value": "Processor '{{{ _ingest.on_failure_processor_type }}}' {{#_ingest.on_failure_processor_tag}}with tag '{{{ _ingest.on_failure_processor_tag }}}' {{/_ingest.on_failure_processor_tag}}in pipeline '{{{ _ingest.pipeline }}}' failed with message '{{{ _ingest.on_failure_message }}}'"
+      }
+    },
+    {
+      "append": {
+        "field": "tags",
+        "value": "preserve_original_event",
+        "allow_duplicates": false
       }
     }
   ]

salt/elasticsearch/files/ingest/suricata.fileinfo

@@ -5,7 +5,8 @@
     { "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.fileinfo.filename", 	"target_field": "file.name",		"ignore_missing": true 	} },
-    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "file.bytes.missing",	"ignore_missing": true 	} },
+    { "rename": 	{ "field": "message2.fileinfo.gaps", 		"target_field": "suricata.fileinfo.gaps",	"ignore_missing": true 	} },
+    { "set":		{ "if": "ctx.suricata?.fileinfo?.gaps == false", 	"field": "file.bytes.missing",	"value": 0 		} },
     { "rename": 	{ "field": "message2.fileinfo.magic", 		"target_field": "file.mime_type",	"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.md5", 		"target_field": "hash.md5",		"ignore_missing": true 	} },
     { "rename": 	{ "field": "message2.fileinfo.sha1", 		"target_field": "hash.sha1",		"ignore_missing": true 	} },

salt/elasticsearch/files/ingest/zeek.ja4d

@@ -0,0 +1,71 @@
+{
+    "description": "zeek.ja4d",
+    "processors": [
+        {
+            "set": {
+                "field": "event.dataset",
+                "value": "ja4d"
+            }
+        },
+        {
+            "remove": {
+                "field": [
+                    "host"
+                ],
+                "ignore_failure": true
+            }
+        },
+        {
+            "json": {
+                "field": "message",
+                "target_field": "message2",
+                "ignore_failure": true
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.ja4d",
+                "target_field": "hash.ja4d",
+                "ignore_missing": true,
+                "if": "ctx?.message2?.ja4d != null && ctx.message2.ja4d.length() > 0"
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.client_mac",
+                "target_field": "host.mac",
+                "ignore_missing": true,
+                "if": "ctx?.message2?.client_mac != null && ctx.message2.client_mac.length() > 0"
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.hostname",
+                "target_field": "host.hostname",
+                "ignore_missing": true,
+                "if": "ctx?.message2?.hostname != null && ctx.message2.hostname.length() > 0"
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.requested_ip",
+                "target_field": "dhcp.requested_address",
+                "ignore_missing": true,
+                "if": "ctx?.message2?.requested_ip != null && ctx.message2.requested_ip.length() > 0"
+            }
+        },
+        {
+            "rename": {
+                "field": "message2.vendor_class_id",
+                "target_field": "zeek.ja4d.vendor_class_id",
+                "ignore_missing": true,
+                "if": "ctx?.message2?.vendor_class_id != null && ctx.message2.vendor_class_id.length() > 0"
+            }
+        },
+        {
+            "pipeline": {
+                "name": "zeek.common"
+            }
+        }
+    ]
+}

salt/elasticsearch/files/ingest/zeek.ssl

@@ -5,6 +5,7 @@
     { "remove":   { "field": ["host"],     "ignore_failure": true } },
     { "json":             { "field": "message",                 "target_field": "message2",             "ignore_failure": true  } },
     { "rename":         { "field": "message2.version",          "target_field": "ssl.version",          "ignore_missing": true  } },
+    { "set":      { "description": "Set transport for the community_id processor", "if": "ctx.ssl?.version == null || !ctx.ssl.version.startsWith('DTLS')", "field": "network.transport", "value": "tcp", "ignore_failure": true } },
     { "rename":         { "field": "message2.cipher",           "target_field": "ssl.cipher",           "ignore_missing": true  } },
     { "rename":         { "field": "message2.curve",            "target_field": "ssl.curve",            "ignore_missing": true  } },
     { "rename":         { "field": "message2.server_name",      "target_field": "ssl.server_name",              "ignore_missing": true  } },