Add cluster_health option to telegraf.conf

Enable cluster health monitoring in Telegraf configuration.

.github/DISCUSSION_TEMPLATE/3-0.yml

@@ -11,6 +11,7 @@ body:
         -
         - 3.0.0
         - 3.1.0
+        - 3.2.0
         - Other (please provide detail below)
     validations:
       required: true

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 3.0.0-20260331 ISO image released on 2026/03/31
+### 3.1.0-20260528 ISO image released on 2026/05/28
 
 
 ### Download and Verify
 
-3.0.0-20260331 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-3.0.0-20260331.iso
+3.1.0-20260528 ISO image:  
+https://download.securityonion.net/file/securityonion/securityonion-3.1.0-20260528.iso
  
-MD5: ECD318A1662A6FDE0EF213F5A9BD4B07  
-SHA1: E55BE314440CCF3392DC0B06BC5E270B43176D9C  
-SHA256: 7FC47405E335CBE5C2B6C51FE7AC60248F35CBE504907B8B5A33822B23F8F4D5  
+MD5: 9D6FF58DEEE24089D722C73169765B3E  
+SHA1: 2B8B816B6CEC3B7F96B3C5E040EBF502DD2C412F  
+SHA256: 62FAB57E247C843D6A04F0796D8162C732B65D82FC3E4A59D087135B9FD32912  
 
 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-3.1.0-20260528.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-3.1.0-20260528.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-3.1.0-20260528.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-3.1.0-20260528.iso.sig securityonion-3.1.0-20260528.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 Wed 27 May 2026 03:03:59 PM 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
+3.2.0

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

salt/allowed_states.map.jinja

@@ -37,8 +37,7 @@
     'elasticfleet',
     'elasticfleet.manager',
     'elasticsearch.cluster',
-    'elastic-fleet-package-registry',
-    'utility'
+    'elastic-fleet-package-registry'
 ] %}
 
 {% set sensor_states = [

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/common/init.sls

@@ -130,6 +130,17 @@ common_sbin:
       - 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
+
 common_sbin_jinja:
   file.recurse:
     - name: /usr/sbin

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}"
@@ -286,6 +291,20 @@ 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

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

@@ -0,0 +1,57 @@
+#!/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 — switch the boot default to the installed UEK8 (6.x) kernel.
+#
+# Security Onion is moving off the EL9 stock kernel / UEK7 (5.x) onto UEK8 (6.x).
+# Installing the kernel-uek-core package adds a UEK8 boot entry but does NOT make it the
+# default: kernel-install/grubby only auto-promote a new kernel within the running
+# kernel's flavor lineage, and we're crossing from a 5.x kernel to the new 6.x UEK flavor.
+# So even with UPDATEDEFAULT=yes and DEFAULTKERNEL=kernel-uek-core the box keeps booting
+# the old kernel. This tool finds the newest installed 6.x UEK kernel and makes it the
+# GRUB default via grubby so the next boot comes up on UEK8.
+#
+# Idempotent: if the UEK8 kernel is already the default it does nothing. It only sets the
+# boot default; it does NOT reboot — the admin reboots the node on their own schedule.
+
+log() { echo "[so-kernel-upgrade] $*"; }
+
+[ "$(id -u)" -eq 0 ] || { log "must run as root"; exit 1; }
+command -v grubby >/dev/null 2>&1 || { log "grubby not found"; exit 1; }
+
+# Newest installed UEK8 (6.x) kernel known to the bootloader. UEK8 vmlinuz paths look like
+# /boot/vmlinuz-6.12.0-203.76.7.5.el9uek.x86_64; the 5.x UEK7 and 5.14 RHCK won't match.
+target="$(grubby --info=ALL 2>/dev/null \
+    | sed -n 's/^kernel="\(.*\)"$/\1/p' \
+    | grep -E '/vmlinuz-6\.[0-9]+.*uek' \
+    | sort -V | tail -1)"
+
+if [ -z "$target" ]; then
+    log "no installed 6.x UEK (UEK8) kernel found — confirm the kernel repo is assigned and"
+    log "'dnf update' has installed kernel-uek-core. Nothing to do."
+    exit 0
+fi
+
+current="$(grubby --default-kernel 2>/dev/null)"
+if [ "$current" = "$target" ]; then
+    log "UEK8 kernel is already the boot default: $target"
+    exit 0
+fi
+
+log "current default kernel: ${current:-unknown}"
+log "switching boot default to UEK8 kernel: $target"
+grubby --set-default="$target" || { log "ERROR: grubby --set-default failed for $target"; exit 1; }
+
+# Verify the change actually took before claiming success.
+now="$(grubby --default-kernel 2>/dev/null)"
+if [ "$now" != "$target" ]; then
+    log "ERROR: default kernel is still '${now:-unknown}' after set-default"
+    exit 1
+fi
+
+log "boot default is now $target"
+log "REBOOT REQUIRED to start using the UEK8 kernel (currently running $(uname -r))."

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

@@ -165,6 +165,8 @@ 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)
 fi
 
 if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then

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
-        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"
-        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"
+if [[ $# -lt 1 ]]; then
+    usage
 fi
+
+#shellcheck disable=SC2154
+echo "$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-start

@@ -5,27 +5,54 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
-
-# Usage: so-start  all | kibana | playbook 
-
+# shellcheck disable=SC1091
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
-	echo $banner
-	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 $banner
+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             Start Kibana"
+    echo "  $0 kibana --force     Force stop all Salt jobs before starting Kibana"
+    exit 1
+}
 
-	if [ "$2" = "--force" ]; 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") 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"	
+if [[ $# -lt 1 ]]; then
+    usage
 fi
+
+#shellcheck disable=SC2154
+echo "$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-stop

@@ -5,21 +5,33 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-
-
-# Usage: so-stop kibana | playbook | thehive
-
+# shellcheck disable=SC1091
 . /usr/sbin/so-common
 
-if [ $# -ge 1 ]; then
-	echo $banner
-	printf "Stopping $1...\n"
-	echo $banner
+usage() {
+    echo "Usage: $0 <component>"
+    echo ""
+    echo "Examples:"
+    echo "  $0 kibana             Stop Kibana"
+    exit 1
+}
 
-	case $1 in
-    		*) docker stop so-$1 ; docker rm so-$1 ;;
-	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"	
+if [[ $# -lt 1 ]]; then
+    usage
 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/elasticfleet/config.sls

@@ -173,7 +173,7 @@ 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

@@ -9,7 +9,6 @@
 
 {% set CORE_ESFLEET_PACKAGES = ELASTICFLEETDEFAULTS.get('elasticfleet', {}).get('packages', {}) %}
 {% set ADDON_CONTENT_INTEGRATION_DEFAULTS = {} %}
-{% set DEBUG_STUFF = {} %}
 
 {% for pkg in ADDON_CONTENT_PACKAGE_COMPONENTS %}
 {%   if pkg.name in CORE_ESFLEET_PACKAGES %}

salt/elasticfleet/enabled.sls

@@ -26,7 +26,9 @@ include:
 wait_for_elasticsearch_elasticfleet:
   cmd.run:
     - name: so-elasticsearch-wait
+{% endif %}
 
+{% if GLOBALS.role == "so-fleet" %}
 # Sync Elastic Agent artifacts to Fleet Node
 elasticagent_syncartifacts:
   file.recurse:
@@ -99,6 +101,17 @@ 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 %}
 
 delete_so-elastic-fleet_so-status.disabled:

salt/elasticfleet/input-defaults.map.jinja

@@ -9,7 +9,6 @@
 
 {% set CORE_ESFLEET_PACKAGES = ELASTICFLEETDEFAULTS.get('elasticfleet', {}).get('packages', {}) %}
 {% set ADDON_INPUT_INTEGRATION_DEFAULTS = {} %}
-{% set DEBUG_STUFF = {} %}
 
 {% for pkg in ADDON_INPUT_PACKAGE_COMPONENTS %}
 {%   if pkg.name in CORE_ESFLEET_PACKAGES %}
@@ -116,7 +115,6 @@
 
 
 {%         do ADDON_INPUT_INTEGRATION_DEFAULTS.update({integration_key: integration_defaults}) %}
-{%         do DEBUG_STUFF.update({integration_key: "Generating defaults for "+ pkg.name })%}
 {%       endfor %}
 {%     endif %}
 {%   endif %}

salt/elasticfleet/manager.sls

@@ -9,16 +9,20 @@
 
 include:
   - elasticfleet.config
+  - kibana.enabled
 
 # If enabled, automatically update Fleet Logstash Outputs
-{% if ELASTICFLEETMERGED.config.server.enable_auto_configuration and grains.role not in ['so-import', 'so-eval'] %}
+{% 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
-{% endif %}
+    - require:
+      - http: wait_for_so-kibana
+{%   endif %}
 
 # If enabled, automatically update Fleet Server URLs & ES Connection
 so-elastic-fleet-auto-configure-server-urls:
@@ -27,6 +31,9 @@ so-elastic-fleet-auto-configure-server-urls:
     - 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:
@@ -35,6 +42,8 @@ so-elastic-fleet-auto-configure-elasticsearch-urls:
     - retry:
         attempts: 4
         interval: 30
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-fleet-auto-configure-artifact-urls:
   cmd.run:
@@ -42,6 +51,8 @@ so-elastic-fleet-auto-configure-artifact-urls:
     - retry:
         attempts: 4
         interval: 30
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-fleet-package-statefile:
   file.managed:
@@ -53,9 +64,9 @@ so-elastic-fleet-package-upgrade:
     - name: /usr/sbin/so-elastic-fleet-package-upgrade
     - retry:
         attempts: 3
-        interval: 10
-    - onchanges:
-      - file: /opt/so/state/elastic_fleet_packages.txt
+        interval: 30
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-fleet-integrations:
   cmd.run:
@@ -63,6 +74,8 @@ so-elastic-fleet-integrations:
     - retry:
         attempts: 3
         interval: 10
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-agent-grid-upgrade:
   cmd.run:
@@ -70,6 +83,8 @@ so-elastic-agent-grid-upgrade:
     - retry:
         attempts: 12
         interval: 5
+    - require:
+      - http: wait_for_so-kibana
 
 so-elastic-fleet-integration-upgrade:
   cmd.run:
@@ -77,16 +92,22 @@ so-elastic-fleet-integration-upgrade:
     - retry:
         attempts: 3
         interval: 10
+    - 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
 
 {% 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

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

@@ -30,6 +30,94 @@ 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
 }
 
+# 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=$(mktemp -d)
+    i=0
+
+    # Fetch the agent policy a single time; we look up integration ids locally below.
+    if ! POLICY_JSON=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+        echo "Error: Failed to retrieve agent policy '$AGENT_POLICY'."
+        rm -f "$FAIL_FILE"
+        rm -rf "$OUT_DIR"
+        return 1
+    fi
+
+    if ! jq -e '.item.package_policies' <<<"$POLICY_JSON" >/dev/null 2>&1; then
+        echo "Error: Invalid agent policy response for '$AGENT_POLICY'."
+        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
@@ -46,7 +134,9 @@ 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
 }
@@ -77,7 +167,9 @@ 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
 }

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
-    printf "\n\nInitial Endpoints Policy - Loading $INTEGRATION\n"
-    elastic_fleet_integration_check "endpoints-initial" "$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
+  elastic_fleet_load_integrations_dir "endpoints-initial" \
+    /opt/so/conf/elastic-fleet/integrations/endpoints-initial "Initial Endpoints Policy" || RETURN_CODE=1
 
   # Grid Nodes - General
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_general/*.json; do
-    printf "\n\nGrid Nodes Policy_General - Loading $INTEGRATION\n"
-    elastic_fleet_integration_check "so-grid-nodes_general" "$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
+  elastic_fleet_load_integrations_dir "so-grid-nodes_general" \
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_general "Grid Nodes Policy_General" || RETURN_CODE=1
 
   # Grid Nodes - Heavy
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy/*.json; do
-    printf "\n\nGrid Nodes Policy_Heavy - Loading $INTEGRATION\n"
-    elastic_fleet_integration_check "so-grid-nodes_heavy" "$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
+  elastic_fleet_load_integrations_dir "so-grid-nodes_heavy" \
+    /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy "Grid Nodes Policy_Heavy" || RETURN_CODE=1
 
-  # Fleet Server - Optional integrations
-  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json; do
-    if ! [ "$INTEGRATION" == "/opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json" ]; then
-      FLEET_POLICY=`echo "$INTEGRATION"| cut -d'/' -f7`
-      printf "\n\nFleet Server Policy - Loading $INTEGRATION\n"
-      elastic_fleet_integration_check "$FLEET_POLICY" "$INTEGRATION"
-      if [ -n "$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 ${INTEGRATION##*/}"
-          RETURN_CODE=1
-          continue
-        fi
-      else
-        printf "\n\nIntegration does not exist - Creating integration\n"
-        if [ "$NAME" != "elasticsearch-logs" ]; then
-          if ! elastic_fleet_integration_create "@$INTEGRATION"; then
-            echo -e "\nFailed to create integration for ${INTEGRATION##*/}"
-            RETURN_CODE=1
-            continue
-          fi
-        fi
-      fi
-    fi
+  # Fleet Server - Optional integrations (adds integration configuration to a given FleetServer_ policy)
+  for FLEET_DIR in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/; do
+    [ -d "$FLEET_DIR" ] || continue
+    INTEGRATIONS=("${FLEET_DIR%/}"/*.json)
+    [ -e "${INTEGRATIONS[0]}" ] || continue
+
+    FLEET_POLICY=$(basename "$FLEET_DIR")
+    elastic_fleet_load_integrations_dir "$FLEET_POLICY" \
+      "${FLEET_DIR%/}" "Fleet Server Policy" "elasticsearch-logs" || RETURN_CODE=1
   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-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" ]] && ! [[ "$INTEGRATION" == "fleet_server-"* ]]; then
-            # Get package name so we know what package to look for when checking the current and latest available version
-            if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
+
+    # One jq pass emits name/package.name/package.version/id for every eligible integration.
+    # The endpoint/fleet_server skips and the default-package gate are applied here in jq.
+    # $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 %}
-            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 $PACKAGE_NAME policy upgrade..."
-                        ERROR=true
-                        continue
-                    fi
-                fi
-            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-            fi
-            {%- endif %}
+            LATEST_VERSION_CACHE[$PACKAGE_NAME]=$AVAILABLE_VERSION
         fi
-    done
+        AVAILABLE_VERSION=${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

@@ -16,7 +16,6 @@
 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
 INTEGRATION_PACKAGE_COMPONENTS=/opt/so/state/esfleet_package_components.json
 INPUT_PACKAGE_COMPONENTS=/opt/so/state/esfleet_input_package_components.json
@@ -29,29 +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
@@ -63,23 +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 $integrations; do
-        if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
-            echo  "Not adding $INTEGRATION, couldn't get package name"
-            continue
-        fi
-        # non-default integrations that are in-use in any policy
-        if ! [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
-            in_use_integrations+=("$PACKAGE_NAME")
-        fi
-    done
+    # non-default integrations that are in-use in any policy
+    while IFS= read -r PACKAGE_NAME; do
+        [ -n "$PACKAGE_NAME" ] && in_use_integrations+=("$PACKAGE_NAME")
+    done < <(jq -r --argjson defaults "$default_packages_json" \
+        '.item.package_policies[].package.name | select(. as $n | ($defaults | index($n)) | not)' \
+        <<<"$policy_json")
 done
 
 if [[ -f $STATE_FILE_SUCCESS  ]]; then
@@ -90,72 +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
-            # get package details
-            package_name=$(echo "$package" | jq -r '.name')
-            latest_version=$(echo "$package" | jq -r '.latest_version')
-            installed_version=$(echo "$package" | jq -r '.installed_version')
-            subscription=$(echo "$package" | jq -r '.subscription')
-            bulk_package=$(echo "$package" | jq '{name: .name, version: .latest_version}' )
+        # Build the bulk install list and the per-package status messages with two jq passes
+        #  instead of a per-package bash loop. The old loop forked ~10 processes per package
+        #  (5 jq + awk/bc for the version compare) and re-parsed/rewrote a growing JSON file on
+        #  every add (O(n^2)). Selection and messages below are identical to that logic.
+        SUB={% if SUB %}true{% else %}false{% endif %}
+        AUTOUP={% if AUTO_UPGRADE_INTEGRATIONS %}true{% else %}false{% endif %}
+        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
-            {% if not SUB %}
-                if [[ "$subscription" != "basic" && "$subscription" != "null" && -n "$subscription" ]]; then
-                    # pass over integrations that require non-basic elastic license
-                    echo "$package_name integration requires an Elastic license of $subscription or greater... skipping"
-                    continue
-                else
-                    if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
-                        echo "$package_name is not installed... Adding to next update."
-                        jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
+        # vnum replicates the previous version_conversion (%d%03d%03d of the first three dotted
+        #  fields); needs() replicates the excluded/subscription/installed/upgrade/in-use logic.
+        JQ_DECISION='
+def vnum:
+  [ (split(".")|.[0:3][] | gsub("[^0-9].*";"") | (if .=="" then "0" else . end) | tonumber) ]
+  | (.[0]//0)*1000000 + (.[1]//0)*1000 + (.[2]//0);
+def needs($sub;$autoup;$excluded;$inuse):
+  .name as $n
+  | ($n | IN($excluded[]) | not)
+  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
-                    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 $BULK_INSTALL_PACKAGE_LIST
+        JQ_ARGS=(--argjson sub "$SUB" --argjson autoup "$AUTOUP" --argjson excluded "$EXCLUDED_JSON" --argjson inuse "$INUSE_JSON")
 
-                                PENDING_UPDATE=true
-                            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-                            else
-                                echo "skipping available upgrade for in use integration - $package_name."
-                            fi
-                            {%- endif %}
-                        fi
-                    fi
-                fi
-            {% else %}
-                if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
-                    echo "$package_name is not installed... Adding to next update."
-                    jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
-                    PENDING_UPDATE=true
-                else
-                    results=$(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
-                        {%- 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[]' "$INSTALLED_PACKAGE_LIST")"
+        # (a) Per-package status messages (parity with the previous echo output).
+        jq -r "${JQ_ARGS[@]}" "$JQ_DECISION"'
+          .packages[]
+          | .name as $n
+          | if ($n|IN($excluded[])) then "Skipping \($n)..."
+            elif (($sub|not) and (.subscription!=null and .subscription!="basic" and .subscription!="")) then
+                 "\($n) integration requires an Elastic license of \(.subscription) or greater... skipping"
+            elif (.installed_version==null or .installed_version=="") then
+                 "\($n) is not installed... Adding to next update."
+            elif ((.latest_version|vnum) > (.installed_version|vnum)) then
+                 (if ($autoup or ($n|IN($inuse[])|not))
+                  then "\($n) is at version \(.installed_version) latest version is \(.latest_version)... Adding to next update."
+                  else "skipping available upgrade for in use integration - \($n)." end)
+            else empty end
+        ' "$INSTALLED_PACKAGE_LIST"
+
+        # (b) The bulk install list, built in a single pass.
+        jq "${JQ_ARGS[@]}" "$JQ_DECISION"'
+          {packages: [ .packages[] | select(needs($sub;$autoup;$excluded;$inuse)) | {name, version: .latest_version} ]}
+        ' "$INSTALLED_PACKAGE_LIST" > "$BULK_INSTALL_PACKAGE_LIST"
+
+        if jq -e '.packages | length > 0' "$BULK_INSTALL_PACKAGE_LIST" >/dev/null; then
+            PENDING_UPDATE=true
+        fi
 
         if [ "$PENDING_UPDATE" = true ]; then
             # Run chunked install of packages

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

@@ -8,18 +8,35 @@
 
 . /usr/sbin/so-elastic-fleet-common
 
+PKG_LOAD_FAILURES=0
+PKG_LOAD_FAILURES_NAMES=()
+
 {%- for PACKAGE in SUPPORTED_PACKAGES %}
-echo "Upgrading {{ PACKAGE }} package..."
-if VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
-    if ! elastic_fleet_package_install "{{ PACKAGE }}" "$VERSION"; then
-        # exit 1 on failure to upgrade a default package, allow salt to handle retries
-        echo -e "\nERROR: Failed to upgrade $PACKAGE to version: $VERSION"
-        exit 1
+if INSTALLED_VERSION=$(elastic_fleet_package_version_check "{{ PACKAGE }}") && LATEST_VERSION=$(elastic_fleet_package_latest_version_check "{{ PACKAGE }}"); then
+
+    if [ "$INSTALLED_VERSION" == "$LATEST_VERSION" ]; then
+        echo "{{ PACKAGE }} integration version $INSTALLED_VERSION is already at the reported latest version $LATEST_VERSION, skipping upgrade."
+    else
+        echo "Upgrading {{ PACKAGE }} package 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 }}")
+        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_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
 

salt/elasticsearch/cluster.sls

@@ -9,9 +9,12 @@
 {%   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 %}
+{%     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
@@ -35,6 +38,20 @@ so_index_template_dir:
       {%- 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() %}
@@ -116,6 +133,18 @@ so-elasticsearch-templates:
       - 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 }}
@@ -136,7 +165,8 @@ so-elasticsearch-roles-load:
 {%    set ap = "absent" %}
 {%  endif %}
 {%  if grains.role in ['so-eval', 'so-standalone', 'so-heavynode'] %}
-{%    if ELASTICSEARCHMERGED.index_clean %}
+{#    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" %}

salt/elasticsearch/defaults.yaml

@@ -2,6 +2,7 @@ elasticsearch:
   enabled: false
   version: 9.3.3
   index_clean: true
+  data_retention_method: DLM
   vm:
     max_map_count: 1048576
   config:
@@ -63,6 +64,8 @@ elasticsearch:
             verification_mode: none
   index_settings:
     global_overrides:
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         template:
           settings:
@@ -143,6 +146,8 @@ elasticsearch:
                 order: desc
     so-common:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -304,6 +309,8 @@ elasticsearch:
               number_of_shards: 1
     so-assistant-chat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: ""
       index_template:
         composed_of:
         - assistant-chat-mappings
@@ -344,6 +351,8 @@ elasticsearch:
             min_age: 0ms
     so-assistant-session:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: ""
       index_template:
         composed_of:
         - assistant-session-mappings
@@ -497,6 +506,8 @@ elasticsearch:
             min_age: 30d
     so-idh:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -605,6 +616,8 @@ elasticsearch:
             min_age: 30d
     so-import:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -787,6 +800,8 @@ elasticsearch:
             min_age: 0ms
     so-kismet:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - kismet-mappings
@@ -836,6 +851,8 @@ elasticsearch:
             min_age: 30d
     so-kratos:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -904,6 +921,8 @@ elasticsearch:
             min_age: 30d
     so-hydra:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -1049,6 +1068,8 @@ elasticsearch:
             min_age: 0ms
     so-logs:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - so-data-streams-mappings
@@ -1129,6 +1150,8 @@ elasticsearch:
             min_age: 30d
     so-logs-detections_x_alerts:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - so-data-streams-mappings
@@ -1192,6 +1215,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1307,6 +1332,8 @@ elasticsearch:
             min_age: 30d
     so-elastic-agent-monitor:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1369,6 +1396,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_apm_server:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-elastic_agent.apm_server@package
@@ -1433,6 +1462,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_auditbeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-elastic_agent.auditbeat@package
@@ -1497,6 +1528,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_cloudbeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-elastic_agent.cloudbeat@package
@@ -1561,6 +1594,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_endpoint_security:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1620,6 +1655,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_filebeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1679,6 +1716,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_fleet_server:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1735,6 +1774,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_heartbeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-elastic_agent.heartbeat@package
@@ -1799,6 +1840,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_metricbeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1858,6 +1901,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_osquerybeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1917,6 +1962,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent_x_packetbeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-elastic_agent.packetbeat@package
@@ -1981,6 +2028,8 @@ elasticsearch:
             min_age: 30d
     so-logs-elasticsearch_x_server:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-elasticsearch.server@package
@@ -2045,10 +2094,13 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_actions:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - .logs-endpoint.actions@package
         - .logs-endpoint.actions@custom
+        - endpoint@custom
         - event-mappings
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -2058,8 +2110,9 @@ elasticsearch:
           hidden: false
         ignore_missing_component_templates:
         - .logs-endpoint.actions@custom
+        - endpoint@custom
         index_patterns:
-        - logs-endpoint.actions-*
+        - .logs-endpoint.actions-*
         priority: 501
         template:
           settings:
@@ -2104,10 +2157,13 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_action_x_responses:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - .logs-endpoint.action.responses@package
         - .logs-endpoint.action.responses@custom
+        - endpoint@custom
         - event-mappings
         - so-fleet_integrations.ip_mappings-1
         - so-fleet_globals-1
@@ -2117,14 +2173,15 @@ elasticsearch:
           hidden: false
         ignore_missing_component_templates:
         - .logs-endpoint.action.responses@custom
+        - endpoint@custom
         index_patterns:
-        - logs-endpoint.action.responses-*
+        - .logs-endpoint.action.responses-*
         priority: 501
         template:
           settings:
             index:
               lifecycle:
-                name: so-logs-endpoint.actions-logs
+                name: so-logs-endpoint.action.responses-logs
               mapping:
                 total_fields:
                   limit: 5000
@@ -2163,6 +2220,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_alerts:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.alerts@package
@@ -2222,6 +2281,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_diagnostic_x_collection:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - .logs-endpoint.diagnostic.collection@package
@@ -2297,6 +2358,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_events_x_api:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.events.api@package
@@ -2356,6 +2419,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_events_x_file:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.events.file@package
@@ -2415,6 +2480,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_events_x_library:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.events.library@package
@@ -2474,6 +2541,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_events_x_network:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.events.network@package
@@ -2533,6 +2602,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_events_x_process:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.events.process@package
@@ -2592,6 +2663,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_events_x_registry:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.events.registry@package
@@ -2651,6 +2724,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_events_x_security:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-endpoint.events.security@package
@@ -2710,6 +2785,8 @@ elasticsearch:
             min_age: 30d
     so-logs-endpoint_x_heartbeat:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - .logs-endpoint.heartbeat@package
@@ -2769,6 +2846,8 @@ elasticsearch:
             min_age: 30d
     so-logs-http_endpoint_x_generic:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-http_endpoint.generic@package
@@ -2817,6 +2896,8 @@ elasticsearch:
             min_age: 30d
     so-logs-httpjson_x_generic:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-httpjson.generic@package
@@ -2882,6 +2963,8 @@ elasticsearch:
               number_of_replicas: 0
     so-logs-osquery-manager_x_action_x_responses:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         _meta:
           managed: true
@@ -2953,6 +3036,8 @@ elasticsearch:
               number_of_replicas: 0
     so-logs-osquery-manager_x_result:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         _meta:
           managed: true
@@ -3005,6 +3090,8 @@ elasticsearch:
             min_age: 30d
     so-logs-soc:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -3113,6 +3200,8 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_application:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3162,6 +3251,8 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_auth:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3211,6 +3302,8 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_security:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3260,6 +3353,8 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_syslog:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3309,6 +3404,8 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_system:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3358,6 +3455,8 @@ elasticsearch:
             min_age: 30d
     so-logs-windows_x_forwarded:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-windows.forwarded@package
@@ -3405,6 +3504,8 @@ elasticsearch:
             min_age: 30d
     so-logs-windows_x_powershell:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-windows.powershell@package
@@ -3452,6 +3553,8 @@ elasticsearch:
             min_age: 30d
     so-logs-windows_x_powershell_operational:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-windows.powershell_operational@package
@@ -3499,6 +3602,8 @@ elasticsearch:
             min_age: 30d
     so-logs-windows_x_sysmon_operational:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-windows.sysmon_operational@package
@@ -3546,6 +3651,8 @@ elasticsearch:
             min_age: 30d
     so-logs-winlog_x_winlog:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - logs-winlog.winlog@package
@@ -3594,6 +3701,8 @@ elasticsearch:
             min_age: 30d
     so-logstash:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -3709,6 +3818,8 @@ elasticsearch:
             min_age: 30d
     so-metrics-endpoint_x_metadata:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - metrics-endpoint.metadata@package
@@ -3756,6 +3867,8 @@ elasticsearch:
             min_age: 30d
     so-metrics-endpoint_x_metrics:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - metrics-endpoint.metrics@package
@@ -3803,6 +3916,8 @@ elasticsearch:
             min_age: 30d
     so-metrics-endpoint_x_policy:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - metrics-endpoint.policy@package
@@ -3850,6 +3965,8 @@ elasticsearch:
             min_age: 30d
     so-metrics-fleet_server_x_agent_status:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - metrics@tsdb-settings
@@ -3874,6 +3991,8 @@ elasticsearch:
               number_of_replicas: 0
     so-metrics-fleet_server_x_agent_versions:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - metrics@tsdb-settings
@@ -3898,6 +4017,8 @@ elasticsearch:
               number_of_replicas: 0
     so-redis:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4013,6 +4134,8 @@ elasticsearch:
             min_age: 30d
     so-strelka:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4130,6 +4253,8 @@ elasticsearch:
             min_age: 30d
     so-suricata:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4246,6 +4371,8 @@ elasticsearch:
             min_age: 30d
     so-suricata_x_alerts:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4362,6 +4489,8 @@ elasticsearch:
             min_age: 30d
     so-syslog:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4478,6 +4607,8 @@ elasticsearch:
             min_age: 30d
     so-zeek:
       index_sorting: false
+      data_stream_lifecycle:
+        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings

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

@@ -177,12 +177,84 @@
                 "description": "Extract IPs from Elastic Agent events (host.ip) and adds them to related.ip"
             }
         },
+        {
+            "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",
@@ -202,11 +274,12 @@
                     "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/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  } },

salt/elasticsearch/soc_elasticsearch.yaml

@@ -4,6 +4,13 @@ elasticsearch:
     forcedType: bool
     advanced: True
     helpLink: elasticsearch
+  data_retention_method:
+    description: Method for data retention. Options are ILM or DLM. For single node deployments and most distributed grid users, DLM will be the recommended option for simplified management. Those with more complex use cases may prefer ILM. The latter allows for more granular control, but requires more management overhead.
+    options:
+    - ILM
+    - DLM
+    forcedType: string
+    global: True
   version:
     description: "This specifies the version of the following containers: so-elastic-fleet-package-registry, so-elastic-agent, so-elastic-fleet, so-kibana, so-logstash and so-elasticsearch. Modifying this value in the Elasticsearch defaults.yaml will result in catastrophic grid failure."
     readonly: True
@@ -13,7 +20,7 @@ elasticsearch:
     description: Specify the memory heap size in (m)egabytes for Elasticsearch.
     helpLink: elasticsearch
   index_clean:
-    description: Determines if indices should be considered for deletion by available disk space in the cluster. Otherwise, indices will only be deleted by the age defined in the ILM settings. This setting only applies to EVAL, STANDALONE, and HEAVY NODE installations. Other installations can only use ILM settings.
+    description: Determines if indices should be considered for deletion by available disk space in the cluster. Otherwise, data is retained by the configured lifecycle settings. This setting only applies to EVAL, STANDALONE, and HEAVY NODE installations. Other installations use lifecycle settings only.
     forcedType: bool
     helpLink: elasticsearch
   vm:
@@ -139,6 +146,23 @@ elasticsearch:
     custom010: *pipelines
   index_settings:
     global_overrides:
+      data_stream_lifecycle:
+        data_retention:
+          description: |
+            The retention period for all data streams. Retention does not define the period that the data will be removed, but the minimum time period they will be kept.
+
+            Use a number followed by a time unit, such as 7d. Leave blank for indefinite retention where supported.
+
+            Configured retention period also affects the frequency of rolling over data streams.
+              - If retention is less than or equal to 1 day, max_age will be 1 hour
+              - If retention is less than or equal to 14 days, max_age will be 1 day
+              - If retention is less than or equal to 90 days, max_age will be 7 days
+              - If retention is greater than 90 days, max_age will be 30 days
+          forcedType: string
+          allowedNodeTypes:
+            - heavynode
+          regex: ^$|^[0-9]{1,5}(?:d|h|m|s)$
+          regexFailureMessage: Must be blank or a number followed by d, h, m, or s, such as 7d.
       index_template:
         template:
           settings:
@@ -311,13 +335,30 @@ elasticsearch:
               forcedType: string
               global: True
               helpLink: elasticsearch
-    so-logs: &indexSettings
+    so-logs: &dataStreamSettings
       index_sorting:
         description: Sorts the index by event time, at the cost of additional processing resource consumption.
         forcedType: bool
         global: True
         advanced: True
         helpLink: elasticsearch
+      data_stream_lifecycle:
+        data_retention:
+          description: |
+            The retention period for this data stream. Retention does not define the period that the data will be removed, but the minimum time period it will be kept.
+
+            Use a number followed by a time unit, such as 7d. Leave blank for indefinite retention where supported.
+
+            Configured retention period also affects the frequency of rolling over this data stream.
+              - If retention is less than or equal to 1 day, max_age will be 1 hour
+              - If retention is less than or equal to 14 days, max_age will be 1 day
+              - If retention is less than or equal to 90 days, max_age will be 7 days
+              - If retention is greater than 90 days, max_age will be 30 days
+          forcedType: string
+          allowedNodeTypes:
+            - heavynode
+          regex: ^$|^[0-9]{1,5}(?:d|h|m|s)$
+          regexFailureMessage: Must be blank or a number followed by d, h, m, or s, such as 7d.
       index_template:
         index_patterns:
           description: Patterns for matching multiple indices or tables.
@@ -335,6 +376,14 @@ elasticsearch:
                 global: True
                 advanced: True
                 helpLink: elasticsearch
+              auto_expand_replicas:
+                description: Automatically expand the number of replicas based on the number of data nodes in the cluster. This can help ensure high availability as the cluster scales up or down.
+                forcedType: string
+                regex: "^(0-[1-9]|1-[2-9]|2-[3-9]|3-[4-9]|4-[5-9]|5-[6-9]|6-[7-9]|7-[89]|8-9|[0-9]-all|false)$"
+                regexFailureMessage: Must be in the format of "x-y" where x is minimum number of replicas and y is maximum number of replicas, or "0-all" to specify a minimum of 0 and no maximum, or "false" to disable automatic replica expansion.
+                global: True
+                advanced: True
+                helpLink: elasticsearch
               mapping:
                 total_fields:
                   limit:
@@ -596,65 +645,349 @@ elasticsearch:
             global: True
             advanced: True
             helpLink: elasticsearch
-    so-logs-system_x_auth: *indexSettings
-    so-logs-system_x_syslog: *indexSettings
-    so-logs-system_x_system: *indexSettings
-    so-logs-system_x_application: *indexSettings
-    so-logs-system_x_security: *indexSettings
-    so-logs-windows_x_forwarded: *indexSettings
-    so-logs-windows_x_powershell: *indexSettings
-    so-logs-windows_x_powershell_operational: *indexSettings
-    so-logs-windows_x_sysmon_operational: *indexSettings
-    so-logs-winlog_x_winlog: *indexSettings
-    so-logs-detections_x_alerts: *indexSettings
-    so-logs-http_endpoint_x_generic: *indexSettings
-    so-logs-httpjson_x_generic: *indexSettings
-    so-logs-osquery-manager-actions: *indexSettings
-    so-logs-osquery-manager-action_x_responses: *indexSettings
-    so-logs-osquery-manager_x_action_x_responses: *indexSettings
-    so-logs-osquery-manager_x_result: *indexSettings
-    so-logs-elastic_agent_x_apm_server: *indexSettings
-    so-logs-elastic_agent_x_auditbeat: *indexSettings
-    so-logs-elastic_agent_x_cloudbeat: *indexSettings
-    so-logs-elastic_agent_x_endpoint_security: *indexSettings
-    so-logs-endpoint_x_alerts: *indexSettings
-    so-logs-endpoint_x_events_x_api: *indexSettings
-    so-logs-endpoint_x_events_x_file: *indexSettings
-    so-logs-endpoint_x_events_x_library: *indexSettings
-    so-logs-endpoint_x_events_x_network: *indexSettings
-    so-logs-endpoint_x_events_x_process: *indexSettings
-    so-logs-endpoint_x_events_x_registry: *indexSettings
-    so-logs-endpoint_x_events_x_security: *indexSettings
-    so-logs-elastic_agent_x_filebeat: *indexSettings
-    so-logs-elastic_agent_x_fleet_server: *indexSettings
-    so-logs-elastic_agent_x_heartbeat: *indexSettings
-    so-logs-elastic_agent: *indexSettings
-    so-logs-elastic_agent_x_metricbeat: *indexSettings
-    so-logs-elastic_agent_x_osquerybeat: *indexSettings
-    so-logs-elastic_agent_x_packetbeat: *indexSettings
-    so-logs-elasticsearch_x_server: *indexSettings
-    so-metrics-endpoint_x_metadata: *indexSettings
-    so-metrics-endpoint_x_metrics: *indexSettings
-    so-metrics-endpoint_x_policy: *indexSettings
-    so-metrics-nginx_x_stubstatus: *indexSettings
-    so-metrics-vsphere_x_datastore: *indexSettings
-    so-metrics-vsphere_x_host: *indexSettings
-    so-metrics-vsphere_x_virtualmachine: *indexSettings
-    so-case: *indexSettings
-    so-common: *indexSettings
-    so-endgame: *indexSettings
-    so-idh: *indexSettings
-    so-suricata: *indexSettings
-    so-suricata_x_alerts: *indexSettings
-    so-import: *indexSettings
-    so-kratos: *indexSettings
-    so-hydra: *indexSettings
-    so-kismet: *indexSettings
-    so-logstash: *indexSettings
-    so-redis: *indexSettings
-    so-strelka: *indexSettings
-    so-syslog: *indexSettings
-    so-zeek: *indexSettings
+    so-logs-system_x_auth: *dataStreamSettings
+    so-logs-system_x_syslog: *dataStreamSettings
+    so-logs-system_x_system: *dataStreamSettings
+    so-logs-system_x_application: *dataStreamSettings
+    so-logs-system_x_security: *dataStreamSettings
+    so-logs-windows_x_forwarded: *dataStreamSettings
+    so-logs-windows_x_powershell: *dataStreamSettings
+    so-logs-windows_x_powershell_operational: *dataStreamSettings
+    so-logs-windows_x_sysmon_operational: *dataStreamSettings
+    so-logs-winlog_x_winlog: *dataStreamSettings
+    so-logs-detections_x_alerts: *dataStreamSettings
+    so-logs-http_endpoint_x_generic: *dataStreamSettings
+    so-logs-httpjson_x_generic: *dataStreamSettings
+    so-logs-osquery-manager-actions: *dataStreamSettings
+    so-logs-osquery-manager-action_x_responses: *dataStreamSettings
+    so-logs-osquery-manager_x_action_x_responses: *dataStreamSettings
+    so-logs-osquery-manager_x_result: *dataStreamSettings
+    so-logs-elastic_agent_x_apm_server: *dataStreamSettings
+    so-logs-elastic_agent_x_auditbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_cloudbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_endpoint_security: *dataStreamSettings
+    so-logs-endpoint_x_alerts: *dataStreamSettings
+    so-logs-endpoint_x_events_x_api: *dataStreamSettings
+    so-logs-endpoint_x_events_x_file: *dataStreamSettings
+    so-logs-endpoint_x_events_x_library: *dataStreamSettings
+    so-logs-endpoint_x_events_x_network: *dataStreamSettings
+    so-logs-endpoint_x_events_x_process: *dataStreamSettings
+    so-logs-endpoint_x_events_x_registry: *dataStreamSettings
+    so-logs-endpoint_x_events_x_security: *dataStreamSettings
+    so-logs-elastic_agent_x_filebeat: *dataStreamSettings
+    so-logs-elastic_agent_x_fleet_server: *dataStreamSettings
+    so-logs-elastic_agent_x_heartbeat: *dataStreamSettings
+    so-logs-elastic_agent: *dataStreamSettings
+    so-logs-elastic_agent_x_metricbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_osquerybeat: *dataStreamSettings
+    so-logs-elastic_agent_x_packetbeat: *dataStreamSettings
+    so-logs-elasticsearch_x_server: *dataStreamSettings
+    so-metrics-endpoint_x_metadata: *dataStreamSettings
+    so-metrics-endpoint_x_metrics: *dataStreamSettings
+    so-metrics-endpoint_x_policy: *dataStreamSettings
+    so-metrics-nginx_x_stubstatus: *dataStreamSettings
+    so-metrics-vsphere_x_datastore: *dataStreamSettings
+    so-metrics-vsphere_x_host: *dataStreamSettings
+    so-metrics-vsphere_x_virtualmachine: *dataStreamSettings
+    so-common: *dataStreamSettings
+    so-endgame: *dataStreamSettings
+    so-idh: *dataStreamSettings
+    so-suricata: *dataStreamSettings
+    so-suricata_x_alerts: *dataStreamSettings
+    so-import: *dataStreamSettings
+    so-kratos: *dataStreamSettings
+    so-hydra: *dataStreamSettings
+    so-kismet: *dataStreamSettings
+    so-logstash: *dataStreamSettings
+    so-redis: *dataStreamSettings
+    so-strelka: *dataStreamSettings
+    so-syslog: *dataStreamSettings
+    so-zeek: *dataStreamSettings
+    # Managed SOC integration annotations are inserted below this line. Referencing '*dataStreamSettings'
+    so-case: &indexSettings
+      index_sorting:
+        description: Sorts the index by event time, at the cost of additional processing resource consumption.
+        forcedType: bool
+        global: True
+        advanced: True
+        helpLink: elasticsearch
+      index_template:
+        index_patterns:
+          description: Patterns for matching multiple indices or tables.
+          forcedType: "[]string"
+          multiline: True
+          global: True
+          advanced: True
+          helpLink: elasticsearch
+        template:
+          settings:
+            index:
+              number_of_replicas:
+                description: Number of replicas required for this index. Multiple replicas protects against data loss, but also increases storage costs.
+                forcedType: int
+                global: True
+                advanced: True
+                helpLink: elasticsearch
+              auto_expand_replicas:
+                description: Automatically expand the number of replicas based on the number of data nodes in the cluster. This can help ensure high availability as the cluster scales up or down.
+                forcedType: string
+                regex: "^(0-[1-9]|1-[2-9]|2-[3-9]|3-[4-9]|4-[5-9]|5-[6-9]|6-[7-9]|7-[89]|8-9|[0-9]-all|false)$"
+                regexFailureMessage: Must be in the format of "x-y" where x is minimum number of replicas and y is maximum number of replicas, or "0-all" to specify a minimum of 0 and no maximum, or "false" to disable automatic replica expansion.
+                global: True
+                advanced: True
+                helpLink: elasticsearch
+              mapping:
+                total_fields:
+                  limit:
+                    description: Max number of fields that can exist on a single index. Larger values will consume more resources.
+                    global: True
+                    advanced: True
+                    helpLink: elasticsearch
+              refresh_interval:
+                description: Seconds between index refreshes. Shorter intervals can cause query performance to suffer since this is a synchronous and resource-intensive operation.
+                global: True
+                advanced: True
+                helpLink: elasticsearch
+              number_of_shards:
+                description: Number of shards required for this index. Using multiple shards increases fault tolerance, but also increases storage and network costs.
+                global: True
+                advanced: True
+                helpLink: elasticsearch
+              sort:
+                field:
+                  description: The field to sort by. Must set index_sorting to True.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+                order:
+                  description: The order to sort by. Must set index_sorting to True.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+          mappings:
+            _meta:
+              package:
+                name:
+                  description: Meta settings for the mapping.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+              managed_by:
+                  description: Meta settings for the mapping.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+              managed:
+                  description: Meta settings for the mapping.
+                  forcedType: bool
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+        composed_of:
+          description: The index template is composed of these component templates.
+          forcedType: "[]string"
+          global: True
+          advanced: True
+          helpLink: elasticsearch
+        priority:
+          description: The priority of the index template.
+          forcedType: int
+          global: True
+          advanced: True
+          helpLink: elasticsearch
+      policy:
+        phases:
+          hot:
+            min_age:
+              description: Minimum age of index. This determines when the index should be moved to the hot tier.
+              global: True
+              advanced: True
+              helpLink: elasticsearch
+            actions:
+              set_priority:
+                priority:
+                  description: Priority of index. This is used for recovery after a node restart. Indices with higher priorities are recovered before indices with lower priorities.
+                  forcedType: int
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+              rollover:
+                max_age:
+                  description: Maximum age of index.  Once an index reaches this limit, it will be rolled over into a new index.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+                max_primary_shard_size:
+                  description: Maximum primary shard size. Once an index reaches this limit, it will be rolled over into a new index.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+              shrink:
+                method:
+                  description: Shrink the index to a new index with fewer primary shards. Shrink operation is by count or size.
+                  options:
+                  - COUNT
+                  - SIZE
+                  global: True
+                  advanced: True
+                  forcedType: string
+                number_of_shards:
+                  title: shard count
+                  description: Desired shard count. Note that this value is only used when the shrink method selected is 'COUNT'.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                max_primary_shard_size:
+                  title: max shard size
+                  description: Desired shard size in gb/tb/pb eg. 100gb. Note that this value is only used when the shrink method selected is 'SIZE'.
+                  regex: ^[0-9]+(?:gb|tb|pb)$
+                  global: True
+                  forcedType: string
+                  advanced: True
+                allow_write_after_shrink:
+                  description: Allow writes after shrink.
+                  global: True
+                  forcedType: bool
+                  default: False
+                  advanced: True
+              forcemerge:
+                max_num_segments:
+                  description: Reduce the number of segments in each index shard and clean up deleted documents.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                index_codec:
+                  title: compression
+                  description: Use higher compression for stored fields at the cost of slower performance.
+                  forcedType: bool
+                  global: True
+                  default: False
+                  advanced: True
+          warm:
+            min_age:
+              description: Minimum age of index. ex. 30d - This determines when the index should be moved to the warm tier. Nodes in the warm tier generally don’t need to be as fast as those in the hot tier. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and warm min_age set to 30 then there will be 30 days from index creation to rollover and then an additional 30 days before moving to warm tier.
+              regex: ^[0-9]{1,5}d$
+              forcedType: string
+              global: True
+              advanced: True
+              helpLink: elasticsearch
+            actions:
+              set_priority:
+                priority:
+                  description: Priority of index. This is used for recovery after a node restart. Indices with higher priorities are recovered before indices with lower priorities.
+                  forcedType: int
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+              rollover:
+                max_age:
+                  description: Maximum age of index.  Once an index reaches this limit, it will be rolled over into a new index.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+                max_primary_shard_size:
+                  description: Maximum primary shard size. Once an index reaches this limit, it will be rolled over into a new index.
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+              shrink:
+                method:
+                  description: Shrink the index to a new index with fewer primary shards. Shrink operation is by count or size.
+                  options:
+                  - COUNT
+                  - SIZE
+                  global: True
+                  advanced: True
+                number_of_shards:
+                  title: shard count
+                  description: Desired shard count. Note that this value is only used when the shrink method selected is 'COUNT'.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                max_primary_shard_size:
+                  title: max shard size
+                  description: Desired shard size in gb/tb/pb eg. 100gb. Note that this value is only used when the shrink method selected is 'SIZE'.
+                  regex: ^[0-9]+(?:gb|tb|pb)$
+                  global: True
+                  forcedType: string
+                  advanced: True
+                allow_write_after_shrink:
+                  description: Allow writes after shrink.
+                  global: True
+                  forcedType: bool
+                  default: False
+                  advanced: True
+              forcemerge:
+                max_num_segments:
+                  description: Reduce the number of segments in each index shard and clean up deleted documents.
+                  global: True
+                  forcedType: int
+                  advanced: True
+                index_codec:
+                  title: compression
+                  description: Use higher compression for stored fields at the cost of slower performance.
+                  forcedType: bool
+                  global: True
+                  default: False
+                  advanced: True
+              allocate:
+                number_of_replicas:
+                  description: Set the number of replicas. Remains the same as the previous phase by default.
+                  forcedType: int
+                  global: True
+                  advanced: True
+          cold:
+            min_age:
+              description: Minimum age of index. ex. 60d - This determines when the index should be moved to the cold tier.  While still searchable, this tier is typically optimized for lower storage costs rather than search speed. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and cold min_age set to 60 then there will be 30 days from index creation to rollover and then an additional 60 days before moving to cold tier.
+              regex: ^[0-9]{1,5}d$
+              forcedType: string
+              global: True
+              advanced: True
+              helpLink: elasticsearch
+            actions:
+              set_priority:
+                priority:
+                  description: Used for index recovery after a node restart. Indices with higher priorities are recovered before indices with lower priorities.
+                  forcedType: int
+                  global: True
+                  advanced: True
+                  helpLink: elasticsearch
+              allocate:
+                number_of_replicas:
+                  description: Set the number of replicas. Remains the same as the previous phase by default.
+                  forcedType: int
+                  global: True
+                  advanced: True
+          delete:
+            min_age:
+              description: Minimum age of index. ex. 90d - This determines when the index should be deleted. It’s important to note that this is calculated relative to the rollover date (NOT the original creation date of the index). For example, if you have an index that is set to rollover after 30 days and delete min_age set to 90 then there will be 30 days from index creation to rollover and then an additional 90 days before deletion.
+              regex: ^[0-9]{1,5}d$
+              forcedType: string
+              global: True
+              advanced: True
+              helpLink: elasticsearch
+        _meta:
+          package:
+            name:
+              description: Meta settings for the mapping.
+              global: True
+              advanced: True
+              helpLink: elasticsearch
+          managed_by:
+            description: Meta settings for the mapping.
+            global: True
+            advanced: True
+            helpLink: elasticsearch
+          managed:
+            description: Meta settings for the mapping.
+            forcedType: bool
+            global: True
+            advanced: True
+            helpLink: elasticsearch
+    sos-backup: *indexSettings
+    so-detection: *indexSettings
+    so-assistant-chat: *indexSettings
+    so-assistant-session: *indexSettings
     so-metrics-fleet_server_x_agent_status: &fleetMetricsSettings
       index_sorting:
         description: Sorts the index by event time, at the cost of additional processing resource consumption.

salt/elasticsearch/template.map.jinja

@@ -4,7 +4,11 @@
    Elastic License 2.0. #}
 
 {% import_yaml 'elasticsearch/defaults.yaml' as ELASTICSEARCHDEFAULTS %}
+{# ELASTICSEARCHMERGED only used here to collect data_retention_method. This file intentionally works with ELASTICSEARCHDEFAULTS #}
+{% from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
+
 {% set DEFAULT_GLOBAL_OVERRIDES = ELASTICSEARCHDEFAULTS.elasticsearch.index_settings.pop('global_overrides') %}
+{% set DATA_RETENTION_METHOD = ELASTICSEARCHMERGED.data_retention_method %}
 
 {% set PILLAR_GLOBAL_OVERRIDES = {} %}
 {% set ES_INDEX_PILLAR = salt['pillar.get']('elasticsearch:index_settings', {}) %}
@@ -61,15 +65,25 @@
 {% if ALL_ADDON_SETTINGS_ORIG.keys() | length > 0 %}
 {%   for index in ALL_ADDON_SETTINGS_ORIG.keys() %}
 {%     do ALL_ADDON_SETTINGS_GLOBAL_OVERRIDES.update({index: salt['defaults.merge'](ALL_ADDON_SETTINGS_ORIG[index], PILLAR_GLOBAL_OVERRIDES, in_place=False)}) %}
+{#     Explicitly excluding addon indices from ES_INDEX_SETTINGS_ORIG
+         When manager.soc_managed_annotations runs, new entries are added to the salt/elasticsearch/defaults.yaml file to support 'revert to default' functionality.
+         Subsequent map renders will then incorrectly include 'integration X' in 'ES_INDEX_SETTINGS_ORIG' due to being in the defaults.yaml file. #}
+{%     if index in ES_INDEX_SETTINGS_ORIG.keys() %}
+{%       do ES_INDEX_SETTINGS_ORIG.pop(index) %}
+{%     endif %}
 {%   endfor %}
 {% endif %}
 
 {% set ES_INDEX_SETTINGS = {} %}
-{% macro create_final_index_template(DEFINED_SETTINGS, GLOBAL_OVERRIDES, FINAL_INDEX_SETTINGS) %}
+{% macro create_final_index_template(DEFINED_SETTINGS, GLOBAL_OVERRIDES, FINAL_INDEX_SETTINGS, EXCLUDE_INDICES=[]) %}
 
 {% do GLOBAL_OVERRIDES.update(salt['defaults.merge'](GLOBAL_OVERRIDES, ES_INDEX_PILLAR, in_place=False)) %}
 {% for index, settings in GLOBAL_OVERRIDES.items() %}
 
+{%   if index in EXCLUDE_INDICES %}
+{%     continue %}
+{%   endif %}
+
 {#   prevent this action from being performed on custom defined indices. #}
 {#   the custom defined index is not present in either of the dictionaries and fails to reder. #}
 {%   if index in DEFINED_SETTINGS and index in GLOBAL_OVERRIDES %}
@@ -95,6 +109,17 @@
 {%     if not settings.get('index_sorting', False) | to_bool and settings.index_template.template.settings.index.sort is defined %}
 {%       do settings.index_template.template.settings.index.pop('sort') %}
 {%     endif %}
+{%     if DATA_RETENTION_METHOD == 'DLM' and settings.index_template.data_stream is defined and settings.data_stream_lifecycle is defined %}
+{%       if settings.data_stream_lifecycle.data_retention is defined and settings.data_stream_lifecycle.data_retention %}
+{%         do settings.index_template.template.update({'lifecycle': {'data_retention': settings.data_stream_lifecycle.data_retention}}) %}
+{%       else %}
+{%         do settings.index_template.template.update({'lifecycle': {}}) %}
+{%       endif %}
+{%       if settings.index_template.template.settings.index.lifecycle is not defined %}
+{%         do settings.index_template.template.settings.index.update({'lifecycle': {}}) %}
+{%       endif %}
+{%       do settings.index_template.template.settings.index.lifecycle.update({'prefer_ilm': false}) %}
+{%     endif %}
 {%   endif %}
 
 {# advanced ilm actions #}
@@ -150,10 +175,19 @@
 {% endfor %}
 {% endmacro %}
 
-{{ create_final_index_template(ES_INDEX_SETTINGS_ORIG, ES_INDEX_SETTINGS_GLOBAL_OVERRIDES, ES_INDEX_SETTINGS) }}
-{{ create_final_index_template(ALL_ADDON_SETTINGS_ORIG, ALL_ADDON_SETTINGS_GLOBAL_OVERRIDES, ALL_ADDON_SETTINGS) }}
+{# Exclude addon integrations from final ES_INDEX_SETTINGS #}
+{{ create_final_index_template(ES_INDEX_SETTINGS_ORIG, ES_INDEX_SETTINGS_GLOBAL_OVERRIDES, ES_INDEX_SETTINGS, ALL_ADDON_SETTINGS_ORIG.keys() | list ) }}
+
+{# Exclude SO managed indices, otherwise ALL_ADDON_SETTINGS will include pillar values
+  of core integrations without merging defaults, resulting in an overlapping, but bad index template being generated. #}
+{{ create_final_index_template(ALL_ADDON_SETTINGS_ORIG, ALL_ADDON_SETTINGS_GLOBAL_OVERRIDES, ALL_ADDON_SETTINGS, ES_INDEX_SETTINGS_ORIG.keys() | list ) }}
 
 {% set SO_MANAGED_INDICES = [] %}
 {% for index, settings in ES_INDEX_SETTINGS.items() %}
 {%   do SO_MANAGED_INDICES.append(index) %}
-{% endfor %}
+{% endfor %}
+
+{% set ADDON_INDICES = [] %}
+{% for index, settings in ALL_ADDON_SETTINGS.items() %}
+{%   do ADDON_INDICES.append(index) %}
+{% endfor %}

salt/elasticsearch/tools/sbin/so-elasticsearch-templates-load

@@ -11,10 +11,8 @@ ADDON_STATEFILE_SUCCESS=/opt/so/state/addon_estemplates.txt
 ELASTICSEARCH_TEMPLATES_DIR="/opt/so/conf/elasticsearch/templates"
 SO_TEMPLATES_DIR="${ELASTICSEARCH_TEMPLATES_DIR}/index"
 ADDON_TEMPLATES_DIR="${ELASTICSEARCH_TEMPLATES_DIR}/addon-index"
-SO_LOAD_FAILURES=0
-ADDON_LOAD_FAILURES=0
-SO_LOAD_FAILURES_NAMES=()
-ADDON_LOAD_FAILURES_NAMES=()
+FAILED_NAMES=()
+FAILED_COUNT=0
 IS_HEAVYNODE="false"
 FORCE="false"
 VERBOSE="false"
@@ -46,20 +44,86 @@ while [[ $# -gt 0 ]]; do
     shift
 done
 
+# Max number of concurrent template PUT jobs. Override via env if needed.
+MAX_TEMPLATE_JOBS=${MAX_TEMPLATE_JOBS:-10}
+
+# Block until fewer than MAX_TEMPLATE_JOBS background jobs are running.
+template_throttle() {
+    while (( $(jobs -rp | wc -l) >= MAX_TEMPLATE_JOBS )); do
+        wait -n
+    done
+}
+
+# Per-job failure markers and an output lock for serializing parallel job output.
+# Each failed load drops one file (named after the template) into FAIL_DIR; the
+# output of each job is flushed as a single block under flock so concurrent jobs
+# never interleave their (chatty) retry output.
+FAIL_DIR=$(mktemp -d)
+OUTPUT_LOCK="${FAIL_DIR}/.output.lock"
+: > "$OUTPUT_LOCK"
+trap 'rm -rf "$FAIL_DIR"' EXIT
+
+# Record a failure: $1 = the template name/path to report later. Slashes are
+# encoded so the path becomes a safe single filename.
+record_failure() {
+    local marker="${1//\//__}"
+    : > "${FAIL_DIR}/fail.${marker}"
+}
+
+# Populate FAILED_NAMES and FAILED_COUNT from the current phase's markers.
+# Must run in the current shell (not a command substitution) so the array sticks.
+collect_failures() {
+    FAILED_NAMES=()
+    FAILED_COUNT=0
+    local f name
+    shopt -s nullglob
+    for f in "${FAIL_DIR}"/fail.*; do
+        name="${f##*/fail.}"
+        name="${name//__//}"
+        FAILED_NAMES+=("$name")
+        FAILED_COUNT=$((FAILED_COUNT + 1))
+    done
+    shopt -u nullglob
+}
+
+# Clear markers and names between phases so SO and addon counts stay independent.
+reset_failures() {
+    shopt -s nullglob
+    rm -f "${FAIL_DIR}"/fail.*
+    shopt -u nullglob
+    FAILED_NAMES=()
+    FAILED_COUNT=0
+}
+
+# Print a block of text atomically (under the shared output lock) so the output
+# of concurrent background jobs is not interleaved.
+locked_echo() {
+    { flock 9; printf '%s\n' "$1"; } 9>>"$OUTPUT_LOCK"
+}
+
+# Loads one template file via PUT. Intended to be dispatched as a background job.
+#   $1 uri          - e.g. _component_template/foo or _index_template/foo
+#   $2 file         - path to the template JSON
+#   $3 report_name  - name/path to record if this load fails
 load_template() {
     local uri="$1"
     local file="$2"
+    local report_name="$3"
+    local out rc=0 block
 
-    echo "Loading template file $file"
-    if ! output=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}"); then
-        echo "$output"
-
-        return 1
-
+    # Capture everything (including retry's diagnostic chatter) into one block so
+    # concurrent jobs never interleave; the whole block is flushed under one flock.
+    block="Loading template file $file"$'\n'
+    if ! out=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}" 2>&1); then
+        block+="$out"$'\n'
+        rc=1
     elif [[ "$VERBOSE" == "true" ]]; then
-        echo "$output"
+        block+="$out"$'\n'
     fi
 
+    { flock 9; printf '%s' "$block"; } 9>>"$OUTPUT_LOCK"
+
+    (( rc != 0 )) && record_failure "$report_name"
 }
 
 check_required_component_template_exists() {
@@ -110,6 +174,9 @@ load_component_templates() {
         return
     fi
 
+    # Dispatch loads as throttled background jobs. The barrier (wait) happens in
+    # the caller after all component groups have been dispatched, since index
+    # templates must not load until every component template is in place.
     for component in "$pattern"/*.json; do
         tmpl_name=$(basename "${component%.json}")
 
@@ -118,21 +185,11 @@ load_component_templates() {
             tmpl_name="${tmpl_name%-mappings}-mappings"
         fi
 
-        if ! load_template "_component_template/${tmpl_name}" "$component"; then
-            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
-            SO_LOAD_FAILURES_NAMES+=("$component")
-        fi
+        template_throttle
+        load_template "_component_template/${tmpl_name}" "$component" "$component" &
     done
 }
 
-check_elasticsearch_responsive() {
-    # Cannot load templates if Elasticsearch is not responding.
-    #  NOTE: Slightly faster exit w/ failure than previous "retry 240 1" if there is a problem with Elasticsearch the
-    #    script should exit sooner rather than hang at the 'so-elasticsearch-templates' salt state.
-    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."
-}
-
 index_templates_exist() {
     local templates_dir="$1"
 
@@ -180,6 +237,9 @@ if [[ "$FORCE" == "true" || ! -f "$SO_STATEFILE_SUCCESS" ]] && index_templates_e
     load_component_templates "Elastic Agent" "elastic-agent"
     load_component_templates "Security Onion" "so"
 
+    # Barrier: every component template PUT must complete before we snapshot the
+    # component template list and start loading index templates that depend on them.
+    wait
     component_templates=$(so-elasticsearch-component-templates-list)
     echo -e "Loading Security Onion index templates...\n"
     for so_idx_tmpl in "${SO_TEMPLATES_DIR}"/*.json; do
@@ -189,7 +249,7 @@ if [[ "$FORCE" == "true" || ! -f "$SO_STATEFILE_SUCCESS" ]] && index_templates_e
             # TODO: Better way to load only heavynode specific templates
             if ! check_heavynode_compatiable_index_template "$tmpl_name"; then
                 if [[ "$VERBOSE" == "true" ]]; then
-                    echo "Skipping over $so_idx_tmpl, template is not a heavynode specific index template."
+                    locked_echo "Skipping over $so_idx_tmpl, template is not a heavynode specific index template."
                 fi
 
                 continue
@@ -197,32 +257,34 @@ if [[ "$FORCE" == "true" || ! -f "$SO_STATEFILE_SUCCESS" ]] && index_templates_e
         fi
 
         if check_required_component_template_exists "$so_idx_tmpl"; then
-            if ! load_template "_index_template/$tmpl_name" "$so_idx_tmpl"; then
-                SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
-                SO_LOAD_FAILURES_NAMES+=("$so_idx_tmpl")
-            fi
+            template_throttle
+            load_template "_index_template/$tmpl_name" "$so_idx_tmpl" "$so_idx_tmpl" &
         else
-            echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
-            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
-            SO_LOAD_FAILURES_NAMES+=("$so_idx_tmpl")
+            locked_echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
+            record_failure "$so_idx_tmpl"
 
             continue
         fi
     done
 
-    if [[ $SO_LOAD_FAILURES -eq 0 ]]; then
+    # Barrier: all SO index template PUTs must finish before tallying failures.
+    wait
+
+    collect_failures
+    if [[ $FAILED_COUNT -eq 0 ]]; then
         echo "All Security Onion core templates loaded successfully."
 
         touch "$SO_STATEFILE_SUCCESS"
     else
-        echo "Encountered $SO_LOAD_FAILURES failure(s) loading templates:"
-        for failed_template in "${SO_LOAD_FAILURES_NAMES[@]}"; do
+        echo "Encountered $FAILED_COUNT failure(s) loading templates:"
+        for failed_template in "${FAILED_NAMES[@]}"; do
             echo "  - $failed_template"
         done
         if [[ "$SHOULD_EXIT_ON_FAILURE" == "true" ]]; then
             fail "Failed to load all Security Onion core templates successfully."
         fi
     fi
+    reset_failures
 elif ! index_templates_exist "$SO_TEMPLATES_DIR"; then
     echo "No Security Onion core index templates found in ${SO_TEMPLATES_DIR}, skipping."
 elif [[ -f "$SO_STATEFILE_SUCCESS" ]]; then
@@ -241,26 +303,27 @@ if should_load_addon_templates; then
         tmpl_name=$(basename "${addon_idx_tmpl%-template.json}")
 
         if check_required_component_template_exists "$addon_idx_tmpl"; then
-            if ! load_template "_index_template/${tmpl_name}" "$addon_idx_tmpl"; then
-                ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
-                ADDON_LOAD_FAILURES_NAMES+=("$addon_idx_tmpl")
-            fi
+            template_throttle
+            load_template "_index_template/${tmpl_name}" "$addon_idx_tmpl" "$addon_idx_tmpl" &
         else
-            echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
-            ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
-            ADDON_LOAD_FAILURES_NAMES+=("$addon_idx_tmpl")
+            locked_echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
+            record_failure "$addon_idx_tmpl"
 
             continue
         fi
     done
 
-    if [[ $ADDON_LOAD_FAILURES -eq 0 ]]; then
+    # Barrier: all addon index template PUTs must finish before tallying failures.
+    wait
+
+    collect_failures
+    if [[ $FAILED_COUNT -eq 0 ]]; then
         echo "All addon integration templates loaded successfully."
 
         touch "$ADDON_STATEFILE_SUCCESS"
     else
-        echo "Encountered $ADDON_LOAD_FAILURES failure(s) loading addon integration templates:"
-        for failed_template in "${ADDON_LOAD_FAILURES_NAMES[@]}"; do
+        echo "Encountered $FAILED_COUNT failure(s) loading addon integration templates:"
+        for failed_template in "${FAILED_NAMES[@]}"; do
             echo "  - $failed_template"
         done
         if [[ "$SHOULD_EXIT_ON_FAILURE" == "true" ]]; then

salt/elasticsearch/tools/sbin_jinja/so-elasticsearch-dlm-apply

@@ -0,0 +1,175 @@
+#!/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-common
+
+{%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
+{%- set DATA_RETENTION_METHOD = ELASTICSEARCHMERGED.data_retention_method %}
+
+ELASTICSEARCH_TEMPLATES_DIR="${ELASTICSEARCH_TEMPLATES_DIR:-/opt/so/conf/elasticsearch/templates}"
+TEMPLATE_DIRS=(
+    "${ELASTICSEARCH_TEMPLATES_DIR}/index"
+    "${ELASTICSEARCH_TEMPLATES_DIR}/addon-index"
+)
+DATA_RETENTION_METHOD=$(cat <<'EOF'
+{{ DATA_RETENTION_METHOD }}
+EOF
+)
+DLM_FAILURES=0
+DLM_FAILURE_NAMES=()
+
+if [[ "$DATA_RETENTION_METHOD" != "DLM" && "$DATA_RETENTION_METHOD" != "ILM" ]]; then
+    echo "Unsupported data retention method $DATA_RETENTION_METHOD. Expected DLM or ILM."
+    exit 1
+fi
+
+validate_template_file() {
+    local template_file="$1"
+
+    if ! jq -e 'type == "object" and (.data_stream == null or (.data_stream | type == "object")) and (.template.lifecycle == null or (.template.lifecycle | type == "object")) and (.template.lifecycle.data_retention == null or (.template.lifecycle.data_retention | type == "string"))' >/dev/null 2>&1 "$template_file"; then
+        echo "Invalid index template JSON: $template_file"
+        return 1
+    fi
+}
+
+is_data_stream_template() {
+    jq -e '.data_stream | type == "object"' >/dev/null 2>&1 "$1"
+}
+
+has_data_stream_lifecycle() {
+    jq -e '.template.lifecycle | type == "object"' >/dev/null 2>&1 "$1"
+}
+
+get_data_retention() {
+    jq -r '.template.lifecycle.data_retention // ""' "$1"
+}
+
+find_template_file() {
+    local template="$1"
+    local template_dir
+    local template_file
+
+    for template_dir in "${TEMPLATE_DIRS[@]}"; do
+        template_file="${template_dir}/${template}-template.json"
+
+        if [[ -f "$template_file" ]]; then
+            echo "$template_file"
+            return 0
+        fi
+    done
+
+    return 1
+}
+
+set_data_stream_lifecycle() {
+    local data_stream="$1"
+    local data_retention="$2"
+    local body
+    local output
+
+    if [[ -n "$data_retention" ]]; then
+        if jq -e --arg data_stream "$data_stream" --arg data_retention "$data_retention" '.data_streams[]? | select(.name == $data_stream and .lifecycle.enabled == true and .lifecycle.data_retention == $data_retention)' >/dev/null 2>&1 <<< "$data_streams"; then
+            echo "DLM lifecycle already set for $data_stream with data_retention $data_retention, skipping."
+            return 0
+        fi
+    elif jq -e --arg data_stream "$data_stream" '.data_streams[]? | select(.name == $data_stream and .lifecycle.enabled == true and (.lifecycle.data_retention == null))' >/dev/null 2>&1 <<< "$data_streams"; then
+        echo "DLM lifecycle already set for $data_stream with indefinite retention, skipping."
+        return 0
+    fi
+
+    if [[ -n "$data_retention" ]]; then
+        body=$(jq -cn --arg data_retention "$data_retention" '{data_retention: $data_retention}')
+    else
+        # Setting indefinite retention
+        body='{}'
+    fi
+
+    if ! output=$(so-elasticsearch-query "_data_stream/${data_stream}/_lifecycle" -XPUT -d "$body" --retry 3 --retry-delay 5 --fail); then
+        echo "Failed to set data stream lifecycle for $data_stream."
+        return 1
+    fi
+
+    if [[ -n "$data_retention" ]]; then
+        echo "Set DLM lifecycle for $data_stream with data_retention $data_retention."
+    else
+        echo "Set DLM lifecycle for $data_stream with indefinite retention."
+    fi
+}
+
+disable_data_stream_lifecycle() {
+    local data_stream="$1"
+    local body='{"enabled":false}'
+    local output
+
+    if ! jq -e --arg data_stream "$data_stream" '.data_streams[]? | select(.name == $data_stream and .lifecycle != null and .lifecycle.enabled != false)' >/dev/null 2>&1 <<< "$data_streams"; then
+        # No action needed
+        return 0
+    fi
+
+    if ! output=$(so-elasticsearch-query "_data_stream/${data_stream}/_lifecycle" -XPUT -d "$body" --retry 3 --retry-delay 5 --fail); then
+        echo "Failed to disable data stream lifecycle for $data_stream."
+        return 1
+    fi
+
+    echo "Disabled DLM lifecycle for $data_stream."
+}
+
+process_data_stream() {
+    local data_stream="$1"
+    local data_retention="$2"
+
+    if [[ "$DATA_RETENTION_METHOD" == "DLM" ]]; then
+        set_data_stream_lifecycle "$data_stream" "$data_retention"
+    else
+        disable_data_stream_lifecycle "$data_stream"
+    fi
+}
+
+check_elasticsearch_responsive
+
+if ! data_streams=$(so-elasticsearch-query "_data_stream?format=json" --retry 3 --retry-delay 5 --fail); then
+    echo "Failed to retrieve data streams."
+    exit 1
+fi
+
+while read -r data_stream_config; do
+    data_stream=$(jq -r '.name' <<< "$data_stream_config")
+    template=$(jq -r '.template' <<< "$data_stream_config")
+
+    if ! template_file=$(find_template_file "$template"); then
+        echo "Skipping $data_stream: index template file not found for $template."
+        continue
+    fi
+
+    validate_template_file "$template_file" || exit 1
+
+    if ! is_data_stream_template "$template_file"; then
+        echo "Skipping $data_stream: $template_file is not a data stream template."
+        continue
+    fi
+
+    if [[ "$DATA_RETENTION_METHOD" == "DLM" ]] && ! has_data_stream_lifecycle "$template_file"; then
+        echo "Skipping $data_stream: $template_file does not define data stream lifecycle."
+        continue
+    fi
+
+    data_retention=$(get_data_retention "$template_file")
+
+    if ! process_data_stream "$data_stream" "$data_retention"; then
+        DLM_FAILURES=$((DLM_FAILURES + 1))
+        DLM_FAILURE_NAMES+=("$data_stream")
+    fi
+done < <(jq -c '.data_streams[]' <<< "$data_streams")
+
+if [[ $DLM_FAILURES -eq 0 ]]; then
+    echo "Data stream lifecycle updates completed successfully."
+else
+    echo "Encountered $DLM_FAILURES failure(s) updating data stream lifecycle:"
+    for failed_data_stream in "${DLM_FAILURE_NAMES[@]}"; do
+        echo "  - $failed_data_stream"
+    done
+    exit 1
+fi

salt/elasticsearch/tools/sbin_jinja/so-elasticsearch-ilm-policy-load

@@ -6,6 +6,48 @@
 
 . /usr/sbin/so-common
 
+MAX_JOBS=${MAX_ILM_JOBS:-10}
+
+# Lock used to serialize block writes so concurrent jobs never interleave their output.
+ILM_OUTPUT_LOCK=$(mktemp)
+ILM_FAIL_FILE=$(mktemp)
+trap 'rm -f "$ILM_OUTPUT_LOCK" "$ILM_FAIL_FILE"' EXIT
+
+# Policies are loaded concurrently (up to MAX_JOBS at a time) for speed. Each policy's block is
+# printed the moment its curl returns, so output appears in COMPLETION ORDER, not the order
+# policies are defined in configuration.
+echo "Loading ILM policies concurrently; output below appears in completion order, not configuration order."
+echo
+
+put_policy() {
+  local desc="$1" policyname="$2" data="$3" result rc=0
+  if ! result=$(curl -K /opt/so/conf/elasticsearch/curl.config -s -k -L --fail \
+    -X PUT "https://localhost:9200/_ilm/policy/${policyname}" \
+    -H 'Content-Type: application/json' -d"${data}" 2>&1); then
+    rc=1
+  elif ! jq -e '.acknowledged == true' <<<"$result" >/dev/null 2>&1; then
+    rc=1
+  fi
+
+  # curl above ran in parallel; serialize just this block write so concurrent jobs never interleave.
+  {
+    flock 200
+    printf 'Setting up %s policy...\n%s\n\n' "${desc}" "${result}"
+    if (( rc != 0 )); then
+      printf '%s\n' "${policyname}" >>"$ILM_FAIL_FILE"
+    fi
+  } 200>>"${ILM_OUTPUT_LOCK}"
+
+  return "$rc"
+}
+
+# Block until fewer than MAX_JOBS background curls are running.
+throttle() {
+  while (( $(jobs -rp | wc -l) >= MAX_JOBS )); do
+    wait -n || true
+  done
+}
+
 {%- from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS %}
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS %}
@@ -14,35 +56,36 @@
 {%- for index, settings in ES_INDEX_SETTINGS.items() %}
 {%-   if settings.policy is defined %}
 {%-     if index == 'so-logs-detections.alerts' %}
-  echo
-  echo "Setting up so-logs-detections.alerts-so policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-so" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "so-logs-detections.alerts-so" "{{ index }}-so" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     elif index == 'so-logs-soc' %}
-  echo
-  echo "Setting up so-soc-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/so-soc-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
-  echo
-  echo "Setting up {{ index }}-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "so-soc-logs" "so-soc-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
+  throttle
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     else %}
-  echo
-  echo "Setting up {{ index }}-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     endif %}
 {%-   endif %}
 {%- endfor %}
-echo
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   for index, settings in ALL_ADDON_SETTINGS.items() %}
 {%-     if settings.policy is defined %}
-  echo
-  echo "Setting up {{ index }}-logs policy..."
-  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  echo
+  throttle
+  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
 {%-     endif %}
 {%-   endfor %}
 {%- endif %}
+
+wait || true
+
+if [[ -s "$ILM_FAIL_FILE" ]]; then
+  echo "ERROR: Failed to load ILM policy(s):"
+  while read -r POLICY; do
+    echo " - $POLICY"
+  done < "$ILM_FAIL_FILE"
+  exit 1
+else
+  echo "Successfully loaded all ILM policies."
+fi

salt/kafka/enabled.sls

@@ -32,7 +32,7 @@ so-kafka:
     - networks:
       - sobridge:
         - ipv4_address: {{ DOCKERMERGED.containers['so-kafka'].ip }}
-    - user: kafka
+    - user: "960"
     - environment:
         KAFKA_HEAP_OPTS: -Xmx2G -Xms1G
         KAFKA_OPTS: "-javaagent:/opt/jolokia/agents/jolokia-agent-jvm-javaagent.jar=port=8778,host={{ DOCKERMERGED.containers['so-kafka'].ip }},policyLocation=file:/opt/jolokia/jolokia.xml {%- if KAFKA_EXTERNAL_ACCESS %} -Djava.security.auth.login.config=/opt/kafka/config/kafka_server_jaas.conf {% endif -%}"

salt/kibana/enabled.sls

@@ -6,6 +6,7 @@
 {% from 'allowed_states.map.jinja' import allowed_states %}
 {% if sls.split('.')[0] in allowed_states %}
 {%   from 'docker/docker.map.jinja' import DOCKERMERGED %}
+{%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
 {%   from 'vars/globals.map.jinja' import GLOBALS %}
 
 include:
@@ -17,7 +18,7 @@ so-kibana:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-kibana:{{ GLOBALS.so_version }}
     - hostname: kibana
-    - user: kibana
+    - user: "932:0"
     - networks:
       - sobridge:
         - ipv4_address: {{ DOCKERMERGED.containers['so-kibana'].ip }}
@@ -60,6 +61,19 @@ so-kibana:
     - watch:
       - file: kibanaconfig
 
+wait_for_so-kibana:
+  http.wait_for_successful_query:
+    - name: "http://localhost:5601/api/status"
+    - username: 'so_elastic'
+    - password: '{{ ELASTICSEARCHMERGED.auth.users.so_elastic_user.pass }}'
+    - ssl: True
+    - verify_ssl: False
+    - status: 200
+    - wait_for: 600
+    - request_interval: 15
+    - require:
+      - docker_container: so-kibana
+
 delete_so-kibana_so-status.disabled:
   file.uncomment:
     - name: /opt/so/conf/so-status/so-status.conf

salt/kratos/soc_kratos.yaml

@@ -103,7 +103,7 @@ kratos:
   config:
     session:
       lifespan: 
-        description: Defines the length of a login session.
+        description: Defines the length of a login session before it will timeout, and require a new login.
         global: True
         helpLink: kratos
       whoami:

salt/logstash/defaults.yaml

@@ -26,12 +26,12 @@ logstash:
     manager:
       - so/0011_input_endgame.conf
       - so/0012_input_elastic_agent.conf.jinja
-      - so/0013_input_lumberjack_fleet.conf
+      - so/0013_input_lumberjack_fleet.conf.jinja
       - so/9999_output_redis.conf.jinja
     receiver:
       - so/0011_input_endgame.conf
       - so/0012_input_elastic_agent.conf.jinja
-      - so/0013_input_lumberjack_fleet.conf
+      - so/0013_input_lumberjack_fleet.conf.jinja
       - so/9999_output_redis.conf.jinja
     search:
       - so/0900_input_redis.conf.jinja
@@ -69,4 +69,5 @@ logstash:
     pipeline_x_batch_x_size: 125
     pipeline_x_ecs_compatibility: disabled
   dmz_nodes: []
+  latency_metrics: False
 

salt/logstash/enabled.sls

@@ -33,7 +33,7 @@ so-logstash:
     - networks:
       - sobridge:
         - ipv4_address: {{ DOCKERMERGED.containers['so-logstash'].ip }}
-    - user: logstash
+    - user: "931:0"
     - extra_hosts:
     {% for node in LOGSTASH_NODES %}
     {%   for hostname, ip in node.items() %}

salt/logstash/pipelines/config/so/0012_input_elastic_agent.conf.jinja

@@ -1,3 +1,4 @@
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED %}
 input {
   elastic_agent {
     port => 5055
@@ -11,10 +12,15 @@ input {
   }
 }
 filter {
-if ![metadata] {
-  mutate {
-    rename => {"@metadata" => "metadata"}
+  {% if LOGSTASH_MERGED.get('latency_metrics', False) %}
+  ruby {
+    code => "event.set('[_tmp][logstash_from_agent]', Time.now().utc.iso8601(3));"
+  }
+  {% endif %}
+  if ![metadata] {
+    mutate {
+      rename => {"@metadata" => "metadata"}
+    }
   }
 }
-}
 

salt/logstash/pipelines/config/so/0013_input_lumberjack_fleet.conf

@@ -1,23 +0,0 @@
-input {
-  elastic_agent {
-    port => 5056
-    tags => [ "elastic-agent", "fleet-lumberjack-input" ]
-    ssl_enabled => true
-    ssl_certificate => "/usr/share/logstash/elasticfleet-lumberjack.crt"
-    ssl_key => "/usr/share/logstash/elasticfleet-lumberjack.key"
-    ecs_compatibility => v8
-    id => "fleet-lumberjack-in"  
-    codec => "json"
-  }
-}
-
-
-filter {
-if ![metadata] {
-  mutate {
-    rename => {"@metadata" => "metadata"}
-  }
-}
-}
-
-

salt/logstash/pipelines/config/so/0013_input_lumberjack_fleet.conf.jinja

@@ -0,0 +1,26 @@
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED %}
+input {
+  elastic_agent {
+    port => 5056
+    tags => [ "elastic-agent", "fleet-lumberjack-input" ]
+    ssl_enabled => true
+    ssl_certificate => "/usr/share/logstash/elasticfleet-lumberjack.crt"
+    ssl_key => "/usr/share/logstash/elasticfleet-lumberjack.key"
+    ecs_compatibility => v8
+    id => "fleet-lumberjack-in"
+    codec => "json"
+  }
+}
+
+filter {
+  {% if LOGSTASH_MERGED.get('latency_metrics', False) %}
+  ruby {
+    code => "event.set('[_tmp][logstash_from_fleet]', Time.now().utc.iso8601(3));"
+  }
+  {% endif %}
+  if ![metadata] {
+    mutate {
+      rename => {"@metadata" => "metadata"}
+    }
+  }
+}

salt/logstash/pipelines/config/so/0800_input_kafka.conf.jinja

@@ -1,3 +1,4 @@
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED %}
 {%- set kafka_password = salt['pillar.get']('kafka:config:password') %}
 {%- set kafka_trustpass = salt['pillar.get']('kafka:config:trustpass') %}
 {%- set kafka_brokers = salt['pillar.get']('kafka:nodes', {}) %}
@@ -30,6 +31,11 @@ input {
     }
 }
 filter {
+  {% if LOGSTASH_MERGED.get('latency_metrics', False) %}
+  ruby {
+    code => "event.set('[_tmp][logstash_from_kafka]', Time.now().utc.iso8601(3));"
+  }
+  {% endif %}
   if ![metadata] {
     mutate {
       rename => { "@metadata" => "metadata" }

salt/logstash/pipelines/config/so/0900_input_redis.conf.jinja

@@ -1,4 +1,4 @@
-{%- from 'logstash/map.jinja' import LOGSTASH_REDIS_NODES with context %}
+{%- from 'logstash/map.jinja' import LOGSTASH_REDIS_NODES, LOGSTASH_MERGED %}
 {%- set REDIS_PASS = salt['pillar.get']('redis:config:requirepass') %}
 
 {%- for index in range(LOGSTASH_REDIS_NODES|length) %}
@@ -18,3 +18,10 @@ input {
 }
 {%   endfor %}
 {% endfor -%}
+filter {
+  {% if LOGSTASH_MERGED.get('latency_metrics', False) %}
+  ruby {
+    code => "event.set('[_tmp][logstash_from_redis]', Time.now().utc.iso8601(3));"
+  }
+  {% endif %}
+}

salt/logstash/pipelines/config/so/9805_output_elastic_agent.conf.jinja

@@ -1,3 +1,11 @@
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED %}
+{% if LOGSTASH_MERGED.get('latency_metrics', False) %}
+filter {
+  ruby {
+    code => "event.set('[_tmp][logstash_to_elasticsearch]', Time.now().utc.iso8601(3));"
+  }
+}
+{% endif %}
 output {
   if "elastic-agent" in [tags] and "so-ip-mappings" in [tags] {
     elasticsearch {

salt/logstash/pipelines/config/so/9806_output_lumberjack_fleet.conf.jinja

@@ -13,13 +13,20 @@ filter {
                     add_tag => "fleet-lumberjack-{{ GLOBALS.hostname }}"
           }
   }
-
-output { 
-    lumberjack { 
-        codec => json 
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED %}
+{% if LOGSTASH_MERGED.get('latency_metrics', False) %}
+filter {
+  ruby {
+    code => "event.set('[_tmp][fleet_to_logstash]', Time.now().utc.iso8601(3));"
+  }
+}
+{% endif %}
+output {
+    lumberjack {
+        codec => json
         hosts => {{  FAILOVER_LOGSTASH_NODES }}
         ssl_certificate => "/usr/share/filebeat/ca.crt"
-        port => 5056 
+        port => 5056
         id => "fleet-lumberjack-{{ GLOBALS.hostname }}"
-        } 
+        }
     }

salt/logstash/pipelines/config/so/9999_output_redis.conf.jinja

@@ -1,10 +1,17 @@
+{%- from 'logstash/map.jinja' import LOGSTASH_MERGED %}
 {%- if grains.role in ['so-heavynode', 'so-receiver'] %}
   {%- set HOST = GLOBALS.hostname %}
 {%- else %}
   {%- set HOST = GLOBALS.manager %}
 {%- endif %}
 {%- set REDIS_PASS = salt['pillar.get']('redis:config:requirepass') %}
-
+{% if LOGSTASH_MERGED.get('latency_metrics', False) %}
+filter {
+  ruby {
+    code => "event.set('[_tmp][logstash_to_redis]', Time.now().utc.iso8601(3));"
+  }
+}
+{% endif %}
 output {
 	redis {
 		host => '{{ HOST }}'

salt/logstash/soc_logstash.yaml

@@ -86,3 +86,8 @@ logstash:
     multiline: True
     advanced: True
     forcedType: "[]string"
+  latency_metrics:
+    description: Enable latency metrics within events processed by logstash. Useful for pinpointing log ingest delay.
+    forcedType: bool
+    global: False
+    advanced: True

salt/manager/files/mirror-kernel.txt

@@ -0,0 +1,2 @@
+https://repo.securityonion.net/file/so-repo/prod/3/oracle/9-uek8
+https://repo-alt.securityonion.net/prod/3/oracle/9-uek8

salt/manager/files/repodownload.conf

@@ -10,4 +10,9 @@ keepcache=0
 name=Security Onion Repo repo
 mirrorlist=file:///opt/so/conf/reposync/mirror.txt
 enabled=1
-gpgcheck=1
+gpgcheck=1
+[securityonionkernelsync]
+name=Security Onion Kernel Repo repo
+mirrorlist=file:///opt/so/conf/reposync/mirror-kernel.txt
+enabled=1
+gpgcheck=1

salt/manager/init.sls

@@ -86,6 +86,28 @@ repo_dir:
       - group
     - show_changes: False
 
+kernelrepo_dir:
+  file.directory:
+    - name: /nsm/kernelrepo
+    - user: socore
+    - group: socore
+    - recurse:
+      - user
+      - group
+    - show_changes: False
+
+# Ensure /nsm/kernelrepo is always a valid (if empty) repo before it is ever assigned to
+# a client. Without repodata/repomd.xml an enabled file:///nsm/kernelrepo repo makes every
+# dnf operation fail; so-repo-sync only populates it after the highstate, so seed an empty
+# repo here. Only runs when repodata is missing, so it won't clobber a synced repo.
+kernelrepo_init_empty:
+  cmd.run:
+    - name: createrepo /nsm/kernelrepo
+    - unless: 'test -e /nsm/kernelrepo/repodata/repomd.xml'
+    - require:
+      - file: kernelrepo_dir
+      - pkg: install_createrepo
+
 manager_sbin:
   file.recurse:
     - name: /usr/sbin
@@ -122,6 +144,13 @@ so-repo-mirrorlist:
     - user: socore
     - group: socore
 
+so-repo-kernel-mirrorlist:
+  file.managed:
+    - name: /opt/so/conf/reposync/mirror-kernel.txt
+    - source: salt://manager/files/mirror-kernel.txt
+    - user: socore
+    - group: socore
+
 so-repo-sync:
   {%     if MANAGERMERGED.reposync.enabled %}
   cron.present:

salt/manager/managed_soc_annotations.sls

@@ -16,40 +16,35 @@
 {%       endif %}
 {%     endfor %}
 {%   endfor %}
+{%   set soc_annotation_lines = [] %}
+{%   set defaults_lines = [] %}
+{%   for k in matched_integration_names %}
+{%     do soc_annotation_lines.append('    ' ~ k ~ ': *dataStreamSettings') %}
+{%     do defaults_lines.append('    ' ~ k ~ ':') %}
+{%     set defaults_yaml = salt['slsutil.serialize']('yaml', ADDON_INTEGRATION_DEFAULTS[k], default_flow_style=False).strip() %}
+{%     for line in defaults_yaml.splitlines() %}
+{%       do defaults_lines.append('      ' ~ line) %}
+{%     endfor %}
+{%   endfor %}
 {%   set es_soc_annotations = '/opt/so/saltstack/default/salt/elasticsearch/soc_elasticsearch.yaml' %}
-{{   es_soc_annotations }}:
-     file.serialize:
-       - dataset:
-           {% set data = salt['file.read'](es_soc_annotations) | load_yaml %}
-           {% set es = data.get('elasticsearch', {}) %}
-           {% set index_settings = es.get('index_settings', {}) %}
-           {% set input = index_settings.get('so-logs', {}) %}
-           {% for k in matched_integration_names %}
-           {%   do index_settings.update({k: input}) %}
-           {% endfor %}
-           {% for k in addon_integration_keys %}
-           {%   if k not in matched_integration_names and k in index_settings %}
-           {%     do index_settings.pop(k) %}
-           {%   endif %}
-           {% endfor %}
-           {{ data }}
+manage_soc_annotations:
+  file.blockreplace:
+    - name: {{ es_soc_annotations }}
+    - marker_start: '    # START managed SOC integration annotations'
+    - marker_end: '    # END managed SOC integration annotations'
+    - content: {{ soc_annotation_lines | join('\n') | tojson }}
+    - insert_after_match: '^    # Managed SOC integration annotations are inserted below this line\.'
+    - append_if_not_found: False
+    - show_changes: True
 
 {#   Managed elasticsearch/defaults.yaml file for enabling 'Revert to default' via SOC UI for newly added config items #}
 {%   set es_defaults = '/opt/so/saltstack/default/salt/elasticsearch/defaults.yaml' %}
 {{   es_defaults }}:
-     file.serialize:
-       - dataset:
-           {% set data = salt['file.read'](es_defaults) | load_yaml %}
-           {% set es = data.get('elasticsearch', {}) %}
-           {% set index_settings = es.get('index_settings', {}) %}
-           {% for k in matched_integration_names %}
-           {%   set input = ADDON_INTEGRATION_DEFAULTS[k] %}
-           {%     do index_settings.update({k: input})%}
-           {% endfor %}
-           {% for k in addon_integration_keys %}
-           {%   if k not in matched_integration_names and k in index_settings %}
-           {%     do index_settings.pop(k) %}
-           {%   endif %}
-           {% endfor %}
-           {{ data }}
-{% endif %}
+  file.blockreplace:
+    - marker_start: '    # START managed SOC integration defaults'
+    - marker_end: '    # END managed SOC integration defaults'
+    - content: {{ defaults_lines | join('\n') | tojson }}
+    - insert_after_match: '^  index_settings:$'
+    - append_if_not_found: False
+    - show_changes: True
+{% endif %}

salt/manager/sync_es_users.sls

@@ -31,11 +31,13 @@ sync_es_users:
       - http: wait_for_kratos
       - file: so-user.lock # require so-user.lock file to be missing
 
-# we dont want this added too early in setup, so we add the onlyif to verify 'startup_states: highstate'
-# is in the minion config. That line is added before the final highstate during setup
+# we dont want this added too early in setup, so the onlyif gates on the
+# /opt/so/state/setup-complete marker. The marker is written by
+# mark_setup_complete in setup/so-functions just before the final setup
+# highstate (and by an upgrade-path state for systems set up under the old gate).
 so-user_sync:
   cron.present:
     - user: root
     - name: 'PATH=/usr/local/sbin:/usr/local/bin:/sbin:/bin:/usr/sbin:/usr/bin:/root/bin /usr/sbin/so-user sync &>> /opt/so/log/soc/sync.log'
     - identifier: so-user_sync
-    - onlyif: "grep -x 'startup_states: highstate' /etc/salt/minion"
+    - onlyif: "test -e /opt/so/state/setup-complete"

salt/manager/tools/sbin/so-boot-mine-update

@@ -0,0 +1,117 @@
+#!/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.
+
+# Runs once per boot on managers (via so-boot-mine-update.service), before
+# so-boot-highstate.service. Waits for the responsive minion set to settle, pushes
+# mine.update, waits until every up minion has actually reported to the mine, then
+# warms the master's per-minion pillar cache so the mine-backed node pillars (node
+# IPs, ES/Redis/Logstash/hypervisor discovery -- some glob- and some pillar/grain-
+# targeted) are complete before the boot highstate renders them. Otherwise a node
+# that is up but not yet fully reported gets dropped from those pillars and torn
+# out of the configs they build (e.g. so-elasticsearch ExtraHosts -> container recreate).
+
+MAX_WAIT=${MINE_UPDATE_MAX_WAIT:-180}   # hard backstop only
+INTERVAL=10
+STABLE_CHECKS=3                          # up-count must hold steady this many polls
+elapsed=0
+prev=-1
+stable=0
+up=0
+
+# Wait for the *reachable* minion set to settle rather than for every accepted
+# key to report up: an operator may accept a minion's key and then intentionally
+# power off that host, so requiring up >= accepted would never be satisfied and
+# we'd always burn the full MAX_WAIT. Once the responsive count stops growing we
+# stop waiting and run mine.update against whoever is up.
+while [ "$elapsed" -lt "$MAX_WAIT" ]; do
+  up=$(/usr/bin/salt-run manage.up --out=json 2>/dev/null \
+    | python3 -c 'import sys,json; print(len(json.load(sys.stdin)))' 2>/dev/null)
+  up=${up:-0}
+  if [ "$up" -gt 0 ] && [ "$up" -eq "$prev" ]; then
+    stable=$((stable + 1))
+    [ "$stable" -ge "$STABLE_CHECKS" ] && break
+  else
+    stable=0
+  fi
+  prev=$up
+  sleep "$INTERVAL"
+  elapsed=$((elapsed + INTERVAL))
+done
+
+echo "so-boot-mine-update: ${up} minions up (settled after ${elapsed}s); running mine.update"
+/usr/bin/salt '*' mine.update --out=txt
+
+# A node that is up but has not yet re-reported network.ip_addrs to the mine is
+# silently dropped from mine-backed pillars (elasticsearch:nodes, node_data, ...)
+# when highstate recompiles them -- which e.g. removes it from so-elasticsearch
+# ExtraHosts and forces a container recreate. After the broad mine.update above,
+# wait until every up minion actually has network.ip_addrs in the mine, re-pushing
+# mine.update to stragglers, before releasing the boot highstate. Bounded by the
+# same MAX_WAIT backstop so a slow/down node never blocks boot indefinitely.
+missing=""
+while [ "$elapsed" -lt "$MAX_WAIT" ]; do
+  up_json=$(/usr/bin/salt-run manage.up --out=json 2>/dev/null)
+  mine_json=$(/usr/bin/salt-run mine.get '*' network.ip_addrs tgt_type=glob --out=json 2>/dev/null)
+  missing=$(printf '%s' "$up_json" | python3 -c '
+import sys, json
+up = set(json.load(sys.stdin) or [])
+mine = {k for k, v in (json.loads(sys.argv[1]) or {}).items() if v}
+print("\n".join(sorted(up - mine)))
+' "$mine_json" 2>/dev/null)
+  if [ -z "$missing" ]; then
+    echo "so-boot-mine-update: mine complete for all up minions after ${elapsed}s"
+    break
+  fi
+  echo "so-boot-mine-update: mine missing up minion(s): $(echo $missing); re-running mine.update"
+  for m in $missing; do /usr/bin/salt "$m" mine.update --out=txt; done
+  sleep "$INTERVAL"
+  elapsed=$((elapsed + INTERVAL))
+done
+[ -n "$missing" ] && echo "so-boot-mine-update: WARNING ${MAX_WAIT}s backstop hit; up minion(s) still absent from mine: $(echo $missing); highstate may drop them from configs"
+
+# The pillar/compound-targeted node pillars (elasticsearch:nodes, redis:nodes,
+# logstash:nodes, hypervisor:nodes) resolve their target against the master's
+# per-minion data cache (grains+pillar in .../minions/<id>/data.p), populated only
+# when a minion's pillar is (re)compiled -- separately from the mine. A freshly
+# booted node can be in the mine (glob/node_data sees it) yet absent from that
+# cache, so it is dropped from those pillars and from the configs they build (e.g.
+# so-elasticsearch ExtraHosts). Force a synchronous pillar refresh so the master
+# caches every up node's pillar; refresh_pillar wait=True returns only once the
+# pillar is recompiled (and thus cached for matching). Retry stragglers <= MAX_WAIT.
+echo "so-boot-mine-update: warming master pillar cache for pillar/grain-targeted node pillars"
+/usr/bin/salt '*' saltutil.refresh_pillar wait=True --out=txt
+missing=""
+while [ "$elapsed" -lt "$MAX_WAIT" ]; do
+  up_json=$(/usr/bin/salt-run manage.up --out=json 2>/dev/null)
+  cached_json=$(/usr/bin/salt-run cache.pillar tgt='*' --out=json 2>/dev/null)
+  missing=$(printf '%s' "$up_json" | python3 -c '
+import sys, json
+up = set(json.load(sys.stdin) or [])
+cached = {k for k, v in (json.loads(sys.argv[1]) or {}).items() if v}
+print("\n".join(sorted(up - cached)))
+' "$cached_json" 2>/dev/null)
+  if [ -z "$missing" ]; then
+    echo "so-boot-mine-update: pillar cache warm for all up minions after ${elapsed}s"
+    break
+  fi
+  echo "so-boot-mine-update: pillar not yet cached for: $(echo $missing); refreshing"
+  for m in $missing; do /usr/bin/salt "$m" saltutil.refresh_pillar wait=True --out=txt; done
+  sleep "$INTERVAL"
+  elapsed=$((elapsed + INTERVAL))
+done
+[ -n "$missing" ] && echo "so-boot-mine-update: WARNING ${MAX_WAIT}s backstop hit; pillar not cached for: $(echo $missing); pillar-targeted pillars may drop them"
+
+# Log what the mine-backed pillars render so the boot-time state is inspectable.
+/usr/bin/salt-call saltutil.refresh_pillar >/dev/null 2>&1
+sleep 2
+for key in node_data elasticsearch:nodes; do
+  rendered=$(/usr/bin/salt-call --out=json pillar.get "$key" 2>/dev/null \
+    | python3 -c 'import sys,json; print(json.dumps(json.load(sys.stdin).get("local"), indent=2, sort_keys=True))' 2>/dev/null)
+  echo "so-boot-mine-update: ${key} rendered as:"
+  echo "${rendered:-null}"
+done
+exit 0

salt/manager/tools/sbin/so-detections-overrides-import

@@ -0,0 +1,381 @@
+#!/usr/bin/env python3
+
+# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
+# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
+# https://securityonion.net/license; you may not use this file except in compliance with the
+# Elastic License 2.0.
+
+# Imports detection overrides (e.g. from so-detections-backup) into the so-detection
+# index. Reads <publicId>.<ext> files (NDJSON, one override per line) from a source
+# directory, looks up the matching detection by publicId+engine, validates each
+# override against the same rules SOC enforces, dedupes against existing overrides
+# (operational fields only), and appends new ones.
+
+import argparse
+import ipaddress
+import json
+import os
+import re
+import sys
+from datetime import datetime
+
+import requests
+from requests.auth import HTTPBasicAuth
+import urllib3
+
+urllib3.disable_warnings(urllib3.exceptions.InsecureRequestWarning)
+
+DEFAULT_INDEX = "so-detection"
+AUTH_FILE = "/opt/so/conf/elasticsearch/curl.config"
+ES_URL = "https://localhost:9200"
+
+# Engines we know how to handle and the file extension the backup script writes.
+ENGINES = {
+    "suricata": "txt",
+}
+
+# Standard Suricata variables that ship with Security Onion. Anything else
+# referenced in an override is "custom" and the user needs to make sure it
+# exists in SOC Config before the override will function.
+BUILTIN_SURICATA_VARS = {
+    "$HOME_NET", "$EXTERNAL_NET",
+    "$HTTP_SERVERS", "$DNS_SERVERS", "$SQL_SERVERS", "$SMTP_SERVERS",
+    "$TELNET_SERVERS", "$AIM_SERVERS", "$DC_SERVERS", "$MODBUS_SERVER",
+    "$MODBUS_CLIENT", "$ENIP_CLIENT", "$ENIP_SERVER",
+    "$HTTP_PORTS", "$SHELLCODE_PORTS", "$ORACLE_PORTS", "$SSH_PORTS",
+    "$FTP_PORTS", "$FILE_DATA_PORTS",
+}
+
+VAR_PATTERN = re.compile(r"\$[A-Z_][A-Z0-9_]*")
+
+# Canonical valid values, per securityonion-soc/model/detection.go.
+SURICATA_OVERRIDE_TYPES = {"suppress", "threshold", "modify"}
+SUPPRESS_TRACKS = {"by_src", "by_dst", "by_either"}
+THRESHOLD_TRACKS = {"by_src", "by_dst", "by_both"}
+THRESHOLD_TYPES = {"limit", "threshold", "both"}
+
+STALE_WARNING = """\
+WARNING: so-detections-backup does not remove backup files when overrides are
+deleted via the Security Onion web UI. As a result, files in the source
+directory may represent overrides that were intentionally deleted and should
+NOT be re-imported.
+
+Before continuing, verify that the source directory reflects the overrides you
+actually want imported. Remove any files corresponding to overrides you previously deleted.
+"""
+
+
+def make_session(auth_file):
+    with open(auth_file, "r") as f:
+        for line in f:
+            if line.startswith("user ="):
+                creds = line.split("=", 1)[1].strip().replace('"', "")
+                user, _, password = creds.partition(":")
+                session = requests.Session()
+                session.auth = HTTPBasicAuth(user, password)
+                session.headers.update({"Content-Type": "application/json"})
+                session.verify = False
+                return session
+    raise RuntimeError(f"Could not find 'user =' line in {auth_file}")
+
+
+def find_detection(session, index, public_id, engine):
+    query = {
+        "query": {"bool": {"must": [
+            {"term": {"so_detection.publicId": public_id}},
+            {"term": {"so_detection.engine": engine}},
+        ]}},
+        "size": 2,
+    }
+    r = session.get(f"{ES_URL}/{index}/_search", json=query)
+    r.raise_for_status()
+    hits = r.json().get("hits", {}).get("hits", [])
+    if not hits:
+        return None, None, None
+    if len(hits) > 1:
+        # Shouldn't happen — publicId is unique per engine — but flag it.
+        print(f"  WARN: {len(hits)} detections matched publicId={public_id} engine={engine}; using first")
+    hit = hits[0]
+    existing = hit["_source"].get("so_detection", {}).get("overrides") or []
+    return hit["_id"], hit["_index"], existing
+
+
+def update_overrides(session, doc_index, doc_id, overrides):
+    body = {"doc": {"so_detection": {"overrides": overrides}}}
+    r = session.post(f"{ES_URL}/{doc_index}/_update/{doc_id}", json=body)
+    r.raise_for_status()
+    return r.json()
+
+
+def dedupe_key(override):
+    """Operational fields only, per Override.Equal() in detection.go.
+    Excludes timestamps and isEnabled so re-imports don't appear unique."""
+    t = override.get("type")
+    if t == "suppress":
+        return (t, override.get("track"), override.get("ip"))
+    if t == "threshold":
+        return (t, override.get("thresholdType"), override.get("track"),
+                override.get("count"), override.get("seconds"))
+    if t == "modify":
+        return (t, override.get("regex"), override.get("value"))
+
+
+def _validate_suricata_ip(ip):
+    if not ip:
+        return "ip cannot be empty"
+    if ip.startswith("$"):
+        return None
+    if ip.startswith("[") and ip.endswith("]"):
+        for part in ip[1:-1].split(","):
+            err = _validate_single_ip(part.strip())
+            if err:
+                return f"invalid IP in list: {err}"
+        return None
+    return _validate_single_ip(ip)
+
+
+def _validate_single_ip(ip):
+    try:
+        if "/" in ip:
+            ipaddress.ip_network(ip, strict=False)
+        else:
+            ipaddress.ip_address(ip)
+    except ValueError:
+        return f"invalid IP/CIDR {ip!r}"
+    return None
+
+
+def validate_override(override, engine):
+    """Mirror Override.Validate() from securityonion-soc/model/detection.go.
+    Returns None on success, an error string otherwise."""
+    t = override.get("type")
+    if not t:
+        return "override type is required"
+    if t not in SURICATA_OVERRIDE_TYPES:
+        return f"invalid type {t!r}: must be one of {sorted(SURICATA_OVERRIDE_TYPES)}"
+
+    has = {k: override.get(k) is not None for k in
+           ("regex", "value", "thresholdType", "track", "ip", "count", "seconds", "customFilter")}
+
+    if t == "suppress":
+        if not has["ip"] or not has["track"]:
+            return "suppress requires 'ip' and 'track'"
+        if any(has[k] for k in ("regex", "value", "thresholdType", "count", "seconds", "customFilter")):
+            return "suppress has unnecessary fields"
+        if override["track"] not in SUPPRESS_TRACKS:
+            return f"invalid track {override['track']!r}: must be one of {sorted(SUPPRESS_TRACKS)}"
+        return _validate_suricata_ip(override["ip"])
+
+    if t == "threshold":
+        if not all(has[k] for k in ("thresholdType", "track", "count", "seconds")):
+            return "threshold requires 'thresholdType', 'track', 'count', 'seconds'"
+        if any(has[k] for k in ("regex", "value", "customFilter")):
+            return "threshold has unnecessary fields"
+        if override["thresholdType"] not in THRESHOLD_TYPES:
+            return f"invalid thresholdType {override['thresholdType']!r}: must be one of {sorted(THRESHOLD_TYPES)}"
+        if override["track"] not in THRESHOLD_TRACKS:
+            return f"invalid track {override['track']!r}: must be one of {sorted(THRESHOLD_TRACKS)}"
+        if not isinstance(override["count"], int) or override["count"] <= 0:
+            return f"count must be a positive integer, got {override['count']!r}"
+        if not isinstance(override["seconds"], int) or override["seconds"] <= 0:
+            return f"seconds must be a positive integer, got {override['seconds']!r}"
+        return None
+
+    if t == "modify":
+        if not has["regex"] or not has["value"]:
+            return "modify requires 'regex' and 'value'"
+        if any(has[k] for k in ("thresholdType", "track", "count", "seconds", "customFilter")):
+            return "modify has unnecessary fields"
+        try:
+            re.compile(override["regex"])
+        except re.error as e:
+            return f"invalid regex: {e}"
+        return None
+
+
+def parse_overrides_file(path):
+    """Parse a file written by so-detections-backup.py: NDJSON, one override
+    per line. Returns a list of (override_dict, line_number)."""
+    overrides = []
+    with open(path, "r") as f:
+        for i, line in enumerate(f, start=1):
+            line = line.strip()
+            if not line:
+                continue
+            overrides.append((json.loads(line), i))
+    return overrides
+
+
+def describe(override):
+    """Human-readable summary of the operational fields for a given override type."""
+    t = override.get("type")
+    if t == "suppress":
+        return f"type=suppress track={override.get('track')} ip={override.get('ip')}"
+    if t == "threshold":
+        return (f"type=threshold track={override.get('track')} "
+                f"thresholdType={override.get('thresholdType')} "
+                f"count={override.get('count')} seconds={override.get('seconds')}")
+    if t == "modify":
+        return f"type=modify regex={override.get('regex')!r}"
+
+
+def collect_custom_vars(override):
+    found = set()
+    for value in override.values():
+        if isinstance(value, str):
+            for match in VAR_PATTERN.findall(value):
+                if match not in BUILTIN_SURICATA_VARS:
+                    found.add(match)
+    return found
+
+
+def parse_args():
+    p = argparse.ArgumentParser(
+        description="Import detection overrides into the so-detection index.",
+    )
+    p.add_argument("--source", "-s", required=True,
+                   help="Source directory containing <publicId>.<ext> override files.")
+    p.add_argument("--engine", "-e", default="suricata", choices=list(ENGINES.keys()),
+                   help="Detection engine (default: suricata).")
+    p.add_argument("--dry-run", "-n", action="store_true",
+                   help="Print what would happen without writing to Elasticsearch.")
+    p.add_argument("--no-import-note", action="store_true",
+                   help="Do not prepend '[Imported YYYY-MM-DD] ' to the override note.")
+    p.add_argument("--index", "-i", default=DEFAULT_INDEX,
+                   help=f"Elasticsearch index to update (default: {DEFAULT_INDEX}).")
+    return p.parse_args()
+
+
+def confirm_proceed(args):
+    """Show the stale-backup warning. Dry-run prints it and continues. Real
+    runs require the user typing 'yes' at the prompt."""
+    print(STALE_WARNING)
+    if args.dry_run:
+        print("(dry-run: no acknowledgement required)\n")
+        return True
+    answer = input("Type 'yes' to acknowledge and continue: ").strip().lower()
+    print()
+    return answer == "yes"
+
+
+def main():
+    args = parse_args()
+
+    if not os.path.isdir(args.source):
+        print(f"ERROR: source directory not found: {args.source}", file=sys.stderr)
+        sys.exit(1)
+
+    extension = ENGINES[args.engine]
+    files = sorted(f for f in os.listdir(args.source) if f.endswith(f".{extension}"))
+    if not files:
+        print(f"No *.{extension} files found in {args.source}")
+        sys.exit(0)
+
+    if not confirm_proceed(args):
+        print("Aborted.")
+        sys.exit(1)
+
+    session = make_session(AUTH_FILE)
+    today = datetime.now().strftime("%Y-%m-%d")
+    note_prefix = "" if args.no_import_note else f"[Imported {today}] "
+
+    counts = {"added": 0, "skipped_dedupe": 0, "skipped_not_found": 0, "invalid": 0, "error": 0}
+    custom_vars = set()
+
+    mode = "DRY-RUN" if args.dry_run else "IMPORT"
+    print(f"[{mode}] engine={args.engine} source={args.source} index={args.index}\n")
+
+    for filename in files:
+        public_id = os.path.splitext(filename)[0]
+        path = os.path.join(args.source, filename)
+        print(f"{public_id}:")
+
+        try:
+            new_overrides = parse_overrides_file(path)
+        except (json.JSONDecodeError, OSError) as e:
+            print(f"  ERROR: could not parse {filename}: {e}")
+            counts["error"] += 1
+            continue
+
+        if not new_overrides:
+            print("  SKIP: empty file")
+            continue
+
+        try:
+            doc_id, doc_index, existing = find_detection(session, args.index, public_id, args.engine)
+        except requests.HTTPError as e:
+            print(f"  ERROR: search failed: {e}")
+            counts["error"] += 1
+            continue
+
+        if doc_id is None:
+            print(f"  WARN: no detection found for publicId={public_id} engine={args.engine}; skipping")
+            counts["skipped_not_found"] += len(new_overrides)
+            continue
+
+        existing_keys = {dedupe_key(o) for o in existing}
+        merged = list(existing)
+        added_this_file = 0
+
+        for override, line_no in new_overrides:
+            err = validate_override(override, args.engine)
+            if err:
+                print(f"  INVALID (line {line_no}): {err}")
+                counts["invalid"] += 1
+                continue
+
+            custom_vars.update(collect_custom_vars(override))
+            key = dedupe_key(override)
+            if key in existing_keys:
+                print(f"  SKIP (line {line_no}): duplicate of existing override [{describe(override)}]")
+                counts["skipped_dedupe"] += 1
+                continue
+
+            if note_prefix:
+                override = dict(override)
+                override["note"] = note_prefix + (override.get("note") or "")
+
+            merged.append(override)
+            existing_keys.add(key)
+            added_this_file += 1
+            print(f"  ADD (line {line_no}): {describe(override)}")
+
+        if added_this_file == 0:
+            continue
+
+        if args.dry_run:
+            print(f"  DRY-RUN: would update {doc_index}/{doc_id} "
+                  f"({len(existing)} existing → {len(merged)} total)")
+            counts["added"] += added_this_file
+            continue
+
+        try:
+            update_overrides(session, doc_index, doc_id, merged)
+            print(f"  UPDATED {doc_index}/{doc_id} ({len(existing)} → {len(merged)})")
+            counts["added"] += added_this_file
+        except requests.HTTPError as e:
+            print(f"  ERROR: update failed: {e}")
+            counts["error"] += 1
+
+    print()
+    print("=" * 60)
+    print(f"Summary ({mode}):")
+    print(f"  Overrides added:           {counts['added']}")
+    print(f"  Skipped (already present): {counts['skipped_dedupe']}")
+    print(f"  Skipped (no detection):    {counts['skipped_not_found']}")
+    print(f"  Invalid (failed checks):   {counts['invalid']}")
+    print(f"  Errors:                    {counts['error']}")
+
+    if custom_vars:
+        print()
+        print("WARNING: detected custom Suricata variables in imported overrides:")
+        for v in sorted(custom_vars):
+            print(f"  {v}")
+        print("If any of these are not already defined in SOC Config (Suricata variables),")
+        print("you must add them manually before the rules will function correctly.")
+
+    sys.exit(0 if counts["error"] == 0 and counts["invalid"] == 0 else 1)
+
+
+if __name__ == "__main__":
+    main()

salt/manager/tools/sbin/so-detections-overrides-import_test.py

@@ -0,0 +1,588 @@
+# 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 importlib.util
+import json
+import os
+import shutil
+import sys
+import tempfile
+import unittest
+from importlib.machinery import SourceFileLoader
+from io import StringIO
+from unittest.mock import MagicMock, patch
+
+import requests
+
+# The script has no .py extension; spec_from_file_location can't auto-detect a
+# loader, so we hand it a SourceFileLoader explicitly. (load_module() is
+# deprecated in 3.14 and slated for removal in 3.15.)
+HERE = os.path.dirname(os.path.abspath(__file__))
+SCRIPT = os.path.join(HERE, "so-detections-overrides-import")
+_loader = SourceFileLoader("so_overrides_import", SCRIPT)
+_spec = importlib.util.spec_from_loader("so_overrides_import", _loader)
+soi = importlib.util.module_from_spec(_spec)
+_loader.exec_module(soi)
+
+
+class TestValidateSuppress(unittest.TestCase):
+    def test_valid(self):
+        self.assertIsNone(soi.validate_override(
+            {"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}, "suricata"))
+
+    def test_valid_var(self):
+        self.assertIsNone(soi.validate_override(
+            {"type": "suppress", "track": "by_either", "ip": "$HOME_NET"}, "suricata"))
+
+    def test_valid_cidr(self):
+        self.assertIsNone(soi.validate_override(
+            {"type": "suppress", "track": "by_dst", "ip": "10.0.0.0/8"}, "suricata"))
+
+    def test_valid_bracket_list(self):
+        self.assertIsNone(soi.validate_override(
+            {"type": "suppress", "track": "by_src", "ip": "[1.2.3.4,10.0.0.0/8]"}, "suricata"))
+
+    def test_missing_ip(self):
+        err = soi.validate_override({"type": "suppress", "track": "by_src"}, "suricata")
+        self.assertIn("requires", err)
+
+    def test_missing_track(self):
+        err = soi.validate_override({"type": "suppress", "ip": "1.2.3.4"}, "suricata")
+        self.assertIn("requires", err)
+
+    def test_invalid_track(self):
+        err = soi.validate_override(
+            {"type": "suppress", "track": "by_both", "ip": "1.2.3.4"}, "suricata")
+        self.assertIn("invalid track", err)
+
+    def test_invalid_ip(self):
+        err = soi.validate_override(
+            {"type": "suppress", "track": "by_src", "ip": "not-an-ip"}, "suricata")
+        self.assertIn("invalid IP", err)
+
+    def test_unnecessary_field(self):
+        err = soi.validate_override(
+            {"type": "suppress", "track": "by_src", "ip": "1.2.3.4", "count": 5}, "suricata")
+        self.assertIn("unnecessary fields", err)
+
+
+class TestValidateThreshold(unittest.TestCase):
+    def test_valid(self):
+        self.assertIsNone(soi.validate_override({
+            "type": "threshold", "track": "by_src",
+            "thresholdType": "limit", "count": 10, "seconds": 60,
+        }, "suricata"))
+
+    def test_valid_by_both(self):
+        self.assertIsNone(soi.validate_override({
+            "type": "threshold", "track": "by_both",
+            "thresholdType": "both", "count": 1, "seconds": 1,
+        }, "suricata"))
+
+    def test_track_by_either_invalid(self):
+        err = soi.validate_override({
+            "type": "threshold", "track": "by_either",
+            "thresholdType": "limit", "count": 10, "seconds": 60,
+        }, "suricata")
+        self.assertIn("invalid track", err)
+
+    def test_invalid_threshold_type(self):
+        err = soi.validate_override({
+            "type": "threshold", "track": "by_src",
+            "thresholdType": "bogus", "count": 10, "seconds": 60,
+        }, "suricata")
+        self.assertIn("invalid thresholdType", err)
+
+    def test_zero_count(self):
+        err = soi.validate_override({
+            "type": "threshold", "track": "by_src",
+            "thresholdType": "limit", "count": 0, "seconds": 60,
+        }, "suricata")
+        self.assertIn("count", err)
+
+    def test_negative_seconds(self):
+        err = soi.validate_override({
+            "type": "threshold", "track": "by_src",
+            "thresholdType": "limit", "count": 10, "seconds": -1,
+        }, "suricata")
+        self.assertIn("seconds", err)
+
+    def test_missing_field(self):
+        err = soi.validate_override({
+            "type": "threshold", "track": "by_src",
+            "thresholdType": "limit", "count": 10,  # missing seconds
+        }, "suricata")
+        self.assertIn("requires", err)
+
+    def test_unnecessary_field(self):
+        err = soi.validate_override({
+            "type": "threshold", "track": "by_src",
+            "thresholdType": "limit", "count": 10, "seconds": 60,
+            "regex": "foo",
+        }, "suricata")
+        self.assertIn("unnecessary fields", err)
+
+
+class TestValidateModify(unittest.TestCase):
+    def test_valid(self):
+        self.assertIsNone(soi.validate_override(
+            {"type": "modify", "regex": r"content:\"foo\"", "value": "content:bar"}, "suricata"))
+
+    def test_invalid_regex(self):
+        err = soi.validate_override(
+            {"type": "modify", "regex": "(unbalanced", "value": "x"}, "suricata")
+        self.assertIn("invalid regex", err)
+
+    def test_missing_value(self):
+        err = soi.validate_override({"type": "modify", "regex": "x"}, "suricata")
+        self.assertIn("requires", err)
+
+    def test_unnecessary_field(self):
+        err = soi.validate_override(
+            {"type": "modify", "regex": "x", "value": "y", "track": "by_src"}, "suricata")
+        self.assertIn("unnecessary fields", err)
+
+
+class TestValidateMisc(unittest.TestCase):
+    def test_unknown_type(self):
+        err = soi.validate_override({"type": "suppresss", "track": "by_src", "ip": "1.2.3.4"}, "suricata")
+        self.assertIn("invalid type", err)
+
+    def test_missing_type(self):
+        err = soi.validate_override({"track": "by_src"}, "suricata")
+        self.assertIn("type is required", err)
+
+
+class TestValidateIP(unittest.TestCase):
+    def test_plain_ipv4(self):
+        self.assertIsNone(soi._validate_suricata_ip("1.2.3.4"))
+
+    def test_plain_ipv6(self):
+        self.assertIsNone(soi._validate_suricata_ip("::1"))
+
+    def test_cidr(self):
+        self.assertIsNone(soi._validate_suricata_ip("10.0.0.0/8"))
+
+    def test_var(self):
+        self.assertIsNone(soi._validate_suricata_ip("$CONCOURSEWORKERS"))
+
+    def test_bracket_list(self):
+        self.assertIsNone(soi._validate_suricata_ip("[1.2.3.4, 10.0.0.0/8]"))
+
+    def test_bracket_list_bad_member(self):
+        err = soi._validate_suricata_ip("[1.2.3.4,nope]")
+        self.assertIn("invalid IP in list", err)
+
+    def test_empty(self):
+        self.assertIn("empty", soi._validate_suricata_ip(""))
+
+    def test_invalid(self):
+        self.assertIn("invalid", soi._validate_suricata_ip("999.999.999.999"))
+
+
+class TestDedupeKey(unittest.TestCase):
+    def test_suppress(self):
+        a = {"type": "suppress", "track": "by_src", "ip": "1.2.3.4", "count": 99}
+        b = {"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}
+        # count is irrelevant for suppress dedupe
+        self.assertEqual(soi.dedupe_key(a), soi.dedupe_key(b))
+
+    def test_suppress_differs_on_ip(self):
+        a = {"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}
+        b = {"type": "suppress", "track": "by_src", "ip": "5.6.7.8"}
+        self.assertNotEqual(soi.dedupe_key(a), soi.dedupe_key(b))
+
+    def test_threshold(self):
+        a = {"type": "threshold", "track": "by_src", "thresholdType": "limit",
+             "count": 10, "seconds": 60, "ip": "ignored"}
+        b = {"type": "threshold", "track": "by_src", "thresholdType": "limit",
+             "count": 10, "seconds": 60}
+        self.assertEqual(soi.dedupe_key(a), soi.dedupe_key(b))
+
+    def test_threshold_differs_on_count(self):
+        a = {"type": "threshold", "track": "by_src", "thresholdType": "limit",
+             "count": 10, "seconds": 60}
+        b = {"type": "threshold", "track": "by_src", "thresholdType": "limit",
+             "count": 20, "seconds": 60}
+        self.assertNotEqual(soi.dedupe_key(a), soi.dedupe_key(b))
+
+    def test_modify(self):
+        a = {"type": "modify", "regex": "x", "value": "y"}
+        b = {"type": "modify", "regex": "x", "value": "y"}
+        self.assertEqual(soi.dedupe_key(a), soi.dedupe_key(b))
+
+
+class TestDescribe(unittest.TestCase):
+    def test_suppress(self):
+        s = soi.describe({"type": "suppress", "track": "by_src", "ip": "1.2.3.4"})
+        self.assertIn("suppress", s)
+        self.assertIn("by_src", s)
+        self.assertIn("1.2.3.4", s)
+
+    def test_threshold_includes_count(self):
+        s = soi.describe({"type": "threshold", "track": "by_src",
+                          "thresholdType": "limit", "count": 10, "seconds": 60})
+        self.assertIn("count=10", s)
+        self.assertIn("seconds=60", s)
+
+    def test_modify(self):
+        s = soi.describe({"type": "modify", "regex": "foo"})
+        self.assertIn("modify", s)
+        self.assertIn("foo", s)
+
+
+class TestParseOverridesFile(unittest.TestCase):
+    def _write(self, content):
+        fd, path = tempfile.mkstemp(suffix=".txt")
+        os.close(fd)
+        with open(path, "w") as f:
+            f.write(content)
+        self.addCleanup(os.unlink, path)
+        return path
+
+    def test_single_line(self):
+        path = self._write('{"type":"suppress","track":"by_src","ip":"1.2.3.4"}')
+        result = soi.parse_overrides_file(path)
+        self.assertEqual(len(result), 1)
+        self.assertEqual(result[0][0]["type"], "suppress")
+        self.assertEqual(result[0][1], 1)
+
+    def test_ndjson(self):
+        path = self._write(
+            '{"type":"suppress","track":"by_src","ip":"1.2.3.4"}\n'
+            '{"type":"suppress","track":"by_dst","ip":"5.6.7.8"}\n'
+        )
+        result = soi.parse_overrides_file(path)
+        self.assertEqual(len(result), 2)
+        self.assertEqual(result[1][1], 2)
+
+    def test_empty(self):
+        path = self._write("")
+        self.assertEqual(soi.parse_overrides_file(path), [])
+
+    def test_blank_lines_skipped(self):
+        path = self._write('\n{"type":"suppress","track":"by_src","ip":"1.2.3.4"}\n\n')
+        result = soi.parse_overrides_file(path)
+        self.assertEqual(len(result), 1)
+        self.assertEqual(result[0][1], 2)  # line number reflects original position
+
+    def test_invalid_raises(self):
+        path = self._write("not json")
+        with self.assertRaises(json.JSONDecodeError):
+            soi.parse_overrides_file(path)
+
+
+class TestCollectCustomVars(unittest.TestCase):
+    def test_finds_custom(self):
+        v = soi.collect_custom_vars({"ip": "$CONCOURSEWORKERS"})
+        self.assertEqual(v, {"$CONCOURSEWORKERS"})
+
+    def test_filters_builtins(self):
+        v = soi.collect_custom_vars({"ip": "$HOME_NET"})
+        self.assertEqual(v, set())
+
+    def test_mixed(self):
+        v = soi.collect_custom_vars({"ip": "[$HOME_NET,$MYNET]"})
+        self.assertEqual(v, {"$MYNET"})
+
+    def test_non_string_fields_ignored(self):
+        v = soi.collect_custom_vars({"count": 10, "isEnabled": True})
+        self.assertEqual(v, set())
+
+
+class TestMakeSession(unittest.TestCase):
+    def _write(self, content):
+        fd, path = tempfile.mkstemp()
+        os.close(fd)
+        with open(path, "w") as f:
+            f.write(content)
+        self.addCleanup(os.unlink, path)
+        return path
+
+    def test_valid_auth_file(self):
+        path = self._write('user = "admin:secret"\n')
+        session = soi.make_session(path)
+        self.assertEqual(session.auth.username, "admin")
+        self.assertEqual(session.auth.password, "secret")
+        self.assertFalse(session.verify)
+
+    def test_missing_user_line(self):
+        path = self._write("# no user line here\n")
+        with self.assertRaises(RuntimeError):
+            soi.make_session(path)
+
+
+class TestFindDetection(unittest.TestCase):
+    def _session_with_response(self, payload):
+        session = MagicMock()
+        response = MagicMock()
+        response.json.return_value = payload
+        response.raise_for_status.return_value = None
+        session.get.return_value = response
+        return session
+
+    def test_found(self):
+        session = self._session_with_response({"hits": {"hits": [{
+            "_id": "abc", "_index": "so-detection",
+            "_source": {"so_detection": {"overrides": [{"type": "suppress"}]}},
+        }]}})
+        doc_id, idx, existing = soi.find_detection(session, "so-detection", "2049201", "suricata")
+        self.assertEqual(doc_id, "abc")
+        self.assertEqual(idx, "so-detection")
+        self.assertEqual(len(existing), 1)
+
+    def test_not_found(self):
+        session = self._session_with_response({"hits": {"hits": []}})
+        doc_id, idx, existing = soi.find_detection(session, "so-detection", "x", "suricata")
+        self.assertIsNone(doc_id)
+        self.assertIsNone(idx)
+        self.assertIsNone(existing)
+
+    def test_no_overrides_field(self):
+        session = self._session_with_response({"hits": {"hits": [{
+            "_id": "abc", "_index": "so-detection",
+            "_source": {"so_detection": {}},
+        }]}})
+        _, _, existing = soi.find_detection(session, "so-detection", "x", "suricata")
+        self.assertEqual(existing, [])
+
+    def test_multiple_hits_warns(self):
+        session = self._session_with_response({"hits": {"hits": [
+            {"_id": "a", "_index": "i", "_source": {"so_detection": {"overrides": []}}},
+            {"_id": "b", "_index": "i", "_source": {"so_detection": {"overrides": []}}},
+        ]}})
+        with patch("sys.stdout", new=StringIO()) as out:
+            doc_id, _, _ = soi.find_detection(session, "i", "x", "suricata")
+        self.assertEqual(doc_id, "a")
+        self.assertIn("WARN", out.getvalue())
+
+
+class TestUpdateOverrides(unittest.TestCase):
+    def test_posts_to_update_endpoint(self):
+        session = MagicMock()
+        response = MagicMock()
+        response.raise_for_status.return_value = None
+        response.json.return_value = {"result": "updated"}
+        session.post.return_value = response
+
+        result = soi.update_overrides(session, "so-detection", "abc", [{"type": "suppress"}])
+
+        self.assertEqual(result, {"result": "updated"})
+        url = session.post.call_args[0][0]
+        self.assertIn("/_update/abc", url)
+        body = session.post.call_args[1]["json"]
+        self.assertEqual(body["doc"]["so_detection"]["overrides"], [{"type": "suppress"}])
+
+
+class TestConfirmProceed(unittest.TestCase):
+    def test_dry_run_skips_prompt(self):
+        args = MagicMock(dry_run=True)
+        with patch("sys.stdout", new=StringIO()):
+            self.assertTrue(soi.confirm_proceed(args))
+
+    def test_yes_input(self):
+        args = MagicMock(dry_run=False)
+        with patch("sys.stdout", new=StringIO()):
+            with patch("builtins.input", return_value="yes"):
+                self.assertTrue(soi.confirm_proceed(args))
+
+    def test_yes_input_case_insensitive(self):
+        args = MagicMock(dry_run=False)
+        with patch("sys.stdout", new=StringIO()):
+            with patch("builtins.input", return_value="YES"):
+                self.assertTrue(soi.confirm_proceed(args))
+
+    def test_no_input_aborts(self):
+        args = MagicMock(dry_run=False)
+        with patch("sys.stdout", new=StringIO()):
+            with patch("builtins.input", return_value="no"):
+                self.assertFalse(soi.confirm_proceed(args))
+
+    def test_empty_input_aborts(self):
+        args = MagicMock(dry_run=False)
+        with patch("sys.stdout", new=StringIO()):
+            with patch("builtins.input", return_value=""):
+                self.assertFalse(soi.confirm_proceed(args))
+
+
+class TestParseArgs(unittest.TestCase):
+    def test_defaults(self):
+        with patch.object(sys, "argv", ["cmd", "--source", "/some/path"]):
+            args = soi.parse_args()
+        self.assertEqual(args.source, "/some/path")
+        self.assertEqual(args.engine, "suricata")
+        self.assertFalse(args.dry_run)
+        self.assertFalse(args.no_import_note)
+        self.assertEqual(args.index, soi.DEFAULT_INDEX)
+
+    def test_all_options(self):
+        argv = ["cmd", "-s", "/x", "-e", "suricata", "-n",
+                "--no-import-note", "-i", "alt-index"]
+        with patch.object(sys, "argv", argv):
+            args = soi.parse_args()
+        self.assertEqual(args.source, "/x")
+        self.assertTrue(args.dry_run)
+        self.assertTrue(args.no_import_note)
+        self.assertEqual(args.index, "alt-index")
+
+
+class TestMain(unittest.TestCase):
+    def setUp(self):
+        self.tmpdir = tempfile.mkdtemp()
+        self.addCleanup(shutil.rmtree, self.tmpdir, ignore_errors=True)
+        # Stub make_session so tests don't need /opt/so/conf/elasticsearch/curl.config.
+        p = patch.object(soi, "make_session", return_value=MagicMock())
+        p.start()
+        self.addCleanup(p.stop)
+
+    def _write_file(self, public_id, overrides, ext="txt"):
+        """Write an NDJSON override file. Entries may be dicts or raw strings (for malformed input)."""
+        path = os.path.join(self.tmpdir, f"{public_id}.{ext}")
+        with open(path, "w") as f:
+            for o in overrides:
+                f.write(o if isinstance(o, str) else json.dumps(o))
+                f.write("\n")
+        return path
+
+    def _run_main(self, *extra_argv, input_response="yes"):
+        """Run main() with stdout/stderr captured and input mocked. Returns (stdout, stderr, exit_code)."""
+        argv = ["cmd", "--source", self.tmpdir, *extra_argv]
+        out, err = StringIO(), StringIO()
+        with patch.object(sys, "argv", argv), \
+                patch("sys.stdout", new=out), \
+                patch("sys.stderr", new=err), \
+                patch("builtins.input", return_value=input_response):
+            with self.assertRaises(SystemExit) as cm:
+                soi.main()
+        return out.getvalue(), err.getvalue(), cm.exception.code
+
+    def test_source_dir_missing(self):
+        argv = ["cmd", "--source", "/no/such/path/here"]
+        err = StringIO()
+        with patch.object(sys, "argv", argv), patch("sys.stderr", new=err):
+            with self.assertRaises(SystemExit) as cm:
+                soi.main()
+        self.assertEqual(cm.exception.code, 1)
+        self.assertIn("source directory not found", err.getvalue())
+
+    def test_no_files_found(self):
+        out, _, code = self._run_main()
+        self.assertEqual(code, 0)
+        self.assertIn("No *.txt files found", out)
+
+    def test_user_aborts(self):
+        self._write_file("1001", [{"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}])
+        out, _, code = self._run_main(input_response="no")
+        self.assertEqual(code, 1)
+        self.assertIn("Aborted", out)
+
+    def test_parse_error_increments_error(self):
+        # Malformed JSON line — parse_overrides_file raises JSONDecodeError.
+        self._write_file("1002", ["not json"])
+        out, _, code = self._run_main("--dry-run")
+        self.assertEqual(code, 1)  # invalid+error → non-zero
+        self.assertIn("could not parse", out)
+        self.assertIn("Errors:                    1", out)
+
+    def test_empty_file_skipped(self):
+        # Blank lines only — parse_overrides_file returns []; main reports "empty file" and continues.
+        path = os.path.join(self.tmpdir, "1003.txt")
+        with open(path, "w") as f:
+            f.write("\n\n")
+        out, _, code = self._run_main("--dry-run")
+        self.assertEqual(code, 0)
+        self.assertIn("empty file", out)
+
+    @patch.object(soi, "find_detection")
+    def test_search_http_error(self, mock_find):
+        mock_find.side_effect = requests.HTTPError("boom")
+        self._write_file("1004", [{"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}])
+        out, _, code = self._run_main("--dry-run")
+        self.assertEqual(code, 1)
+        self.assertIn("search failed", out)
+
+    @patch.object(soi, "find_detection")
+    def test_no_detection_found(self, mock_find):
+        mock_find.return_value = (None, None, None)
+        self._write_file("1005", [{"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}])
+        out, _, code = self._run_main("--dry-run")
+        self.assertEqual(code, 0)
+        self.assertIn("no detection found", out)
+        self.assertIn("Skipped (no detection):    1", out)
+
+    @patch.object(soi, "find_detection")
+    def test_all_duplicates_no_update(self, mock_find):
+        existing = [{"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}]
+        mock_find.return_value = ("doc1", "so-detection", existing)
+        self._write_file("1006", [{"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}])
+        out, _, code = self._run_main("--dry-run")
+        self.assertEqual(code, 0)
+        self.assertIn("SKIP", out)
+        self.assertNotIn("DRY-RUN: would update", out)  # added_this_file == 0 branch
+
+    @patch.object(soi, "update_overrides")
+    @patch.object(soi, "find_detection")
+    def test_happy_path_full(self, mock_find, mock_update):
+        # Exercises: ADD, dedupe SKIP, INVALID, note prefix, UPDATE, custom-vars warning, exit=1 (invalid present)
+        existing = [{"type": "suppress", "track": "by_src", "ip": "9.9.9.9"}]
+        mock_find.return_value = ("doc1", "so-detection", existing)
+        mock_update.return_value = {"result": "updated"}
+        self._write_file("1007", [
+            {"type": "suppress", "track": "by_src", "ip": "1.2.3.4"},                # ADD
+            {"type": "suppress", "track": "by_src", "ip": "9.9.9.9"},                # SKIP (dupe of existing)
+            {"type": "suppress", "track": "bogus",  "ip": "1.2.3.4"},                # INVALID
+            {"type": "suppress", "track": "by_src", "ip": "$CONCOURSEWORKERS"},      # ADD + custom var
+        ])
+        out, _, code = self._run_main()
+        self.assertEqual(code, 1)  # one invalid -> non-zero
+
+        mock_update.assert_called_once()
+        merged = mock_update.call_args[0][3]
+        self.assertEqual(len(merged), 3)  # 1 existing + 2 new
+        new_notes = [o.get("note", "") for o in merged if o.get("ip") in ("1.2.3.4", "$CONCOURSEWORKERS")]
+        self.assertTrue(all(n.startswith("[Imported ") for n in new_notes))
+
+        self.assertIn("ADD", out)
+        self.assertIn("SKIP", out)
+        self.assertIn("INVALID", out)
+        self.assertIn("UPDATED", out)
+        self.assertIn("$CONCOURSEWORKERS", out)
+
+    @patch.object(soi, "update_overrides")
+    @patch.object(soi, "find_detection")
+    def test_no_import_note_preserves_note(self, mock_find, mock_update):
+        mock_find.return_value = ("doc1", "so-detection", [])
+        mock_update.return_value = {"result": "updated"}
+        self._write_file("1008", [
+            {"type": "suppress", "track": "by_src", "ip": "1.2.3.4", "note": "original"},
+        ])
+        _, _, code = self._run_main("--no-import-note")
+        self.assertEqual(code, 0)
+        merged = mock_update.call_args[0][3]
+        self.assertEqual(merged[0]["note"], "original")  # no prefix applied
+
+    @patch.object(soi, "find_detection")
+    def test_dry_run_skips_update(self, mock_find):
+        mock_find.return_value = ("doc1", "so-detection", [])
+        self._write_file("1009", [{"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}])
+        with patch.object(soi, "update_overrides") as mock_update:
+            out, _, code = self._run_main("--dry-run")
+        self.assertEqual(code, 0)
+        mock_update.assert_not_called()
+        self.assertIn("DRY-RUN: would update", out)
+
+    @patch.object(soi, "update_overrides")
+    @patch.object(soi, "find_detection")
+    def test_update_http_error(self, mock_find, mock_update):
+        mock_find.return_value = ("doc1", "so-detection", [])
+        mock_update.side_effect = requests.HTTPError("nope")
+        self._write_file("1010", [{"type": "suppress", "track": "by_src", "ip": "1.2.3.4"}])
+        out, _, code = self._run_main()
+        self.assertEqual(code, 1)
+        self.assertIn("update failed", out)
+
+
+if __name__ == "__main__":
+    unittest.main()

salt/manager/tools/sbin/so-pillar-import

@@ -1,329 +0,0 @@
-#!/usr/bin/env python3
-
-# Copyright Security Onion Solutions LLC and/or licensed to Security Onion Solutions LLC under one
-# or more contributor license agreements. Licensed under the Elastic License 2.0 as shown at
-# https://securityonion.net/license; you may not use this file except in compliance with the
-# Elastic License 2.0.
-
-"""
-so-pillar-import — populate the so_pillar.* schema in so-postgres from the
-on-disk Salt pillar tree.
-
-Reads /opt/so/saltstack/local/pillar/, decomposes each .sls file into a
-(scope, role|minion_id, pillar_path, data) tuple, and UPSERTs it into
-so_pillar.pillar_entry. Idempotent — re-running with no SLS edits produces
-no version bumps because the audit trigger only writes a row when data
-actually changes.
-
-Bootstrap and mine-driven files are skipped (see EXCLUDE_BASENAMES /
-EXCLUDE_PREFIXES below). Files containing Jinja templates ({% or {{) are
-also skipped — those stay disk-authoritative and ext_pillar_first: False
-means they render before the PG overlay anyway.
-
-All SQL goes through `docker exec so-postgres psql` so no separate DSN
-config is required at first-install time. Designed to be called by
-salt/postgres/schema_pillar.sls (initial seed) and by salt/manager/tools/
-sbin/so-minion (per-minion sync on add/delete).
-"""
-
-import argparse
-import json
-import os
-import shlex
-import subprocess
-import sys
-from pathlib import Path
-
-import yaml
-
-
-PILLAR_LOCAL_ROOT = Path("/opt/so/saltstack/local/pillar")
-PILLAR_DEFAULT_ROOT = Path("/opt/so/saltstack/default/pillar")
-DOCKER_CONTAINER = "so-postgres"
-PG_SUPERUSER = "postgres"
-PG_DATABASE = "securityonion"
-
-# Files that must NEVER move to Postgres. These are read by Salt before
-# Postgres is reachable, or contain renderer-time computed values (mine, etc.).
-EXCLUDE_BASENAMES = {
-    "secrets.sls",
-    "auth.sls",          # postgres/auth.sls bootstrap
-    "top.sls",
-}
-# Filename prefixes to skip — these are renderer-time computed pillars
-# (Salt mine, file_exists guards, etc.) that have to stay on disk.
-EXCLUDE_PATH_FRAGMENTS = (
-    "/elasticsearch/nodes.sls",
-    "/redis/nodes.sls",
-    "/kafka/nodes.sls",
-    "/hypervisor/nodes.sls",
-    "/logstash/nodes.sls",
-    "/node_data/ips.sls",
-    "/postgres/auth.sls",
-    "/elasticsearch/auth.sls",
-    "/kibana/secrets.sls",
-)
-
-
-def log(level, msg):
-    print(f"[{level}] {msg}", file=sys.stderr)
-
-
-def is_jinja_templated(content_bytes):
-    return b"{%" in content_bytes or b"{{" in content_bytes
-
-
-def classify(path):
-    """Return (scope, role_name, minion_id, pillar_path) for a pillar file
-    or None to skip it. role_name is None for now — the importer leaves role
-    membership to the so_pillar.minion trigger and the salt/auth reactor."""
-    rel_str = str(path)
-    if path.name in EXCLUDE_BASENAMES:
-        return None
-    for frag in EXCLUDE_PATH_FRAGMENTS:
-        if frag in rel_str:
-            return None
-
-    # /local/pillar/minions/<id>.sls  or  adv_<id>.sls
-    if path.parent.name == "minions":
-        stem = path.stem  # filename without .sls
-        if stem.startswith("adv_"):
-            mid = stem[4:]
-            return ("minion", None, mid, f"minions.adv_{mid}")
-        return ("minion", None, stem, f"minions.{stem}")
-
-    # /local/pillar/<section>/<file>.sls
-    if path.parent.parent == PILLAR_LOCAL_ROOT or path.parent.parent == PILLAR_DEFAULT_ROOT:
-        section = path.parent.name
-        stem = path.stem
-        # Only soc_<section>.sls and adv_<section>.sls are SOC-managed pillar
-        # surfaces. Other files (e.g. nodes.sls, auth.sls, *.token) are
-        # either covered by EXCLUDE_PATH_FRAGMENTS or are bootstrap surfaces
-        # we leave alone for now.
-        if stem.startswith("soc_") or stem.startswith("adv_"):
-            return ("global", None, None, f"{section}.{stem}")
-        return None
-
-    return None
-
-
-def parse_yaml_file(path):
-    with open(path, "rb") as f:
-        content = f.read()
-    if not content.strip():
-        return {}
-    if is_jinja_templated(content):
-        return None
-    data = yaml.safe_load(content)
-    if data is None:
-        return {}
-    if not isinstance(data, dict):
-        return {"_raw": data}
-    return data
-
-
-def derive_node_type(minion_id):
-    """Conventional Security Onion minion ids are <host>_<role>. Take the
-    last underscore-delimited token as the canonical role suffix."""
-    parts = minion_id.rsplit("_", 1)
-    if len(parts) == 2:
-        return parts[1]
-    return None
-
-
-def docker_psql(sql, *, db=PG_DATABASE, user=PG_SUPERUSER, on_error_stop=True, capture=True):
-    """Run sql via docker exec ... psql. Returns stdout as str."""
-    args = [
-        "docker", "exec", "-i", DOCKER_CONTAINER,
-        "psql", "-U", user, "-d", db, "-tA", "-q",
-    ]
-    if on_error_stop:
-        args += ["-v", "ON_ERROR_STOP=1"]
-    proc = subprocess.run(
-        args, input=sql.encode(),
-        capture_output=capture, check=False,
-    )
-    if proc.returncode != 0:
-        sys.stderr.write(proc.stderr.decode(errors="replace"))
-        raise RuntimeError(f"docker exec psql failed (rc={proc.returncode})")
-    return proc.stdout.decode(errors="replace")
-
-
-def upsert_minion(minion_id, node_type):
-    sql = (
-        "INSERT INTO so_pillar.minion (minion_id, node_type) "
-        f"VALUES ({pg_str(minion_id)}, {pg_str(node_type) if node_type else 'NULL'}) "
-        "ON CONFLICT (minion_id) DO UPDATE SET node_type = EXCLUDED.node_type;"
-    )
-    docker_psql(sql)
-
-
-def delete_minion(minion_id):
-    """CASCADE removes pillar_entry + role_member rows."""
-    sql = f"DELETE FROM so_pillar.minion WHERE minion_id = {pg_str(minion_id)};"
-    docker_psql(sql)
-
-
-def upsert_pillar_entry(scope, role_name, minion_id, pillar_path, data, reason):
-    """Insert or update the row keyed by the partial unique index that
-    matches scope. Audit trigger handles history; versioning trigger bumps
-    version only when data changes."""
-    data_json = json.dumps(data)
-    role_sql = pg_str(role_name) if role_name else "NULL"
-    minion_sql = pg_str(minion_id) if minion_id else "NULL"
-    reason_sql = pg_str(reason)
-
-    if scope == "global":
-        conflict = "(pillar_path) WHERE scope='global'"
-    elif scope == "role":
-        conflict = "(role_name, pillar_path) WHERE scope='role'"
-    elif scope == "minion":
-        conflict = "(minion_id, pillar_path) WHERE scope='minion'"
-    else:
-        raise ValueError(f"unknown scope {scope!r}")
-
-    sql = (
-        "BEGIN;\n"
-        f"SELECT set_config('so_pillar.change_reason', {reason_sql}, true);\n"
-        f"INSERT INTO so_pillar.pillar_entry "
-        f"(scope, role_name, minion_id, pillar_path, data, change_reason) "
-        f"VALUES ({pg_str(scope)}, {role_sql}, {minion_sql}, {pg_str(pillar_path)}, {pg_jsonb(data_json)}, {reason_sql}) "
-        f"ON CONFLICT {conflict} DO UPDATE "
-        f"SET data = EXCLUDED.data, change_reason = EXCLUDED.change_reason;\n"
-        "COMMIT;\n"
-    )
-    docker_psql(sql)
-
-
-def pg_str(s):
-    """Escape a Python str for inclusion in literal SQL. Pillar content has
-    already been validated as YAML; we just need standard SQL escaping."""
-    if s is None:
-        return "NULL"
-    return "'" + str(s).replace("'", "''") + "'"
-
-
-def pg_jsonb(json_str):
-    return pg_str(json_str) + "::jsonb"
-
-
-def walk_pillar_root(root, paths):
-    if not root.is_dir():
-        return
-    for path in root.rglob("*.sls"):
-        if path.is_file():
-            paths.append(path)
-
-
-def import_minion(minion_id, node_type, dry_run, reason):
-    """Re-import every pillar file for a single minion."""
-    if not minion_id:
-        raise ValueError("minion_id required for --scope minion")
-
-    upsert_minion(minion_id, node_type)
-    log("INFO", f"Upserted minion row {minion_id} (node_type={node_type})")
-
-    targets = [
-        PILLAR_LOCAL_ROOT / "minions" / f"{minion_id}.sls",
-        PILLAR_LOCAL_ROOT / "minions" / f"adv_{minion_id}.sls",
-    ]
-    for path in targets:
-        if not path.exists():
-            log("INFO", f"  (no file at {path})")
-            continue
-        klass = classify(path)
-        if not klass:
-            log("INFO", f"  skip {path} (excluded)")
-            continue
-        scope, role, mid, pillar_path = klass
-        data = parse_yaml_file(path)
-        if data is None:
-            log("WARN", f"  skip {path} (Jinja-templated; stays disk-only)")
-            continue
-        if dry_run:
-            log("DRY", f"  would upsert {scope}/{pillar_path} = {len(json.dumps(data))} bytes")
-            continue
-        upsert_pillar_entry(scope, role, mid, pillar_path, data, reason)
-        log("INFO", f"  imported {scope}/{pillar_path}")
-
-
-def import_all(dry_run, reason):
-    """Walk the entire local pillar tree and import every eligible file."""
-    paths = []
-    walk_pillar_root(PILLAR_LOCAL_ROOT, paths)
-
-    imported = 0
-    skipped = 0
-    minions_seen = set()
-
-    for path in sorted(paths):
-        klass = classify(path)
-        if not klass:
-            skipped += 1
-            continue
-        scope, role, minion_id, pillar_path = klass
-        data = parse_yaml_file(path)
-        if data is None:
-            log("WARN", f"skip {path} (Jinja-templated; stays disk-only)")
-            skipped += 1
-            continue
-
-        if scope == "minion" and minion_id not in minions_seen:
-            node_type = derive_node_type(minion_id)
-            if not dry_run:
-                upsert_minion(minion_id, node_type)
-            minions_seen.add(minion_id)
-
-        if dry_run:
-            log("DRY", f"would upsert {scope}/{pillar_path} ({len(json.dumps(data))} bytes)")
-        else:
-            upsert_pillar_entry(scope, role, minion_id, pillar_path, data, reason)
-            log("INFO", f"imported {scope}/{pillar_path}")
-        imported += 1
-
-    log("INFO", f"done: {imported} imported, {skipped} skipped")
-
-
-def main():
-    ap = argparse.ArgumentParser(description=__doc__)
-    ap.add_argument("--scope", choices=("global", "role", "minion", "all"), default="all")
-    ap.add_argument("--minion-id")
-    ap.add_argument("--node-type", help="override node_type for --scope minion (default: derived from minion_id)")
-    ap.add_argument("--delete", action="store_true",
-                    help="With --scope minion, remove the minion row (and its pillar rows via CASCADE)")
-    ap.add_argument("--dry-run", action="store_true")
-    ap.add_argument("--diff", action="store_true",
-                    help="(reserved) print structural diffs vs current DB content")
-    ap.add_argument("--yes", action="store_true",
-                    help="Skip confirmation prompts (currently unused; reserved)")
-    ap.add_argument("--reason", default="so-pillar-import",
-                    help="change_reason recorded in pillar_entry_history")
-    args = ap.parse_args()
-
-    try:
-        if args.scope == "minion":
-            if not args.minion_id:
-                ap.error("--minion-id required when --scope minion")
-            if args.delete:
-                if args.dry_run:
-                    log("DRY", f"would delete {args.minion_id}")
-                else:
-                    delete_minion(args.minion_id)
-                    log("INFO", f"deleted {args.minion_id}")
-            else:
-                node_type = args.node_type or derive_node_type(args.minion_id)
-                import_minion(args.minion_id, node_type, args.dry_run, args.reason)
-        elif args.scope == "all":
-            import_all(args.dry_run, args.reason)
-        else:
-            log("ERROR", f"--scope {args.scope} not yet implemented; use --scope all or --scope minion")
-            return 2
-    except Exception as e:
-        log("ERROR", str(e))
-        return 1
-
-    return 0
-
-
-if __name__ == "__main__":
-    sys.exit(main())

salt/manager/tools/sbin/so-repo-sync

@@ -10,5 +10,16 @@ NOROOT=1
 set -e
 
 curl --retry 5 --retry-delay 60 -A "reposync/$(sync_options)" https://sigs.securityonion.net/checkup --output /tmp/checkup
+
 dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionsync --download-metadata -p /nsm/repo/
 createrepo /nsm/repo
+
+# The kernel repo section is deployed to repodownload.conf by the manager highstate, which
+# runs AFTER this script during soup. On the first upgrade to a kernel-aware version the
+# on-disk config still predates the section, so guard on its presence to avoid dnf's
+# "Unknown repo: 'securityonionkernelsync'" aborting the sync (set -e). The next sync after the
+# highstate deploys the section will pick it up.
+if grep -q '^\[securityonionkernelsync\]' /opt/so/conf/reposync/repodownload.conf; then
+  dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionkernelsync --download-metadata -p /nsm/kernelrepo/
+  createrepo /nsm/kernelrepo
+fi

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

@@ -13,64 +13,6 @@ import json
 
 lockFile = "/tmp/so-yaml.lock"
 
-# postsalt: so-yaml supports three backend modes for PG-managed pillar paths:
-#
-#   dual      — write disk + mirror to so_pillar.*. Reads from disk.
-#               Used during the migration transition when disk is still
-#               canonical and PG runs as a shadow.
-#   postgres  — write to so_pillar.* only. Reads from so_pillar.*. No disk
-#               file is touched. The end state once cutover is complete.
-#   disk      — disk only, no PG. Emergency rollback escape hatch.
-#
-# Bootstrap and mine-driven files (secrets.sls, ca/init.sls, */nodes.sls,
-# top.sls, etc.) are always handled on disk regardless of mode — those paths
-# are explicitly excluded by so_yaml_postgres.locate() raising SkipPath.
-#
-# Mode resolution: SO_YAML_BACKEND env var, then /opt/so/conf/so-yaml/mode,
-# then default 'dual' (safe upgrade behavior — flipping to 'postgres' is
-# done by schema_pillar.sls after the schema is in place and the importer
-# has run at least once).
-
-MODE_FILE = "/opt/so/conf/so-yaml/mode"
-VALID_MODES = ("dual", "postgres", "disk")
-DEFAULT_MODE = "dual"
-
-try:
-    sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
-    import so_yaml_postgres
-    _SO_YAML_PG_AVAILABLE = True
-except Exception as _exc:
-    _SO_YAML_PG_AVAILABLE = False
-
-
-def _resolveBackendMode():
-    env = os.environ.get("SO_YAML_BACKEND")
-    if env and env in VALID_MODES:
-        return env
-    try:
-        with open(MODE_FILE, "r") as fh:
-            value = fh.read().strip()
-        if value in VALID_MODES:
-            return value
-    except (IOError, OSError):
-        pass
-    return DEFAULT_MODE
-
-
-_BACKEND_MODE = _resolveBackendMode()
-
-
-def _isPgManaged(filename):
-    """True when so-yaml should route this file's reads/writes through
-    so_pillar.*. False for bootstrap/mine-driven files that always live on
-    disk, and for arbitrary YAML paths outside the pillar tree."""
-    if not _SO_YAML_PG_AVAILABLE:
-        return False
-    try:
-        return so_yaml_postgres.is_pg_managed(filename)
-    except Exception:
-        return False
-
 
 def showUsage(args):
     print('Usage: {} <COMMAND> <YAML_FILE> [ARGS...]'.format(sys.argv[0]), file=sys.stderr)
@@ -83,14 +25,8 @@ def showUsage(args):
     print('    get [-r]         - Displays (to stdout) the value stored in the given key. Requires KEY arg. Use -r for raw output without YAML formatting.', file=sys.stderr)
     print('    remove           - Removes a yaml key, if it exists. Requires KEY arg.', file=sys.stderr)
     print('    replace          - Replaces (or adds) a new key and set its value. Requires KEY and VALUE args.', file=sys.stderr)
-    print('    purge            - Delete the YAML file from disk and remove its rows from so_pillar.* (no KEY arg).', file=sys.stderr)
     print('    help             - Prints this usage information.', file=sys.stderr)
     print('', file=sys.stderr)
-    print('  Backend mode:', file=sys.stderr)
-    print('    Resolved from $SO_YAML_BACKEND, then /opt/so/conf/so-yaml/mode, default "dual".', file=sys.stderr)
-    print('    Valid values: dual | postgres | disk. Bootstrap pillar files (secrets, ca, *.nodes.sls)', file=sys.stderr)
-    print('    are always handled on disk regardless of mode.', file=sys.stderr)
-    print('', file=sys.stderr)
     print('  Where:', file=sys.stderr)
     print('   YAML_FILE          - Path to the file that will be modified. Ex: /opt/so/conf/service/conf.yaml', file=sys.stderr)
     print('   KEY                - YAML key, does not support \' or " characters at this time. Ex: level1.level2', file=sys.stderr)
@@ -103,24 +39,6 @@ def showUsage(args):
 
 
 def loadYaml(filename):
-    """Load a YAML file's content as a dict.
-
-    PG-canonical mode (`postgres`): for PG-managed paths, read from
-    so_pillar.pillar_entry. A missing row is treated as an empty dict so
-    that `replace`/`add` on a fresh path can populate it from scratch.
-
-    Other modes / non-PG-managed paths: read from disk as today.
-    """
-    if _BACKEND_MODE == "postgres" and _isPgManaged(filename):
-        try:
-            data = so_yaml_postgres.read_yaml(filename)
-        except so_yaml_postgres.SkipPath:
-            data = None
-        except Exception as e:
-            print(f"so-yaml: pg read failed for {filename}: {e}", file=sys.stderr)
-            sys.exit(1)
-        return data if data is not None else {}
-
     try:
         with open(filename, "r") as file:
             content = file.read()
@@ -134,97 +52,8 @@ def loadYaml(filename):
 
 
 def writeYaml(filename, content):
-    """Persist `content` for `filename`.
-
-    PG-canonical mode + PG-managed path: write only to so_pillar.*. A PG
-    failure is fatal (no disk fallback) — caller must retry.
-
-    Dual mode: write disk, then mirror to PG (failures are warnings).
-
-    Disk mode or non-PG-managed path: write disk only.
-    """
-    if _BACKEND_MODE == "postgres" and _isPgManaged(filename):
-        if not _SO_YAML_PG_AVAILABLE:
-            print("so-yaml: PG-canonical mode requires so_yaml_postgres module", file=sys.stderr)
-            sys.exit(1)
-        ok, msg = so_yaml_postgres.write_yaml(
-            filename, content,
-            reason="so-yaml " + " ".join(sys.argv[1:2]))
-        if not ok:
-            print(f"so-yaml: pg write failed for {filename}: {msg}", file=sys.stderr)
-            sys.exit(1)
-        return None
-
     file = open(filename, "w")
-    result = yaml.safe_dump(content, file)
-    file.close()
-
-    if _BACKEND_MODE == "dual":
-        _mirrorToPostgres(filename, content)
-    return result
-
-
-def _mirrorToPostgres(filename, content):
-    """Best-effort dual-write of a YAML mutation into so_pillar.*. Skips
-    files outside the PG-managed pillar surface (secrets.sls,
-    elasticsearch/nodes.sls, etc.) and silently degrades when so-postgres
-    is unreachable. Disk write is canonical in dual mode; this never
-    raises.
-
-    Only real PG failures (`pg write failed: ...`) are logged so the
-    common cases (skipped path, postgres not running) don't pollute
-    stderr."""
-    if not _SO_YAML_PG_AVAILABLE:
-        return
-    try:
-        ok, msg = so_yaml_postgres.write_yaml(filename, content,
-                                              reason="so-yaml " + " ".join(sys.argv[1:2]))
-        if not ok and msg.startswith("pg write failed"):
-            print(f"so-yaml: {msg}", file=sys.stderr)
-    except Exception as e:  # pragma: no cover — defensive: never break disk write
-        print(f"so-yaml: pg mirror exception: {e}", file=sys.stderr)
-
-
-def purgeFile(filename):
-    """Delete a YAML file from disk and remove the matching rows from
-    so_pillar.*. Idempotent — missing file/row counts as success.
-
-    PG-canonical mode + PG-managed path: PG delete is canonical. If a stale
-    disk file from the dual-write era happens to still exist, it's removed
-    too as a cleanup courtesy. PG failure is fatal in this mode.
-
-    Dual / disk modes: remove disk first; PG cleanup is best-effort."""
-    if _BACKEND_MODE == "postgres" and _isPgManaged(filename):
-        if not _SO_YAML_PG_AVAILABLE:
-            print("so-yaml: PG-canonical mode requires so_yaml_postgres module", file=sys.stderr)
-            return 1
-        ok, msg = so_yaml_postgres.purge_yaml(filename, reason="so-yaml purge")
-        if not ok:
-            print(f"so-yaml: pg purge failed for {filename}: {msg}", file=sys.stderr)
-            return 1
-        if os.path.exists(filename):
-            try:
-                os.remove(filename)
-            except Exception as e:
-                print(f"so-yaml: warn — could not remove stale disk file {filename}: {e}", file=sys.stderr)
-        return 0
-
-    if os.path.exists(filename):
-        try:
-            os.remove(filename)
-        except Exception as e:
-            print(f"Failed to remove {filename}: {e}", file=sys.stderr)
-            return 1
-
-    if _BACKEND_MODE == "dual" and _SO_YAML_PG_AVAILABLE:
-        try:
-            ok, msg = so_yaml_postgres.purge_yaml(filename,
-                                                  reason="so-yaml purge")
-            if not ok and msg.startswith("pg purge failed"):
-                print(f"so-yaml: {msg}", file=sys.stderr)
-        except Exception as e:
-            print(f"so-yaml: pg purge exception: {e}", file=sys.stderr)
-    return 0
+    return yaml.safe_dump(content, file)
 
 
 def appendItem(content, key, listItem):
@@ -542,18 +371,6 @@ def get(args):
     return 0
 
 
-def purge(args):
-    """purge YAML_FILE — delete the file from disk and remove the matching
-    rows from so_pillar.* in so-postgres. Used by so-minion's delete path
-    (in place of `rm -f`) so the audit log captures the deletion and
-    role_member rows get cleaned up via FK CASCADE on so_pillar.minion."""
-    if len(args) != 1:
-        print('Missing filename arg', file=sys.stderr)
-        showUsage(None)
-        return 1
-    return purgeFile(args[0])
-
-
 def main():
     args = sys.argv[1:]
 
@@ -571,7 +388,6 @@ def main():
         "get": get,
         "remove": remove,
         "replace": replace,
-        "purge": purge,
     }
 
     code = 1

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

@@ -991,329 +991,3 @@ class TestLoadYaml(unittest.TestCase):
                     soyaml.loadYaml("/tmp/so-yaml_test-unreadable.yaml")
                     sysmock.assert_called_with(1)
                     self.assertIn("Error reading file", mock_stderr.getvalue())
-
-
-class TestPurge(unittest.TestCase):
-
-    def test_purge_missing_arg(self):
-        # showUsage calls sys.exit(1); patch it like the other tests do.
-        with patch('sys.exit', new=MagicMock()):
-            with patch('sys.stderr', new=StringIO()) as mock_stderr:
-                rc = soyaml.purge([])
-                self.assertEqual(rc, 1)
-                self.assertIn("Missing filename", mock_stderr.getvalue())
-
-    def test_purge_existing_file(self):
-        filename = "/tmp/so-yaml_test_purge.yaml"
-        with open(filename, "w") as f:
-            f.write("key: value\n")
-        # Disable PG mirror so the test doesn't shell out to docker.
-        with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', False):
-            rc = soyaml.purge([filename])
-        self.assertEqual(rc, 0)
-        import os as _os
-        self.assertFalse(_os.path.exists(filename))
-
-    def test_purge_missing_file_idempotent(self):
-        filename = "/tmp/so-yaml_test_purge_missing.yaml"
-        import os as _os
-        if _os.path.exists(filename):
-            _os.remove(filename)
-        with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', False):
-            rc = soyaml.purge([filename])
-        self.assertEqual(rc, 0)
-
-
-class TestSoYamlPostgres(unittest.TestCase):
-    """Tests the path-locator and write/purge contract of the dual-write
-    backend module without actually contacting Postgres."""
-
-    def setUp(self):
-        import importlib
-        self.mod = importlib.import_module("so_yaml_postgres")
-
-    def test_locate_global_soc(self):
-        scope, role, mid, path = self.mod.locate(
-            "/opt/so/saltstack/local/pillar/soc/soc_soc.sls")
-        self.assertEqual(scope, "global")
-        self.assertIsNone(role)
-        self.assertIsNone(mid)
-        self.assertEqual(path, "soc.soc_soc")
-
-    def test_locate_global_advanced(self):
-        scope, role, mid, path = self.mod.locate(
-            "/opt/so/saltstack/local/pillar/soc/adv_soc.sls")
-        self.assertEqual(scope, "global")
-        self.assertEqual(path, "soc.adv_soc")
-
-    def test_locate_minion(self):
-        scope, role, mid, path = self.mod.locate(
-            "/opt/so/saltstack/local/pillar/minions/h1_sensor.sls")
-        self.assertEqual(scope, "minion")
-        self.assertEqual(mid, "h1_sensor")
-        self.assertEqual(path, "minions.h1_sensor")
-
-    def test_locate_minion_advanced(self):
-        scope, role, mid, path = self.mod.locate(
-            "/opt/so/saltstack/local/pillar/minions/adv_h1_sensor.sls")
-        self.assertEqual(scope, "minion")
-        self.assertEqual(mid, "h1_sensor")
-        self.assertEqual(path, "minions.adv_h1_sensor")
-
-    def test_locate_skip_secrets(self):
-        with self.assertRaises(self.mod.SkipPath):
-            self.mod.locate("/opt/so/saltstack/local/pillar/secrets.sls")
-
-    def test_locate_skip_postgres_auth(self):
-        with self.assertRaises(self.mod.SkipPath):
-            self.mod.locate("/opt/so/saltstack/local/pillar/postgres/auth.sls")
-
-    def test_locate_skip_mine_driven(self):
-        with self.assertRaises(self.mod.SkipPath):
-            self.mod.locate("/opt/so/saltstack/local/pillar/elasticsearch/nodes.sls")
-
-    def test_locate_skip_top(self):
-        with self.assertRaises(self.mod.SkipPath):
-            self.mod.locate("/opt/so/saltstack/local/pillar/top.sls")
-
-    def test_locate_skip_unrelated(self):
-        with self.assertRaises(self.mod.SkipPath):
-            self.mod.locate("/etc/hostname")
-
-    def test_pg_str_escapes(self):
-        self.assertEqual(self.mod._pg_str("a'b"), "'a''b'")
-        self.assertEqual(self.mod._pg_str(None), "NULL")
-
-    def test_conflict_target(self):
-        self.assertIn("scope='global'", self.mod._conflict_target("global"))
-        self.assertIn("scope='role'", self.mod._conflict_target("role"))
-        self.assertIn("scope='minion'", self.mod._conflict_target("minion"))
-        with self.assertRaises(ValueError):
-            self.mod._conflict_target("bogus")
-
-    def test_write_yaml_skips_disk_only_path(self):
-        with patch.object(self.mod, '_is_enabled', return_value=True):
-            ok, msg = self.mod.write_yaml(
-                "/opt/so/saltstack/local/pillar/secrets.sls",
-                {"secrets": {"foo": "bar"}})
-        self.assertFalse(ok)
-        self.assertIn("disk-only", msg)
-
-    def test_write_yaml_unreachable(self):
-        with patch.object(self.mod, '_is_enabled', return_value=False):
-            ok, msg = self.mod.write_yaml(
-                "/opt/so/saltstack/local/pillar/soc/soc_soc.sls",
-                {"soc": {"foo": "bar"}})
-        self.assertFalse(ok)
-        self.assertEqual(msg, "postgres unreachable")
-
-    def test_is_pg_managed_true(self):
-        self.assertTrue(self.mod.is_pg_managed(
-            "/opt/so/saltstack/local/pillar/minions/h1_sensor.sls"))
-        self.assertTrue(self.mod.is_pg_managed(
-            "/opt/so/saltstack/local/pillar/soc/soc_soc.sls"))
-
-    def test_is_pg_managed_false_for_bootstrap(self):
-        self.assertFalse(self.mod.is_pg_managed(
-            "/opt/so/saltstack/local/pillar/secrets.sls"))
-        self.assertFalse(self.mod.is_pg_managed(
-            "/opt/so/saltstack/local/pillar/postgres/auth.sls"))
-        self.assertFalse(self.mod.is_pg_managed(
-            "/opt/so/saltstack/local/pillar/elasticsearch/nodes.sls"))
-
-    def test_read_yaml_unreachable(self):
-        with patch.object(self.mod, '_is_enabled', return_value=False):
-            self.assertIsNone(self.mod.read_yaml(
-                "/opt/so/saltstack/local/pillar/soc/soc_soc.sls"))
-
-    def test_read_yaml_skips_disk_only(self):
-        with patch.object(self.mod, '_is_enabled', return_value=True):
-            with self.assertRaises(self.mod.SkipPath):
-                self.mod.read_yaml(
-                    "/opt/so/saltstack/local/pillar/secrets.sls")
-
-    def test_read_yaml_returns_data(self):
-        with patch.object(self.mod, '_is_enabled', return_value=True):
-            with patch.object(self.mod, '_docker_psql',
-                              return_value='{"soc": {"foo": "bar"}}\n'):
-                data = self.mod.read_yaml(
-                    "/opt/so/saltstack/local/pillar/soc/soc_soc.sls")
-        self.assertEqual(data, {"soc": {"foo": "bar"}})
-
-    def test_read_yaml_returns_none_when_no_row(self):
-        with patch.object(self.mod, '_is_enabled', return_value=True):
-            with patch.object(self.mod, '_docker_psql', return_value=''):
-                data = self.mod.read_yaml(
-                    "/opt/so/saltstack/local/pillar/soc/soc_soc.sls")
-        self.assertIsNone(data)
-
-    def test_read_yaml_minion_query_shape(self):
-        captured = {}
-
-        def fake_psql(sql):
-            captured['sql'] = sql
-            return '{"host": {"mainip": "10.0.0.1"}}'
-
-        with patch.object(self.mod, '_is_enabled', return_value=True):
-            with patch.object(self.mod, '_docker_psql', side_effect=fake_psql):
-                data = self.mod.read_yaml(
-                    "/opt/so/saltstack/local/pillar/minions/h1_sensor.sls")
-        self.assertEqual(data, {"host": {"mainip": "10.0.0.1"}})
-        self.assertIn("scope='minion'", captured['sql'])
-        self.assertIn("'h1_sensor'", captured['sql'])
-        self.assertIn("'minions.h1_sensor'", captured['sql'])
-
-    def test_is_enabled_public_alias(self):
-        with patch.object(self.mod, '_is_enabled', return_value=True):
-            self.assertTrue(self.mod.is_enabled())
-        with patch.object(self.mod, '_is_enabled', return_value=False):
-            self.assertFalse(self.mod.is_enabled())
-
-
-class TestSoYamlBackendMode(unittest.TestCase):
-    """Tests so-yaml's backend-mode resolution and PG-canonical routing
-    for read/write/purge. The PG calls themselves are stubbed; what we're
-    asserting is that the right backend is chosen for each (mode, path)
-    combination."""
-
-    def test_resolve_mode_env_overrides_file(self):
-        with patch.dict('os.environ', {'SO_YAML_BACKEND': 'postgres'}):
-            self.assertEqual(soyaml._resolveBackendMode(), 'postgres')
-        with patch.dict('os.environ', {'SO_YAML_BACKEND': 'disk'}):
-            self.assertEqual(soyaml._resolveBackendMode(), 'disk')
-
-    def test_resolve_mode_invalid_env_falls_back(self):
-        with patch.dict('os.environ', {'SO_YAML_BACKEND': 'garbage'}, clear=False):
-            with patch('builtins.open', side_effect=IOError):
-                self.assertEqual(soyaml._resolveBackendMode(), 'dual')
-
-    def test_resolve_mode_default_dual(self):
-        env = {k: v for k, v in __import__('os').environ.items()
-               if k != 'SO_YAML_BACKEND'}
-        with patch.dict('os.environ', env, clear=True):
-            with patch('builtins.open', side_effect=IOError):
-                self.assertEqual(soyaml._resolveBackendMode(), 'dual')
-
-    def test_is_pg_managed_proxies(self):
-        with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-            self.assertTrue(soyaml._isPgManaged(
-                "/opt/so/saltstack/local/pillar/minions/h1_sensor.sls"))
-            self.assertFalse(soyaml._isPgManaged(
-                "/opt/so/saltstack/local/pillar/secrets.sls"))
-
-    def test_is_pg_managed_false_when_module_unavailable(self):
-        with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', False):
-            self.assertFalse(soyaml._isPgManaged(
-                "/opt/so/saltstack/local/pillar/minions/h1_sensor.sls"))
-
-    def test_load_yaml_postgres_mode_reads_pg(self):
-        with patch.object(soyaml, '_BACKEND_MODE', 'postgres'):
-            with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                with patch.object(soyaml.so_yaml_postgres, 'is_pg_managed',
-                                  return_value=True):
-                    with patch.object(soyaml.so_yaml_postgres, 'read_yaml',
-                                      return_value={"a": 1}):
-                        result = soyaml.loadYaml(
-                            "/opt/so/saltstack/local/pillar/soc/soc_soc.sls")
-        self.assertEqual(result, {"a": 1})
-
-    def test_load_yaml_postgres_mode_returns_empty_when_no_row(self):
-        with patch.object(soyaml, '_BACKEND_MODE', 'postgres'):
-            with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                with patch.object(soyaml.so_yaml_postgres, 'is_pg_managed',
-                                  return_value=True):
-                    with patch.object(soyaml.so_yaml_postgres, 'read_yaml',
-                                      return_value=None):
-                        result = soyaml.loadYaml(
-                            "/opt/so/saltstack/local/pillar/soc/soc_soc.sls")
-        self.assertEqual(result, {})
-
-    def test_load_yaml_postgres_mode_reads_disk_for_bootstrap(self):
-        import tempfile, os as _os
-        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
-            f.write("foo: bar\n")
-            tmp = f.name
-        try:
-            with patch.object(soyaml, '_BACKEND_MODE', 'postgres'):
-                with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                    with patch.object(soyaml.so_yaml_postgres,
-                                      'is_pg_managed', return_value=False):
-                        result = soyaml.loadYaml(tmp)
-            self.assertEqual(result, {"foo": "bar"})
-        finally:
-            _os.unlink(tmp)
-
-    def test_write_yaml_postgres_mode_skips_disk(self):
-        import tempfile, os as _os
-        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
-            tmp = f.name
-        _os.unlink(tmp)
-        try:
-            with patch.object(soyaml, '_BACKEND_MODE', 'postgres'):
-                with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                    with patch.object(soyaml.so_yaml_postgres, 'is_pg_managed',
-                                      return_value=True):
-                        with patch.object(soyaml.so_yaml_postgres, 'write_yaml',
-                                          return_value=(True, 'ok')) as mock_w:
-                            soyaml.writeYaml(tmp, {"x": 1})
-            self.assertFalse(_os.path.exists(tmp))
-            mock_w.assert_called_once()
-        finally:
-            if _os.path.exists(tmp):
-                _os.unlink(tmp)
-
-    def test_write_yaml_postgres_mode_failure_is_fatal(self):
-        with patch.object(soyaml, '_BACKEND_MODE', 'postgres'):
-            with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                with patch.object(soyaml.so_yaml_postgres, 'is_pg_managed',
-                                  return_value=True):
-                    with patch.object(soyaml.so_yaml_postgres, 'write_yaml',
-                                      return_value=(False, 'pg write failed: connection refused')):
-                        with patch('sys.exit', new=MagicMock()) as sysmock:
-                            with patch('sys.stderr', new=StringIO()) as mock_err:
-                                soyaml.writeYaml(
-                                    "/opt/so/saltstack/local/pillar/soc/soc_soc.sls",
-                                    {"x": 1})
-        sysmock.assert_called_with(1)
-
-    def test_write_yaml_disk_mode_skips_pg(self):
-        import tempfile, os as _os
-        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
-            tmp = f.name
-        try:
-            with patch.object(soyaml, '_BACKEND_MODE', 'disk'):
-                with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                    with patch.object(soyaml.so_yaml_postgres, 'write_yaml') as mock_w:
-                        soyaml.writeYaml(tmp, {"x": 1})
-            mock_w.assert_not_called()
-            with open(tmp) as f:
-                self.assertIn('x: 1', f.read())
-        finally:
-            _os.unlink(tmp)
-
-    def test_purge_postgres_mode_calls_pg_only(self):
-        import tempfile, os as _os
-        with tempfile.NamedTemporaryFile(mode='w', suffix='.yaml', delete=False) as f:
-            tmp = f.name
-        _os.unlink(tmp)
-        with patch.object(soyaml, '_BACKEND_MODE', 'postgres'):
-            with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                with patch.object(soyaml.so_yaml_postgres, 'is_pg_managed',
-                                  return_value=True):
-                    with patch.object(soyaml.so_yaml_postgres, 'purge_yaml',
-                                      return_value=(True, 'ok')) as mock_p:
-                        rc = soyaml.purgeFile(tmp)
-        self.assertEqual(rc, 0)
-        mock_p.assert_called_once()
-
-    def test_purge_postgres_mode_failure_returns_nonzero(self):
-        with patch.object(soyaml, '_BACKEND_MODE', 'postgres'):
-            with patch.object(soyaml, '_SO_YAML_PG_AVAILABLE', True):
-                with patch.object(soyaml.so_yaml_postgres, 'is_pg_managed',
-                                  return_value=True):
-                    with patch.object(soyaml.so_yaml_postgres, 'purge_yaml',
-                                      return_value=(False, 'pg purge failed: x')):
-                        with patch('sys.stderr', new=StringIO()):
-                            rc = soyaml.purgeFile(
-                                "/opt/so/saltstack/local/pillar/minions/h1_sensor.sls")
-        self.assertEqual(rc, 1)

salt/manager/tools/sbin/so_yaml_postgres.py

@@ -1,320 +0,0 @@
-# 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_yaml_postgres — Postgres-backed dual-write helpers for so-yaml.py.
-
-so-yaml.py writes YAML pillar files on disk; this module mirrors those
-writes into so_pillar.* in so-postgres so ext_pillar and the SOC
-PostgresConfigstore see the same data. During the postsalt transition
-disk is canonical; PG writes are best-effort and never fail the disk
-operation.
-
-Connection: shells out to `docker exec so-postgres psql -U postgres -d
-securityonion`. Same pattern so-pillar-import uses; avoids needing a
-separate DSN config at install time. Performance is fine because so-yaml
-is invoked from infrequent code paths (setup scripts, so-minion,
-so-firewall); SOC's hot path uses the in-process pgxpool in
-PostgresConfigstore, not so-yaml.
-
-Path-to-row mapping mirrors PostgresConfigstore.locateSetting in
-securityonion-soc:
-
-  /opt/so/saltstack/local/pillar/<section>/soc_<section>.sls
-        -> scope=global, pillar_path=<section>.soc_<section>
-  /opt/so/saltstack/local/pillar/<section>/adv_<section>.sls
-        -> scope=global, pillar_path=<section>.adv_<section>
-  /opt/so/saltstack/local/pillar/minions/<id>.sls
-        -> scope=minion, minion_id=<id>, pillar_path=minions.<id>
-  /opt/so/saltstack/local/pillar/minions/adv_<id>.sls
-        -> scope=minion, minion_id=<id>, pillar_path=minions.adv_<id>
-
-Files outside that mapping (notably secrets.sls, postgres/auth.sls,
-elasticsearch/nodes.sls, etc.) are skipped — they stay disk-only forever
-or render dynamically and don't belong in PG.
-"""
-
-import json
-import os
-import shlex
-import subprocess
-import sys
-
-DOCKER_CONTAINER = os.environ.get("SO_PILLAR_PG_CONTAINER", "so-postgres")
-PG_DATABASE = os.environ.get("SO_PILLAR_PG_DATABASE", "securityonion")
-PG_USER = os.environ.get("SO_PILLAR_PG_USER", "postgres")
-
-# File paths whose mutations stay disk-only forever. Mirrors EXCLUDE_*
-# in so-pillar-import.
-DISK_ONLY_PATHS = (
-    "/opt/so/saltstack/local/pillar/secrets.sls",
-    "/opt/so/saltstack/local/pillar/postgres/auth.sls",
-    "/opt/so/saltstack/local/pillar/elasticsearch/auth.sls",
-    "/opt/so/saltstack/local/pillar/kibana/secrets.sls",
-)
-DISK_ONLY_FRAGMENTS = (
-    "/elasticsearch/nodes.sls",
-    "/redis/nodes.sls",
-    "/kafka/nodes.sls",
-    "/hypervisor/nodes.sls",
-    "/logstash/nodes.sls",
-    "/node_data/ips.sls",
-    "/top.sls",
-)
-
-
-class SkipPath(Exception):
-    """Raised when a file path is intentionally not mirrored to PG."""
-
-
-def is_enabled():
-    """Public alias for callers that want to probe PG reachability without
-    relying on a leading-underscore private name."""
-    return _is_enabled()
-
-
-def _is_enabled():
-    """PG dual-write only fires if so-postgres is reachable. Cheap probe.
-    Returns True when docker exec succeeds, False otherwise. We never
-    want a PG hiccup to fail a disk write on a manager whose Postgres is
-    momentarily unreachable."""
-    try:
-        proc = subprocess.run(
-            ["docker", "exec", DOCKER_CONTAINER,
-             "pg_isready", "-h", "127.0.0.1", "-U", PG_USER, "-q"],
-            capture_output=True, timeout=5, check=False,
-        )
-        return proc.returncode == 0
-    except (FileNotFoundError, subprocess.TimeoutExpired, OSError):
-        return False
-
-
-def locate(path):
-    """Translate a so-yaml file path to (scope, role_name, minion_id, pillar_path).
-    Raises SkipPath when the file is not part of the PG-managed surface."""
-    norm = os.path.normpath(path)
-
-    if norm in DISK_ONLY_PATHS:
-        raise SkipPath(f"{path}: explicit disk-only allowlist")
-    for frag in DISK_ONLY_FRAGMENTS:
-        if frag in norm:
-            raise SkipPath(f"{path}: matches disk-only fragment {frag}")
-
-    parent = os.path.basename(os.path.dirname(norm))
-    grandparent = os.path.basename(os.path.dirname(os.path.dirname(norm)))
-    name = os.path.basename(norm)
-    if not name.endswith(".sls"):
-        raise SkipPath(f"{path}: not a .sls file")
-    stem = name[:-4]
-
-    if parent == "minions":
-        if stem.startswith("adv_"):
-            mid = stem[4:]
-            return ("minion", None, mid, f"minions.adv_{mid}")
-        return ("minion", None, stem, f"minions.{stem}")
-
-    # /local/pillar/<section>/<file>.sls
-    if grandparent == "pillar" and parent and parent != "":
-        if stem.startswith("soc_") or stem.startswith("adv_"):
-            return ("global", None, None, f"{parent}.{stem}")
-        raise SkipPath(f"{path}: <section>/{stem}.sls is not a soc_/adv_ file")
-
-    raise SkipPath(f"{path}: unrecognised pillar layout")
-
-
-def _pg_str(s):
-    if s is None:
-        return "NULL"
-    return "'" + str(s).replace("'", "''") + "'"
-
-
-def _docker_psql(sql):
-    """Run sql via docker exec ... psql. Returns stdout. Caller catches
-    exceptions and downgrades to a warning."""
-    proc = subprocess.run(
-        ["docker", "exec", "-i", DOCKER_CONTAINER,
-         "psql", "-U", PG_USER, "-d", PG_DATABASE,
-         "-tA", "-q", "-v", "ON_ERROR_STOP=1"],
-        input=sql.encode(), capture_output=True, check=False, timeout=30,
-    )
-    if proc.returncode != 0:
-        raise RuntimeError(proc.stderr.decode(errors="replace") or
-                           f"docker exec psql exit {proc.returncode}")
-    return proc.stdout.decode(errors="replace")
-
-
-def _conflict_target(scope):
-    if scope == "global":
-        return "(pillar_path) WHERE scope='global'"
-    if scope == "role":
-        return "(role_name, pillar_path) WHERE scope='role'"
-    if scope == "minion":
-        return "(minion_id, pillar_path) WHERE scope='minion'"
-    raise ValueError(f"unknown scope {scope!r}")
-
-
-def is_pg_managed(path):
-    """True if this path maps to a so_pillar.* row (locate() succeeds).
-    Bootstrap and mine-driven files return False — they always live on
-    disk regardless of so-yaml's backend mode."""
-    try:
-        locate(path)
-        return True
-    except SkipPath:
-        return False
-
-
-def read_yaml(path):
-    """Return the content dict stored in so_pillar.pillar_entry for `path`,
-    or None when no row exists. Raises SkipPath when `path` is not part of
-    the PG-managed surface (caller should read disk in that case).
-
-    Used by so-yaml.py PG-canonical mode so `replace`, `get`, etc. resolve
-    against the database rather than a stale (or absent) disk file."""
-    if not _is_enabled():
-        return None
-    scope, role, minion_id, pillar_path = locate(path)
-
-    if scope == "minion":
-        sql = ("SELECT data FROM so_pillar.pillar_entry "
-               "WHERE scope='minion' "
-               f"AND minion_id={_pg_str(minion_id)} "
-               f"AND pillar_path={_pg_str(pillar_path)}")
-    elif scope == "role":
-        sql = ("SELECT data FROM so_pillar.pillar_entry "
-               "WHERE scope='role' "
-               f"AND role_name={_pg_str(role)} "
-               f"AND pillar_path={_pg_str(pillar_path)}")
-    else:
-        sql = ("SELECT data FROM so_pillar.pillar_entry "
-               "WHERE scope='global' "
-               f"AND pillar_path={_pg_str(pillar_path)}")
-
-    try:
-        out = _docker_psql(sql).strip()
-    except Exception:
-        return None
-    if not out:
-        return None
-    try:
-        return json.loads(out)
-    except (ValueError, TypeError):
-        return None
-
-
-def write_yaml(path, content_dict, *, reason="so-yaml dual-write"):
-    """Mirror the disk write at `path` (whose content was just rendered as
-    `content_dict`) into so_pillar.pillar_entry. Best-effort: any failure
-    is swallowed so the caller (so-yaml.py) does not see it as a fatal."""
-    if not _is_enabled():
-        return False, "postgres unreachable"
-    try:
-        scope, role, minion_id, pillar_path = locate(path)
-    except SkipPath as e:
-        return False, str(e)
-
-    data_json = json.dumps(content_dict if content_dict is not None else {})
-    role_sql = _pg_str(role)
-    minion_sql = _pg_str(minion_id)
-    reason_sql = _pg_str(reason)
-    conflict = _conflict_target(scope)
-
-    sql_parts = []
-    if scope == "minion":
-        # FK requires the minion row before pillar_entry can reference it.
-        sql_parts.append(
-            f"INSERT INTO so_pillar.minion (minion_id) VALUES ({minion_sql}) "
-            "ON CONFLICT (minion_id) DO NOTHING;"
-        )
-    sql_parts.append(
-        "BEGIN;\n"
-        f"SELECT set_config('so_pillar.change_reason', {reason_sql}, true);\n"
-        "INSERT INTO so_pillar.pillar_entry "
-        "(scope, role_name, minion_id, pillar_path, data, change_reason) "
-        f"VALUES ({_pg_str(scope)}, {role_sql}, {minion_sql}, "
-        f"{_pg_str(pillar_path)}, {_pg_str(data_json)}::jsonb, {reason_sql}) "
-        f"ON CONFLICT {conflict} DO UPDATE "
-        "SET data = EXCLUDED.data, change_reason = EXCLUDED.change_reason;\n"
-        "COMMIT;\n"
-    )
-
-    try:
-        _docker_psql("\n".join(sql_parts))
-    except Exception as e:
-        return False, f"pg write failed: {e}"
-    return True, "ok"
-
-
-def purge_yaml(path, *, reason="so-yaml purge"):
-    """Mirror the disk file deletion at `path` by deleting the matching
-    pillar_entry rows. For minion files also deletes the so_pillar.minion
-    row (CASCADE removes pillar_entry + role_member rows)."""
-    if not _is_enabled():
-        return False, "postgres unreachable"
-    try:
-        scope, role, minion_id, pillar_path = locate(path)
-    except SkipPath as e:
-        return False, str(e)
-
-    reason_sql = _pg_str(reason)
-    parts = ["BEGIN;",
-             f"SELECT set_config('so_pillar.change_reason', {reason_sql}, true);"]
-
-    if scope == "minion":
-        # If both <id>.sls and adv_<id>.sls are gone the trigger / CASCADE
-        # cleans up role_member; otherwise we just remove this one row.
-        parts.append(
-            f"DELETE FROM so_pillar.pillar_entry "
-            f"WHERE scope='minion' AND minion_id={_pg_str(minion_id)} "
-            f"AND pillar_path={_pg_str(pillar_path)};"
-        )
-        parts.append(
-            f"DELETE FROM so_pillar.minion WHERE minion_id={_pg_str(minion_id)} "
-            "AND NOT EXISTS (SELECT 1 FROM so_pillar.pillar_entry "
-            f"WHERE minion_id={_pg_str(minion_id)});"
-        )
-    else:
-        parts.append(
-            f"DELETE FROM so_pillar.pillar_entry "
-            f"WHERE scope={_pg_str(scope)} AND pillar_path={_pg_str(pillar_path)};"
-        )
-
-    parts.append("COMMIT;")
-
-    try:
-        _docker_psql("\n".join(parts))
-    except Exception as e:
-        return False, f"pg purge failed: {e}"
-    return True, "ok"
-
-
-# CLI for diagnostics. Not exercised by so-yaml.py itself.
-def _main(argv):
-    import argparse
-    ap = argparse.ArgumentParser()
-    ap.add_argument("op", choices=("locate", "ping"))
-    ap.add_argument("path", nargs="?")
-    args = ap.parse_args(argv)
-
-    if args.op == "ping":
-        ok = _is_enabled()
-        print("ok" if ok else "unreachable")
-        return 0 if ok else 1
-    if args.op == "locate":
-        if not args.path:
-            ap.error("locate requires PATH")
-        try:
-            scope, role, minion_id, pillar_path = locate(args.path)
-            print(f"scope={scope} role={role} minion_id={minion_id} pillar_path={pillar_path}")
-            return 0
-        except SkipPath as e:
-            print(f"SKIP: {e}", file=sys.stderr)
-            return 2
-
-    return 1
-
-
-if __name__ == "__main__":
-    sys.exit(_main(sys.argv[1:]))

salt/manager/tools/sbin/soup

@@ -16,6 +16,7 @@ POSTVERSION=$INSTALLEDVERSION
 INSTALLEDSALTVERSION=$(salt --versions-report | grep Salt: | awk '{print $2}')
 BATCHSIZE=5
 SOUP_LOG=/root/soup.log
+SOUP_DEBUG_LOG=/root/soup-debug.log
 WHATWOULDYOUSAYYAHDOHERE=soup
 whiptail_title='Security Onion UPdater'
 NOTIFYCUSTOMELASTICCONFIG=false
@@ -34,6 +35,7 @@ if [[ -f /etc/salt/cloud.profiles.d/socloud.conf ]]; then
 fi
 # used to display messages to the user at the end of soup
 declare -a FINAL_MESSAGE_QUEUE=()
+SOUP_ERR_CONTEXT=
 
 
 check_err() {
@@ -114,11 +116,52 @@ check_err() {
       echo "$err_msg"
     fi
 
+    if [[ -n $SOUP_ERR_CONTEXT ]]; then
+      echo ""
+      printf '%s\n' "$SOUP_ERR_CONTEXT"
+    fi
+
+    echo "SOUP XTRACE debug log (if enabled) at $SOUP_DEBUG_LOG. Re-run soup with SOUP_DEBUG=1 to create $SOUP_DEBUG_LOG"
+
     exit $exit_code
   fi
 
 }
 
+# Collect bash error context before passing off to check_err()
+on_err() {
+  local exit_code=$?
+  # Ignore failures in blocks that explicitly disabled errexit with `set +e`.
+  [[ $- == *e* ]] || return $exit_code
+  # turn off xtrace to prevent added noise in debug log
+  set +x 2>/dev/null || true
+
+  # Use first error context, multiple errors can happen with command substitutions or nested functions. We just need context from the initial error.
+  [[ -n $SOUP_ERR_CONTEXT ]] && return $exit_code
+
+  local cmd=$BASH_COMMAND
+  local line=${BASH_LINENO[0]}
+  local function=${FUNCNAME[1]:-main}
+  local source=${BASH_SOURCE[1]##*/}
+  local -a err_lines=(
+    "ERROR on: ${cmd}"
+    "  source: ${source}:${line} in ${function}()"
+  )
+  local i caller_line caller_src caller_func
+
+  for ((i=2; i<${#FUNCNAME[@]}-1; i++)); do
+    caller_line=${BASH_LINENO[$((i-1))]}
+    [[ -n $caller_line && $caller_line -gt 0 ]] || continue
+    caller_src=${BASH_SOURCE[$i]##*/}
+    caller_func=${FUNCNAME[$i]:-main}
+    err_lines+=("  called by: ${caller_src}:${caller_line} in ${caller_func}()")
+  done
+
+  SOUP_ERR_CONTEXT=$(printf '%s\n' "${err_lines[@]}")
+
+  return $exit_code
+}
+
 airgap_mounted() {
   # Let's see if the ISO is already mounted.
   if [[ -f /tmp/soagupdate/SecurityOnion/VERSION ]]; then
@@ -188,13 +231,6 @@ airgap_update_dockers() {
   fi
 }
 
-backup_old_states_pillars() {
-
-	tar czf /nsm/backup/$(echo $INSTALLEDVERSION)_$(date +%Y%m%d-%H%M%S)_soup_default_states_pillars.tar.gz /opt/so/saltstack/default/
-	tar czf /nsm/backup/$(echo $INSTALLEDVERSION)_$(date +%Y%m%d-%H%M%S)_soup_local_states_pillars.tar.gz /opt/so/saltstack/local/
-
-}
-
 update_registry() {
   docker stop so-dockerregistry
   docker rm so-dockerregistry
@@ -209,6 +245,7 @@ check_airgap() {
       UPDATE_DIR=/tmp/soagupdate/SecurityOnion
       AGDOCKER=/tmp/soagupdate/docker
       AGREPO=/tmp/soagupdate/minimal/Packages
+      AGUEKREPO=/tmp/soagupdate/uek/Packages
   else
       is_airgap=1
   fi
@@ -350,10 +387,11 @@ highstate() {
 masterlock() {
   echo "Locking Salt Master"
   mv -v $TOPFILE $BACKUPTOPFILE
-  echo "base:" > $TOPFILE
-  echo "  $MINIONID:" >> $TOPFILE
-  echo "    - ca" >> $TOPFILE
-  echo "    - elasticsearch" >> $TOPFILE
+  # Render the real top file only for the host running soup; every other
+  # minion gets an empty top (no states) while the master is upgrading.
+  echo "{% if grains['id'] == '$MINIONID' %}" > $TOPFILE
+  cat $BACKUPTOPFILE >> $TOPFILE
+  echo "{% endif %}" >> $TOPFILE
 }
 
 masterunlock() {
@@ -370,8 +408,9 @@ preupgrade_changes() {
     # This function is to add any new pillar items if needed.
     echo "Checking to see if changes are needed."
 
-    [[ "$INSTALLEDVERSION" =~ ^2\.4\.21[0-9]+$ ]] && up_to_3.0.0   
+    [[ "$INSTALLEDVERSION" =~ ^2\.4\.21[0-9]+$ ]] && up_to_3.0.0
     [[ "$INSTALLEDVERSION" == "3.0.0" ]] && up_to_3.1.0
+    [[ "$INSTALLEDVERSION" == "3.1.0" ]] && up_to_3.2.0
     true
 }
 
@@ -381,6 +420,7 @@ postupgrade_changes() {
 
     [[ "$POSTVERSION" =~ ^2\.4\.21[0-9]+$ ]] && post_to_3.0.0
     [[ "$POSTVERSION" == "3.0.0" ]] && post_to_3.1.0
+    [[ "$POSTVERSION" == "3.1.0" ]] && post_to_3.2.0
     true
 }
 
@@ -533,6 +573,23 @@ elasticfleet_set_agent_logging_level_warn() {
     done <<< "$policies_to_update"
 }
 
+update_logstash_pipeline_name() {
+    local original_pipeline_name="$1"
+    local new_pipeline_name="$2"
+
+    echo "Checking for conflicting logstash defined_pipelines pillar value."
+    local LOGSTASH_FILE=/opt/so/saltstack/local/pillar/logstash/soc_logstash.sls
+    local MINIONDIR=/opt/so/saltstack/local/pillar/minions
+    for pillar_file in "$LOGSTASH_FILE" "$MINIONDIR"/*.sls; do
+        [[ -f "$pillar_file" ]] || continue
+        if grep -q "$original_pipeline_name$" "$pillar_file"; then
+            echo "Found conflicting defined_pipeline pillar value in $pillar_file. Updating to use the new logstash pipeline name."
+            sed -i "s#$original_pipeline_name\$#$new_pipeline_name#g" "$pillar_file"
+            chown socore:socore "$pillar_file"
+        fi
+    done
+}
+
 check_transform_health_and_reauthorize() {
     . /usr/sbin/so-elastic-fleet-common
 
@@ -556,14 +613,23 @@ check_transform_health_and_reauthorize() {
     # - unhealthy (any non-green health status)
     # - metadata has run_as_kibana_system: false (this fix is specific to transforms started prior to Kibana 9.3.3)
     # - are not orphaned (integration is not somehow missing/corrupt/uninstalled)
+    local tmp_transforms tmp_stats tmp_installed
+    tmp_transforms=$(mktemp)
+    tmp_stats=$(mktemp)
+    tmp_installed=$(mktemp)
+
+    echo "$transforms_doc" > "$tmp_transforms"
+    echo "$stats_doc"      > "$tmp_stats"
+    echo "$installed_doc"  > "$tmp_installed"
+
     local unhealthy_transforms
     unhealthy_transforms=$(jq -c -n \
-        --argjson t "$transforms_doc" \
-        --argjson s "$stats_doc" \
-        --argjson i "$installed_doc" '
-        ($i.items | map({key: .name, value: .version}) | from_entries) as $pkg_ver
-        | ($s.transforms | map({key: .id, value: .health.status}) | from_entries) as $health
-        | [ $t.transforms[]
+        --slurpfile t "$tmp_transforms" \
+        --slurpfile s "$tmp_stats" \
+        --slurpfile i "$tmp_installed" '
+        ($i[0].items | map({key: .name, value: .version}) | from_entries) as $pkg_ver
+        | ($s[0].transforms | map({key: .id, value: .health.status}) | from_entries) as $health
+        | [ $t[0].transforms[]
             | select(._meta.run_as_kibana_system == false)
             | select(($health[.id] // "unknown") != "green")
             | {id, pkg: ._meta.package.name, ver: ($pkg_ver[._meta.package.name])}
@@ -604,6 +670,8 @@ check_transform_health_and_reauthorize() {
         (( total_failures += $(jq 'map(select(.success != true)) | length' <<< "$resp" 2>/dev/null) ))
     done <<< "$unhealthy_transforms"
 
+    rm -f "$tmp_transforms" "$tmp_stats" "$tmp_installed"
+
     if [[ "$total_failures" -gt 0 ]]; then
         echo "Some transform(s) failed to reauthorize."
     fi
@@ -644,6 +712,31 @@ ensure_postgres_secret() {
   chown socore:socore "$secrets_file"
 }
 
+rename_strelka_scan_lnk() {
+  echo "Renaming strelka pillar ScanLNK to ScanLnk."
+  local STRELKA_FILE=/opt/so/saltstack/local/pillar/strelka/soc_strelka.sls
+  local MINIONDIR=/opt/so/saltstack/local/pillar/minions
+  local OLD_KEY=strelka.backend.config.backend.scanners.ScanLNK
+  local NEW_KEY=strelka.backend.config.backend.scanners.ScanLnk
+  local TMP_VALUE_FILE
+  TMP_VALUE_FILE=$(mktemp)
+
+  for pillar_file in "$STRELKA_FILE" "$MINIONDIR"/*.sls; do
+    [[ -f "$pillar_file" ]] || continue
+    # Skip if ScanLNK doesn't exist
+    so-yaml.py get "$pillar_file" "$OLD_KEY" > "$TMP_VALUE_FILE" 2>/dev/null || continue
+    echo "Found 'ScanLNK' key in $pillar_file. Renaming to 'ScanLnk'."
+    so-yaml.py add "$pillar_file" "$NEW_KEY" "file:$TMP_VALUE_FILE"
+    so-yaml.py remove "$pillar_file" "$OLD_KEY"
+  done
+
+  rm -f "$TMP_VALUE_FILE"
+}
+
+fix_logstash_0013_lumberjack_pipeline_name() {
+    update_logstash_pipeline_name "so/0013_input_lumberjack_fleet.conf" "so/0013_input_lumberjack_fleet.conf.jinja"
+}
+
 up_to_3.1.0() {
   ensure_postgres_local_pillar
   ensure_postgres_secret
@@ -651,7 +744,8 @@ up_to_3.1.0() {
   elasticsearch_backup_index_templates
   # Clear existing component template state file.
   rm -f /opt/so/state/esfleet_component_templates.json
-
+  rename_strelka_scan_lnk
+  fix_logstash_0013_lumberjack_pipeline_name
 
   INSTALLEDVERSION=3.1.0
 }
@@ -688,6 +782,121 @@ post_to_3.1.0() {
 
 ### 3.1.0 End ###
 
+### 3.2.0 Scripts ###
+
+bootstrap_so_soc_database() {
+  # init-db.sh is mounted into so-postgres at /docker-entrypoint-initdb.d/init-db.sh
+  # and runs automatically only on a fresh data directory. Hosts upgrading from
+  # 3.1.0 already have /nsm/postgres populated, so the so_soc bootstrap block
+  # added in 3.2 never fires. Re-run the script explicitly; it's idempotent.
+  echo "Bootstrapping so_soc database via init-db.sh."
+  # The postgres image has no USER directive, so `docker exec` defaults to
+  # root, and the container env intentionally omits POSTGRES_USER (the upstream
+  # entrypoint defaults it transiently during first-init only). Recreate both
+  # so psql inside init-db.sh resolves the connect user correctly.
+  local exec_cmd="docker exec -u postgres -e POSTGRES_USER=postgres so-postgres bash /docker-entrypoint-initdb.d/init-db.sh"
+  if ! /usr/sbin/so-postgres-wait; then
+    FINAL_MESSAGE_QUEUE+=("WARNING: so-postgres was not ready during the 3.2.0 upgrade; the so_soc database may not have been bootstrapped. Re-run manually: $exec_cmd")
+    return 0
+  fi
+  if ! $exec_cmd; then
+    FINAL_MESSAGE_QUEUE+=("WARNING: init-db.sh failed inside so-postgres during the 3.2.0 upgrade; the so_soc database may not have been bootstrapped. Re-run manually: $exec_cmd")
+    return 0
+  fi
+  echo "so_soc bootstrap complete."
+}
+
+# Existing grids should keep ILM unless an admin explicitly opts in to DLM.
+pin_elasticsearch_data_retention_method() {
+  local elasticsearch_file=/opt/so/saltstack/local/pillar/elasticsearch/soc_elasticsearch.sls
+  mkdir -p "$(dirname "$elasticsearch_file")"
+  [[ -f "$elasticsearch_file" ]] || touch "$elasticsearch_file"
+
+  if so-yaml.py get -r "$elasticsearch_file" elasticsearch.data_retention_method >/dev/null 2>&1; then
+    echo "elasticsearch.data_retention_method already set; leaving as-is."
+    return 0
+  fi
+
+  echo "Pinning existing grid to ILM data retention."
+  so-yaml.py add "$elasticsearch_file" elasticsearch.data_retention_method ILM
+  chown socore:socore "$elasticsearch_file"
+}
+
+# Addes auto_expand_replicas setting to .kibana_streams index template
+#
+# In Kibana 9.3.3 the auto_expand_replicas setting was not added to the .kibana_streams index template. Causing single node deployments to be stuck in yellow state (unable to assign replica). Here we update the template in place using the so_kibana system user (system managed index template) to include the auto_expand_replicas setting
+#
+# Reference: https://github.com/elastic/kibana/issues/263048
+kibana_backport_streams_index_template() {
+    local current_template updated_template
+
+    set +e
+    if ! current_template=$(so-elasticsearch-query "_index_template/.kibana_streams" --retry 3 --retry-delay 5 --fail); then
+        echo "Index template .kibana_streams does not exist, skipping backport."
+        return 0
+    fi
+    set -e
+
+    updated_template=$(jq '.index_templates[0].index_template | .template.settings += {"index.auto_expand_replicas": "0-1"} | del(.created_date_millis, .modified_date_millis)' <<< "$current_template")
+
+    if ! kibana_user_pass=$(/usr/sbin/so-yaml.py get -r /opt/so/saltstack/local/pillar/elasticsearch/auth.sls elasticsearch.auth.users.so_kibana_user.pass); then
+        echo "Unable to retrieve so_kibana_user password, skipping .kibana_streams index template backport."
+        return 0
+    fi
+
+    if ! so-elasticsearch-query "_index_template/.kibana_streams" -XPUT -d "$updated_template" -u "so_kibana:$kibana_user_pass" --retry 3 --retry-delay 5 --fail; then
+        echo "Unable to automatically update .kibana_streams index template"
+        return 0
+    fi
+
+}
+
+# Runs kafka-features.sh upgrade --release-version $1
+#   Upgrades Kafka KRaft cluster metadata
+update_kafka_metadata() {
+    metadata_version="$1"
+    global_pillar="/opt/so/saltstack/local/pillar/global/soc_global.sls"
+    if PIPELINE=$(so-yaml.py get -r "$global_pillar" global.pipeline 2> /dev/null) && [[ "$PIPELINE" == "KAFKA" ]]; then
+        kafka_nodes_raw=$(salt-call pillar.get kafka:nodes --out=json)
+        if kafka_nodes=$(jq -er '.local | select(type == "object" and length > 0)' <<< "$kafka_nodes_raw"); then
+            bootstrap_servers=$(jq -r '[to_entries[] | select(.value.role | contains("broker")) | "\(.value.ip):9092"] | join(",")' <<< "$kafka_nodes")
+            echo "Upgrading Kafka KRaft cluster version"
+            so-kafka-cli kafka-features.sh --bootstrap-server "$bootstrap_servers" --command-config /opt/kafka/config/kraft/client.properties upgrade --release-version "$metadata_version" 2>/dev/null || true
+
+            return 0
+        else
+            FINAL_MESSAGE_QUEUE+=("WARNING: Unable to automatically perform Kafka KRaft cluster metadata update. This step can be performed manually using the following command (replacing \$BROKER_IP with the ip of atleast 1 available Kafka broker):")
+            FINAL_MESSAGE_QUEUE+=("    - so-kafka-cli kafka-features.sh --bootstrap-server \$BROKER_IP:9092 --command-config /opt/kafka/config/kraft/client.properties upgrade --release-version $metadata_version")
+        fi
+    else
+        echo "Nothing to do!"
+    fi
+}
+
+up_to_3.2.0() {
+  fix_logstash_0013_lumberjack_pipeline_name
+
+  pin_elasticsearch_data_retention_method
+
+  INSTALLEDVERSION=3.2.0
+}
+
+post_to_3.2.0() {
+  bootstrap_so_soc_database
+
+  # Including agent regen script here since it was missed in post_to_3.1.0
+  echo "Regenerating Elastic Agent Installers"
+  /sbin/so-elastic-agent-gen-installers
+
+  kibana_backport_streams_index_template
+
+  update_kafka_metadata "4.3"
+
+  POSTVERSION=3.2.0
+}
+
+### 3.2.0 End ###
+
 
 repo_sync() {
   echo "Sync the local repo."
@@ -796,13 +1005,19 @@ update_airgap_rules() {
   rsync -a $UPDATE_DIR/agrules/securityonion-resources/* /nsm/securityonion-resources/
 }
 
-update_airgap_repo() {
+update_airgap_repos() {
   # Update the files in the repo
-  echo "Syncing new updates to /nsm/repo"
-  rsync -a $AGREPO/* /nsm/repo/
-  echo "Creating repo"
+  echo "Syncing new updates to /nsm/repo & /nsm/kernelrepo"
+  # Airgap soup copies new files into the local repo, but doesn't remove old packages. Retaining the ability to rollback package updates
+  rsync -a "$AGREPO"/ /nsm/repo/
+  rsync -a "$AGUEKREPO"/ /nsm/kernelrepo/
+
   dnf -y install yum-utils createrepo_c
+
+  echo "Running createrepo for /nsm/repo"
   createrepo /nsm/repo
+  echo "Running createrepo for /nsm/kernelrepo"
+  createrepo /nsm/kernelrepo
 }
 
 update_salt_mine() {
@@ -939,6 +1154,9 @@ verify_es_version_compatibility() {
     local is_active_intermediate_upgrade=1
     # supported upgrade paths for SO-ES versions
     declare -A es_upgrade_map=(
+        ["8.18.4"]="8.18.6 8.18.8 9.0.8"
+	    ["8.18.6"]="8.18.8 9.0.8"
+	    ["8.18.8"]="9.0.8"
         ["9.0.8"]="9.3.3"
     )
 
@@ -962,6 +1180,171 @@ verify_es_version_compatibility() {
         exit 160
     fi
 
+    compatible_es_versions="$target_es_version"
+    for current_version in "${!es_upgrade_map[@]}"; do
+        # shellcheck disable=SC2076
+        if [[ " ${es_upgrade_map[$current_version]} " =~ " $target_es_version " ]]; then
+            compatible_es_versions+=" $current_version"
+        fi
+    done
+
+    # Check if the given ES version can directly upgrade to the target ES version. Used to assist with catching lagging nodes during the upgrade process
+    es_version_can_upgrade_to_target() {
+        local current_version="$1"
+        # shellcheck disable=SC2076
+        if [[ -n "$current_version" && " $compatible_es_versions " =~ " $current_version " ]]; then
+            return 0
+        fi
+
+        return 1
+    }
+
+    # Gather Elasticsearch cluster version info and verify that each node in the cluster is running a version compatible with the target ES version.
+    verify_searchnodes_es_target_compatibility() {
+        local retries=20
+        local retry_count=0
+        local delay=180
+        local expected_es_nodes searchnode_minions attempt
+        local searchnode_discovery_success=false
+        SEARCHNODE_ES_VERSIONS=""
+
+        for attempt in {1..3}; do
+            if searchnode_minions=$(set -o pipefail; salt-key --out=json --list=accepted 2> /dev/null | jq -r '.minions[]? | select(endswith("searchnode"))'); then
+                searchnode_discovery_success=true
+                break
+            fi
+
+            echo "Failed to retrieve grid searchnodes via salt-key... Retrying in 30 seconds. Attempt $attempt of 3."
+            sleep 30
+        done
+
+        if [[ "$searchnode_discovery_success" != "true" ]]; then
+            echo "Failed to retrieve grid searchnodes via salt-key."
+            return 1
+        fi
+
+        # Always add node running soup to expected es nodes
+        expected_es_nodes="${MINIONID%_*}"
+        while IFS= read -r searchnode_minion; do
+            [[ -z "$searchnode_minion" ]] && continue
+            expected_es_nodes+=$'\n'"${searchnode_minion%_searchnode}"
+        done <<< "$searchnode_minions"
+
+        while [[ $retry_count -lt $retries ]]; do
+            SEARCHNODE_ES_VERSIONS=$(so-elasticsearch-query _nodes/_all/version --retry 5 --retry-delay 10 --fail 2>&1)
+            local exit_status=$?
+
+            if [[ $exit_status -ne 0 ]]; then
+                echo "Failed to retrieve Elasticsearch versions from searchnodes... Retrying in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+                ((retry_count++))
+                sleep $delay
+                continue
+            fi
+
+            local all_searchnodes_compatible=true
+            while IFS=$'\t' read -r node current_version; do
+                [[ -z "$node" ]] && continue
+                if ! es_version_can_upgrade_to_target "$current_version"; then
+                    echo "Searchnode $node is running Elasticsearch $current_version, which is not directly upgradable to Elasticsearch $target_es_version."
+                    all_searchnodes_compatible=false
+                fi
+            done < <(echo "$SEARCHNODE_ES_VERSIONS" | jq -r '.nodes | to_entries[] | [.value.name, .value.version] | @tsv')
+
+            while IFS= read -r expected_es_node; do
+                [[ -z "$expected_es_node" ]] && continue
+                if ! echo "$SEARCHNODE_ES_VERSIONS" | jq -e --arg node "$expected_es_node" '.nodes | to_entries | any(.value.name == $node)' > /dev/null; then
+                    echo "Searchnode $expected_es_node did not report an Elasticsearch version. It may be offline or still upgrading."
+                    all_searchnodes_compatible=false
+                fi
+            done <<< "$expected_es_nodes"
+
+            if [[ "$all_searchnodes_compatible" == true ]]; then
+                echo "All Searchnodes are upgradable to Elasticsearch $target_es_version."
+                return 0
+            fi
+
+            echo "One or more Searchnodes cannot upgrade directly to Elasticsearch $target_es_version. Rechecking in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+            ((retry_count++))
+            sleep $delay
+        done
+
+        return 1
+    }
+
+    # Gather heavynode version info and verify that each node is running a version compatible with the target ES version.
+    verify_heavynodes_es_target_compatibility() {
+        local heavynode_minions attempt
+        local retries=20
+        local retry_count=0
+        local delay=180
+        local heavynode_discovery_success=false
+        HEAVYNODE_ES_VERSIONS=""
+
+        for attempt in {1..3}; do
+            if heavynode_minions=$(set -o pipefail; salt-key --out=json --list=accepted 2> /dev/null | jq -r '.minions[]? | select(endswith("heavynode"))'); then
+                heavynode_discovery_success=true
+                break
+            fi
+
+            echo "Failed to retrieve grid heavynodes via salt-key... Retrying in 30 seconds. Attempt $attempt of 3."
+            sleep 30
+        done
+
+        if [[ "$heavynode_discovery_success" != "true" ]]; then
+            echo "Failed to retrieve grid heavynodes via salt-key."
+            return 1
+        fi
+
+        if [[ -z "$heavynode_minions" ]]; then
+            echo "No heavynodes detected. Skipping heavynode Elasticsearch version compatibility check."
+            return 0
+        fi
+
+        while [[ $retry_count -lt $retries ]]; do
+            HEAVYNODE_ES_VERSIONS=$(salt -C 'G@role:so-heavynode' cmd.run 'set -o pipefail; so-elasticsearch-query / --retry 5 --retry-delay 10 | jq -er ".version.number"' shell=/bin/bash --out=json 2> /dev/null)
+            local exit_status=$?
+
+            if [[ $exit_status -ne 0 ]]; then
+                echo "Failed to retrieve Elasticsearch version from one or more heavynodes... Retrying in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+                ((retry_count++))
+                sleep $delay
+                continue
+            fi
+
+            local all_heavynodes_compatible=true
+            while IFS=$'\t' read -r node current_version; do
+                [[ -z "$node" ]] && continue
+                if ! es_version_can_upgrade_to_target "$current_version"; then
+                    echo "Heavynode $node is running Elasticsearch $current_version, which is not directly upgradable to Elasticsearch $target_es_version."
+                    all_heavynodes_compatible=false
+                fi
+            done < <(echo "$HEAVYNODE_ES_VERSIONS" | jq -r 'to_entries[] | [.key, .value] | @tsv')
+
+            while IFS= read -r heavynode_minion; do
+                [[ -z "$heavynode_minion" ]] && continue
+                if ! echo "$HEAVYNODE_ES_VERSIONS" | jq -se --arg minion "$heavynode_minion" 'add | has($minion)' > /dev/null; then
+                    echo "Heavynode $heavynode_minion did not report an Elasticsearch version. It may be offline or still upgrading."
+                    all_heavynodes_compatible=false
+                fi
+            done <<< "$heavynode_minions"
+
+            if [[ "$all_heavynodes_compatible" == true ]]; then
+                echo -e "\nAll heavynodes can upgrade to Elasticsearch $target_es_version."
+                return 0
+            fi
+
+            echo "One or more heavynodes cannot upgrade directly to Elasticsearch $target_es_version. Rechecking in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+            ((retry_count++))
+            sleep $delay
+        done
+
+        return 1
+    }
+
+    if [[ ! -f "$es_verification_script" ]]; then
+        create_intermediate_upgrade_verification_script "$es_verification_script"
+    fi
+
     for statefile in "${es_required_version_statefile_base}"-*; do
         [[ -f $statefile ]] || continue
 
@@ -980,10 +1363,6 @@ verify_es_version_compatibility() {
             continue
         fi
 
-        if [[ ! -f "$es_verification_script" ]]; then
-            create_intermediate_upgrade_verification_script "$es_verification_script"
-        fi
-
         echo -e "\n##############################################################################################################################\n"
         echo "A previously required intermediate Elasticsearch upgrade was detected. Verifying that all Searchnodes/Heavynodes have successfully upgraded Elasticsearch to $es_required_version_statefile_value before proceeding with soup to avoid potential data loss! This command can take up to an hour to complete."
         if ! timeout --foreground 4000 bash "$es_verification_script" "$es_required_version_statefile_value" "$statefile"; then
@@ -1005,6 +1384,26 @@ verify_es_version_compatibility() {
 
     # shellcheck disable=SC2076 # Do not want a regex here eg usage " 8.18.8 9.0.8 " =~ " 9.0.8 "
     if [[ " ${es_upgrade_map[$es_version]} " =~ " $target_es_version " || "$es_version" == "$target_es_version" ]]; then
+        if ! verify_searchnodes_es_target_compatibility || ! verify_heavynodes_es_target_compatibility; then
+            echo -e "\n!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+
+            echo "One or more Searchnode(s)/Heavynode(s) cannot upgrade directly to Elasticsearch $target_es_version. This can happen with soups that include Elasticsearch upgrades being run in quick succession. Typically, this will resolve itself as the grid synchronizes. Please allow time for all Searchnodes/Heavynodes to have upgraded Elasticsearch to a compatible version with $target_es_version before running soup again to avoid potential data loss!"
+
+            if [[ -n "$HEAVYNODE_ES_VERSIONS" ]]; then
+                echo "Current heavynode Elasticsearch versions:"
+                echo "$HEAVYNODE_ES_VERSIONS" | jq '.'
+            fi
+
+            if [[ -n "$SEARCHNODE_ES_VERSIONS" ]]; then
+                echo "Current searchnode Elasticsearch versions:"
+                echo "$SEARCHNODE_ES_VERSIONS" | jq '.nodes | to_entries | map({(.value.name): .value.version}) | sort | add'
+            fi
+
+            echo -e "\n!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+
+            exit 161
+        fi
+
         # supported upgrade
         return 0
     else
@@ -1290,7 +1689,7 @@ EOF
 
 # Keeping this block in case we need to do a hotfix that requires salt update
 apply_hotfix() {
-   echo "No actions required. ($INSTALLEDVERSION/$HOTFIXVERSION)"
+    echo "No actions required. ($INSTALLEDVERSION/$HOTFIXVERSION)"
 }
 
 failed_soup_restore_items() {
@@ -1362,19 +1761,19 @@ main() {
   echo "Verifying we have the latest soup script."
   verify_latest_update_script
 
-  echo "Verifying Elasticsearch version compatibility before upgrading."
-  verify_es_version_compatibility
-
   echo "Let's see if we need to update Security Onion."
   upgrade_check
   upgrade_space
 
+  echo "Verifying Elasticsearch version compatibility across the grid before upgrading."
+  verify_es_version_compatibility
+
   echo "Checking for Salt Master and Minion updates."
   upgrade_check_salt
   set -e
 
   if [[ $is_airgap -eq 0 ]]; then
-    update_airgap_repo
+    update_airgap_repos
     dnf clean all
     check_os_updates
   elif [[ $OS == 'oracle' ]]; then
@@ -1388,7 +1787,8 @@ main() {
     echo "Applying $HOTFIXVERSION hotfix"
     # since we don't run the backup.config_backup state on import we wont snapshot previous version states and pillars
     if [[ ! "$MINION_ROLE" == "import" ]]; then
-      backup_old_states_pillars
+        echo "Running so-config-backup script."
+        /sbin/so-config-backup
     fi
     copy_new_files
     create_local_directories "/opt/so/saltstack/default"
@@ -1444,8 +1844,8 @@ main() {
     # since we don't run the backup.config_backup state on import we wont snapshot previous version states and pillars
     if [[ ! "$MINION_ROLE" == "import" ]]; then
       echo ""
-      echo "Creating snapshots of default and local Salt states and pillars and saving to /nsm/backup/"
-      backup_old_states_pillars
+      echo "Running so-config-backup script."
+      /sbin/so-config-backup
     fi
 
     echo ""
@@ -1657,4 +2057,20 @@ EOF
   read -r input
 fi
 
-main "$@" | tee -a $SOUP_LOG
+set -o errtrace
+trap on_err ERR
+
+if [[ $SOUP_DEBUG == 1 ]]; then
+  if [ -f $SOUP_DEBUG_LOG ]; then
+    current_time=$(date +%Y%m%d.%H%M%S)
+    mv $SOUP_DEBUG_LOG $SOUP_DEBUG_LOG.$INSTALLEDVERSION.$current_time
+  fi
+  exec {SOUP_XTRACE_FD}>>"$SOUP_DEBUG_LOG"
+  export SOUP_XTRACE_FD
+  BASH_XTRACEFD=$SOUP_XTRACE_FD
+  PS4='+ [${BASH_SOURCE##*/}:${LINENO} ${FUNCNAME[0]:-main}()] | '
+  set -x
+  export SOUP_DEBUG
+fi
+
+main "$@" 2>&1 | tee -a $SOUP_LOG

salt/nginx/enabled.sls

@@ -59,6 +59,7 @@ so-nginx:
       - /opt/so/conf/navigator/layers/:/opt/socore/html/navigator/assets/so:ro
       - /opt/so/conf/navigator/config.json:/opt/socore/html/navigator/assets/config.json:ro
       - /nsm/repo:/opt/socore/html/repo:ro
+      - /nsm/kernelrepo:/opt/socore/html/kernelrepo:ro
       - /nsm/rules:/nsm/rules:ro
       {%   if NGINXMERGED.external_suricata %}
       - /opt/so/rules/nids/suri:/surirules:ro

salt/nginx/etc/nginx.conf

@@ -225,6 +225,7 @@ http {
 			limit_req             zone=auth_throttle burst={{ NGINXMERGED.config.throttle_login_burst }} nodelay;
 			limit_req_status      429;
 			proxy_pass            http://{{ GLOBALS.manager }}:4433;
+			proxy_set_header      Connection "Close";
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;
 			proxy_set_header      Host $host;
@@ -237,6 +238,7 @@ http {
 		location ~ ^/auth/.*?(whoami|logout|settings|errors|webauthn.js) {
 			rewrite               /auth/(.*) /$1 break;
 			proxy_pass            http://{{ GLOBALS.manager }}:4433;
+			proxy_set_header      Connection "Close";
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;
 			proxy_set_header      Host $host;
@@ -321,6 +323,16 @@ http {
 			autoindex_localtime on;
 		}
 
+		location /kernelrepo/ {
+			allow all;
+			sendfile on;
+			sendfile_max_chunk 1m;
+			autoindex on;
+			autoindex_exact_size off;
+			autoindex_format html;
+			autoindex_localtime on;
+		}
+
 		location /influxdb/ {
 			auth_request          /auth/sessions/whoami;
 			rewrite               /influxdb/api/(.*) /api/$1 break;

salt/orch/delete_hypervisor.sls

@@ -3,7 +3,14 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-{% set hypervisor = pillar.minion_id %}
+{% set hypervisor = pillar.get('minion_id', '') %}
+
+{% if not hypervisor|regex_match('^([A-Za-z0-9._-]{1,253})$') %}
+{%   do salt.log.error('delete_hypervisor_orch: refusing unsafe minion_id=' ~ hypervisor) %}
+delete_hypervisor_invalid_minion_id:
+  test.fail_without_changes:
+    - name: delete_hypervisor_invalid_minion_id
+{% else %}
 
 ensure_hypervisor_mine_deleted:
   salt.function:
@@ -20,3 +27,5 @@ update_salt_cloud_profile:
     - sls:
       - salt.cloud.config
     - concurrent: True
+
+{% endif %}

salt/orch/so_pillar_reload.sls

@@ -1,112 +0,0 @@
-# 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.
-
-# Driven by the so_pillar_changed reactor. Translates a so_pillar.pillar_entry
-# change into (cache.clear_pillar -> saltutil.refresh_pillar -> state.apply)
-# on the appropriate target.
-#
-# Routing rules live in the DISPATCH map below — one entry per
-# (pillar_path prefix) -> (state sls, role grain). Add new services here
-# rather than wiring more reactors.
-#
-# Idempotent: state.apply is idempotent; if the pillar value didn't actually
-# change anything observable, the affected state runs a no-op. Bulk imports
-# and replays are safe.
-
-{% set change       = salt['pillar.get']('so_pillar_change', {}) %}
-{% set scope        = change.get('scope') %}
-{% set role         = change.get('role_name') %}
-{% set minion       = change.get('minion_id') %}
-{% set changes      = change.get('changes', []) %}
-
-{# (pillar_path prefix) -> {sls: <state to apply>, role: <role grain that runs it>}
-   role is a grain value (e.g. 'so-sensor'), used to compute compound targets
-   when the change is global or role-scoped. #}
-{% set DISPATCH = {
-    'suricata.':       {'sls': 'suricata.config',     'roles': ['so-sensor', 'so-heavynode', 'so-standalone']},
-    'sensor.':         {'sls': 'suricata.config',     'roles': ['so-sensor', 'so-heavynode', 'so-standalone']},
-    'zeek.':           {'sls': 'zeek.config',         'roles': ['so-sensor', 'so-heavynode', 'so-standalone']},
-    'stenographer.':   {'sls': 'stenographer.config', 'roles': ['so-sensor', 'so-heavynode', 'so-standalone']},
-    'pcap.':           {'sls': 'pcap.config',         'roles': ['so-sensor', 'so-heavynode', 'so-standalone']},
-    'logstash.':       {'sls': 'logstash.config',     'roles': ['so-manager', 'so-managersearch', 'so-managerhype', 'so-receiver']},
-    'redis.':          {'sls': 'redis.config',        'roles': ['so-manager', 'so-managersearch', 'so-managerhype', 'so-standalone']},
-    'kafka.':          {'sls': 'kafka.config',        'roles': ['so-manager', 'so-managersearch', 'so-managerhype', 'so-receiver', 'so-searchnode']},
-    'elasticsearch.':  {'sls': 'elasticsearch.config','roles': ['so-manager', 'so-managersearch', 'so-managerhype', 'so-searchnode', 'so-heavynode', 'so-standalone']},
-    'kibana.':         {'sls': 'kibana.config',       'roles': ['so-manager', 'so-managersearch', 'so-managerhype', 'so-standalone']},
-    'soc.':            {'sls': 'soc.config',          'roles': ['so-manager', 'so-managersearch', 'so-managerhype', 'so-standalone']},
-    'telegraf.':       {'sls': 'telegraf.config',     'roles': ['*']},
-    'fleet.':          {'sls': 'fleet.config',        'roles': ['so-fleet']},
-    'strelka.':        {'sls': 'strelka.config',      'roles': ['so-sensor', 'so-heavynode', 'so-standalone']},
-} %}
-
-{# Collect a deduplicated set of (sls, target_kind) actions. target_kind is
-   either 'minion:<id>' (scope=minion) or 'roles:so-x,so-y' (scope=role/global). #}
-{% set actions = {} %}
-
-{% for c in changes %}
-{%   set path = c.get('pillar_path', '') %}
-{%   for prefix, action in DISPATCH.items() %}
-{%     if path.startswith(prefix) %}
-{%       set sls = action['sls'] %}
-{%       if scope == 'minion' and minion %}
-{%         set key = sls ~ '|minion|' ~ minion %}
-{%         set _ = actions.update({key: {'sls': sls, 'tgt': minion, 'tgt_type': 'glob'}}) %}
-{%       else %}
-{%         set role_targets = action['roles'] %}
-{%         if '*' in role_targets %}
-{%           set tgt = '*' %}
-{%           set tgt_type = 'glob' %}
-{%         else %}
-{%           set tgt = ('I@role:' ~ role_targets|join(' or I@role:')) %}
-{%           set tgt_type = 'compound' %}
-{%         endif %}
-{%         set key = sls ~ '|' ~ tgt %}
-{%         set _ = actions.update({key: {'sls': sls, 'tgt': tgt, 'tgt_type': tgt_type}}) %}
-{%       endif %}
-{%     endif %}
-{%   endfor %}
-{% endfor %}
-
-{% if actions %}
-
-{% for key, action in actions.items() %}
-{% set safe_id = loop.index0 | string %}
-
-so_pillar_reload_clear_cache_{{ safe_id }}:
-  salt.runner:
-    - name: cache.clear_pillar
-    - tgt: '{{ action.tgt }}'
-    - tgt_type: '{{ action.tgt_type }}'
-
-so_pillar_reload_refresh_pillar_{{ safe_id }}:
-  salt.function:
-    - name: saltutil.refresh_pillar
-    - tgt: '{{ action.tgt }}'
-    - tgt_type: '{{ action.tgt_type }}'
-    - kwarg:
-        wait: True
-    - require:
-      - salt: so_pillar_reload_clear_cache_{{ safe_id }}
-
-so_pillar_reload_apply_state_{{ safe_id }}:
-  salt.state:
-    - tgt: '{{ action.tgt }}'
-    - tgt_type: '{{ action.tgt_type }}'
-    - sls:
-      - {{ action.sls }}
-    - queue: True
-    - require:
-      - salt: so_pillar_reload_refresh_pillar_{{ safe_id }}
-{% endfor %}
-
-{% else %}
-
-{# No DISPATCH entry matched. Pillar still gets refreshed so any other states
-   read fresh values, but no service-specific reload is invoked. #}
-so_pillar_reload_unmapped_path_noop:
-  test.nop
-  {% do salt.log.info('orch.so_pillar_reload: no dispatch match for %s' % changes) %}
-
-{% endif %}

salt/orch/vm_pillar_clean.sls

@@ -12,7 +12,14 @@
 {% if 'vrt' in salt['pillar.get']('features', []) %}
 
 {%   do salt.log.debug('vm_pillar_clean_orch: Running') %}
-{%   set vm_name = pillar.get('vm_name') %}
+{%   set vm_name = pillar.get('vm_name', '') %}
+
+{%   if not vm_name|regex_match('^([A-Za-z0-9._-]{1,253})$') %}
+{%     do salt.log.error('vm_pillar_clean_orch: refusing unsafe vm_name=' ~ vm_name) %}
+vm_pillar_clean_invalid_name:
+  test.fail_without_changes:
+    - name: vm_pillar_clean_invalid_name
+{%   else %}
 
 delete_adv_{{ vm_name }}_pillar:
   module.run:
@@ -24,6 +31,8 @@ delete_{{ vm_name }}_pillar:
     - file.remove:
       - path: /opt/so/saltstack/local/pillar/minions/{{ vm_name }}.sls
 
+{%   endif %}
+
 {% else %}
 
 {%   do salt.log.error(

salt/postgres/config.sls

@@ -46,10 +46,10 @@ postgresinitdir:
     - require:
       - file: postgresconfdir
 
-postgresinitusers:
+postgresinitdb:
   file.managed:
-    - name: /opt/so/conf/postgres/init/init-users.sh
-    - source: salt://postgres/files/init-users.sh
+    - name: /opt/so/conf/postgres/init/init-db.sh
+    - source: salt://postgres/files/init-db.sh
     - user: 939
     - group: 939
     - mode: 755

salt/postgres/enabled.sls

@@ -31,7 +31,7 @@ so-postgres:
       - POSTGRES_DB=securityonion
       # Passwords are delivered via mounted 0600 secret files, not plaintext env vars.
       # The upstream postgres image resolves POSTGRES_PASSWORD_FILE; entrypoint.sh and
-      # init-users.sh resolve SO_POSTGRES_PASS_FILE the same way.
+      # init-db.sh resolve SO_POSTGRES_PASS_FILE the same way.
       - POSTGRES_PASSWORD_FILE=/run/secrets/postgres_password
       - SO_POSTGRES_USER={{ SO_POSTGRES_USER }}
       - SO_POSTGRES_PASS_FILE=/run/secrets/so_postgres_pass
@@ -46,7 +46,7 @@ so-postgres:
       - /opt/so/conf/postgres/postgresql.conf:/conf/postgresql.conf:ro
       - /opt/so/conf/postgres/pg_hba.conf:/conf/pg_hba.conf:ro
       - /opt/so/conf/postgres/secrets:/run/secrets:ro
-      - /opt/so/conf/postgres/init/init-users.sh:/docker-entrypoint-initdb.d/init-users.sh:ro
+      - /opt/so/conf/postgres/init/init-db.sh:/docker-entrypoint-initdb.d/init-db.sh:ro
       - /etc/pki/postgres.crt:/conf/postgres.crt:ro
       - /etc/pki/postgres.key:/conf/postgres.key:ro
       - /etc/pki/tls/certs/intca.crt:/conf/ca.crt:ro
@@ -70,7 +70,7 @@ so-postgres:
     - watch:
       - file: postgresconf
       - file: postgreshba
-      - file: postgresinitusers
+      - file: postgresinitdb
       - file: postgres_super_secret
       - file: postgres_app_secret
       - x509: postgres_crt
@@ -78,7 +78,7 @@ so-postgres:
     - require:
       - file: postgresconf
       - file: postgreshba
-      - file: postgresinitusers
+      - file: postgresinitdb
       - file: postgres_super_secret
       - file: postgres_app_secret
       - x509: postgres_crt

salt/postgres/files/init-db.sh

@@ -17,6 +17,7 @@ psql -v ON_ERROR_STOP=1 --username "$POSTGRES_USER" --dbname "$POSTGRES_DB" <<-E
         END IF;
     END
     \$\$;
+    GRANT ALL ON SCHEMA public TO "$SO_POSTGRES_USER";
     GRANT ALL PRIVILEGES ON DATABASE "$POSTGRES_DB" TO "$SO_POSTGRES_USER";
     -- Lock the SOC database down at the connect layer; PUBLIC gets CONNECT
     -- by default, which would let per-minion telegraf roles open sessions
@@ -31,4 +32,4 @@ EOSQL
 # only ensures the shared database exists on first initialization.
 if ! psql -U "$POSTGRES_USER" -tAc "SELECT 1 FROM pg_database WHERE datname='so_telegraf'" | grep -q 1; then
     psql -v ON_ERROR_STOP=1 -U "$POSTGRES_USER" -c "CREATE DATABASE so_telegraf"
-fi
+fi

salt/postgres/files/schema/pillar/001_schema.sql

@@ -1,124 +0,0 @@
--- so_pillar schema: queryable, versioned, audited pillar config store.
--- Replaces flat-file Salt pillar consumed via salt.pillar.postgres ext_pillar.
--- Idempotent. Run via salt/postgres/schema_pillar.sls inside the so-postgres container.
-
-CREATE SCHEMA IF NOT EXISTS so_pillar;
-
-CREATE TABLE IF NOT EXISTS so_pillar.scope (
-    scope_kind   text PRIMARY KEY,
-    precedence   int  NOT NULL,
-    description  text
-);
-
-INSERT INTO so_pillar.scope(scope_kind, precedence, description) VALUES
-    ('global', 100, 'Applies to every minion'),
-    ('role',   200, 'Applies to minions whose minion_id matches a top.sls compound role match'),
-    ('minion', 300, 'Applies only to a single minion (per-minion overlay)')
-ON CONFLICT (scope_kind) DO NOTHING;
-
-CREATE TABLE IF NOT EXISTS so_pillar.role (
-    role_name      text PRIMARY KEY,
-    match_kind     text NOT NULL CHECK (match_kind IN ('compound','grain','glob','list')),
-    match_expr     text NOT NULL,
-    description    text
-);
-
-CREATE TABLE IF NOT EXISTS so_pillar.minion (
-    minion_id     text PRIMARY KEY,
-    node_type     text,
-    hostname      text,
-    extra_roles   text[] NOT NULL DEFAULT '{}',
-    created_at    timestamptz NOT NULL DEFAULT now(),
-    updated_at    timestamptz NOT NULL DEFAULT now()
-);
-
-CREATE TABLE IF NOT EXISTS so_pillar.role_member (
-    role_name   text NOT NULL REFERENCES so_pillar.role(role_name) ON DELETE CASCADE,
-    minion_id   text NOT NULL REFERENCES so_pillar.minion(minion_id) ON DELETE CASCADE,
-    source      text NOT NULL DEFAULT 'computed' CHECK (source IN ('computed','manual','imported')),
-    PRIMARY KEY (role_name, minion_id)
-);
-
-CREATE INDEX IF NOT EXISTS ix_role_member_minion ON so_pillar.role_member(minion_id);
-
--- pillar_entry holds the actual data. as_json=True ext_pillar reads `data` directly.
-CREATE TABLE IF NOT EXISTS so_pillar.pillar_entry (
-    id              bigserial PRIMARY KEY,
-    scope           text NOT NULL REFERENCES so_pillar.scope(scope_kind),
-    role_name       text REFERENCES so_pillar.role(role_name) ON DELETE CASCADE,
-    minion_id       text REFERENCES so_pillar.minion(minion_id) ON DELETE CASCADE,
-    pillar_path     text NOT NULL,
-    data            jsonb NOT NULL,
-    is_secret       boolean NOT NULL DEFAULT false,
-    sort_key        int NOT NULL DEFAULT 0,
-    version         int NOT NULL DEFAULT 1,
-    updated_at      timestamptz NOT NULL DEFAULT now(),
-    updated_by      text NOT NULL DEFAULT current_user,
-    change_reason   text,
-    CONSTRAINT pillar_entry_scope_target CHECK (
-           (scope='global' AND role_name IS NULL AND minion_id IS NULL)
-        OR (scope='role'   AND role_name IS NOT NULL AND minion_id IS NULL)
-        OR (scope='minion' AND role_name IS NULL AND minion_id IS NOT NULL)
-    ),
-    -- Reserved namespaces that MUST stay rendered from SLS (mine-driven). Nothing
-    -- under these prefixes is allowed in the database; the merge logic relies on
-    -- ext_pillar leaving these subtrees alone.
-    CONSTRAINT pillar_entry_reserved_paths CHECK (
-        pillar_path NOT LIKE 'elasticsearch.nodes%'
-        AND pillar_path NOT LIKE 'redis.nodes%'
-        AND pillar_path NOT LIKE 'kafka.nodes%'
-        AND pillar_path NOT LIKE 'hypervisor.nodes%'
-        AND pillar_path NOT LIKE 'logstash.nodes%'
-        AND pillar_path NOT LIKE 'node_data.ips%'
-    )
-);
-
-CREATE UNIQUE INDEX IF NOT EXISTS ux_pillar_entry_global ON so_pillar.pillar_entry(pillar_path)
-    WHERE scope = 'global';
-CREATE UNIQUE INDEX IF NOT EXISTS ux_pillar_entry_role ON so_pillar.pillar_entry(role_name, pillar_path)
-    WHERE scope = 'role';
-CREATE UNIQUE INDEX IF NOT EXISTS ux_pillar_entry_minion ON so_pillar.pillar_entry(minion_id, pillar_path)
-    WHERE scope = 'minion';
-
-CREATE INDEX IF NOT EXISTS ix_pillar_entry_minion_hot ON so_pillar.pillar_entry(minion_id)
-    WHERE scope = 'minion';
-CREATE INDEX IF NOT EXISTS ix_pillar_entry_role_hot ON so_pillar.pillar_entry(role_name)
-    WHERE scope = 'role';
-
--- Append-only audit log for every change to pillar_entry. No FK to entry so DELETE
--- history survives the row removal.
-CREATE TABLE IF NOT EXISTS so_pillar.pillar_entry_history (
-    history_id     bigserial PRIMARY KEY,
-    entry_id       bigint,
-    op             text NOT NULL CHECK (op IN ('INSERT','UPDATE','DELETE')),
-    scope          text NOT NULL,
-    role_name      text,
-    minion_id      text,
-    pillar_path    text NOT NULL,
-    old_data       jsonb,
-    new_data       jsonb,
-    is_secret      boolean,
-    version        int,
-    changed_at     timestamptz NOT NULL DEFAULT now(),
-    changed_by     text NOT NULL DEFAULT current_user,
-    change_reason  text
-);
-
-CREATE INDEX IF NOT EXISTS ix_pillar_history_entry  ON so_pillar.pillar_entry_history(entry_id, changed_at DESC);
-CREATE INDEX IF NOT EXISTS ix_pillar_history_minion ON so_pillar.pillar_entry_history(minion_id, changed_at DESC);
-CREATE INDEX IF NOT EXISTS ix_pillar_history_role   ON so_pillar.pillar_entry_history(role_name,  changed_at DESC);
-
--- Drift watch — populated by a pg_cron job that re-renders the on-disk SLS files
--- and compares them to pillar_entry. Cleared once cutover completes.
-CREATE TABLE IF NOT EXISTS so_pillar.drift_log (
-    id              bigserial PRIMARY KEY,
-    scope           text NOT NULL,
-    role_name       text,
-    minion_id       text,
-    pillar_path     text NOT NULL,
-    disk_data       jsonb,
-    db_data         jsonb,
-    detected_at     timestamptz NOT NULL DEFAULT now()
-);
-
-CREATE INDEX IF NOT EXISTS ix_drift_log_detected ON so_pillar.drift_log(detected_at DESC);

salt/postgres/files/schema/pillar/002_views.sql

@@ -1,49 +0,0 @@
--- Views consumed by the Salt master's salt.pillar.postgres ext_pillar with
--- as_json=True. Each view exposes data ordered by (sort_key, pillar_path) so
--- the deep-merge in ext_pillar resolves precedence deterministically.
---
--- ext_pillar always binds exactly one parameter to the query: (minion_id,).
--- Master-config queries reference these views and add WHERE clauses, e.g.:
---   SELECT data FROM so_pillar.v_pillar_role WHERE minion_id = %s
---   SELECT data FROM so_pillar.v_pillar_minion WHERE minion_id = %s
--- For v_pillar_global the binding is satisfied with `WHERE %s IS NOT NULL`.
-
-CREATE OR REPLACE VIEW so_pillar.v_pillar_global AS
-    SELECT pillar_path, sort_key, data
-      FROM so_pillar.pillar_entry
-     WHERE scope = 'global'
-       AND is_secret = false
-     ORDER BY sort_key, pillar_path;
-
--- Role view exposes minion_id so the master-config WHERE clause can filter to
--- the rows that apply to the requesting minion. JOIN to role_member fans out
--- one row per (role assignment, pillar entry) tuple.
-CREATE OR REPLACE VIEW so_pillar.v_pillar_role AS
-    SELECT rm.minion_id,
-           pe.role_name,
-           pe.pillar_path,
-           pe.sort_key,
-           pe.data
-      FROM so_pillar.pillar_entry pe
-      JOIN so_pillar.role_member rm ON rm.role_name = pe.role_name
-     WHERE pe.scope = 'role'
-       AND pe.is_secret = false;
-
-CREATE OR REPLACE VIEW so_pillar.v_pillar_minion AS
-    SELECT minion_id,
-           pillar_path,
-           sort_key,
-           data
-      FROM so_pillar.pillar_entry
-     WHERE scope = 'minion'
-       AND is_secret = false;
-
--- v_pillar_secrets is filled in by 004_secrets.sql once pgcrypto is available;
--- placeholder here returns no rows so initial schema deploy succeeds even on a
--- container that has not yet loaded pgcrypto.
-CREATE OR REPLACE VIEW so_pillar.v_pillar_secrets AS
-    SELECT NULL::text AS minion_id,
-           NULL::text AS pillar_path,
-           NULL::int  AS sort_key,
-           '{}'::jsonb AS data
-     WHERE false;

salt/postgres/files/schema/pillar/003_history_trigger.sql

@@ -1,120 +0,0 @@
--- Audit trigger: every INSERT/UPDATE/DELETE on so_pillar.pillar_entry writes a
--- row to pillar_entry_history. Captures the actor (current_user), reason
--- (passed via SET LOCAL so_pillar.change_reason), and full before/after data.
-
-CREATE OR REPLACE FUNCTION so_pillar.fn_pillar_entry_audit() RETURNS trigger
-LANGUAGE plpgsql AS $fn$
-DECLARE
-    v_reason text := current_setting('so_pillar.change_reason', true);
-BEGIN
-    IF (TG_OP = 'INSERT') THEN
-        INSERT INTO so_pillar.pillar_entry_history(
-            entry_id, op, scope, role_name, minion_id, pillar_path,
-            old_data, new_data, is_secret, version, changed_by, change_reason)
-        VALUES (NEW.id, 'INSERT', NEW.scope, NEW.role_name, NEW.minion_id, NEW.pillar_path,
-                NULL, NEW.data, NEW.is_secret, NEW.version, NEW.updated_by, v_reason);
-        RETURN NEW;
-    ELSIF (TG_OP = 'UPDATE') THEN
-        IF OLD.data IS DISTINCT FROM NEW.data
-           OR OLD.is_secret IS DISTINCT FROM NEW.is_secret THEN
-            INSERT INTO so_pillar.pillar_entry_history(
-                entry_id, op, scope, role_name, minion_id, pillar_path,
-                old_data, new_data, is_secret, version, changed_by, change_reason)
-            VALUES (NEW.id, 'UPDATE', NEW.scope, NEW.role_name, NEW.minion_id, NEW.pillar_path,
-                    OLD.data, NEW.data, NEW.is_secret, NEW.version, NEW.updated_by, v_reason);
-        END IF;
-        RETURN NEW;
-    ELSIF (TG_OP = 'DELETE') THEN
-        INSERT INTO so_pillar.pillar_entry_history(
-            entry_id, op, scope, role_name, minion_id, pillar_path,
-            old_data, new_data, is_secret, version, changed_by, change_reason)
-        VALUES (OLD.id, 'DELETE', OLD.scope, OLD.role_name, OLD.minion_id, OLD.pillar_path,
-                OLD.data, NULL, OLD.is_secret, OLD.version, current_user, v_reason);
-        RETURN OLD;
-    END IF;
-    RETURN NULL;
-END
-$fn$;
-
-DROP TRIGGER IF EXISTS pillar_entry_audit ON so_pillar.pillar_entry;
-CREATE TRIGGER pillar_entry_audit
-    AFTER INSERT OR UPDATE OR DELETE ON so_pillar.pillar_entry
-    FOR EACH ROW EXECUTE FUNCTION so_pillar.fn_pillar_entry_audit();
-
--- updated_at + version maintenance: bump version on every UPDATE that changes data.
-CREATE OR REPLACE FUNCTION so_pillar.fn_pillar_entry_versioning() RETURNS trigger
-LANGUAGE plpgsql AS $fn$
-BEGIN
-    IF (TG_OP = 'UPDATE') THEN
-        IF OLD.data IS DISTINCT FROM NEW.data
-           OR OLD.is_secret IS DISTINCT FROM NEW.is_secret THEN
-            NEW.version := OLD.version + 1;
-            NEW.updated_at := now();
-        ELSE
-            NEW.version := OLD.version;
-            NEW.updated_at := OLD.updated_at;
-        END IF;
-    END IF;
-    RETURN NEW;
-END
-$fn$;
-
-DROP TRIGGER IF EXISTS pillar_entry_versioning ON so_pillar.pillar_entry;
-CREATE TRIGGER pillar_entry_versioning
-    BEFORE UPDATE ON so_pillar.pillar_entry
-    FOR EACH ROW EXECUTE FUNCTION so_pillar.fn_pillar_entry_versioning();
-
--- Recompute role_member rows for a minion based on node_type.
--- Compound matchers in pillar/top.sls are pure suffix patterns of the form
--- '*_<rolename>' plus the special multi-role 'manager/managersearch/managerhype'
--- bucket. node_type is split on common dashes/underscores; any token that
--- matches a known role_name produces a role_member row.
-CREATE OR REPLACE FUNCTION so_pillar.fn_recompute_role_members(p_minion_id text)
-RETURNS void LANGUAGE plpgsql AS $fn$
-DECLARE
-    v_node_type text;
-    v_extra     text[];
-    v_role      text;
-BEGIN
-    SELECT node_type, extra_roles INTO v_node_type, v_extra
-      FROM so_pillar.minion WHERE minion_id = p_minion_id;
-
-    IF v_node_type IS NULL THEN
-        RETURN;
-    END IF;
-
-    DELETE FROM so_pillar.role_member
-     WHERE minion_id = p_minion_id AND source = 'computed';
-
-    -- Main role from node_type.
-    IF EXISTS (SELECT 1 FROM so_pillar.role WHERE role_name = lower(v_node_type)) THEN
-        INSERT INTO so_pillar.role_member(role_name, minion_id, source)
-        VALUES (lower(v_node_type), p_minion_id, 'computed')
-        ON CONFLICT DO NOTHING;
-    END IF;
-
-    -- Extra roles supplied by the importer / reactor for compound matchers
-    -- that need to apply multiple buckets (e.g. managersearch also gets the
-    -- 'manager' bucket per top.sls line 36 grouping).
-    FOREACH v_role IN ARRAY COALESCE(v_extra, '{}'::text[]) LOOP
-        IF EXISTS (SELECT 1 FROM so_pillar.role WHERE role_name = v_role) THEN
-            INSERT INTO so_pillar.role_member(role_name, minion_id, source)
-            VALUES (v_role, p_minion_id, 'computed')
-            ON CONFLICT DO NOTHING;
-        END IF;
-    END LOOP;
-END
-$fn$;
-
-CREATE OR REPLACE FUNCTION so_pillar.fn_minion_after_change() RETURNS trigger
-LANGUAGE plpgsql AS $fn$
-BEGIN
-    PERFORM so_pillar.fn_recompute_role_members(COALESCE(NEW.minion_id, OLD.minion_id));
-    RETURN COALESCE(NEW, OLD);
-END
-$fn$;
-
-DROP TRIGGER IF EXISTS minion_role_sync ON so_pillar.minion;
-CREATE TRIGGER minion_role_sync
-    AFTER INSERT OR UPDATE OF node_type, extra_roles ON so_pillar.minion
-    FOR EACH ROW EXECUTE FUNCTION so_pillar.fn_minion_after_change();

salt/postgres/files/schema/pillar/004_secrets.sql

@@ -1,130 +0,0 @@
--- pgcrypto-backed secret storage for pillar_entry rows where is_secret = true.
--- The plaintext value is encrypted with a symmetric key held in a server-side
--- GUC (so_pillar.master_key) which is set per-role via ALTER ROLE so the key
--- never touches a flat file readable by Salt itself.
-
-CREATE EXTENSION IF NOT EXISTS pgcrypto WITH SCHEMA public;
-
--- Encrypt a JSONB value using the configured master key. Stored as a JSONB
--- envelope {"_enc": "<armored ciphertext>"} so the same column type is reused.
-CREATE OR REPLACE FUNCTION so_pillar.fn_encrypt_jsonb(p_value jsonb)
-RETURNS jsonb LANGUAGE plpgsql AS $fn$
-DECLARE
-    v_key text := current_setting('so_pillar.master_key', true);
-BEGIN
-    IF v_key IS NULL OR v_key = '' THEN
-        RAISE EXCEPTION 'so_pillar.master_key GUC not configured';
-    END IF;
-    RETURN jsonb_build_object(
-        '_enc',
-        encode(pgp_sym_encrypt(p_value::text, v_key), 'base64')
-    );
-END
-$fn$;
-
--- Decrypt the envelope produced by fn_encrypt_jsonb. SECURITY DEFINER so callers
--- with no direct access to pgcrypto/master_key can still pull plaintext via the
--- v_pillar_secrets view.
-CREATE OR REPLACE FUNCTION so_pillar.fn_decrypt_jsonb(p_envelope jsonb)
-RETURNS jsonb LANGUAGE plpgsql SECURITY DEFINER AS $fn$
-DECLARE
-    v_key text := current_setting('so_pillar.master_key', true);
-    v_ct  text;
-BEGIN
-    IF v_key IS NULL OR v_key = '' THEN
-        RAISE EXCEPTION 'so_pillar.master_key GUC not configured';
-    END IF;
-    v_ct := p_envelope->>'_enc';
-    IF v_ct IS NULL THEN
-        RETURN p_envelope;          -- not encrypted; pass through
-    END IF;
-    RETURN pgp_sym_decrypt(decode(v_ct, 'base64'), v_key)::jsonb;
-END
-$fn$;
-
-REVOKE ALL ON FUNCTION so_pillar.fn_decrypt_jsonb(jsonb) FROM PUBLIC;
-
--- Secrets view consumed by ext_pillar. Decrypts at the boundary so Salt sees
--- plaintext JSONB. Filters the rows to those that apply to the requesting
--- minion via current_setting, since views can't take parameters and ext_pillar
--- can only bind one parameter per query.
---
--- Master-config query: SELECT data FROM so_pillar.v_pillar_secrets WHERE %s IS NOT NULL
--- The %s satisfies the bound parameter; the view itself reads the minion_id
--- from a session GUC set by a small wrapper function (see fn_pillar_secrets).
-CREATE OR REPLACE FUNCTION so_pillar.fn_pillar_secrets(p_minion_id text)
-RETURNS TABLE(data jsonb)
-LANGUAGE sql STABLE SECURITY DEFINER AS $fn$
-    SELECT so_pillar.fn_decrypt_jsonb(pe.data)
-      FROM so_pillar.pillar_entry pe
-     WHERE pe.is_secret = true
-       AND ( pe.scope = 'global'
-          OR (pe.scope = 'role'
-              AND pe.role_name IN (
-                  SELECT role_name FROM so_pillar.role_member
-                   WHERE minion_id = p_minion_id))
-          OR (pe.scope = 'minion' AND pe.minion_id = p_minion_id))
-     ORDER BY pe.sort_key, pe.pillar_path;
-$fn$;
-
--- Replace the placeholder view from 002 with a parameterised version. Master
--- config query becomes:
---   SELECT data FROM so_pillar.fn_pillar_secrets(%s) AS s
-DROP VIEW IF EXISTS so_pillar.v_pillar_secrets;
-CREATE OR REPLACE VIEW so_pillar.v_pillar_secrets AS
-    SELECT NULL::text AS minion_id,
-           NULL::text AS pillar_path,
-           NULL::int  AS sort_key,
-           '{}'::jsonb AS data
-     WHERE false;
-COMMENT ON VIEW so_pillar.v_pillar_secrets IS
-    'Deprecated placeholder; use SELECT data FROM so_pillar.fn_pillar_secrets(minion_id) instead';
-
--- Convenience helper for so-yaml.py and the importer to set a secret without
--- ever exposing the master_key to the caller. SECURITY DEFINER means the
--- caller does not need read access to so_pillar.master_key.
-CREATE OR REPLACE FUNCTION so_pillar.fn_set_secret(
-    p_scope         text,
-    p_role_name     text,
-    p_minion_id     text,
-    p_pillar_path   text,
-    p_value         jsonb,
-    p_change_reason text DEFAULT NULL
-) RETURNS bigint LANGUAGE plpgsql SECURITY DEFINER AS $fn$
-DECLARE
-    v_envelope jsonb := so_pillar.fn_encrypt_jsonb(p_value);
-    v_id       bigint;
-BEGIN
-    PERFORM set_config('so_pillar.change_reason',
-                       COALESCE(p_change_reason, 'fn_set_secret'),
-                       true);
-
-    INSERT INTO so_pillar.pillar_entry(
-        scope, role_name, minion_id, pillar_path, data, is_secret, change_reason)
-    VALUES (p_scope, p_role_name, p_minion_id, p_pillar_path, v_envelope, true, p_change_reason)
-    ON CONFLICT (pillar_path) WHERE scope='global' DO UPDATE
-       SET data = EXCLUDED.data, is_secret = true, change_reason = EXCLUDED.change_reason
-       RETURNING id INTO v_id;
-
-    IF v_id IS NULL THEN
-        UPDATE so_pillar.pillar_entry
-           SET data = v_envelope, is_secret = true, change_reason = p_change_reason
-         WHERE scope = p_scope
-           AND COALESCE(role_name,'') = COALESCE(p_role_name,'')
-           AND COALESCE(minion_id,'') = COALESCE(p_minion_id,'')
-           AND pillar_path = p_pillar_path
-         RETURNING id INTO v_id;
-
-        IF v_id IS NULL THEN
-            INSERT INTO so_pillar.pillar_entry(
-                scope, role_name, minion_id, pillar_path, data, is_secret, change_reason)
-            VALUES (p_scope, p_role_name, p_minion_id, p_pillar_path, v_envelope, true, p_change_reason)
-            RETURNING id INTO v_id;
-        END IF;
-    END IF;
-
-    RETURN v_id;
-END
-$fn$;
-
-REVOKE ALL ON FUNCTION so_pillar.fn_set_secret(text,text,text,text,jsonb,text) FROM PUBLIC;

salt/postgres/files/schema/pillar/005_seed_roles.sql

@@ -1,39 +0,0 @@
--- Seed the so_pillar.role table with the role buckets defined in pillar/top.sls.
--- The match_expr column preserves the original Salt compound expression purely
--- as documentation; PG-side membership is materialised in role_member.
--- Idempotent: ON CONFLICT lets re-application leave existing rows untouched.
-
-INSERT INTO so_pillar.role(role_name, match_kind, match_expr, description) VALUES
-    ('manager',       'compound', '*_manager or *_managersearch or *_managerhype',
-        'Manager-class node. Includes managersearch and managerhype subtypes.'),
-    ('managersearch', 'compound', '*_managersearch',
-        'Combined manager + searchnode role.'),
-    ('managerhype',   'compound', '*_managerhype',
-        'Combined manager + hypervisor role.'),
-    ('sensor',        'compound', '*_sensor',
-        'Sensor node running zeek/suricata/strelka.'),
-    ('eval',          'compound', '*_eval',
-        'Single-node evaluation install (manager + sensor + storage on one host).'),
-    ('standalone',    'compound', '*_standalone',
-        'Single-node production install (no distributed cluster).'),
-    ('heavynode',     'compound', '*_heavynode',
-        'Distributed manager node carrying logstash + ES.'),
-    ('idh',           'compound', '*_idh',
-        'Intrusion-detection-honeypot node.'),
-    ('searchnode',    'compound', '*_searchnode',
-        'Distributed Elasticsearch search node.'),
-    ('receiver',      'compound', '*_receiver',
-        'Kafka receiver node.'),
-    ('import',        'compound', '*_import',
-        'Single-node import-only install.'),
-    ('fleet',         'compound', '*_fleet',
-        'Elastic Fleet server node.'),
-    ('hypervisor',    'compound', '*_hypervisor',
-        'Hypervisor host (libvirt). Hosts VM minions.'),
-    ('desktop',       'compound', '*_desktop',
-        'Desktop minion (no firewall/nginx pillars apply).'),
-    ('not_desktop',   'compound', '* and not *_desktop',
-        'Pseudo-role; matches every minion that is not a desktop. Used for global firewall/nginx.'),
-    ('libvirt',       'grain',    'salt-cloud:driver:libvirt',
-        'Pseudo-role; matches any minion with grain salt-cloud.driver = libvirt.')
-ON CONFLICT (role_name) DO NOTHING;

salt/postgres/files/schema/pillar/006_rls.sql

@@ -1,107 +0,0 @@
--- Roles + Row-Level Security policies for the so_pillar schema.
--- Three roles:
---   so_pillar_master         — connected by salt-master ext_pillar. Read-only.
---                              RLS forces it to skip is_secret rows; reads
---                              encrypted secrets only via fn_pillar_secrets().
---   so_pillar_writer         — connected by so-yaml dual-write and the SOC
---                              PostgresConfigstore. Read+write on pillar_entry,
---                              minion, role_member.
---   so_pillar_secret_owner   — owns the master encryption key GUC; sole role
---                              allowed to call fn_set_secret directly. Other
---                              writers reach this function only via grants.
---
--- The existing app role so_postgres_user (created by init-users.sh) is granted
--- INTO so_pillar_writer so SOC keeps using its existing connection but inherits
--- pillar-write capability.
-
-DO $$
-BEGIN
-    IF NOT EXISTS (SELECT 1 FROM pg_roles WHERE rolname = 'so_pillar_master') THEN
-        CREATE ROLE so_pillar_master NOLOGIN;
-    END IF;
-    IF NOT EXISTS (SELECT 1 FROM pg_roles WHERE rolname = 'so_pillar_writer') THEN
-        CREATE ROLE so_pillar_writer NOLOGIN;
-    END IF;
-    IF NOT EXISTS (SELECT 1 FROM pg_roles WHERE rolname = 'so_pillar_secret_owner') THEN
-        CREATE ROLE so_pillar_secret_owner NOLOGIN;
-    END IF;
-END
-$$;
-
--- USAGE on the schema is the bare minimum needed to reference its tables.
--- CONNECT on the database is needed before the role can establish a session
--- at all (default privileges on a new DB grant CONNECT to PUBLIC, but if the
--- securityonion database is restricted that grant has to be explicit).
--- Password + LOGIN privileges are set later in schema_pillar.sls because
--- the password lives in pillar (secrets:pillar_master_pass) and plain SQL
--- can't substitute pillar values.
-GRANT CONNECT ON DATABASE securityonion TO so_pillar_master, so_pillar_writer, so_pillar_secret_owner;
-GRANT USAGE ON SCHEMA so_pillar TO so_pillar_master, so_pillar_writer, so_pillar_secret_owner;
-
--- Read access for ext_pillar through the views only.
-GRANT SELECT ON so_pillar.v_pillar_global,
-                so_pillar.v_pillar_role,
-                so_pillar.v_pillar_minion
-    TO so_pillar_master;
-GRANT EXECUTE ON FUNCTION so_pillar.fn_pillar_secrets(text) TO so_pillar_master;
-
--- (change_queue grants live in 008_change_notify.sql alongside the table itself,
--- since the table doesn't exist until 008 runs.)
-
--- Writer needs CRUD on pillar_entry/minion/role_member plus access to seed tables.
-GRANT SELECT, INSERT, UPDATE, DELETE
-    ON so_pillar.pillar_entry,
-       so_pillar.minion,
-       so_pillar.role_member
-    TO so_pillar_writer;
-GRANT SELECT ON so_pillar.role, so_pillar.scope TO so_pillar_writer;
-GRANT SELECT, INSERT, UPDATE, DELETE ON so_pillar.drift_log TO so_pillar_writer;
-GRANT USAGE, SELECT ON ALL SEQUENCES IN SCHEMA so_pillar TO so_pillar_writer;
-GRANT SELECT ON so_pillar.pillar_entry_history TO so_pillar_writer;
-
--- Secret owner can call fn_set_secret directly; writer goes through it via the
--- function's SECURITY DEFINER attribute, which executes as the function owner.
-GRANT EXECUTE ON FUNCTION so_pillar.fn_set_secret(text,text,text,text,jsonb,text)
-    TO so_pillar_writer, so_pillar_secret_owner;
-
--- so_postgres_user (SOC's existing app user, created by init-users.sh) inherits
--- writer privilege so the PostgresConfigstore in SOC can mutate pillars without
--- a second connection pool. Inheritance is per-PG default (NOINHERIT must be
--- explicit), so this just works.
-DO $$
-BEGIN
-    IF EXISTS (SELECT 1 FROM pg_roles WHERE rolname = current_setting('so_pillar.app_role', true))
-    THEN
-        EXECUTE format('GRANT so_pillar_writer TO %I',
-                       current_setting('so_pillar.app_role', true));
-    ELSIF EXISTS (SELECT 1 FROM pg_roles WHERE rolname = 'so_postgres_user') THEN
-        GRANT so_pillar_writer TO so_postgres_user;
-    END IF;
-END
-$$;
-
--- RLS on pillar_entry: master sees only non-secret rows. Writer sees all
--- (it must, to UPDATE secret rows when so-yaml replaces them). Secret rows
--- still require fn_decrypt_jsonb to read plaintext.
-ALTER TABLE so_pillar.pillar_entry ENABLE ROW LEVEL SECURITY;
-ALTER TABLE so_pillar.pillar_entry FORCE ROW LEVEL SECURITY;
-
-DROP POLICY IF EXISTS pillar_entry_master_read    ON so_pillar.pillar_entry;
-DROP POLICY IF EXISTS pillar_entry_writer_all     ON so_pillar.pillar_entry;
-DROP POLICY IF EXISTS pillar_entry_owner_all      ON so_pillar.pillar_entry;
-
-CREATE POLICY pillar_entry_master_read ON so_pillar.pillar_entry
-    FOR SELECT TO so_pillar_master
-    USING (NOT is_secret);
-
-CREATE POLICY pillar_entry_writer_all ON so_pillar.pillar_entry
-    FOR ALL TO so_pillar_writer
-    USING (true)
-    WITH CHECK (true);
-
-CREATE POLICY pillar_entry_owner_all ON so_pillar.pillar_entry
-    FOR ALL TO so_pillar_secret_owner
-    USING (true)
-    WITH CHECK (true);
-
--- minion / role_member do not need RLS — they hold no secrets.

salt/postgres/files/schema/pillar/007_drift_pgcron.sql

@@ -1,43 +0,0 @@
--- Drift detection + retention via pg_cron. Optional — the schema_pillar.sls
--- state guards this file behind the postgres:so_pillar:drift_check_enabled
--- pillar flag because pg_cron may not be loaded on every install.
-
-CREATE EXTENSION IF NOT EXISTS pg_cron;
-
--- Retention: trim pillar_entry_history older than a year. Adjustable via the
--- so_pillar.history_retention_days GUC (default 365 if unset).
-CREATE OR REPLACE FUNCTION so_pillar.fn_history_retain()
-RETURNS void LANGUAGE plpgsql AS $fn$
-DECLARE
-    v_days int := COALESCE(current_setting('so_pillar.history_retention_days', true)::int, 365);
-BEGIN
-    DELETE FROM so_pillar.pillar_entry_history
-     WHERE changed_at < (now() - (v_days::text || ' days')::interval);
-END
-$fn$;
-
--- Drift retention: keep two weeks of drift_log.
-CREATE OR REPLACE FUNCTION so_pillar.fn_drift_retain()
-RETURNS void LANGUAGE plpgsql AS $fn$
-BEGIN
-    DELETE FROM so_pillar.drift_log
-     WHERE detected_at < (now() - interval '14 days');
-END
-$fn$;
-
--- pg_cron schedules (idempotent — unschedule any existing same-named job first).
-DO $$
-DECLARE
-    v_jobid bigint;
-BEGIN
-    SELECT jobid INTO v_jobid FROM cron.job WHERE jobname = 'so_pillar_history_retain';
-    IF v_jobid IS NOT NULL THEN PERFORM cron.unschedule(v_jobid); END IF;
-    PERFORM cron.schedule('so_pillar_history_retain', '15 3 * * *',
-                          'SELECT so_pillar.fn_history_retain();');
-
-    SELECT jobid INTO v_jobid FROM cron.job WHERE jobname = 'so_pillar_drift_retain';
-    IF v_jobid IS NOT NULL THEN PERFORM cron.unschedule(v_jobid); END IF;
-    PERFORM cron.schedule('so_pillar_drift_retain', '20 3 * * *',
-                          'SELECT so_pillar.fn_drift_retain();');
-END
-$$;

salt/postgres/files/schema/pillar/008_change_notify.sql

@@ -1,89 +0,0 @@
--- pg_notify-driven change fan-out for so_pillar.pillar_entry.
---
--- Two layers:
---   1. so_pillar.change_queue          — durable, drained by the salt-master
---                                        engine. Survives engine downtime,
---                                        de-duplicated by id, processed once.
---   2. pg_notify('so_pillar_change')   — wakeup signal. Payload is the
---                                        change_queue row id and locator
---                                        (no secret data — channels are
---                                        snoopable by anyone with LISTEN).
---
--- The salt-master engine LISTENs on the channel for low-latency wakeup,
--- then SELECTs unprocessed change_queue rows so a missed notification
--- (engine restart, network blip) self-heals on the next event.
-
-CREATE TABLE IF NOT EXISTS so_pillar.change_queue (
-    id            bigserial PRIMARY KEY,
-    scope         text        NOT NULL,
-    role_name     text,
-    minion_id     text,
-    pillar_path   text        NOT NULL,
-    op            text        NOT NULL CHECK (op IN ('INSERT','UPDATE','DELETE')),
-    enqueued_at   timestamptz NOT NULL DEFAULT now(),
-    processed_at  timestamptz
-);
-
--- Hot index for the engine's drain query.
-CREATE INDEX IF NOT EXISTS ix_change_queue_unprocessed
-    ON so_pillar.change_queue (id)
-    WHERE processed_at IS NULL;
-
--- Retention index: pg_cron job in 007 sweeps processed rows older than 7d.
-CREATE INDEX IF NOT EXISTS ix_change_queue_processed_at
-    ON so_pillar.change_queue (processed_at)
-    WHERE processed_at IS NOT NULL;
-
-CREATE OR REPLACE FUNCTION so_pillar.fn_pillar_entry_notify()
-    RETURNS trigger
-    LANGUAGE plpgsql
-AS $$
-DECLARE
-    v_row record;
-    v_id  bigint;
-BEGIN
-    IF TG_OP = 'DELETE' THEN
-        v_row := OLD;
-    ELSE
-        v_row := NEW;
-    END IF;
-
-    INSERT INTO so_pillar.change_queue
-        (scope, role_name, minion_id, pillar_path, op)
-    VALUES
-        (v_row.scope, v_row.role_name, v_row.minion_id, v_row.pillar_path, TG_OP)
-    RETURNING id INTO v_id;
-
-    -- Payload is the queue id + locator only. Engine joins back to
-    -- pillar_entry if it needs the data — keeps secrets off the wire.
-    PERFORM pg_notify('so_pillar_change', json_build_object(
-        'queue_id',    v_id,
-        'scope',       v_row.scope,
-        'role_name',   v_row.role_name,
-        'minion_id',   v_row.minion_id,
-        'pillar_path', v_row.pillar_path,
-        'op',          TG_OP
-    )::text);
-
-    RETURN NULL;
-END;
-$$;
-
-DROP TRIGGER IF EXISTS tg_pillar_entry_notify ON so_pillar.pillar_entry;
-CREATE TRIGGER tg_pillar_entry_notify
-    AFTER INSERT OR UPDATE OR DELETE
-    ON so_pillar.pillar_entry
-    FOR EACH ROW
-    EXECUTE FUNCTION so_pillar.fn_pillar_entry_notify();
-
--- Role grants on the change_queue table. Lived in 006_rls.sql historically but
--- moved here so the GRANT references resolve — 006 runs before this file does.
--- Engine reads + drains the change queue from the salt-master process. It
--- needs SELECT to find unprocessed rows and UPDATE to mark them processed.
--- The queue contains only locator metadata (no pillar data), so the master
--- role's existing privilege footprint is unchanged in practice.
-GRANT SELECT, UPDATE ON so_pillar.change_queue TO so_pillar_master;
-GRANT USAGE ON SEQUENCE so_pillar.change_queue_id_seq TO so_pillar_master;
--- Writer needs INSERT (the trigger runs as table owner, so this is just for
--- direct testing / manual replays from psql).
-GRANT INSERT ON so_pillar.change_queue TO so_pillar_writer;

salt/postgres/init.sls

@@ -8,7 +8,6 @@
 include:
 {% if PGMERGED.enabled %}
   - postgres.enabled
-  - postgres.schema_pillar
 {% else %}
   - postgres.disabled
 {% endif %}

salt/postgres/schema_pillar.sls

@@ -1,187 +0,0 @@
-# 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 'postgres' in allowed_states %}
-{%   from 'vars/globals.map.jinja' import GLOBALS %}
-
-# Deploys the so_pillar schema (tables, views, audit triggers, secrets,
-# RLS, pg_cron retention) inside the so-postgres container. Idempotent —
-# every CREATE / GRANT is wrapped in IF NOT EXISTS / ON CONFLICT or DO
-# blocks so re-running the state is a no-op when the schema is current.
-#
-# Gated on the postgres:so_pillar:enabled feature flag (default false).
-# Flip to true once the postsalt branch is ready to bring ext_pillar live.
-
-include:
-  - postgres.enabled
-
-{% set so_pillar_enabled = salt['pillar.get']('postgres:so_pillar:enabled', False) %}
-{% if so_pillar_enabled %}
-
-{% set drift_enabled = salt['pillar.get']('postgres:so_pillar:drift_check_enabled', False) %}
-{% set schema_dir = '/opt/so/saltstack/default/salt/postgres/files/schema/pillar' %}
-
-# Wait for postgres to actually accept TCP connections. Same idiom as
-# telegraf_users.sls. The docker_container.running state returns earlier than
-# the database is ready on first init.
-so_pillar_postgres_wait_ready:
-  cmd.run:
-    - name: |
-        for i in $(seq 1 60); do
-          if docker exec so-postgres pg_isready -h 127.0.0.1 -U postgres -q 2>/dev/null; then
-            exit 0
-          fi
-          sleep 2
-        done
-        echo "so-postgres did not accept TCP connections within 120s" >&2
-        exit 1
-    - require:
-      - docker_container: so-postgres
-
-{% set sql_files = [
-     '001_schema.sql',
-     '002_views.sql',
-     '003_history_trigger.sql',
-     '004_secrets.sql',
-     '005_seed_roles.sql',
-     '006_rls.sql',
-] %}
-
-{% if drift_enabled %}
-{%   do sql_files.append('007_drift_pgcron.sql') %}
-{% endif %}
-
-# 008 always applies — pg_notify-driven change fan-out is what the salt-master
-# pg_notify_pillar engine consumes. Without it reactor wiring sees no events.
-{% do sql_files.append('008_change_notify.sql') %}
-
-{% for sql_file in sql_files %}
-so_pillar_apply_{{ sql_file | replace('.', '_') }}:
-  cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d securityonion \
-          < {{ schema_dir }}/{{ sql_file }}
-    - require:
-      - cmd: so_pillar_postgres_wait_ready
-{%   if not loop.first %}
-      - cmd: so_pillar_apply_{{ sql_files[loop.index0 - 1] | replace('.', '_') }}
-{%   endif %}
-{% endfor %}
-
-# Set the master encryption key GUC on the secret-owner role. The key itself
-# is generated by setup/so-functions::secrets_pillar() (extended for postsalt)
-# and lives in /opt/so/conf/postgres/so_pillar.key (mode 0400) — never read by
-# Salt itself; the value flows into PG via ALTER ROLE so it sits only in the
-# server's role catalog.
-so_pillar_master_key_configure:
-  cmd.run:
-    - name: |
-        if [ -r /opt/so/conf/postgres/so_pillar.key ]; then
-          KEY="$(< /opt/so/conf/postgres/so_pillar.key)"
-          docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d securityonion <<EOSQL
-        ALTER ROLE so_pillar_secret_owner SET so_pillar.master_key = '$KEY';
-        ALTER ROLE so_pillar_master       SET so_pillar.master_key = '$KEY';
-        ALTER ROLE so_pillar_writer       SET so_pillar.master_key = '$KEY';
-        EOSQL
-        else
-          echo "so_pillar.key not present yet; setup/so-functions must generate it before schema_pillar.sls" >&2
-          exit 1
-        fi
-    - require:
-      - cmd: so_pillar_apply_{{ sql_files[-1] | replace('.', '_') }}
-
-# Set login passwords on the so_pillar_* roles. 006_rls.sql creates the roles
-# as NOLOGIN with no password (plain SQL can't substitute pillar values), so
-# the salt-master ext_pillar and the pg_notify_pillar engine — both of which
-# connect as so_pillar_master via TCP — would fail with "password
-# authentication failed" without this step. The password lives in pillar
-# under secrets:pillar_master_pass (generated by setup/so-functions::secrets_pillar)
-# and is the same one rendered into ext_pillar_postgres.conf.jinja and the
-# engines.conf pg_notify_pillar block, so all three sides agree.
-so_pillar_role_login_passwords:
-  cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d securityonion <<EOSQL
-        ALTER ROLE so_pillar_master       WITH LOGIN PASSWORD '{{ pillar['secrets']['pillar_master_pass'] }}';
-        ALTER ROLE so_pillar_writer       WITH LOGIN PASSWORD '{{ pillar['secrets']['pillar_master_pass'] }}';
-        ALTER ROLE so_pillar_secret_owner WITH LOGIN PASSWORD '{{ pillar['secrets']['pillar_master_pass'] }}';
-        EOSQL
-    - require:
-      - cmd: so_pillar_master_key_configure
-
-# Install psycopg2 into salt-master's bundled python so the pg_notify_pillar
-# engine module can `import psycopg2`. Without this the engine's import fails
-# silently in salt's loader and the engine just never starts. salt's bundled
-# python at /opt/saltstack/salt/bin/python3 doesn't ship psycopg by default.
-#
-# Uses cmd.run with an `unless` import-test rather than pip.installed because
-# pip exits non-zero if patchelf isn't on PATH (it tries to rewrite the
-# psycopg2 wheel's RPATH after extraction), even though the wheel is fully
-# installed and importable. salt's pip.installed surfaces the non-zero exit
-# as a state failure and the cascade kills schema_pillar's downstream work.
-# `import psycopg2` succeeds either way, so that's the actual readiness gate.
-#
-# Pip's stdout/stderr is redirected to /opt/so/log/so_pillar/psycopg2_install.log
-# so the literal "ERROR: ... patchelf" line doesn't get hoovered up into
-# /root/sosetup.log and then into /root/errors.log by verify_setup's
-# substring-grep for "ERROR". The redirect target is preserved for
-# triage if `import psycopg2` ever does fail.
-so_pillar_psycopg2_in_salt_python:
-  cmd.run:
-    - name: |
-        mkdir -p /opt/so/log/so_pillar
-        /opt/saltstack/salt/bin/pip3 install --quiet psycopg2-binary \
-          >/opt/so/log/so_pillar/psycopg2_install.log 2>&1 \
-          || true
-    - unless: /opt/saltstack/salt/bin/python3 -c "import psycopg2"
-    - require:
-      - cmd: so_pillar_role_login_passwords
-
-# Run the importer once after the schema is in place. Idempotent — re-runs
-# with no SLS edits produce zero row changes.
-so_pillar_initial_import:
-  cmd.run:
-    - name: /usr/sbin/so-pillar-import --yes --reason 'schema_pillar.sls initial import'
-    - require:
-      - cmd: so_pillar_psycopg2_in_salt_python
-
-# Flip so-yaml from dual-write to PG-canonical for managed paths now that
-# the schema and importer are both in place. Bootstrap files (secrets.sls,
-# postgres/auth.sls, ca/init.sls, *.nodes.sls, top.sls, ...) remain on disk
-# regardless because so_yaml_postgres.locate() raises SkipPath for them.
-so_pillar_so_yaml_mode_dir:
-  file.directory:
-    - name: /opt/so/conf/so-yaml
-    - user: socore
-    - group: socore
-    - mode: '0755'
-    - makedirs: True
-
-so_pillar_so_yaml_mode_postgres:
-  file.managed:
-    - name: /opt/so/conf/so-yaml/mode
-    - contents: postgres
-    - user: socore
-    - group: socore
-    - mode: '0644'
-    - require:
-      - file: so_pillar_so_yaml_mode_dir
-      - cmd: so_pillar_initial_import
-
-{% else %}
-
-so_pillar_disabled_noop:
-  test.nop
-
-{% endif %}
-
-{% else %}
-
-{{sls}}_state_not_allowed:
-  test.fail_without_changes:
-    - name: {{sls}}_state_not_allowed
-
-{% endif %}

salt/postgres/telegraf_users.sls

@@ -18,38 +18,22 @@ include:
 {% set TG_OUT = TELEGRAFMERGED.output | upper %}
 {% if TG_OUT in ['POSTGRES', 'BOTH'] %}
 
-# docker_container.running returns as soon as the container starts, but on
-# first-init docker-entrypoint.sh starts a temporary postgres with
-# `listen_addresses=''` to run /docker-entrypoint-initdb.d scripts, then
-# shuts it down before exec'ing the real CMD. A default pg_isready check
-# (Unix socket) passes during that ephemeral phase and races the shutdown
-# with "the database system is shutting down". Checking TCP readiness on
-# 127.0.0.1 only succeeds after the final postgres binds the port.
 postgres_wait_ready:
   cmd.run:
-    - name: |
-        for i in $(seq 1 60); do
-          if docker exec so-postgres pg_isready -h 127.0.0.1 -U postgres -q 2>/dev/null; then
-            exit 0
-          fi
-          sleep 2
-        done
-        echo "so-postgres did not accept TCP connections within 120s" >&2
-        exit 1
+    - name: /usr/sbin/so-postgres-wait
     - require:
       - docker_container: so-postgres
+      - file: postgres_sbin
 
-# Ensure the shared Telegraf database exists. init-users.sh only runs on a
+# Ensure the shared Telegraf database exists. init-db.sh only runs on a
 # fresh data dir, so hosts upgraded onto an existing /nsm/postgres volume
 # would otherwise never get so_telegraf.
 postgres_create_telegraf_db:
   cmd.run:
-    - name: |
-        if ! docker exec so-postgres psql -U postgres -tAc "SELECT 1 FROM pg_database WHERE datname='so_telegraf'" | grep -q 1; then
-          docker exec so-postgres psql -v ON_ERROR_STOP=1 -U postgres -c "CREATE DATABASE so_telegraf"
-        fi
+    - name: /usr/sbin/so-telegraf-postgres create_db
     - require:
       - cmd: postgres_wait_ready
+      - file: postgres_sbin
 
 # Provision the shared group role and schema once. Every per-minion role is a
 # member of so_telegraf, and each Telegraf connection does SET ROLE so_telegraf
@@ -57,68 +41,26 @@ postgres_create_telegraf_db:
 # on first write are owned by the group role and every member can INSERT/SELECT.
 postgres_telegraf_group_role:
   cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
-        DO $$
-        BEGIN
-            IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'so_telegraf') THEN
-                CREATE ROLE so_telegraf NOLOGIN;
-            END IF;
-        END
-        $$;
-        GRANT CONNECT ON DATABASE so_telegraf TO so_telegraf;
-        CREATE SCHEMA IF NOT EXISTS telegraf AUTHORIZATION so_telegraf;
-        GRANT USAGE, CREATE ON SCHEMA telegraf TO so_telegraf;
-        CREATE SCHEMA IF NOT EXISTS partman;
-        CREATE EXTENSION IF NOT EXISTS pg_partman SCHEMA partman;
-        CREATE EXTENSION IF NOT EXISTS pg_cron;
-        -- Telegraf (running as so_telegraf) calls partman.create_parent()
-        -- on first write of each metric, which needs USAGE on the partman
-        -- schema, EXECUTE on its functions/procedures, and write access to
-        -- partman.part_config so it can register new partitioned parents.
-        GRANT USAGE, CREATE ON SCHEMA partman TO so_telegraf;
-        GRANT SELECT, INSERT, UPDATE, DELETE ON ALL TABLES IN SCHEMA partman TO so_telegraf;
-        GRANT EXECUTE ON ALL FUNCTIONS IN SCHEMA partman TO so_telegraf;
-        GRANT EXECUTE ON ALL PROCEDURES IN SCHEMA partman TO so_telegraf;
-        -- partman creates per-parent template tables (partman.template_*) at
-        -- runtime; default privileges extend DML/sequence access to them.
-        ALTER DEFAULT PRIVILEGES IN SCHEMA partman
-            GRANT SELECT, INSERT, UPDATE, DELETE ON TABLES TO so_telegraf;
-        ALTER DEFAULT PRIVILEGES IN SCHEMA partman
-            GRANT USAGE, SELECT, UPDATE ON SEQUENCES TO so_telegraf;
-        -- Hourly partman maintenance. cron.schedule is idempotent by jobname.
-        SELECT cron.schedule(
-          'telegraf-partman-maintenance',
-          '17 * * * *',
-          'CALL partman.run_maintenance_proc()'
-        );
-        EOSQL
+    - name: /usr/sbin/so-telegraf-postgres group_role
     - require:
       - cmd: postgres_create_telegraf_db
+      - file: postgres_sbin
 
 {%   set creds = salt['pillar.get']('telegraf:postgres_creds', {}) %}
 {%   for mid, entry in creds.items() %}
 {%     if entry.get('user') and entry.get('pass') %}
 {%       set u = entry.user %}
-{%       set p = entry.pass | replace("'", "''") %}
+{%       set p = entry.pass %}
 
 postgres_telegraf_role_{{ u }}:
   cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
-        DO $$
-        BEGIN
-            IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '{{ u }}') THEN
-                EXECUTE format('CREATE ROLE %I WITH LOGIN PASSWORD %L', '{{ u }}', '{{ p }}');
-            ELSE
-                EXECUTE format('ALTER ROLE %I WITH PASSWORD %L', '{{ u }}', '{{ p }}');
-            END IF;
-        END
-        $$;
-        GRANT CONNECT ON DATABASE so_telegraf TO "{{ u }}";
-        GRANT so_telegraf TO "{{ u }}";
-        EOSQL
+    - name: /usr/sbin/so-telegraf-postgres user
+    - env:
+      - ROLE_USER: {{ u | tojson }}
+      - ROLE_PASS: {{ p | tojson }}
+    - hide_output: True
     - require:
+      - file: postgres_sbin
       - cmd: postgres_telegraf_group_role
 
 {%     endif %}
@@ -130,21 +72,12 @@ postgres_telegraf_role_{{ u }}:
 {%   set retention = salt['pillar.get']('postgres:telegraf:retention_days', 14) | int %}
 postgres_telegraf_retention_reconcile:
   cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
-        DO $$
-        BEGIN
-            IF EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_partman') THEN
-                UPDATE partman.part_config
-                SET retention = '{{ retention }} days',
-                    retention_keep_table = false
-                WHERE parent_table LIKE 'telegraf.%';
-            END IF;
-        END
-        $$;
-        EOSQL
+    - name: /usr/sbin/so-telegraf-postgres retention
+    - env:
+      - RETENTION_DAYS: {{ retention }}
     - require:
       - cmd: postgres_telegraf_group_role
+      - file: postgres_sbin
 
 {% endif %}
 

salt/postgres/tools/sbin/so-postgres-backup

@@ -7,15 +7,29 @@
 
 . /usr/sbin/so-common
 
+# Without pipefail, a pipeline's exit status is gzip's. A failed pg_dumpall would
+# otherwise be masked by a successful gzip, silently producing a valid .gz that
+# holds a truncated dump.
+set -o pipefail
+
 # Backups contain role password hashes and full chat data; keep them 0600.
 umask 0077
 
 TODAY=$(date '+%Y_%m_%d')
 BACKUPDIR=/nsm/backup
 BACKUPFILE="$BACKUPDIR/so-postgres-backup-$TODAY.sql.gz"
+TMPFILE="$BACKUPFILE.tmp"
 MAXBACKUPS=7
+LOGFILE=/opt/so/log/postgres/backup.log
 
-mkdir -p $BACKUPDIR
+log() {
+  echo "$(date '+%Y-%m-%d %H:%M:%S') $*" >> "$LOGFILE"
+}
+
+mkdir -p "$BACKUPDIR"
+
+# Remove any temp files left behind by a previously crashed run
+rm -f "$BACKUPDIR"/so-postgres-backup-*.sql.gz.tmp
 
 # Skip if already backed up today
 if [ -f "$BACKUPFILE" ]; then
@@ -27,13 +41,33 @@ if ! docker ps --format '{{.Names}}' | grep -q '^so-postgres$'; then
   exit 0
 fi
 
-# Dump all databases and roles, compress
-docker exec so-postgres pg_dumpall -U postgres | gzip > "$BACKUPFILE"
+# Always clean up the temp file on exit; the success path clears this trap
+# after the atomic rename so the finished backup is not deleted.
+trap 'rm -f "$TMPFILE"' EXIT
 
-# Retention cleanup
-NUMBACKUPS=$(find $BACKUPDIR -type f -name "so-postgres-backup*" | wc -l)
+# Dump all databases and roles, compress. Write to a temp file so the final
+# filename only ever appears for a complete, verified backup.
+if ! docker exec so-postgres pg_dumpall -U postgres | gzip > "$TMPFILE"; then
+  log "ERROR: pg_dumpall/gzip failed; backup aborted"
+  exit 1
+fi
+
+# Verify the compressed stream is intact before publishing it
+if ! gzip -t "$TMPFILE"; then
+  log "ERROR: backup failed gzip integrity check; backup aborted"
+  exit 1
+fi
+
+# Atomically publish the verified backup
+mv "$TMPFILE" "$BACKUPFILE"
+trap - EXIT
+log "OK: wrote $BACKUPFILE"
+
+# Retention cleanup (only reached after a successful backup). The glob is
+# restricted to finished backups so an in-progress .tmp can never be counted.
+NUMBACKUPS=$(find "$BACKUPDIR" -type f -name "so-postgres-backup-*.sql.gz" | wc -l)
 while [ "$NUMBACKUPS" -gt "$MAXBACKUPS" ]; do
-  OLDEST=$(find $BACKUPDIR -type f -name "so-postgres-backup*" -printf '%T+ %p\n' | sort | head -n 1 | awk -F" " '{print $2}')
+  OLDEST=$(find "$BACKUPDIR" -type f -name "so-postgres-backup-*.sql.gz" -printf '%T+ %p\n' | sort | head -n 1 | awk -F" " '{print $2}')
   rm -f "$OLDEST"
-  NUMBACKUPS=$(find $BACKUPDIR -type f -name "so-postgres-backup*" | wc -l)
+  NUMBACKUPS=$(find "$BACKUPDIR" -type f -name "so-postgres-backup-*.sql.gz" | wc -l)
 done

salt/postgres/tools/sbin/so-postgres-wait

@@ -0,0 +1,32 @@
+#!/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.
+
+# Wait for the so-postgres container to accept TCP connections.
+#
+# docker_container.running returns as soon as the container starts, but on
+# first-init docker-entrypoint.sh starts a temporary postgres with
+# `listen_addresses=''` to run /docker-entrypoint-initdb.d scripts, then
+# shuts it down before exec'ing the real CMD. A default pg_isready check
+# (Unix socket) passes during that ephemeral phase and races the shutdown
+# with "the database system is shutting down". Checking TCP readiness on
+# 127.0.0.1 only succeeds after the final postgres binds the port.
+#
+# Usage: so-postgres-wait [iterations] [sleep_seconds]
+# Default: 60 iterations, 2s sleep (~120s total).
+
+ITERATIONS=${1:-60}
+SLEEP_SECONDS=${2:-2}
+
+for i in $(seq 1 "$ITERATIONS"); do
+  if docker exec so-postgres pg_isready -h 127.0.0.1 -U postgres -q 2>/dev/null; then
+    exit 0
+  fi
+  sleep "$SLEEP_SECONDS"
+done
+
+echo "so-postgres did not accept TCP connections within $((ITERATIONS * SLEEP_SECONDS))s" >&2
+exit 1

salt/postgres/tools/sbin/so-telegraf-postgres

@@ -0,0 +1,110 @@
+#!/bin/bash
+set -e
+
+# Provision Telegraf state inside the so-postgres container.
+# Usage: so-telegraf-postgres <subcommand>
+#   create_db    Ensure the so_telegraf database exists.
+#   group_role   Provision the so_telegraf group role, telegraf/partman schemas,
+#                pg_partman, pg_cron, and the hourly partman maintenance job.
+#   user         Create or update a per-minion login role granted to so_telegraf.
+#                Env: ROLE_USER, ROLE_PASS.
+#   retention    Reconcile partman retention on telegraf parents.
+#                Env: RETENTION_DAYS.
+
+cmd="${1:?subcommand required}"
+
+case "$cmd" in
+  create_db)
+    if ! docker exec so-postgres psql -U postgres -tAc \
+        "SELECT 1 FROM pg_database WHERE datname='so_telegraf'" | grep -q 1; then
+      docker exec so-postgres psql -v ON_ERROR_STOP=1 -U postgres \
+        -c "CREATE DATABASE so_telegraf"
+    fi
+    ;;
+
+  group_role)
+    docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
+DO $$
+BEGIN
+    IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'so_telegraf') THEN
+        CREATE ROLE so_telegraf NOLOGIN;
+    END IF;
+END
+$$;
+GRANT CONNECT ON DATABASE so_telegraf TO so_telegraf;
+CREATE SCHEMA IF NOT EXISTS telegraf AUTHORIZATION so_telegraf;
+GRANT USAGE, CREATE ON SCHEMA telegraf TO so_telegraf;
+CREATE SCHEMA IF NOT EXISTS partman;
+CREATE EXTENSION IF NOT EXISTS pg_partman SCHEMA partman;
+CREATE EXTENSION IF NOT EXISTS pg_cron;
+-- Telegraf (running as so_telegraf) calls partman.create_parent()
+-- on first write of each metric, which needs USAGE on the partman
+-- schema, EXECUTE on its functions/procedures, and write access to
+-- partman.part_config so it can register new partitioned parents.
+GRANT USAGE, CREATE ON SCHEMA partman TO so_telegraf;
+GRANT SELECT, INSERT, UPDATE, DELETE ON ALL TABLES IN SCHEMA partman TO so_telegraf;
+GRANT EXECUTE ON ALL FUNCTIONS IN SCHEMA partman TO so_telegraf;
+GRANT EXECUTE ON ALL PROCEDURES IN SCHEMA partman TO so_telegraf;
+-- partman creates per-parent template tables (partman.template_*) at
+-- runtime; default privileges extend DML/sequence access to them.
+ALTER DEFAULT PRIVILEGES IN SCHEMA partman
+    GRANT SELECT, INSERT, UPDATE, DELETE ON TABLES TO so_telegraf;
+ALTER DEFAULT PRIVILEGES IN SCHEMA partman
+    GRANT USAGE, SELECT, UPDATE ON SEQUENCES TO so_telegraf;
+-- Hourly partman maintenance. cron.schedule is idempotent by jobname.
+SELECT cron.schedule(
+  'telegraf-partman-maintenance',
+  '17 * * * *',
+  'CALL partman.run_maintenance_proc()'
+);
+EOSQL
+    ;;
+
+  user)
+    : "${ROLE_USER:?ROLE_USER is required}"
+    : "${ROLE_PASS:?ROLE_PASS is required}"
+    # psql does not substitute :vars inside dollar-quoted strings, so the
+    # conditional CREATE/ALTER is built outside any DO block and dispatched
+    # with \gexec. format() handles identifier/literal quoting.
+    docker exec -i so-postgres psql \
+      -v ON_ERROR_STOP=1 \
+      -v role_user="$ROLE_USER" \
+      -v role_pass="$ROLE_PASS" \
+      -U postgres -d so_telegraf <<'EOSQL'
+SELECT format(
+  CASE WHEN EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = :'role_user')
+       THEN 'ALTER ROLE %I WITH LOGIN PASSWORD %L'
+       ELSE 'CREATE ROLE %I WITH LOGIN PASSWORD %L'
+  END,
+  :'role_user',
+  :'role_pass'
+) \gexec
+GRANT CONNECT ON DATABASE so_telegraf TO :"role_user";
+GRANT so_telegraf TO :"role_user";
+EOSQL
+    ;;
+
+  retention)
+    : "${RETENTION_DAYS:?RETENTION_DAYS is required}"
+    # \gset + \if guards against a missing pg_partman without using a DO
+    # block (psql :var substitution doesn't reach into dollar-quoted code).
+    docker exec -i so-postgres psql \
+      -v ON_ERROR_STOP=1 \
+      -v retention_days="$RETENTION_DAYS" \
+      -U postgres -d so_telegraf <<'EOSQL'
+SELECT CASE WHEN EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_partman')
+            THEN 'true' ELSE 'false' END AS has_partman \gset
+\if :has_partman
+UPDATE partman.part_config
+SET retention = :'retention_days' || ' days',
+    retention_keep_table = false
+WHERE parent_table LIKE 'telegraf.%';
+\endif
+EOSQL
+    ;;
+
+  *)
+    echo "Unknown subcommand: $cmd" >&2
+    exit 1
+    ;;
+esac

salt/reactor/check_hypervisor.sls

@@ -3,12 +3,15 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-{% if data['id'].endswith('_hypervisor') and data['result'] == True %}
+{% set hid = data['id'] %}
+{% if hid|regex_match('^([A-Za-z0-9._-]{1,253})$')
+   and hid.endswith('_hypervisor')
+   and data['result'] == True %}
 
 {%   if data['act'] == 'accept' %}
 check_and_trigger:
   runner.setup_hypervisor.setup_environment:
-    - minion_id: {{ data['id'] }}
+    - minion_id: {{ hid }}
 {%   endif %}
 
 {%   if data['act'] == 'delete' %}
@@ -17,8 +20,7 @@ delete_hypervisor:
     - args:
       - mods: orch.delete_hypervisor
       - pillar:
-          minion_id: {{ data['id'] }}
+          minion_id: {{ hid }}
 {%   endif %}
 
 {% endif %}
-

salt/reactor/createEmptyPillar.sls

@@ -1,7 +1,7 @@
 #!py
 
 # 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 
+# 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.
 
@@ -9,30 +9,42 @@ import logging
 import os
 import pwd
 import grp
+import re
+
+log = logging.getLogger(__name__)
+
+PILLAR_ROOT = '/opt/so/saltstack/local/pillar/minions/'
+_VMNAME_RE = re.compile(r'^[A-Za-z0-9._-]{1,253}$')
+
 
 def run():
-  vm_name = data['kwargs']['name']
-  logging.error("createEmptyPillar reactor: vm_name: %s" % vm_name)
-  pillar_root = '/opt/so/saltstack/local/pillar/minions/'
+  vm_name = data.get('kwargs', {}).get('name', '')
+  if not _VMNAME_RE.match(str(vm_name)):
+    log.error("createEmptyPillar reactor: refusing unsafe vm_name=%r", vm_name)
+    return {}
+
+  log.info("createEmptyPillar reactor: vm_name: %s", vm_name)
   pillar_files = ['adv_' + vm_name + '.sls', vm_name + '.sls']
 
   try:
-    # Get socore user and group IDs
     socore_uid = pwd.getpwnam('socore').pw_uid
     socore_gid = grp.getgrnam('socore').gr_gid
+    pillar_root_real = os.path.realpath(PILLAR_ROOT)
 
     for f in pillar_files:
-      full_path = pillar_root + f
-      if not os.path.exists(full_path):
-        # Create empty file
-        os.mknod(full_path)
-        # Set ownership to socore:socore
-        os.chown(full_path, socore_uid, socore_gid)
-        # Set mode to 644 (rw-r--r--)
-        os.chmod(full_path, 0o640)
-        logging.error("createEmptyPillar reactor: created %s with socore:socore ownership and mode 644" % f)
+      full_path = os.path.join(PILLAR_ROOT, f)
+      resolved = os.path.realpath(full_path)
+      if os.path.dirname(resolved) != pillar_root_real:
+        log.error("createEmptyPillar reactor: refusing path outside pillar root: %s", resolved)
+        continue
+      if os.path.exists(resolved):
+        continue
+      os.mknod(resolved)
+      os.chown(resolved, socore_uid, socore_gid)
+      os.chmod(resolved, 0o640)
+      log.info("createEmptyPillar reactor: created %s with socore:socore ownership and mode 0640", f)
 
   except (KeyError, OSError) as e:
-    logging.error("createEmptyPillar reactor: Error setting ownership/permissions: %s" % str(e))
+    log.error("createEmptyPillar reactor: Error setting ownership/permissions: %s", e)
 
   return {}

salt/reactor/deleteKey.sls

@@ -1,18 +1,40 @@
+#!py
+
 # 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.
 
-remove_key:
-  wheel.key.delete:
-    - args:
-      - match: {{ data['name'] }}
+import logging
+import re
 
-{{ data['name'] }}_pillar_clean:
-  runner.state.orchestrate:
-    - args:
-      - mods: orch.vm_pillar_clean
-      - pillar:
-          vm_name: {{ data['name'] }}
+log = logging.getLogger(__name__)
 
-{% do salt.log.info('deleteKey reactor: deleted minion key: %s' % data['name']) %}
+_VMNAME_RE = re.compile(r'^[A-Za-z0-9._-]{1,253}$')
+
+
+def run():
+  name = data.get('name', '')
+  if not _VMNAME_RE.match(str(name)):
+    log.error("deleteKey reactor: refusing unsafe name=%r", name)
+    return {}
+
+  log.info("deleteKey reactor: deleted minion key: %s", name)
+
+  return {
+    'remove_key': {
+      'wheel.key.delete': [
+        {'args': [
+          {'match': name},
+        ]},
+      ],
+    },
+    '%s_pillar_clean' % name: {
+      'runner.state.orchestrate': [
+        {'args': [
+          {'mods': 'orch.vm_pillar_clean'},
+          {'pillar': {'vm_name': name}},
+        ]},
+      ],
+    },
+  }

salt/reactor/so_pillar_changed.sls

@@ -1,27 +0,0 @@
-# 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.
-
-# Fires for every event tagged 'so/pillar/changed'. Source of those events
-# is the pg_notify_pillar engine on the salt-master, which in turn drains
-# so_pillar.change_queue (populated by the AFTER trigger on
-# so_pillar.pillar_entry — see 008_change_notify.sql).
-#
-# All routing logic — which pillar paths reload which services on which
-# targets — lives in orch.so_pillar_reload so it stays editable as one
-# YAML table without touching reactor wiring.
-
-{% set payload = data.get('data', {}) %}
-{% do salt.log.info('so_pillar_changed reactor: %s' % payload) %}
-
-so_pillar_dispatch_reload:
-  runner.state.orchestrate:
-    - args:
-      - mods: orch.so_pillar_reload
-      - pillar:
-          so_pillar_change:
-            scope: {{ payload.get('scope') | json }}
-            role_name: {{ payload.get('role_name') | json }}
-            minion_id: {{ payload.get('minion_id') | json }}
-            changes: {{ payload.get('changes', []) | json }}

salt/registry/enabled.sls

@@ -16,7 +16,7 @@ include:
 # Install the registry container
 so-dockerregistry:
   docker_container.running:
-    - image: ghcr.io/security-onion-solutions/registry:3.0.0
+    - image: ghcr.io/security-onion-solutions/registry:3.1.1
     - hostname: so-registry
     - networks:
       - sobridge:

salt/repo/client/oracle.sls

@@ -6,6 +6,10 @@
 {% from 'repo/client/map.jinja' import REPOPATH with context %}
 {% from 'vars/globals.map.jinja' import GLOBALS %}
 
+{% import_yaml 'salt/minion.defaults.yaml' as saltversion %}
+{% set saltversion = saltversion.salt.minion.version %}
+{% set INSTALLEDSALTVERSION = grains.saltversion %}
+
 {% set role = grains.id.split('_') | last %}
 {% set MANAGER = salt['grains.get']('master') %}
 {% if grains['os'] == 'OEL' %}
@@ -57,6 +61,32 @@ so_repo:
     - enabled: 1
     - gpgcheck: 1
 
+# Only assign the kernel repo once this node's running salt matches the version this
+# SO release ships. During a soup the grid is mid-salt-upgrade; gating here keeps the
+# UEK8 kernel repo (and the kernel update it enables) from activating until the node is
+# fully on the target salt, the same way other states defer across the upgrade window.
+{% if saltversion | string == INSTALLEDSALTVERSION | string %}
+so_kernel_repo:
+  pkgrepo.managed:
+    - name: securityonionkernel
+    - humanname: Security Onion Kernel Repo
+  {% if GLOBALS.is_manager %}
+    - baseurl: file:///nsm/kernelrepo/
+  {% else %}
+    - baseurl: https://{{ GLOBALS.repo_host }}/kernelrepo
+  {% endif %}
+    - enabled: 1
+    - gpgcheck: 1
+    # Supplementary kernel repo: tolerate it being empty/unreachable (e.g. before the
+    # manager has populated /nsm/kernelrepo) so a missing repomd.xml can't make every
+    # dnf/pkg operation on the grid fail.
+    - skip_if_unavailable: 1
+    # Only assign the kernel repo once physical NIC names are pinned by MAC, so the
+    # UEK8 kernel update can't renumber interfaces SO binds by name (see pin_nic_names
+    # in salt/common/init.sls, which drops this marker via /usr/sbin/so-nic-pin).
+    - onlyif: 'test -e /opt/so/state/nic_names_pinned'
+{% endif %}
+
 {% endif %}
   
 # TODO: Add a pillar entry for custom repos

salt/salt/engines/master/pg_notify_pillar.py

@@ -1,200 +0,0 @@
-# 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.
-
-# -*- coding: utf-8 -*-
-
-"""
-pg_notify_pillar — Salt master engine that bridges so_pillar.change_queue
-into the Salt event bus.
-
-Architecture (see 008_change_notify.sql):
-  pillar_entry  -- AFTER trigger -->  change_queue (durable)
-                                       + pg_notify('so_pillar_change') (wakeup)
-                                                                |
-                                       LISTEN <-- this engine <-+
-                                       SELECT/UPDATE change_queue
-                                                                |
-                                       fire_event('so/pillar/changed', ...)
-                                                                |
-                                       reactor matches tag --> orch
-
-Why a queue + notify rather than just notify: pg_notify is fire-and-forget
-within a session. If the engine is down or the LISTEN connection is broken
-when a write happens, the notification is lost forever. The change_queue
-lets us recover — on (re)connect, we drain everything still flagged
-processed_at IS NULL.
-
-Debounce: bulk operations (so-pillar-import, fresh installs) can fire
-hundreds of notifications per second. The engine collects whatever lands in
-a short window and emits one event per (scope, role, minion) tuple so the
-reactor isn't stampeded.
-"""
-
-import json
-import logging
-import os
-import select
-import time
-
-import salt.utils.event
-
-log = logging.getLogger(__name__)
-
-__virtualname__ = 'pg_notify_pillar'
-
-DEFAULT_CHANNEL = 'so_pillar_change'
-DEFAULT_DEBOUNCE_MS = 500
-DEFAULT_RECONNECT_BACKOFF = 5
-DEFAULT_BACKLOG_INTERVAL = 30
-DEFAULT_BATCH_LIMIT = 500
-
-EVENT_TAG = 'so/pillar/changed'
-
-
-def __virtual__():
-    try:
-        import psycopg2  # noqa: F401
-        return __virtualname__
-    except ImportError:
-        return False, 'pg_notify_pillar engine requires psycopg2'
-
-
-def start(dsn=None,
-          host='127.0.0.1',
-          port=5432,
-          dbname='securityonion',
-          user='so_pillar_master',
-          password=None,
-          channel=DEFAULT_CHANNEL,
-          debounce_ms=DEFAULT_DEBOUNCE_MS,
-          reconnect_backoff=DEFAULT_RECONNECT_BACKOFF,
-          backlog_interval=DEFAULT_BACKLOG_INTERVAL,
-          batch_limit=DEFAULT_BATCH_LIMIT,
-          password_file=None):
-    """
-    Run the change-queue bridge until the master shuts the engine down.
-
-    Either pass a full ``dsn`` string, or supply discrete kwargs. The
-    password may also be read from ``password_file`` (mode 0400) so the
-    engine config in ``/etc/salt/master.d/`` doesn't have to embed it
-    inline — only the file path.
-    """
-    import psycopg2
-    import psycopg2.extensions
-
-    if dsn is None:
-        if password is None and password_file:
-            try:
-                with open(password_file, 'r') as fh:
-                    password = fh.read().strip()
-            except (IOError, OSError) as exc:
-                log.error('pg_notify_pillar: cannot read password_file %s: %s',
-                          password_file, exc)
-                return
-        dsn = _build_dsn(host=host, port=port, dbname=dbname,
-                         user=user, password=password)
-
-    bus = salt.utils.event.get_master_event(
-        __opts__, __opts__['sock_dir'], listen=False)
-
-    log.info('pg_notify_pillar: starting (channel=%s debounce=%dms)',
-             channel, debounce_ms)
-
-    while True:
-        conn = None
-        try:
-            conn = psycopg2.connect(dsn)
-            conn.set_isolation_level(
-                psycopg2.extensions.ISOLATION_LEVEL_AUTOCOMMIT)
-            cur = conn.cursor()
-            cur.execute('LISTEN {0}'.format(channel))
-            log.info('pg_notify_pillar: connected; LISTEN %s', channel)
-
-            _drain(cur, bus, batch_limit)
-
-            while True:
-                ready, _, _ = select.select([conn], [], [], backlog_interval)
-                if not ready:
-                    _drain(cur, bus, batch_limit)
-                    continue
-
-                conn.poll()
-                _consume_notifies(conn)
-
-                if debounce_ms > 0:
-                    time.sleep(debounce_ms / 1000.0)
-                    conn.poll()
-                    _consume_notifies(conn)
-
-                _drain(cur, bus, batch_limit)
-
-        except Exception as exc:  # psycopg2.Error subclasses + OS errors
-            log.error('pg_notify_pillar: %s; reconnecting in %ds',
-                      exc, reconnect_backoff)
-        finally:
-            if conn is not None:
-                try:
-                    conn.close()
-                except Exception:
-                    pass
-        time.sleep(reconnect_backoff)
-
-
-def _build_dsn(host, port, dbname, user, password):
-    parts = ['host={0}'.format(host),
-             'port={0}'.format(port),
-             'dbname={0}'.format(dbname),
-             'user={0}'.format(user)]
-    if password:
-        parts.append('password={0}'.format(password))
-    return ' '.join(parts)
-
-
-def _consume_notifies(conn):
-    # We don't use the payload directly — the queue table is the source of
-    # truth, and draining it covers any notifications we missed. So just
-    # discard them; their presence already proved there's something to drain.
-    while conn.notifies:
-        conn.notifies.pop(0)
-
-
-def _drain(cur, bus, batch_limit):
-    """Mark unprocessed change_queue rows processed and emit one event per
-    (scope, role_name, minion_id) group. SKIP LOCKED so multiple masters
-    sharing a Postgres don't double-process."""
-    cur.execute("""
-        UPDATE so_pillar.change_queue
-           SET processed_at = now()
-         WHERE id IN (
-             SELECT id FROM so_pillar.change_queue
-              WHERE processed_at IS NULL
-              ORDER BY id
-              FOR UPDATE SKIP LOCKED
-              LIMIT %s)
-        RETURNING id, scope, role_name, minion_id, pillar_path, op
-    """, (batch_limit,))
-    rows = cur.fetchall()
-    if not rows:
-        return
-
-    groups = {}
-    for row_id, scope, role_name, minion_id, pillar_path, op in rows:
-        key = (scope, role_name, minion_id)
-        groups.setdefault(key, []).append({
-            'queue_id':    row_id,
-            'pillar_path': pillar_path,
-            'op':          op,
-        })
-
-    for (scope, role_name, minion_id), changes in groups.items():
-        payload = {
-            'scope':     scope,
-            'role_name': role_name,
-            'minion_id': minion_id,
-            'changes':   changes,
-        }
-        log.debug('pg_notify_pillar: firing %s for %s',
-                  EVENT_TAG, payload)
-        bus.fire_event(payload, EVENT_TAG)

salt/salt/files/engines.conf

@@ -1,27 +1,7 @@
 engines_dirs:
   - /etc/salt/engines
 
-# All salt-master engines must be declared in this single file.
-# Salt's master.d/*.conf merge replaces top-level lists rather than
-# concatenating them, so a sibling .conf with its own `engines:` list
-# would silently overwrite this one (only the last loaded file's list
-# would survive). Anything new — including postsalt's pg_notify_pillar
-# engine, gated on postgres:so_pillar:enabled below — gets appended
-# here under the same `engines:` key.
 engines:
-{% if salt['pillar.get']('postgres:so_pillar:enabled', False) %}
-  - pg_notify_pillar:
-      host: {{ pillar.get('postgres', {}).get('host', '127.0.0.1') }}
-      port: {{ pillar.get('postgres', {}).get('port', 5432) }}
-      dbname: securityonion
-      user: so_pillar_master
-      password: {{ pillar['secrets']['pillar_master_pass'] }}
-      channel: so_pillar_change
-      debounce_ms: {{ pillar.get('postgres', {}).get('so_pillar', {}).get('engine_debounce_ms', 500) }}
-      reconnect_backoff: {{ pillar.get('postgres', {}).get('so_pillar', {}).get('engine_reconnect_backoff', 5) }}
-      backlog_interval: {{ pillar.get('postgres', {}).get('so_pillar', {}).get('engine_backlog_interval', 30) }}
-      batch_limit: {{ pillar.get('postgres', {}).get('so_pillar', {}).get('engine_batch_limit', 500) }}
-{% endif %}
   - checkmine:
       interval: 60
   - pillarWatch:

salt/salt/master.sls

@@ -14,8 +14,7 @@
 
 include:
   - salt.minion
-  - salt.master.ext_pillar_postgres
-  - salt.master.pg_notify_pillar_engine
+  - salt.master.boot_mine_update
 {%   if 'vrt' in salt['pillar.get']('features', []) %}
   - salt.cloud
   - salt.cloud.reactor_config_hypervisor
@@ -63,7 +62,6 @@ engines_config:
   file.managed:
     - name: /etc/salt/master.d/engines.conf
     - source: salt://salt/files/engines.conf
-    - template: jinja
 
 # update the bootstrap script when used for salt-cloud
 salt_bootstrap_cloud:

salt/salt/master/boot_mine_update.sls

@@ -0,0 +1,29 @@
+# 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.
+
+# Manages /etc/systemd/system/so-boot-mine-update.service, a manager-only
+# Type=oneshot unit that pushes `salt '*' mine.update` once per boot, ordered
+# before so-boot-highstate.service so mine-backed pillars (node IPs, ES/Redis/
+# Logstash discovery) are fresh before the boot highstate renders them.
+
+include:
+  - systemd.reload
+
+so_boot_mine_update_unit_file:
+  file.managed:
+    - name: /etc/systemd/system/so-boot-mine-update.service
+    - source: salt://salt/service/so-boot-mine-update.service
+    - onchanges_in:
+      - module: systemd_reload
+
+# Only enable once setup is complete. Until then the gate file is missing and
+# the unit's own ConditionPathExists would no-op it anyway.
+so_boot_mine_update_service:
+  service.enabled:
+    - name: so-boot-mine-update.service
+    - onlyif: test -e /opt/so/state/setup-complete
+    - require:
+      - file: so_boot_mine_update_unit_file
+      - module: systemd_reload

salt/salt/master/ext_pillar_postgres.sls

@@ -1,46 +0,0 @@
-# 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.
-
-# Drops /etc/salt/master.d/ext_pillar_postgres.conf so the salt-master loads
-# pillar overlays from the so_pillar.* schema in so-postgres alongside the
-# on-disk SLS pillar tree. Gated on the postgres:so_pillar:enabled feature
-# flag (default false) so the file only appears once the schema is deployed
-# and the importer has run at least once.
-
-{% from 'allowed_states.map.jinja' import allowed_states %}
-{% if 'salt.master' in allowed_states %}
-
-{% if salt['pillar.get']('postgres:so_pillar:enabled', False) %}
-
-ext_pillar_postgres_config:
-  file.managed:
-    - name: /etc/salt/master.d/ext_pillar_postgres.conf
-    - source: salt://salt/master/files/ext_pillar_postgres.conf.jinja
-    - template: jinja
-    - mode: '0640'
-    - user: root
-    - group: salt
-    - watch_in:
-      - service: salt_master_service
-
-{% else %}
-
-# When the flag is off make sure any previously-deployed config is removed
-# so a rollback flips behavior cleanly.
-ext_pillar_postgres_config_absent:
-  file.absent:
-    - name: /etc/salt/master.d/ext_pillar_postgres.conf
-    - watch_in:
-      - service: salt_master_service
-
-{% endif %}
-
-{% else %}
-
-{{sls}}_state_not_allowed:
-  test.fail_without_changes:
-    - name: {{sls}}_state_not_allowed
-
-{% endif %}

salt/salt/master/files/ext_pillar_postgres.conf.jinja

@@ -1,38 +0,0 @@
-# /etc/salt/master.d/ext_pillar_postgres.conf
-# Rendered by salt/salt/master/ext_pillar_postgres.sls.
-# Reads the so_pillar.* schema in so-postgres and overlays it onto SLS pillar.
-# SLS still renders first (ext_pillar_first: False) so bootstrap and mine-driven
-# pillars work before Postgres is reachable; PG values overlay/override on top.
-
-postgres:
-  host: {{ pillar.get('postgres', {}).get('host', '127.0.0.1') }}
-  port: {{ pillar.get('postgres', {}).get('port', 5432) }}
-  db: securityonion
-  user: so_pillar_master
-  pass: {{ pillar['secrets']['pillar_master_pass'] }}
-
-ext_pillar_first: False
-pillar_source_merging_strategy: smart
-pillar_merge_lists: False
-
-pillar_cache: True
-pillar_cache_backend: disk
-pillar_cache_ttl: {{ pillar.get('postgres', {}).get('so_pillar', {}).get('pillar_cache_ttl', 60) }}
-
-# List form (not mapping form) so result rows merge into the pillar root rather
-# than under a named subtree. Verified against salt/pillar/sql_base.py: list
-# entries pass root=None to enter_root() which sets self.focus = self.result.
-ext_pillar:
-  - postgres:
-      - query: "SELECT data FROM so_pillar.v_pillar_global WHERE %s IS NOT NULL ORDER BY sort_key, pillar_path"
-        as_json: True
-        ignore_null: True
-      - query: "SELECT data FROM so_pillar.v_pillar_role WHERE minion_id = %s ORDER BY sort_key, pillar_path"
-        as_json: True
-        ignore_null: True
-      - query: "SELECT data FROM so_pillar.v_pillar_minion WHERE minion_id = %s ORDER BY sort_key, pillar_path"
-        as_json: True
-        ignore_null: True
-      - query: "SELECT data FROM so_pillar.fn_pillar_secrets(%s)"
-        as_json: True
-        ignore_null: True