oracle 10 testing

.github/DISCUSSION_TEMPLATE/3-0.yml

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

HOTFIX

@@ -1 +1 @@
-
+20260528

VERSION

@@ -1 +1 @@
-3.2.0
+3.1.0

pillar/data/addtotab.sh

@@ -0,0 +1,59 @@
+#!/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

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

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

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

salt/common/init.sls

@@ -130,17 +130,6 @@ 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/packages.sls

@@ -26,14 +26,33 @@ commonpkgs:
       - net-tools
       - nmap-ncat
       - procps-ng
+{# OL10 test path: python3-docker / python3-m2crypto are not packaged in EPEL 10 and are not
+   referenced by SO code (salt uses its bundled docker module from salt/python_modules.sls).
+   python3-rich is also unavailable on EL10 (its pygments dep is not packaged), so it is
+   installed via pip below. Gate on the grain because GLOBALS/pillars are not available this
+   early (see header note). #}
+{% if grains['osmajorrelease']|int < 10 %}
       - python3-docker
       - python3-m2crypto
+      - python3-rich
+{% else %}
+      - python3-pip
+{% endif %}
       - python3-packaging
       - python3-pyyaml
-      - python3-rich
       - rsync
       - sqlite
       - tcpdump
       - unzip
       - wget
       - yum-utils
+
+{% if grains['osmajorrelease']|int >= 10 %}
+# OL10 test path: rich is not packaged for EL10; install it into the system python3 for so-status.
+commonpkgs_pip_rich:
+  cmd.run:
+    - name: python3 -m pip install rich
+    - unless: python3 -c "import rich"
+    - require:
+      - pkg: commonpkgs
+{% endif %}

salt/common/tools/sbin/so-common

@@ -142,11 +142,6 @@ 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}"
@@ -291,20 +286,6 @@ 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
@@ -373,7 +354,12 @@ gpg_rpm_import() {
 	else
 		local RPMKEYSLOC="$UPDATE_DIR/salt/repo/client/files/$OS/keys"
 	fi
-	RPMKEYS=('RPM-GPG-KEY-oracle' 'RPM-GPG-KEY-EPEL-9' 'SALT-PROJECT-GPG-PUBKEY-2023.pub' 'docker.pub' 'securityonion.pub')
+	if [[ "$OSVER" == "10" ]]; then
+		# OL10 test path uses public repos; the public oracle-epel-release and docker repos provide their own keys
+		RPMKEYS=('RPM-GPG-KEY-oracle' 'SALT-PROJECT-GPG-PUBKEY-2023.pub')
+	else
+		RPMKEYS=('RPM-GPG-KEY-oracle' 'RPM-GPG-KEY-EPEL-9' 'SALT-PROJECT-GPG-PUBKEY-2023.pub' 'docker.pub' 'securityonion.pub')
+	fi
 	for RPMKEY in "${RPMKEYS[@]}"; do
 		rpm --import $RPMKEYSLOC/$RPMKEY
 		echo "Imported $RPMKEY"
@@ -645,9 +631,9 @@ salt_minion_count() {
 }
 
 set_os() {
-	if [ -f /etc/redhat-release ] && grep -q "Red Hat Enterprise Linux release 9" /etc/redhat-release && [ -f /etc/oracle-release ]; then
+	if [ -f /etc/oracle-release ] && grep -qE "release (9|10)\b" /etc/oracle-release; then
 		OS=oracle
-		OSVER=9
+		OSVER=$(grep -oE "release [0-9]+" /etc/oracle-release | grep -oE "[0-9]+")
 		is_oracle=true
 		is_rpm=true
 	fi

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

@@ -112,8 +112,23 @@ update_docker_containers() {
   # does not include so-elastic-fleet since that container uses so-elastic-agent image
   local IMAGES_USING_ES_VERSION=("so-elasticsearch")
 
-  rm -rf $SIGNPATH >> "$LOG_FILE" 2>&1 
+  rm -rf $SIGNPATH >> "$LOG_FILE" 2>&1
-  mkdir -p $SIGNPATH >> "$LOG_FILE" 2>&1 
+  mkdir -p $SIGNPATH >> "$LOG_FILE" 2>&1
+
+  # OL10 test path: GnuPG 2.4 enables the keybox daemon (keyboxd) by default, which deadlocks
+  # under the rapid sequential gpg --verify calls below ("waiting for lock ... keydb_search
+  # failed: Connection timed out ... No public key"). Editing the default homedir's common.conf
+  # is unreliable (gpg re-adds use-keyboxd when it re-initializes the homedir), so run all the
+  # image-signature gpg ops in a dedicated homedir whose pre-written common.conf leaves keyboxd
+  # off, forcing the classic keybox. Isolated from the system keyring and deterministic.
+  if [ "$OSVER" = "10" ]; then
+    export GNUPGHOME="$SIGNPATH/gnupg"
+    rm -rf "$GNUPGHOME" >> "$LOG_FILE" 2>&1
+    mkdir -p "$GNUPGHOME" >> "$LOG_FILE" 2>&1
+    chmod 700 "$GNUPGHOME"
+    echo "# keyboxd disabled for SO image signature verification on EL10" > "$GNUPGHOME/common.conf"
+    gpgconf --kill keyboxd gpg-agent >> "$LOG_FILE" 2>&1 || true
+  fi
 
   # Let's make sure we have the public key
   run_check_net_err \

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

@@ -1,57 +0,0 @@
-#!/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-nic-pin

@@ -1,76 +0,0 @@
-#!/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

@@ -5,41 +5,27 @@
 # 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
 
-usage() {
+if [ $# -ge 1 ]; then
-    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
-}
 
-if [[ $# -lt 1 ]]; then
+        echo $banner
-    usage
+        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"
-fi
+        echo $banner
 
-#shellcheck disable=SC2154
+        if [ "$2" = "--force" ]; then
-echo "$banner"
+                printf "\nForce-stopping all Salt jobs before proceeding\n\n"
-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" "$1"
+                salt-call saltutil.kill_all_jobs
-echo "$banner"
+        fi
-if [[ "$2" = "--force" ]] || [[ "$2" = "-f" ]]; then
+
-    printf "\nForce-stopping all Salt jobs before proceeding\n\n"
+        case $1 in
-    salt-call saltutil.kill_all_jobs
+                "elastic-fleet") docker stop so-elastic-fleet && docker rm so-elastic-fleet && salt-call state.apply elasticfleet queue=True;;
+                *)  docker stop so-$1 ; docker rm so-$1 ; salt-call state.apply $1 queue=True;;
+        esac
+else
+        echo -e "\nPlease provide an argument by running like so-restart $component, or by using the component-specific script.\nEx. so-restart logstash, or so-logstash-restart\n"
 fi
-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

@@ -5,54 +5,27 @@
 # https://securityonion.net/license; you may not use this file except in compliance with the
 # Elastic License 2.0.
 
-# shellcheck disable=SC1091
+
+
+# Usage: so-start  all | kibana | playbook 
+
 . /usr/sbin/so-common
 
-usage() {
+if [ $# -ge 1 ]; then
-    echo "Usage: $0 <component> [args]"
+	echo $banner
-    echo ""
+	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 "Supported args:"
+	echo $banner
-    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 [[ $# -lt 1 ]]; then
+	if [ "$2" = "--force" ]; then
-    usage
+   		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 $component, or by using the component-specific script.\nEx. so-start logstash, or so-logstash-start\n"	
 fi
-
-#shellcheck disable=SC2154
-echo "$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

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

@@ -63,8 +63,7 @@ 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/docker/init.sls

@@ -18,10 +18,18 @@ dockergroup:
 dockerheldpackages:
   pkg.installed:
     - pkgs:
+{% if GLOBALS.os_version|int >= 10 %}
+      # OL10 test path: install latest Docker CE from the public repo (no .el9 builds available)
+      - containerd.io
+      - docker-ce
+      - docker-ce-cli
+      - docker-ce-rootless-extras
+{% else %}
       - containerd.io: 2.2.1-1.el9
       - docker-ce: 3:29.2.1-1.el9
       - docker-ce-cli: 1:29.2.1-1.el9
       - docker-ce-rootless-extras: 29.2.1-1.el9
+{% endif %}
     - hold: True
     - update_holds: True
 

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","import","manager", "managerhype", "managersearch","standalone" ] %}
+{% if role in [ "eval","fleet","heavynode","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

@@ -9,6 +9,7 @@
 
 {% 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

@@ -101,17 +101,6 @@ 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

@@ -9,6 +9,7 @@
 
 {% 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 %}
@@ -115,6 +116,7 @@
 
 
 {%         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

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

@@ -30,94 +30,6 @@ 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
@@ -134,9 +46,7 @@ elastic_fleet_integration_create() {
 
     JSON_STRING=$1
 
-    # --retry-all-errors so transient 409 conflicts (concurrent writes to the same agent
+    if ! fleet_api "package_policies" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
-    # policy) are retried; curl --retry alone does not retry 409.
-    if ! fleet_api "package_policies" --retry-all-errors -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPOST -d "$JSON_STRING"; then
         return 1
     fi
 }
@@ -167,9 +77,7 @@ elastic_fleet_integration_update() {
 
     JSON_STRING=$2
 
-    # --retry-all-errors so transient 409 conflicts (concurrent writes to the same agent
+    if ! fleet_api "package_policies/$UPDATE_ID" -H 'kbn-xsrf: true' -H 'Content-Type: application/json' -XPUT -d "$JSON_STRING"; then
-    # 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

@@ -9,45 +9,108 @@
 RETURN_CODE=0
 
 if [ ! -f /opt/so/state/eaintegrations.txt ]; then
+  # First, check for any package upgrades
+  /usr/sbin/so-elastic-fleet-package-upgrade
 
-  # update Fleet Server policies
+  # Second, update Fleet Server policies
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-fleet-server
 
-  # configure Elastic Defend Integration separately
+  # Third, configure Elastic Defend Integration seperately
   /usr/sbin/so-elastic-fleet-integration-policy-elastic-defend
 
-  # Each group fetches its agent policy once and dispatches create/update writes concurrently.
-
   # Initial Endpoints
-  elastic_fleet_load_integrations_dir "endpoints-initial" \
+  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/endpoints-initial/*.json; do
-    /opt/so/conf/elastic-fleet/integrations/endpoints-initial "Initial Endpoints Policy" || RETURN_CODE=1
+    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
 
   # Grid Nodes - General
-  elastic_fleet_load_integrations_dir "so-grid-nodes_general" \
+  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_general/*.json; do
-    /opt/so/conf/elastic-fleet/integrations/grid-nodes_general "Grid Nodes Policy_General" || RETURN_CODE=1
+    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
 
   # Grid Nodes - Heavy
-  elastic_fleet_load_integrations_dir "so-grid-nodes_heavy" \
+  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy/*.json; do
-    /opt/so/conf/elastic-fleet/integrations/grid-nodes_heavy "Grid Nodes Policy_Heavy" || RETURN_CODE=1
+    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
 
-  # Fleet Server - Optional integrations (adds integration configuration to a given FleetServer_ policy)
+  # Fleet Server - Optional integrations
-  for FLEET_DIR in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/; do
+  for INTEGRATION in /opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json; do
-    [ -d "$FLEET_DIR" ] || continue
+    if ! [ "$INTEGRATION" == "/opt/so/conf/elastic-fleet/integrations-optional/FleetServer*/*.json" ]; then
-    INTEGRATIONS=("${FLEET_DIR%/}"/*.json)
+      FLEET_POLICY=`echo "$INTEGRATION"| cut -d'/' -f7`
-    [ -e "${INTEGRATIONS[0]}" ] || continue
+      printf "\n\nFleet Server Policy - Loading $INTEGRATION\n"
-
+      elastic_fleet_integration_check "$FLEET_POLICY" "$INTEGRATION"
-    FLEET_POLICY=$(basename "$FLEET_DIR")
+      if [ -n "$INTEGRATION_ID" ]; then
-    elastic_fleet_load_integrations_dir "$FLEET_POLICY" \
+        printf "\n\nIntegration $NAME exists - Updating integration\n"
-      "${FLEET_DIR%/}" "Fleet Server Policy" "elasticsearch-logs" || RETURN_CODE=1
+        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
   done
 
   # Only create the state file if all policies were created/updated successfully
-  if [[ $RETURN_CODE -eq 0 ]]; then
+  if [[ "$RETURN_CODE" != "1" ]]; then
     touch /opt/so/state/eaintegrations.txt
-  else
-    exit 1
   fi
 else
-  echo "Fleet integration policies already loaded."
+  exit $RETURN_CODE
-  exit 0
 fi

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

@@ -23,90 +23,73 @@ 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 $agent_policies; do
-    # Fetch the agent policy a single time; package name/version and integration id are all
+    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
-    # extracted locally below instead of re-fetching the same policy per integration.
-    if ! POLICY_JSON=$(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 $integrations; do
-    # One jq pass emits name/package.name/package.version/id for every eligible integration.
+        if ! [[ "$INTEGRATION" == "elastic-defend-endpoints" ]] && ! [[ "$INTEGRATION" == "fleet_server-"* ]]; then
-    # The endpoint/fleet_server skips and the default-package gate are applied here in jq.
+            # Get package name so we know what package to look for when checking the current and latest available version
-    # $defaults (not $def, a jq reserved keyword) holds the default package list.
+            if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
-    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 $PACKAGE_NAME"
                 exit 1
             fi
-            LATEST_VERSION_CACHE[$PACKAGE_NAME]=$AVAILABLE_VERSION
+            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-        fi
+            if [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
-        AVAILABLE_VERSION=${LATEST_VERSION_CACHE[$PACKAGE_NAME]}
+            {%- endif %}
-
+                # Get currently installed version of package
-        if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
+                attempt=0
-            # Dry run, then (if clean) the actual upgrade, dispatched as a throttled background
+                max_attempts=3
-            # job. Each job builds its full log into one block, then flushes it under a single
+                while [ $attempt -lt $max_attempts ]; do
-            # shared lock (OUTPUT_LOCK) so concurrent jobs never interleave on stdout; a failed
+                    if PACKAGE_VERSION=$(elastic_fleet_integration_policy_package_version "$AGENT_POLICY" "$INTEGRATION") && AVAILABLE_VERSION=$(elastic_fleet_package_latest_version_check "$PACKAGE_NAME"); then
-            # job also appends a marker line to FAIL_FILE while holding that same lock.
+                        break
-            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 $INTEGRATION"
                     fi
-                else
+                    attempt=$((attempt + 1))
-                    block+="Errors detected during dry run for $PACKAGE_NAME policy upgrade..."$'\n'
+                done
-                    fail="dryrun-errors $INTEGRATION"
+                if [ $attempt -eq $max_attempts ]; then
+                    echo "Error: Failed getting $PACKAGE_VERSION or $AVAILABLE_VERSION"
+                    exit 1
                 fi
-                {
+
-                    flock 9
+                # Get integration ID
-                    printf '%s' "$block"
+                if ! INTEGRATION_ID=$(elastic_fleet_integration_id "$AGENT_POLICY" "$INTEGRATION"); then
-                    [ -n "$fail" ] && printf '%s\n' "$fail" >>"$FAIL_FILE"
+                    exit 1
-                } 9>>"$OUTPUT_LOCK"
+                fi
-            } &
+
+                if [[ "$PACKAGE_VERSION" != "$AVAILABLE_VERSION" ]]; then
+                    # Dry run of the upgrade
+                    echo ""
+                    echo "Current $PACKAGE_NAME package version ($PACKAGE_VERSION) is not the same as the latest available package ($AVAILABLE_VERSION)..."
+                    echo "Upgrading $INTEGRATION..."
+                    echo "Starting dry run..."
+                    if ! DRYRUN_OUTPUT=$(elastic_fleet_integration_policy_dryrun_upgrade "$INTEGRATION_ID"); then
+                        exit 1
+                    fi
+                    DRYRUN_ERRORS=$(echo "$DRYRUN_OUTPUT" | jq .[].hasErrors)
+
+                    # If no errors with dry run, proceed with actual upgrade
+                    if [[ "$DRYRUN_ERRORS" == "false" ]]; then
+                        echo "No errors detected. Proceeding with upgrade..."
+                        if ! elastic_fleet_integration_policy_upgrade "$INTEGRATION_ID"; then
+                            echo "Error: Upgrade failed for $PACKAGE_NAME with integration ID '$INTEGRATION_ID'."
+                            ERROR=true
+                            continue
+                        fi
+                    else
+                        echo "Errors detected during dry run for $PACKAGE_NAME policy upgrade..."
+                        ERROR=true
+                        continue
+                    fi
+                fi
+            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
+            fi
+            {%- endif %}
         fi
-    done < <(jq -r --argjson defaults "$default_packages_json" '
+    done
-        .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

@@ -16,6 +16,7 @@
 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
@@ -28,6 +29,29 @@ 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
@@ -39,23 +63,23 @@ 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 ! policy_json=$(fleet_api "agent_policies/$AGENT_POLICY"); then
+    if ! integrations=$(elastic_fleet_integration_policy_names "$AGENT_POLICY"); then
         # skip the agent policy if we can't get required info, let salt retry. Integrations loaded by this script are non-default integrations.
         echo "Skipping $AGENT_POLICY.. "
         continue
     fi
-    # non-default integrations that are in-use in any policy
+    for INTEGRATION in $integrations; do
-    while IFS= read -r PACKAGE_NAME; do
+        if ! PACKAGE_NAME=$(elastic_fleet_integration_policy_package_name "$AGENT_POLICY" "$INTEGRATION"); then
-        [ -n "$PACKAGE_NAME" ] && in_use_integrations+=("$PACKAGE_NAME")
+            echo  "Not adding $INTEGRATION, couldn't get package name"
-    done < <(jq -r --argjson defaults "$default_packages_json" \
+            continue
-        '.item.package_policies[].package.name | select(. as $n | ($defaults | index($n)) | not)' \
+        fi
-        <<<"$policy_json")
+        # non-default integrations that are in-use in any policy
+        if ! [[ " ${default_packages[@]} " =~ " $PACKAGE_NAME " ]]; then
+            in_use_integrations+=("$PACKAGE_NAME")
+        fi
+    done
 done
 
 if [[ -f $STATE_FILE_SUCCESS  ]]; then
@@ -66,55 +90,72 @@ 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
 
-        # Build the bulk install list and the per-package status messages with two jq passes
+        while read -r package; do
-        #  instead of a per-package bash loop. The old loop forked ~10 processes per package
+            # get package details
-        #  (5 jq + awk/bc for the version compare) and re-parsed/rewrote a growing JSON file on
+            package_name=$(echo "$package" | jq -r '.name')
-        #  every add (O(n^2)). Selection and messages below are identical to that logic.
+            latest_version=$(echo "$package" | jq -r '.latest_version')
-        SUB={% if SUB %}true{% else %}false{% endif %}
+            installed_version=$(echo "$package" | jq -r '.installed_version')
-        AUTOUP={% if AUTO_UPGRADE_INTEGRATIONS %}true{% else %}false{% endif %}
+            subscription=$(echo "$package" | jq -r '.subscription')
-        EXCLUDED_JSON=$(printf '%s\n' "${EXCLUDED_INTEGRATIONS[@]}" | jq -R 'select(length>0)' | jq -s '.')
+            bulk_package=$(echo "$package" | jq '{name: .name, version: .latest_version}' )
-        INUSE_JSON=$(printf '%s\n' "${in_use_integrations[@]}" | jq -R 'select(length>0)' | jq -s 'unique')
 
-        # vnum replicates the previous version_conversion (%d%03d%03d of the first three dotted
+            if [[ ! "${EXCLUDED_INTEGRATIONS[@]}" =~ "$package_name" ]]; then
-        #  fields); needs() replicates the excluded/subscription/installed/upgrade/in-use logic.
+            {% if not SUB %}
-        JQ_DECISION='
+                if [[ "$subscription" != "basic" && "$subscription" != "null" && -n "$subscription" ]]; then
-def vnum:
+                    # pass over integrations that require non-basic elastic license
-  [ (split(".")|.[0:3][] | gsub("[^0-9].*";"") | (if .=="" then "0" else . end) | tonumber) ]
+                    echo "$package_name integration requires an Elastic license of $subscription or greater... skipping"
-  | (.[0]//0)*1000000 + (.[1]//0)*1000 + (.[2]//0);
+                    continue
-def needs($sub;$autoup;$excluded;$inuse):
+                else
-  .name as $n
+                    if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
-  | ($n | IN($excluded[]) | not)
+                        echo "$package_name is not installed... Adding to next update."
-  and ( $sub or (.subscription==null or .subscription=="basic" or .subscription=="") )
+                        jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
-  and ( (.installed_version==null or .installed_version=="")
-        or ( ((.latest_version|vnum) > (.installed_version|vnum))
-             and ( $autoup or ($n | IN($inuse[]) | not) ) ) );'
 
-        JQ_ARGS=(--argjson sub "$SUB" --argjson autoup "$AUTOUP" --argjson excluded "$EXCLUDED_JSON" --argjson inuse "$INUSE_JSON")
+                        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
 
-        # (a) Per-package status messages (parity with the previous echo output).
+                                PENDING_UPDATE=true
-        jq -r "${JQ_ARGS[@]}" "$JQ_DECISION"'
+                            {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-          .packages[]
+                            else
-          | .name as $n
+                                echo "skipping available upgrade for in use integration - $package_name."
-          | if ($n|IN($excluded[])) then "Skipping \($n)..."
+                            fi
-            elif (($sub|not) and (.subscription!=null and .subscription!="basic" and .subscription!="")) then
+                            {%- endif %}
-                 "\($n) integration requires an Elastic license of \(.subscription) or greater... skipping"
+                        fi
-            elif (.installed_version==null or .installed_version=="") then
+                    fi
-                 "\($n) is not installed... Adding to next update."
+                fi
-            elif ((.latest_version|vnum) > (.installed_version|vnum)) then
+            {% else %}
-                 (if ($autoup or ($n|IN($inuse[])|not))
+                if [[ "$installed_version" == "null" || -z "$installed_version" ]]; then
-                  then "\($n) is at version \(.installed_version) latest version is \(.latest_version)... Adding to next update."
+                    echo "$package_name is not installed... Adding to next update."
-                  else "skipping available upgrade for in use integration - \($n)." end)
+                    jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
-            else empty end
+                    PENDING_UPDATE=true
-        ' "$INSTALLED_PACKAGE_LIST"
+                else
-
+                    results=$(compare_versions "$latest_version" "$installed_version")
-        # (b) The bulk install list, built in a single pass.
+                    if [ $results == "greater" ]; then
-        jq "${JQ_ARGS[@]}" "$JQ_DECISION"'
+                        {#- When auto_upgrade_integrations is false, skip upgrading in_use_integrations  #}
-          {packages: [ .packages[] | select(needs($sub;$autoup;$excluded;$inuse)) | {name, version: .latest_version} ]}
+                        {%- if not AUTO_UPGRADE_INTEGRATIONS %}
-        ' "$INSTALLED_PACKAGE_LIST" > "$BULK_INSTALL_PACKAGE_LIST"
+                        if ! [[ " ${in_use_integrations[@]} " =~ " $package_name " ]]; then
-
+                        {%- endif %}
-        if jq -e '.packages | length > 0' "$BULK_INSTALL_PACKAGE_LIST" >/dev/null; then
+                            echo "$package_name is at version $installed_version latest version is $latest_version... Adding to next update."
-            PENDING_UPDATE=true
+                            jq --argjson package "$bulk_package" '.packages += [$package]' $BULK_INSTALL_PACKAGE_LIST > $BULK_INSTALL_PACKAGE_TMP && mv $BULK_INSTALL_PACKAGE_TMP $BULK_INSTALL_PACKAGE_LIST
-        fi
+                            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")"
 
         if [ "$PENDING_UPDATE" = true ]; then
             # Run chunked install of packages

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

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

@@ -181,9 +181,6 @@ 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

@@ -9,12 +9,9 @@
 {%   from 'elasticsearch/config.map.jinja' import ELASTICSEARCHMERGED %}
 {%   from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS, SO_MANAGED_INDICES %}
 {%   if GLOBALS.role != 'so-heavynode' %}
-{%     from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS, ADDON_INDICES %}
+{%     from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS %}
 {%   endif %}
 
-include:
-  - elasticsearch.enabled
-
 escomponenttemplates:
   file.recurse:
     - name: /opt/so/conf/elasticsearch/templates/component
@@ -38,20 +35,6 @@ 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() %}
@@ -133,18 +116,6 @@ 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 }}
@@ -165,8 +136,7 @@ so-elasticsearch-roles-load:
 {%    set ap = "absent" %}
 {%  endif %}
 {%  if grains.role in ['so-eval', 'so-standalone', 'so-heavynode'] %}
-{#    Remove so-elasticsearch-indices-delete script when using DLM #}
+{%    if ELASTICSEARCHMERGED.index_clean %}
-{%    if ELASTICSEARCHMERGED.index_clean and ELASTICSEARCHMERGED.data_retention_method == "ILM" %}
 {%      set ap = "present" %}
 {%    else %}
 {%      set ap = "absent" %}

salt/elasticsearch/defaults.yaml

@@ -2,7 +2,6 @@ elasticsearch:
   enabled: false
   version: 9.3.3
   index_clean: true
-  data_retention_method: DLM
   vm:
     max_map_count: 1048576
   config:
@@ -64,8 +63,6 @@ elasticsearch:
             verification_mode: none
   index_settings:
     global_overrides:
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         template:
           settings:
@@ -146,8 +143,6 @@ elasticsearch:
                 order: desc
     so-common:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -309,8 +304,6 @@ elasticsearch:
               number_of_shards: 1
     so-assistant-chat:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: ""
       index_template:
         composed_of:
         - assistant-chat-mappings
@@ -351,8 +344,6 @@ elasticsearch:
             min_age: 0ms
     so-assistant-session:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: ""
       index_template:
         composed_of:
         - assistant-session-mappings
@@ -506,8 +497,6 @@ elasticsearch:
             min_age: 30d
     so-idh:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -616,8 +605,6 @@ elasticsearch:
             min_age: 30d
     so-import:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -800,8 +787,6 @@ elasticsearch:
             min_age: 0ms
     so-kismet:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - kismet-mappings
@@ -851,8 +836,6 @@ elasticsearch:
             min_age: 30d
     so-kratos:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -921,8 +904,6 @@ elasticsearch:
             min_age: 30d
     so-hydra:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -1068,8 +1049,6 @@ elasticsearch:
             min_age: 0ms
     so-logs:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - so-data-streams-mappings
@@ -1150,8 +1129,6 @@ 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
@@ -1215,8 +1192,6 @@ elasticsearch:
             min_age: 30d
     so-logs-elastic_agent:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1332,8 +1307,6 @@ elasticsearch:
             min_age: 30d
     so-elastic-agent-monitor:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -1396,8 +1369,6 @@ 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
@@ -1462,8 +1433,6 @@ 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
@@ -1528,8 +1497,6 @@ 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
@@ -1594,8 +1561,6 @@ 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
@@ -1655,8 +1620,6 @@ 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
@@ -1716,8 +1679,6 @@ 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
@@ -1774,8 +1735,6 @@ 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
@@ -1840,8 +1799,6 @@ 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
@@ -1901,8 +1858,6 @@ 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
@@ -1962,8 +1917,6 @@ 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
@@ -2028,8 +1981,6 @@ 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
@@ -2094,13 +2045,10 @@ 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
@@ -2110,9 +2058,8 @@ 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:
@@ -2157,13 +2104,10 @@ 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
@@ -2173,15 +2117,14 @@ 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.action.responses-logs
+                name: so-logs-endpoint.actions-logs
               mapping:
                 total_fields:
                   limit: 5000
@@ -2220,8 +2163,6 @@ 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
@@ -2281,8 +2222,6 @@ 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
@@ -2358,8 +2297,6 @@ 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
@@ -2419,8 +2356,6 @@ 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
@@ -2480,8 +2415,6 @@ 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
@@ -2541,8 +2474,6 @@ 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
@@ -2602,8 +2533,6 @@ 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
@@ -2663,8 +2592,6 @@ 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
@@ -2724,8 +2651,6 @@ 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
@@ -2785,8 +2710,6 @@ 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
@@ -2846,8 +2769,6 @@ 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
@@ -2896,8 +2817,6 @@ 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
@@ -2963,8 +2882,6 @@ 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
@@ -3036,8 +2953,6 @@ 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
@@ -3090,8 +3005,6 @@ elasticsearch:
             min_age: 30d
     so-logs-soc:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -3200,8 +3113,6 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_application:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3251,8 +3162,6 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_auth:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3302,8 +3211,6 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_security:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3353,8 +3260,6 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_syslog:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3404,8 +3309,6 @@ elasticsearch:
             min_age: 30d
     so-logs-system_x_system:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - event-mappings
@@ -3455,8 +3358,6 @@ 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
@@ -3504,8 +3405,6 @@ 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
@@ -3553,8 +3452,6 @@ 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
@@ -3602,8 +3499,6 @@ 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
@@ -3651,8 +3546,6 @@ 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
@@ -3701,8 +3594,6 @@ elasticsearch:
             min_age: 30d
     so-logstash:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -3818,8 +3709,6 @@ 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
@@ -3867,8 +3756,6 @@ 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
@@ -3916,8 +3803,6 @@ 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
@@ -3965,8 +3850,6 @@ 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
@@ -3991,8 +3874,6 @@ 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
@@ -4017,8 +3898,6 @@ elasticsearch:
               number_of_replicas: 0
     so-redis:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4079,10 +3958,13 @@ elasticsearch:
         - vulnerability-mappings
         - common-settings
         - common-dynamic-mappings
+        - logs-redis.log@package
+        - logs-redis.log@custom
         data_stream:
           allow_custom_routing: false
           hidden: false
-        ignore_missing_component_templates: []
+        ignore_missing_component_templates:
+        - logs-redis.log@custom
         index_patterns:
         - logs-redis.log*
         priority: 501
@@ -4134,8 +4016,6 @@ elasticsearch:
             min_age: 30d
     so-strelka:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4253,8 +4133,6 @@ elasticsearch:
             min_age: 30d
     so-suricata:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4371,8 +4249,6 @@ elasticsearch:
             min_age: 30d
     so-suricata_x_alerts:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4489,8 +4365,6 @@ elasticsearch:
             min_age: 30d
     so-syslog:
       index_sorting: false
-      data_stream_lifecycle:
-        data_retention: 90d
       index_template:
         composed_of:
         - agent-mappings
@@ -4607,8 +4481,6 @@ 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/zeek.ssl

@@ -5,7 +5,6 @@
     { "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

@@ -4,13 +4,6 @@ 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
@@ -20,7 +13,7 @@ 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, 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.
+    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.
     forcedType: bool
     helpLink: elasticsearch
   vm:
@@ -146,23 +139,6 @@ 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:
@@ -335,30 +311,13 @@ elasticsearch:
               forcedType: string
               global: True
               helpLink: elasticsearch
-    so-logs: &dataStreamSettings
+    so-logs: &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
-      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.
@@ -376,14 +335,6 @@ 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:
@@ -645,349 +596,65 @@ elasticsearch:
             global: True
             advanced: True
             helpLink: elasticsearch
-    so-logs-system_x_auth: *dataStreamSettings
+    so-logs-system_x_auth: *indexSettings
-    so-logs-system_x_syslog: *dataStreamSettings
+    so-logs-system_x_syslog: *indexSettings
-    so-logs-system_x_system: *dataStreamSettings
+    so-logs-system_x_system: *indexSettings
-    so-logs-system_x_application: *dataStreamSettings
+    so-logs-system_x_application: *indexSettings
-    so-logs-system_x_security: *dataStreamSettings
+    so-logs-system_x_security: *indexSettings
-    so-logs-windows_x_forwarded: *dataStreamSettings
+    so-logs-windows_x_forwarded: *indexSettings
-    so-logs-windows_x_powershell: *dataStreamSettings
+    so-logs-windows_x_powershell: *indexSettings
-    so-logs-windows_x_powershell_operational: *dataStreamSettings
+    so-logs-windows_x_powershell_operational: *indexSettings
-    so-logs-windows_x_sysmon_operational: *dataStreamSettings
+    so-logs-windows_x_sysmon_operational: *indexSettings
-    so-logs-winlog_x_winlog: *dataStreamSettings
+    so-logs-winlog_x_winlog: *indexSettings
-    so-logs-detections_x_alerts: *dataStreamSettings
+    so-logs-detections_x_alerts: *indexSettings
-    so-logs-http_endpoint_x_generic: *dataStreamSettings
+    so-logs-http_endpoint_x_generic: *indexSettings
-    so-logs-httpjson_x_generic: *dataStreamSettings
+    so-logs-httpjson_x_generic: *indexSettings
-    so-logs-osquery-manager-actions: *dataStreamSettings
+    so-logs-osquery-manager-actions: *indexSettings
-    so-logs-osquery-manager-action_x_responses: *dataStreamSettings
+    so-logs-osquery-manager-action_x_responses: *indexSettings
-    so-logs-osquery-manager_x_action_x_responses: *dataStreamSettings
+    so-logs-osquery-manager_x_action_x_responses: *indexSettings
-    so-logs-osquery-manager_x_result: *dataStreamSettings
+    so-logs-osquery-manager_x_result: *indexSettings
-    so-logs-elastic_agent_x_apm_server: *dataStreamSettings
+    so-logs-elastic_agent_x_apm_server: *indexSettings
-    so-logs-elastic_agent_x_auditbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_auditbeat: *indexSettings
-    so-logs-elastic_agent_x_cloudbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_cloudbeat: *indexSettings
-    so-logs-elastic_agent_x_endpoint_security: *dataStreamSettings
+    so-logs-elastic_agent_x_endpoint_security: *indexSettings
-    so-logs-endpoint_x_alerts: *dataStreamSettings
+    so-logs-endpoint_x_alerts: *indexSettings
-    so-logs-endpoint_x_events_x_api: *dataStreamSettings
+    so-logs-endpoint_x_events_x_api: *indexSettings
-    so-logs-endpoint_x_events_x_file: *dataStreamSettings
+    so-logs-endpoint_x_events_x_file: *indexSettings
-    so-logs-endpoint_x_events_x_library: *dataStreamSettings
+    so-logs-endpoint_x_events_x_library: *indexSettings
-    so-logs-endpoint_x_events_x_network: *dataStreamSettings
+    so-logs-endpoint_x_events_x_network: *indexSettings
-    so-logs-endpoint_x_events_x_process: *dataStreamSettings
+    so-logs-endpoint_x_events_x_process: *indexSettings
-    so-logs-endpoint_x_events_x_registry: *dataStreamSettings
+    so-logs-endpoint_x_events_x_registry: *indexSettings
-    so-logs-endpoint_x_events_x_security: *dataStreamSettings
+    so-logs-endpoint_x_events_x_security: *indexSettings
-    so-logs-elastic_agent_x_filebeat: *dataStreamSettings
+    so-logs-elastic_agent_x_filebeat: *indexSettings
-    so-logs-elastic_agent_x_fleet_server: *dataStreamSettings
+    so-logs-elastic_agent_x_fleet_server: *indexSettings
-    so-logs-elastic_agent_x_heartbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_heartbeat: *indexSettings
-    so-logs-elastic_agent: *dataStreamSettings
+    so-logs-elastic_agent: *indexSettings
-    so-logs-elastic_agent_x_metricbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_metricbeat: *indexSettings
-    so-logs-elastic_agent_x_osquerybeat: *dataStreamSettings
+    so-logs-elastic_agent_x_osquerybeat: *indexSettings
-    so-logs-elastic_agent_x_packetbeat: *dataStreamSettings
+    so-logs-elastic_agent_x_packetbeat: *indexSettings
-    so-logs-elasticsearch_x_server: *dataStreamSettings
+    so-logs-elasticsearch_x_server: *indexSettings
-    so-metrics-endpoint_x_metadata: *dataStreamSettings
+    so-metrics-endpoint_x_metadata: *indexSettings
-    so-metrics-endpoint_x_metrics: *dataStreamSettings
+    so-metrics-endpoint_x_metrics: *indexSettings
-    so-metrics-endpoint_x_policy: *dataStreamSettings
+    so-metrics-endpoint_x_policy: *indexSettings
-    so-metrics-nginx_x_stubstatus: *dataStreamSettings
+    so-metrics-nginx_x_stubstatus: *indexSettings
-    so-metrics-vsphere_x_datastore: *dataStreamSettings
+    so-metrics-vsphere_x_datastore: *indexSettings
-    so-metrics-vsphere_x_host: *dataStreamSettings
+    so-metrics-vsphere_x_host: *indexSettings
-    so-metrics-vsphere_x_virtualmachine: *dataStreamSettings
+    so-metrics-vsphere_x_virtualmachine: *indexSettings
-    so-common: *dataStreamSettings
+    so-case: *indexSettings
-    so-endgame: *dataStreamSettings
+    so-common: *indexSettings
-    so-idh: *dataStreamSettings
+    so-endgame: *indexSettings
-    so-suricata: *dataStreamSettings
+    so-idh: *indexSettings
-    so-suricata_x_alerts: *dataStreamSettings
+    so-suricata: *indexSettings
-    so-import: *dataStreamSettings
+    so-suricata_x_alerts: *indexSettings
-    so-kratos: *dataStreamSettings
+    so-import: *indexSettings
-    so-hydra: *dataStreamSettings
+    so-kratos: *indexSettings
-    so-kismet: *dataStreamSettings
+    so-hydra: *indexSettings
-    so-logstash: *dataStreamSettings
+    so-kismet: *indexSettings
-    so-redis: *dataStreamSettings
+    so-logstash: *indexSettings
-    so-strelka: *dataStreamSettings
+    so-redis: *indexSettings
-    so-syslog: *dataStreamSettings
+    so-strelka: *indexSettings
-    so-zeek: *dataStreamSettings
+    so-syslog: *indexSettings
-    # Managed SOC integration annotations are inserted below this line. Referencing '*dataStreamSettings'
+    so-zeek: *indexSettings
-    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

@@ -4,11 +4,7 @@
    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', {}) %}
@@ -65,25 +61,15 @@
 {% 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, EXCLUDE_INDICES=[]) %}
+{% macro create_final_index_template(DEFINED_SETTINGS, GLOBAL_OVERRIDES, FINAL_INDEX_SETTINGS) %}
 
 {% 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 %}
@@ -109,17 +95,6 @@
 {%     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 #}
@@ -175,19 +150,10 @@
 {% endfor %}
 {% endmacro %}
 
-{# Exclude addon integrations from final ES_INDEX_SETTINGS #}
+{{ create_final_index_template(ES_INDEX_SETTINGS_ORIG, ES_INDEX_SETTINGS_GLOBAL_OVERRIDES, 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 ) }}
+{{ create_final_index_template(ALL_ADDON_SETTINGS_ORIG, ALL_ADDON_SETTINGS_GLOBAL_OVERRIDES, ALL_ADDON_SETTINGS) }}
-
-{# 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

@@ -11,8 +11,10 @@ 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"
-FAILED_NAMES=()
+SO_LOAD_FAILURES=0
-FAILED_COUNT=0
+ADDON_LOAD_FAILURES=0
+SO_LOAD_FAILURES_NAMES=()
+ADDON_LOAD_FAILURES_NAMES=()
 IS_HEAVYNODE="false"
 FORCE="false"
 VERBOSE="false"
@@ -44,86 +46,20 @@ 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
 
-    # Capture everything (including retry's diagnostic chatter) into one block so
+    echo "Loading template file $file"
-    # concurrent jobs never interleave; the whole block is flushed under one flock.
+    if ! output=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}"); then
-    block="Loading template file $file"$'\n'
+        echo "$output"
-    if ! out=$(retry 3 3 "so-elasticsearch-query $uri -d@$file -XPUT" "{\"acknowledged\":true}" 2>&1); then
+
-        block+="$out"$'\n'
+        return 1
-        rc=1
+
     elif [[ "$VERBOSE" == "true" ]]; then
-        block+="$out"$'\n'
+        echo "$output"
     fi
 
-    { flock 9; printf '%s' "$block"; } 9>>"$OUTPUT_LOCK"
-
-    (( rc != 0 )) && record_failure "$report_name"
 }
 
 check_required_component_template_exists() {
@@ -174,9 +110,6 @@ 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}")
 
@@ -185,11 +118,21 @@ load_component_templates() {
             tmpl_name="${tmpl_name%-mappings}-mappings"
         fi
 
-        template_throttle
+        if ! load_template "_component_template/${tmpl_name}" "$component"; then
-        load_template "_component_template/${tmpl_name}" "$component" "$component" &
+            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
+            SO_LOAD_FAILURES_NAMES+=("$component")
+        fi
     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"
 
@@ -237,9 +180,6 @@ 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
@@ -249,7 +189,7 @@ 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
-                    locked_echo "Skipping over $so_idx_tmpl, template is not a heavynode specific index template."
+                    echo "Skipping over $so_idx_tmpl, template is not a heavynode specific index template."
                 fi
 
                 continue
@@ -257,34 +197,32 @@ if [[ "$FORCE" == "true" || ! -f "$SO_STATEFILE_SUCCESS" ]] && index_templates_e
         fi
 
         if check_required_component_template_exists "$so_idx_tmpl"; then
-            template_throttle
+            if ! load_template "_index_template/$tmpl_name" "$so_idx_tmpl"; then
-            load_template "_index_template/$tmpl_name" "$so_idx_tmpl" "$so_idx_tmpl" &
+                SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
+                SO_LOAD_FAILURES_NAMES+=("$so_idx_tmpl")
+            fi
         else
-            locked_echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
+            echo "Skipping over $so_idx_tmpl due to missing required component template(s)."
-            record_failure "$so_idx_tmpl"
+            SO_LOAD_FAILURES=$((SO_LOAD_FAILURES + 1))
+            SO_LOAD_FAILURES_NAMES+=("$so_idx_tmpl")
 
             continue
         fi
     done
 
-    # Barrier: all SO index template PUTs must finish before tallying failures.
+    if [[ $SO_LOAD_FAILURES -eq 0 ]]; then
-    wait
-
-    collect_failures
-    if [[ $FAILED_COUNT -eq 0 ]]; then
         echo "All Security Onion core templates loaded successfully."
 
         touch "$SO_STATEFILE_SUCCESS"
     else
-        echo "Encountered $FAILED_COUNT failure(s) loading templates:"
+        echo "Encountered $SO_LOAD_FAILURES failure(s) loading templates:"
-        for failed_template in "${FAILED_NAMES[@]}"; do
+        for failed_template in "${SO_LOAD_FAILURES_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
@@ -303,27 +241,26 @@ if should_load_addon_templates; then
         tmpl_name=$(basename "${addon_idx_tmpl%-template.json}")
 
         if check_required_component_template_exists "$addon_idx_tmpl"; then
-            template_throttle
+            if ! load_template "_index_template/${tmpl_name}" "$addon_idx_tmpl"; then
-            load_template "_index_template/${tmpl_name}" "$addon_idx_tmpl" "$addon_idx_tmpl" &
+                ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
+                ADDON_LOAD_FAILURES_NAMES+=("$addon_idx_tmpl")
+            fi
         else
-            locked_echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
+            echo "Skipping over $addon_idx_tmpl due to missing required component template(s)."
-            record_failure "$addon_idx_tmpl"
+            ADDON_LOAD_FAILURES=$((ADDON_LOAD_FAILURES + 1))
+            ADDON_LOAD_FAILURES_NAMES+=("$addon_idx_tmpl")
 
             continue
         fi
     done
 
-    # Barrier: all addon index template PUTs must finish before tallying failures.
+    if [[ $ADDON_LOAD_FAILURES -eq 0 ]]; then
-    wait
-
-    collect_failures
-    if [[ $FAILED_COUNT -eq 0 ]]; then
         echo "All addon integration templates loaded successfully."
 
         touch "$ADDON_STATEFILE_SUCCESS"
     else
-        echo "Encountered $FAILED_COUNT failure(s) loading addon integration templates:"
+        echo "Encountered $ADDON_LOAD_FAILURES failure(s) loading addon integration templates:"
-        for failed_template in "${FAILED_NAMES[@]}"; do
+        for failed_template in "${ADDON_LOAD_FAILURES_NAMES[@]}"; do
             echo "  - $failed_template"
         done
         if [[ "$SHOULD_EXIT_ON_FAILURE" == "true" ]]; then

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

@@ -1,175 +0,0 @@
-#!/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

@@ -6,48 +6,6 @@
 
 . /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 (( $(jobs -rp | wc -l) >= MAX_JOBS )); do
-    wait -n || true
-  done
-}
-
 {%- from 'elasticsearch/template.map.jinja' import ES_INDEX_SETTINGS %}
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   from 'elasticsearch/template.map.jinja' import ALL_ADDON_SETTINGS %}
@@ -56,36 +14,35 @@ throttle() {
 {%- for index, settings in ES_INDEX_SETTINGS.items() %}
 {%-   if settings.policy is defined %}
 {%-     if index == 'so-logs-detections.alerts' %}
-  throttle
+  echo
-  put_policy "so-logs-detections.alerts-so" "{{ index }}-so" '{ "policy": {{ settings.policy | tojson(true) }} }' &
+  echo "Setting up so-logs-detections.alerts-so policy..."
+  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$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
 {%-     elif index == 'so-logs-soc' %}
-  throttle
+  echo
-  put_policy "so-soc-logs" "so-soc-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
+  echo "Setting up so-soc-logs policy..."
-  throttle
+  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/so-soc-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
-  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
+  echo
+  echo
+  echo "Setting up {{ index }}-logs policy..."
+  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$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
 {%-     else %}
-  throttle
+  echo
-  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
+  echo "Setting up {{ index }}-logs policy..."
+  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$SESSIONCOOKIE" -s -k -L -X PUT "https://localhost:9200/_ilm/policy/{{ index }}-logs" -H 'Content-Type: application/json' -d'{ "policy": {{ settings.policy | tojson(true) }} }'
+  echo
 {%-     endif %}
 {%-   endif %}
 {%- endfor %}
+echo
 {%- if GLOBALS.role != "so-heavynode" %}
 {%-   for index, settings in ALL_ADDON_SETTINGS.items() %}
 {%-     if settings.policy is defined %}
-  throttle
+  echo
-  put_policy "{{ index }}-logs" "{{ index }}-logs" '{ "policy": {{ settings.policy | tojson(true) }} }' &
+  echo "Setting up {{ index }}-logs policy..."
+  curl -K /opt/so/conf/elasticsearch/curl.config -b "sid=$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
 {%-     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: "960"
+    - user: kafka
     - 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

@@ -6,7 +6,6 @@
 {% 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:
@@ -18,7 +17,7 @@ so-kibana:
   docker_container.running:
     - image: {{ GLOBALS.registry_host }}:5000/{{ GLOBALS.image_repo }}/so-kibana:{{ GLOBALS.so_version }}
     - hostname: kibana
-    - user: "932:0"
+    - user: kibana
     - networks:
       - sobridge:
         - ipv4_address: {{ DOCKERMERGED.containers['so-kibana'].ip }}
@@ -61,19 +60,6 @@ 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 before it will timeout, and require a new login.
+        description: Defines the length of a login session.
         global: True
         helpLink: kratos
       whoami:

salt/logstash/enabled.sls

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

salt/manager/files/mirror-kernel.txt

@@ -1,2 +0,0 @@
-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

@@ -10,9 +10,4 @@ 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

@@ -86,28 +86,6 @@ 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
@@ -144,13 +122,6 @@ 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

@@ -16,35 +16,40 @@
 {%       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' %}
-manage_soc_annotations:
+{{   es_soc_annotations }}:
-  file.blockreplace:
+     file.serialize:
-    - name: {{ es_soc_annotations }}
+       - dataset:
-    - marker_start: '    # START managed SOC integration annotations'
+           {% set data = salt['file.read'](es_soc_annotations) | load_yaml %}
-    - marker_end: '    # END managed SOC integration annotations'
+           {% set es = data.get('elasticsearch', {}) %}
-    - content: {{ soc_annotation_lines | join('\n') | tojson }}
+           {% set index_settings = es.get('index_settings', {}) %}
-    - insert_after_match: '^    # Managed SOC integration annotations are inserted below this line\.'
+           {% set input = index_settings.get('so-logs', {}) %}
-    - append_if_not_found: False
+           {% for k in matched_integration_names %}
-    - show_changes: True
+           {%   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 }}
 
 {#   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.blockreplace:
+     file.serialize:
-    - marker_start: '    # START managed SOC integration defaults'
+       - dataset:
-    - marker_end: '    # END managed SOC integration defaults'
+           {% set data = salt['file.read'](es_defaults) | load_yaml %}
-    - content: {{ defaults_lines | join('\n') | tojson }}
+           {% set es = data.get('elasticsearch', {}) %}
-    - insert_after_match: '^  index_settings:$'
+           {% set index_settings = es.get('index_settings', {}) %}
-    - append_if_not_found: False
+           {% for k in matched_integration_names %}
-    - show_changes: True
+           {%   set input = ADDON_INTEGRATION_DEFAULTS[k] %}
-{% endif %}
+           {%     do index_settings.update({k: input})%}
+           {% endfor %}
+           {% for k in addon_integration_keys %}
+           {%   if k not in matched_integration_names and k in index_settings %}
+           {%     do index_settings.pop(k) %}
+           {%   endif %}
+           {% endfor %}
+           {{ data }}
+{% endif %}

salt/manager/sync_es_users.sls

@@ -31,13 +31,11 @@ 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 the onlyif gates on the
+# we dont want this added too early in setup, so we add the onlyif to verify 'startup_states: highstate'
-# /opt/so/state/setup-complete marker. The marker is written by
+# is in the minion config. That line is added before the final highstate during setup
-# 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: "test -e /opt/so/state/setup-complete"
+    - onlyif: "grep -x 'startup_states: highstate' /etc/salt/minion"

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

@@ -1,117 +0,0 @@
-#!/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-repo-sync

@@ -10,16 +10,5 @@ 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/soup

@@ -16,7 +16,6 @@ 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
@@ -35,7 +34,6 @@ 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() {
@@ -116,52 +114,11 @@ 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
@@ -231,6 +188,13 @@ 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
@@ -245,7 +209,6 @@ 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
@@ -387,11 +350,10 @@ highstate() {
 masterlock() {
   echo "Locking Salt Master"
   mv -v $TOPFILE $BACKUPTOPFILE
-  # Render the real top file only for the host running soup; every other
+  echo "base:" > $TOPFILE
-  # minion gets an empty top (no states) while the master is upgrading.
+  echo "  $MINIONID:" >> $TOPFILE
-  echo "{% if grains['id'] == '$MINIONID' %}" > $TOPFILE
+  echo "    - ca" >> $TOPFILE
-  cat $BACKUPTOPFILE >> $TOPFILE
+  echo "    - elasticsearch" >> $TOPFILE
-  echo "{% endif %}" >> $TOPFILE
 }
 
 masterunlock() {
@@ -408,9 +370,8 @@ 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
 }
 
@@ -420,7 +381,6 @@ 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
 }
 
@@ -782,121 +742,6 @@ 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."
@@ -1005,19 +850,13 @@ update_airgap_rules() {
   rsync -a $UPDATE_DIR/agrules/securityonion-resources/* /nsm/securityonion-resources/
 }
 
-update_airgap_repos() {
+update_airgap_repo() {
   # Update the files in the repo
-  echo "Syncing new updates to /nsm/repo & /nsm/kernelrepo"
+  echo "Syncing new updates to /nsm/repo"
-  # Airgap soup copies new files into the local repo, but doesn't remove old packages. Retaining the ability to rollback package updates
+  rsync -a $AGREPO/* /nsm/repo/
-  rsync -a "$AGREPO"/ /nsm/repo/
+  echo "Creating 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() {
@@ -1689,7 +1528,13 @@ EOF
 
 # Keeping this block in case we need to do a hotfix that requires salt update
 apply_hotfix() {
-    echo "No actions required. ($INSTALLEDVERSION/$HOTFIXVERSION)"
+    if [[ "$INSTALLEDVERSION" == "3.1.0" ]] ; then
+       # Do not remove this fix_logstash_0013_lumberjack_pipeline_name in future hotfixes without first validating older
+       #  installs referencing "so/0013_input_lumberjack_fleet.conf" via pillar are upgradable
+       fix_logstash_0013_lumberjack_pipeline_name
+    else
+        echo "No actions required. ($INSTALLEDVERSION/$HOTFIXVERSION)"
+    fi
 }
 
 failed_soup_restore_items() {
@@ -1761,19 +1606,19 @@ main() {
   echo "Verifying we have the latest soup script."
   verify_latest_update_script
 
+  echo "Verifying Elasticsearch version compatibility across the grid 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_repos
+    update_airgap_repo
     dnf clean all
     check_os_updates
   elif [[ $OS == 'oracle' ]]; then
@@ -1787,8 +1632,7 @@ 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
-        echo "Running so-config-backup script."
+      backup_old_states_pillars
-        /sbin/so-config-backup
     fi
     copy_new_files
     create_local_directories "/opt/so/saltstack/default"
@@ -1844,8 +1688,8 @@ 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 "Running so-config-backup script."
+      echo "Creating snapshots of default and local Salt states and pillars and saving to /nsm/backup/"
-      /sbin/so-config-backup
+      backup_old_states_pillars
     fi
 
     echo ""
@@ -2057,20 +1901,4 @@ EOF
   read -r input
 fi
 
-set -o errtrace
+main "$@" | tee -a $SOUP_LOG
-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

@@ -59,7 +59,6 @@ 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

@@ -323,16 +323,6 @@ 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/postgres/files/init-db.sh

@@ -17,7 +17,6 @@ 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 "$SO_POSTGRES_USER";
     -- Lock the SOC database down at the connect layer; PUBLIC gets CONNECT
     -- by default, which would let per-minion telegraf roles open sessions
@@ -32,4 +31,4 @@ EOSQL
 # only ensures the shared database exists on first initialization.
 if ! psql -U "$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/telegraf_users.sls

@@ -18,12 +18,26 @@ 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: /usr/sbin/so-postgres-wait
+    - 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
-      - file: postgres_sbin
 
 # 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

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

@@ -1,32 +0,0 @@
-#!/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/registry/enabled.sls

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

salt/repo/client/init.sls

@@ -1,5 +1,6 @@
 {% from 'vars/globals.map.jinja' import GLOBALS %}
-{% if GLOBALS.os == 'OEL' %}
+{# OL10 test path uses public repos; skip the SO repo state (which removes public repos and points at /nsm/repo) #}
+{% if GLOBALS.os == 'OEL' and GLOBALS.os_version|int == 9 %}
 include:
   - repo.client.oracle
 {% endif %}

salt/repo/client/oracle.sls

@@ -6,10 +6,6 @@
 {% 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' %}
@@ -61,32 +57,6 @@ 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/master.sls

@@ -14,7 +14,6 @@
 
 include:
   - salt.minion
-  - salt.master.boot_mine_update
 {%   if 'vrt' in salt['pillar.get']('features', []) %}
   - salt.cloud
   - salt.cloud.reactor_config_hypervisor

salt/salt/master/boot_mine_update.sls

@@ -1,29 +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.
-
-# 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/minion/boot_highstate.sls

@@ -1,31 +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.
-
-# Manages /etc/systemd/system/so-boot-highstate.service, a Type=oneshot
-# RemainAfterExit=yes unit that runs `salt-call state.highstate` exactly once
-# per system boot. Replaces the legacy `startup_states: highstate` minion
-# config, which fired on every salt-minion service restart (causing a redundant
-# highstate whenever a highstate itself restarted salt-minion).
-
-include:
-  - systemd.reload
-
-so_boot_highstate_unit_file:
-  file.managed:
-    - name: /etc/systemd/system/so-boot-highstate.service
-    - source: salt://salt/service/so-boot-highstate.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 -- this just keeps
-# `systemctl is-enabled` honest for the sync_es_users gate.
-so_boot_highstate_service:
-  service.enabled:
-    - name: so-boot-highstate.service
-    - onlyif: test -e /opt/so/state/setup-complete
-    - require:
-      - file: so_boot_highstate_unit_file
-      - module: systemd_reload

salt/salt/minion/init.sls

@@ -17,7 +17,6 @@ include:
   - repo.client
   - salt.mine_functions
   - salt.minion.service_file
-  - salt.minion.boot_highstate
 {% if GLOBALS.is_manager %}
   - ca.signing_policy
 {% endif %}
@@ -81,33 +80,11 @@ set_log_levels:
       - "log_level: info"
       - "log_level_logfile: info"
 
-# startup_states: highstate caused a full highstate to run on every
+enable_startup_states:
-# salt-minion service start, including the restart triggered when a highstate
+  file.uncomment:
-# itself modified the minion config (beacons, mine, unit file). Replaced by
-# so-boot-highstate.service (managed in salt.minion.boot_highstate), which
-# runs once per system boot only. Strip the line from /etc/salt/minion on
-# upgrade; both the commented and uncommented forms historically existed.
-remove_startup_states:
-  file.line:
     - name: /etc/salt/minion
-    - match: 'startup_states: highstate'
+    - regex: '^startup_states: highstate$'
-    - mode: delete
+    - unless: pgrep so-setup
-
-# Upgrade-path bridge: systems that already passed setup under the old gate
-# (`grep -x 'startup_states: highstate' /etc/salt/minion`) get a /opt/so/state/setup-complete
-# marker so so-boot-highstate.service can be enabled and the so-user_sync cron
-# in sync_es_users.sls keeps installing. Setup-in-progress systems instead get
-# the marker from `mark_setup_complete` in setup/so-functions at the right
-# moment. `replace: false` means we never overwrite a marker once written.
-mark_setup_complete_for_upgrades:
-  file.managed:
-    - name: /opt/so/state/setup-complete
-    - replace: false
-    - makedirs: True
-    - onlyif: "grep -qx 'startup_states: highstate' /etc/salt/minion"
-    - require_in:
-      - file: remove_startup_states
-      - service: so_boot_highstate_service
 
 {% endif %}
 

salt/salt/service/so-boot-highstate.service

@@ -1,14 +0,0 @@
-[Unit]
-Description=Security Onion boot-time highstate (runs once per boot)
-After=salt-minion.service network-online.target docker.service
-Wants=network-online.target docker.service
-Requires=salt-minion.service
-ConditionPathExists=/opt/so/state/setup-complete
-
-[Service]
-Type=oneshot
-RemainAfterExit=yes
-ExecStart=/usr/bin/salt-call state.highstate -l info queue=True
-
-[Install]
-WantedBy=multi-user.target

salt/salt/service/so-boot-mine-update.service

@@ -1,15 +0,0 @@
-[Unit]
-Description=Security Onion boot-time grid mine.update (managers, runs once per boot before highstate)
-After=salt-master.service salt-minion.service network-online.target
-Wants=network-online.target
-Requires=salt-master.service salt-minion.service
-Before=so-boot-highstate.service
-ConditionPathExists=/opt/so/state/setup-complete
-
-[Service]
-Type=oneshot
-RemainAfterExit=yes
-ExecStart=/usr/sbin/so-boot-mine-update
-
-[Install]
-WantedBy=multi-user.target

salt/setup/virt/setSalt.sls

@@ -8,6 +8,11 @@ set_role_grain:
     - name: role
     - value: so-{{ grains.id.split("_") | last }}
 
+set_highstate:
+  file.append:
+    - name: /etc/salt/minion
+    - text: 'startup_states: highstate'
+
 enable_salt_minion:
   service.enabled:
     - name: salt-minion

salt/soc/config.sls

@@ -134,30 +134,6 @@ socsigmasopipeline:
     - group: 939
     - mode: 600
 
-socsigmaplaybookpipeline:
-  file.managed:
-    - name: /opt/so/conf/soc/sigma_playbook_pipeline.yaml
-    - source: salt://soc/files/soc/sigma_playbook_pipeline.yaml
-    - user: 939
-    - group: 939
-    - mode: 600
-
-socplaybookplaceholdermap:
-  file.managed:
-    - name: /opt/so/conf/soc/playbook_placeholder_map.yaml
-    - source: salt://soc/files/soc/playbook_placeholder_map.yaml
-    - user: 939
-    - group: 939
-    - mode: 600
-
-socplaybookplaceholdermapcustom:
-  file.managed:
-    - name: /opt/so/conf/soc/playbook_placeholder_map_custom.yaml
-    - source: salt://soc/files/soc/playbook_placeholder_map_custom.yaml
-    - user: 939
-    - group: 939
-    - mode: 600
-
 socbanner:
   file.managed:
     - name: /opt/so/conf/soc/banner.md

salt/soc/defaults.yaml

@@ -1464,7 +1464,6 @@ soc:
           sigmaRulePackages:
             - core
             - emerging_threats_addon
-          useEsql: false
         elastic:
           hostUrl:
           remoteHostUrls: []
@@ -1502,9 +1501,6 @@ soc:
               - repo: https://github.com/Security-Onion-Solutions/securityonion-resources-playbooks
                 branch: main
                 folder: securityonion-normalized
-              - repo: https://github.com/Security-Onion-Solutions/securityonion-resources-playbooks
-                branch: published
-                folder: sigma
             airgap:
               - repo: file:///nsm/airgap-resources/playbooks/securityonion-resources-playbooks
                 branch: main
@@ -1523,16 +1519,6 @@ soc:
               serviceAccountJSON: ""
               serviceAccountLocation: ""
               healthTimeoutSeconds: 5
-        onionconfig:
-          saltstackDir: /opt/so/saltstack
-          bypassEnabled: false
-        postgres:
-          host: ""
-          port: 5432
-          sslMode: "allow"
-          database: securityonion
-          user: ""
-          password: ""
         salt:
           queueDir: /opt/sensoroni/queue
           timeoutMs: 45000
@@ -1774,13 +1760,13 @@ soc:
               enabled: true
           queries:
             - name: Default Query
-              description: Show all events grouped by module and dataset
-              query: '* | groupby event.module* event.dataset'
-              showSubtitle: true
-            - name: Observer
               description: Show all events grouped by the observer host
               query: '* | groupby observer.name'
               showSubtitle: true
+            - name: Log Type
+              description: Show all events grouped by module and dataset
+              query: '* | groupby event.module* event.dataset'
+              showSubtitle: true
             - name: SOC - Auth
               description: Users authenticated to SOC grouped by IP address and identity
               query: 'event.dataset:kratos.audit AND msg:*authenticated* | groupby http.request.headers.x-real-ip user.name'

salt/soc/enabled.sls

@@ -45,10 +45,7 @@ so-soc:
       - /opt/so/conf/soc/motd.md:/opt/sensoroni/html/motd.md:ro
       - /opt/so/conf/soc/banner.md:/opt/sensoroni/html/login/banner.md:ro
       - /opt/so/conf/soc/sigma_so_pipeline.yaml:/opt/sensoroni/sigma_so_pipeline.yaml:ro
-      - /opt/so/conf/soc/sigma_playbook_pipeline.yaml:/opt/sensoroni/sigma_playbook_pipeline.yaml:ro
+      - /opt/so/conf/soc/sigma_final_pipeline.yaml:/opt/sensoroni/sigma_final_pipeline.yaml:rw
-      - /opt/so/conf/soc/sigma_final_pipeline.yaml:/opt/sensoroni/sigma_final_pipeline.yaml:ro
-      - /opt/so/conf/soc/playbook_placeholder_map.yaml:/opt/sensoroni/playbook_placeholder_map.yaml:ro
-      - /opt/so/conf/soc/playbook_placeholder_map_custom.yaml:/opt/sensoroni/playbook_placeholder_map_custom.yaml:ro
       - /opt/so/conf/soc/custom.js:/opt/sensoroni/html/js/custom.js:ro
       - /opt/so/conf/soc/custom_roles:/opt/sensoroni/rbac/custom_roles:ro
       - /opt/so/conf/soc/soc_users_roles:/opt/sensoroni/rbac/users_roles:rw
@@ -102,8 +99,6 @@ so-soc:
       - file: soccustomroles
       - file: socusersroles
       - file: socclientsroles
-      - file: socplaybookplaceholdermap
-      - file: socplaybookplaceholdermapcustom
 
 delete_so-soc_so-status.disabled:
   file.uncomment:

salt/soc/files/soc/playbook_placeholder_map.yaml

@@ -1,49 +0,0 @@
-# Global Playbook placeholder map: %token% -> event field path.
-#
-# Loaded by the SOC Playbook module and used to resolve `field|expand:%placeholder%` values 
-# from an alert when converting playbook questions to OQL. 
-# Left: the %token% used in a question
-# Right: the event field its value is read from (event_data.-nested or bare; the module
-# tries both). 
-#
-# Example: with `src_ip: source.ip` (below), a question that writes
-# `source.ip|expand: '%src_ip%'` resolves %src_ip% to the alert's source.ip at convert time.
-#
-# This is the global base layer. To add or override tokens edit playbook_placeholder_map_custom.yaml.
-# those entries overlay this map and win on conflict.
-
-CommandLine: process.command_line
-CurrentDirectory: process.working_directory
-Image: process.executable
-ImageLoaded: dll.name
-ParentImage: process.parent.executable
-ParentName: process.parent.name
-ParentProcessGuid: process.parent.entity_id
-ProcessGuid: process.entity_id
-TargetFilename: file.name
-TargetObject: registry.path
-TargetUserName: user.target.name
-User: user.name
-community_id: network.community_id
-dns_resolved_ip: dns.resolved_ip
-document_id: soc_id
-dst_ip: destination.ip
-dst_port: destination.port
-event_data_source_ip: source.ip
-file_path: file.path
-file_dirs: process.file_dirs
-file_name: process.name
-file_paths: process.file_paths
-hostname: host.name
-private_ip: network.private_ip
-public_ip: network.public_ip
-related_hosts: related.hosts
-related_ip: related.ip
-src_ip: source.ip
-dns_query_name: dns.query_name
-flow_id: log.id.uid
-payload: network.data.decoded
-rule_category: rule.category
-rule_name: rule.name
-rule_uuid: rule.uuid
-src_port: source.port

salt/soc/files/soc/playbook_placeholder_map_custom.yaml

@@ -1,14 +0,0 @@
-# Custom Playbook placeholder map: %token% -> event field path.
-#
-#
-# Left: the %token% used in a playbook question.
-# Right: the event field its value is read from (event_data.-nested or bare; the module tries
-# both). Note: a token that is simply named after a flat event field resolves automatically
-# without an entry here - only add a mapping when the token name differs from the field name.
-#
-# Example:
-#
-# account_id: cloudflare.account_id
-#
-# A question that writes
-# `account_id|expand: '%account_id%'` resolves %account_id% from the alert at convert time.

salt/soc/files/soc/sigma_playbook_pipeline.yaml

@@ -1,12 +0,0 @@
-name: Security Onion - Playbook Pipeline
-priority: 97
-transformations:
-    # Route string fields to their lowercase-normalized .caseless subfield so wildcard
-    # matches are case-insensitive.
-    - id: case_insensitive_string_fields
-      type: field_name_mapping
-      mapping:
-        process.executable: process.executable.caseless
-        process.parent.executable: process.parent.executable.caseless
-        process.command_line: process.command_line.caseless
-        process.parent.command_line: process.parent.command_line.caseless

salt/soc/files/soc/sigma_so_pipeline.yaml

@@ -63,14 +63,6 @@ transformations:
       rule_conditions:
       - type: logsource
         category: antivirus
-    # OS-agnostic process_creation scoping for product-less (NIDS/host-pivot) rules.
-    - id: process_creation_os_agnostic
-      type: add_condition
-      conditions:
-        event.category: process
-      rule_conditions:
-      - type: logsource
-        category: process_creation
     # Transforms the `Hashes` field to ECS fields
     # ECS fields are used by the hash fields emitted by Elastic Defend
     # If shipped with Elastic Agent, sysmon logs will also have hashes mapped to ECS fields    
@@ -116,40 +108,6 @@ transformations:
       - type: logsource
         product: windows
         category: driver_load
-    - id: ecs_fix_process_creation
-      type: field_name_mapping
-      mapping:
-        # bare `Hashes` (the combined-string case is broken out above)
-        winlog.event_data.Hashes: process.hash.sha256
-        winlog.event_data.IntegrityLevel: process.Ext.token.integrity_level_name
-        winlog.event_data.ParentName: process.parent.name
-      rule_conditions:
-      - type: logsource
-        product: windows
-        category: process_creation
-    - id: ecs_fix_registry_set
-      type: field_name_mapping
-      mapping:
-        winlog.event_data.Details: registry.data.strings
-        # field rename only; EventType values (SetValue/CreateKey) still differ from
-        # event.action values (modification/creation)
-        winlog.event_data.EventType: event.action
-      rule_conditions:
-      - type: logsource
-        product: windows
-        category: registry_set
-    - id: ecs_fix_image_load
-      type: field_name_mapping
-      mapping:
-        file.path: dll.path
-        file.code_signature.signed: dll.code_signature.exists
-        winlog.event_data.Signature: dll.code_signature.subject_name
-        file.code_signature.status: dll.code_signature.status
-        winlog.event_data.Hashes: dll.hash.sha256
-      rule_conditions:
-      - type: logsource
-        product: windows
-        category: image_load
     - id: linux_security_add-fields
       type: add_condition
       conditions:
@@ -323,15 +281,6 @@ transformations:
       rule_conditions:
       - type: logsource
         category: file_event
-    # Scope image_load rules to Elastic Endpoint library events (event.category:library, dll.*
-    # populated).
-    - id: endpoint_image_load_add-fields
-      type: add_condition
-      conditions:
-        event.category: 'library'
-      rule_conditions:
-      - type: logsource
-        category: image_load
     # Maps network rules to all network logs
     # This targets all network logs, all services, generated from endpoints and network
     - id: network_add-fields

salt/soc/merged.map.jinja

@@ -16,14 +16,6 @@
 {% do SOCMERGED.config.server.update({'additionalCA': MANAGERMERGED.additionalCA}) %}
 {% do SOCMERGED.config.server.update({'insecureSkipVerify': MANAGERMERGED.insecureSkipVerify}) %}
 
-{% if not SOCMERGED.config.server.modules.postgres.host %}
-{%   do SOCMERGED.config.server.modules.postgres.update({'host': GLOBALS.manager}) %}
-{% endif %}
-{% if not SOCMERGED.config.server.modules.postgres.password %}
-{%   do SOCMERGED.config.server.modules.postgres.update({'password': salt['pillar.get']('postgres:auth:users:so_postgres_user:pass', '')}) %}
-{%   do SOCMERGED.config.server.modules.postgres.update({'user': salt['pillar.get']('postgres:auth:users:so_postgres_user:user', 'so_postgres')}) %}
-{% endif %}
-
 {# if SOCMERGED.config.server.modules.cases == httpcase details come from the soc pillar #}
 {% if SOCMERGED.config.server.modules.cases != 'soc' %}
 {%   do SOCMERGED.config.server.modules.elastic.update({'casesEnabled': false}) %}

salt/soc/soc_soc.yaml

@@ -46,15 +46,7 @@ soc:
         syntax: yaml
         file: True
         global: True
-        advanced: False
+        advanced: True
-        helpLink: security-onion-console-customization
-      playbook_placeholder_map_custom__yaml:
-        title: Playbook Placeholder Map
-        description: Custom mappings of Playbook %placeholder% tokens to event fields.
-        syntax: yaml
-        file: True
-        global: True
-        advanced: False
         helpLink: security-onion-console-customization
   config:
     licenseKey:
@@ -391,11 +383,6 @@ soc:
             global: True
             advanced: False
             helpLink: sigma
-          useEsql:
-            description: "(Pre-release) Use Elasticsearch Piped Query Language (ES|QL) instead of EQL (Elastic Query Language) for Elasticsearch queries. The Sigma converter will output ES|QL instead of EQL, allowing support for correlations."
-            global: True
-            advanced: True
-            forcedType: bool
         elastic:
           index:
             description: Comma-separated list of indices or index patterns (wildcard "*" supported) that SOC will search for records.
@@ -466,42 +453,6 @@ soc:
             description: Duration (in milliseconds) that must elapse after a grid node fails to check-in before the node will be marked offline (fault).
             global: True
             advanced: True
-        onionconfig:
-          saltstackDir:
-            description: Root directory containing the SaltStack tree that SOC reads and writes configuration from. Should not be changed under normal circumstances.
-            global: True
-            advanced: True
-          bypassEnabled:
-            description: When enabled, errors encountered while reading the SaltStack pillar tree (missing files, unreadable directories, etc.) are logged but do not prevent SOC from starting or serving settings. Intended for advanced troubleshooting and recovery scenarios when the pillar tree is partially unreadable.
-            global: True
-            advanced: True
-            forcedType: bool
-        postgres:
-          host:
-            description: Hostname or IP address of the PostgreSQL server used by SOC. Defaults to the manager hostname.
-            global: True
-            advanced: True
-          port:
-            description: Port of the PostgreSQL server used by SOC.
-            global: True
-            advanced: True
-          sslMode:
-            description: "Use encrypted connections to the PostgreSQL server. Must be one of the following values: disable, allow, prefer, require, verify-ca, verify-full.  Defaults to allow."
-            global: True
-            advanced: True
-          database:
-            description: Database used by SOC to authenticate to the PostgreSQL server.
-            global: True
-            advanced: True
-          user:
-            description: Username used by SOC to authenticate to the PostgreSQL server.
-            global: True
-            advanced: True
-          password:
-            description: Password used by SOC to authenticate to the PostgreSQL server.
-            global: True
-            sensitive: True
-            advanced: True
         salt:
           longRelayTimeoutMs:
             description: Duration (in milliseconds) to wait for a response from the Salt API when executing tasks known for being long running before giving up and showing an error on the SOC UI.
@@ -867,7 +818,6 @@ soc:
           description: List of available external tools visible in the SOC UI. Each tool is defined in JSON object notation, and must include the "name" key and "link" key, where the link is the tool's URL.
           global: True
           advanced: True
-          multiline: True
           forcedType: "[]{}"
         exportNodeId:
           description: The node ID on which export jobs will be executed.

salt/suricata/enabled.sls

@@ -65,11 +65,10 @@ so-suricata:
       - file: suriclassifications
 
 surirulereload:
-  cmd.run:
+  cmd.run: 
     - name: /usr/sbin/so-suricata-reload-rules >> /opt/so/log/suricata/reload.log 2>&1
-    - onchanges:
+    - onchanges: 
         - file: surirulesync
-    - onlyif: test -f /opt/so/rules/suricata/all-rulesets.rules
     - require:
         - docker_container: so-suricata
     

salt/suricata/tools/sbin/so-suricata-reload-rules

@@ -7,59 +7,5 @@
 
 . /usr/sbin/so-common
 
-RULES_FILE="/opt/so/rules/suricata/all-rulesets.rules"
+retry 60 3 'docker exec so-suricata /opt/suricata/bin/suricatasc -c reload-rules /var/run/suricata/suricata-command.socket' '{"message":"done","return":"OK"}' || fail "The Suricata container was not ready in time."
-SOCKET="/var/run/suricata/suricata-command.socket"
+retry 60 3 'docker exec so-suricata /opt/suricata/bin/suricatasc -c ruleset-reload-nonblocking /var/run/suricata/suricata-command.socket' '{"message":"done","return":"OK"}' || fail "The Suricata container was not ready in time."
-SURICATASC="docker exec so-suricata /opt/suricata/bin/suricatasc"
-
-# Format an epoch as a human-readable local timestamp for log messages.
-fmt_time() { date -d "@$1" '+%Y-%m-%d %H:%M:%S %Z' 2>/dev/null; }
-
-# Prefix each input line with the current timestamp.
-timestamp_lines() { while IFS= read -r line; do printf '%s %s\n' "$(date '+%Y-%m-%d %H:%M:%S %Z')" "$line"; done; }
-
-# Epoch of Suricata's last *completed* ruleset reload; non-zero return on failure.
-suricata_reload_epoch() {
-  local out ts
-  out=$($SURICATASC -c ruleset-reload-time "$SOCKET" 2>/dev/null)
-  ts=$(echo "$out" | jq -r '.message[0].last_reload // empty' 2>/dev/null)
-  [ -n "$ts" ] || return 1
-  date -d "$ts" +%s 2>/dev/null
-}
-
-# Trigger a fresh reload and confirm Suricata is running a ruleset at least as new
-# as the rules file. Returns 0 only when both hold, so retry keeps going until an
-# in-progress reload clears and our own reload completes.
-reload_and_verify() {
-  local out reload_epoch
-  out=$($SURICATASC -c reload-rules "$SOCKET")
-  echo "reload-rules: $out"
-
-  if [[ "$out" =~ "Reload already in progress" ]]; then
-    echo "A reload is already in progress; waiting for it to clear so a fresh reload can load the current ruleset."
-    return 1
-  fi
-  if [[ ! "$out" =~ '{"message":"done","return":"OK"}' ]]; then
-    echo "Suricata not ready or unexpected reload output; will retry."
-    return 1
-  fi
-
-  reload_epoch=$(suricata_reload_epoch) || { echo "Could not read ruleset-reload-time; will retry."; return 1; }
-  if [ "$reload_epoch" -ge "$target_mtime" ]; then
-    echo "Loaded ruleset is current: last reload ($(fmt_time "$reload_epoch")) is newer than rules file ($(fmt_time "$target_mtime"))."
-    return 0
-  fi
-  echo "Loaded ruleset is stale: last reload ($(fmt_time "$reload_epoch")) is older than rules file ($(fmt_time "$target_mtime")); retrying."
-  return 1
-}
-
-# Run the reload/verify, timestamping every line of output (ours and the
-# retry/fail helpers') so reload.log shows when each step ran. The pipeline is
-# synchronous, so the log is fully flushed and ordered before we exit; the
-# script's real exit code is preserved via PIPESTATUS.
-{
-  # Epoch mtime of the ruleset we need Suricata to have loaded. Captured once so
-  # a file update mid-reload does not move the goalpost.
-  target_mtime=$(stat -c %Y "$RULES_FILE") || fail "Could not stat the Suricata rules file: $RULES_FILE"
-  retry 60 3 'reload_and_verify' || fail "Suricata did not load the current ruleset in time."
-} 2>&1 | timestamp_lines
-exit "${PIPESTATUS[0]}"

salt/telegraf/etc/telegraf.conf

@@ -244,7 +244,6 @@
   username = "{{ ES_USER }}"
   password = "{{ ES_PASS }}"
   insecure_skip_verify = true
-  cluster_health = true
 {%- elif grains['role'] in ['so-searchnode']  %}
 [[inputs.elasticsearch]]
   servers = ["https://{{ NODEIP }}:9200"]

salt/top.sls

@@ -83,6 +83,7 @@ base:
     - zeek
     - strelka
     - elastalert
+    - utility
     - elasticfleet
     - pcap.cleanup
 
@@ -112,6 +113,7 @@ base:
     - zeek
     - strelka
     - elastalert
+    - utility
     - elasticfleet
     - stig
     - kafka
@@ -139,6 +141,7 @@ base:
     - elastic-fleet-package-registry
     - kibana
     - elastalert
+    - utility
     - elasticfleet
     - stig
     - kafka
@@ -165,6 +168,7 @@ base:
     - elastic-fleet-package-registry
     - kibana
     - elastalert
+    - utility
     - elasticfleet
     - kafka
 
@@ -194,6 +198,7 @@ base:
     - elastic-fleet-package-registry
     - kibana
     - elastalert
+    - utility
     - elasticfleet
     - stig
     - kafka
@@ -217,6 +222,7 @@ base:
     - elasticsearch
     - elastic-fleet-package-registry
     - kibana
+    - utility
     - suricata
     - zeek
     - elasticfleet

salt/utility/bin/eval

@@ -0,0 +1,29 @@
+#!/bin/bash
+# Wait for ElasticSearch to come up, so that we can query for version infromation
+echo -n "Waiting for ElasticSearch..."
+COUNT=0
+ELASTICSEARCH_CONNECTED="no"
+while [[ "$COUNT" -le 30 ]]; do
+  curl -K /opt/so/conf/elasticsearch/curl.config -k --output /dev/null --silent --head --fail -L https://{{ GLOBALS.manager_ip }}:9200
+  if [ $? -eq 0 ]; then
+    ELASTICSEARCH_CONNECTED="yes"
+    echo "connected!"
+    break
+  else
+    ((COUNT+=1))
+    sleep 1
+    echo -n "."
+  fi
+done
+if [ "$ELASTICSEARCH_CONNECTED" == "no" ]; then
+  echo
+  echo -e "Connection attempt timed out.  Unable to connect to ElasticSearch.  \nPlease try: \n  -checking log(s) in /var/log/elasticsearch/\n  -running 'docker ps' \n  -running 'sudo so-elastic-restart'"
+  echo
+
+  exit
+fi
+
+echo "Applying cross cluster search config..."
+    curl -K /opt/so/conf/elasticsearch/curl.config -s -k -XPUT -L https://{{ GLOBALS.manager_ip }}:9200/_cluster/settings \
+         -H 'Content-Type: application/json' \
+         -d "{\"persistent\": {\"search\": {\"remote\": {\"{{ grains.host }}\": {\"seeds\": [\"127.0.0.1:9300\"]}}}}}"

salt/utility/init.sls

@@ -0,0 +1,22 @@
+{% from 'allowed_states.map.jinja' import allowed_states %}
+{% from 'vars/globals.map.jinja' import GLOBALS %}
+
+{% if sls in allowed_states %}
+  {% if grains['role'] in ['so-eval', 'so-import'] %}
+fixsearch:
+  cmd.script:
+    - shell: /bin/bash
+    - cwd: /opt/so
+    - source: salt://utility/bin/eval
+    - template: jinja
+    - defaults:
+        GLOBALS: {{ GLOBALS }}
+  {% endif %}
+
+{% else %}
+
+{{sls}}_state_not_allowed:
+  test.fail_without_changes:
+    - name: {{sls}}_state_not_allowed
+
+{% endif %}

salt/vars/globals.map.jinja

@@ -31,6 +31,7 @@
     'so_model': INIT.GRAINS.get('sosmodel',''),
     'sensoroni_key': INIT.PILLAR.sensoroni.config.sensoronikey,
     'os': INIT.GRAINS.os,
+    'os_version': INIT.GRAINS.osmajorrelease,
     'os_family': INIT.GRAINS.os_family,
     'application_urls': {},
     'manager_roles': [

setup/so-functions

@@ -29,12 +29,8 @@ title() {
 }
 
 fail_setup() {
-	local err_msg=$1
-	if [[ -n "$err_msg" ]]; then
-		error "$err_msg"
-	fi
 	error "Setup encountered an unrecoverable failure, exiting"
-	echo "setup incomplete: $err_msg" > /root/failure
+	touch /root/failure
 	exit 1
 }
 
@@ -543,19 +539,16 @@ configure_minion() {
 		"  x509_v2: true"\
 		"log_level: info"\
 		"log_level_logfile: info"\
-		"log_file: /opt/so/log/salt/minion" >> "$minion_config"
+		"log_file: /opt/so/log/salt/minion"\
+		"#startup_states: highstate" >> "$minion_config"
 
 }
 
-mark_setup_complete() {
+checkin_at_boot() {
-	# Writes the setup-complete marker. Salt's so-boot-highstate.service
+	local minion_config=/etc/salt/minion
-	# (boot-time oneshot) and the so-user_sync cron gate in
-	# salt/manager/sync_es_users.sls both key off this file.
-	local marker=/opt/so/state/setup-complete
 
-	info "Marking setup as complete"
+	info "Enabling checkin at boot"
-	mkdir -p "$(dirname "$marker")"
+	sed -i 's/#startup_states: highstate/startup_states: highstate/' "$minion_config"
-	touch "$marker"
 }
 
 check_requirements() {
@@ -701,7 +694,7 @@ compare_main_nic_ip() {
 			EOM
 
 		  [[ -n $TESTING ]] || whiptail --title "$whiptail_title" --msgbox "$message" 11 75
-		  kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup "Main IP mismatch"
+		  kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup
 	  fi
 	else
 		# Setup uses MAINIP, but since we ignore the equality condition when using a VPN 
@@ -759,7 +752,8 @@ configure_management_bond() {
 	info "Setting up $bond_name management interface with mode $bond_mode"
 
 	if [[ ${#MBNICS[@]} -eq 0 ]]; then
-		fail_setup "No management bond NICs selected"
+		error "[ERROR] No management bond NICs were selected."
+		fail_setup
 	fi
 
 	nmcli -t -f NAME con show | grep -Fxq "$bond_name"
@@ -889,7 +883,6 @@ create_repo() {
 	title "Create the repo directory"
 	logCmd "dnf -y install yum-utils createrepo_c"
 	logCmd "createrepo /nsm/repo"
-	logCmd "createrepo /nsm/kernelrepo"
 }
 
 
@@ -910,14 +903,15 @@ detect_cloud() {
 
 detect_os() {
 	title "Detecting Base OS"
-	if [ -f /etc/redhat-release ] && grep -q "Red Hat Enterprise Linux release 9" /etc/redhat-release && [ -f /etc/oracle-release ]; then
+	if [ -f /etc/oracle-release ] && grep -qE "release (9|10)\b" /etc/oracle-release; then
 		OS=oracle
-		OSVER=9
+		OSVER=$(grep -oE "release [0-9]+" /etc/oracle-release | grep -oE "[0-9]+")
 		is_oracle=true
 		is_rpm=true
 		is_supported=true
 	else
-		fail_setup "This OS is not supported. Security Onion requires Oracle Linux 9."
+		info "This OS is not supported. Security Onion requires Oracle Linux 9 or 10."
+		fail_setup
 	fi
 
 	info "Found OS: $OS $OSVER"
@@ -925,7 +919,7 @@ detect_os() {
 
 download_elastic_agent_artifacts() {
 	if ! update_elastic_agent 2>&1 | tee -a "$setup_log"; then
-		fail_setup "Failed to update Elastic Agent"
+		fail_setup
 	fi
 }
 
@@ -983,8 +977,6 @@ docker_seed_registry() {
 		docker_seed_update_percent=25
 
 		update_docker_containers 'netinstall' '' 'docker_seed_update' '/dev/stdout' 2>&1 | tee -a "$setup_log"
-        # Use pipe exit status of 'update_docker_containers' for return code
-		return ${PIPESTATUS[0]}
 	fi
 }
 
@@ -1569,7 +1561,7 @@ proxy_validate() {
 		error "Received error: $proxy_test_err"
 		if [[ -n $TESTING ]]; then
 			error "Exiting setup"
-			kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup "Proxy validation failed"
+			kill -SIGINT "$(ps --pid $$ -oppid=)"; fail_setup
 		fi
 	fi
 	return $ret
@@ -1776,7 +1768,8 @@ ensure_pyyaml() {
 	local result=$?
 	set +o pipefail
 	if [[ $result -ne 0 ]] || ! rpm -q python3-pyyaml >/dev/null 2>&1; then
-		fail_setup "Failed to install python3-pyyaml (exit=$result)"
+		error "Failed to install python3-pyyaml (exit=$result)"
+		fail_setup
 	fi
 	info "python3-pyyaml installed successfully"
 }
@@ -1790,6 +1783,15 @@ ensure_pyyaml() {
 # - securityonion/salt/salt/minion.defaults.yaml
 
 securityonion_repo() {
+	if [[ "$OSVER" == "10" ]]; then
+		# TEST PATH: Oracle Linux 10 uses the public OL10 + EPEL + Docker CE repos.
+		# Keep the stock /etc/yum.repos.d/* in place, skip the SO mirror and local reposync.
+		gpg_rpm_import
+		logCmd "dnf -y install oracle-epel-release-el10"
+		logCmd "dnf -y config-manager --add-repo https://download.docker.com/linux/rhel/docker-ce.repo"
+		logCmd "dnf repolist"
+		return
+	fi
 	# Remove all the current repos
 	logCmd "dnf -v clean all"
 	logCmd "mkdir -vp /root/oldrepos"
@@ -1814,16 +1816,6 @@ securityonion_repo() {
 			echo "mirrorlist=file:///etc/yum/mirror.txt" >> /etc/yum.repos.d/securityonion.repo
 			echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
-			echo "https://repo.securityonion.net/file/so-repo/prod/3/oracle/9-uek8" > /etc/yum/mirror-kernel.txt
-			echo "https://so-repo-east.s3.us-east-005.backblazeb2.com/prod/3/oracle/9-uek8" >> /etc/yum/mirror-kernel.txt
-			echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
-			echo "name=Security Onion Kernel Repo repo" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "mirrorlist=file:///etc/yum/mirror-kernel.txt" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
-			# Supplementary kernel repo: tolerate it being empty/unreachable so a missing
-			# repomd.xml can't make every dnf operation fail before the repo is populated.
-			echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 			logCmd "dnf repolist"
 		else
 			echo "[securityonion]" > /etc/yum.repos.d/securityonion.repo
@@ -1832,13 +1824,6 @@ securityonion_repo() {
 			echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
 			echo "sslverify=0" >> /etc/yum.repos.d/securityonion.repo
-			echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
-			echo "name=Security Onion Kernel Repo" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "baseurl=https://$MSRV/kernelrepo" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "sslverify=0" >> /etc/yum.repos.d/securityonionkernel.repo
-			echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 			logCmd "dnf repolist"
 		fi
 	elif [[ ! $waitforstate ]]; then
@@ -1848,25 +1833,12 @@ securityonion_repo() {
 		echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
 		echo "sslverify=0" >> /etc/yum.repos.d/securityonion.repo
-		echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
-		echo "name=Security Onion Kernel Repo" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "baseurl=https://$MSRV/kernelrepo" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "sslverify=0" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 	elif [[ $waitforstate ]]; then
 		echo "[securityonion]" > /etc/yum.repos.d/securityonion.repo
 		echo "name=Security Onion Repo" >> /etc/yum.repos.d/securityonion.repo
 		echo "baseurl=file:///nsm/repo/" >> /etc/yum.repos.d/securityonion.repo
 		echo "enabled=1" >> /etc/yum.repos.d/securityonion.repo
 		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonion.repo
-		echo "[securityonionkernel]" > /etc/yum.repos.d/securityonionkernel.repo
-		echo "name=Security Onion Kernel Repo" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "baseurl=file:///nsm/kernelrepo/" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "enabled=1" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "gpgcheck=1" >> /etc/yum.repos.d/securityonionkernel.repo
-		echo "skip_if_unavailable=1" >> /etc/yum.repos.d/securityonionkernel.repo
 	fi
 	logCmd "dnf repolist all"
 	if [[ $waitforstate ]]; then
@@ -1882,12 +1854,9 @@ repo_sync_local() {
 	# Sync the repo from the SO repo locally.
 	info "Adding Repo Download Configuration"
 	mkdir -p /nsm/repo
-	mkdir -p /nsm/kernelrepo
 	mkdir -p /opt/so/conf/reposync/cache
 	echo "https://repo.securityonion.net/file/so-repo/prod/3/oracle/9" > /opt/so/conf/reposync/mirror.txt
 	echo "https://repo-alt.securityonion.net/prod/3/oracle/9" >> /opt/so/conf/reposync/mirror.txt
-	echo "https://repo.securityonion.net/file/so-repo/prod/3/oracle/9-uek8" > /opt/so/conf/reposync/mirror-kernel.txt
-	echo "https://repo-alt.securityonion.net/prod/3/oracle/9-uek8" >> /opt/so/conf/reposync/mirror-kernel.txt
 	echo "[main]" > /opt/so/conf/reposync/repodownload.conf
 	echo "gpgcheck=1" >> /opt/so/conf/reposync/repodownload.conf
 	echo "installonly_limit=3" >> /opt/so/conf/reposync/repodownload.conf
@@ -1901,18 +1870,12 @@ repo_sync_local() {
 	echo "mirrorlist=file:///opt/so/conf/reposync/mirror.txt" >> /opt/so/conf/reposync/repodownload.conf
 	echo "enabled=1" >> /opt/so/conf/reposync/repodownload.conf
 	echo "gpgcheck=1" >> /opt/so/conf/reposync/repodownload.conf
-	echo "[securityonionkernel]" >> /opt/so/conf/reposync/repodownload.conf
-	echo "name=Security Onion Kernel Repo repo" >> /opt/so/conf/reposync/repodownload.conf
-	echo "mirrorlist=file:///opt/so/conf/reposync/mirror-kernel.txt" >> /opt/so/conf/reposync/repodownload.conf
-	echo "enabled=1" >> /opt/so/conf/reposync/repodownload.conf
-	echo "gpgcheck=1" >> /opt/so/conf/reposync/repodownload.conf
 
 	logCmd "dnf repolist"
 
 	if [[ ! $is_airgap ]]; then
 		curl --retry 5 --retry-delay 60 -A "netinstall/$SOVERSION/$OS/$(uname -r)/1" https://sigs.securityonion.net/checkup --output /tmp/install
-		retry 5 60 "dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionsync --download-metadata -p /nsm/repo/" >> "$setup_log" 2>&1 || fail_setup "Failed to sync repos"
+		retry 5 60 "dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionsync --download-metadata -p /nsm/repo/" >> "$setup_log" 2>&1 || fail_setup
-		retry 5 60 "dnf reposync --norepopath -g --delete -m -c /opt/so/conf/reposync/repodownload.conf --repoid=securityonionkernel --download-metadata -p /nsm/kernelrepo/" >> "$setup_log" 2>&1 || fail_setup "Failed to sync kernel repos"
 		# After the download is complete run createrepo
 		create_repo
 	fi
@@ -1923,12 +1886,19 @@ saltify() {
 	info "Installing Salt $SALTVERSION"
 	chmod u+x ../salt/salt/scripts/bootstrap-salt.sh
 
+	# Normally Salt packages come from the SO mirror, so -r disables the bootstrap's own repo setup.
+	# On the OL10 test path there is no SO mirror, so let bootstrap configure the public Salt repo.
+	local saltrepoflag="-r"
+	if [[ "$OSVER" == "10" ]]; then
+		saltrepoflag=""
+	fi
+
 	if [[ $waitforstate ]]; then
 		# install all for a manager
-		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh -r -M -X stable $SALTVERSION" || fail_setup "Failed to install salt master"
+		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh $saltrepoflag -M -X stable $SALTVERSION" || fail_setup
 	else
 		# just a minion
-		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh -r -X stable $SALTVERSION" || fail_setup "Failed to install salt minion"
+		retry 30 10 "bash ../salt/salt/scripts/bootstrap-salt.sh $saltrepoflag -X stable $SALTVERSION" || fail_setup
 	fi
 
 	salt_install_module_deps
@@ -2000,7 +1970,7 @@ set_main_ip() {
 			info "MAINIP=$MAINIP"
 			info "MNIC_IP=$MNIC_IP"
 			whiptail_error_message "The management IP could not be determined. Please check the log at /root/sosetup.log and verify the network configuration. Select OK to exit."
-			fail_setup "Could not determine MAINIP or MNIC_IP"
+			fail_setup
 		fi
 		sleep 1
 	done
@@ -2204,7 +2174,7 @@ set_initial_firewall_access() {
 set_management_interface() {
 	title "Setting up the main interface"
 	if [[ $MNIC == "bond1" ]]; then
-		configure_management_bond || fail_setup "Failed to configure management bond"
+		configure_management_bond || fail_setup
 	fi
 
 	if [ "$address_type" = 'DHCP' ]; then
@@ -2269,13 +2239,6 @@ update_sudoers_for_testing() {
 }
 
 update_packages() {
-	# Pin physical NIC names by MAC BEFORE pulling packages, so the UEK8 kernel that
-	# the update below installs can't renumber the interfaces SO binds by name. Doing
-	# it here (instead of waiting for the common highstate) also drops the
-	# /opt/so/state/nic_names_pinned marker that gates the kernel repo, so the kernel
-	# repo is assigned on the very first highstate and the kernel isn't downgraded and
-	# then re-upgraded. Run-once: so-nic-pin no-ops if the marker already exists.
-	logCmd "bash ../salt/common/tools/sbin/so-nic-pin"
 	logCmd "dnf repolist"
 	logCmd "dnf -y update --allowerasing --exclude=salt*,docker*,containerd*"
 	RMREPOFILES=("oracle-linux-ol9.repo" "uek-ol9.repo" "virt-ol9.repo")

setup/so-setup

@@ -9,17 +9,14 @@
 # Make sure you are root before doing anything
 uid="$(id -u)"
 if [ "$uid" -ne 0 ]; then
-	echo "This script must be run using sudo!" >&2
+	echo "This script must be run using sudo!"
-	exit 1
+	fail_setup
 fi
 
 # Save the original argument array since we modify it
 original_args=("$@")
 
-cd "$(dirname "$0")" || {
+cd "$(dirname "$0")" || fail_setup
-	echo "Unable to change to setup directory" >&2
-	exit 1
-}
 
 echo "Getting started..."
 
@@ -90,7 +87,8 @@ if [[ "$setup_type" == 'iso' ]]; then
 	if [[ $is_rpm ]]; then
 		is_iso=true
 	else
-		fail_setup "Only use 'so-setup iso' for an ISO install on Security Onion ISO images. Please run 'so-setup network' instead."
+		echo "Only use 'so-setup iso' for an ISO install on Security Onion ISO images. Please run 'so-setup network' instead."
+		fail_setup
 	fi
 fi
 
@@ -129,7 +127,7 @@ catch() {
 	info "Fatal error occurred at $1 in so-setup, failing setup."
 	grep --color=never "ERROR" "$setup_log" > "$error_log"
 	whiptail_setup_failed
-	fail_setup "Fatal error occurred at $1 in so-setup"
+	fail_setup
 }
 
 # Add the progress function for manager node type installs
@@ -225,8 +223,6 @@ if [ -n "$test_profile" ]; then
 	WEBPASSWD1=0n10nus3r
 	WEBPASSWD2=0n10nus3r
 	NODE_DESCRIPTION="${HOSTNAME} - ${install_type} - ${MSRVIP_OFFSET}"
-	# opt out of telemetry for automated testing
-	telemetry=1
 
 	update_sudoers_for_testing
 fi
@@ -237,7 +233,8 @@ case "$setup_type" in
 		info "Beginning Security Onion $setup_type install"
 		;;
 	*)
-		fail_setup "Invalid install type, must be 'iso', 'network' or 'desktop'."
+		error "Invalid install type, must be 'iso', 'network' or 'desktop'."
+		fail_setup
 		;;
 esac
 
@@ -770,9 +767,7 @@ if ! [[ -f $install_opt_file ]]; then
 		title "Applying the registry state"
 		logCmd "salt-call state.apply -l info registry"
 		title "Seeding the docker registry"
-		if ! docker_seed_registry; then
+		docker_seed_registry
-			fail_setup "Failed to seed the docker registry"
-		fi
 		title "Applying the manager state"
 		logCmd "salt-call state.apply -l info manager"
 		logCmd "salt-call state.apply influxdb -l info"
@@ -794,9 +789,10 @@ if ! [[ -f $install_opt_file ]]; then
 		title "Setting up Elastic Fleet"
 		logCmd "salt-call state.apply elasticfleet.config"	
 		if ! logCmd so-elastic-fleet-setup; then
-			fail_setup "Failed to run so-elastic-fleet-setup"
+			error "Failed to run so-elastic-fleet-setup"
+			fail_setup
 		fi
-		mark_setup_complete
+		checkin_at_boot
 		set_initial_firewall_access
         initialize_elasticsearch_indices "so-case so-casehistory so-assistant-session so-assistant-chat"
 		# run a final highstate before enabling scheduled highstates. 

setup/so-verify

@@ -143,15 +143,15 @@ main() {
         cat $error_log
         echo "--------------------------"
         exit_code=1
-        echo "Found setup errors. Check $error_log for details" > /root/failure
+        touch /root/failure
     elif using_iso && cron_error_in_mail_spool; then
         echo "WARNING: Unexpected cron job output in mail spool"
         exit_code=1
-        echo "Unexpected cron job output found in /var/spool/mail/" > /root/failure
+        touch /root/failure
     elif is_manager_node && status_failed; then
         echo "WARNING: Containers are not in a healthy state"
         exit_code=1
-        echo "Containers are not in a healthy state. Check so-status for details" > /root/failure
+        touch /root/failure
     else
         echo "Successfully completed setup!"
         touch /root/success