Merge pull request #15937 from Security-Onion-Solutions/hotfix/3.1.0

Hotfix/3.1.0

DOWNLOAD_AND_VERIFY_ISO.md

@@ -1,17 +1,17 @@
-### 3.0.0-20260331 ISO image released on 2026/03/31
+### 3.1.0-20260528 ISO image released on 2026/05/28
 
 
 ### Download and Verify
 
-3.0.0-20260331 ISO image:  
-https://download.securityonion.net/file/securityonion/securityonion-3.0.0-20260331.iso
+3.1.0-20260528 ISO image:  
+https://download.securityonion.net/file/securityonion/securityonion-3.1.0-20260528.iso
  
-MD5: ECD318A1662A6FDE0EF213F5A9BD4B07  
-SHA1: E55BE314440CCF3392DC0B06BC5E270B43176D9C  
-SHA256: 7FC47405E335CBE5C2B6C51FE7AC60248F35CBE504907B8B5A33822B23F8F4D5  
+MD5: 9D6FF58DEEE24089D722C73169765B3E  
+SHA1: 2B8B816B6CEC3B7F96B3C5E040EBF502DD2C412F  
+SHA256: 62FAB57E247C843D6A04F0796D8162C732B65D82FC3E4A59D087135B9FD32912  
 
 Signature for ISO image:  
-https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.0.0-20260331.iso.sig
+https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.1.0-20260528.iso.sig
 
 Signing key:  
 https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/main/KEYS  
@@ -25,22 +25,22 @@ wget https://raw.githubusercontent.com/Security-Onion-Solutions/securityonion/3/
 
 Download the signature file for the ISO:  
 ```
-wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.0.0-20260331.iso.sig
+wget https://github.com/Security-Onion-Solutions/securityonion/raw/3/main/sigs/securityonion-3.1.0-20260528.iso.sig
 ```
 
 Download the ISO image:  
 ```
-wget https://download.securityonion.net/file/securityonion/securityonion-3.0.0-20260331.iso
+wget https://download.securityonion.net/file/securityonion/securityonion-3.1.0-20260528.iso
 ```
 
 Verify the downloaded ISO image using the signature file:  
 ```
-gpg --verify securityonion-3.0.0-20260331.iso.sig securityonion-3.0.0-20260331.iso
+gpg --verify securityonion-3.1.0-20260528.iso.sig securityonion-3.1.0-20260528.iso
 ```
 
 The output should show "Good signature" and the Primary key fingerprint should match what's shown below:
 ```
-gpg: Signature made Mon 30 Mar 2026 06:22:14 PM EDT using RSA key ID FE507013
+gpg: Signature made Wed 27 May 2026 03:03:59 PM EDT using RSA key ID FE507013
 gpg: Good signature from "Security Onion Solutions, LLC <info@securityonionsolutions.com>"
 gpg: WARNING: This key is not certified with a trusted signature!
 gpg:          There is no indication that the signature belongs to the owner.

HOTFIX

@@ -0,0 +1 @@
+20260528

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

@@ -165,6 +165,8 @@ if [[ $EXCLUDE_FALSE_POSITIVE_ERRORS == 'Y' ]]; then
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|upgrading component template"  # false positive (elasticsearch index or template names contain 'error')
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|upgrading composable template" # false positive (elasticsearch composable template names contain 'error')
     EXCLUDED_ERRORS="$EXCLUDED_ERRORS|Error while parsing document for index \[.ds-logs-kratos-so-.*object mapping for \[file\]" # false positive (mapping error occuring BEFORE kratos index has rolled over in 2.4.210)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|No such container"            # false positive (telegraf trying to run stats on an old container)
+    EXCLUDED_ERRORS="$EXCLUDED_ERRORS|passwords do not match"       # false positive (automated hydra test)
 fi
 
 if [[ $EXCLUDE_KNOWN_ERRORS == 'Y' ]]; then

salt/elasticfleet/enabled.sls

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

salt/elasticsearch/defaults.yaml

@@ -3958,10 +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

salt/elasticsearch/files/ingest/zeek.ja4d

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

salt/manager/tools/sbin/soup

@@ -533,6 +533,23 @@ elasticfleet_set_agent_logging_level_warn() {
     done <<< "$policies_to_update"
 }
 
+update_logstash_pipeline_name() {
+    local original_pipeline_name="$1"
+    local new_pipeline_name="$2"
+
+    echo "Checking for conflicting logstash defined_pipelines pillar value."
+    local LOGSTASH_FILE=/opt/so/saltstack/local/pillar/logstash/soc_logstash.sls
+    local MINIONDIR=/opt/so/saltstack/local/pillar/minions
+    for pillar_file in "$LOGSTASH_FILE" "$MINIONDIR"/*.sls; do
+        [[ -f "$pillar_file" ]] || continue
+        if grep -q "$original_pipeline_name$" "$pillar_file"; then
+            echo "Found conflicting defined_pipeline pillar value in $pillar_file. Updating to use the new logstash pipeline name."
+            sed -i "s#$original_pipeline_name\$#$new_pipeline_name#g" "$pillar_file"
+            chown socore:socore "$pillar_file"
+        fi
+    done
+}
+
 check_transform_health_and_reauthorize() {
     . /usr/sbin/so-elastic-fleet-common
 
@@ -676,6 +693,10 @@ rename_strelka_scan_lnk() {
   rm -f "$TMP_VALUE_FILE"
 }
 
+fix_logstash_0013_lumberjack_pipeline_name() {
+    update_logstash_pipeline_name "so/0013_input_lumberjack_fleet.conf" "so/0013_input_lumberjack_fleet.conf.jinja"
+}
+
 up_to_3.1.0() {
   ensure_postgres_local_pillar
   ensure_postgres_secret
@@ -684,6 +705,7 @@ up_to_3.1.0() {
   # Clear existing component template state file.
   rm -f /opt/so/state/esfleet_component_templates.json
   rename_strelka_scan_lnk
+  fix_logstash_0013_lumberjack_pipeline_name
 
   INSTALLEDVERSION=3.1.0
 }
@@ -971,6 +993,9 @@ verify_es_version_compatibility() {
     local is_active_intermediate_upgrade=1
     # supported upgrade paths for SO-ES versions
     declare -A es_upgrade_map=(
+        ["8.18.4"]="8.18.6 8.18.8 9.0.8"
+	    ["8.18.6"]="8.18.8 9.0.8"
+	    ["8.18.8"]="9.0.8"
         ["9.0.8"]="9.3.3"
     )
 
@@ -994,6 +1019,171 @@ verify_es_version_compatibility() {
         exit 160
     fi
 
+    compatible_es_versions="$target_es_version"
+    for current_version in "${!es_upgrade_map[@]}"; do
+        # shellcheck disable=SC2076
+        if [[ " ${es_upgrade_map[$current_version]} " =~ " $target_es_version " ]]; then
+            compatible_es_versions+=" $current_version"
+        fi
+    done
+
+    # Check if the given ES version can directly upgrade to the target ES version. Used to assist with catching lagging nodes during the upgrade process
+    es_version_can_upgrade_to_target() {
+        local current_version="$1"
+        # shellcheck disable=SC2076
+        if [[ -n "$current_version" && " $compatible_es_versions " =~ " $current_version " ]]; then
+            return 0
+        fi
+
+        return 1
+    }
+
+    # Gather Elasticsearch cluster version info and verify that each node in the cluster is running a version compatible with the target ES version.
+    verify_searchnodes_es_target_compatibility() {
+        local retries=20
+        local retry_count=0
+        local delay=180
+        local expected_es_nodes searchnode_minions attempt
+        local searchnode_discovery_success=false
+        SEARCHNODE_ES_VERSIONS=""
+
+        for attempt in {1..3}; do
+            if searchnode_minions=$(set -o pipefail; salt-key --out=json --list=accepted 2> /dev/null | jq -r '.minions[]? | select(endswith("searchnode"))'); then
+                searchnode_discovery_success=true
+                break
+            fi
+
+            echo "Failed to retrieve grid searchnodes via salt-key... Retrying in 30 seconds. Attempt $attempt of 3."
+            sleep 30
+        done
+
+        if [[ "$searchnode_discovery_success" != "true" ]]; then
+            echo "Failed to retrieve grid searchnodes via salt-key."
+            return 1
+        fi
+
+        # Always add node running soup to expected es nodes
+        expected_es_nodes="${MINIONID%_*}"
+        while IFS= read -r searchnode_minion; do
+            [[ -z "$searchnode_minion" ]] && continue
+            expected_es_nodes+=$'\n'"${searchnode_minion%_searchnode}"
+        done <<< "$searchnode_minions"
+
+        while [[ $retry_count -lt $retries ]]; do
+            SEARCHNODE_ES_VERSIONS=$(so-elasticsearch-query _nodes/_all/version --retry 5 --retry-delay 10 --fail 2>&1)
+            local exit_status=$?
+
+            if [[ $exit_status -ne 0 ]]; then
+                echo "Failed to retrieve Elasticsearch versions from searchnodes... Retrying in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+                ((retry_count++))
+                sleep $delay
+                continue
+            fi
+
+            local all_searchnodes_compatible=true
+            while IFS=$'\t' read -r node current_version; do
+                [[ -z "$node" ]] && continue
+                if ! es_version_can_upgrade_to_target "$current_version"; then
+                    echo "Searchnode $node is running Elasticsearch $current_version, which is not directly upgradable to Elasticsearch $target_es_version."
+                    all_searchnodes_compatible=false
+                fi
+            done < <(echo "$SEARCHNODE_ES_VERSIONS" | jq -r '.nodes | to_entries[] | [.value.name, .value.version] | @tsv')
+
+            while IFS= read -r expected_es_node; do
+                [[ -z "$expected_es_node" ]] && continue
+                if ! echo "$SEARCHNODE_ES_VERSIONS" | jq -e --arg node "$expected_es_node" '.nodes | to_entries | any(.value.name == $node)' > /dev/null; then
+                    echo "Searchnode $expected_es_node did not report an Elasticsearch version. It may be offline or still upgrading."
+                    all_searchnodes_compatible=false
+                fi
+            done <<< "$expected_es_nodes"
+
+            if [[ "$all_searchnodes_compatible" == true ]]; then
+                echo "All Searchnodes are upgradable to Elasticsearch $target_es_version."
+                return 0
+            fi
+
+            echo "One or more Searchnodes cannot upgrade directly to Elasticsearch $target_es_version. Rechecking in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+            ((retry_count++))
+            sleep $delay
+        done
+
+        return 1
+    }
+
+    # Gather heavynode version info and verify that each node is running a version compatible with the target ES version.
+    verify_heavynodes_es_target_compatibility() {
+        local heavynode_minions attempt
+        local retries=20
+        local retry_count=0
+        local delay=180
+        local heavynode_discovery_success=false
+        HEAVYNODE_ES_VERSIONS=""
+
+        for attempt in {1..3}; do
+            if heavynode_minions=$(set -o pipefail; salt-key --out=json --list=accepted 2> /dev/null | jq -r '.minions[]? | select(endswith("heavynode"))'); then
+                heavynode_discovery_success=true
+                break
+            fi
+
+            echo "Failed to retrieve grid heavynodes via salt-key... Retrying in 30 seconds. Attempt $attempt of 3."
+            sleep 30
+        done
+
+        if [[ "$heavynode_discovery_success" != "true" ]]; then
+            echo "Failed to retrieve grid heavynodes via salt-key."
+            return 1
+        fi
+
+        if [[ -z "$heavynode_minions" ]]; then
+            echo "No heavynodes detected. Skipping heavynode Elasticsearch version compatibility check."
+            return 0
+        fi
+
+        while [[ $retry_count -lt $retries ]]; do
+            HEAVYNODE_ES_VERSIONS=$(salt -C 'G@role:so-heavynode' cmd.run 'set -o pipefail; so-elasticsearch-query / --retry 5 --retry-delay 10 | jq -er ".version.number"' shell=/bin/bash --out=json 2> /dev/null)
+            local exit_status=$?
+
+            if [[ $exit_status -ne 0 ]]; then
+                echo "Failed to retrieve Elasticsearch version from one or more heavynodes... Retrying in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+                ((retry_count++))
+                sleep $delay
+                continue
+            fi
+
+            local all_heavynodes_compatible=true
+            while IFS=$'\t' read -r node current_version; do
+                [[ -z "$node" ]] && continue
+                if ! es_version_can_upgrade_to_target "$current_version"; then
+                    echo "Heavynode $node is running Elasticsearch $current_version, which is not directly upgradable to Elasticsearch $target_es_version."
+                    all_heavynodes_compatible=false
+                fi
+            done < <(echo "$HEAVYNODE_ES_VERSIONS" | jq -r 'to_entries[] | [.key, .value] | @tsv')
+
+            while IFS= read -r heavynode_minion; do
+                [[ -z "$heavynode_minion" ]] && continue
+                if ! echo "$HEAVYNODE_ES_VERSIONS" | jq -se --arg minion "$heavynode_minion" 'add | has($minion)' > /dev/null; then
+                    echo "Heavynode $heavynode_minion did not report an Elasticsearch version. It may be offline or still upgrading."
+                    all_heavynodes_compatible=false
+                fi
+            done <<< "$heavynode_minions"
+
+            if [[ "$all_heavynodes_compatible" == true ]]; then
+                echo -e "\nAll heavynodes can upgrade to Elasticsearch $target_es_version."
+                return 0
+            fi
+
+            echo "One or more heavynodes cannot upgrade directly to Elasticsearch $target_es_version. Rechecking in $delay seconds. Attempt $((retry_count + 1)) of $retries."
+            ((retry_count++))
+            sleep $delay
+        done
+
+        return 1
+    }
+
+    if [[ ! -f "$es_verification_script" ]]; then
+        create_intermediate_upgrade_verification_script "$es_verification_script"
+    fi
+
     for statefile in "${es_required_version_statefile_base}"-*; do
         [[ -f $statefile ]] || continue
 
@@ -1012,10 +1202,6 @@ verify_es_version_compatibility() {
             continue
         fi
 
-        if [[ ! -f "$es_verification_script" ]]; then
-            create_intermediate_upgrade_verification_script "$es_verification_script"
-        fi
-
         echo -e "\n##############################################################################################################################\n"
         echo "A previously required intermediate Elasticsearch upgrade was detected. Verifying that all Searchnodes/Heavynodes have successfully upgraded Elasticsearch to $es_required_version_statefile_value before proceeding with soup to avoid potential data loss! This command can take up to an hour to complete."
         if ! timeout --foreground 4000 bash "$es_verification_script" "$es_required_version_statefile_value" "$statefile"; then
@@ -1037,6 +1223,26 @@ verify_es_version_compatibility() {
 
     # shellcheck disable=SC2076 # Do not want a regex here eg usage " 8.18.8 9.0.8 " =~ " 9.0.8 "
     if [[ " ${es_upgrade_map[$es_version]} " =~ " $target_es_version " || "$es_version" == "$target_es_version" ]]; then
+        if ! verify_searchnodes_es_target_compatibility || ! verify_heavynodes_es_target_compatibility; then
+            echo -e "\n!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+
+            echo "One or more Searchnode(s)/Heavynode(s) cannot upgrade directly to Elasticsearch $target_es_version. This can happen with soups that include Elasticsearch upgrades being run in quick succession. Typically, this will resolve itself as the grid synchronizes. Please allow time for all Searchnodes/Heavynodes to have upgraded Elasticsearch to a compatible version with $target_es_version before running soup again to avoid potential data loss!"
+
+            if [[ -n "$HEAVYNODE_ES_VERSIONS" ]]; then
+                echo "Current heavynode Elasticsearch versions:"
+                echo "$HEAVYNODE_ES_VERSIONS" | jq '.'
+            fi
+
+            if [[ -n "$SEARCHNODE_ES_VERSIONS" ]]; then
+                echo "Current searchnode Elasticsearch versions:"
+                echo "$SEARCHNODE_ES_VERSIONS" | jq '.nodes | to_entries | map({(.value.name): .value.version}) | sort | add'
+            fi
+
+            echo -e "\n!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!\n"
+
+            exit 161
+        fi
+
         # supported upgrade
         return 0
     else
@@ -1322,7 +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() {
@@ -1394,7 +1606,7 @@ main() {
   echo "Verifying we have the latest soup script."
   verify_latest_update_script
 
-  echo "Verifying Elasticsearch version compatibility before upgrading."
+  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."

salt/nginx/etc/nginx.conf

@@ -225,6 +225,7 @@ http {
 			limit_req             zone=auth_throttle burst={{ NGINXMERGED.config.throttle_login_burst }} nodelay;
 			limit_req_status      429;
 			proxy_pass            http://{{ GLOBALS.manager }}:4433;
+			proxy_set_header      Connection "Close";
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;
 			proxy_set_header      Host $host;
@@ -237,6 +238,7 @@ http {
 		location ~ ^/auth/.*?(whoami|logout|settings|errors|webauthn.js) {
 			rewrite               /auth/(.*) /$1 break;
 			proxy_pass            http://{{ GLOBALS.manager }}:4433;
+			proxy_set_header      Connection "Close";
 			proxy_read_timeout    90;
 			proxy_connect_timeout 90;
 			proxy_set_header      Host $host;

salt/postgres/config.sls

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

salt/postgres/enabled.sls

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

salt/postgres/telegraf_users.sls

@@ -39,17 +39,15 @@ postgres_wait_ready:
     - require:
       - docker_container: so-postgres
 
-# Ensure the shared Telegraf database exists. init-users.sh only runs on a
+# Ensure the shared Telegraf database exists. init-db.sh only runs on a
 # fresh data dir, so hosts upgraded onto an existing /nsm/postgres volume
 # would otherwise never get so_telegraf.
 postgres_create_telegraf_db:
   cmd.run:
-    - name: |
-        if ! docker exec so-postgres psql -U postgres -tAc "SELECT 1 FROM pg_database WHERE datname='so_telegraf'" | grep -q 1; then
-          docker exec so-postgres psql -v ON_ERROR_STOP=1 -U postgres -c "CREATE DATABASE so_telegraf"
-        fi
+    - name: /usr/sbin/so-telegraf-postgres create_db
     - require:
       - cmd: postgres_wait_ready
+      - file: postgres_sbin
 
 # Provision the shared group role and schema once. Every per-minion role is a
 # member of so_telegraf, and each Telegraf connection does SET ROLE so_telegraf
@@ -57,68 +55,26 @@ postgres_create_telegraf_db:
 # on first write are owned by the group role and every member can INSERT/SELECT.
 postgres_telegraf_group_role:
   cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
-        DO $$
-        BEGIN
-            IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = 'so_telegraf') THEN
-                CREATE ROLE so_telegraf NOLOGIN;
-            END IF;
-        END
-        $$;
-        GRANT CONNECT ON DATABASE so_telegraf TO so_telegraf;
-        CREATE SCHEMA IF NOT EXISTS telegraf AUTHORIZATION so_telegraf;
-        GRANT USAGE, CREATE ON SCHEMA telegraf TO so_telegraf;
-        CREATE SCHEMA IF NOT EXISTS partman;
-        CREATE EXTENSION IF NOT EXISTS pg_partman SCHEMA partman;
-        CREATE EXTENSION IF NOT EXISTS pg_cron;
-        -- Telegraf (running as so_telegraf) calls partman.create_parent()
-        -- on first write of each metric, which needs USAGE on the partman
-        -- schema, EXECUTE on its functions/procedures, and write access to
-        -- partman.part_config so it can register new partitioned parents.
-        GRANT USAGE, CREATE ON SCHEMA partman TO so_telegraf;
-        GRANT SELECT, INSERT, UPDATE, DELETE ON ALL TABLES IN SCHEMA partman TO so_telegraf;
-        GRANT EXECUTE ON ALL FUNCTIONS IN SCHEMA partman TO so_telegraf;
-        GRANT EXECUTE ON ALL PROCEDURES IN SCHEMA partman TO so_telegraf;
-        -- partman creates per-parent template tables (partman.template_*) at
-        -- runtime; default privileges extend DML/sequence access to them.
-        ALTER DEFAULT PRIVILEGES IN SCHEMA partman
-            GRANT SELECT, INSERT, UPDATE, DELETE ON TABLES TO so_telegraf;
-        ALTER DEFAULT PRIVILEGES IN SCHEMA partman
-            GRANT USAGE, SELECT, UPDATE ON SEQUENCES TO so_telegraf;
-        -- Hourly partman maintenance. cron.schedule is idempotent by jobname.
-        SELECT cron.schedule(
-          'telegraf-partman-maintenance',
-          '17 * * * *',
-          'CALL partman.run_maintenance_proc()'
-        );
-        EOSQL
+    - name: /usr/sbin/so-telegraf-postgres group_role
     - require:
       - cmd: postgres_create_telegraf_db
+      - file: postgres_sbin
 
 {%   set creds = salt['pillar.get']('telegraf:postgres_creds', {}) %}
 {%   for mid, entry in creds.items() %}
 {%     if entry.get('user') and entry.get('pass') %}
 {%       set u = entry.user %}
-{%       set p = entry.pass | replace("'", "''") %}
+{%       set p = entry.pass %}
 
 postgres_telegraf_role_{{ u }}:
   cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
-        DO $$
-        BEGIN
-            IF NOT EXISTS (SELECT FROM pg_catalog.pg_roles WHERE rolname = '{{ u }}') THEN
-                EXECUTE format('CREATE ROLE %I WITH LOGIN PASSWORD %L', '{{ u }}', '{{ p }}');
-            ELSE
-                EXECUTE format('ALTER ROLE %I WITH PASSWORD %L', '{{ u }}', '{{ p }}');
-            END IF;
-        END
-        $$;
-        GRANT CONNECT ON DATABASE so_telegraf TO "{{ u }}";
-        GRANT so_telegraf TO "{{ u }}";
-        EOSQL
+    - name: /usr/sbin/so-telegraf-postgres user
+    - env:
+      - ROLE_USER: {{ u | tojson }}
+      - ROLE_PASS: {{ p | tojson }}
+    - hide_output: True
     - require:
+      - file: postgres_sbin
       - cmd: postgres_telegraf_group_role
 
 {%     endif %}
@@ -130,21 +86,12 @@ postgres_telegraf_role_{{ u }}:
 {%   set retention = salt['pillar.get']('postgres:telegraf:retention_days', 14) | int %}
 postgres_telegraf_retention_reconcile:
   cmd.run:
-    - name: |
-        docker exec -i so-postgres psql -v ON_ERROR_STOP=1 -U postgres -d so_telegraf <<'EOSQL'
-        DO $$
-        BEGIN
-            IF EXISTS (SELECT 1 FROM pg_catalog.pg_extension WHERE extname = 'pg_partman') THEN
-                UPDATE partman.part_config
-                SET retention = '{{ retention }} days',
-                    retention_keep_table = false
-                WHERE parent_table LIKE 'telegraf.%';
-            END IF;
-        END
-        $$;
-        EOSQL
+    - name: /usr/sbin/so-telegraf-postgres retention
+    - env:
+      - RETENTION_DAYS: {{ retention }}
     - require:
       - cmd: postgres_telegraf_group_role
+      - file: postgres_sbin
 
 {% endif %}
 

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

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

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

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

salt/strelka/defaults.yaml

@@ -261,7 +261,7 @@ strelka:
               priority: 5
               options:
                 limit: 1000
-          'ScanLNK':
+          'ScanLnk':
             - positive:
                 flavors:
                   - 'lnk_file'

salt/strelka/soc_strelka.yaml

@@ -99,7 +99,7 @@ strelka:
           'ScanJpeg': *scannerOptions
           'ScanJson': *scannerOptions
           'ScanLibarchive': *scannerOptions
-          'ScanLNK': *scannerOptions
+          'ScanLnk': *scannerOptions
           'ScanLsb': *scannerOptions
           'ScanLzma': *scannerOptions
           'ScanMacho': *scannerOptions

salt/telegraf/defaults.yaml

@@ -1,6 +1,6 @@
 telegraf:
   enabled: False
-  output: BOTH
+  output: INFLUXDB
   config:
     interval: '30s'
     metric_batch_size: 1000

salt/top.sls

@@ -119,7 +119,7 @@ base:
     - kafka
     - pcap.cleanup
 
-  '*_manager or *_managerhype and G@saltversion:{{saltversion}} and not I@node_data:False':
+  '*_manager and G@saltversion:{{saltversion}} and not I@node_data:False':
     - match: compound
     - salt.master
     - registry
@@ -146,6 +146,32 @@ base:
     - stig
     - kafka
 
+  '*_managerhype and G@saltversion:{{saltversion}} and not I@node_data:False':
+    - match: compound
+    - salt.master
+    - registry
+    - nginx
+    - influxdb
+    - postgres
+    - strelka.manager
+    - soc
+    - kratos
+    - hydra
+    - firewall
+    - manager
+    - sensoroni
+    - telegraf
+    - backup.config_backup
+    - elasticsearch
+    - logstash
+    - redis
+    - elastic-fleet-package-registry
+    - kibana
+    - elastalert
+    - utility
+    - elasticfleet
+    - kafka
+
   '*_managerhype and I@features:vrt and G@saltversion:{{saltversion}}':
     - match: compound
     - manager.hypervisor
@@ -286,7 +312,6 @@ base:
     - libvirt
     - libvirt.images
     - elasticfleet.install_agent_grid
-    - stig
   
   '*_desktop and G@saltversion:{{saltversion}}':
     - sensoroni