Fbnoroot2

.github/workflows/build-artifact/ARTIFACT_INVENTORY.template

@@ -16,9 +16,9 @@ registry/repository/image_name:version
 
 | Subsystem| Component | Fully Qualified Container-Image Name (registry/repository/image_name:version)|
 |----|----|----|
-| Logging | BusyBox (OpenSearch) | __OS_SYSCTL_FULL_IMAGE__ |
 | Logging | Fluent Bit | __FB_FULL_IMAGE__ |
 | Logging | Elasticsearch Exporter | __ES_EXPORTER_FULL_IMAGE__ |
+| Logging | initContainer (Fluent Bit, OpenSearch) | __OS_SYSCTL_FULL_IMAGE__ |
 | Logging | OpenSearch | __OS_FULL_IMAGE__ |
 | Logging | OpenSearch Dashboards| __OSD_FULL_IMAGE__ |
 | Metrics | Alertmanager | __ALERTMANAGER_FULL_IMAGE__ |

CHANGELOG.md

@@ -1,5 +1,22 @@
 # SAS Viya Monitoring for Kubernetes
 
+## Unreleased
+* **Logging**
+  * [SECURITY] Fluent Bit log collecting pods no longer run as `root` user.  In addition, the database used to
+maintain state information for the log collector has moved to a hostPath volume and been renamed. A new initContainer
+has been added to handle migrating any existing state information and make adjustments to file ownership/permissions.
+NOTE: This initContainer runs under as `root` user but only runs briefly during the initial deployment process.
+  * [SECURITY] OpenSearch pods has been reconfigured to allow `readOnlyRootFilesystem` to be set to 'true'. A
+new initContainer has been added to facilitate this.
+  * [SECURITY] Runtime security controls for log monitoring stack (i.e. Fluent Bit, OpenSearch, OpenSearch
+Dashboards and Elasticsearch Exporter) pods have been tightened.  Changes include: adding seccompProfile; 
+and disallowing privileged containers, privilege escalation and removing all Linux capabilities.  As noted
+above, some initContainers require less restrictive security but these only run briefly during the initial
+deployment process.
+  * [SECURITY] On OpenShift, all Fluent Bit pods now use custom SCC objects to support changes described above.
+  * [CHANGE] Improved handling of long log messages and those from some Crunchy Data pods
+
+
 ## Version 1.2.32 (09DEC2024)
 * **Overall**
   * [CHANGE] Comments added to user.env files within samples/generic-base to clarify security best-practices; other
@@ -8,6 +25,7 @@ cleanup.
   * [SECURITY] Set `seccompProfile` to `RuntimeDefault` for OpenSearch, OpenSearch Dashboards and Fluent Bit pods in
 non-OpenShift environments.
 
+
 ## Version 1.2.31 (15NOV2024)
 * **Logging**
   * [UPGRADE] OpenSearch and OpenSearch Dashboards upgraded from 2.15.0 to 2.17.1
@@ -16,6 +34,7 @@ required a new serviceMonitor (elasticsearch-v2) be deployed.
   * [UPGRADE] Fluent Bit upgraded from 3.1.3 to 3.1.9
   * [UPGRADE] OpenSearch Data Source Plugin to Grafana upgraded from 2.18.0 to 2.21.1
 
+
 ## Version 1.2.30 (11OCT2024)
 * **Logging**
   * [SECURITY] OpenSearch Dashboards pod `securityContext` updated to set allowPrivilegeEscalation to 'false'

bin/common.sh

@@ -289,7 +289,11 @@ function generateImageKeysFile {
 
    #arg1 Full container image
    #arg2 name of template file
-   #arg3 prefix to insert in placeholders (optional)
+   #arg3 prefix to insert in placeholders (optional; defaults to "")
+   #arg4 flag to override omit_image_key logic (optional; defaults to "false")
+
+   #NOTE: arg4 is required to handle 2 initContainers (for OpenSearch and Fluent Bit)
+   #      for which the template file contains settings other than image specs
 
    local pullsecret_text
 
@@ -299,6 +303,7 @@ function generateImageKeysFile {
    fi
 
    prefix=${3:-""}
+   ignoreOmitImageKeys=${4:-"false"}
 
    imageKeysFile="$TMP_DIR/imageKeysFile.yaml"
    template_file=$2
@@ -310,7 +315,7 @@ function generateImageKeysFile {
       log_debug "Modifying an existing imageKeysFile"
    fi
 
-   if [ "$V4M_OMIT_IMAGE_KEYS" == "true" ]; then
+   if [ "$V4M_OMIT_IMAGE_KEYS" == "true" ] && [ "$ignoreOmitImageKeys" != "true" ]; then
       cp $TMP_DIR/empty.yaml $imageKeysFile
       return 0
    fi

component_versions.env

@@ -19,6 +19,7 @@ FLUENTBIT_HELM_CHART_REPO=fluent
 FLUENTBIT_HELM_CHART_NAME=fluent-bit
 FLUENTBIT_HELM_CHART_VERSION=0.47.10
 FB_FULL_IMAGE="cr.fluentbit.io/fluent/fluent-bit:3.1.9"
+FB_INITCONTAINER_FULL_IMAGE="docker.io/library/busybox:latest"
 
 #OpenSearch
 OPENSEARCH_HELM_CHART_REPO=opensearch

logging/bin/deploy_fluentbit_azmonitor.sh

@@ -39,7 +39,8 @@ fi
 log_info "Deploying Fluent Bit (Azure Monitor)"
 
 #Generate yaml file with all container-related keys#Generate yaml file with all container-related keys
-generateImageKeysFile "$FB_FULL_IMAGE"          "logging/fb/fb_container_image.template"
+generateImageKeysFile "$FB_FULL_IMAGE"               "logging/fb/fb_container_image.template"
+generateImageKeysFile "$FB_INITCONTAINER_FULL_IMAGE" "logging/fb/fb_initcontainer_image.template" "" "true"
 
 # Fluent Bit user customizations
 FB_AZMONITOR_USER_YAML="${FB_AZMONITOR_USER_YAML:-$USER_DIR/logging/user-values-fluent-bit-azmonitor.yaml}"
@@ -66,22 +67,22 @@ if [ "$(kubectl -n $LOG_NS get secret connection-info-azmonitor -o name 2>/dev/n
 
    if [ "$AZMONITOR_CUSTOMER_ID" != "NotProvided"  ] && [ "$AZMONITOR_SHARED_KEY" != "NotProvided" ]; then
       log_info "Creating secret [connection-info-azmonitor] in [$LOG_NS] namespace to hold Azure connection information."
-      kubectl -n $LOG_NS create secret generic connection-info-azmonitor --from-literal=customer_id=$AZMONITOR_CUSTOMER_ID --from-literal=shared_key=$AZMONITOR_SHARED_KEY
+      kubectl -n "$LOG_NS" create secret generic connection-info-azmonitor --from-literal=customer_id="$AZMONITOR_CUSTOMER_ID" --from-literal=shared_key="$AZMONITOR_SHARED_KEY"
    else
       log_error "Unable to create secret [$LOG_NS/connection-info-azmonitor] because missing required information: [AZMONITOR_CUSTOMER_ID: $AZMONITOR_CUSTOMER_ID ; AZMONITOR_SHARED_KEY: $AZMONITOR_SHARED_KEY]."
       log_error "You must provide this information via environment variables or create the secret [connection-info-azmonitor] before running this script."
       exit 1
    fi
 else
    log_info "Obtaining connection information from existing secret [$LOG_NS/connection-info-azmonitor]"
-   export AZMONITOR_CUSTOMER_ID=$(kubectl -n $LOG_NS get secret connection-info-azmonitor -o=jsonpath="{.data.customer_id}" |base64 --decode)
-   export AZMONITOR_SHARED_KEY=$(kubectl -n $LOG_NS get secret connection-info-azmonitor -o=jsonpath="{.data.shared_key}" |base64 --decode)
+   export AZMONITOR_CUSTOMER_ID=$(kubectl -n "$LOG_NS" get secret connection-info-azmonitor -o=jsonpath="{.data.customer_id}" |base64 --decode)
+   export AZMONITOR_SHARED_KEY=$(kubectl -n "$LOG_NS" get secret connection-info-azmonitor -o=jsonpath="{.data.shared_key}" |base64 --decode)
 fi
 
 # Check for an existing Helm release of stable/fluent-bit
 if helm3ReleaseExists fbaz $LOG_NS; then
    log_info "Removing an existing release of deprecated stable/fluent-bit Helm chart from from the [$LOG_NS] namespace [$(date)]"
-   helm  $helmDebug  delete -n $LOG_NS fbaz
+   helm  $helmDebug  delete -n "$LOG_NS" fbaz
 
    if [ $(kubectl get servicemonitors -A |grep fluent-bit-v2 -c) -ge 1 ]; then
       log_debug "Updated serviceMonitor [fluent-bit-v2] appears to be deployed."
@@ -94,19 +95,19 @@ else
 fi
 
 # Multiline parser setup
-LOG_MULTILINE_ENABLED="${LOG_MULTILINE_ENABLED}"
+LOG_MULTILINE_ENABLED="${LOG_MULTILINE_ENABLED:-true}"
 if [ "$LOG_MULTILINE_ENABLED" == "true" ]; then
   LOG_MULTILINE_PARSER="docker, cri"
 else
   LOG_MULTILINE_PARSER=""
 fi
 
 # Create ConfigMap containing Fluent Bit configuration
-kubectl -n $LOG_NS apply -f $FB_CONFIGMAP
+kubectl -n "$LOG_NS" apply -f $FB_CONFIGMAP
 
 # Create ConfigMap containing Viya-customized parsers (delete it first)
-kubectl -n $LOG_NS delete configmap fbaz-viya-parsers --ignore-not-found
-kubectl -n $LOG_NS create configmap fbaz-viya-parsers  --from-file=logging/fb/viya-parsers.conf
+kubectl -n "$LOG_NS" delete configmap fbaz-viya-parsers --ignore-not-found
+kubectl -n "$LOG_NS" create configmap fbaz-viya-parsers  --from-file=logging/fb/viya-parsers.conf
 
 TRACING_ENABLE="${TRACING_ENABLE:-false}"
 if [ "$TRACING_ENABLE" == "true" ]; then
@@ -146,13 +147,25 @@ fi
 MON_NS="${MON_NS:-monitoring}"
 
 # Create ConfigMap containing Kubernetes container runtime log format
-kubectl -n $LOG_NS delete configmap fbaz-env-vars --ignore-not-found
-kubectl -n $LOG_NS create configmap fbaz-env-vars \
+kubectl -n "$LOG_NS" delete configmap fbaz-env-vars --ignore-not-found
+kubectl -n "$LOG_NS" create configmap fbaz-env-vars \
                    --from-literal=KUBERNETES_RUNTIME_LOGFMT=$KUBERNETES_RUNTIME_LOGFMT \
                    --from-literal=LOG_MULTILINE_PARSER="${LOG_MULTILINE_PARSER}" \
                    --from-literal=MON_NS="${MON_NS}"
 
-kubectl -n $LOG_NS label configmap fbaz-env-vars   managed-by=v4m-es-script
+kubectl -n "$LOG_NS" label configmap fbaz-env-vars   managed-by=v4m-es-script
+
+# Check to see if we are upgrading from earlier version requiring root access
+if [ "$( kubectl -n $LOG_NS get configmap fbaz-dbmigrate-script -o name --ignore-not-found)" != "configmap/fbaz-dbmigrate-script" ]; then
+   log_debug "Removing FB pods (if they exist) to allow migration."
+   kubectl -n "$LOG_NS" delete daemonset v4m-fbaz --ignore-not-found
+fi
+
+# Create ConfigMap containing Fluent Bit database migration script
+kubectl -n "$LOG_NS" delete configmap fbaz-dbmigrate-script --ignore-not-found
+kubectl -n "$LOG_NS" create configmap fbaz-dbmigrate-script --from-file logging/fb/migrate_fbstate_db.sh
+kubectl -n "$LOG_NS" label  configmap fbaz-dbmigrate-script managed-by=v4m-es-script
+
 
  ## Get Helm Chart Name
  log_debug "Fluent Bit Helm Chart: repo [$FLUENTBIT_HELM_CHART_REPO] name [$FLUENTBIT_HELM_CHART_NAME] version [$FLUENTBIT_HELM_CHART_VERSION]"
@@ -170,9 +183,12 @@ helm $helmDebug upgrade --install v4m-fbaz  --namespace $LOG_NS  \
   --set fullnameOverride=v4m-fbaz \
   $chart2install
 
+#pause to allow migration script to complete (if necessary)
+sleep 20
 
 #Container Security: Disable Token Automounting at ServiceAccount; enable for Pod
 disable_sa_token_automount $LOG_NS v4m-fbaz
+# FB pods will restart after following call if automount is not already enabled
 enable_pod_token_automount $LOG_NS daemonset v4m-fbaz
 
 # Force restart of daemonset to ensure we pick up latest config changes

logging/bin/deploy_fluentbit_opensearch.sh

@@ -55,7 +55,7 @@ helm2ReleaseCheck fb-$LOG_NS
 # Check for an existing Helm release of stable/fluent-bit
 if helm3ReleaseExists fb $LOG_NS; then
    log_verbose "Removing an existing release of deprecated stable/fluent-bit Helm chart from from the [$LOG_NS] namespace [$(date)]"
-   helm  $helmDebug  delete -n $LOG_NS fb
+   helm  $helmDebug  delete -n "$LOG_NS" fb
 
    if [ $(kubectl get servicemonitors -A |grep fluent-bit-v2 -c) -ge 1 ]; then
       log_debug "Updated serviceMonitor [fluent-bit-v2] appears to be deployed."
@@ -68,7 +68,8 @@ else
 fi
 
 #Generate yaml file with all container-related keys
-generateImageKeysFile "$FB_FULL_IMAGE"          "logging/fb/fb_container_image.template"
+generateImageKeysFile "$FB_FULL_IMAGE"                "logging/fb/fb_container_image.template"
+generateImageKeysFile "$FB_INITCONTAINER_FULL_IMAGE"  "logging/fb/fb_initcontainer_image.template" "" "true"
 
 # Fluent Bit user customizations
 FB_OPENSEARCH_USER_YAML="${FB_OPENSEARCH_USER_YAML:-$USER_DIR/logging/user-values-fluent-bit-opensearch.yaml}"
@@ -98,19 +99,19 @@ fi
 log_debug "Using FB ConfigMap:" $FB_CONFIGMAP
 
 # Multiline parser setup
-LOG_MULTILINE_ENABLED=${LOG_MULTILINE_ENABLED}
+LOG_MULTILINE_ENABLED=${LOG_MULTILINE_ENABLED:-true}
 if [ "$LOG_MULTILINE_ENABLED" == "true" ]; then
   LOG_MULTILINE_PARSER="docker, cri"
 else
   LOG_MULTILINE_PARSER=""
 fi
 
 # Create ConfigMap containing Fluent Bit configuration
-kubectl -n $LOG_NS apply -f $FB_CONFIGMAP
+kubectl -n "$LOG_NS" apply -f $FB_CONFIGMAP
 
 # Create ConfigMap containing Viya-customized parsers (delete it first)
-kubectl -n $LOG_NS delete configmap fb-viya-parsers --ignore-not-found
-kubectl -n $LOG_NS create configmap fb-viya-parsers  --from-file=logging/fb/viya-parsers.conf
+kubectl -n "$LOG_NS" delete configmap fb-viya-parsers --ignore-not-found
+kubectl -n "$LOG_NS" create configmap fb-viya-parsers  --from-file=logging/fb/viya-parsers.conf
 
 TRACING_ENABLE="${TRACING_ENABLE:-false}"
 if [ "$TRACING_ENABLE" == "true" ]; then
@@ -150,14 +151,25 @@ fi
 MON_NS="${MON_NS:-monitoring}"
 
 # Create ConfigMap containing Kubernetes container runtime log format
-kubectl -n $LOG_NS delete configmap fb-env-vars --ignore-not-found
-kubectl -n $LOG_NS create configmap fb-env-vars \
+kubectl -n "$LOG_NS" delete configmap fb-env-vars --ignore-not-found
+kubectl -n "$LOG_NS" create configmap fb-env-vars \
                    --from-literal=KUBERNETES_RUNTIME_LOGFMT="$KUBERNETES_RUNTIME_LOGFMT" \
                    --from-literal=LOG_MULTILINE_PARSER="${LOG_MULTILINE_PARSER}"         \
                    --from-literal=SEARCH_SERVICENAME="${ES_SERVICENAME}"                 \
                    --from-literal=MON_NS="${MON_NS}"
 
-kubectl -n $LOG_NS label configmap fb-env-vars   managed-by=v4m-es-script
+kubectl -n "$LOG_NS" label configmap fb-env-vars   managed-by=v4m-es-script
+
+# Check to see if we are upgrading from earlier version requiring root access
+if [ "$( kubectl -n $LOG_NS get configmap fb-dbmigrate-script -o name --ignore-not-found)" != "configmap/fb-dbmigrate-script" ]; then
+   log_debug "Removing FB pods (if they exist) to allow migration."
+   kubectl -n "$LOG_NS" delete daemonset v4m-fb --ignore-not-found
+fi
+
+# Create ConfigMap containing Fluent Bit database migration script
+kubectl -n "$LOG_NS" delete configmap fb-dbmigrate-script --ignore-not-found
+kubectl -n "$LOG_NS" create configmap fb-dbmigrate-script --from-file logging/fb/migrate_fbstate_db.sh
+kubectl -n "$LOG_NS" label  configmap fb-dbmigrate-script managed-by=v4m-es-script
 
 ## Get Helm Chart Name
 log_debug "Fluent Bit Helm Chart: repo [$FLUENTBIT_HELM_CHART_REPO] name [$FLUENTBIT_HELM_CHART_NAME] version [$FLUENTBIT_HELM_CHART_VERSION]"
@@ -176,8 +188,13 @@ helm $helmDebug upgrade --install --namespace $LOG_NS v4m-fb  \
   --set fullnameOverride=v4m-fb \
   $chart2install
 
+#pause to allow migration script to complete (if necessary)
+log_debug "Pausing to allow migration script to complete"
+sleep 20
+
 #Container Security: Disable Token Automounting at ServiceAccount; enable for Pod
 disable_sa_token_automount $LOG_NS v4m-fb
+# FB pods will restart after following call if automount is not already enabled
 enable_pod_token_automount $LOG_NS daemonset v4m-fb
 
 # Force restart of daemonset to ensure we pick up latest config changes

logging/bin/deploy_opensearch.sh

@@ -40,6 +40,7 @@ fi
 #Generate yaml files with all container-related keys
 generateImageKeysFile "$OS_FULL_IMAGE"          "logging/opensearch/os_container_image.template"
 generateImageKeysFile "$OS_SYSCTL_FULL_IMAGE"   "$imageKeysFile"  "OS_SYSCTL_"
+generateImageKeysFile "$OS_FULL_IMAGE"          "logging/opensearch/os_initcontainer_image.template" "" "true"
 
 # get credentials
 export ES_ADMIN_PASSWD=${ES_ADMIN_PASSWD}

logging/bin/deploy_openshift_prereqs.sh

@@ -25,6 +25,20 @@ fi
 # link OpenSearch serviceAccounts to 'privileged' scc
 oc adm policy add-scc-to-user privileged -z v4m-os -n $LOG_NS
 
+# create the 'v4m-logging-v2' SCC, if it does not already exist
+if oc get scc v4m-logging-v2 2>/dev/null 1>&2; then
+   log_info "Skipping scc creation; using existing scc [v4m-logging-v2]"
+else
+   oc create -f logging/openshift/fb_v4m-logging-v2_scc.yaml
+fi
+
+# create the 'v4m-k8sevents' SCC, if it does not already exist
+if oc get scc v4m-k8sevents 2>/dev/null 1>&2; then
+   log_info "Skipping scc creation; using existing scc [v4m-k8sevents]"
+else
+   oc create -f logging/openshift/fb_v4m-k8sevents_scc.yaml
+fi
+
 log_info "OpenShift Prerequisites have been deployed."
 
 log_debug "Script [$this_script] has completed [$(date)]"

logging/bin/remove_fluentbit_azmonitor.sh

@@ -30,7 +30,7 @@ kubectl -n $LOG_NS delete configmap fbaz-fluent-bit-config   --ignore-not-found
 kubectl -n $LOG_NS delete configmap fbaz-viya-parsers        --ignore-not-found
 kubectl -n $LOG_NS delete configmap fbaz-viya-tracing        --ignore-not-found
 kubectl -n $LOG_NS delete configmap fbaz-env-vars            --ignore-not-found
-
+kubectl -n $LOG_NS delete configmap fbaz-dbmigrate-script    --ignore-not-found
 
 # Should we leave secret in place?
 log_info "Removing Connection information  (secret)"

logging/bin/remove_fluentbit_opensearch.sh

@@ -27,6 +27,7 @@ kubectl -n $LOG_NS delete configmap fb-fluent-bit-config   --ignore-not-found
 kubectl -n $LOG_NS delete configmap fb-viya-parsers        --ignore-not-found
 kubectl -n $LOG_NS delete configmap fb-viya-tracing        --ignore-not-found
 kubectl -n $LOG_NS delete configmap fb-env-vars            --ignore-not-found
+kubectl -n $LOG_NS delete configmap fb-dbmigrate-script    --ignore-not-found
 
 log_debug "Script [$this_script] has completed [$(date)]"
 echo ""

logging/bin/remove_openshift_artifacts.sh

@@ -19,7 +19,10 @@ if [ "$OPENSHIFT_ARTIFACTS_REMOVE" != "true" ]; then
 fi
 
 # remove custom OpenShift SCC
-oc delete scc v4mlogging --ignore-not-found
+oc delete scc v4mlogging     --ignore-not-found
+oc delete scc v4m-logging-v2 --ignore-not-found
+oc delete scc v4m-k8sevents  --ignore-not-found
+
 
 
 log_info "OpenShift Prerequisites have been removed."

logging/esexporter/values-es-exporter.yaml

@@ -173,3 +173,6 @@ prometheusRule:
     annotations:
       description: The heap usage is over 90% for 15m
       summary: Elasticsearch node {{$labels.node}} heap usage is high
+
+securityContext:
+  privileged: false

logging/fb/fb_initcontainer_image.template

@@ -0,0 +1,26 @@
+initContainers:
+- name: chowner-v4m-fb-storage
+  image: __IMAGE_REPO_3LEVEL__:__IMAGE_TAG__
+  imagePullPolicy: IfNotPresent
+  command: ['sh', '-c', "./usr/bin/migrate_fbstate_db.sh"]
+  securityContext:
+    privileged: true
+    allowPrivilegeEscalation: true
+    readOnlyRootFilesystem: true
+    capabilities:
+      drop: ["all"]
+      add: ["CHOWN"]
+    runAsUser: 0
+    runAsNonRoot: false
+  volumeMounts:
+  - name: v4m-fb-storage
+    mountPath: /var/log/v4m-fb-storage
+  - name: dbmigrate-script
+    mountPath: /usr/bin/migrate_fbstate_db.sh
+    readOnly: false
+    subPath: migrate_fbstate_db.sh
+  - mountPath: /var/log
+    name: varlog
+    readOnly: true
+
+