Add support for excluding specific containers in log analysis across multiple healthcheck runbooks

codebundles/k8s-daemonset-healthcheck/runbook.robot

@@ -39,13 +39,15 @@ Analyze Application Log Patterns for DaemonSet `${DAEMONSET_NAME}` in Namespace
     ...    context=${CONTEXT}
     ...    kubeconfig=${kubeconfig}
     ...    log_age=${LOG_AGE}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     ${scan_results}=    RW.K8sLog.Scan Logs For Issues
     ...    log_dir=${log_dir}
     ...    workload_type=daemonset
     ...    workload_name=${DAEMONSET_NAME}
     ...    namespace=${NAMESPACE}
     ...    categories=@{LOG_PATTERN_CATEGORIES}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     ${log_health_score}=    RW.K8sLog.Calculate Log Health Score    scan_results=${scan_results}
 
@@ -98,12 +100,14 @@ Detect Log Anomalies for DaemonSet `${DAEMONSET_NAME}` in Namespace `${NAMESPACE
     ...    context=${CONTEXT}
     ...    kubeconfig=${kubeconfig}
     ...    log_age=${LOG_AGE}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     ${anomaly_results}=    RW.K8sLog.Analyze Log Anomalies
     ...    log_dir=${log_dir}
     ...    workload_type=daemonset
     ...    workload_name=${DAEMONSET_NAME}
     ...    namespace=${NAMESPACE}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     # Process anomaly issues
     ${anomaly_issues}=    Evaluate    $anomaly_results.get('issues', [])
@@ -945,9 +949,21 @@ Suite Initialization
     ...    pattern=\d+
     ...    example=1
     ...    default=1
+    ${EXCLUDED_CONTAINER_NAMES}=    RW.Core.Import User Variable    EXCLUDED_CONTAINER_NAMES
+    ...    type=string
+    ...    description=Comma-separated list of container names to exclude from log analysis (e.g., linkerd-proxy, istio-proxy, vault-agent).
+    ...    pattern=.*
+    ...    example=linkerd-proxy,istio-proxy,vault-agent
+    ...    default=linkerd-proxy,istio-proxy,vault-agent
 
-    # Convert comma-separated string to list
+    # Convert comma-separated strings to lists
     @{LOG_PATTERN_CATEGORIES}=    Split String    ${LOG_PATTERN_CATEGORIES_STR}    ,
+    @{EXCLUDED_CONTAINERS_RAW}=    Run Keyword If    "${EXCLUDED_CONTAINER_NAMES}" != ""    Split String    ${EXCLUDED_CONTAINER_NAMES}    ,    ELSE    Create List
+    @{EXCLUDED_CONTAINERS}=    Create List
+    FOR    ${container}    IN    @{EXCLUDED_CONTAINERS_RAW}
+        ${trimmed_container}=    Strip String    ${container}
+        Append To List    ${EXCLUDED_CONTAINERS}    ${trimmed_container}
+    END
 
     Set Suite Variable    ${kubeconfig}
     Set Suite Variable    ${KUBERNETES_DISTRIBUTION_BINARY}
@@ -961,6 +977,8 @@ Suite Initialization
     Set Suite Variable    ${ANOMALY_THRESHOLD}
     Set Suite Variable    ${CONTAINER_RESTART_AGE}
     Set Suite Variable    ${CONTAINER_RESTART_THRESHOLD}
+    Set Suite Variable    ${EXCLUDED_CONTAINER_NAMES}
+    Set Suite Variable    @{EXCLUDED_CONTAINERS}
     ${env}=    Evaluate    {"KUBECONFIG":"${kubeconfig.key}","KUBERNETES_DISTRIBUTION_BINARY":"${KUBERNETES_DISTRIBUTION_BINARY}","CONTEXT":"${CONTEXT}","NAMESPACE":"${NAMESPACE}","DAEMONSET_NAME":"${DAEMONSET_NAME}","CONTAINER_RESTART_AGE":"${CONTAINER_RESTART_AGE}","CONTAINER_RESTART_THRESHOLD":"${CONTAINER_RESTART_THRESHOLD}"}
     Set Suite Variable    ${env}
 

codebundles/k8s-deployment-healthcheck/runbook.robot

@@ -112,6 +112,12 @@ Suite Initialization
     ...    pattern=.*
     ...    example=linkerd-proxy,istio-proxy,vault-agent
     ...    default=linkerd-proxy,istio-proxy,vault-agent
+    ${CONTAINER_NAME}=    RW.Core.Import User Variable    CONTAINER_NAME
+    ...    type=string
+    ...    description=Optional: the specific container name to fetch logs from. If not set, the primary application container is auto-detected by excluding known sidecars.
+    ...    pattern=.*
+    ...    example=controller
+    ...    default=
 
     ${CONTAINER_RESTART_AGE}=    RW.Core.Import User Variable    CONTAINER_RESTART_AGE
     ...    type=string
@@ -152,6 +158,7 @@ Suite Initialization
     Set Suite Variable    ${LOG_SCAN_TIMEOUT}
     Set Suite Variable    ${EXCLUDED_CONTAINER_NAMES}
     Set Suite Variable    @{EXCLUDED_CONTAINERS}
+    Set Suite Variable    ${CONTAINER_NAME}
 
     Set Suite Variable    ${CONTAINER_RESTART_AGE}
     Set Suite Variable    ${CONTAINER_RESTART_THRESHOLD}
@@ -401,9 +408,41 @@ Fetch Deployment Logs for `${DEPLOYMENT_NAME}` in Namespace `${NAMESPACE}`
     ...    data:logs-bulk
     # Skip pod-related checks if deployment is scaled to 0
     IF    not ${SKIP_POD_CHECKS}
-        # Fetch raw logs
+        # Determine which container to fetch logs from
+        IF    "${CONTAINER_NAME}" != ""
+            ${target_container}=    Set Variable    ${CONTAINER_NAME}
+        ELSE
+            # Auto-detect primary container by listing containers and excluding known sidecars
+            ${container_json}=    RW.CLI.Run Cli
+            ...    cmd=${KUBERNETES_DISTRIBUTION_BINARY} get deployment/${DEPLOYMENT_NAME} --context ${CONTEXT} -n ${NAMESPACE} -o jsonpath='{.spec.template.spec.containers[*].name}'
+            ...    env=${env}
+            ...    secret_file__kubeconfig=${kubeconfig}
+            ...    include_in_history=false
+            @{all_containers}=    Split String    ${container_json.stdout}
+            ${container_count}=    Get Length    ${all_containers}
+            ${target_container}=    Set Variable    ${EMPTY}
+            IF    ${container_count} > 0
+                FOR    ${cname}    IN    @{all_containers}
+                    ${is_excluded}=    Evaluate    "${cname}" in ${EXCLUDED_CONTAINERS}
+                    IF    not ${is_excluded}
+                        ${target_container}=    Set Variable    ${cname}
+                        BREAK
+                    END
+                END
+                IF    "${target_container}" == ""
+                    ${target_container}=    Set Variable    ${all_containers}[0]
+                END
+            END
+        END
+
+        # Build the kubectl logs command with or without -c flag
+        IF    "${target_container}" != ""
+            ${logs_cmd}=    Set Variable    ${KUBERNETES_DISTRIBUTION_BINARY} logs deployment/${DEPLOYMENT_NAME} -c ${target_container} --context ${CONTEXT} -n ${NAMESPACE} --tail=${LOG_LINES} --since=${LOG_AGE}
+        ELSE
+            ${logs_cmd}=    Set Variable    ${KUBERNETES_DISTRIBUTION_BINARY} logs deployment/${DEPLOYMENT_NAME} --context ${CONTEXT} -n ${NAMESPACE} --tail=${LOG_LINES} --since=${LOG_AGE}
+        END
         ${deployment_logs}=    RW.CLI.Run Cli
-        ...    cmd=${KUBERNETES_DISTRIBUTION_BINARY} logs deployment/${DEPLOYMENT_NAME} --context ${CONTEXT} -n ${NAMESPACE} --tail=${LOG_LINES} --since=${LOG_AGE}
+        ...    cmd=${logs_cmd}
         ...    env=${env}
         ...    secret_file__kubeconfig=${kubeconfig}
         ...    show_in_rwl_cheatsheet=true
@@ -412,13 +451,13 @@ Fetch Deployment Logs for `${DEPLOYMENT_NAME}` in Namespace `${NAMESPACE}`
         IF    ${deployment_logs.returncode} == 0
             # Filter logs to remove repetitive health check messages and focus on meaningful content
             ${filtered_logs}=    RW.CLI.Run Cli
-            ...    cmd=echo "${deployment_logs.stdout}" | grep -v -E "(Checking.*Health|Health.*Check|healthcheck|/health|GET /|POST /health|probe|liveness|readiness)" | grep -E "(error|ERROR|warn|WARN|exception|Exception|fail|FAIL|fatal|FATAL|panic|stack|trace|timeout|connection.*refused|unable.*connect|authentication.*failed|denied|forbidden|unauthorized|500|502|503|504)" | tail -50 || echo "No significant errors or warnings found in recent logs"
+            ...    cmd=echo "${deployment_logs.stdout}" | grep -v -E "(Checking.*Health|Health.*Check|healthcheck|/health|GET /health|POST /health|probe|liveness|readiness)" | grep -E "(error|ERROR|warn|WARN|exception|Exception|fail|FAIL|fatal|FATAL|panic|stack|trace|timeout|connection.*refused|unable.*connect|authentication.*failed|denied|forbidden|unauthorized|500|502|503|504)" | tail -50 || echo "No significant errors or warnings found in recent logs"
             ...    env=${env}
             ...    include_in_history=false
 
             # Also get a sample of non-health-check logs for context
             ${context_logs}=    RW.CLI.Run Cli
-            ...    cmd=echo "${deployment_logs.stdout}" | grep -v -E "(Checking.*Health|Health.*Check|healthcheck|/health|GET /|POST /health|probe|liveness|readiness)" | head -20 | tail -10
+            ...    cmd=echo "${deployment_logs.stdout}" | grep -v -E "(Checking.*Health|Health.*Check|healthcheck|/health|GET /health|POST /health|probe|liveness|readiness)" | head -20 | tail -10
             ...    env=${env}
             ...    include_in_history=false
 

codebundles/k8s-stacktrace-health/runbook.robot

@@ -162,7 +162,12 @@ Analyze Workload Stacktraces for ${WORKLOAD_TYPE} `${WORKLOAD_NAME}` in Namespac
     # Skip pod-related checks if workload is scaled to 0
     IF    not ${SKIP_STACKTRACE_CHECKS}
         # Convert comma-separated string to list for excluded containers
-        @{EXCLUDED_CONTAINERS}=    Run Keyword If    "${EXCLUDED_CONTAINER_NAMES}" != ""    Split String    ${EXCLUDED_CONTAINER_NAMES}    ,    ELSE    Create List
+        @{EXCLUDED_CONTAINERS_RAW}=    Run Keyword If    "${EXCLUDED_CONTAINER_NAMES}" != ""    Split String    ${EXCLUDED_CONTAINER_NAMES}    ,    ELSE    Create List
+        @{EXCLUDED_CONTAINERS}=    Create List
+        FOR    ${container}    IN    @{EXCLUDED_CONTAINERS_RAW}
+            ${trimmed_container}=    Strip String    ${container}
+            Append To List    ${EXCLUDED_CONTAINERS}    ${trimmed_container}
+        END
 
         # Fetch logs using RW.K8sLog library (same pattern as deployment healthcheck)
         ${log_dir}=    RW.K8sLog.Fetch Workload Logs

codebundles/k8s-stacktrace-health/sli.robot

@@ -83,7 +83,12 @@ Suite Initialization
 
 
     # Convert comma-separated string to list
-    @{EXCLUDED_CONTAINERS}=    Run Keyword If    "${EXCLUDED_CONTAINER_NAMES}" != ""    Split String    ${EXCLUDED_CONTAINER_NAMES}    ,    ELSE    Create List
+    @{EXCLUDED_CONTAINERS_RAW}=    Run Keyword If    "${EXCLUDED_CONTAINER_NAMES}" != ""    Split String    ${EXCLUDED_CONTAINER_NAMES}    ,    ELSE    Create List
+    @{EXCLUDED_CONTAINERS}=    Create List
+    FOR    ${container}    IN    @{EXCLUDED_CONTAINERS_RAW}
+        ${trimmed_container}=    Strip String    ${container}
+        Append To List    ${EXCLUDED_CONTAINERS}    ${trimmed_container}
+    END
     Set Suite Variable    @{EXCLUDED_CONTAINERS}
 
     # Initialize score variables

codebundles/k8s-statefulset-healthcheck/runbook.robot

@@ -39,13 +39,15 @@ Analyze Application Log Patterns for StatefulSet `${STATEFULSET_NAME}` in Namesp
     ...    context=${CONTEXT}
     ...    kubeconfig=${kubeconfig}
     ...    log_age=${LOG_AGE}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     ${scan_results}=    RW.K8sLog.Scan Logs For Issues
     ...    log_dir=${log_dir}
     ...    workload_type=statefulset
     ...    workload_name=${STATEFULSET_NAME}
     ...    namespace=${NAMESPACE}
     ...    categories=@{LOG_PATTERN_CATEGORIES}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     ${log_health_score}=    RW.K8sLog.Calculate Log Health Score    scan_results=${scan_results}
 
@@ -99,12 +101,14 @@ Detect Log Anomalies for StatefulSet `${STATEFULSET_NAME}` in Namespace `${NAMES
     ...    context=${CONTEXT}
     ...    kubeconfig=${kubeconfig}
     ...    log_age=${LOG_AGE}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     ${anomaly_results}=    RW.K8sLog.Analyze Log Anomalies
     ...    log_dir=${log_dir}
     ...    workload_type=statefulset
     ...    workload_name=${STATEFULSET_NAME}
     ...    namespace=${NAMESPACE}
+    ...    excluded_containers=${EXCLUDED_CONTAINERS}
 
     # Process anomaly issues
     ${anomaly_issues}=    Evaluate    $anomaly_results.get('issues', [])
@@ -970,9 +974,21 @@ Suite Initialization
     ...    pattern=\d+
     ...    example=1
     ...    default=1
+    ${EXCLUDED_CONTAINER_NAMES}=    RW.Core.Import User Variable    EXCLUDED_CONTAINER_NAMES
+    ...    type=string
+    ...    description=Comma-separated list of container names to exclude from log analysis (e.g., linkerd-proxy, istio-proxy, vault-agent).
+    ...    pattern=.*
+    ...    example=linkerd-proxy,istio-proxy,vault-agent
+    ...    default=linkerd-proxy,istio-proxy,vault-agent
 
-    # Convert comma-separated string to list
+    # Convert comma-separated strings to lists
     @{LOG_PATTERN_CATEGORIES}=    Split String    ${LOG_PATTERN_CATEGORIES_STR}    ,
+    @{EXCLUDED_CONTAINERS_RAW}=    Run Keyword If    "${EXCLUDED_CONTAINER_NAMES}" != ""    Split String    ${EXCLUDED_CONTAINER_NAMES}    ,    ELSE    Create List
+    @{EXCLUDED_CONTAINERS}=    Create List
+    FOR    ${container}    IN    @{EXCLUDED_CONTAINERS_RAW}
+        ${trimmed_container}=    Strip String    ${container}
+        Append To List    ${EXCLUDED_CONTAINERS}    ${trimmed_container}
+    END
 
     Set Suite Variable    ${kubeconfig}
     Set Suite Variable    ${KUBERNETES_DISTRIBUTION_BINARY}
@@ -986,6 +1002,8 @@ Suite Initialization
     Set Suite Variable    ${ANOMALY_THRESHOLD}
     Set Suite Variable    ${CONTAINER_RESTART_AGE}
     Set Suite Variable    ${CONTAINER_RESTART_THRESHOLD}
+    Set Suite Variable    ${EXCLUDED_CONTAINER_NAMES}
+    Set Suite Variable    @{EXCLUDED_CONTAINERS}
     ${env}=    Evaluate    {"KUBECONFIG":"${kubeconfig.key}","KUBERNETES_DISTRIBUTION_BINARY":"${KUBERNETES_DISTRIBUTION_BINARY}","CONTEXT":"${CONTEXT}","NAMESPACE":"${NAMESPACE}","STATEFULSET_NAME":"${STATEFULSET_NAME}","CONTAINER_RESTART_AGE":"${CONTAINER_RESTART_AGE}","CONTAINER_RESTART_THRESHOLD":"${CONTAINER_RESTART_THRESHOLD}"}
     Set Suite Variable    ${env}
 

libraries/RW/CLI/CLI.py

@@ -184,7 +184,7 @@ def _create_secrets_from_kwargs(**kwargs) -> list[platform.ShellServiceRequestSe
         if not key.startswith(SECRET_PREFIX) and not key.startswith(SECRET_FILE_PREFIX):
             continue
         if not isinstance(value, platform.Secret):
-            logger.warning(
+            logger.warn(
                 f"kwarg secret {value} in key {key} is the wrong type, should be platform.Secret"
             )
             continue
@@ -217,7 +217,7 @@ def _copy_files_to_staging_dir(source_dir: str, staging_dir: str) -> dict:
                 with open(staged_path, "w", encoding="utf-8") as out_f:
                     out_f.write(content)
             except Exception as e:
-                logger.warning(f"Could not stage file '{full_path}': {e}")
+                logger.warn(f"Could not stage file '{full_path}': {e}")
     return files_dict
 
 def find_file(*paths):
@@ -326,7 +326,7 @@ def run_bash_file(
     else:
         # Not found directly, so do fallback logic with resolve_path_to_robot
         cwd = os.getcwd()
-        logger.warning(f"File '{bash_file}' not found in '{cwd}'. Attempting fallback logic...")
+        logger.warn(f"File '{bash_file}' not found in '{cwd}'. Attempting fallback logic...")
 
         # Might return something like "/path/to/.../sli.robot"
         rw_path_to_robot = resolve_path_to_robot()

libraries/RW/CLI/json_parser.py

@@ -134,13 +134,13 @@ def parse_cli_json_output(
         try:
             jmespath_result = jmespath.search(jmespath_str, json_data)
             if jmespath_result == None:
-                logger.warning(
+                logger.warn(
                     f"The jmespath extraction string: {jmespath_str} returned None for the variable: {varname} with kwarg parts: {kwarg_parts} - did a previous extract fail?"
                 )
             variable_results[varname] = jmespath_result
             variable_from_path[varname] = jmespath_str
         except Exception as e:
-            logger.warning(
+            logger.warn(
                 f"Failed to extract jmespath data: {json.dumps(variable_results[varname])} with path: {jmespath_str} due to: {e}"
             )
             variable_results[varname] = None
@@ -154,7 +154,7 @@ def parse_cli_json_output(
         jmespath_str = kwargs[key]
         from_varname = kwarg_parts[1]
         if from_varname not in variable_results.keys():
-            logger.warning(
+            logger.warn(
                 f"attempted to reference from_var {from_varname} when it has not been created yet. Available vars: {variable_results.keys()}"
             )
             continue
@@ -167,7 +167,7 @@ def parse_cli_json_output(
             variable_results[to_varname] = jmespath.search(jmespath_str, variable_results[from_varname])
             variable_from_path[to_varname] = jmespath_str
         except Exception as e:
-            logger.warning(
+            logger.warn(
                 f"Failed to extract jmespath data: {json.dumps(variable_results[from_varname])} with path: {jmespath_str} due to: {e}"
             )
             variable_results[to_varname] = None
@@ -181,7 +181,7 @@ def parse_cli_json_output(
         varname = kwarg_parts[0]
         filter_type = kwarg_parts[1]
         if filter_type not in RECOGNIZED_FILTERS:
-            logger.warning(f"filter: {filter_type} is not in the expected types: {RECOGNIZED_FILTERS}")
+            logger.warn(f"filter: {filter_type} is not in the expected types: {RECOGNIZED_FILTERS}")
             continue
         filter_amount = kwarg_parts[2]
         field_to_filter_on = kwargs[key]
@@ -231,7 +231,7 @@ def parse_cli_json_output(
             continue
         from_varname = kwargs[key]
         if from_varname not in variable_results.keys():
-            logger.warning(
+            logger.warn(
                 f"attempted to reference from_var {from_varname} when it has not been created yet. Available vars: {variable_results.keys()}"
             )
             continue
@@ -289,7 +289,7 @@ def _check_for_json_issue(
             logger.info(f"Query {query} not in recognized list: {RECOGNIZED_JSON_PARSE_QUERIES}")
             continue
         if prefix not in variable_results.keys():
-            logger.warning(
+            logger.warn(
                 f"Variable {prefix} hasn't been defined by assignment or extract, try define it in {variable_results.keys()} first"
             )
             continue
@@ -303,7 +303,7 @@ def _check_for_json_issue(
                 variable_value = float(variable_value)
                 numeric_castable = True
             except Exception as e:
-                logger.warning(
+                logger.warn(
                     f"Numeric parse query requested but values not castable: {query_value} and {variable_value}"
                 )
         # If True/False string passed from robot layer, cast it to bool

libraries/RW/CLI/stdout_parser.py

@@ -173,7 +173,7 @@ def parse_cli_output_by_line(
             query_parts = parse_query.split("__")
             if len(query_parts) != 2:
                 if not squelch_further_warnings:
-                    logger.warning(f"Could not parse query: {parse_query}")
+                    logger.warn(f"Could not parse query: {parse_query}")
                 squelch_further_warnings = True
                 continue
             prefix = query_parts[0]
@@ -192,7 +192,7 @@ def parse_cli_output_by_line(
                         capture_group_value = float(capture_group_value)
                         numeric_castable = True
                     except Exception as e:
-                        logger.warning(
+                        logger.warn(
                             f"Numeric parse query requested but values not castable: {query_value} and {capture_group_value}"
                         )
                 # process applicable query

libraries/RW/K8sApplications/_test_parsers.py

@@ -73,7 +73,7 @@ def test_golang_report():
     with open(f"{THIS_DIR}/{TEST_DATA_DIR}/golang.log", "r") as f:
         data = f.read()
     if len(data) > MAX_LOG_LINES:
-        logger.warning(
+        logger.warn(
             f"Length of logs provided for parsing stacktraces is greater than {MAX_LOG_LINES}, be aware this could effect performance"
         )
     results = parse_stacktraces(