Merge branch 'master' into sy/kyverno-saved-views

.github/CODEOWNERS

@@ -243,6 +243,11 @@ datadog_checks_base/datadog_checks/base/checks/windows/              @DataDog/wi
 /cisco_duo/*.md                                                      @DataDog/saas-integrations @DataDog/documentation
 /cisco_duo/manifest.json                                             @DataDog/saas-integrations @DataDog/documentation
 
+/cisco_secure_endpoint/                                              @DataDog/saas-integrations
+/cisco_secure_endpoint/*.md                                          @DataDog/saas-integrations @DataDog/documentation
+/cisco_secure_endpoint/manifest.json                                 @DataDog/saas-integrations @DataDog/documentation
+/cisco_secure_endpoint/assets/logs/                                  @DataDog/saas-integrations @DataDog/documentation @DataDog/logs-backend
+
 /mimecast/                                                          @DataDog/saas-integrations
 /mimecast/*.md                                                      @DataDog/saas-integrations @DataDog/documentation
 /mimecast/manifest.json                                             @DataDog/saas-integrations @DataDog/documentation

.github/workflows/config/labeler.yml

@@ -99,6 +99,8 @@ integration/cisco_duo:
 - cisco_duo/**/*
 integration/cisco_sdwan:
 - cisco_sdwan/**/*
+integration/cisco_secure_endpoint:
+- cisco_secure_endpoint/**/*
 integration/cisco_secure_firewall:
 - cisco_secure_firewall/**/*
 integration/cisco_umbrella_dns:

argo_rollouts/README.md

@@ -82,6 +82,11 @@ See [service_checks.json][8] for a list of service checks provided by this integ
 
 Need help? Contact [Datadog support][9].
 
+## Further Reading
+
+Additional helpful documentation, links, and articles:
+
+- [Monitoring the health and performance of your container-native CI/CD pipelines][11]
 
 [1]: https://argoproj.github.io/rollouts/
 [2]: https://app.datadoghq.com/account/settings/agent/latest
@@ -93,3 +98,4 @@ Need help? Contact [Datadog support][9].
 [8]: https://github.com/DataDog/integrations-core/blob/master/argo_rollouts/assets/service_checks.json
 [9]: https://docs.datadoghq.com/help/
 [10]: https://docs.datadoghq.com/agent/kubernetes/log/
+[11]: https://www.datadoghq.com/blog/container-native-ci-cd-integrations/

argo_workflows/README.md

@@ -80,6 +80,11 @@ See [service_checks.json][8] for a list of service checks provided by this integ
 
 Need help? Contact [Datadog support][9].
 
+## Further Reading
+
+Additional helpful documentation, links, and articles:
+
+- [Monitoring the health and performance of your container-native CI/CD pipelines][12]
 
 [1]: https://argo-workflows.readthedocs.io/en/stable/
 [2]: https://app.datadoghq.com/account/settings/agent/latest
@@ -92,3 +97,4 @@ Need help? Contact [Datadog support][9].
 [9]: https://docs.datadoghq.com/help/
 [10]: https://docs.datadoghq.com/agent/kubernetes/log/
 [11]: https://argo-workflows.readthedocs.io/en/stable/metrics/
+[12]: https://www.datadoghq.com/blog/container-native-ci-cd-integrations/

argocd/README.md

@@ -181,6 +181,12 @@ See [service_checks.json][8] for a list of service checks provided by this integ
 
 Need help? Contact [Datadog support][9].
 
+## Further Reading
+
+Additional helpful documentation, links, and articles:
+
+- [Monitoring the health and performance of your container-native CI/CD pipelines][16]
+
 
 [1]: https://argo-cd.readthedocs.io/en/stable/
 [2]: https://app.datadoghq.com/account/settings/agent/latest
@@ -197,4 +203,5 @@ Need help? Contact [Datadog support][9].
 [13]: https://github.com/DataDog/integrations-core/blob/7.45.x/argocd/datadog_checks/argocd/data/conf.yaml.example#L164-L166
 [14]: https://argo-cd.readthedocs.io/en/stable/operator-manual/metrics/#exposing-application-labels-as-prometheus-metrics
 [15]: https://github.com/DataDog/integrations-core/blob/master/argocd/datadog_checks/argocd/data/conf.yaml.example#L45-L72
+[16]: https://www.datadoghq.com/blog/container-native-ci-cd-integrations/
 

cisco_sdwan/assets/monitors/device_reboot.json

@@ -8,10 +8,10 @@
   ],
   "description": "Repeated reboots are an indication of potential issues like software-related glitches, low memory conditions, corrupt software images, hardware faults, or software bugs. By identifying these concerns, this monitor ensures network stability and optimized performance.",
   "definition": {
-	"name": "[Cisco SD-WAN] Device {{hostname.name}} ({{system_ip.name}}) rebooted more than 3 times in the last 10 minutes",
+	"name": "[Cisco SD-WAN] Device {{device_hostname.name}} ({{device_ip.name}}) rebooted more than 3 times in the last 10 minutes",
 	"type": "query alert",
-	"query": "sum(last_10m):sum:cisco_sdwan.reboot.count{*} by {device_namespace,hostname,system_ip} > 3",
-	"message": "{{#is_alert}}\nSD-WAN Device {{hostname.name}} ({{system_ip.name}}) rebooted more than 3 times in the last 10 minutes.\n{{/is_alert}}\n\nTo know more about the status of your device, you can have more information from the [NDM page for the device {{device_namespace.name}}:{{system_ip.name}}](/infrastructure/devices/graph?inspectedDevice={{device_namespace.name}}%3A{{system_ip.name}}).",
+	"query": "sum(last_10m):sum:cisco_sdwan.reboot.count{*} by {device_namespace,device_hostname,device_ip,device_id} > 3",
+	"message": "{{#is_alert}}\nSD-WAN Device {{device_hostname.name}} ({{device_ip.name}}) rebooted more than 3 times in the last 10 minutes.\n{{/is_alert}}\n\nTo know more about the status of your device, you can have more information from the [NDM page for the device {{device_namespace.name}}:{{device_ip.name}}](/infrastructure/devices/graph?inspectedDevice={{device_namespace.name}}%3A{{device_ip.name}}).",
 	"tags": [],
 	"options": {
 		"thresholds": {

cisco_sdwan/assets/monitors/device_unreachable.json

@@ -8,10 +8,10 @@
   ],
   "description": "This monitor checks the reachability of Cisco SD-WAN devices within a specified namespace. It triggers an alert if a device becomes unreachable, indicating potential network connectivity issues.",
   "definition": {
-	"name": "[Cisco SD-WAN] Device unreachable alert on {{hostname.name}} in namespace {{device_namespace.name}}",
+	"name": "[Cisco SD-WAN] Device unreachable alert on {{device_hostname.name}} in namespace {{device_namespace.name}}",
 	"type": "query alert",
-	"query": "avg(last_5m):max:cisco_sdwan.device.reachable{*} by {hostname,system_ip,device_namespace} < 0.8",
-	"message": "{{#is_alert}}\nA network device {{hostname.name}} with IP {{system_ip.name}} in namespace {{device_namespace.name}} is unreachable.\n{{/is_alert}}\n{{#is_alert_recovery}}\nA network device {{hostname.name}} with IP {{system_ip.name}} in namespace {{device_namespace.name}} is reachable again.\n{{/is_alert_recovery}}\n\nTo know more about the status of your device, you can have more information from the [NDM page for the device {{device_namespace.name}}:{{system_ip.name}}](/infrastructure/devices/graph?inspectedDevice={{device_namespace.name}}%3A{{system_ip.name}}).",
+	"query": "avg(last_5m):max:cisco_sdwan.device.reachable{*} by {device_hostname,device_ip,device_namespace,device_id} < 0.8",
+	"message": "{{#is_alert}}\nA network device {{device_hostname.name}} with IP {{device_ip.name}} in namespace {{device_namespace.name}} is unreachable.\n{{/is_alert}}\n{{#is_alert_recovery}}\nA network device {{device_hostname.name}} with IP {{device_ip.name}} in namespace {{device_namespace.name}} is reachable again.\n{{/is_alert_recovery}}\n\nTo know more about the status of your device, you can have more information from the [NDM page for the device {{device_namespace.name}}:{{device_ip.name}}](/infrastructure/devices/graph?inspectedDevice={{device_namespace.name}}%3A{{device_ip.name}}).",
 	"tags": [],
 	"options": {
 		"thresholds": {

cisco_sdwan/assets/monitors/tunnel_down.json

@@ -8,10 +8,10 @@
 	],
 	"description": "This monitor detects when a Cisco SD-WAN tunnel becomes unavailable between two devices. It tracks the status of tunnels within a specified namespace and triggers an alert if a tunnel goes down, indicating potential connectivity issues.",
 	"definition": {
-		"name": "[Cisco SD-WAN] Tunnel is down between {{local_color.name}} {{hostname.name}} ({{system_ip.name}}) to {{remote_color.name}} {{remote_hostname.name}} ({{remote_system_ip.name}})",
+		"name": "[Cisco SD-WAN] Tunnel is down between {{local_color.name}} {{hostname.name}} ({{device_ip.name}}) to {{remote_color.name}} {{remote_hostname.name}} ({{remote_device_ip.name}})",
 		"type": "query alert",
-		"query": "min(last_15m):min:cisco_sdwan.tunnel.status{*} by {device_namespace,system_ip,hostname,local_color,remote_system_ip,remote_hostname,remote_color} < 1",
-		"message": "{{#is_alert}}\nSD-WAN Tunnel is down between device {{hostname.name}} ({{system_ip.name}}), color {{local_color.name}} to device {{remote_hostname.name}} ({{remote_system_ip.name}}), color {{remote_color.name}}.\n{{/is_alert}}\n\n{{#is_alert_recovery}}\nSD-WAN Tunnel is back up between device {{hostname.name}} ({{system_ip.name}}), color {{local_color.name}} to device {{remote_hostname.name}} ({{remote_system_ip.name}}), color {{remote_color.name}}.\n{{/is_alert_recovery}}\n\nTo know more about the status of your device, you can have more information from the [NDM page for the device {{device_namespace.name}}:{{system_ip.name}}](/infrastructure/devices/graph?inspectedDevice={{device_namespace.name}}%3A{{system_ip.name}}).",
+		"query": "min(last_15m):min:cisco_sdwan.tunnel.status{*} by {device_id,device_namespace,device_ip,device_hostname,local_color,remote_device_ip,remote_device_hostname,remote_color} < 1",
+		"message": "{{#is_alert}}\nSD-WAN Tunnel is down between device {{device_hostname.name}} ({{device_ip.name}}), color {{local_color.name}} to device {{remote_device_hostname.name}} ({{remote_device_ip.name}}), color {{remote_color.name}}.\n{{/is_alert}}\n\n{{#is_alert_recovery}}\nSD-WAN Tunnel is back up between device {{device_hostname.name}} ({{device_ip.name}}), color {{local_color.name}} to device {{remote_device_hostname.name}} ({{remote_device_ip.name}}), color {{remote_color.name}}.\n{{/is_alert_recovery}}\n\nTo know more about the status of your device, you can have more information from the [NDM page for the device {{device_namespace.name}}:{{device_ip.name}}](/infrastructure/devices/graph?inspectedDevice={{device_namespace.name}}%3A{{device_ip.name}}).",
 		"tags": [],
 		"options": {
 			"thresholds": {

cisco_secure_endpoint/CHANGELOG.md

@@ -0,0 +1,7 @@
+# CHANGELOG - cisco_secure_endpoint
+
+## 1.0.0 / 2024-06-17
+
+***Added***:
+
+* Initial Release

cisco_secure_endpoint/README.md

@@ -0,0 +1,42 @@
+# Agent Check: cisco_secure_endpoint
+
+## Overview
+
+This check monitors [Cisco Secure Endpoint][1].
+
+## Setup
+
+### Installation
+
+The Cisco Secure Endpoint check is included in the [Datadog Agent][2] package.
+No additional installation is needed on your server.
+
+### Configuration
+
+1. <List of steps to configure this integration>
+
+### Validation
+
+<Steps to validate integration is functioning as expected>
+
+## Data Collected
+
+### Metrics
+
+The Cisco Secure Endpoint integration does not include any metrics.
+
+### Service Checks
+
+The Cisco Secure Endpoint integration does not include any service checks.
+
+### Events
+
+The Cisco Secure Endpoint integration does not include any events.
+
+## Troubleshooting
+
+Need help? Contact [Datadog support][3].
+
+[1]: **LINK_TO_INTEGRATION_SITE**
+[2]: https://app.datadoghq.com/account/settings#agent
+[3]: https://docs.datadoghq.com/help/

cisco_secure_endpoint/assets/service_checks.json

@@ -0,0 +1 @@
+[]

cisco_secure_endpoint/manifest.json

@@ -0,0 +1,40 @@
+{
+    "manifest_version": "2.0.0",
+    "app_uuid": "9636c2eb-34f6-4aa4-a236-c39e47b21c79",
+    "app_id": "cisco-secure-endpoint",
+    "display_on_public_website": false,
+    "tile": {
+        "overview": "README.md#Overview",
+        "configuration": "README.md#Setup",
+        "support": "README.md#Support",
+        "changelog": "CHANGELOG.md",
+        "description": "Gain insights into Cisco Secure Endpoint logs",
+        "title": "cisco-secure-endpoint",
+        "media": [],
+        "classifier_tags": [
+            "Category::Log Collection",
+            "Category::Security",
+            "Submitted Data Type::Logs"
+        ]
+    },
+    "assets": {
+        "integration": {
+            "auto_install": false,
+            "source_type_id": 18601889,
+            "source_type_name": "Cisco Secure Endpoint",
+            "events": {
+                "creates_events": false
+            },
+            "service_checks": {
+                "metadata_path": "assets/service_checks.json"
+            }
+        }
+    },
+    "author": {
+        "support_email": "help@datadoghq.com",
+        "name": "Datadog",
+        "homepage": "https://www.datadoghq.com",
+        "sales_email": "info@datadoghq.com"
+    },
+    "oauth": {}
+}

fluxcd/README.md

@@ -92,6 +92,7 @@ Need help? Contact [Datadog support][9].
 Additional helpful documentation, links, and articles:
 
 - [Monitoring your container-native technologies][11]
+- [Monitoring the health and performance of your container-native CI/CD pipelines][13]
 
 
 [1]: https://fluxcd.io/
@@ -106,3 +107,4 @@ Additional helpful documentation, links, and articles:
 [10]: https://docs.datadoghq.com/agent/guide/use-community-integrations/?tab=agentv721v621#installation
 [11]: https://www.datadoghq.com/blog/container-native-integrations/#cicd-with-flux
 [12]: https://docs.datadoghq.com/agent/kubernetes/log/
+[13]: https://www.datadoghq.com/blog/container-native-ci-cd-integrations/

kyverno/assets/monitors/controller_drops.json

@@ -0,0 +1,33 @@
+{
+    "version": 2,
+    "created_at": "2024-07-22",
+    "last_updated_at": "2024-07-22",
+    "title": "Controller element is dropped",
+    "description": "Dropping occurs when the controller tries to process an item several times and fails each time.  This usually indicates an unrecoverable error. This monitor alerts when a controller reports a dropped element.",
+    "definition": {
+        "name": "[Kyverno] Controller Element Drops",
+        "type": "query alert",
+        "query": "sum(last_5m):sum:kyverno.controller.drop.count{*} by {controller_name,kube_cluster_name}.as_count() >= 1",
+        "message": "{{#is_alert}}\n\nKyverno Controller: {{controller_name.name}} reported {{value}} dropped element in {{kube_cluster_name.name}} cluster.\n\nDropping usually indicates an unrecoverable error, the controller retried to process an item a couple of times and after failing every try drop the item.\n\n{{/is_alert}}",
+        "tags": [
+            "integration:kyverno"
+        ],
+        "options": {
+            "thresholds": {
+                "critical": 1
+            },
+            "notify_audit": false,
+            "include_tags": true,
+            "new_group_delay": 60,
+            "notify_no_data": false,
+            "silenced": {}
+        },
+        "priority": null,
+        "restriction_policy": {
+            "bindings": []
+        }
+    },
+    "tags": [
+        "integration:kyverno"
+    ]
+}

kyverno/manifest.json

@@ -45,6 +45,9 @@
         "metadata_path": "assets/service_checks.json"
       }
     },
+   "monitors": {
+      "metadata_path": "assets/monitors/controller_drops.json"
+    },
     "saved_views": {
       "Kyverno Logs Overview": "assets/saved_views/logs_overview.json",
       "Kyverno Error Logs Overview": "assets/saved_views/error_logs_overview.json"

postgres/changelog.d/18081.fixed

@@ -0,0 +1 @@
+Fixed postgres check crash when pg_stat_statements was not yet loaded

postgres/datadog_checks/postgres/statements.py

@@ -308,7 +308,10 @@ def _load_pg_stat_statements(self):
             if self._check.pg_settings.get("track_io_timing") != "on":
                 desired_columns -= PG_STAT_STATEMENTS_TIMING_COLUMNS
 
-            pg_stat_statements_max = int(self._check.pg_settings.get("pg_stat_statements.max"))
+            pg_stat_statements_max_setting = self._check.pg_settings.get("pg_stat_statements.max")
+            pg_stat_statements_max = int(
+                pg_stat_statements_max_setting if pg_stat_statements_max_setting is not None else 0
+            )
             if pg_stat_statements_max > self._pg_stat_statements_max_warning_threshold:
                 self._check.record_warning(
                     DatabaseConfigurationError.high_pg_stat_statements_max,

sqlserver/assets/monitors/sqlserver_db_not_sync.json

@@ -6,7 +6,7 @@
   "tags": [
     "integration:sql-server"
   ],
-  "description": "Backups are essential for data protection, disaster recovery, and maintenance operations. This monitor tracks how synchronized your database is with its backup. Alerts help to avoid scenarios where backups are are incomplete, leaving your data at risk.",
+  "description": "Backups are essential for data protection, disaster recovery, and maintenance operations. This monitor checks if your database is marked for replication sync. Alerts help to avoid scenarios where databases are not synced, leaving your data at risk.",
   "definition": {
     "message": "SQLServer database is not marked for replication sync. It may not be synced with its backup.",
     "name": "[SQLServer] Database is not marked for replication sync",
@@ -31,4 +31,4 @@
     ],
     "type": "query alert"
   }
-}
+}

tekton/README.md

@@ -42,6 +42,12 @@ See [service_checks.json][8] for a list of service checks provided by this integ
 
 Need help? Contact [Datadog support][9].
 
+## Further Reading
+
+Additional helpful documentation, links, and articles:
+
+- [Monitoring the health and performance of your container-native CI/CD pipelines][11]
+
 
 [1]: https://tekton.dev/
 [2]: https://app.datadoghq.com/account/settings/agent/latest
@@ -52,4 +58,5 @@ Need help? Contact [Datadog support][9].
 [7]: https://github.com/DataDog/integrations-core/blob/master/tekton/metadata.csv
 [8]: https://github.com/DataDog/integrations-core/blob/master/tekton/assets/service_checks.json
 [9]: https://docs.datadoghq.com/help/
-[10]: https://docs.datadoghq.com/integrations/openmetrics/
+[10]: https://docs.datadoghq.com/integrations/openmetrics/
+[11]: https://www.datadoghq.com/blog/container-native-ci-cd-integrations/