From e8946ab9784672c5ebbf324c08240a2f06b4e2f0 Mon Sep 17 00:00:00 2001 From: Avital Pinnick Date: Wed, 1 Mar 2023 14:38:56 +0200 Subject: [PATCH] [enterprise-4.13] CNV-17386: Consolidate support files Signed-off-by: Avital Pinnick --- _topic_maps/_topic_map.yml | 45 +++++------ modules/cluster-logging-about-components.adoc | 13 ---- .../monitoring-about-cluster-monitoring.adoc | 1 - modules/telemetry-about-telemetry.adoc | 3 +- ...lemetry-what-information-is-collected.adoc | 9 +-- ... virt-about-dv-conditions-and-events.adoc} | 12 +-- .../virt-about-the-overview-dashboard.adoc | 1 - modules/virt-about-vm-events.adoc | 14 ---- ...zing-datavolume-conditions-and-events.adoc | 68 ++++++++--------- modules/virt-collecting-data-about-vms.adoc | 24 ------ ...ollecting-data-about-your-environment.adoc | 22 ------ modules/virt-common-error-messages.adoc | 2 +- ... => virt-defining-watchdog-device-vm.adoc} | 28 +++---- modules/virt-installing-a-watchdog.adoc | 33 --------- modules/virt-installing-watchdog-agent.adoc | 35 +++++++++ modules/virt-live-migration-metrics.adoc | 7 +- modules/virt-template-vm-probe-config.adoc | 57 -------------- modules/virt-viewing-logs-cli.adoc | 4 +- .../virt-viewing-namespace-events-cli.adoc | 19 ----- modules/virt-viewing-resource-events-cli.adoc | 32 -------- ...virt-viewing-virtual-machine-logs-web.adoc | 14 ++-- modules/virt-viewing-vm-events-web.adoc | 18 ----- .../eco-self-node-remediation-operator.adoc | 2 +- virt/live_migration/virt-live-migration.adoc | 2 +- virt/live_migration/virt-migrate-vmi.adoc | 10 ++- virt/support/monitoring/_attributes | 1 + virt/support/monitoring/images | 1 + virt/support/monitoring/modules | 1 + virt/support/monitoring/snippets | 1 + .../virt-exposing-custom-metrics-for-vms.adoc | 14 ++-- .../monitoring/virt-monitoring-overview.adoc | 24 ++++++ .../monitoring/virt-monitoring-vm-health.adoc | 54 ++++++++++++++ .../virt-prometheus-queries.adoc | 6 +- .../virt-running-cluster-checkups.adoc | 7 +- virt/support/virt-collecting-virt-data.adoc | 62 ++++++++++------ ...tavolumes-using-events-and-conditions.adoc | 12 --- virt/support/virt-events.adoc | 18 ----- virt/support/virt-logs.adoc | 15 ---- virt/support/virt-monitor-vmi-migration.adoc | 25 ------- virt/support/virt-monitoring-vm-health.adoc | 26 ------- .../virt-openshift-cluster-monitoring.adoc | 25 ------- virt/support/virt-support-overview.adoc | 74 +++++++++++++++++++ virt/support/virt-troubleshooting.adoc | 50 +++++++++++++ ...t-using-dashboard-to-get-cluster-info.adoc | 13 ---- virt/virt-4-13-release-notes.adoc | 6 +- virt/virt-getting-started.adoc | 1 - .../virt-configuring-a-watchdog.adoc | 23 ------ 47 files changed, 388 insertions(+), 546 deletions(-) rename modules/{virt-about-conditions-and-events.adoc => virt-about-dv-conditions-and-events.adoc} (65%) delete mode 100644 modules/virt-about-vm-events.adoc delete mode 100644 modules/virt-collecting-data-about-vms.adoc delete mode 100644 modules/virt-collecting-data-about-your-environment.adoc rename modules/{virt-defining-a-watchdog.adoc => virt-defining-watchdog-device-vm.adoc} (56%) delete mode 100644 modules/virt-installing-a-watchdog.adoc create mode 100644 modules/virt-installing-watchdog-agent.adoc delete mode 100644 modules/virt-template-vm-probe-config.adoc delete mode 100644 modules/virt-viewing-namespace-events-cli.adoc delete mode 100644 modules/virt-viewing-resource-events-cli.adoc delete mode 100644 modules/virt-viewing-vm-events-web.adoc create mode 120000 virt/support/monitoring/_attributes create mode 120000 virt/support/monitoring/images create mode 120000 virt/support/monitoring/modules create mode 120000 virt/support/monitoring/snippets rename virt/support/{ => monitoring}/virt-exposing-custom-metrics-for-vms.adoc (61%) create mode 100644 virt/support/monitoring/virt-monitoring-overview.adoc create mode 100644 virt/support/monitoring/virt-monitoring-vm-health.adoc rename virt/support/{ => monitoring}/virt-prometheus-queries.adoc (79%) rename virt/support/{ => monitoring}/virt-running-cluster-checkups.adoc (63%) delete mode 100644 virt/support/virt-diagnosing-datavolumes-using-events-and-conditions.adoc delete mode 100644 virt/support/virt-events.adoc delete mode 100644 virt/support/virt-logs.adoc delete mode 100644 virt/support/virt-monitor-vmi-migration.adoc delete mode 100644 virt/support/virt-monitoring-vm-health.adoc delete mode 100644 virt/support/virt-openshift-cluster-monitoring.adoc create mode 100644 virt/support/virt-support-overview.adoc create mode 100644 virt/support/virt-troubleshooting.adoc delete mode 100644 virt/support/virt-using-dashboard-to-get-cluster-info.adoc delete mode 100644 virt/virtual_machines/advanced_vm_management/virt-configuring-a-watchdog.adoc diff --git a/_topic_maps/_topic_map.yml b/_topic_maps/_topic_map.yml index ee524e59d1..15d3dc2990 100644 --- a/_topic_maps/_topic_map.yml +++ b/_topic_maps/_topic_map.yml @@ -3569,8 +3569,6 @@ Topics: File: virt-configuring-vgpu-passthrough - Name: Configuring mediated devices File: virt-configuring-mediated-devices - - Name: Configuring a watchdog device - File: virt-configuring-a-watchdog - Name: Automatic importing and updating of pre-defined boot sources File: virt-automatic-bootsource-updates - Name: Enabling descheduler evictions on virtual machines @@ -3710,35 +3708,32 @@ Topics: - Name: Preventing node reconciliation File: virt-preventing-node-reconciliation # Removed the Node Networking content from the topic map because this section is now part of the OCP docs -# Logging, events, and monitoring +# Support, was Logging, events, and monitoring - Name: Support Dir: support Topics: - - Name: Viewing OpenShift Virtualization logs - File: virt-logs - - Name: Viewing events - File: virt-events - - Name: Monitoring live migration - File: virt-monitor-vmi-migration - - Name: Diagnosing data volumes using events and conditions - File: virt-diagnosing-datavolumes-using-events-and-conditions - - Name: Monitoring virtual machine health with health probes - File: virt-monitoring-vm-health - - Name: Viewing cluster information - File: virt-using-dashboard-to-get-cluster-info - - Name: OpenShift cluster monitoring, logging, and Telemetry - File: virt-openshift-cluster-monitoring - - Name: Running OpenShift cluster checkups - File: virt-running-cluster-checkups - - Name: Prometheus queries for virtual resources - File: virt-prometheus-queries - - Name: Exposing custom metrics for virtual machines - File: virt-exposing-custom-metrics-for-vms - - Name: OpenShift Virtualization runbooks - File: virt-runbooks + - Name: Support overview + File: virt-support-overview - Name: Collecting data for Red Hat Support File: virt-collecting-virt-data Distros: openshift-enterprise + - Name: Monitoring + Dir: monitoring + Topics: + - Name: Monitoring overview + File: virt-monitoring-overview + - Name: OpenShift cluster checkup framework + File: virt-running-cluster-checkups + - Name: Prometheus queries for virtual resources + File: virt-prometheus-queries + - Name: Virtual machine custom metrics + File: virt-exposing-custom-metrics-for-vms + - Name: Virtual machine health checks + File: virt-monitoring-vm-health + - Name: Troubleshooting + File: virt-troubleshooting + - Name: Runbooks + File: virt-runbooks - Name: Backup and restore Dir: backup_restore Topics: diff --git a/modules/cluster-logging-about-components.adoc b/modules/cluster-logging-about-components.adoc index fd3d5ba0d2..14d79d9bfe 100644 --- a/modules/cluster-logging-about-components.adoc +++ b/modules/cluster-logging-about-components.adoc @@ -1,12 +1,6 @@ // Module included in the following assemblies: // // * logging/cluster-logging.adoc -// * virt/support/virt-openshift-cluster-monitoring.adoc - - -ifeval::["{context}" == "virt-openshift-cluster-monitoring"] -:virt-logging: -endif::[] :_content-type: CONCEPT [id="cluster-logging-about-components_{context}"] @@ -21,10 +15,3 @@ The major components of the {logging} are: * log store - This is where the logs are stored. The default implementation is Elasticsearch. You can use the default Elasticsearch log store or forward logs to external log stores. The default log store is optimized and tested for short-term storage. * visualization - This is the UI component you can use to view logs, graphs, charts, and so forth. The current implementation is Kibana. -ifndef::virt-logging[] -This document might refer to log store or Elasticsearch, visualization or Kibana, collection or Fluentd, interchangeably, except where noted. -endif::virt-logging[] - -ifeval::["{context}" == "virt-openshift-cluster-monitoring"] -:!virt-logging: -endif::[] diff --git a/modules/monitoring-about-cluster-monitoring.adoc b/modules/monitoring-about-cluster-monitoring.adoc index df32740a52..80596811f7 100644 --- a/modules/monitoring-about-cluster-monitoring.adoc +++ b/modules/monitoring-about-cluster-monitoring.adoc @@ -1,6 +1,5 @@ // Module included in the following assemblies: // -// * virt/support/virt-openshift-cluster-monitoring.adoc // * monitoring/monitoring-overview.adoc // This module uses a conditionalized title so that the module diff --git a/modules/telemetry-about-telemetry.adoc b/modules/telemetry-about-telemetry.adoc index 6da1d9ce15..598000ef44 100644 --- a/modules/telemetry-about-telemetry.adoc +++ b/modules/telemetry-about-telemetry.adoc @@ -1,13 +1,12 @@ // Module included in the following assemblies: // -// * virt/support/virt-openshift-cluster-monitoring.adoc // * support/remote_health_monitoring/about-remote-health-monitoring.adoc :_content-type: CONCEPT [id="telemetry-about-telemetry_{context}"] = About Telemetry -Telemetry sends a carefully chosen subset of the cluster monitoring metrics to Red Hat. The Telemeter Client fetches the metrics values every four minutes and thirty seconds and uploads the data to Red Hat. These metrics are described in this document. +Telemetry sends a carefully chosen subset of the cluster monitoring metrics to Red Hat. The Telemeter Client fetches the metrics values every four minutes and thirty seconds and uploads the data to Red Hat. These metrics are described in this document. This stream of data is used by Red Hat to monitor the clusters in real-time and to react as necessary to problems that impact our customers. It also allows Red Hat to roll out {product-title} upgrades to customers to minimize service impact and continuously improve the upgrade experience. diff --git a/modules/telemetry-what-information-is-collected.adoc b/modules/telemetry-what-information-is-collected.adoc index c1aebcf6f5..671349adf7 100644 --- a/modules/telemetry-what-information-is-collected.adoc +++ b/modules/telemetry-what-information-is-collected.adoc @@ -1,12 +1,8 @@ // Module included in the following assemblies: // -// * virt/support/virt-openshift-cluster-monitoring.adoc // * support/remote_health_monitoring/about-remote-health-monitoring.adoc -ifeval::["{context}" == "virt-openshift-cluster-monitoring"] -:virt-cluster: -endif::[] - +:_content-type: REFERENCE [id="what-information-is-collected_{context}"] = Information collected by Telemetry @@ -35,6 +31,3 @@ endif::openshift-dedicated[] Telemetry does not collect identifying information such as user names or passwords. Red Hat does not intend to collect personal information. If Red Hat discovers that personal information has been inadvertently received, Red Hat will delete such information. To the extent that any telemetry data constitutes personal data, please refer to the link:https://www.redhat.com/en/about/privacy-policy[Red Hat Privacy Statement] for more information about Red Hat's privacy practices. -ifeval::["{context}" == "virt-openshift-cluster-monitoring"] -:!virt-cluster: -endif::[] diff --git a/modules/virt-about-conditions-and-events.adoc b/modules/virt-about-dv-conditions-and-events.adoc similarity index 65% rename from modules/virt-about-conditions-and-events.adoc rename to modules/virt-about-dv-conditions-and-events.adoc index 927107bcf6..f659f66d41 100644 --- a/modules/virt-about-conditions-and-events.adoc +++ b/modules/virt-about-dv-conditions-and-events.adoc @@ -1,12 +1,12 @@ // Module included in the following assemblies: // -// * virt/support/virt-diagnosing-datavolumes-using-events-and-conditions.adoc +// * virt/support/virt-troubleshooting.adoc :_content-type: CONCEPT -[id="virt-about-conditions-and-events.adoc_{context}"] -= About conditions and events +[id="virt-about-dv-conditions-and-events.adoc_{context}"] += About data volume conditions and events -Diagnose data volume issues by examining the output of the `Conditions` and `Events` sections +You can diagnose data volume issues by examining the output of the `Conditions` and `Events` sections generated by the command: [source,terminal] @@ -14,7 +14,7 @@ generated by the command: $ oc describe dv ---- -There are three `Types` in the `Conditions` section that display: +The `Conditions` section displays the following `Types`: * `Bound` * `Running` @@ -29,7 +29,7 @@ The `Events` section provides the following additional information: The output from `oc describe` does not always contains `Events`. -An event is generated when either `Status`, `Reason`, or `Message` changes. +An event is generated when the `Status`, `Reason`, or `Message` changes. Both conditions and events react to changes in the state of the data volume. For example, if you misspell the URL during an import operation, the import diff --git a/modules/virt-about-the-overview-dashboard.adoc b/modules/virt-about-the-overview-dashboard.adoc index 31c0211fe8..79d461b27c 100644 --- a/modules/virt-about-the-overview-dashboard.adoc +++ b/modules/virt-about-the-overview-dashboard.adoc @@ -1,6 +1,5 @@ // Module included in the following assemblies: // -// * virt/support/virt-using-dashboard-to-get-cluster-info.adoc // * web_console/using-dashboard-to-get-cluster-information.adoc ifeval::["{context}" == "virt-using-dashboard-to-get-cluster-info"] diff --git a/modules/virt-about-vm-events.adoc b/modules/virt-about-vm-events.adoc deleted file mode 100644 index d488b5fa75..0000000000 --- a/modules/virt-about-vm-events.adoc +++ /dev/null @@ -1,14 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/support/virt-events.adoc - -:_content-type: CONCEPT -[id="virt-about-vm-events_{context}"] -= About virtual machine events - -{product-title} events are records of important life-cycle information in a -namespace and are useful for monitoring and troubleshooting resource -scheduling, creation, and deletion issues. - -{VirtProductName} adds events for virtual machines and virtual machine instances. These -can be viewed from either the web console or the CLI. diff --git a/modules/virt-analyzing-datavolume-conditions-and-events.adoc b/modules/virt-analyzing-datavolume-conditions-and-events.adoc index 40f080b1bf..7013b97684 100644 --- a/modules/virt-analyzing-datavolume-conditions-and-events.adoc +++ b/modules/virt-analyzing-datavolume-conditions-and-events.adoc @@ -1,9 +1,9 @@ // Module included in the following assemblies: // -// * virt/support/virt-analyzing-datavolumes-using-events-and-conditions.adoc +// * virt/support/virt-troubleshooting.adoc [id="virt-analyzing-datavolume-conditions-and-events_{context}"] -= Analyzing data volumes using conditions and events += Analyzing data volume conditions and events By inspecting the `Conditions` and `Events` sections generated by the `describe` command, you determine the state of the data volume @@ -16,7 +16,7 @@ There are many different combinations of conditions. Each must be evaluated in i Examples of various combinations follow. -* `Bound` – A successfully bound PVC displays in this example. +* `Bound` - A successfully bound PVC displays in this example. + Note that the `Type` is `Bound`, so the `Status` is `True`. If the PVC is not bound, the `Status` is `False`. @@ -33,21 +33,21 @@ in this case `datavolume-controller`: [source,terminal] ---- Status: - Conditions: - Last Heart Beat Time: 2020-07-15T03:58:24Z - Last Transition Time: 2020-07-15T03:58:24Z - Message: PVC win10-rootdisk Bound - Reason: Bound - Status: True - Type: Bound - - Events: - Type Reason Age From Message - ---- ------ ---- ---- ------- - Normal Bound 24s datavolume-controller PVC example-dv Bound + Conditions: + Last Heart Beat Time: 2020-07-15T03:58:24Z + Last Transition Time: 2020-07-15T03:58:24Z + Message: PVC win10-rootdisk Bound + Reason: Bound + Status: True + Type: Bound +... + Events: + Type Reason Age From Message + ---- ------ ---- ---- ------- + Normal Bound 24s datavolume-controller PVC example-dv Bound ---- -* `Running` – In this case, note that `Type` is `Running` and `Status` is `False`, +* `Running` - In this case, note that `Type` is `Running` and `Status` is `False`, indicating that an event has occurred that caused an attempted operation to fail, changing the Status from `True` to `False`. + @@ -67,19 +67,19 @@ attempting to access the data volume: [source,terminal] ---- Status: - Conditions: - Last Heart Beat Time: 2020-07-15T04:31:39Z - Last Transition Time: 2020-07-15T04:31:39Z - Message: Import Complete - Reason: Completed - Status: False - Type: Running - - Events: - Type Reason Age From Message - ---- ------ ---- ---- ------- - Warning Error 12s (x2 over 14s) datavolume-controller Unable to connect - to http data source: expected status code 200, got 404. Status: 404 Not Found + Conditions: + Last Heart Beat Time: 2020-07-15T04:31:39Z + Last Transition Time: 2020-07-15T04:31:39Z + Message: Import Complete + Reason: Completed + Status: False + Type: Running +... + Events: + Type Reason Age From Message + ---- ------ ---- ---- ------- + Warning Error 12s (x2 over 14s) datavolume-controller Unable to connect + to http data source: expected status code 200, got 404. Status: 404 Not Found ---- * `Ready` – If `Type` is `Ready` and `Status` is `True`, then the data volume is ready @@ -90,9 +90,9 @@ used, the `Status` is `False`: [source,terminal] ---- Status: - Conditions: - Last Heart Beat Time: 2020-07-15T04:31:39Z - Last Transition Time: 2020-07-15T04:31:39Z - Status: True - Type: Ready + Conditions: + Last Heart Beat Time: 2020-07-15T04:31:39Z + Last Transition Time: 2020-07-15T04:31:39Z + Status: True + Type: Ready ---- diff --git a/modules/virt-collecting-data-about-vms.adoc b/modules/virt-collecting-data-about-vms.adoc deleted file mode 100644 index ae95c91cc1..0000000000 --- a/modules/virt-collecting-data-about-vms.adoc +++ /dev/null @@ -1,24 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/support/virt-collecting-virt-data.adoc - -:_content-type: PROCEDURE -[id="virt-collecting-data-about-vms_{context}"] -= Collecting data about virtual machines - -Collecting data about malfunctioning virtual machines (VMs) minimizes the time required to analyze and determine the root cause. - -.Prerequisites - -* Windows VMs: -** Record the Windows patch update details for Red Hat Support. -** Install the latest version of the VirtIO drivers. The VirtIO drivers include the QEMU guest agent. -** If Remote Desktop Protocol (RDP) is enabled, try to connect to the VMs with RDP to determine whether there is a problem with the connection software. - -.Procedure - -. Collect detailed `must-gather` data about the malfunctioning VMs. -. Collect screenshots of VMs that have crashed before you restart them. -. Record factors that the malfunctioning VMs have in common. For example, the VMs have the same host or network. -// . Collect memory dumps from VMs _before_ remediation attempts. -// Uncomment this line for CNV-20256. diff --git a/modules/virt-collecting-data-about-your-environment.adoc b/modules/virt-collecting-data-about-your-environment.adoc deleted file mode 100644 index fc9e576bcc..0000000000 --- a/modules/virt-collecting-data-about-your-environment.adoc +++ /dev/null @@ -1,22 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/support/virt-collecting-virt-data.adoc - -:_content-type: PROCEDURE -[id="virt-collecting-data-about-your-environment_{context}"] -= Collecting data about your environment - -Collecting data about your environment minimizes the time required to analyze and determine the root cause. - -.Prerequisites - -* Set the retention time for Prometheus metrics data to a minimum of seven days. -* Configure the Alertmanager to capture relevant alerts and to send them to a dedicated mailbox so that they can be viewed and persisted outside the cluster. -* Record the exact number of affected nodes and virtual machines. - -.Procedure - -. Collect `must-gather` data for the cluster by using the default `must-gather` image. -. Collect `must-gather` data for {rh-storage-first}, if necessary. -. Collect `must-gather` data for {VirtProductName} by using the {VirtProductName} `must-gather` image. -. Collect Prometheus metrics for the cluster. \ No newline at end of file diff --git a/modules/virt-common-error-messages.adoc b/modules/virt-common-error-messages.adoc index 91ab0df617..dee79d7110 100644 --- a/modules/virt-common-error-messages.adoc +++ b/modules/virt-common-error-messages.adoc @@ -1,6 +1,6 @@ // Module included in the following assemblies: // -// * virt/support/virt-logs.adoc +// * virt/support/virt-troubleshooting.adoc :_content-type: REFERENCE [id="virt-common-error-messages_{context}"] diff --git a/modules/virt-defining-a-watchdog.adoc b/modules/virt-defining-watchdog-device-vm.adoc similarity index 56% rename from modules/virt-defining-a-watchdog.adoc rename to modules/virt-defining-watchdog-device-vm.adoc index 039dd21a3d..b2b80b38b0 100644 --- a/modules/virt-defining-a-watchdog.adoc +++ b/modules/virt-defining-watchdog-device-vm.adoc @@ -1,24 +1,20 @@ // Module included in the following assemblies: // -// * virt/virtual_machines/advanced_vm_management/virt-configuring-a-watchdog.adoc +// * virt/support/monitoring/virt-monitoring-vm-health.adoc :_content-type: PROCEDURE -[id="virt-defining-a-watchdog"] -= Defining a watchdog device +[id="virt-defining-watchdog-device-vm"] += Configuring a watchdog device for the virtual machine -Define how the watchdog proceeds when the operating system (OS) no longer responds. +You configure a watchdog device for the virtual machine (VM). -.Available actions -[horizontal] -`poweroff`:: The virtual machine (VM) powers down immediately. If `spec.running` is set to `true`, or `spec.runStrategy` is not set to `manual`, then the VM reboots. -`reset`:: The VM reboots in place and the guest OS cannot react. Because the length of time required for the guest OS to reboot can cause liveness probes to timeout, use of this option is discouraged. This timeout can extend the time it takes the VM to reboot if cluster-level protections notice the liveness probe failed and forcibly reschedule it. -`shutdown`:: The VM gracefully powers down by stopping all services. +.Prerequisites +* The VM must have kernel support for an `i6300esb` watchdog device. {op-system-base-full} images support `i6300esb`. .Procedure -. Create a YAML file with the following contents: - +. Create a `YAML` file with the following contents: + [source,yaml] ---- @@ -32,7 +28,7 @@ spec: running: false template: metadata: - labels: + labels: kubevirt.io/vm: vm2-rhel84-watchdog spec: domain: @@ -43,15 +39,13 @@ spec: action: "poweroff" <1> ... ---- -<1> Specify the `watchdog` action (`poweroff`, `reset`, or `shutdown`). - +<1> Specify `poweroff`, `reset`, or `shutdown`. + The example above configures the `i6300esb` watchdog device on a RHEL8 VM with the poweroff action and exposes the device as `/dev/watchdog`. + This device can now be used by the watchdog binary. . Apply the YAML file to your cluster by running the following command: - + [source,yaml] ---- @@ -68,7 +62,6 @@ This procedure is provided for testing watchdog functionality only and must not -- . Run the following command to verify that the VM is connected to the watchdog device: - + [source,terminal] ---- @@ -77,7 +70,6 @@ $ lspci | grep watchdog -i . Run one of the following commands to confirm the watchdog is active: - * Trigger a kernel panic: + [source,terminal] @@ -85,7 +77,7 @@ $ lspci | grep watchdog -i # echo c > /proc/sysrq-trigger ---- -* Terminate the watchdog service: +* Stop the watchdog service: + [source,terminal] ---- diff --git a/modules/virt-installing-a-watchdog.adoc b/modules/virt-installing-a-watchdog.adoc deleted file mode 100644 index 921b1c2f4c..0000000000 --- a/modules/virt-installing-a-watchdog.adoc +++ /dev/null @@ -1,33 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/virtual_machines/advanced_vm_management/virt-configuring-a-watchdog.adoc - -:_content-type: PROCEDURE -[id="virt-installing-a-watchdog_{context}"] -= Installing a watchdog device - -Install the `watchdog` package on your virtual machine and start the watchdog service. - -.Procedure - -. As a root user, install the `watchdog` package and dependencies: -+ -[source,terminal] ----- -# yum install watchdog ----- - -. Uncomment the following line in the `/etc/watchdog.conf` file, and save the changes: -+ -[source,terminal] ----- -#watchdog-device = /dev/watchdog ----- - -. Enable the watchdog service to start on boot: - -+ -[source,terminal] ----- -# systemctl enable --now watchdog.service ----- diff --git a/modules/virt-installing-watchdog-agent.adoc b/modules/virt-installing-watchdog-agent.adoc new file mode 100644 index 0000000000..e64399c36d --- /dev/null +++ b/modules/virt-installing-watchdog-agent.adoc @@ -0,0 +1,35 @@ +// Module included in the following assemblies: +// +// * virt/support/monitoring/virt-monitoring-vm-health.adoc + +:_content-type: PROCEDURE +[id="virt-installing-watchdog-agent_{context}"] += Installing the watchdog agent on the guest + +You install the watchdog agent on the guest and start the `watchdog` service. + +.Procedure + +. Log in to the virtual machine as root user. + +. Install the `watchdog` package and its dependencies: ++ +[source,terminal] +---- +# yum install watchdog +---- + +. Uncomment the following line in the `/etc/watchdog.conf` file and save the changes: ++ +[source,terminal] +---- +#watchdog-device = /dev/watchdog +---- + +. Enable the `watchdog` service to start on boot: + ++ +[source,terminal] +---- +# systemctl enable --now watchdog.service +---- diff --git a/modules/virt-live-migration-metrics.adoc b/modules/virt-live-migration-metrics.adoc index 7be47a5c90..823c768e54 100644 --- a/modules/virt-live-migration-metrics.adoc +++ b/modules/virt-live-migration-metrics.adoc @@ -1,6 +1,5 @@ // Module included in the following assemblies: // -// * virt/support/virt-monitor-vmi-migration.adoc // * virt/support/virt-prometheus-queries.adoc :_content-type: REFERENCE @@ -9,11 +8,11 @@ The following metrics can be queried to show live migration status: -`kubevirt_migrate_vmi_data_processed_bytes`:: The amount of guest operating system (OS) data that has migrated to the new virtual machine (VM). Type: Gauge. +`kubevirt_migrate_vmi_data_processed_bytes`:: The amount of guest operating system data that has migrated to the new virtual machine (VM). Type: Gauge. -`kubevirt_migrate_vmi_data_remaining_bytes`:: The amount of guest OS data that remains to be migrated. Type: Gauge. +`kubevirt_migrate_vmi_data_remaining_bytes`:: The amount of guest operating system data that remains to be migrated. Type: Gauge. -`kubevirt_migrate_vmi_dirty_memory_rate_bytes`:: The rate at which memory is becoming dirty in the guest OS. Dirty memory is data that has been changed but not yet written to disk. Type: Gauge. +`kubevirt_migrate_vmi_dirty_memory_rate_bytes`:: The rate at which memory is becoming dirty in the guest operating system. Dirty memory is data that has been changed but not yet written to disk. Type: Gauge. `kubevirt_migrate_vmi_pending_count`:: The number of pending migrations. Type: Gauge. diff --git a/modules/virt-template-vm-probe-config.adoc b/modules/virt-template-vm-probe-config.adoc deleted file mode 100644 index fdf6664cb4..0000000000 --- a/modules/virt-template-vm-probe-config.adoc +++ /dev/null @@ -1,57 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/support/virt-monitoring-vm-health.adoc - -[id="virt-template-vm-probe-config_{context}"] -= Template: Virtual machine configuration file for defining health checks - -[source,yaml] ----- -apiVersion: kubevirt.io/v1 -kind: VirtualMachine -metadata: - labels: - special: vm-fedora - name: vm-fedora -spec: - template: - metadata: - labels: - special: vm-fedora - spec: - domain: - devices: - disks: - - disk: - bus: virtio - name: containerdisk - - disk: - bus: virtio - name: cloudinitdisk - resources: - requests: - memory: 1024M - readinessProbe: - httpGet: - port: 1500 - initialDelaySeconds: 120 - periodSeconds: 20 - timeoutSeconds: 10 - failureThreshold: 3 - successThreshold: 3 - terminationGracePeriodSeconds: 180 - volumes: - - name: containerdisk - containerDisk: - image: kubevirt/fedora-cloud-registry-disk-demo - - cloudInitNoCloud: - userData: |- - #cloud-config - password: fedora - chpasswd: { expire: False } - bootcmd: - - setenforce 0 - - dnf install -y nmap-ncat - - systemd-run --unit=httpserver nc -klp 1500 -e '/usr/bin/echo -e HTTP/1.1 200 OK\\n\\nHello World!' - name: cloudinitdisk ----- diff --git a/modules/virt-viewing-logs-cli.adoc b/modules/virt-viewing-logs-cli.adoc index a9edc69127..ffa55c30cf 100644 --- a/modules/virt-viewing-logs-cli.adoc +++ b/modules/virt-viewing-logs-cli.adoc @@ -1,12 +1,12 @@ // Module included in the following assemblies: // -// * virt/support/virt-logs.adoc +// * virt/support/virt-troubleshooting.adoc :_content-type: PROCEDURE [id="virt-viewing-logs-cli_{context}"] = Viewing {VirtProductName} logs with the CLI -Configure log verbosity for {VirtProductName} components by editing the `HyperConverged` custom resource (CR). Then, view logs for the component pods by using the `oc` CLI tool. +You can configure the verbosity level of {VirtProductName} component logs by editing the `HyperConverged` custom resource (CR). Then, you can view logs for the component pods by using the `oc` CLI tool. .Procedure diff --git a/modules/virt-viewing-namespace-events-cli.adoc b/modules/virt-viewing-namespace-events-cli.adoc deleted file mode 100644 index d214a7a1e5..0000000000 --- a/modules/virt-viewing-namespace-events-cli.adoc +++ /dev/null @@ -1,19 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/support/virt-events.adoc - -:_content-type: PROCEDURE -[id="virt-viewing-namespace-events-cli_{context}"] -= Viewing namespace events in the CLI - -Use the {product-title} client to get the events for a namespace. - -.Procedure - -* In the namespace, use the `oc get` command: -+ -[source,terminal] ----- -$ oc get events ----- - diff --git a/modules/virt-viewing-resource-events-cli.adoc b/modules/virt-viewing-resource-events-cli.adoc deleted file mode 100644 index 9463405cca..0000000000 --- a/modules/virt-viewing-resource-events-cli.adoc +++ /dev/null @@ -1,32 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/support/virt-events.adoc - -:_content-type: PROCEDURE -[id="virt-viewing-resource-events-cli_{context}"] -= Viewing resource events in the CLI - -Events are included in the resource description, which you can get using the -{product-title} client. - -.Procedure - -* In the namespace, use the `oc describe` command. The following example shows -how to get the events for a virtual machine, a virtual machine instance, and the -virt-launcher pod for a virtual machine: -+ -[source,terminal] ----- -$ oc describe vm ----- -+ -[source,terminal] ----- -$ oc describe vmi ----- -+ -[source,terminal] ----- -$ oc describe pod virt-launcher- ----- - diff --git a/modules/virt-viewing-virtual-machine-logs-web.adoc b/modules/virt-viewing-virtual-machine-logs-web.adoc index 913db118b6..a557681ced 100644 --- a/modules/virt-viewing-virtual-machine-logs-web.adoc +++ b/modules/virt-viewing-virtual-machine-logs-web.adoc @@ -1,21 +1,19 @@ // Module included in the following assemblies: // -// * virt/support/virt-logs.adoc +// * virt/support/virt-troubleshooting.adoc :_content-type: PROCEDURE [id="virt-viewing-virtual-machine-logs-web_{context}"] -= Viewing virtual machine logs in the web console += Viewing virtual machine logs with the web console -Get virtual machine logs from the associated virtual machine launcher pod. +You can view virtual machine logs with the {product-title} web console. .Procedure -. In the {product-title} console, click *Virtualization* -> *VirtualMachines* from the side menu. +. Navigate to *Virtualization* -> *VirtualMachines*. . Select a virtual machine to open the *VirtualMachine details* page. -. Click the *Details* tab. +. On the *Details* tab, click the pod name to open the *Pod details* page. -. Click the `virt-launcher-` pod in the *Pod* section to open the *Pod details* page. - -. Click the *Logs* tab to view the pod logs. +. Click the *Logs* tab to view the logs. diff --git a/modules/virt-viewing-vm-events-web.adoc b/modules/virt-viewing-vm-events-web.adoc deleted file mode 100644 index fed6600121..0000000000 --- a/modules/virt-viewing-vm-events-web.adoc +++ /dev/null @@ -1,18 +0,0 @@ -// Module included in the following assemblies: -// -// * virt/support/virt-events.adoc - -:_content-type: PROCEDURE -[id="virt-viewing-vm-events-web_{context}"] -= Viewing the events for a virtual machine in the web console - -You can view streaming events for a running virtual machine on the *VirtualMachine details* page of the web console. - -.Procedure - -. Click *Virtualization* -> *VirtualMachines* from the side menu. -. Select a virtual machine to open the *VirtualMachine details* page. -. Click the *Events* tab to view streaming events for the virtual machine. - -* The ▮▮ button pauses the events stream. -* The ▶ button resumes a paused events stream. diff --git a/nodes/nodes/ecosystems/eco-self-node-remediation-operator.adoc b/nodes/nodes/ecosystems/eco-self-node-remediation-operator.adoc index 2e21ddc6d4..b71a2767ea 100644 --- a/nodes/nodes/ecosystems/eco-self-node-remediation-operator.adoc +++ b/nodes/nodes/ecosystems/eco-self-node-remediation-operator.adoc @@ -15,7 +15,7 @@ include::modules/eco-self-node-remediation-about-watchdog.adoc[leveloffset=+2] [role="_additional-resources"] .Additional resources -xref:../../../virt/virtual_machines/advanced_vm_management/virt-configuring-a-watchdog.adoc#virt-configuring-a-watchdog[Configuring a watchdog] +xref:../../../virt/support/monitoring/virt-monitoring-vm-health.adoc#watchdog_virt-monitoring-vm-health[Configuring a watchdog] include::modules/eco-self-node-remediation-operator-control-plane-fencing.adoc[leveloffset=+1] diff --git a/virt/live_migration/virt-live-migration.adoc b/virt/live_migration/virt-live-migration.adoc index e1842009e7..b6ad276510 100644 --- a/virt/live_migration/virt-live-migration.adoc +++ b/virt/live_migration/virt-live-migration.adoc @@ -13,6 +13,6 @@ include::modules/virt-about-live-migration.adoc[leveloffset=+1] == Additional resources * xref:../../virt/live_migration/virt-migrate-vmi.adoc#virt-migrate-vmi[Migrating a virtual machine instance to another node] -* xref:../../virt/support/virt-monitor-vmi-migration.adoc#virt-monitor-vmi-migration[Monitoring live migration] +* xref:../../virt/support/monitoring/virt-prometheus-queries.adoc#virt-live-migration-metrics_virt-prometheus-queries[Live migration metrics] * xref:../../virt/live_migration/virt-live-migration-limits.adoc#virt-live-migration-limits[Live migration limiting] * xref:../../virt/virtual_machines/virtual_disks/virt-creating-data-volumes.adoc#virt-customizing-storage-profile_virt-creating-data-volumes[Customizing the storage profile] \ No newline at end of file diff --git a/virt/live_migration/virt-migrate-vmi.adoc b/virt/live_migration/virt-migrate-vmi.adoc index c30a05b11f..e14e7372ff 100644 --- a/virt/live_migration/virt-migrate-vmi.adoc +++ b/virt/live_migration/virt-migrate-vmi.adoc @@ -15,11 +15,19 @@ If a virtual machine uses a host model CPU, you can perform live migration of th include::modules/virt-initiating-vm-migration-web.adoc[leveloffset=+1] +[id="monitoring-live-migration-by-using-the-web-console_{context}"] +=== Monitoring live migration by using the web console + +You can monitor the progress of all live migrations on the xref:../../virt/virt-web-console-overview.adoc#virtualization-overview-migrations_virt-web-console-overview[*Overview* -> *Migrations* tab] in the web console. + +You can view the migration metrics of a virtual machine on the xref:../../virt/virt-web-console-overview.adoc#ui-virtualmachine-details-metrics_virt-web-console-overview[*VirtualMachine details* -> *Metrics* tab] in the web console. + include::modules/virt-initiating-vm-migration-cli.adoc[leveloffset=+1] +include::modules/virt-monitoring-vm-migration-cli.adoc[leveloffset=+2] + [role="_additional-resources"] [id="virt-migrate-vmi_additional-resources"] == Additional resources -* xref:../../virt/support/virt-monitor-vmi-migration.adoc#virt-monitor-vmi-migration[Monitoring live migration] * xref:../../virt/live_migration/virt-cancel-vmi-migration.adoc#virt-cancel-vmi-migration[Cancelling the live migration of a virtual machine instance] diff --git a/virt/support/monitoring/_attributes b/virt/support/monitoring/_attributes new file mode 120000 index 0000000000..5b32de1e01 --- /dev/null +++ b/virt/support/monitoring/_attributes @@ -0,0 +1 @@ +../../_attributes \ No newline at end of file diff --git a/virt/support/monitoring/images b/virt/support/monitoring/images new file mode 120000 index 0000000000..5fa6987088 --- /dev/null +++ b/virt/support/monitoring/images @@ -0,0 +1 @@ +../../images \ No newline at end of file diff --git a/virt/support/monitoring/modules b/virt/support/monitoring/modules new file mode 120000 index 0000000000..8b0e854007 --- /dev/null +++ b/virt/support/monitoring/modules @@ -0,0 +1 @@ +../../modules \ No newline at end of file diff --git a/virt/support/monitoring/snippets b/virt/support/monitoring/snippets new file mode 120000 index 0000000000..7bf6da9a51 --- /dev/null +++ b/virt/support/monitoring/snippets @@ -0,0 +1 @@ +../../snippets \ No newline at end of file diff --git a/virt/support/virt-exposing-custom-metrics-for-vms.adoc b/virt/support/monitoring/virt-exposing-custom-metrics-for-vms.adoc similarity index 61% rename from virt/support/virt-exposing-custom-metrics-for-vms.adoc rename to virt/support/monitoring/virt-exposing-custom-metrics-for-vms.adoc index b40c8bedd9..e051604c5b 100644 --- a/virt/support/virt-exposing-custom-metrics-for-vms.adoc +++ b/virt/support/monitoring/virt-exposing-custom-metrics-for-vms.adoc @@ -20,16 +20,16 @@ include::modules/virt-accessing-node-exporter-outside-cluster.adoc[leveloffset=+ [role="_additional-resources"] [id="additional-resources_virt-exposing-custom-metrics-for-vms"] == Additional resources -* xref:../../monitoring/configuring-the-monitoring-stack.adoc#configuring-the-monitoring-stack[Configuring the monitoring stack] +* xref:../../../monitoring/configuring-the-monitoring-stack.adoc#configuring-the-monitoring-stack[Configuring the monitoring stack] -* xref:../../monitoring/enabling-monitoring-for-user-defined-projects.adoc#enabling-monitoring-for-user-defined-projects[Enabling monitoring for user-defined projects] +* xref:../../../monitoring/enabling-monitoring-for-user-defined-projects.adoc#enabling-monitoring-for-user-defined-projects[Enabling monitoring for user-defined projects] -* xref:../../monitoring/managing-metrics.adoc#managing-metrics[Managing metrics] +* xref:../../../monitoring/managing-metrics.adoc#managing-metrics[Managing metrics] -* xref:../../monitoring/reviewing-monitoring-dashboards.adoc#reviewing-monitoring-dashboards[Reviewing monitoring dashboards] +* xref:../../../monitoring/reviewing-monitoring-dashboards.adoc#reviewing-monitoring-dashboards[Reviewing monitoring dashboards] -* xref:../../applications/application-health.adoc#application-health[Monitoring application health by using health checks] +* xref:../../../applications/application-health.adoc#application-health[Monitoring application health by using health checks] -* xref:../../nodes/pods/nodes-pods-configmaps.adoc#nodes-pods-configmaps[Creating and using config maps] +* xref:../../../nodes/pods/nodes-pods-configmaps.adoc#nodes-pods-configmaps[Creating and using config maps] -* xref:../../virt/virtual_machines/virt-controlling-vm-states.adoc#virt-controlling-vm-states[Controlling virtual machine states] +* xref:../../../virt/virtual_machines/virt-controlling-vm-states.adoc#virt-controlling-vm-states[Controlling virtual machine states] diff --git a/virt/support/monitoring/virt-monitoring-overview.adoc b/virt/support/monitoring/virt-monitoring-overview.adoc new file mode 100644 index 0000000000..7f863ebcfd --- /dev/null +++ b/virt/support/monitoring/virt-monitoring-overview.adoc @@ -0,0 +1,24 @@ +:_content-type: ASSEMBLY +[id="virt-monitoring-overview"] += Monitoring overview +include::_attributes/common-attributes.adoc[] +:context: virt-monitoring-overview + +toc::[] + +You can monitor the health of your cluster and virtual machines (VMs) with the following tools: + +xref:../../../virt/support/monitoring/virt-running-cluster-checkups.adoc#virt-running-cluster-checkups[{product-title} cluster checkup framework]:: +Check network connectivity and latency by using predefined, automated tests. + +:FeatureName: The {product-title} cluster checkup framework +include::snippets/technology-preview.adoc[] + +xref:../../../virt/support/monitoring/virt-prometheus-queries.adoc#virt-prometheus-queries[Prometheus queries for virtual resources]:: +Query vCPU, network, storage, and guest memory swapping usage and live migration progress. + +xref:../../../virt/support/monitoring/virt-exposing-custom-metrics-for-vms.adoc#virt-exposing-custom-metrics-for-vms[VM custom metrics]:: +Configure the `node-exporter` service to expose internal VM metrics and processes. + +xref:../../../virt/support/monitoring/virt-monitoring-vm-health.adoc#[VM health checks]:: +Configure readiness, liveness, and guest agent ping probes and a watchdog for VMs. diff --git a/virt/support/monitoring/virt-monitoring-vm-health.adoc b/virt/support/monitoring/virt-monitoring-vm-health.adoc new file mode 100644 index 0000000000..0ca4e6d078 --- /dev/null +++ b/virt/support/monitoring/virt-monitoring-vm-health.adoc @@ -0,0 +1,54 @@ +:_content-type: ASSEMBLY +[id="virt-monitoring-vm-health"] += Virtual machine health checks +include::_attributes/common-attributes.adoc[] +:context: virt-monitoring-vm-health + +toc::[] + +You can configure virtual machine (VM) health checks by defining readiness and liveness probes in the `VirtualMachine` resource. + +include::modules/virt-about-readiness-liveness-probes.adoc[leveloffset=+1] + +include::modules/virt-define-http-readiness-probe.adoc[leveloffset=+2] + +include::modules/virt-define-tcp-readiness-probe.adoc[leveloffset=+2] + +include::modules/virt-define-http-liveness-probe.adoc[leveloffset=+2] + +[id="watchdog_{context}"] +== Defining a watchdog + +You can define a watchdog to monitor the health of the guest operating system by performing the following steps: + +. Configure a watchdog device for the virtual machine (VM). +. Install the watchdog agent on the guest. + +The watchdog device monitors the agent and performs one of the following actions if the guest operating system is unresponsive: + +* `poweroff`: The VM powers down immediately. If `spec.running` is set to `true` or `spec.runStrategy` is not set to `manual`, then the VM reboots. +* `reset`: The VM reboots in place and the guest operating system cannot react. ++ +[NOTE] +==== +The reboot time might cause liveness probes to time out. If cluster-level protections detect a failed liveness probe, the VM might be forcibly rescheduled, increasing the reboot time. +==== + +* `shutdown`: The VM gracefully powers down by stopping all services. + +[NOTE] +==== +Watchdog is not available for Windows VMs. +==== + +include::modules/virt-defining-watchdog-device-vm.adoc[leveloffset=+2] + +include::modules/virt-installing-watchdog-agent.adoc[leveloffset=+2] + +include::modules/virt-define-guest-agent-ping-probe.adoc[leveloffset=+1] + +[id="additional-resources_monitoring-vm-health"] +[role="_additional-resources"] +== Additional resources + +* xref:../../../applications/application-health.adoc#application-health[Monitoring application health by using health checks] diff --git a/virt/support/virt-prometheus-queries.adoc b/virt/support/monitoring/virt-prometheus-queries.adoc similarity index 79% rename from virt/support/virt-prometheus-queries.adoc rename to virt/support/monitoring/virt-prometheus-queries.adoc index f6bc384937..1628879ed8 100644 --- a/virt/support/virt-prometheus-queries.adoc +++ b/virt/support/monitoring/virt-prometheus-queries.adoc @@ -14,7 +14,7 @@ Use the {product-title} monitoring dashboard to query virtualization metrics. [id="prerequisites_{context}"] == Prerequisites -* To use the vCPU metric, the `schedstats=enable` kernel argument must be applied to the `MachineConfig` object. This kernel argument enables scheduler statistics used for debugging and performance tuning and adds a minor additional load to the scheduler. See the xref:../../post_installation_configuration/machine-configuration-tasks.adoc#nodes-nodes-kernel-arguments_post-install-machine-configuration-tasks[{product-title} machine configuration tasks] documentation for more information on applying a kernel argument. +* To use the vCPU metric, the `schedstats=enable` kernel argument must be applied to the `MachineConfig` object. This kernel argument enables scheduler statistics used for debugging and performance tuning and adds a minor additional load to the scheduler. For more information, see xref:../../../post_installation_configuration/machine-configuration-tasks.html#nodes-nodes-kernel-arguments_post-install-machine-configuration-tasks[Adding kernel arguments to nodes]. * For guest memory swapping queries to return data, memory swapping must be enabled on the virtual guests. @@ -26,13 +26,13 @@ include::modules/monitoring-querying-metrics-for-user-defined-projects-as-a-deve include::modules/virt-querying-metrics.adoc[leveloffset=+1] -include::modules/virt-live-migration-metrics.adoc[leveloffset=+1] +include::modules/virt-live-migration-metrics.adoc[leveloffset=+2] [id="additional-resources_virt-prometheus-queries"] [role="_additional-resources"] == Additional resources -* xref:../../monitoring/monitoring-overview.adoc#monitoring-overview[Monitoring overview] +* xref:../../../monitoring/monitoring-overview.adoc#monitoring-overview[Monitoring overview] * link:https://prometheus.io/docs/prometheus/latest/querying/basics/[Querying Prometheus] diff --git a/virt/support/virt-running-cluster-checkups.adoc b/virt/support/monitoring/virt-running-cluster-checkups.adoc similarity index 63% rename from virt/support/virt-running-cluster-checkups.adoc rename to virt/support/monitoring/virt-running-cluster-checkups.adoc index 6f6de9ecd4..a9c0c66ae7 100644 --- a/virt/support/virt-running-cluster-checkups.adoc +++ b/virt/support/monitoring/virt-running-cluster-checkups.adoc @@ -1,6 +1,6 @@ :_content-type: ASSEMBLY [id="virt-running-cluster-checkups"] -= Running cluster checkups += {product-title} cluster checkup framework include::_attributes/common-attributes.adoc[] :context: virt-running-cluster-checkups @@ -11,12 +11,7 @@ toc::[] :FeatureName: The {product-title} cluster checkup framework include::snippets/technology-preview.adoc[] - include::modules/virt-about-cluster-checkup-framework.adoc[leveloffset=+1] include::modules/virt-measuring-latency-vm-secondary-network.adoc[leveloffset=+1] -[role="_additional-resources"] -[id="additional-resources_running-cluster-checkups"] -== Additional resources -* xref:../../virt/virtual_machines/vm_networking/virt-attaching-vm-multiple-networks.adoc#virt-attaching-vm-multiple-networks[Attaching a virtual machine to multiple networks] diff --git a/virt/support/virt-collecting-virt-data.adoc b/virt/support/virt-collecting-virt-data.adoc index baa5523a5e..ead0a1d7a1 100644 --- a/virt/support/virt-collecting-virt-data.adoc +++ b/virt/support/virt-collecting-virt-data.adoc @@ -17,34 +17,48 @@ Prometheus is a time-series database and a rule evaluation engine for metrics. P Alertmanager:: The Alertmanager service handles alerts received from Prometheus. The Alertmanager is also responsible for sending the alerts to external notification systems. -include::modules/virt-collecting-data-about-your-environment.adoc[leveloffset=+1] +For information about the {product-title} monitoring stack, see xref:../../monitoring/monitoring-overview.adoc#about-openshift-monitoring[About {product-title} monitoring]. -[id="additional-resources_collecting-data-about-your-environment"] -[role="_additional-resources"] -=== Additional resources -* Configuring the xref:../../monitoring/configuring-the-monitoring-stack.adoc#modifying-retention-time-for-prometheus-metrics-data_configuring-the-monitoring-stack[retention time] for Prometheus metrics data -* Configuring the Alertmanager to send xref:../../monitoring/managing-alerts.adoc#sending-notifications-to-external-systems_managing-alerts[alert notifications] to external systems -* Collecting `must-gather` data for xref:../../support/gathering-cluster-data.adoc#support_gathering_data_gathering-cluster-data[{product-title}] -* Collecting `must-gather` data for link:https://access.redhat.com/documentation/en-us/red_hat_openshift_data_foundation/4.13/html-single/troubleshooting_openshift_data_foundation/index#downloading-log-files-and-diagnostic-information_rhodf[{rh-storage-first}] -* Collecting `must-gather` data for xref:../../virt/support/virt-collecting-virt-data.adoc#virt-using-virt-must-gather_virt-collecting-virt-data[{VirtProductName}] -* Collecting Prometheus metrics for xref:../../monitoring/managing-metrics.adoc#querying-metrics-for-all-projects-as-an-administrator_managing-metrics[all projects] as a cluster administrator +// This procedure is in the assembly so that we can add xrefs instead of a long list of additional resources. +[id="virt-collecting-data-about-your-environment_{context}"] +== Collecting data about your environment -include::modules/virt-collecting-data-about-vms.adoc[leveloffset=+1] +Collecting data about your environment minimizes the time required to analyze and determine the root cause. -[id="additional-resources_collecting-data-about-vms"] -[role="_additional-resources"] -=== Additional resources -* Installing xref:../../virt/virtual_machines/virt-installing-qemu-guest-agent.adoc#virt-installing-virtio-drivers-existing-windows_virt-installing-qemu-guest-agent[VirtIO drivers] on Windows VMs -* Downloading and installing link:https://access.redhat.com/solutions/6957701[VirtIO drivers] on Windows VMs without host access -* Connecting to Windows VMs with RDP using the xref:../../virt/virtual_machines/virt-accessing-vm-consoles.adoc#virt-vm-rdp-console-web_virt-accessing-vm-consoles[web console] or the xref:../../virt/virtual_machines/virt-accessing-vm-consoles.adoc#virt-accessing-rdp-console_virt-accessing-vm-consoles[command line] -* Collecting `must-gather` data about xref:../../virt/support/virt-collecting-virt-data.adoc#virt-must-gather-options_virt-collecting-virt-data[virtual machines] -// * Collecting virtual machine memory dumps. [link TBD. CNV-20256] +.Prerequisites + +* xref:../../monitoring/configuring-the-monitoring-stack.adoc#modifying-retention-time-for-prometheus-metrics-data_configuring-the-monitoring-stack[Set the retention time for Prometheus metrics data] to a minimum of seven days. +* xref:../../monitoring/managing-alerts.adoc#sending-notifications-to-external-systems_managing-alerts[Configure the Alertmanager to capture relevant alerts and to send alert notifications to a dedicated mailbox] so that they can be viewed and persisted outside the cluster. +* Record the exact number of affected nodes and virtual machines. + +.Procedure + +. xref:../../support/gathering-cluster-data.adoc#support_gathering_data_gathering-cluster-data[Collect must-gather data for the cluster]. +. link:https://access.redhat.com/documentation/en-us/red_hat_openshift_data_foundation/4.12/html-single/troubleshooting_openshift_data_foundation/index#downloading-log-files-and-diagnostic-information_rhodf[Collect must-gather data for {rh-storage-first}], if necessary. +. xref:../../virt/support/virt-collecting-virt-data.adoc#virt-using-virt-must-gather_virt-collecting-virt-data[Collect must-gather data for {VirtProductName}]. +. xref:../../monitoring/managing-metrics.adoc#querying-metrics-for-all-projects-as-an-administrator_managing-metrics[Collect Prometheus metrics for the cluster]. + +[id="virt-collecting-data-about-vms_{context}"] +== Collecting data about virtual machines + +Collecting data about malfunctioning virtual machines (VMs) minimizes the time required to analyze and determine the root cause. + +.Prerequisites + +* Linux VMs: xref:../../virt/virtual_machines/virt-installing-qemu-guest-agent.adoc#virt-installing-qemu-guest-agent-on-linux-vm_virt-installing-qemu-guest-agent[Install the latest QEMU guest agent]. +* Windows VMs: +** Record the Windows patch update details. +** link:https://access.redhat.com/solutions/6957701[Install the latest VirtIO drivers]. +** xref:../../virt/virtual_machines/virt-installing-qemu-guest-agent.adoc#virt-installing-virtio-drivers-existing-windows_virt-installing-qemu-guest-agent[Install the latest QEMU guest agent]. +** If Remote Desktop Protocol (RDP) is enabled, try to connect to the VMs with RDP by using the xref:../../virt/virtual_machines/virt-accessing-vm-consoles.adoc#virt-vm-rdp-console-web_virt-accessing-vm-consoles[web console] or the xref:../../virt/virtual_machines/virt-accessing-vm-consoles.adoc#virt-accessing-rdp-console_virt-accessing-vm-consoles[command line] to determine whether there is a problem with the connection software. + +.Procedure + +. xref:../../virt/support/virt-collecting-virt-data.adoc#virt-must-gather-options_virt-collecting-virt-data[Collect must-gather data for the VMs] using the `gather_vms_details` script. +. Collect screenshots of VMs that have crashed _before_ you restart them. +. xref:../../virt/virt-using-the-cli-tools.html#vm-memory-dump-commands_virt-using-the-cli-tools[Collect memory dumps from VMs] _before_ remediation attempts. +. Record factors that the malfunctioning VMs have in common. For example, the VMs have the same host or network. include::modules/virt-using-virt-must-gather.adoc[leveloffset=+1] include::modules/virt-must-gather-options.adoc[leveloffset=+2] - -[id="additional-resources_must-gather-virt"] -[role="_additional-resources"] -=== Additional resources -* xref:../../support/gathering-cluster-data.adoc#about-must-gather_gathering-cluster-data[About the `must-gather` tool] diff --git a/virt/support/virt-diagnosing-datavolumes-using-events-and-conditions.adoc b/virt/support/virt-diagnosing-datavolumes-using-events-and-conditions.adoc deleted file mode 100644 index 6e125f6cee..0000000000 --- a/virt/support/virt-diagnosing-datavolumes-using-events-and-conditions.adoc +++ /dev/null @@ -1,12 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-diagnosing-datavolumes-using-events-and-conditions"] -= Diagnosing data volumes using events and conditions -include::_attributes/common-attributes.adoc[] -:context: virt-diagnosing-datavolumes-using-events-and-conditions - -toc::[] - -Use the `oc describe` command to analyze and help resolve issues with data volumes. - -include::modules/virt-about-conditions-and-events.adoc[leveloffset=+1] -include::modules/virt-analyzing-datavolume-conditions-and-events.adoc[leveloffset=+1] diff --git a/virt/support/virt-events.adoc b/virt/support/virt-events.adoc deleted file mode 100644 index e8a746374d..0000000000 --- a/virt/support/virt-events.adoc +++ /dev/null @@ -1,18 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-events"] -= Viewing events -include::_attributes/common-attributes.adoc[] -:context: virt-events - -toc::[] - -include::modules/virt-about-vm-events.adoc[leveloffset=+1] - -See also: -xref:../../nodes/clusters/nodes-containers-events.adoc#nodes-containers-events[Viewing system event information in an {product-title} cluster]. - -include::modules/virt-viewing-vm-events-web.adoc[leveloffset=+1] - -include::modules/virt-viewing-namespace-events-cli.adoc[leveloffset=+1] - -include::modules/virt-viewing-resource-events-cli.adoc[leveloffset=+1] diff --git a/virt/support/virt-logs.adoc b/virt/support/virt-logs.adoc deleted file mode 100644 index 98abf63bfe..0000000000 --- a/virt/support/virt-logs.adoc +++ /dev/null @@ -1,15 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-logs"] -= Viewing {VirtProductName} logs -include::_attributes/common-attributes.adoc[] -:context: virt-logs - -toc::[] - -You can view logs for {VirtProductName} components and virtual machines by using the web console or the `oc` CLI. You can retrieve virtual machine logs from the `virt-launcher` pod. To control log verbosity, edit the `HyperConverged` custom resource. - -include::modules/virt-viewing-logs-cli.adoc[leveloffset=+1] - -include::modules/virt-viewing-virtual-machine-logs-web.adoc[leveloffset=+1] - -include::modules/virt-common-error-messages.adoc[leveloffset=+1] \ No newline at end of file diff --git a/virt/support/virt-monitor-vmi-migration.adoc b/virt/support/virt-monitor-vmi-migration.adoc deleted file mode 100644 index 17bcd4fcaf..0000000000 --- a/virt/support/virt-monitor-vmi-migration.adoc +++ /dev/null @@ -1,25 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-monitor-vmi-migration"] -= Monitoring live migration -include::_attributes/common-attributes.adoc[] -:context: virt-monitor-vmi-migration - -toc::[] - -You can monitor the progress of live migration from either the web console or the CLI. - -[id="monitoring-live-migration-by-using-the-web-console_{context}"] -== Monitoring live migration by using the web console - -You can monitor the progress of all live migrations on the xref:../../virt/virt-web-console-overview.adoc#virtualization-overview-migrations_virt-web-console-overview[*Overview -> Migrations* tab] in the web console. - -You can view the migration metrics of a virtual machine on the xref:../../virt/virt-web-console-overview.adoc#ui-virtualmachine-details-metrics_virt-web-console-overview[*VirtualMachine details -> Metrics* tab] in the web console. - -include::modules/virt-monitoring-vm-migration-cli.adoc[leveloffset=+1] - -[id="metrics_virt-monitor-vmi-migration"] -== Metrics - -You can use xref:../../virt/support/virt-prometheus-queries.adoc#virt-prometheus-queries[Prometheus queries] to monitor live migration. - -include::modules/virt-live-migration-metrics.adoc[leveloffset=+2] \ No newline at end of file diff --git a/virt/support/virt-monitoring-vm-health.adoc b/virt/support/virt-monitoring-vm-health.adoc deleted file mode 100644 index ebec742b27..0000000000 --- a/virt/support/virt-monitoring-vm-health.adoc +++ /dev/null @@ -1,26 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-monitoring-vm-health"] -= Monitoring virtual machine health with health probes -include::_attributes/common-attributes.adoc[] -:context: virt-monitoring-vm-health - -toc::[] - -A virtual machine (VM) can become unhealthy due to transient issues such as connectivity loss, deadlocks, or problems with external dependencies. A health check periodically performs diagnostics on a VM by using any combination of the readiness and liveness probes. - -include::modules/virt-about-readiness-liveness-probes.adoc[leveloffset=+1] - -include::modules/virt-define-http-readiness-probe.adoc[leveloffset=+1] - -include::modules/virt-define-tcp-readiness-probe.adoc[leveloffset=+1] - -include::modules/virt-define-http-liveness-probe.adoc[leveloffset=+1] - -include::modules/virt-define-guest-agent-ping-probe.adoc[leveloffset=+1] - - -[id="additional-resources_monitoring-vm-health"] -[role="_additional-resources"] -== Additional resources - -* xref:../../applications/application-health.adoc#application-health[Monitoring application health by using health checks] diff --git a/virt/support/virt-openshift-cluster-monitoring.adoc b/virt/support/virt-openshift-cluster-monitoring.adoc deleted file mode 100644 index 4da54278d6..0000000000 --- a/virt/support/virt-openshift-cluster-monitoring.adoc +++ /dev/null @@ -1,25 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-openshift-cluster-monitoring"] -= {product-title} cluster monitoring, logging, and Telemetry -include::_attributes/common-attributes.adoc[] -:context: virt-openshift-cluster-monitoring - -toc::[] - -{product-title} provides various resources for monitoring at the cluster level. - -// Cluster monitoring -include::modules/monitoring-about-cluster-monitoring.adoc[leveloffset=+1] - -// OpenShift Logging -include::modules/cluster-logging-about-components.adoc[leveloffset=+1] - -For more information on OpenShift Logging, see the xref:../../logging/cluster-logging.adoc#cluster-logging[OpenShift Logging] documentation. - -// Telemetry -include::modules/telemetry-about-telemetry.adoc[leveloffset=+1] -include::modules/telemetry-what-information-is-collected.adoc[leveloffset=+2] - -== CLI troubleshooting and debugging commands - -For a list of the `oc` client troubleshooting and debugging commands, see the xref:../../cli_reference/openshift_cli/developer-cli-commands.adoc#cli-developer-commands[{product-title} CLI tools] documentation. diff --git a/virt/support/virt-support-overview.adoc b/virt/support/virt-support-overview.adoc new file mode 100644 index 0000000000..fa46f24213 --- /dev/null +++ b/virt/support/virt-support-overview.adoc @@ -0,0 +1,74 @@ +:_content-type: ASSEMBLY +[id="virt-support-overview"] += Support overview +include::_attributes/common-attributes.adoc[] +:context: virt-support-overview + +toc::[] + +You can collect data about your environment, monitor the health of your cluster and virtual machines (VMs), and troubleshoot {VirtProductName} resources with the following tools. + +[id="virt-web-console_{context}"] +== Web console + +The {product-title} web console displays resource usage, alerts, events, and trends for your cluster and for {VirtProductName} components and resources. + +.Web console pages for monitoring and troubleshooting +[options="header"] +|==== +|Page |Description + +|*Overview* page +|Cluster details, status, alerts, inventory, and resource usage + +|*Virtualization* -> xref:../../virt/virt-web-console-overview.adoc#virtualization-overview-overview_virt-web-console-overview[*Overview* tab] +|{VirtProductName} resources, usage, alerts, and status + +|*Virtualization* -> xref:../../virt/virt-web-console-overview.adoc#virtualization-overview-top-consumers_virt-web-console-overview[*Top consumers* tab] +|Top consumers of CPU, memory, and storage + +|*Virtualization* -> xref:../../virt/virt-web-console-overview.adoc#virtualization-overview-migrations_virt-web-console-overview[*Migrations* tab] +|Progress of live migrations + +|*VirtualMachines* -> *VirtualMachine* -> *VirtualMachine details* -> xref:../../virt/virt-web-console-overview.adoc#ui-virtualmachine-details-metrics_virt-web-console-overview[*Metrics* tab] +|VM resource usage, storage, network, and migration + +|*VirtualMachines* -> *VirtualMachine* -> *VirtualMachine details* -> xref:../../virt/virt-web-console-overview.adoc#ui-virtualmachine-details-events_virt-web-console-overview[*Events* tab] +|List of VM events +|==== + +[id="collecting-data-for-red-hat-support_{context}"] +== Collecting data for Red Hat Support + +When you submit a xref:../../support/getting-support.adoc#support-submitting-a-case_getting-support[support case] to Red Hat Support, it is helpful to provide debugging information. You can gather debugging information by performing the following steps: + +xref:../../virt/support/virt-collecting-virt-data.adoc#virt-collecting-data-about-your-environment_virt-collecting-virt-data[Collecting data about your environment]:: +Configure Prometheus and Alertmanager and collect `must-gather` data for {product-title} and {VirtProductName}. + +xref:../../virt/support/virt-collecting-virt-data.adoc#virt-collecting-data-about-vms_virt-collecting-virt-data[Collecting data about VMs]:: +Collect `must-gather` data and memory dumps from VMs. + +xref:../../virt/support/virt-collecting-virt-data.adoc#virt-using-virt-must-gather_virt-collecting-virt-data[`must-gather` tool for {VirtProductName}]:: +Configure and use the `must-gather` tool. + +[id="monitoring_{context}"] +== Monitoring + +You can monitor the health of your cluster and VMs. For details about monitoring tools, see the xref:../../virt/support/monitoring/virt-monitoring-overview.adoc#virt-monitoring-overview[Monitoring overview]. + +[id="troubleshooting_{context}"] +== Troubleshooting + +Troubleshoot {VirtProductName} components and VMs and resolve issues that trigger alerts in the web console. + +xref:../../virt/support/virt-troubleshooting.adoc#events_virt-troubleshooting[Events]:: +View important life-cycle information for VMs, namespaces, and resources. + +xref:../../virt/support/virt-troubleshooting.adoc#virt-logs_virt-troubleshooting[Logs]:: +View and configure logs for {VirtProductName} components and VMs. + +xref:../../virt/support/virt-runbooks.adoc#virt-runbooks[Runbooks]:: +Diagnose and resolve issues that trigger {VirtProductName} alerts in the web console. + +xref:../../virt/support/virt-troubleshooting.adoc#troubleshooting-data-volumes_virt-troubleshooting[Troubleshooting data volumes]:: +Troubleshoot data volumes by analyzing conditions and events. diff --git a/virt/support/virt-troubleshooting.adoc b/virt/support/virt-troubleshooting.adoc new file mode 100644 index 0000000000..432a57dce2 --- /dev/null +++ b/virt/support/virt-troubleshooting.adoc @@ -0,0 +1,50 @@ +:_content-type: ASSEMBLY +[id="virt-troubleshooting"] += Troubleshooting +include::_attributes/common-attributes.adoc[] +:context: virt-troubleshooting + +toc::[] + +[id="events_{context}"] +== Events + +xref:../../nodes/clusters/nodes-containers-events.adoc#nodes-containers-events[{product-title} events] are records of important life-cycle information and are useful for monitoring and troubleshooting resource issues. You can gather information about the following events: + +* VM events: Navigate to the xref:../../virt/virt-web-console-overview.adoc#ui-virtualmachine-details-events_virt-web-console-overview[*Events* tab] of the *VirtualMachine details* page in the web console. + +* Namespace events: Use the `oc get` command with the namespace: ++ +[source,terminal] +---- +$ oc get events -n +---- ++ +See the xref:../../nodes/clusters/nodes-containers-events.adoc#nodes-containers-events-list_nodes-containers-events[list of events] for details about specific events. + +* Resource events: Use the `oc describe` command with the resource: ++ +[source,terminal] +---- +$ oc describe +---- + +[id="virt-logs_{context}"] +== Logs + +You can view logs for {VirtProductName} components and VMs by using the web console or the `oc` CLI tool. You can retrieve virtual machine logs from the `virt-launcher` pod. To control log verbosity, edit the `HyperConverged` custom resource. + +include::modules/virt-viewing-virtual-machine-logs-web.adoc[leveloffset=+2] + +include::modules/virt-viewing-logs-cli.adoc[leveloffset=+2] + +include::modules/virt-common-error-messages.adoc[leveloffset=+2] + +[id="troubleshooting-data-volumes_{context}"] +== Troubleshooting data volumes + +You can check the `Conditions` and `Events` sections of the `DataVolume` object to analyze and resolve issues. + +include::modules/virt-about-dv-conditions-and-events.adoc[leveloffset=+2] + +include::modules/virt-analyzing-datavolume-conditions-and-events.adoc[leveloffset=+2] diff --git a/virt/support/virt-using-dashboard-to-get-cluster-info.adoc b/virt/support/virt-using-dashboard-to-get-cluster-info.adoc deleted file mode 100644 index 8fac0b9339..0000000000 --- a/virt/support/virt-using-dashboard-to-get-cluster-info.adoc +++ /dev/null @@ -1,13 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-using-dashboard-to-get-cluster-info"] -= Using the {product-title} dashboard to get cluster information -include::_attributes/common-attributes.adoc[] -:context: virt-using-dashboard-to-get-cluster-info - -toc::[] - -Access the {product-title} dashboard, which captures high-level information about the cluster, by clicking *Home > Dashboards > Overview* from the {product-title} web console. - -The {product-title} dashboard provides various cluster information, captured in individual dashboard _cards_. - -include::modules/virt-about-the-overview-dashboard.adoc[leveloffset=+1] diff --git a/virt/virt-4-13-release-notes.adoc b/virt/virt-4-13-release-notes.adoc index 1694dd7e2c..802c4c733f 100644 --- a/virt/virt-4-13-release-notes.adoc +++ b/virt/virt-4-13-release-notes.adoc @@ -104,7 +104,7 @@ Deprecated features are included in the current release and supported. However, * In a future release, support for the legacy HPP custom resource, and the associated storage class, will be deprecated. Beginning in {VirtProductName} {VirtVersion}, the HPP Operator uses the Kubernetes Container Storage Interface (CSI) driver to configure local storage. The Operator continues to support the existing (legacy) format of the HPP custom resource and the associated storage class. If you use the HPP Operator, plan to xref:../virt/virtual_machines/virtual_disks/virt-configuring-local-storage-for-vms.adoc#virt-configuring-local-storage-for-vms[create a storage class for the CSI driver] as part of your migration strategy. - + [id="virt-4-13-removed"] @@ -180,7 +180,7 @@ link:https://access.redhat.com/support/offerings/techpreview[Technology Preview //CNV-21824 -* You can now run xref:../virt/support/virt-running-cluster-checkups.adoc#virt-measuring-latency-vm-secondary-network_virt-running-cluster-checkups[{product-title} cluster checkups] to measure network latency between VMs. +* You can now run xref:../virt/support/monitoring/virt-running-cluster-checkups.adoc#virt-running-cluster-checkups[{product-title} cluster checkups] to measure network latency between VMs. //CNV-20526 * The Tekton Tasks Operator (TTO) now xref:../virt/virtual_machines/virt-managing-vms-openshift-pipelines.adoc#virt-managing-vms-openshift-pipelines[integrates {VirtProductName} with {pipelines-title}]. TTO includes cluster tasks and example pipelines that allow you to: @@ -192,7 +192,7 @@ link:https://access.redhat.com/support/offerings/techpreview[Technology Preview ** Customize a basic Windows 10 installation and then create a new image and template. //CNV-20149 -* You can now use the xref:../virt/support/virt-monitoring-vm-health.adoc#virt-define-guest-agent-ping-probe_virt-monitoring-vm-health[guest agent ping probe] to determine if the QEMU guest agent is running on a virtual machine. +* You can now use the xref:../virt/support/monitoring/virt-monitoring-vm-health.adoc#virt-define-guest-agent-ping-probe_virt-monitoring-vm-health[guest agent ping probe] to determine if the QEMU guest agent is running on a virtual machine. //CNV-20963 * You can now use Microsoft Windows 11 as a guest operating system. However, {VirtProductName} {VirtVersion} does not support USB disks, which are required for a critical function of BitLocker recovery. To protect recovery keys, use other methods described in the link:https://learn.microsoft.com/en-us/windows/security/information-protection/bitlocker/bitlocker-recovery-guide-plan[BitLocker recovery guide]. diff --git a/virt/virt-getting-started.adoc b/virt/virt-getting-started.adoc index 9862867871..c686e2c7dc 100644 --- a/virt/virt-getting-started.adoc +++ b/virt/virt-getting-started.adoc @@ -65,7 +65,6 @@ Manage the VMs: VMs are connected to the pod network by default. You must configure a secondary network, such as Linux bridge or SR-IOV, and then add the network to the VM configuration. ==== -* xref:../virt/support/virt-logs.adoc#virt-logs[View {VirtProductName} logs by using the CLI]. * xref:../virt/virtual_machines/virt-automating-windows-sysprep.adoc#virt-automating-windows-sysprep[Automate Windows VM deployments with `sysprep`]. * xref:../virt/live_migration/virt-live-migration.adoc#virt-live-migration[Live migrate VMs]. * xref:../virt/backup_restore/virt-backup-restore-overview.adoc#virt-backup-restore-overview[Back up and restore VMs]. diff --git a/virt/virtual_machines/advanced_vm_management/virt-configuring-a-watchdog.adoc b/virt/virtual_machines/advanced_vm_management/virt-configuring-a-watchdog.adoc deleted file mode 100644 index e30c34d54b..0000000000 --- a/virt/virtual_machines/advanced_vm_management/virt-configuring-a-watchdog.adoc +++ /dev/null @@ -1,23 +0,0 @@ -:_content-type: ASSEMBLY -[id="virt-configuring-a-watchdog"] -= Configuring a watchdog -include::_attributes/common-attributes.adoc[] -:context: virt-configuring-a-watchdog - -toc::[] - -Expose a watchdog by configuring the virtual machine (VM) for a watchdog device, installing the watchdog, and starting the watchdog service. - -[id="{context}_prerequisites"] -== Prerequisites - -* The virtual machine must have kernel support for an `i6300esb` watchdog device. {op-system-base-full} images support `i6300esb`. - -include::modules/virt-defining-a-watchdog.adoc[leveloffset=+1] -include::modules/virt-installing-a-watchdog.adoc[leveloffset=+1] - -[id="{context}_additional-resources"] -[role="_additional-resources"] -== Additional resources - -* xref:../../../applications/application-health.html[Monitoring application health by using health checks]