From 7993c39beeef1eaa8ce797044935d82ceb2c02e6 Mon Sep 17 00:00:00 2001 From: nbaenam Date: Tue, 27 Aug 2024 13:23:40 +0200 Subject: [PATCH 1/8] feat(K8s): Updating the K8s troubleshooting section --- .../configure-control-plane-monitoring.mdx | 2 +- .../get-logs-version.mdx | 2 +- .../common-error-messages/error-messages.mdx | 31 +++++ .../error-sending-events.mdx | 26 ++++ .../failed-discover-kube.mdx | 33 +++++ .../installation-error-dockerhub-registry.mdx | 20 +++ .../invalid-nr-license.mdx | 24 ++++ .../pod-not-starting.mdx | 37 ++++++ .../repo-newrelic-not-found.mdx | 26 ++++ .../unable-connect-server.mdx | 24 ++++ ...gration-troubleshooting-error-messages.mdx | 119 ------------------ ...ration-troubleshooting-not-seeing-data.mdx | 29 ----- ...ng-missing-nodes.mdx => missing-nodes.mdx} | 2 +- .../troubleshooting/not-seeing-data.mdx | 33 +++++ .../configure-control-plane-monitoring.mdx | 2 +- .../get-logs-version.mdx | 2 +- ...gration-troubleshooting-error-messages.mdx | 116 ----------------- ...ng-missing-nodes.mdx => missing-nodes.mdx} | 2 +- ...ot-seeing-data.mdx => not-seeing-data.mdx} | 2 +- .../configure-control-plane-monitoring.mdx | 2 +- .../get-logs-version.mdx | 2 +- ...gration-troubleshooting-error-messages.mdx | 116 ----------------- ...ng-missing-nodes.mdx => missing-nodes.mdx} | 2 +- ...ot-seeing-data.mdx => not-seeing-data.mdx} | 2 +- .../configure-control-plane-monitoring.mdx | 2 +- .../get-logs-version.mdx | 2 +- ...gration-troubleshooting-error-messages.mdx | 116 ----------------- ...ng-missing-nodes.mdx => missing-nodes.mdx} | 2 +- ...ot-seeing-data.mdx => not-seeing-data.mdx} | 2 +- .../configure-control-plane-monitoring.mdx | 2 +- .../get-logs-version.mdx | 2 +- ...gration-troubleshooting-error-messages.mdx | 116 ----------------- ...ng-missing-nodes.mdx => missing-nodes.mdx} | 2 +- ...ot-seeing-data.mdx => not-seeing-data.mdx} | 2 +- src/install/kubernetes/find-data.mdx | 2 +- src/nav/kubernetes-pixie.yml | 36 ++++-- 36 files changed, 300 insertions(+), 642 deletions(-) create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/installation-error-dockerhub-registry.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/invalid-nr-license.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/repo-newrelic-not-found.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/unable-connect-server.mdx delete mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx delete mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx rename src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-missing-nodes.mdx => missing-nodes.mdx} (92%) create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx delete mode 100644 src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx rename src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-missing-nodes.mdx => missing-nodes.mdx} (91%) rename src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-not-seeing-data.mdx => not-seeing-data.mdx} (90%) delete mode 100644 src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx rename src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-missing-nodes.mdx => missing-nodes.mdx} (93%) rename src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-not-seeing-data.mdx => not-seeing-data.mdx} (89%) delete mode 100644 src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx rename src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-missing-nodes.mdx => missing-nodes.mdx} (91%) rename src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-not-seeing-data.mdx => not-seeing-data.mdx} (86%) delete mode 100644 src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx rename src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-missing-nodes.mdx => missing-nodes.mdx} (92%) rename src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/{kubernetes-integration-troubleshooting-not-seeing-data.mdx => not-seeing-data.mdx} (91%) diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx index 2421a46e84e..4fbd34b1545 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx @@ -372,5 +372,5 @@ SELECT latest(timestamp) FROM K8sApiServerSample, K8sEtcdSample, K8sSchedulerSam ``` - If you still can't see Control Plane data, try the solution described in [Kubernetes integration troubleshooting: Not seeing data](/docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data). + If you still can't see Control Plane data, check out [this troubleshooting page](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data). diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx index 4370b0dda06..7e6481ebe77 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx @@ -11,7 +11,7 @@ redirects: freshnessValidatedDate: never --- -To generate verbose logs and get version and configuration information, follow the steps below. For troubleshooting help, see [Not seeing data](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data) or [Error messages](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +To generate verbose logs and get version and configuration information, follow the steps below. For troubleshooting help, see [Not seeing data](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data) or [Error messages](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). If you're using version 2 of the integration, see [Kubernetes logs in version 2](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview/#logs-version2). diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages.mdx new file mode 100644 index 00000000000..9d350204660 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages.mdx @@ -0,0 +1,31 @@ +--- +title: Error messages +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: 'Some of the more common error messages found in the infrastructure agent logs for New Relic Kubernetes integration.' +redirects: + - /docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages + - /docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages +freshnessValidatedDate: 2024-09-02 +--- + +It's possible that you may see error messages from your terminal during the installation of the Kubernetes integration, or when you check your New Relic infrastructure logs after the integration is installed. + +These are the possible error messages you can see: + +* [Error sending events](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events) +* [Failed to discover kube-state-metrics](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube) +* [Invalid New Relic license](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/invalid-nr-license) +* [Installation error due to Dockerhub and registry.k8s.io](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/installation-error-dockerhub-registry) +* [Pod is not starting](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting) +* [Repo newrelic not found](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/repo-newrelic-not-found) +* [Unable to connect to the server](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/unable-connect-server) + + + + + + diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx new file mode 100644 index 00000000000..e0133fd03c9 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx @@ -0,0 +1,26 @@ +--- +title: 'Error sending events' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if you receive an error when sending events. +freshnessValidatedDate: 2024-09-02 +--- + +## Problem + +The agent can't connect to the New Relic servers and you see an error like the following in the logs of the `agent` or `forwarder` containers: + + ```shell + 2018-04-09T18:16:35.497195185Z time="2018-04-09T18:16:35Z" level=error + msg="metric sender can't process 1 times" error="Error sending events: + Post https://staging-infra-api.newrelic.com/metrics/events/bulk: + net/http: request canceled (Client.Timeout exceeded while awaiting headers)" + ``` + + +## Solution + +Depending on the exact nature of the error the message in the logs may differ. To address this problem, see the [New Relic networks documentation](/docs/new-relic-solutions/get-started/networks/#infrastructure). \ No newline at end of file diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx new file mode 100644 index 00000000000..c3d894cc25b --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx @@ -0,0 +1,33 @@ +--- +title: 'Failed to discover kube-state-metrics' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if kube-state-metrics is not found. +freshnessValidatedDate: 2024-09-02 +--- + +## Problem + +The Kubernetes integration requires `kube-state-metrics`. If this is missing, you'll see an error like the following in the `newrelic-infra` container logs: + + ```shell + time="2022-06-21T09:12:20Z" level=error msg="retrieving scraper data: retrieving ksm data: discovering KSM endpoints: timeout discovering endpoints" + ``` + +## Solution + +Check the following: + + * `kube-state-metrics` has not been deployed into the cluster. + * `kube-state-metrics` is deployed using a custom deployment. + * There are multiple versions of `kube-state-metrics` running and the Kubernetes integration is not finding the correct one. + +The Kubernetes integration automatically detects `kube-state-metrics` in your cluster, using by default the label `"app.kubernetes.io/name=kube-state-metrics"` across all namespaces. + + + + You can change the discovery behavior in the `ksm.config` of the [Helm chart] (https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml) values. + diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/installation-error-dockerhub-registry.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/installation-error-dockerhub-registry.mdx new file mode 100644 index 00000000000..885fc64ec86 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/installation-error-dockerhub-registry.mdx @@ -0,0 +1,20 @@ +--- +title: 'Installation error due to Dockerhub and registry.k8s.io' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if you have an installation error due to Dockerhub and registry.k8s.io. +freshnessValidatedDate: 2024-09-02 +--- + +## Problem + +You have a problem with the [New Relic dockerhub](https://hub.docker.com/u/newrelic) and Google's [`registry.k8s.io`](https://github.com/kubernetes/registry.k8s.io) during the installation. + + +## Solution + +Check you've added their domains to your allow list. The installation pulls the container images from this location. You can [test connectivity to `registry.k8s.io`](https://kubernetes.io/blog/2023/03/10/image-registry-redirect/#how-can-i-check-if-i-am-impacted) to find the extra Google registry domains to add to your whitelist. `registry.k8s.io` usually redirects to your local registry domain. For example, `asia-northeast1-docker.pkg.dev` based on your region. + diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/invalid-nr-license.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/invalid-nr-license.mdx new file mode 100644 index 00000000000..ed60d3e9199 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/invalid-nr-license.mdx @@ -0,0 +1,24 @@ +--- +title: 'Invalid New Relic license' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if the New Relic license is invalid. +freshnessValidatedDate: 2024-09-02 +--- + +## Problem + +You are getting this error in the logs of the `agent` or `forwarder` containers: + + ```shell + 2018-04-09T14:20:17.750893186Z time="2018-04-09T14:20:17Z" level=error + msg="metric sender can't process 0 times" error="InventoryIngest: events + were not accepted: 401 401 Unauthorized Invalid license key." + ``` + +## Solution + +Make sure you're using a valid . diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx new file mode 100644 index 00000000000..3bafd6fa7ff --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx @@ -0,0 +1,37 @@ +--- +title: 'Pod is not starting' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if the Pod is not starting. +freshnessValidatedDate: 2024-09-02 +--- + +## Problem + +You get the output error `nrk8s-kubelet pod is not starting` when you follow the guided installation. + +## Solution + +This error indicates that the Kubernetes kubelet pod can't be started within 5 minutes, and the installation script fails due to this timeout. + +In this case, you can run this command to see the pod's status and restarts: + + ```bash + kubectl get pods -o wide -n newrelic | grep nrk8s-kubelet + ``` + +Check the following: + + * If the pod is in `ImagePullBackOff` status, please check your network connection to allow image pulling from the [right domains](/docs/new-relic-solutions/get-started/networks). + + + * If the pod is in `Pending` or `ContainerCreating` status, please run these commands to find out the possible reasons from the logs: + + ```bash + kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic + kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic -c kubelet + ``` + diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/repo-newrelic-not-found.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/repo-newrelic-not-found.mdx new file mode 100644 index 00000000000..eb687bea5a2 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/repo-newrelic-not-found.mdx @@ -0,0 +1,26 @@ +--- +title: 'Repo newrelic not found' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if the newrelic repo is not found. +freshnessValidatedDate: 2024-09-02 +--- + +## Problem + +You see this error message during your [Kubernetes integration installation](/install/kubernetes/) with Helm or Manifest. + + ```shell + repo newrelic not found + ``` + +## Solution + +Add the newrelic repo to your helm chart by running this command: + + ```shell + helm repo add newrelic https://helm-charts.newrelic.com + ``` \ No newline at end of file diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/unable-connect-server.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/unable-connect-server.mdx new file mode 100644 index 00000000000..e42abcf51b7 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/unable-connect-server.mdx @@ -0,0 +1,24 @@ +--- +title: 'Unable to connect to the server' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if you're having issues with the networking connection. +freshnessValidatedDate: 2024-09-02 +--- + +## Problem + +You get this output error when you're following the guided install. + + ```shell + Unable to connect to the server: dial tcp [7777:777:7777:7777:77::77]:443: i/o timeout + ``` + +## Solution + +This indicates that you're experiencing a network connection issue between the Kubernetes client and the Kubernetes API server. Make sure your Kubernetes client can connect to your Kubernetes API server before running the guided install again. + + diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx deleted file mode 100644 index a5cf4def122..00000000000 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx +++ /dev/null @@ -1,119 +0,0 @@ ---- -title: Error messages -type: troubleshooting -tags: - - Integrations - - Kubernetes integration - - Troubleshooting -metaDescription: 'Some of the more common error messages found in the infrastructure agent logs for New Relic Kubernetes integration.' -redirects: - - /docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages - - /docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages -freshnessValidatedDate: never ---- - -## Problem [#problem] - -You are getting error messages for the [New Relic Kubernetes integration](/docs/integrations/host-integrations/host-integrations-list/kubernetes-monitoring-integration) from your terminal during the Kubernetes integration installation or in your New Relic infrastructure logs after the Kubernetes integration installation. - - - - If you see the following error message during your manual Kubernetes intergration installation: - - ```shell - repo newrelic not found - ``` - - You may have forgotten or skipped this command for adding the newrelic repo to your helm chart: - - ```shell - helm repo add newrelic https://helm-charts.newrelic.com - ``` - - - - If the license you are using is invalid then you will see an error like this in the logs of the `agent` or `forwarder` containers: - - ```shell - 2018-04-09T14:20:17.750893186Z time="2018-04-09T14:20:17Z" level=error - msg="metric sender can't process 0 times" error="InventoryIngest: events - were not accepted: 401 401 Unauthorized Invalid license key." - ``` - - To resolve this problem make sure you specify a valid . - - - - If the agent is not able to connect to New Relic servers you will see an error like the following in the logs of the `agent` or `forwarder` containers: - - ```shell - 2018-04-09T18:16:35.497195185Z time="2018-04-09T18:16:35Z" level=error - msg="metric sender can't process 1 times" error="Error sending events: - Post https://staging-infra-api.newrelic.com/metrics/events/bulk: - net/http: request canceled (Client.Timeout exceeded while awaiting headers)" - ``` - - Depending on the exact nature of the error the message in the logs may differ. - - To address this problem, see the [New Relic networks documentation](/docs/apm/new-relic-apm/getting-started/networks#infrastructure). - - - - The Kubernetes integration requires `kube-state-metrics`. If this is missing, you'll see an error like the following in the `newrelic-infra` container logs: - - ```shell - time="2022-06-21T09:12:20Z" level=error msg="retrieving scraper data: retrieving ksm data: discovering KSM endpoints: timeout discovering endpoints" - ``` - - Common reasons for this error include: - - * `kube-state-metrics` has not been deployed into the cluster. - * `kube-state-metrics` is deployed using a custom deployment. - * There are multiple versions of `kube-state-metrics` running and the Kubernetes integration is not finding the correct one. - - The Kubernetes integration automatically discovers `kube-state-metrics` in your cluster using by default leveraging the label `"app.kubernetes.io/name=kube-state-metrics"` across all namespaces. - - You can change the discovery behavior in the `ksm.config` of the helm [chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). - - - - During the guided install, an output error like the one below indicates that you are experiencing a networking connection issue between the Kubernetes client and Kubernetes API server. Please make sure your Kubernetes client can connect to your Kubernetes API server before you run the guided install again. - - ```shell - Unable to connect to the server: dial tcp [7777:777:7777:7777:77::77]:443: i/o timeout - ``` - - - - During the guided install, an output error, like `nrk8s-kubelet pod is not starting`, indicates that the Kubernetes kubelet pod cannot be started within 5 minutes and the installation script exits due to this timeout. - In this case, you can run `kubectl get pods -o wide -n newrelic | grep nrk8s-kubelet` to see the pod's status and restarts. - - * If the pod is in `ImagePullBackOff` status, please check you network connection to allow image pulling from the domains listed [here](/install/kubernetes). - * If the pod is in `Pending` or `ContainerCreating` status, please use `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic` and `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic -c kubelet` to figure out the potential reasons from the logs. - - - - If you have a problem with the [New Relic dockerhub](https://hub.docker.com/u/newrelic) and Google's [`registry.k8s.io`](https://github.com/kubernetes/registry.k8s.io) during the installation, check you've added their domains to your allow list. The installation pulls the container images from this location. You may need to follow the [commands](https://kubernetes.io/blog/2023/03/10/image-registry-redirect/#how-can-i-check-if-i-am-impacted) to find the extra Google registry domains to add to your whitelist. `registry.k8s.io` usually redirects to your local registry domain. For example, `asia-northeast1-docker.pkg.dev` based on your region. - - diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx deleted file mode 100644 index 03305fec8f3..00000000000 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx +++ /dev/null @@ -1,29 +0,0 @@ ---- -title: 'Not seeing data' -type: troubleshooting -tags: - - Integrations - - Kubernetes integration - - Troubleshooting -metaDescription: Some troubleshooting tips if you are not seeing data show up for your New Relic Kubernetes integration. -redirects: - - /docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data - - /docs/kubernetes-integration-troubleshooting-not-seeing-data - - /docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data -freshnessValidatedDate: never ---- - -## Problem - -You have [installed the New Relic Kubernetes integration](/install/kubernetes/), but are not seeing Kubernetes data in your New Relic account. - -## Solution - -1. Confirm you have configured `CLUSTER_NAME` and `NRI_LICENSE_KEY` correctly. See the [installation instructions](/docs/integrations/host-integrations/host-integrations-list/kubernetes-monitoring-integration#install) for more information. -2. Confirm the deployment of the integration was successful by running: - ``` - kubectl get pods -o wide -n - kubectl get deployments -o wide -n - kubectl get daemonsets -o wide -n - ``` -3. [Retrieve the logs from the infrastructure agent and the integration](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) and ensure there are no [error messages](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx similarity index 92% rename from src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx rename to src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 7dd0e95904d..7988ead86dd 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -35,4 +35,4 @@ If you [deployed the infrastructure agent](#install) and completed the [Kubernet FROM K8sNodeSample SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName LIMIT max SINCE 1 DAY AGO ``` -3. [Retrieve the logs from the infrastructure agent](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) on the nodes that do not appear in the cluster explorer and confirm there are no [error messages](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +3. [Retrieve the logs from the infrastructure agent](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) on the nodes that do not appear in the cluster explorer and confirm there are no [error messages](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx new file mode 100644 index 00000000000..dacbe5a61c6 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx @@ -0,0 +1,33 @@ +--- +title: 'Not seeing data' +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips if you are not seeing data show up for your New Relic Kubernetes integration. +redirects: + - /docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data + - /docs/kubernetes-integration-troubleshooting-not-seeing-data + - /docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data + - docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data +freshnessValidatedDate: never +--- + +## Problem + +You have installed the [New Relic Kubernetes integration](/install/kubernetes/), but you don't see any Kubernetes data in your New Relic account. + +## Solution + +1. Make sure that you have configured the `CLUSTER_NAME` and `NRI_LICENSE_KEY` parameters correctly in the [`values-newrelic.yaml`](https://github.com/newrelic/helm-charts/blob/master/charts/nri-bundle/values.yaml) file. + +2. Confirm the successful deployment of the integration by running these commands: + + ```bash + kubectl get pods -o wide -n + kubectl get deployments -o wide -n + kubectl get daemonsets -o wide -n + ``` + +3. [Check the logs](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) from the infrastructure agent and the integration and make sure that there are no error messages. diff --git a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx index 059baea215f..b228dbf6f04 100644 --- a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx +++ b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx @@ -388,5 +388,5 @@ SELECT latest(timestamp) FROM K8sApiServerSample, K8sEtcdSample, K8sSchedulerSam ``` - Si aún no puede ver los datos del plano de control, pruebe la solución descrita en [Kubernetes integración resolución de problemas: No ver datos](/docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data). + Si aún no puede ver los datos del plano de control, pruebe la solución descrita en [Kubernetes integración resolución de problemas: No ver datos](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data). diff --git a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx index bb179f8027e..146b06d7c07 100644 --- a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx +++ b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx @@ -9,7 +9,7 @@ freshnessValidatedDate: never translationType: machine --- -Para generar un registro detallado y obtener información de versión y configuración, siga los pasos a continuación. Para obtener ayuda sobre la resolución de problemas, consulte [No ver datos](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data) o [mensaje de error](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +Para generar un registro detallado y obtener información de versión y configuración, siga los pasos a continuación. Para obtener ayuda sobre la resolución de problemas, consulte [No ver datos](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data) o [mensaje de error](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). Si está empleando la versión 2 de la integración, consulte [Iniciar sesión enKubernetes versión 2](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview/#logs-version2). diff --git a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx deleted file mode 100644 index 49f08cf2a87..00000000000 --- a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx +++ /dev/null @@ -1,116 +0,0 @@ ---- -title: Mensaje de error -type: troubleshooting -tags: - - Integrations - - Kubernetes integration - - Troubleshooting -metaDescription: Some of the more common error messages found in the infrastructure agent logs for New Relic Kubernetes integration. -freshnessValidatedDate: never -translationType: machine ---- - -## Problema [#problem] - -Recibe un mensaje de error para la [integración de New Relic Kubernetes ](/docs/integrations/host-integrations/host-integrations-list/kubernetes-monitoring-integration)desde su terminal durante la instalación de la integración Kubernetes o en su registro New Relic Infrastructure después de la instalación de la integración de Kubernetes . - - - - Si ve el siguiente mensaje de error durante la instalación manual de integración de Kubernetes: - - ```shell - repo newrelic not found - ``` - - Es posible que haya olvidado u omitido este comando para agregar el repositorio de newrelic a su gráfico de timón: - - ```shell - helm repo add newrelic https://helm-charts.newrelic.com - ``` - - - - Si la licencia que está utilizando no es válida, verá un error como este en el registro del contenedor `agent` o `forwarder` : - - ```shell - 2018-04-09T14:20:17.750893186Z time="2018-04-09T14:20:17Z" level=error - msg="metric sender can't process 0 times" error="InventoryIngest: events - were not accepted: 401 401 Unauthorized Invalid license key." - ``` - - Para resolver este problema, asegúrese de especificar un válido. - - - - Si el agente no puede conectarse a los servidores New Relic , verá un error como el siguiente en el registro del contenedor `agent` o `forwarder`: - - ```shell - 2018-04-09T18:16:35.497195185Z time="2018-04-09T18:16:35Z" level=error - msg="metric sender can't process 1 times" error="Error sending events: - Post https://staging-infra-api.newrelic.com/metrics/events/bulk: - net/http: request canceled (Client.Timeout exceeded while awaiting headers)" - ``` - - Dependiendo de la naturaleza exacta del error, el mensaje en el registro puede diferir. - - Para solucionar este problema, consulte la [documentación de redes de New Relic](/docs/apm/new-relic-apm/getting-started/networks#infrastructure). - - - - La integración de Kubernetes requiere `kube-state-metrics`. Si falta esto, verá un error como el siguiente en el registro del contenedor `newrelic-infra` : - - ```shell - time="2022-06-21T09:12:20Z" level=error msg="retrieving scraper data: retrieving ksm data: discovering KSM endpoints: timeout discovering endpoints" - ``` - - Las razones comunes para este error incluyen: - - * `kube-state-metrics` no se ha implementado en el clúster. - * `kube-state-metrics` es desplegar usando un despliegue personalizado. - * Hay varias versiones de `kube-state-metrics` ejecutándose y la integración de Kubernetes no encuentra la correcta. - - La integración Kubernetes descubre automáticamente `kube-state-metrics` en su clúster aprovechando de forma predeterminada la etiqueta `"app.kubernetes.io/name=kube-state-metrics"` en todo el espacio de nombres. - - Puede cambiar el comportamiento de descubrimiento en el `ksm.config` de los [valores del gráfico de](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml) timón. - - - - Durante la instalación guiada, un error de salida como el siguiente indica que está experimentando un problema de conexión de red entre el cliente de Kubernetes y el servidor API de Kubernetes. Asegúrese de que su cliente de Kubernetes pueda conectarse a su servidor API de Kubernetes antes de volver a ejecutar la instalación guiada. - - ```shell - Unable to connect to the server: dial tcp [7777:777:7777:7777:77::77]:443: i/o timeout - ``` - - - - Durante la instalación guiada, un error de salida, como `nrk8s-kubelet pod is not starting`, indica que el pod Kubernetes kubelet no se puede iniciar en 5 minutos y el script de instalación se cierra debido a este tiempo de espera. En este caso, puede ejecutar `kubectl get pods -o wide -n newrelic | grep nrk8s-kubelet` para ver el estado y los reinicios del pod. - - * Si el pod está en estado `ImagePullBackOff`, verifique su conexión de red para permitir la extracción de imágenes del dominio que se enumera [aquí](/install/kubernetes). - * Si el pod está en estado `Pending` o `ContainerCreating`, utilice `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic` y `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic -c kubelet` para descubrir los posibles motivos en el registro. - - - - Si tienes un problema con el [dockerhubNew Relic ](https://hub.docker.com/u/newrelic)y [el`registry.k8s.io`](https://github.com/kubernetes/registry.k8s.io) de Google durante la instalación, verifica que agregaste su dominio a tu lista de 'permitidos'. La instalación extrae las imágenes del contenedor de esta ubicación. Es posible que deba seguir los [comandos](https://kubernetes.io/blog/2023/03/10/image-registry-redirect/#how-can-i-check-if-i-am-impacted) para encontrar el dominio de registro de Google adicional para agregar a su lista blanca. `registry.k8s.io` normalmente redirige a su dominio de registro local. Por ejemplo, `asia-northeast1-docker.pkg.dev` según su región. - - diff --git a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx similarity index 91% rename from src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx rename to src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 7776b7b961f..7d7135ece0d 100644 --- a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx +++ b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -34,4 +34,4 @@ Si [implementó el agente de infraestructura](#install) y completó el [procedim FROM K8sNodeSample SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName LIMIT max SINCE 1 DAY AGO ``` -3. [Recuperar el log del agente de infraestructura](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) sobre los nodos que no aparecen en el cluster explorer y confirmar que no hay ningún [mensaje de error](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +3. [Recuperar el log del agente de infraestructura](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) sobre los nodos que no aparecen en el cluster explorer y confirmar que no hay ningún [mensaje de error](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). diff --git a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx similarity index 90% rename from src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx rename to src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx index db70a91ab44..6e3bc852ba6 100644 --- a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx +++ b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx @@ -26,4 +26,4 @@ Ha [instalado la integración de New Relic Kubernetes](/install/kubernetes/), pe kubectl get daemonsets -o wide -n ``` -3. [Recupere el registro del agente de infraestructura y de la integración](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) y asegúrese de que no haya [mensajes de error](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +3. [Recupere el registro del agente de infraestructura y de la integración](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) y asegúrese de que no haya [mensajes de error](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). diff --git a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx index 1f812235e05..a37bde50cf9 100644 --- a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx +++ b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx @@ -388,5 +388,5 @@ SELECT latest(timestamp) FROM K8sApiServerSample, K8sEtcdSample, K8sSchedulerSam ``` - それでもコントロールプレーンのデータが表示されない場合は、 [Kubernetesインテグレーションのトラブルシューティングで説明している解決方法を試してみてください。データが見えない](/docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data) 。 + それでもコントロールプレーンのデータが表示されない場合は、 [Kubernetesインテグレーションのトラブルシューティングで説明している解決方法を試してみてください。データが見えない](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data) 。 diff --git a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx index a51f57f8da1..032c9a261b5 100644 --- a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx +++ b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx @@ -9,7 +9,7 @@ freshnessValidatedDate: never translationType: machine --- -詳細なログを生成し、バージョンと設定情報を取得するには、次の手順に従います。 トラブルシューティングのヘルプについては、「 [データが表示されない」](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data)または[「エラーメッセージ」を](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages)参照してください。 +詳細なログを生成し、バージョンと設定情報を取得するには、次の手順に従います。 トラブルシューティングのヘルプについては、「 [データが表示されない」](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data)または[「エラーメッセージ」を](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages)参照してください。 インテグレーションのバージョン 2 を使用している場合は、 [バージョン 2 のKubernetes](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview/#logs-version2)を参照してください。 diff --git a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx deleted file mode 100644 index 81e7f95c558..00000000000 --- a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx +++ /dev/null @@ -1,116 +0,0 @@ ---- -title: エラーメッセージ -type: troubleshooting -tags: - - Integrations - - Kubernetes integration - - Troubleshooting -metaDescription: Some of the more common error messages found in the infrastructure agent logs for New Relic Kubernetes integration. -freshnessValidatedDate: never -translationType: machine ---- - -## 問題 [#problem] - -Kubernetes 統合のインストール中に端末から、または Kubernetes 統合のインストール後に [New Relic](/docs/integrations/host-integrations/host-integrations-list/kubernetes-monitoring-integration) インフラストラクチャ ログに、New Relic Kubernetes 統合のエラー メッセージが表示されます。 - - - - Kubernetes 統合の手動インストール中に次のエラー メッセージが表示された場合: - - ```shell - repo newrelic not found - ``` - - Helm チャートに newrelic リポジトリを追加するためのこのコマンドを忘れたか、スキップした可能性があります。 - - ```shell - helm repo add newrelic https://helm-charts.newrelic.com - ``` - - - - 使用しているライセンスが無効な場合、 `agent`または`forwarder`コンテナのログに次のようなエラーが表示されます。 - - ```shell - 2018-04-09T14:20:17.750893186Z time="2018-04-09T14:20:17Z" level=error - msg="metric sender can't process 0 times" error="InventoryIngest: events - were not accepted: 401 401 Unauthorized Invalid license key." - ``` - - この問題を解決するには、有効なを指定してください。 - - - - エージェントがNewRelicサーバーに接続できない場合、 `agent`または`forwarder`コンテナのログに次のようなエラーが表示されます。 - - ```shell - 2018-04-09T18:16:35.497195185Z time="2018-04-09T18:16:35Z" level=error - msg="metric sender can't process 1 times" error="Error sending events: - Post https://staging-infra-api.newrelic.com/metrics/events/bulk: - net/http: request canceled (Client.Timeout exceeded while awaiting headers)" - ``` - - エラーの内容によっては、ログに表示されるメッセージが異なる場合があります。 - - この問題に対処するには、 [New Relic networks documentation](/docs/apm/new-relic-apm/getting-started/networks#infrastructure) を参照してください。 - - - - Kubernetesインテグレーションには `kube-state-metrics` が必要です。 これが欠落している場合は、 `newrelic-infra`コンテナ ログに次のようなエラーが表示されます。 - - ```shell - time="2022-06-21T09:12:20Z" level=error msg="retrieving scraper data: retrieving ksm data: discovering KSM endpoints: timeout discovering endpoints" - ``` - - このエラーが発生する一般的な理由は以下の通りです。 - - * `kube-state-metrics` クラスターにデプロイされていません。 - * `kube-state-metrics` カスタム展開を使用して展開されます。 - * `kube-state-metrics`の複数のバージョンが実行されており、Kubernetes統合が正しいバージョンを検出していません。 - - Kubernetes 統合は、デフォルトですべての名前空間でラベル`"app.kubernetes.io/name=kube-state-metrics"`を利用して、クラスター内の`kube-state-metrics`自動的に検出します。 - - ヘルム[チャート値](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml)の`ksm.config`で検出動作を変更できます。 - - - - ガイド付きインストール中、以下のような出力エラーは、Kubernetes クライアントと Kubernetes API サーバーの間でネットワーク接続の問題が発生していることを示しています。ガイド付きインストールを再度実行する前に、Kubernetes クライアントが Kubernetes API サーバーに接続できることを確認してください。 - - ```shell - Unable to connect to the server: dial tcp [7777:777:7777:7777:77::77]:443: i/o timeout - ``` - - - - ガイド付きインストール中に、 `nrk8s-kubelet pod is not starting`のような出力エラーが発生し、Kubernetes kubelet ポッドを 5 分以内に開始できず、このタイムアウトによりインストール スクリプトが終了したことを示します。この場合、 `kubectl get pods -o wide -n newrelic | grep nrk8s-kubelet` を実行してポッドのステータスを確認し、再起動できます。 - - * ポッドが`ImagePullBackOff`ステータスの場合、ネットワーク接続を確認して、[ここに](/install/kubernetes)リストされているドメインからイメージをプルできるようにしてください。 - * ポッドのステータスが `Pending` または `ContainerCreating` の場合は、 `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic` と `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic -c kubelet` を使用して、ログから考えられる原因を特定してください。 - - - - インストレーション中に[New Relic dockerhub](https://hub.docker.com/u/newrelic)と Google の[`registry.k8s.io`](https://github.com/kubernetes/registry.k8s.io)に問題がある場合は、それらのドメインが「許可」リストに追加されているかどうかを確認してください。 インストレーションはこの場所からコンテナイメージを取得します。 ホワイトリストに追加する追加の Google レジストリ ドメインを見つけるには、 [コマンド](https://kubernetes.io/blog/2023/03/10/image-registry-redirect/#how-can-i-check-if-i-am-impacted)に従う必要がある場合があります。 `registry.k8s.io`通常、ローカル レジストリ ドメインにリダイレクトします。 たとえば、地域に応じて`asia-northeast1-docker.pkg.dev`になります。 - - diff --git a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx similarity index 93% rename from src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx rename to src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 1c354f1d7ed..6f51ba4b1e2 100644 --- a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx +++ b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -34,4 +34,4 @@ translationType: machine FROM K8sNodeSample SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName LIMIT max SINCE 1 DAY AGO ``` -3. [クラスタ エクスプローラに表示されないノードのインフラストラクチャ エージェントからログを取得し](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/)、 [エラー メッセージ](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages)がないことを確認します。 +3. [クラスタ エクスプローラに表示されないノードのインフラストラクチャ エージェントからログを取得し](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/)、 [エラー メッセージ](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages)がないことを確認します。 diff --git a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx similarity index 89% rename from src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx rename to src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx index 863bf854470..946746ecae0 100644 --- a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx +++ b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx @@ -26,4 +26,4 @@ translationType: machine kubectl get daemonsets -o wide -n ``` -3. [インフラストラクチャエージェントと統合からログを取得し、](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) [エラーメッセージ](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages)がないことを確認します。 +3. [インフラストラクチャエージェントと統合からログを取得し、](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) [エラーメッセージ](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages)がないことを確認します。 diff --git a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx index 62ddb38816b..970219d3c21 100644 --- a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx +++ b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx @@ -388,5 +388,5 @@ SELECT latest(timestamp) FROM K8sApiServerSample, K8sEtcdSample, K8sSchedulerSam ``` - 여전히 컨트롤 플레인 데이터가 표시되지 않으면 [Kubernetes 통합 문제 해결: 데이터가 표시되지 않음](/docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data) 에 설명된 솔루션을 시도하십시오. + 여전히 컨트롤 플레인 데이터가 표시되지 않으면 [Kubernetes 통합 문제 해결: 데이터가 표시되지 않음](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data) 에 설명된 솔루션을 시도하십시오. diff --git a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx index 278d65c63a1..c7489bd70e4 100644 --- a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx +++ b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx @@ -9,7 +9,7 @@ freshnessValidatedDate: never translationType: machine --- -자세한 로그를 생성하고 버전 및 설정 정보를 얻으려면 아래 단계를 따르세요. 문제 해결에 대한 도움말은 [데이터가 표시되지 않음](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data) 또는 [오류 메시지를](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages) 참조하세요. +자세한 로그를 생성하고 버전 및 설정 정보를 얻으려면 아래 단계를 따르세요. 문제 해결에 대한 도움말은 [데이터가 표시되지 않음](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data) 또는 [오류 메시지를](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages) 참조하세요. 통합 버전 2를 사용하는 경우 [버전 2의 Kubernetes 로그를](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview/#logs-version2) 참조하세요. diff --git a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx deleted file mode 100644 index 9c6c7752a55..00000000000 --- a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx +++ /dev/null @@ -1,116 +0,0 @@ ---- -title: 오류 메시지 -type: troubleshooting -tags: - - Integrations - - Kubernetes integration - - Troubleshooting -metaDescription: Some of the more common error messages found in the infrastructure agent logs for New Relic Kubernetes integration. -freshnessValidatedDate: never -translationType: machine ---- - -## 문제 [#problem] - -Kubernetes [통합](/docs/integrations/host-integrations/host-integrations-list/kubernetes-monitoring-integration) 설치 중에 터미널에서 또는 Kubernetes 통합 설치 후 New Relic 인프라 로그에서 New Relic Kubernetes 통합에 대한 오류 메시지를 받고 있습니다. - - - - 수동 Kubernetes 통합 설치 중에 다음 오류 메시지가 표시되는 경우: - - ```shell - repo newrelic not found - ``` - - 투구 차트에 newrelic 저장소를 추가하기 위해 이 명령을 잊었거나 건너뛰었을 수 있습니다. - - ```shell - helm repo add newrelic https://helm-charts.newrelic.com - ``` - - - - 사용 중인 라이선스가 유효하지 않은 경우 `agent` 또는 `forwarder` 컨테이너의 로그에 다음과 같은 오류가 표시됩니다. - - ```shell - 2018-04-09T14:20:17.750893186Z time="2018-04-09T14:20:17Z" level=error - msg="metric sender can't process 0 times" error="InventoryIngest: events - were not accepted: 401 401 Unauthorized Invalid license key." - ``` - - 이 문제를 해결하려면 유효한 지정해야 합니다. - - - - 에이전트가 New Relic 서버에 연결할 수 없는 경우 `agent` 또는 `forwarder` 컨테이너의 로그에 다음과 같은 오류가 표시됩니다. - - ```shell - 2018-04-09T18:16:35.497195185Z time="2018-04-09T18:16:35Z" level=error - msg="metric sender can't process 1 times" error="Error sending events: - Post https://staging-infra-api.newrelic.com/metrics/events/bulk: - net/http: request canceled (Client.Timeout exceeded while awaiting headers)" - ``` - - 오류의 정확한 특성에 따라 로그의 메시지가 다를 수 있습니다. - - 이 문제를 해결하려면 [New Relic 네트워크 설명서](/docs/apm/new-relic-apm/getting-started/networks#infrastructure) 를 참조하십시오. - - - - Kubernetes 통합에는 `kube-state-metrics` 필요합니다. 이것이 누락된 경우 `newrelic-infra` 컨테이너 로그에 다음과 같은 오류가 표시됩니다. - - ```shell - time="2022-06-21T09:12:20Z" level=error msg="retrieving scraper data: retrieving ksm data: discovering KSM endpoints: timeout discovering endpoints" - ``` - - 이 오류의 일반적인 이유는 다음과 같습니다. - - * `kube-state-metrics` 클러스터에 배포되지 않았습니다. - * `kube-state-metrics` 사용자 지정 배포를 사용하여 배포됩니다. - * 실행 중인 `kube-state-metrics` 의 여러 버전이 있으며 Kubernetes 통합이 올바른 버전을 찾지 못합니다. - - Kubernetes 통합은 기본적으로 모든 네임스페이스에서 `"app.kubernetes.io/name=kube-state-metrics"` 라벨을 활용하여 클러스터에서 `kube-state-metrics` 자동으로 검색합니다. - - helm [차트 값](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml) 의 `ksm.config` 에서 검색 동작을 변경할 수 있습니다. - - - - 가이드 설치 중에 아래와 같은 출력 오류는 Kubernetes 클라이언트와 Kubernetes API 서버 간에 네트워킹 연결 문제가 발생했음을 나타냅니다. 가이드 설치를 다시 실행하기 전에 Kubernetes 클라이언트가 Kubernetes API 서버에 연결할 수 있는지 확인하십시오. - - ```shell - Unable to connect to the server: dial tcp [7777:777:7777:7777:77::77]:443: i/o timeout - ``` - - - - 가이드 설치 중에 `nrk8s-kubelet pod is not starting`와 같은 출력 오류는 Kubernetes kubelet 포드를 5분 이내에 시작할 수 없으며 이 시간 초과로 인해 설치 스크립트가 종료됨을 나타냅니다. 이 경우 `kubectl get pods -o wide -n newrelic | grep nrk8s-kubelet` 실행하여 포드의 상태를 확인하고 다시 시작할 수 있습니다. - - * 패드가 `ImagePullBackOff` 상태인 경우 [여기에](/install/kubernetes) 나열된 패드에서 이미지를 가져올 수 있도록 네트워크 연결을 확인하세요. - * 포드가 `Pending` 또는 `ContainerCreating` 상태인 경우 `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic` 및 `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic -c kubelet` 를 사용하여 로그에서 잠재적 원인을 파악하십시오. - - - - 설치 중에 [뉴렐릭 dockerhub](https://hub.docker.com/u/newrelic) 및 Google의 [`registry.k8s.io`](https://github.com/kubernetes/registry.k8s.io) 에 문제가 있는 경우, 해당 항목을 사용자 목록에 추가했는지 확인하세요. 설치 시 이 위치에서 컨테이너 이미지를 가져옵니다. 화이트리스트/포함에 추가할 추가 Google 레지스트리를 찾으려면 [명령을](https://kubernetes.io/blog/2023/03/10/image-registry-redirect/#how-can-i-check-if-i-am-impacted) 따라야 할 수도 있습니다. `registry.k8s.io` 일반적으로 로컬 레지스트리 도메인으로 리디렉션됩니다. 예를 들어 지역에 따라 `asia-northeast1-docker.pkg.dev` 입니다. - - diff --git a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx similarity index 91% rename from src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx rename to src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index cfe77d73c4f..26053f2bb74 100644 --- a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx +++ b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -34,4 +34,4 @@ translationType: machine FROM K8sNodeSample SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName LIMIT max SINCE 1 DAY AGO ``` -3. 클러스터 탐색기에 표시되지 않는 노드의 [인프라 에이전트에서 로그를 검색하고](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) [오류 메시지](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages) 가 없는지 확인합니다. +3. 클러스터 탐색기에 표시되지 않는 노드의 [인프라 에이전트에서 로그를 검색하고](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) [오류 메시지](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages) 가 없는지 확인합니다. diff --git a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx similarity index 86% rename from src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx rename to src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx index 63063761ccb..ec87f487481 100644 --- a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx +++ b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx @@ -26,4 +26,4 @@ translationType: machine kubectl get daemonsets -o wide -n ``` -3. [인프라 에이전트 및 통합에서 로그를 검색하고](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) [오류 메시지](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages) 가 없는지 확인합니다. +3. [인프라 에이전트 및 통합에서 로그를 검색하고](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) [오류 메시지](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages) 가 없는지 확인합니다. diff --git a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx index 563fe2bdaad..1d8c49a1540 100644 --- a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx +++ b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/configure-control-plane-monitoring.mdx @@ -388,5 +388,5 @@ SELECT latest(timestamp) FROM K8sApiServerSample, K8sEtcdSample, K8sSchedulerSam ``` - Se você ainda não consegue ver os dados do Control Plane, tente a solução descrita em [Kubernetes integração resolução de problemas: Not see data](/docs/integrations/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data). + Se você ainda não consegue ver os dados do Control Plane, tente a solução descrita em [Kubernetes integração resolução de problemas: Not see data](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data). diff --git a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx index 4abbc96c83d..d28bd0e3cea 100644 --- a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx +++ b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version.mdx @@ -9,7 +9,7 @@ freshnessValidatedDate: never translationType: machine --- -Para gerar log detalhado e obter informações de versão e configuração, siga as etapas abaixo. Para obter ajuda sobre resolução de problemas, consulte [Não vendo dados](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data) ou [mensagem de erro](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +Para gerar log detalhado e obter informações de versão e configuração, siga as etapas abaixo. Para obter ajuda sobre resolução de problemas, consulte [Não vendo dados](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data) ou [mensagem de erro](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). Se você estiver usando a versão 2 da integração, consulte [LogKubernetes na versão 2](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview/#logs-version2). diff --git a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx deleted file mode 100644 index 0a5bed7ab96..00000000000 --- a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages.mdx +++ /dev/null @@ -1,116 +0,0 @@ ---- -title: Mensagem de erro -type: troubleshooting -tags: - - Integrations - - Kubernetes integration - - Troubleshooting -metaDescription: Some of the more common error messages found in the infrastructure agent logs for New Relic Kubernetes integration. -freshnessValidatedDate: never -translationType: machine ---- - -## Problema [#problem] - -Você está recebendo uma mensagem de erro para a [integração do New Relic Kubernetes ](/docs/integrations/host-integrations/host-integrations-list/kubernetes-monitoring-integration)em seu terminal durante a instalação de integração Kubernetes ou em seu log New Relic Infrastructure após a instalação de integração Kubernetes . - - - - Se você vir a seguinte mensagem de erro durante a instalação manual da integração do Kubernetes: - - ```shell - repo newrelic not found - ``` - - Você pode ter esquecido ou ignorado este comando para adicionar o repositório newrelic ao seu gráfico do helm: - - ```shell - helm repo add newrelic https://helm-charts.newrelic.com - ``` - - - - Se a licença que você está usando for inválida, você verá um erro como este no log do contêiner `agent` ou `forwarder` : - - ```shell - 2018-04-09T14:20:17.750893186Z time="2018-04-09T14:20:17Z" level=error - msg="metric sender can't process 0 times" error="InventoryIngest: events - were not accepted: 401 401 Unauthorized Invalid license key." - ``` - - Para resolver esse problema, certifique-se de especificar um válido. - - - - Se o agente não conseguir se conectar aos servidores New Relic você verá um erro como o seguinte no log do contêiner `agent` ou `forwarder`: - - ```shell - 2018-04-09T18:16:35.497195185Z time="2018-04-09T18:16:35Z" level=error - msg="metric sender can't process 1 times" error="Error sending events: - Post https://staging-infra-api.newrelic.com/metrics/events/bulk: - net/http: request canceled (Client.Timeout exceeded while awaiting headers)" - ``` - - Dependendo da natureza exata do erro, a mensagem no log pode ser diferente. - - Para resolver esse problema, consulte a [documentação das redes New Relic](/docs/apm/new-relic-apm/getting-started/networks#infrastructure). - - - - A integração do Kubernetes requer `kube-state-metrics`. Se estiver faltando, você verá um erro como este no log do contêiner `newrelic-infra` : - - ```shell - time="2022-06-21T09:12:20Z" level=error msg="retrieving scraper data: retrieving ksm data: discovering KSM endpoints: timeout discovering endpoints" - ``` - - Os motivos comuns para esse erro incluem: - - * `kube-state-metrics` não foi implantado no cluster. - * `kube-state-metrics` é implantar usando uma implantação personalizada. - * Há diversas versões de `kube-state-metrics` em execução e a integração do Kubernetes não está encontrando a versão correta. - - A integração Kubernetes descobre automaticamente `kube-state-metrics` em seu cluster usando, por padrão, o aproveitamento do rótulo `"app.kubernetes.io/name=kube-state-metrics"` em todo o namespace. - - Você pode alterar o comportamento de descoberta em `ksm.config` dos [valores do gráfico](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml) do Helm. - - - - Durante a instalação guiada, um erro de saída como o mostrado abaixo indica que você está enfrentando um problema de conexão de rede entre o cliente Kubernetes e o servidor API Kubernetes. Certifique-se de que seu cliente Kubernetes possa se conectar ao servidor API Kubernetes antes de executar a instalação guiada novamente. - - ```shell - Unable to connect to the server: dial tcp [7777:777:7777:7777:77::77]:443: i/o timeout - ``` - - - - Durante a instalação guiada, um erro de saída, como `nrk8s-kubelet pod is not starting`, indica que o pod kubelet do Kubernetes não pode ser iniciado em 5 minutos e o script de instalação é encerrado devido a esse tempo limite. Nesse caso, você pode executar `kubectl get pods -o wide -n newrelic | grep nrk8s-kubelet` para ver o status do pod e reinicializá-lo. - - * Se o pod estiver no status `ImagePullBackOff`, verifique sua conexão de rede para permitir a extração de imagens do domínio listado [aqui](/install/kubernetes). - * Se o pod estiver no status `Pending` ou `ContainerCreating`, use `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic` e `kubectl logs newrelic-bundle-nrk8s-kubelet-***** -n newrelic -c kubelet` para descobrir os possíveis motivos do registro. - - - - Se você tiver algum problema com o [dockerhubNew Relic ](https://hub.docker.com/u/newrelic)e [o`registry.k8s.io`](https://github.com/kubernetes/registry.k8s.io) do Google durante a instalação, verifique se adicionou o domínio deles à sua lista de permissões. A instalação extrai as imagens do contêiner desse local. Pode ser necessário seguir os [comandos](https://kubernetes.io/blog/2023/03/10/image-registry-redirect/#how-can-i-check-if-i-am-impacted) para encontrar o domínio de registro extra do Google para adicionar à sua lista de permissões. `registry.k8s.io` geralmente redireciona para seu domínio de registro local. Por exemplo, `asia-northeast1-docker.pkg.dev` com base na sua região. - - diff --git a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx similarity index 92% rename from src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx rename to src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 8f77ac4d1b9..a4a841aa75d 100644 --- a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes.mdx +++ b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -34,4 +34,4 @@ Se você [implantou o agente de infraestrutura](#install) e concluiu o [procedim FROM K8sNodeSample SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName LIMIT max SINCE 1 DAY AGO ``` -3. [Recupere o log do agente de infraestrutura](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) nos nós que não aparecem no cluster explorer e confirme que não há [mensagem de erro](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +3. [Recupere o log do agente de infraestrutura](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) nos nós que não aparecem no cluster explorer e confirme que não há [mensagem de erro](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). diff --git a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx similarity index 91% rename from src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx rename to src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx index 3b3dedb344b..a8b2e2783e3 100644 --- a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data.mdx +++ b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx @@ -26,4 +26,4 @@ Você [instalou a integração do New Relic Kubernetes](/install/kubernetes/), m kubectl get daemonsets -o wide -n ``` -3. [Recupere o log do agente de infraestrutura e integração](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) e certifique-se de que não haja [mensagens de erro](/docs/integrations/host-integrations/troubleshooting/kubernetes-integration-troubleshooting-error-messages). +3. [Recupere o log do agente de infraestrutura e integração](/docs/integrations/kubernetes-integration/troubleshooting/get-logs-version) e certifique-se de que não haja [mensagens de erro](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). diff --git a/src/install/kubernetes/find-data.mdx b/src/install/kubernetes/find-data.mdx index 7616ee6ed51..25bd77996ee 100644 --- a/src/install/kubernetes/find-data.mdx +++ b/src/install/kubernetes/find-data.mdx @@ -13,7 +13,7 @@ Once you've finished all the steps, you can test the connection to make sure eve /> - Not seeing data? If you completed the steps and are still not seeing data, check out [this troubleshooting page](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data/). + Not seeing data? If you completed the steps and are still not seeing data, check out [this troubleshooting page](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data). After the installation, you should see the following in the UI: diff --git a/src/nav/kubernetes-pixie.yml b/src/nav/kubernetes-pixie.yml index af77e2d5f6b..35e17ae72e0 100644 --- a/src/nav/kubernetes-pixie.yml +++ b/src/nav/kubernetes-pixie.yml @@ -77,20 +77,36 @@ pages: path: /docs/kubernetes-pixie/kubernetes-integration/installation/kubernetes-integration-recommended-alert-policy - title: Troubleshooting pages: - - title: Not seeing data - path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-not-seeing-data - title: Common error messages - path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-error-messages - - title: Unidentified certificate - path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/certificate-signed-unknown-authority + pages: + - title: Error messages + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages + - title: Error sending events + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events + - title: Failed to discover kube-state-metrics + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube + - title: Invalid New Relic license + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/invalid-nr-license + - title: Installation error due to Dockerhub and registry.k8s.io + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/installation-error-dockerhub-registry + - title: Pod is not starting + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting + - title: Repo newrelic not found + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/repo-newrelic-not-found + - title: Unable to connect to the server + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/unable-connect-server + - title: Helm configurations are not applied globally + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied + - title: Istio and Kubernetes + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio - title: Missing nodes - path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/kubernetes-integration-troubleshooting-missing-nodes + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes - title: Not seeing control plane data path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-control-plane-data - - title: Istio and Kubernetes - path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio - - title: Helm configurations are not applied globally - path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied + - title: Not seeing data + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data + - title: Unidentified certificate + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/certificate-signed-unknown-authority - title: Pixie pages: - title: Get to know Pixie From 227a51af847b96f298dce3b3e800b97b3ee346cf Mon Sep 17 00:00:00 2001 From: nbaenam Date: Tue, 27 Aug 2024 13:52:12 +0200 Subject: [PATCH 2/8] fix(K8s): Fixed errors in the common error messages section --- .../common-error-messages/failed-discover-kube.mdx | 4 ++-- .../common-error-messages/pod-not-starting.mdx | 4 ++-- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx index c3d894cc25b..bf8d94304fa 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx @@ -25,9 +25,9 @@ Check the following: * `kube-state-metrics` is deployed using a custom deployment. * There are multiple versions of `kube-state-metrics` running and the Kubernetes integration is not finding the correct one. -The Kubernetes integration automatically detects `kube-state-metrics` in your cluster, using by default the label `"app.kubernetes.io/name=kube-state-metrics"` across all namespaces. +The Kubernetes integration automatically detects `kube-state-metrics` in your cluster, using by default the label `app.kubernetes.io/name=kube-state-metrics` across all namespaces. - You can change the discovery behavior in the `ksm.config` of the [Helm chart] (https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml) values. + You can change the discovery behavior in the `ksm.config` of the [Helm chart](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml) values. diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx index 3bafd6fa7ff..62be20ca1df 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx @@ -31,7 +31,7 @@ Check the following: * If the pod is in `Pending` or `ContainerCreating` status, please run these commands to find out the possible reasons from the logs: ```bash - kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic - kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic -c kubelet + kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic + kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic -c kubelet ``` From 860cbed1f60330b090e768fe6413646e433bf25c Mon Sep 17 00:00:00 2001 From: nbaenam Date: Wed, 28 Aug 2024 13:15:11 +0200 Subject: [PATCH 3/8] feat(K8s): Updating the K8s troubleshooting section --- .../k8s-version2/errors.mdx | 2 +- .../k8s-version2/troubleshooting.mdx | 32 ----------- .../troubleshooting/missing-nodes.mdx | 36 ++++++++++++ .../k8s-version2/upgrade-v2.mdx | 2 +- .../helm-configurations-not-applied.mdx | 2 +- .../troubleshooting/issues-with-istio.mdx | 56 +++++++++---------- .../troubleshooting/missing-nodes.mdx | 28 +++++----- .../not-seeing-control-plane-data.mdx | 36 ++++++------ .../troubleshooting/missing-nodes.mdx | 2 +- .../troubleshooting/missing-nodes.mdx | 2 +- .../troubleshooting/missing-nodes.mdx | 2 +- .../troubleshooting/missing-nodes.mdx | 2 +- src/nav/kubernetes-pixie.yml | 10 ++-- 13 files changed, 109 insertions(+), 103 deletions(-) delete mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/errors.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/errors.mdx index e6ae6a9e80a..84f9269939e 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/errors.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/errors.mdx @@ -1,5 +1,5 @@ --- -title: Kubernetes integration errors v2 +title: Kubernetes integration errors (version 2) type: troubleshooting tags: - Integrations diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx deleted file mode 100644 index d3b44465ea0..00000000000 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx +++ /dev/null @@ -1,32 +0,0 @@ ---- -title: "Troubleshooting v2: Missing nodes" -type: troubleshooting -tags: - - Integrations - - Kubernetes integration v2 - - Troubleshooting -metaDescription: Some troubleshooting tips if you're not seeing data show up for your New Relic's Kubernetes integration. -freshnessValidatedDate: never ---- - -## Problem - -You've completed the [installation procedure](/install/kubernetes/) for New Relic's Kubernetes integration and the cluster shows up in your New Relic account, but some or all nodes are missing. - -## Solution - -If you [deployed the infrastructure agent](/docs/infrastructure/infrastructure-monitoring/get-started/choose-infra-install-method/) and completed the [Kubernetes installation procedure](/install/kubernetes/) but not all nodes show up, complete these steps: - -1. Confirm that the infrastructure agent can be scheduled on every node by running: - - ```shell - kubectl describe daemonset newrelic-infra - ``` - -2. Confirm that the time on all nodes is accurate. Nodes that are more than 2 minutes ahead or behind will not show up in the Cluster explorer. The following NRQL query can be used to check if this is the case: - - ```sql - FROM K8sNodeSample SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName LIMIT max SINCE 1 DAY AGO - ``` - -3. [Retrieve the logs from the infrastructure agent](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview/#logs-version2) on the nodes that do not appear in the cluster explorer and confirm there are no [error messages](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/errors/). diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx new file mode 100644 index 00000000000..2876293ade4 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx @@ -0,0 +1,36 @@ +--- +title: "Missing nodes for version 2" +type: troubleshooting +tags: + - Integrations + - Kubernetes integration v2 + - Troubleshooting +redirects: + - /docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting +metaDescription: Some troubleshooting tips if you're not seeing data show up for your New Relic's Kubernetes integration. +freshnessValidatedDate: never +--- + +## Problem + +You [deployed the infrastructure agent](/docs/infrastructure/infrastructure-monitoring/get-started/choose-infra-install-method/) and completed the [Kubernetes installation procedure](/install/kubernetes/) but not all nodes show up. + +## Solution + +Follow these steps: + +1. Confirm that you can schedule the infrastructure agent on each node by running this command: + + ```shell + kubectl describe daemonset newrelic-infra + ``` + +2. Confirm that the time on all nodes is accurate. Nodes that are more than 2 minutes ahead or behind will not show up in the Cluster explorer. The following NRQL query can be used to check if this is the case: + + ```sql + FROM K8sNodeSample + SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' + FACET nodeName LIMIT max SINCE 1 DAY AGO + ``` + +3. [Retrieve the logs from the infrastructure agent](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview/#logs-version2) on the nodes that do not appear in the cluster explorer and confirm there are no [error messages](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/errors/). diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/upgrade-v2.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/upgrade-v2.mdx index 58e140eaf6a..41ac56489df 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/upgrade-v2.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/upgrade-v2.mdx @@ -1,5 +1,5 @@ --- -title: Upgrade from v2 +title: Upgrade from version 2 tags: - Integrations - Kubernetes integration v2 diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied.mdx index 735104653cc..1963066c0a1 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied.mdx @@ -10,7 +10,7 @@ freshnessValidatedDate: 2023-08-02 ## Problem [#problem] -You have completed the [installation procedure](/install/kubernetes/) for New Relic's Kubernetes integration with Helm for the `nri-bundle`, but our Helm templates are not respecting some [global values](https://github.com/newrelic/helm-charts/tree/master/charts/nri-bundle#values) in your `values.yaml`. +You've installed the [New Relic's Kubernetes integration](/install/kubernetes/?dropdown1=helm) with Helm for the `nri-bundle`, but our Helm templates are not respecting some [global values](https://github.com/newrelic/helm-charts/tree/master/charts/nri-bundle#values) in your `values.yaml`. ## Solution [#solution] diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio.mdx index 5f8576c08e1..67e608c3e01 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio.mdx @@ -9,44 +9,44 @@ metaDescription: 'How to troubleshoot Istio issues when the New Relic integratio freshnessValidatedDate: never --- -If you have both Istio and the New Relic Kubernetes integration installed and enabled in your environment, issues may arise. -This page describes one issue with Istio when the New Relic Kubernetes integration is installed. +If you have both Istio and the New Relic Kubernetes integration installed and enabled in your environment, issues may arise. This page describes these issues with Istio when the New Relic Kubernetes integration is installed. -## Problems - - - When Istio is enabled in your clusters, the Istio-deployed Envoy proxies have a Prometheus metric endpoint that exposes Prometheus metrics. +## Istio cluster's xds_grpc metric [#istio-cluster-grpc-metric] - These metrics are associated with a dedicated `cluster_name` as `xds-grpc`. If you also enable the Prometheus agent in New Relic Kubernetes integration, the agent will collect these Envoy-related metrics with `cluster_name` as `xds_grpc` in addition to the metrics with `cluster_name` defined through `global.cluster`. +### Problem - Run the following query to get a full list of Envoy proxy metrics: +When Istio is enabled in your clusters, the Istio-deployed Envoy proxies have a Prometheus metric endpoint that exposes Prometheus metrics. - ```sql - FROM `Metric` - SELECT uniques(metricName) - WHERE cluster_name = 'xds-grpc' SINCE 1 week ago - ``` - +These metrics are associated with a dedicated `cluster_name` as `xds-grpc`. If you also enable the Prometheus agent in New Relic Kubernetes integration, the agent will collect these Envoy-related metrics with `cluster_name` as `xds_grpc` in addition to the metrics with `cluster_name` defined through `global.cluster`. - - When Istio is activated in the `newrelic` namespace, it could potentially cause complications for the New Relic Kubernetes integration pods situated within that namespace. These problems could be severe enough to prevent the pods from being created at all. - An example of such an issue might occur during the installation of the Kubernetes integration. If you see this error message: +### Solution - ``` +Run the following query to get a full list of Envoy proxy metrics: + + ```sql + FROM `Metric` + SELECT uniques(metricName) + WHERE cluster_name = 'xds-grpc' SINCE 1 week ago + ``` + +## Disable Istio for the metadata injection pod [#disable-istio] + +### Problem + +When Istio is activated in the `newrelic` namespace, it could potentially cause complications for the New Relic Kubernetes integration pods situated within that namespace. These problems could be severe enough to prevent the pods from being created at all. + +An example of such an issue might occur during the installation of the Kubernetes integration. If you see this error message: + + ```bash W0518 02:00:14.984463 1 client_config.go:615] Neither --kubeconfig nor --master was specified. Using the inClusterConfig. This might not work. {"err":"secrets \"newrelic-bundle-nri-metadata-injection-admission\" not found","level":"info","msg":"no secret found","source":"k8s/k8s.go:229","time":"2023-05-18T02:00:15Z"} {"level":"info","msg":"creating new secret","source":"cmd/create.go:28","time":"2023-05-18T02:00:15Z"} ... ``` - This indicates that Istio may be active in the `newrelic` namespace. In this case, the envoy proxy does not exit after the `newrelic-bundle-nri-metadata-injection-admission-create` job has successfully created the secret. As a result, the Kubernetes job becomes stuck in progress and fails to finish. +This indicates that Istio may be active in the `newrelic` namespace. In this case, the envoy proxy does not exit after the `newrelic-bundle-nri-metadata-injection-admission-create` job has successfully created the secret. As a result, the Kubernetes job becomes stuck in progress and fails to finish. + +### Solution + +We recommend you deactivate the Istio sidecar injection for the `nri-metadata-injection` pod within the newrelic namespace. To accomplish this, include `--set-string nri-metadata-injection.labels."sidecar\.istio\.io/inject"=false` in your `helm` command when installing the `nri-bundle`. - Therefore, to resolve such issues, we recommend you deactivate the Istio sidecar injection for the `nri-metadata-injection` pod within the newrelic namespace. To accomplish this, include `--set-string nri-metadata-injection.labels."sidecar\.istio\.io/inject"=false` in your `helm` command when installing the `nri-bundle`. - - diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 7988ead86dd..10c4e1fc752 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -13,26 +13,28 @@ freshnessValidatedDate: never ## Problem -You have completed the [installation procedure](/install/kubernetes/) for New Relic's Kubernetes integration and the cluster shows up in your New Relic account, but some or all nodes are missing. +You [deployed the infrastructure agent](/docs/infrastructure/infrastructure-monitoring/get-started/choose-infra-install-method/) and completed the [Kubernetes installation procedure](/install/kubernetes/) but not all nodes show up. ## Solution -If you [deployed the infrastructure agent](#install) and completed the [Kubernetes installation procedure](/install/kubernetes/) but not all nodes show up, complete these steps: +Follow these steps: -1. Confirm that the infrastructure agent can be scheduled on every node by running: +1. Confirm that you can schedule the infrastructure agent on each node by running this command: - ```shell - kubectl describe daemonset RELEASE_NAME-nrk8s-kubelet - ``` + ```shell + kubectl describe daemonset RELEASE_NAME-nrk8s-kubelet + ``` - - Notice that in V2 version of the Kubernetes integration this command changes. See [Troubleshooting K8s v2: Missing nodes](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting). - + + Notice that in V2 version of the Kubernetes integration this command changes. See [Missing nodes (version 2)](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes). + -2. Confirm that the time on all nodes is accurate. Nodes that are more than 2 minutes ahead or behind will not show up in the Cluster explorer. The following NRQL query can be used to check if this is the case: +2. Confirm that the time on all nodes is accurate. Nodes that are more than 2 minutes ahead or behind will not show up in the cluster explorer. The following NRQL query can be used to check if this is the case: - ```sql - FROM K8sNodeSample SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName LIMIT max SINCE 1 DAY AGO - ``` + ```sql + FROM K8sNodeSample + SELECT latest(nr.ingestTimeMs - timestamp) / 1000 AS 'Clock offset seconds' FACET nodeName + LIMIT max SINCE 1 DAY AGO + ``` 3. [Retrieve the logs from the infrastructure agent](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) on the nodes that do not appear in the cluster explorer and confirm there are no [error messages](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages). diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-control-plane-data.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-control-plane-data.mdx index b18f30325a8..9bf85390e64 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-control-plane-data.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-control-plane-data.mdx @@ -13,19 +13,20 @@ freshnessValidatedDate: never ## Problems -You have completed the [installation procedure](/install/kubernetes/) for New Relic's Kubernetes integration, you are seeing Kubernetes data in your New Relic account but there is no data from any of the control plane components. +You've completed the [Kubernetes installation procedure](/install/kubernetes/) and you're seeing Kubernetes data in your New Relic account but there's no data from any of the control plane components. + +## Solution - In case the control plane data is missing, for example `K8sSchedulerSample`, the first thing to do is to check verbose logs of the control plane components. Read how to [enable verbose logging](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/get-logs-version#verbose-logging) + In case the control plane data is missing, for example `K8sSchedulerSample`, the first thing to do is to check verbose logs of the control plane components. Read how to [enable verbose logging](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/#verbose-logging). - * A possibility is that the autodiscovery tries to find in the cluster the control plane pods leveraging the most common labels, in case no pod is found for a single component it does not fail to avoid missing more data. - In this scenario you will see logs similar to the following: + * One possibility is that autodiscovery tries to find the control plane pods in the cluster using the most common labels; if no pod is found for a single component, it does not fail to avoid missing more data. You'll see logs similar to the following: - ``` + ```bash time="2022-06-21T12:21:25Z" level=debug msg="Autodiscovering pods for \"scheduler\"" time="2022-06-21T12:21:25Z" level=debug msg="0 pods found with labels \"tier=control-plane,component=kube-scheduler\"" time="2022-06-21T12:21:25Z" level=debug msg="No pod found for \"scheduler\" with labels \"tier=control-plane,component=kube-scheduler\"" @@ -36,36 +37,33 @@ You have completed the [installation procedure](/install/kubernetes/) for New Re time="2022-06-21T12:21:25Z" level=debug msg="No \"scheduler\" pod has been discovered" ``` - In this case you can change the discovery behavior with the `controlplane.config.[component].autodiscover[].selector` config of the helm [chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). Read more about [control plane components](/docs/kubernetes-pixie/kubernetes-integration/get-started/kubernetes-components/#nrk8s-controlplane). + In this case, you can change the discovery behavior with the `controlplane.config.[component].autodiscover[].selector` config of the [Helm chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). Read more about the [control plane component](/docs/kubernetes-pixie/kubernetes-integration/get-started/kubernetes-components/#nrk8s-controlplane). - * It is also possible that the controlplane component is found, but the authentication with the endpoint fails. - In this scenario you will see logs similar to the following: + * It's also possible that the controlplane component is found, but the authentication with the endpoint fails. You'll see logs similar to the following: - ``` + ```bash time="2022-06-21T15:54:52Z" level=debug msg="Endpoint \"https://localhost:10257\" probe failed, skipping: http request failed with status: 403 Forbidden" ``` In this case you can change the authentication behavior for each endpoints with the `controlplane.config.[component].autodiscover[].endpoints[].auth` config of the helm [chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). - * It is also possible that the controlplane component of the integration is not running on all master nodes. + * It's also possible that the controlplane component of the integration is not running on all master nodes. You can doublecheck that running this command: - You can doublecheck that running: - - ``` + ```bash kubectl get pod -n -l app.kubernetes.io/component=controlplane -o wide ``` - If there is any controlplane pod you want to monitor running on a node whithout a Newrelic monitoring instance then you can change as needed `controlplane.affinity`, `controlplane.nodeSelector` and `controlplane.tolerations` of the helm [chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). + If there is any control plane pod you want to monitor running on a node whithout a New Relic monitoring instance then you can change as needed `controlplane.affinity`, `controlplane.nodeSelector`, and `controlplane.tolerations` of the [Helm chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). Control plane component is in CrashLoopBackOff} > - In case the controlplane components does not autodiscover or scrape succesfully any controlplane pod it enters in CrashLoopBackOff. + In case the control plane components doesn't autodiscover or scrape succesfully any control plane pod it enters in `CrashLoopBackOff`. - As described in the previous section you can change the behaviour of autodiscovery and the authentication methods to meet your needs. + You can change the behaviour of autodiscovery and the authentication methods to meet your needs. - On the other hand if you are not interested in that data you can simply disable the controlplane compoenent by setting `controlplane.enabled=false` in the the helm [chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). + On the other hand, if you are not interested in that data you can simply disable the control plane component by setting `controlplane.enabled=false` in the [Helm chart values](https://github.com/newrelic/nri-kubernetes/blob/main/charts/newrelic-infrastructure/values.yaml). diff --git a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 7d7135ece0d..1045e63aa43 100644 --- a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx +++ b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -25,7 +25,7 @@ Si [implementó el agente de infraestructura](#install) y completó el [procedim ``` - Tenga en cuenta que en la versión V2 de la integración de Kubernetes este comando cambia. Ver [resolución de problemas K8s v2: Nodos faltantes](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting). + Tenga en cuenta que en la versión V2 de la integración de Kubernetes este comando cambia. Ver [resolución de problemas K8s v2: Nodos faltantes](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes). 2. Confirme que la hora en todos los nodos sea exacta. Los nodos que estén más de 2 minutos por delante o por detrás no aparecerán en el explorador de clústeres. Se puede utilizar la siguiente consulta NRQL para comprobar si este es el caso: diff --git a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 6f51ba4b1e2..0101ab799e8 100644 --- a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx +++ b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -25,7 +25,7 @@ translationType: machine ``` - Kubernetesインテグレーションの V2 バージョンでは、このコマンドが変更されることに注意してください。 [「K8s v2 のトラブルシューティング: ノードが見つからない」](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting)を参照してください。 + Kubernetesインテグレーションの V2 バージョンでは、このコマンドが変更されることに注意してください。 [「K8s v2 のトラブルシューティング: ノードが見つからない」](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes)を参照してください。 2. すべてのノードの時刻が正確であることを確認します。2 分以上進んでいる、または遅れているノードは、クラスタ・エクスプローラに表示されません。以下の NRQL クエリを使用して、この問題が発生しているかどうかを確認できます。 diff --git a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index 26053f2bb74..0a65387d862 100644 --- a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx +++ b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -25,7 +25,7 @@ translationType: machine ``` - Kubernetes 통합의 V2 버전에서는 이 명령이 변경됩니다. [K8s v2 문제 해결: 노드 누락을](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting) 참조하세요. + Kubernetes 통합의 V2 버전에서는 이 명령이 변경됩니다. [K8s v2 문제 해결: 노드 누락을](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes) 참조하세요. 2. 모든 노드의 시간이 정확한지 확인합니다. 2분 이상 빠르거나 늦은 노드는 클러스터 탐색기에 표시되지 않습니다. 다음 NRQL 쿼리를 사용하여 이러한 경우를 확인할 수 있습니다. diff --git a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx index a4a841aa75d..0488df88076 100644 --- a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx +++ b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes.mdx @@ -25,7 +25,7 @@ Se você [implantou o agente de infraestrutura](#install) e concluiu o [procedim ``` - Observe que na versão V2 da integração do Kubernetes este comando muda. Consulte [resolução de problemas K8s v2: Nós ausentes](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting). + Observe que na versão V2 da integração do Kubernetes este comando muda. Consulte [resolução de problemas K8s v2: Nós ausentes](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes). 2. Confirme se a hora em todos os nós está precisa. Os nós que estão mais de 2 minutos à frente ou atrás não aparecerão no cluster Explorer. A seguinte consulta NRQL pode ser usada para verificar se este é o caso: diff --git a/src/nav/kubernetes-pixie.yml b/src/nav/kubernetes-pixie.yml index 35e17ae72e0..bf000eb54e6 100644 --- a/src/nav/kubernetes-pixie.yml +++ b/src/nav/kubernetes-pixie.yml @@ -53,12 +53,14 @@ pages: path: /docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/overview - title: Changes introduced in v3 path: /docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/changes-since-v3 - - title: Upgrade from v2 + - title: Upgrade from version 2 path: /docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/upgrade-v2 - - title: Errors for v2 + - title: Errors for version 2 path: /docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/errors - - title: "Troubleshooting v2: Missing nodes" - path: /docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting + - title: Troubleshooting version 2 + pages: + - title: Missing nodes for version 2 + path: /docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes - title: Explore your Kubernetes data pages: - title: Kubernetes cluster From a73699703ab7cace0230b86431ecb931d78d7f99 Mon Sep 17 00:00:00 2001 From: nbaenam Date: Wed, 28 Aug 2024 13:30:46 +0200 Subject: [PATCH 4/8] fix(K8s): Fixed errors in the i18n for renaming files --- .../{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} | 0 .../{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} | 0 .../{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} | 0 .../{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} | 0 4 files changed, 0 insertions(+), 0 deletions(-) rename src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} (100%) rename src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} (100%) rename src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} (100%) rename src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/{troubleshooting.mdx => troubleshooting/missing-nodes.mdx} (100%) diff --git a/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx b/src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx similarity index 100% rename from src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx rename to src/i18n/content/es/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx diff --git a/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx b/src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx similarity index 100% rename from src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx rename to src/i18n/content/jp/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx diff --git a/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx b/src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx similarity index 100% rename from src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx rename to src/i18n/content/kr/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx diff --git a/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx b/src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx similarity index 100% rename from src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting.mdx rename to src/i18n/content/pt/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/k8s-version2/troubleshooting/missing-nodes.mdx From 3e57466b0bad35c41bc0820173c9212d74463ca9 Mon Sep 17 00:00:00 2001 From: nbaenam Date: Fri, 30 Aug 2024 13:39:46 +0200 Subject: [PATCH 5/8] fix(K8s): Added SMEs comments --- .../common-error-messages/error-sending-events.mdx | 3 ++- .../troubleshooting/common-error-messages/pod-not-starting.mdx | 3 +-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx index e0133fd03c9..b62f5f998b1 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx @@ -23,4 +23,5 @@ The agent can't connect to the New Relic servers and you see an error like the f ## Solution -Depending on the exact nature of the error the message in the logs may differ. To address this problem, see the [New Relic networks documentation](/docs/new-relic-solutions/get-started/networks/#infrastructure). \ No newline at end of file +Depending on the exact nature of the error the message in the logs may differ. To address this problem, see the [New Relic networks documentation](/docs/new-relic-solutions/get-started/networks/#infrastructure) and the [Troubleshooting New Relic Infrastructure Agent Networking Issue](https://github.com/newrelic/infrastructure-agent/blob/master/docs/network_troubleshooting.md?) GitHub page. + diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx index 62be20ca1df..a114c34c32f 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx @@ -28,10 +28,9 @@ Check the following: * If the pod is in `ImagePullBackOff` status, please check your network connection to allow image pulling from the [right domains](/docs/new-relic-solutions/get-started/networks). - * If the pod is in `Pending` or `ContainerCreating` status, please run these commands to find out the possible reasons from the logs: + * If the pod is in `Pending` or `ContainerCreating` status, please run these commands to find out the possible reasons from the debug logs: ```bash kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic -c kubelet ``` - From 9b6e0ac120c104f88a20cd8f7bec8c6b4397f57d Mon Sep 17 00:00:00 2001 From: nbaenam Date: Fri, 30 Aug 2024 14:28:37 +0200 Subject: [PATCH 6/8] fix(K8s): Added SMEs comment --- .../troubleshooting/common-error-messages/pod-not-starting.mdx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx index a114c34c32f..15e54b652df 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/pod-not-starting.mdx @@ -28,7 +28,7 @@ Check the following: * If the pod is in `ImagePullBackOff` status, please check your network connection to allow image pulling from the [right domains](/docs/new-relic-solutions/get-started/networks). - * If the pod is in `Pending` or `ContainerCreating` status, please run these commands to find out the possible reasons from the debug logs: + * If the pod is in `Pending` or `ContainerCreating` status, please run these commands to find out the possible reasons from the [debug logs](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/#verbose-logging): ```bash kubectl logs newrelic-bundle-nrk8s-kubelet-n newrelic From 95ac0880fcfeb8e7c31e376bcaa9f01ed5f770ba Mon Sep 17 00:00:00 2001 From: nbaenam Date: Mon, 2 Sep 2024 12:03:36 +0200 Subject: [PATCH 7/8] feat(K8s): Added the troubleshooting overview doc --- .../troubleshooting/overview.mdx | 30 +++++++++++++++++++ src/nav/kubernetes-pixie.yml | 4 ++- 2 files changed, 33 insertions(+), 1 deletion(-) create mode 100644 src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/overview.mdx diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/overview.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/overview.mdx new file mode 100644 index 00000000000..616dd539056 --- /dev/null +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/overview.mdx @@ -0,0 +1,30 @@ +--- +title: Troubleshooting overview +type: troubleshooting +tags: + - Integrations + - Kubernetes integration + - Troubleshooting +metaDescription: Some troubleshooting tips with your Kubernetes integration. +freshnessValidatedDate: 2024-09-02 +--- + +It's possible that you may see error messages during the installation of your Kubernetes integration, or when you check your New Relic infrastructure logs after the integration is installed. + +These pages will help you with the possible errors you may have. + +* [Common error messages](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-messages) + +* [Helm configurations are not applied globally](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied/) + +* [Issues with Istio](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio/) + +* [Missing nodes](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes/) + +* [Not seeing control plane data](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-control-plane-data/) + +* [Not seeing data](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data/) + +* [Certificate signed by unknown authority](/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/certificate-signed-unknown-authority/) + + diff --git a/src/nav/kubernetes-pixie.yml b/src/nav/kubernetes-pixie.yml index bf000eb54e6..c18209e1fdc 100644 --- a/src/nav/kubernetes-pixie.yml +++ b/src/nav/kubernetes-pixie.yml @@ -79,6 +79,8 @@ pages: path: /docs/kubernetes-pixie/kubernetes-integration/installation/kubernetes-integration-recommended-alert-policy - title: Troubleshooting pages: + - title: Troubleshooting overview + path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/overview - title: Common error messages pages: - title: Error messages @@ -99,7 +101,7 @@ pages: path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/unable-connect-server - title: Helm configurations are not applied globally path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/helm-configurations-not-applied - - title: Istio and Kubernetes + - title: Issues with Istio path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/issues-with-istio - title: Missing nodes path: /docs/kubernetes-pixie/kubernetes-integration/troubleshooting/missing-nodes From 79080bd285225bc988a28516ab6ff062ec6034ef Mon Sep 17 00:00:00 2001 From: nbaenam Date: Mon, 9 Sep 2024 13:01:45 +0200 Subject: [PATCH 8/8] fix(K8s): Added SME comments from gts-all --- .../common-error-messages/error-sending-events.mdx | 5 ++--- .../common-error-messages/failed-discover-kube.mdx | 2 +- .../troubleshooting/not-seeing-data.mdx | 4 +--- 3 files changed, 4 insertions(+), 7 deletions(-) diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx index b62f5f998b1..93fdd084d14 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/error-sending-events.mdx @@ -16,12 +16,11 @@ The agent can't connect to the New Relic servers and you see an error like the f ```shell 2018-04-09T18:16:35.497195185Z time="2018-04-09T18:16:35Z" level=error msg="metric sender can't process 1 times" error="Error sending events: - Post https://staging-infra-api.newrelic.com/metrics/events/bulk: + Post https://api.newrelic.com/metrics/events/bulk: net/http: request canceled (Client.Timeout exceeded while awaiting headers)" ``` - ## Solution -Depending on the exact nature of the error the message in the logs may differ. To address this problem, see the [New Relic networks documentation](/docs/new-relic-solutions/get-started/networks/#infrastructure) and the [Troubleshooting New Relic Infrastructure Agent Networking Issue](https://github.com/newrelic/infrastructure-agent/blob/master/docs/network_troubleshooting.md?) GitHub page. +Depending on the exact nature of the error the message in the logs may differ. To address this problem, see the [New Relic networks documentation](/docs/new-relic-solutions/get-started/networks/#infrastructure) and the [Troubleshooting New Relic infrastructure agent networking issue](https://github.com/newrelic/infrastructure-agent/blob/master/docs/network_troubleshooting.md?) GitHub page. diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx index bf8d94304fa..e3ca88a4667 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/common-error-messages/failed-discover-kube.mdx @@ -11,7 +11,7 @@ freshnessValidatedDate: 2024-09-02 ## Problem -The Kubernetes integration requires `kube-state-metrics`. If this is missing, you'll see an error like the following in the `newrelic-infra` container logs: +The Kubernetes integration requires `kube-state-metrics`. If this is missing, you'll see an error like the following in the `nrk8s-ksm` container logs: ```shell time="2022-06-21T09:12:20Z" level=error msg="retrieving scraper data: retrieving ksm data: discovering KSM endpoints: timeout discovering endpoints" diff --git a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx index dacbe5a61c6..5b9417f3c7f 100644 --- a/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx +++ b/src/content/docs/kubernetes-pixie/kubernetes-integration/troubleshooting/not-seeing-data.mdx @@ -25,9 +25,7 @@ You have installed the [New Relic Kubernetes integration](/install/kubernetes/), 2. Confirm the successful deployment of the integration by running these commands: ```bash - kubectl get pods -o wide -n - kubectl get deployments -o wide -n - kubectl get daemonsets -o wide -n + kubectl get pods,deployments,daemonsets -o wide -n ``` 3. [Check the logs](/docs/kubernetes-pixie/kubernetes-integration/advanced-configuration/get-logs-version/) from the infrastructure agent and the integration and make sure that there are no error messages.