5.0
2020-09-15T19:24:13Z
Templates
Kubernetes
Kubernetes
Templates
Kubernetes
Kubernetes ApiServices
Kubernetes Clusters
Kubernetes ComponentStatuses
Kubernetes Containers
Kubernetes Deployments
Kubernetes Nodes
Kubernetes Pods
ApiServices
k8s.discovery[apiservices]
50s
1h
ApiServices: {#NAME} Status Available
k8s.stats[apiservices,{#NAME},Available]
60s
0
TEXT
Kubernetes
Kubernetes ApiServices
{str(True)}=0
ApiServices {#NAME} is not in Available State
AVERAGE
YES
Clusters
k8s.discovery[clusters]
50s
DISABLED
1h
Cluster {#NAME} API Health Check
HTTP_AGENT
k8s.cluster.api.health[{#NAME},{#APIURL}]
60s
0
TEXT
Kubernetes
Kubernetes Clusters
5s
{#APIURL}/healthz
NO
{str(ok)}=0
API {#APIURL} for cluster {#NAME} is not OK
HIGH
ComponentStatuses
k8s.discovery[componentstatuses]
50s
1h
ComponentStatuses: {#NAME} Status Healthy
k8s.stats[componentstatuses,{#NAME},Healthy]
60s
0
TEXT
Kubernetes
Kubernetes ComponentStatuses
{str(True)}=0
ComponentStatuses {#NAME} is not in Healthy State
AVERAGE
YES
Containers
k8s.discovery[containers]
50s
0
Pod {#NAME} container {#CONTAINER} (ns {#NAMESPACE}) Status Ready
k8s.stats[pods,{#NAMESPACE},{#NAME},containerReady,{#CONTAINER}]
60s
0
TEXT
Kubernetes
Kubernetes Containers
{str(True,#3)}=0 and {nodata(100)}=0
Pod {#NAME} container {#CONTAINER} (ns {#NAMESPACE}) is not in Ready State
WARNING
YES
Pod {#NAME} container {#CONTAINER} (ns {#NAMESPACE}) Restart Count
k8s.stats[pods,{#NAMESPACE},{#NAME},containerRestarts,{#CONTAINER}]
60s
Kubernetes
Kubernetes Containers
{delta(600)}>10
Pod {#NAME} container {#CONTAINER} (ns {#NAMESPACE}) restart count > {$CONTAINER_RESTARTS}
WARNING
YES
Deployments
k8s.discovery[deployments]
50s
7d
Deployments: {#NAME} (ns {#NAMESPACE}) NOT UPDATED replicas
CALCULATED
k8s.stats[deployments,{#NAMESPACE},{#NAME},notUpdated]
60s
last("k8s.stats[deployments,{#NAMESPACE},{#NAME},Replicas]")-last("k8s.stats[deployments,{#NAMESPACE},{#NAME},updatedReplicas]")
Kubernetes
Kubernetes Deployments
{min(#3)}>0
Deployment name {#NAME} (ns {#NAMESPACE}) number of not updated replicas > 0
HIGH
YES
Deployments: {#NAME} (ns {#NAMESPACE}) Desired replicas
k8s.stats[deployments,{#NAMESPACE},{#NAME},Replicas]
60s
Kubernetes
Kubernetes Deployments
Deployments: {#NAME} (ns {#NAMESPACE}) Status
k8s.stats[deployments,{#NAMESPACE},{#NAME},statusReady]
60s
0
TEXT
Kubernetes
Kubernetes Deployments
{str(True,#3)}=0
Deployment {#NAME} (ns {#NAMESPACE}) is not in Available Status
HIGH
YES
Deployments: {#NAME} (ns {#NAMESPACE}) UPDATED replicas
k8s.stats[deployments,{#NAMESPACE},{#NAME},updatedReplicas]
60s
Kubernetes
Kubernetes Deployments
Nodes
k8s.discovery[nodes]
50s
Node: {#NAME} Status: DiskPressure
k8s.stats[nodes,{#NAME},DiskPressure]
60s
0
TEXT
Kubernetes
Kubernetes Nodes
{str(True)}=1
Node {#NAME} DiskPressure
HIGH
YES
Node: {#NAME} Status: MemoryPressure
k8s.stats[nodes,{#NAME},MemoryPressure]
60s
0
TEXT
Kubernetes
Kubernetes Nodes
{str(True)}=1
Node {#NAME} MemoryPressure
HIGH
YES
Node: {#NAME} Status: OutOfDisk
k8s.stats[nodes,{#NAME},OutOfDisk]
60s
0
TEXT
Kubernetes
Kubernetes Nodes
{str(True)}=1
Node {#NAME} OutOfDisk
HIGH
YES
Node: {#NAME} Status: PIDPressure
k8s.stats[nodes,{#NAME},PIDPressure]
60s
0
TEXT
Kubernetes
Kubernetes Nodes
{str(True)}=1
Node {#NAME} PIDPressure
HIGH
YES
Node: {#NAME} Status: Ready
k8s.stats[nodes,{#NAME},Ready]
60s
0
TEXT
Kubernetes
Kubernetes Nodes
{str(True)}=0
Node {#NAME} Ready
HIGH
YES
Pods
k8s.discovery[pods]
50s
0
Pod: {#NAME} (ns {#NAMESPACE}) Phase
k8s.stats[pods,{#NAMESPACE},{#NAME},statusPhase]
60s
0
TEXT
Kubernetes
Kubernetes Pods
{str(CrashLoopBackOff)}=1
Pod {#NAME} (ns {#NAMESPACE}) phase "CrashLoopBackOff"
HIGH
YES
{str(Failed)}=1
Pod {#NAME} (ns {#NAMESPACE}) phase "Failed"
HIGH
YES
{str(Unknown)}=1
Pod {#NAME} (ns {#NAMESPACE}) phase "Unknown"
HIGH
YES
Pod: {#NAME} (ns {#NAMESPACE}) Status Ready
k8s.stats[pods,{#NAMESPACE},{#NAME},statusReady]
60s
0
TEXT
Kubernetes
Kubernetes Pods
Pod: {#NAME} (ns {#NAMESPACE}) Status Failed, Reason Evicted
k8s.stats[pods,{#NAMESPACE},{#NAME},statusReason]
60s
0
TEXT
Kubernetes
Kubernetes Pods
{str(Evicted)}=1
Pod {#NAME} (ns {#NAMESPACE}) status Evicted
AVERAGE
YES
{$CONTAINER_RESTARTS}
10