mirror of
https://github.com/replicatedhq/troubleshoot.git
synced 2026-02-14 18:29:53 +00:00
e3adc1cb35
* stashing changes * split filesystem collector into fio and legacy functions * read fio results into analyzer * remove test script * update go.mod * remove old notes * go mod tidy * fix up go.mod * fix up go.mod * refactor tests for fio * make schemas * remove local scripts * local watch script for building troubleshoot * document watch script * fix var names * handle errors if run as non-root * go mod tidy * use String interface * collector happy path test * invalid filesize * invalid filesize * tests * remove old code * remove old init function * let actions tests run this * clean up tests * go mod tidy * remove duplicated type declaration * remove old file create code
553 lines
25 KiB
YAML
553 lines
25 KiB
YAML
# https://kurl.sh/docs/install-with-kurl/system-requirements
|
|
apiVersion: troubleshoot.sh/v1beta2
|
|
kind: HostPreflight
|
|
metadata:
|
|
name: kurl-builtin
|
|
spec:
|
|
collectors:
|
|
- time: {}
|
|
- cpu: {}
|
|
- memory: {}
|
|
- hostServices: {}
|
|
- hostOS: {}
|
|
- diskUsage:
|
|
collectorName: "Ephemeral Disk Usage /var/lib/kubelet"
|
|
path: /var/lib/kubelet
|
|
- diskUsage:
|
|
collectorName: "Ephemeral Disk Usage /var/lib/docker"
|
|
path: /var/lib/docker
|
|
exclude: '{{kurl not .Installer.Spec.Docker.Version}}'
|
|
- diskUsage:
|
|
collectorName: "Ephemeral Disk Usage /var/lib/containerd"
|
|
path: /var/lib/containerd
|
|
exclude: '{{kurl not .Installer.Spec.Containerd.Version}}'
|
|
- diskUsage:
|
|
collectorName: "Ephemeral Disk Usage /var/lib/rook"
|
|
path: /var/lib/rook
|
|
exclude: '{{kurl not .Installer.Spec.Rook.Version}}'
|
|
- diskUsage:
|
|
collectorName: "Ephemeral Disk Usage /var/openebs"
|
|
path: /var/openebs
|
|
exclude: '{{kurl not .Installer.Spec.OpenEBS.Version}}'
|
|
- tcpLoadBalancer:
|
|
collectorName: "Kubernetes API Server Load Balancer"
|
|
port: 6443
|
|
address: {{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }}
|
|
timeout: 3m
|
|
# ha and is first master (primary and not join) and not is upgrade
|
|
exclude: '{{kurl and .Installer.Spec.Kubernetes.Version .Installer.Spec.Kubernetes.LoadBalancerAddress .IsPrimary (not .IsJoin) (not .IsUpgrade) | not }}'
|
|
- http:
|
|
collectorName: "Kubernetes API Server Load Balancer Upgrade"
|
|
get:
|
|
url: https://{{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress | trimSuffix "/" }}/healthz
|
|
insecureSkipVerify: true
|
|
# ha and is first master (primary and not join) and is upgrade (the load balancer backend should already be available)
|
|
exclude: '{{kurl and .Installer.Spec.Kubernetes.Version .Installer.Spec.Kubernetes.LoadBalancerAddress .IsPrimary .IsUpgrade (not .IsJoin) | not }}'
|
|
- tcpPortStatus:
|
|
collectorName: "Kubernetes API TCP Port Status"
|
|
port: 6443
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
- tcpPortStatus:
|
|
collectorName: "ETCD Client API TCP Port Status"
|
|
port: 2379
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
- tcpPortStatus:
|
|
collectorName: "ETCD Server API TCP Port Status"
|
|
port: 2380
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
- tcpPortStatus:
|
|
collectorName: "ETCD Health Server TCP Port Status"
|
|
port: 2381
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
interface: lo
|
|
- tcpPortStatus:
|
|
collectorName: "Kubelet Health Server TCP Port Status"
|
|
port: 10248
|
|
exclude: '{{kurl and (not .IsUpgrade) | not }}'
|
|
interface: lo
|
|
- tcpPortStatus:
|
|
collectorName: "Kubelet API TCP Port Status"
|
|
port: 10250
|
|
exclude: '{{kurl and (not .IsUpgrade) | not }}'
|
|
- tcpPortStatus:
|
|
collectorName: "Kube Controller Manager Health Server TCP Port Status"
|
|
port: 10257
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
interface: lo
|
|
- tcpPortStatus:
|
|
collectorName: "Kube Scheduler Health Server TCP Port Status"
|
|
port: 10259
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
interface: lo
|
|
- tcpConnect:
|
|
collectorName: "Kubernetes API TCP Connection Status"
|
|
address: '{{kurl .Installer.Spec.Kubernetes.MasterAddress }}'
|
|
# run the collector if 1. there is a master address set AND this is a node joining the cluster AND this is not an EKCO internalLB install
|
|
exclude: '{{kurl and .Installer.Spec.Kubernetes.Version .Installer.Spec.Kubernetes.MasterAddress .IsJoin (and .Installer.Spec.Ekco.Version .Installer.Spec.Ekco.EnableInternalLoadBalancer | not) | not }}'
|
|
- filesystemPerformance:
|
|
collectorName: Filesystem Latency Two Minute Benchmark
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
timeout: 2m
|
|
directory: /var/lib/etcd
|
|
fileSize: 22Mi
|
|
operationSizeBytes: 2300
|
|
datasync: true
|
|
enableBackgroundIOPS: true
|
|
backgroundIOPSWarmupSeconds: 10
|
|
backgroundWriteIOPS: 300
|
|
backgroundWriteIOPSJobs: 6
|
|
backgroundReadIOPS: 50
|
|
backgroundReadIOPSJobs: 1
|
|
- certificate:
|
|
collectorName: "Kubernetes API key pair certificate"
|
|
exclude: '{{kurl or (not .IsPrimary) (not .IsUpgrade) }}'
|
|
certificatePath: /etc/kubernetes/pki/apiserver.crt
|
|
keyPath: /etc/kubernetes/pki/apiserver.key
|
|
- certificate:
|
|
collectorName: "Kubernetes ETCD key pair certificate"
|
|
exclude: '{{kurl or (not .IsPrimary) (not .IsUpgrade) }}'
|
|
certificatePath: /etc/kubernetes/pki/etcd/server.crt
|
|
keyPath: /etc/kubernetes/pki/etcd/server.key
|
|
- http:
|
|
collectorName: "Kubernetes API Health"
|
|
exclude: '{{kurl or (not .IsPrimary) (not .IsUpgrade) }}'
|
|
get:
|
|
url: https://localhost:6443/healthz
|
|
insecureSkipVerify: true
|
|
analyzers:
|
|
- certificate:
|
|
collectorName: "Kubernetes API key pair certificate"
|
|
exclude: '{{kurl or (not .IsPrimary) (not .IsUpgrade) }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "key-pair-missing"
|
|
message: Kubernetes API key pair certificate not found in /etc/kubernetes/pki/apiserver.*
|
|
- fail:
|
|
when: "key-pair-switched"
|
|
message: Kubernetes API key pair certificate and key pair are switched
|
|
- fail:
|
|
when: "key-pair-encrypted"
|
|
message: Kubernetes API key pair certificate private key is encrypted
|
|
- fail:
|
|
when: "key-pair-mismatch"
|
|
message: Kubernetes API key pair certificate and key do not match
|
|
- fail:
|
|
when: "key-pair-invalid"
|
|
message: Kubernetes API key pair certificate is invalid
|
|
- pass:
|
|
when: "key-pair-valid"
|
|
message: Kubernetes API key pair certificate is valid
|
|
- certificate:
|
|
collectorName: "Kubernetes ETCD key pair certificate"
|
|
exclude: '{{kurl or (not .IsPrimary) (not .IsUpgrade) }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "key-pair-missing"
|
|
message: Kubernetes ETCD key pair certificate not found in /etc/kubernetes/pki/etcd/server.*
|
|
- fail:
|
|
when: "key-pair-switched"
|
|
message: Kubernetes ETCD certificate and key pair are switched
|
|
- fail:
|
|
when: "key-pair-encrypted"
|
|
message: Kubernetes ETCD certificate private key is encrypted
|
|
- fail:
|
|
when: "key-pair-mismatch"
|
|
message: Kubernetes ETCD certificate and key do not match
|
|
- fail:
|
|
when: "key-pair-invalid"
|
|
message: Kubernetes ETCD key pair certificate is invalid
|
|
- pass:
|
|
when: "key-pair-valid"
|
|
message: Kubernetes ETCD key pair certificate is valid
|
|
- http:
|
|
checkName: "Kubernetes API Health"
|
|
exclude: '{{kurl or (not .IsPrimary) (not .IsUpgrade) }}'
|
|
collectorName: "Kubernetes API Health"
|
|
outcomes:
|
|
- warn:
|
|
when: "error"
|
|
message: Error connecting to Kubernetes API at https://localhost:6443/healthz
|
|
- pass:
|
|
when: "statusCode == 200"
|
|
message: OK HTTP status response from Kubernetes API at https://localhost:6443/healthz
|
|
- warn:
|
|
message: Unexpected status code response from Kubernetes API at https://localhost:6443/healthz
|
|
- cpu:
|
|
checkName: "Number of CPUs"
|
|
outcomes:
|
|
- fail:
|
|
when: "count < 2"
|
|
message: At least 2 CPU cores are required, and 4 CPU cores are recommended
|
|
- warn:
|
|
when: "count < 4"
|
|
message: At least 4 CPU cores are recommended
|
|
- pass:
|
|
message: This server has at least 4 CPU cores
|
|
- memory:
|
|
checkName: "Amount of Memory"
|
|
outcomes:
|
|
- fail:
|
|
when: "< 4G"
|
|
message: At least 4G of memory is required, and 8G of memory is recommended
|
|
- warn:
|
|
when: "< 8G"
|
|
message: At least 8G of memory is recommended
|
|
- pass:
|
|
message: The system has at least 8G of memory
|
|
- diskUsage:
|
|
checkName: "Ephemeral Disk Usage /var/lib/kubelet"
|
|
collectorName: "Ephemeral Disk Usage /var/lib/kubelet"
|
|
outcomes:
|
|
- fail:
|
|
when: "total < 30Gi"
|
|
message: The disk containing directory /var/lib/kubelet has less than 30Gi of total space
|
|
- fail:
|
|
when: "used/total > 80%"
|
|
message: The disk containing directory /var/lib/kubelet is more than 80% full
|
|
- warn:
|
|
when: "used/total > 60%"
|
|
message: The disk containing directory /var/lib/kubelet is more than 60% full
|
|
- warn:
|
|
when: "available < 10Gi"
|
|
message: The disk containing directory /var/lib/kubelet has less than 10Gi of disk space available
|
|
- pass:
|
|
message: The disk containing directory /var/lib/kubelet has at least 30Gi of total space, has at least 10Gi of disk space available, and is less than 60% full
|
|
- diskUsage:
|
|
checkName: "Ephemeral Disk Usage /var/lib/docker"
|
|
collectorName: "Ephemeral Disk Usage /var/lib/docker"
|
|
exclude: '{{kurl not .Installer.Spec.Docker.Version}}'
|
|
outcomes:
|
|
- fail:
|
|
when: "total < 30Gi"
|
|
message: The disk containing directory /var/lib/docker has less than 30Gi of total space
|
|
- fail:
|
|
when: "used/total > 80%"
|
|
message: The disk containing directory /var/lib/docker is more than 80% full
|
|
- warn:
|
|
when: "used/total > 60%"
|
|
message: The disk containing directory /var/lib/docker is more than 60% full
|
|
- warn:
|
|
when: "available < 10Gi"
|
|
message: The disk containing directory /var/lib/docker has less than 10Gi of disk space available
|
|
- pass:
|
|
message: The disk containing directory /var/lib/docker has at least 30Gi of total space, has at least 10Gi of disk space available, and is less than 60% full.
|
|
- diskUsage:
|
|
checkName: "Ephemeral Disk Usage /var/lib/containerd"
|
|
collectorName: "Ephemeral Disk Usage /var/lib/containerd"
|
|
exclude: '{{kurl not .Installer.Spec.Containerd.Version}}'
|
|
outcomes:
|
|
- fail:
|
|
when: "total < 30Gi"
|
|
message: The disk containing directory /var/lib/containerd has less than 30Gi of total space
|
|
- fail:
|
|
when: "used/total > 80%"
|
|
message: The disk containing directory /var/lib/containerd is more than 80% full
|
|
- warn:
|
|
when: "used/total > 60%"
|
|
message: The disk containing directory /var/lib/containerd is more than 60% full
|
|
- warn:
|
|
when: "available < 10Gi"
|
|
message: The disk containing directory /var/lib/containerd has less than 10Gi of disk space available
|
|
- pass:
|
|
message: The disk containing directory /var/lib/containerd has at least 30Gi of total space, has at least 10Gi of disk space available, and is less than 60% full.
|
|
- diskUsage:
|
|
checkName: "Ephemeral Disk Usage /var/lib/rook"
|
|
collectorName: "Ephemeral Disk Usage /var/lib/rook"
|
|
exclude: '{{kurl not .Installer.Spec.Rook.Version}}'
|
|
outcomes:
|
|
- fail:
|
|
when: "used/total > 80%"
|
|
message: The disk containing directory /var/lib/rook is more than 80% full
|
|
- fail:
|
|
when: "available < 10Gi"
|
|
message: The disk containing directory /var/lib/rook has less than 10Gi of disk space available
|
|
- pass:
|
|
message: The disk containing directory /var/lib/rook has sufficient space
|
|
- diskUsage:
|
|
checkName: "Ephemeral Disk Usage /var/openebs"
|
|
collectorName: "Ephemeral Disk Usage /var/openebs"
|
|
exclude: '{{kurl not .Installer.Spec.OpenEBS.Version}}'
|
|
outcomes:
|
|
- warn:
|
|
when: "used/total > 80%"
|
|
message: The disk containing directory /var/openebs is more than 80% full
|
|
- warn:
|
|
when: "available < 10Gi"
|
|
message: The disk containing directory /var/openebs has less than 10Gi of disk space available
|
|
- pass:
|
|
message: The disk containing directory /var/openebs has sufficient space
|
|
- tcpLoadBalancer:
|
|
checkName: "Kubernetes API Server Load Balancer"
|
|
collectorName: "Kubernetes API Server Load Balancer"
|
|
# ha and is first master (primary and not join) and not is upgrade
|
|
exclude: '{{kurl and .Installer.Spec.Kubernetes.Version .Installer.Spec.Kubernetes.LoadBalancerAddress .IsPrimary (not .IsJoin) (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "invalid-address"
|
|
message: The load balancer address {{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }} is not valid.
|
|
- warn:
|
|
when: "connection-refused"
|
|
message: Connection to {{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }} via load balancer was refused.
|
|
- warn:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to {{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }} via load balancer. Check your firewall.
|
|
- warn:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Port 6443 is unavailable
|
|
- pass:
|
|
when: "connected"
|
|
message: Successfully connected to {{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }} via load balancer
|
|
- warn:
|
|
message: Unexpected port status
|
|
- http:
|
|
checkName: "Kubernetes API Server Load Balancer Upgrade"
|
|
collectorName: "Kubernetes API Server Load Balancer Upgrade"
|
|
exclude: '{{kurl and .Installer.Spec.Kubernetes.Version .Installer.Spec.Kubernetes.LoadBalancerAddress .IsPrimary .IsUpgrade (not .IsJoin) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "error"
|
|
message: Error connecting to load balancer at https://{{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }}/healthz
|
|
- pass:
|
|
when: "statusCode == 200"
|
|
message: OK HTTP status response from load balancer at https://{{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }}/healthz
|
|
- fail:
|
|
message: Unexpected status code response from load balancer at https://{{kurl .Installer.Spec.Kubernetes.LoadBalancerAddress }}/healthz
|
|
- tcpPortStatus:
|
|
checkName: "Kubernetes API TCP Port Status"
|
|
collectorName: "Kubernetes API TCP Port Status"
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 6443 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 6443.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 6443. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 6443 is open
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpPortStatus:
|
|
checkName: "ETCD Client API TCP Port Status"
|
|
collectorName: "ETCD Client API TCP Port Status"
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 2379 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 2379.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 2379. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 2379 is open
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpPortStatus:
|
|
checkName: "ETCD Server API TCP Port Status"
|
|
collectorName: "ETCD Server API TCP Port Status"
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 2380 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 2380.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 2380. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 2380 is open
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpPortStatus:
|
|
checkName: "ETCD Health Server TCP Port Status"
|
|
collectorName: "ETCD Health Server TCP Port Status"
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 2381 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 2381.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 2381. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 2381 is available
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpPortStatus:
|
|
checkName: "Kubelet Health Server TCP Port Status"
|
|
collectorName: "Kubelet Health Server TCP Port Status"
|
|
exclude: '{{kurl and (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 10248 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 10248.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 10248. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 10248 is available
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpPortStatus:
|
|
checkName: "Kubelet API TCP Port Status"
|
|
collectorName: "Kubelet API TCP Port Status"
|
|
exclude: '{{kurl and (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 10250 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 10250.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 10250. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 10250 is open
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpPortStatus:
|
|
checkName: "Kube Controller Manager Health Server TCP Port Status"
|
|
collectorName: "Kube Controller Manager Health Server TCP Port Status"
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 10257 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 10257.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 10257. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 10257 is available
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpPortStatus:
|
|
checkName: "Kube Scheduler Health Server TCP Port Status"
|
|
collectorName: "Kube Scheduler Health Server TCP Port Status"
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to port 10259 was refused. This is likely to be a routing problem since this preflight configures a test server to listen on this port.
|
|
- warn:
|
|
when: "address-in-use"
|
|
message: Another process was already listening on port 10259.
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to port 10259. Check your firewall.
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected port status
|
|
- pass:
|
|
when: "connected"
|
|
message: Port 10259 is available
|
|
- warn:
|
|
message: Unexpected port status
|
|
- tcpConnect:
|
|
checkName: "Kubernetes API TCP Connection Status"
|
|
collectorName: "Kubernetes API TCP Connection Status"
|
|
# run the analyzer if 1. there is a master address set AND this is a node joining the cluster AND this is not an EKCO internalLB install
|
|
exclude: '{{kurl and .Installer.Spec.Kubernetes.Version .Installer.Spec.Kubernetes.MasterAddress .IsJoin (and .Installer.Spec.Ekco.Version .Installer.Spec.Ekco.EnableInternalLoadBalancer | not) | not }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "connection-refused"
|
|
message: Connection to the Kubernetes API at address {{kurl .Installer.Spec.Kubernetes.MasterAddress }} was refused
|
|
- fail:
|
|
when: "connection-timeout"
|
|
message: Timed out connecting to the Kubernetes API at address {{kurl .Installer.Spec.Kubernetes.MasterAddress }}
|
|
- fail:
|
|
when: "error"
|
|
message: Unexpected error connecting to the Kubernetes API at address {{kurl .Installer.Spec.Kubernetes.MasterAddress }}
|
|
- pass:
|
|
when: "connected"
|
|
message: Successfully connected to the Kubernetes API at address {{kurl .Installer.Spec.Kubernetes.MasterAddress }}
|
|
- filesystemPerformance:
|
|
collectorName: Filesystem Latency Two Minute Benchmark
|
|
exclude: '{{kurl and .IsPrimary (not .IsUpgrade) | not }}'
|
|
outcomes:
|
|
- pass:
|
|
when: "p99 < 10ms"
|
|
message: "Write latency is ok (p99 target < 10ms, actual: {{ .P99 }})"
|
|
- warn:
|
|
message: "Write latency is high. p99 target < 10ms, actual:{{ .String }}"
|
|
- time:
|
|
checkName: "NTP Status"
|
|
outcomes:
|
|
- fail:
|
|
when: "ntp == unsynchronized+inactive"
|
|
message: "System clock is not synchronized"
|
|
- warn:
|
|
when: "ntp == unsynchronized+active"
|
|
message: System clock not yet synchronized
|
|
- pass:
|
|
when: "ntp == synchronized+active"
|
|
message: "System clock is synchronized"
|
|
- warn:
|
|
when: "timezone != UTC"
|
|
message: "Non UTC timezone can interfere with system function"
|
|
- pass:
|
|
when: "timezone == UTC"
|
|
message: "Timezone is set to UTC"
|
|
- hostOS:
|
|
checkName: "Docker Support"
|
|
exclude: '{{kurl or (not .Installer.Spec.Docker.Version) (semverCompare ">= 20.10.17" .Installer.Spec.Docker.Version) }}'
|
|
outcomes:
|
|
- fail:
|
|
when: "ubuntu = 22.04"
|
|
message: "Docker versions < 20.10.17 not supported on ubuntu 22.04"
|
|
# hijack hostOS analyzer in order to analyze the kURL Installer spec
|
|
- hostOS:
|
|
checkName: "Containerd and Weave Compatibility"
|
|
exclude: '{{kurl or (not .Installer.Spec.Weave.Version) (not .Installer.Spec.Containerd.Version) (semverCompare "1.6.0 - 1.6.4" .Installer.Spec.Containerd.Version | not) }}'
|
|
outcomes:
|
|
- fail:
|
|
message: "Weave is not compatible with containerd versions 1.6.0 - 1.6.4"
|