public_git
/
postgres-operator
mirror of https://github.com/zalando/postgres-operator.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Init add liveness probe 

Signed-off-by: DavidSpek <vanderspek.david@gmail.com>
This commit is contained in:
DavidSpek 2023-05-16 11:17:06 +02:00 committed by David van der Spek
parent af084a5a65
commit db96273ab3
14 changed files with 594 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

133
charts/postgres-operator/crds/operatorconfigurations.yaml
View File

@ -260,6 +260,139 @@ spec:
type: array
items:
type: string
liveness_probe:
description: Probe describes a health check to be performed against
a container to determine whether it is alive or ready to receive
traffic.
properties:
exec:
description: One and only one of the following should be specified.
Exec specifies the action to take.
properties:
command:
description: Command is the command line to execute inside
the container, the working directory for the command is
root ('/') in the container's filesystem. The command
is simply exec'd, it is not run inside a shell, so traditional
shell instructions ('|', etc) won't work. To use a shell,
you need to explicitly call out to that shell. Exit
status of 0 is treated as live/healthy and non-zero
is unhealthy.
items:
type: string
type: array
type: object
failureThreshold:
description: Minimum consecutive failures for the probe to
be considered failed after having succeeded. Defaults to
3. Minimum value is 1.
format: int32
type: integer
httpGet:
description: HTTPGet specifies the http request to perform.
properties:
host:
description: Host name to connect to, defaults to the
pod IP. You probably want to set "Host" in httpHeaders
instead.
type: string
httpHeaders:
description: Custom headers to set in the request. HTTP
allows repeated headers.
items:
description: HTTPHeader describes a custom header to
be used in HTTP probes
properties:
name:
description: The header field name
type: string
value:
description: The header field value
type: string
required:
- name
- value
type: object
type: array
path:
description: Path to access on the HTTP server.
type: string
port:
anyOf:
- type: integer
- type: string
description: Name or number of the port to access on the
container. Number must be in the range 1 to 65535. Name
must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
scheme:
description: Scheme to use for connecting to the host.
Defaults to HTTP.
type: string
required:
- port
type: object
initialDelaySeconds:
description: 'Number of seconds after the container has started
before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
periodSeconds:
description: How often (in seconds) to perform the probe.
Default to 10 seconds. Minimum value is 1.
format: int32
type: integer
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
description: 'TCPSocket specifies an action involving a TCP
port. TCP hooks not yet supported TODO: implement a realistic
TCP lifecycle hook'
properties:
host:
description: 'Optional: Host name to connect to, defaults
to the pod IP.'
type: string
port:
anyOf:
- type: integer
- type: string
description: Number or name of the port to access on the
container. Number must be in the range 1 to 65535. Name
must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
required:
- port
type: object
terminationGracePeriodSeconds:
description: Optional duration in seconds the pod needs to
terminate gracefully upon probe failure. The grace period
is the duration in seconds after the processes running in
the pod are sent a termination signal and the time when
the processes are forcibly halted with a kill signal. Set
this value longer than the expected cleanup time for your
process. If this value is nil, the pod's terminationGracePeriodSeconds
will be used. Otherwise, this value overrides the value
provided by the pod spec. Value must be non-negative integer.
The value zero indicates stop immediately via the kill signal
(no opportunity to shut down). This is a beta field and
requires enabling ProbeTerminationGracePeriod feature gate.
Minimum value is 1. spec.terminationGracePeriodSeconds is
used if unset.
format: int64
type: integer
timeoutSeconds:
description: 'Number of seconds after which the probe times
out. Defaults to 1 second. Minimum value is 1. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
type: object
master_pod_move_timeout:
type: string
default: "20m"

134
charts/postgres-operator/crds/postgresqls.yaml
View File

@ -202,6 +202,140 @@ spec:
items:
type: object
x-kubernetes-preserve-unknown-fields: true
livenessProbe:
description: 'Periodic probe of container liveness. Container
will be restarted if the probe fails. Cannot be updated. More
info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
properties:
exec:
description: One and only one of the following should be
specified. Exec specifies the action to take.
properties:
command:
description: Command is the command line to execute
inside the container, the working directory for the
command is root ('/') in the container's filesystem.
The command is simply exec'd, it is not run inside
a shell, so traditional shell instructions ('|', etc)
won't work. To use a shell, you need to explicitly
call out to that shell. Exit status of 0 is treated
as live/healthy and non-zero is unhealthy.
items:
type: string
type: array
type: object
failureThreshold:
description: Minimum consecutive failures for the probe
to be considered failed after having succeeded. Defaults
to 3. Minimum value is 1.
format: int32
type: integer
httpGet:
description: HTTPGet specifies the http request to perform.
properties:
host:
description: Host name to connect to, defaults to the
pod IP. You probably want to set "Host" in httpHeaders
instead.
type: string
httpHeaders:
description: Custom headers to set in the request. HTTP
allows repeated headers.
items:
description: HTTPHeader describes a custom header
to be used in HTTP probes
properties:
name:
description: The header field name
type: string
value:
description: The header field value
type: string
required:
- name
- value
type: object
type: array
path:
description: Path to access on the HTTP server.
type: string
port:
anyOf:
- type: integer
- type: string
description: Name or number of the port to access on
the container. Number must be in the range 1 to 65535.
Name must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
scheme:
description: Scheme to use for connecting to the host.
Defaults to HTTP.
type: string
required:
- port
type: object
initialDelaySeconds:
description: 'Number of seconds after the container has
started before liveness probes are initiated. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
periodSeconds:
description: How often (in seconds) to perform the probe.
Default to 10 seconds. Minimum value is 1.
format: int32
type: integer
successThreshold:
description: Minimum consecutive successes for the probe
to be considered successful after having failed. Defaults
to 1. Must be 1 for liveness and startup. Minimum value
is 1.
format: int32
type: integer
tcpSocket:
description: 'TCPSocket specifies an action involving a
TCP port. TCP hooks not yet supported TODO: implement
a realistic TCP lifecycle hook'
properties:
host:
description: 'Optional: Host name to connect to, defaults
to the pod IP.'
type: string
port:
anyOf:
- type: integer
- type: string
description: Number or name of the port to access on
the container. Number must be in the range 1 to 65535.
Name must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
required:
- port
type: object
terminationGracePeriodSeconds:
description: Optional duration in seconds the pod needs
to terminate gracefully upon probe failure. The grace
period is the duration in seconds after the processes
running in the pod are sent a termination signal and the
time when the processes are forcibly halted with a kill
signal. Set this value longer than the expected cleanup
time for your process. If this value is nil, the pod's
terminationGracePeriodSeconds will be used. Otherwise,
this value overrides the value provided by the pod spec.
Value must be non-negative integer. The value zero indicates
stop immediately via the kill signal (no opportunity to
shut down). This is a beta field and requires enabling
ProbeTerminationGracePeriod feature gate. Minimum value
is 1. spec.terminationGracePeriodSeconds is used if unset.
format: int64
type: integer
timeoutSeconds:
description: 'Number of seconds after which the probe times
out. Defaults to 1 second. Minimum value is 1. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
type: object
init_containers:
type: array
description: deprecated

13
charts/postgres-operator/values.yaml
View File

@ -205,6 +205,19 @@ configKubernetes:
# whether the Spilo container should run with additional permissions other than parent.
# required by cron which needs setuid
spilo_allow_privilege_escalation: true
# liveness probe for the spilo pod
# liveness_probe:
# httpGet:
# scheme: HTTP
# path: /liveness
# port: 8008
# initialDelaySeconds: 10
# periodSeconds: 10
# timeoutSeconds: 5
# successThreshold: 1
# failureThreshold: 3
# storage resize strategy, available options are: ebs, pvc, off or mixed
storage_resize_mode: pvc
# pod toleration assigned to instances of every Postgres cluster

4
docs/reference/cluster_manifest.md
View File

@ -85,6 +85,10 @@ These parameters are grouped directly under the `spec` key in the manifest.
requires a custom Spilo image. Note the FSGroup of a Pod cannot be changed
without recreating a new Pod. Optional.
* **livenessProbe**
Allows for adding a liveness probe to the Spilo container to detect if it's
running properly.
* **enableMasterLoadBalancer**
boolean flag to override the operator defaults (set by the
`enable_master_load_balancer` parameter) to define whether to enable the load

4
docs/reference/operator_parameters.md
View File

@ -469,6 +469,10 @@ configuration they are grouped under the `kubernetes` key.
process. Required by cron which needs setuid. Without this parameter,
certification rotation & backups will not be done. The default is `true`.
* **liveness_probe**
Allows for adding a liveness probe to the Spilo container to detect if it's
running properly.
* **additional_pod_capabilities**
list of additional capabilities to be added to the postgres container's
SecurityContext (e.g. SYS_NICE etc.). Please, make sure first that the

10
manifests/configmap.yaml
View File

@ -152,6 +152,16 @@ data:
# spilo_runasgroup: 103
# spilo_fsgroup: 103
spilo_privileged: "false"
# liveness_probe: |-
# httpGet:
# scheme: HTTP
# path: /liveness
# port: 8008
# initialDelaySeconds: 10
# periodSeconds: 10
# timeoutSeconds: 5
# successThreshold: 1
# failureThreshold: 3
storage_resize_mode: "pvc"
super_username: postgres
# target_major_version: "15"

133
manifests/operatorconfiguration.crd.yaml
View File

@ -258,6 +258,139 @@ spec:
type: array
items:
type: string
liveness_probe:
description: Probe describes a health check to be performed against
a container to determine whether it is alive or ready to receive
traffic.
properties:
exec:
description: One and only one of the following should be specified.
Exec specifies the action to take.
properties:
command:
description: Command is the command line to execute inside
the container, the working directory for the command is
root ('/') in the container's filesystem. The command
is simply exec'd, it is not run inside a shell, so traditional
shell instructions ('|', etc) won't work. To use a shell,
you need to explicitly call out to that shell. Exit
status of 0 is treated as live/healthy and non-zero
is unhealthy.
items:
type: string
type: array
type: object
failureThreshold:
description: Minimum consecutive failures for the probe to
be considered failed after having succeeded. Defaults to
3. Minimum value is 1.
format: int32
type: integer
httpGet:
description: HTTPGet specifies the http request to perform.
properties:
host:
description: Host name to connect to, defaults to the
pod IP. You probably want to set "Host" in httpHeaders
instead.
type: string
httpHeaders:
description: Custom headers to set in the request. HTTP
allows repeated headers.
items:
description: HTTPHeader describes a custom header to
be used in HTTP probes
properties:
name:
description: The header field name
type: string
value:
description: The header field value
type: string
required:
- name
- value
type: object
type: array
path:
description: Path to access on the HTTP server.
type: string
port:
anyOf:
- type: integer
- type: string
description: Name or number of the port to access on the
container. Number must be in the range 1 to 65535. Name
must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
scheme:
description: Scheme to use for connecting to the host.
Defaults to HTTP.
type: string
required:
- port
type: object
initialDelaySeconds:
description: 'Number of seconds after the container has started
before liveness probes are initiated. More info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
periodSeconds:
description: How often (in seconds) to perform the probe.
Default to 10 seconds. Minimum value is 1.
format: int32
type: integer
successThreshold:
description: Minimum consecutive successes for the probe to
be considered successful after having failed. Defaults to
1. Must be 1 for liveness and startup. Minimum value is
1.
format: int32
type: integer
tcpSocket:
description: 'TCPSocket specifies an action involving a TCP
port. TCP hooks not yet supported TODO: implement a realistic
TCP lifecycle hook'
properties:
host:
description: 'Optional: Host name to connect to, defaults
to the pod IP.'
type: string
port:
anyOf:
- type: integer
- type: string
description: Number or name of the port to access on the
container. Number must be in the range 1 to 65535. Name
must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
required:
- port
type: object
terminationGracePeriodSeconds:
description: Optional duration in seconds the pod needs to
terminate gracefully upon probe failure. The grace period
is the duration in seconds after the processes running in
the pod are sent a termination signal and the time when
the processes are forcibly halted with a kill signal. Set
this value longer than the expected cleanup time for your
process. If this value is nil, the pod's terminationGracePeriodSeconds
will be used. Otherwise, this value overrides the value
provided by the pod spec. Value must be non-negative integer.
The value zero indicates stop immediately via the kill signal
(no opportunity to shut down). This is a beta field and
requires enabling ProbeTerminationGracePeriod feature gate.
Minimum value is 1. spec.terminationGracePeriodSeconds is
used if unset.
format: int64
type: integer
timeoutSeconds:
description: 'Number of seconds after which the probe times
out. Defaults to 1 second. Minimum value is 1. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
type: object
master_pod_move_timeout:
type: string
default: "20m"

10
manifests/postgresql-operator-default-configuration.yaml
View File

@ -78,6 +78,16 @@ configuration:
# inherited_labels:
# - application
# - environment
# liveness_probe:
# httpGet:
# scheme: HTTP
# path: /liveness
# port: 8008
# initialDelaySeconds: 10
# periodSeconds: 10
# timeoutSeconds: 5
# successThreshold: 1
# failureThreshold: 3
master_pod_move_timeout: 20m
# node_readiness_label:
# status: ready

134
manifests/postgresql.crd.yaml
View File

@ -200,6 +200,140 @@ spec:
items:
type: object
x-kubernetes-preserve-unknown-fields: true
livenessProbe:
description: 'Periodic probe of container liveness. Container
will be restarted if the probe fails. Cannot be updated. More
info: https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
properties:
exec:
description: One and only one of the following should be
specified. Exec specifies the action to take.
properties:
command:
description: Command is the command line to execute
inside the container, the working directory for the
command is root ('/') in the container's filesystem.
The command is simply exec'd, it is not run inside
a shell, so traditional shell instructions ('|', etc)
won't work. To use a shell, you need to explicitly
call out to that shell. Exit status of 0 is treated
as live/healthy and non-zero is unhealthy.
items:
type: string
type: array
type: object
failureThreshold:
description: Minimum consecutive failures for the probe
to be considered failed after having succeeded. Defaults
to 3. Minimum value is 1.
format: int32
type: integer
httpGet:
description: HTTPGet specifies the http request to perform.
properties:
host:
description: Host name to connect to, defaults to the
pod IP. You probably want to set "Host" in httpHeaders
instead.
type: string
httpHeaders:
description: Custom headers to set in the request. HTTP
allows repeated headers.
items:
description: HTTPHeader describes a custom header
to be used in HTTP probes
properties:
name:
description: The header field name
type: string
value:
description: The header field value
type: string
required:
- name
- value
type: object
type: array
path:
description: Path to access on the HTTP server.
type: string
port:
anyOf:
- type: integer
- type: string
description: Name or number of the port to access on
the container. Number must be in the range 1 to 65535.
Name must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
scheme:
description: Scheme to use for connecting to the host.
Defaults to HTTP.
type: string
required:
- port
type: object
initialDelaySeconds:
description: 'Number of seconds after the container has
started before liveness probes are initiated. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
periodSeconds:
description: How often (in seconds) to perform the probe.
Default to 10 seconds. Minimum value is 1.
format: int32
type: integer
successThreshold:
description: Minimum consecutive successes for the probe
to be considered successful after having failed. Defaults
to 1. Must be 1 for liveness and startup. Minimum value
is 1.
format: int32
type: integer
tcpSocket:
description: 'TCPSocket specifies an action involving a
TCP port. TCP hooks not yet supported TODO: implement
a realistic TCP lifecycle hook'
properties:
host:
description: 'Optional: Host name to connect to, defaults
to the pod IP.'
type: string
port:
anyOf:
- type: integer
- type: string
description: Number or name of the port to access on
the container. Number must be in the range 1 to 65535.
Name must be an IANA_SVC_NAME.
x-kubernetes-int-or-string: true
required:
- port
type: object
terminationGracePeriodSeconds:
description: Optional duration in seconds the pod needs
to terminate gracefully upon probe failure. The grace
period is the duration in seconds after the processes
running in the pod are sent a termination signal and the
time when the processes are forcibly halted with a kill
signal. Set this value longer than the expected cleanup
time for your process. If this value is nil, the pod's
terminationGracePeriodSeconds will be used. Otherwise,
this value overrides the value provided by the pod spec.
Value must be non-negative integer. The value zero indicates
stop immediately via the kill signal (no opportunity to
shut down). This is a beta field and requires enabling
ProbeTerminationGracePeriod feature gate. Minimum value
is 1. spec.terminationGracePeriodSeconds is used if unset.
format: int64
type: integer
timeoutSeconds:
description: 'Number of seconds after which the probe times
out. Defaults to 1 second. Minimum value is 1. More info:
https://kubernetes.io/docs/concepts/workloads/pods/pod-lifecycle#container-probes'
format: int32
type: integer
type: object
init_containers:
type: array
description: deprecated

1
pkg/apis/acid.zalan.do/v1/operator_configuration_type.go
View File

@ -102,6 +102,7 @@ type KubernetesMetaConfiguration struct {
PodManagementPolicy string `json:"pod_management_policy,omitempty"`
EnableReadinessProbe bool `json:"enable_readiness_probe,omitempty"`
EnableCrossNamespaceSecret bool `json:"enable_cross_namespace_secret,omitempty"`
LivenessProbe *v1.Probe `json:"liveness_probe,omitempty"`
}
// PostgresPodResourcesDefaults defines the spec of default resources

1
pkg/apis/acid.zalan.do/v1/postgresql_type.go
View File

@ -87,6 +87,7 @@ type PostgresSpec struct {
AdditionalVolumes []AdditionalVolume `json:"additionalVolumes,omitempty"`
Streams []Stream `json:"streams,omitempty"`
Env []v1.EnvVar `json:"env,omitempty"`
LivenessProbe *v1.Probe `json:"livenessProbe,omitempty"`
// deprecated json tags
InitContainersOld []v1.Container `json:"init_containers,omitempty"`

15
pkg/cluster/k8sres.go
View File

@ -1207,6 +1207,19 @@ func generateSpiloReadinessProbe() *v1.Probe {
}
}
func generateSpiloLivenessProbe(probe, defaultProbe *v1.Probe) *v1.Probe {
if probe != nil {
return probe
}
if defaultProbe != nil {
return defaultProbe
}
return nil
}
func (c *Cluster) generateStatefulSet(spec *acidv1.PostgresSpec) (*appsv1.StatefulSet, error) {
var (
@ -1326,6 +1339,8 @@ func (c *Cluster) generateStatefulSet(spec *acidv1.PostgresSpec) (*appsv1.Statef
spiloContainer.ReadinessProbe = generateSpiloReadinessProbe()
}
spiloContainer.LivenessProbe = generateSpiloLivenessProbe(spec.LivenessProbe, c.OpConfig.LivenessProbe)
// generate container specs for sidecars specified in the cluster manifest
clusterSpecificSidecars := []v1.Container{}
if spec.Sidecars != nil && len(spec.Sidecars) > 0 {

1
pkg/controller/operator_config.go
View File

@ -125,6 +125,7 @@ func (c *Controller) importConfigurationFromCRD(fromCRD *acidv1.OperatorConfigur
result.PodAntiAffinityTopologyKey = util.Coalesce(fromCRD.Kubernetes.PodAntiAffinityTopologyKey, "kubernetes.io/hostname")
result.PodAntiAffinityPreferredDuringScheduling = fromCRD.Kubernetes.PodAntiAffinityPreferredDuringScheduling
result.PodToleration = fromCRD.Kubernetes.PodToleration
result.LivenessProbe = fromCRD.Kubernetes.LivenessProbe
// Postgres Pod resources
result.DefaultCPURequest = util.Coalesce(fromCRD.PostgresPodResources.DefaultCPURequest, "100m")

1
pkg/util/config/config.go
View File

@ -245,6 +245,7 @@ type Config struct {
TargetMajorVersion string `name:"target_major_version" default:"15"`
PatroniAPICheckInterval time.Duration `name:"patroni_api_check_interval" default:"1s"`
PatroniAPICheckTimeout time.Duration `name:"patroni_api_check_timeout" default:"5s"`
LivenessProbe *v1.Probe `json:"liveness_probe,omitempty"`
EnablePatroniFailsafeMode *bool `name:"enable_patroni_failsafe_mode" default:"false"`
}