karmada-io
/
karmada
mirror of https://github.com/karmada-io/karmada.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #6073 from mszacillo/updated-interpreter 

Updating FlinkDeployment interpreter to display error status, improving health interpreter
This commit is contained in:
karmada-bot 2025-02-05 09:49:02 +08:00 committed by GitHub
parent f2259dc884 f14e0f920f
commit d80b7d4864
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 20 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

23
pkg/resourceinterpreter/default/thirdparty/resourcecustomizations/flink.apache.org/v1beta1/FlinkDeployment/customizations.yaml vendored
View File

@ -7,14 +7,27 @@ spec:
apiVersion: flink.apache.org/v1beta1
kind: FlinkDeployment
customizations:
# FlinkDeployment health is interpreted based on the application's state.
#
# Health Rules:
# 1. If the job is in a terminal state [Failed, Finished, Canceled, Suspended] or in the Running state, it is considered healthy.
# 2. If the job is in an ephemeral state [Reconciling, Initializing, Created]:
# - It is treated as healthy ONLY if there is a published error (e.g., user-related issues like an incorrect image path).
# - Otherwise, it is treated as unhealthy and may be rescheduled.
# 3. Short-lived states [Cancelling, Failing, Restarting] are treated as healthy because they will directly transition to their respective terminal states:
# - Cancelling -> Canceled / Suspended
# - Failing -> Failed
# - Restarting triggers a restart, bringing the job back to the Created state.
#
# For more information on the Flink state diagram, refer to the official documentation: https://nightlies.apache.org/flink/flink-docs-release-1.20/docs/internals/job_scheduling/
healthInterpretation:
luaScript: >
function InterpretHealth(observedObj)
if observedObj.status ~= nil and observedObj.status.jobStatus ~= nil then
if observedObj.status.jobStatus.state ~= 'CREATED' and observedObj.status.jobStatus.state ~= 'RECONCILING' then
if observedObj.status ~= nil and observedObj.status.jobStatus ~= nil and observedObj.status.jobStatus.state ~= nil then
if observedObj.status.jobStatus.state ~= 'CREATED' and observedObj.status.jobStatus.state ~= 'INITIALIZING' and observedObj.status.jobStatus.state ~= 'RECONCILING' then
return true
else
return observedObj.status.jobManagerDeploymentStatus == 'ERROR'
return observedObj.status.error ~= nil or observedObj.status.jobManagerDeploymentStatus == 'ERROR'
end
end
return false
@ -91,6 +104,7 @@ spec:
desiredObj.status = {}
end
clusterInfo = {}
error = ''
jobManagerDeploymentStatus = ''
jobStatus = {}
lifecycleState = ''
@ -102,6 +116,7 @@ spec:
currentStatus = statusItems[i].status
if currentStatus ~= nil then
clusterInfo = currentStatus.clusterInfo
error = currentStatus.error
jobManagerDeploymentStatus = currentStatus.jobManagerDeploymentStatus
jobStatus = currentStatus.jobStatus
observedGeneration = currentStatus.observedGeneration
@ -112,6 +127,7 @@ spec:
end
desiredObj.status.clusterInfo = clusterInfo
desiredObj.status.error = error
desiredObj.status.jobManagerDeploymentStatus = jobManagerDeploymentStatus
desiredObj.status.jobStatus = jobStatus
desiredObj.status.lifecycleState = lifecycleState
@ -128,6 +144,7 @@ spec:
return status
end
status.clusterInfo = observedObj.status.clusterInfo
status.error = observedObj.status.error
status.jobManagerDeploymentStatus = observedObj.status.jobManagerDeploymentStatus
status.jobStatus = observedObj.status.jobStatus
status.observedGeneration = observedObj.status.observedGeneration