Skip to content

fix: propogate health status for pipeline #2547

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
veds-g wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

fix: propogate health status for pipeline #2547

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f9f4645
propogate health status for pipeline
veds-g Apr 13, 2025
cf556b7
Merge branch 'main' into health-prop
veds-g Apr 16, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
43 changes: 42 additions & 1 deletion server/apis/v1/handler.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -269,7 +269,29 @@ func (h *handler) GetClusterSummary(c *gin.Context) {
if value, ok := namespaceSummaryMap[pipeline.Namespace]; ok {
summary = value
}
status, err := getPipelineStatus(&pipeline)

Copy link
Member

@whynowy whynowy Apr 14, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

How bad is the performance (e.g.with 20, 50 pipelines)?

// getting health status for each pipeline
resourceHealth, err := h.healthChecker.getPipelineResourceHealth(h, pipeline.Namespace, pipeline.Name)
if err != nil {
h.respondWithError(c, fmt.Sprintf("Failed to get the resourceHealth for pipeline %q: %s", pipeline.Name, err.Error()))
return
}

// Get a new daemon client for the given pipeline
client, err := h.getPipelineDaemonClient(pipeline.Namespace, pipeline.Name)
if err != nil || client == nil {
h.respondWithError(c, fmt.Sprintf("failed to get daemon service client for pipeline %q, %s", pipeline.Name, err.Error()))
return
}

// Get the data criticality for the given pipeline
dataStatus, err := client.GetPipelineStatus(c, pipeline.Name)
if err != nil {
h.respondWithError(c, fmt.Sprintf("Failed to get the dataStatus for pipeline %q: %s", pipeline.Name, err.Error()))
return
}

status, err := getPipelineConsolidatedHealthStatus(&pipeline, resourceHealth.Status, dataStatus.Status)
if err != nil {
h.respondWithError(c, fmt.Sprintf("Failed to fetch cluster summary, %s", err.Error()))
return
Expand Down Expand Up @@ -1486,6 +1508,25 @@ func getPipelineStatus(pipeline *dfv1.Pipeline) (string, error) {
return retStatus, nil
}

func getPipelineConsolidatedHealthStatus(pipeline *dfv1.Pipeline, resourceHealth, dataStatus string) (string, error) {
retStatus := dfv1.PipelineStatusHealthy

if pipeline.GetDesiredPhase() == dfv1.PipelinePhasePaused || pipeline.GetDesiredPhase() == dfv1.PipelinePhasePausing || pipeline.GetDesiredPhase() == dfv1.PipelinePhaseDeleting {
retStatus = dfv1.PipelineStatusInactive
} else if pipeline.GetDesiredPhase() == dfv1.PipelinePhaseRunning {
if resourceHealth == dfv1.PipelineStatusHealthy && dataStatus == dfv1.PipelineStatusHealthy {
retStatus = dfv1.PipelineStatusHealthy
} else if resourceHealth == dfv1.PipelineStatusUnhealthy || resourceHealth == dfv1.PipelineStatusCritical || dataStatus == dfv1.PipelineStatusCritical {
retStatus = dfv1.PipelineStatusCritical
} else if resourceHealth == dfv1.PipelineStatusWarning || dataStatus == dfv1.PipelineStatusWarning {
retStatus = dfv1.PipelineStatusWarning
}
} else if pipeline.GetDesiredPhase() == dfv1.PipelinePhaseFailed {
retStatus = dfv1.PipelineStatusCritical
}
return retStatus, nil
}

// GetIsbServiceStatus is used to provide the status of a given InterStepBufferService
// TODO: Figure out the correct way to determine if a ISBService is healthy
func getIsbServiceStatus(isbsvc *dfv1.InterStepBufferService) (string, error) {
Expand Down
Loading