Implement selective checkpoint recomputation

This commit is contained in:
2026-07-21 21:59:48 +00:00
parent 22d4f29670
commit c437682407
17 changed files with 902 additions and 180 deletions

View File

@@ -71,93 +71,137 @@ func (r *FilesystemRecorder) SourceFailed(moduleKey string, err error) error {
}
func (r *FilesystemRecorder) ExtractRunning(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := r.laneManifest(StageExtract, StatusRunning, laneID, moduleKey, dependencies)
return r.ExtractRunningForStep("", laneID, moduleKey, dependencies)
}
func (r *FilesystemRecorder) ExtractRunningForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := r.laneManifest(StageExtract, StatusRunning, stepID, laneID, moduleKey, dependencies)
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("extract", laneID), ExtractLaneManifest{StageManifest: manifest})
return r.writeManifest(laneManifestPath("extract", stepID, laneID), ExtractLaneManifest{StageManifest: manifest})
}
func (r *FilesystemRecorder) ExtractSucceeded(laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint, outputs []pipeline.CheckpointArtifact, rejected []contracts.RejectedOutput, warnings []contracts.Warning) error {
return r.ExtractSucceededForStep("", laneID, moduleKey, dependencies, outputs, rejected, warnings)
}
func (r *FilesystemRecorder) ExtractSucceededForStep(stepID, laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint, outputs []pipeline.CheckpointArtifact, rejected []contracts.RejectedOutput, warnings []contracts.Warning) error {
payload := artifactExtractEnvelope{Outputs: artifactCheckpointEnvelopes(outputs), Rejected: cloneRejectedOutputs(rejected), Warnings: cloneWarnings(warnings)}
if err := r.writePayload(lanePayloadPath("extract", laneID, "outputs.json"), payload); err != nil {
if err := r.writePayload(lanePayloadPath("extract", stepID, laneID, "outputs.json"), payload); err != nil {
return err
}
manifest := r.laneManifest(StageExtract, statusForRejected(rejected), laneID, moduleKey, dependencies)
manifest := r.laneManifest(StageExtract, statusForRejected(rejected), stepID, laneID, moduleKey, dependencies)
manifest.OutputDigests = checkpointFingerprints(artifactOutputDigests(outputs))
manifest.ValidationStatus = validationStatusString(warnings, rejected)
manifest.Rejections = rejectionSummaries(rejected)
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("extract", laneID), ExtractLaneManifest{StageManifest: manifest, ChunkCount: len(outputs) + len(rejected), OutputCount: len(outputs)})
return r.writeManifest(laneManifestPath("extract", stepID, laneID), ExtractLaneManifest{StageManifest: manifest, ChunkCount: len(outputs) + len(rejected), OutputCount: len(outputs)})
}
func (r *FilesystemRecorder) ExtractFailed(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := r.laneManifest(StageExtract, StatusFailed, laneID, moduleKey, dependencies)
return r.ExtractFailedForStep("", laneID, moduleKey, dependencies, err)
}
func (r *FilesystemRecorder) ExtractFailedForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := r.laneManifest(StageExtract, StatusFailed, stepID, laneID, moduleKey, dependencies)
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest(laneManifestPath("extract", laneID), ExtractLaneManifest{StageManifest: manifest})
return r.writeManifest(laneManifestPath("extract", stepID, laneID), ExtractLaneManifest{StageManifest: manifest})
}
func (r *FilesystemRecorder) MergeRunning(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := r.laneManifest(StageMerge, StatusRunning, laneID, moduleKey, dependencies)
return r.MergeRunningForStep("", laneID, moduleKey, dependencies)
}
func (r *FilesystemRecorder) MergeRunningForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := r.laneManifest(StageMerge, StatusRunning, stepID, laneID, moduleKey, dependencies)
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("merge", laneID), MergeLaneManifest{StageManifest: manifest})
return r.writeManifest(laneManifestPath("merge", stepID, laneID), MergeLaneManifest{StageManifest: manifest})
}
func (r *FilesystemRecorder) MergeSucceeded(laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint, output pipeline.CheckpointArtifact, warnings []contracts.Warning) error {
if err := r.writePayload(lanePayloadPath("merge", laneID, "output.json"), artifactSingleEnvelope{Output: artifactCheckpointEnvelopeFromOutput(output), Warnings: cloneWarnings(warnings)}); err != nil {
return r.MergeSucceededForStep("", laneID, moduleKey, dependencies, output, warnings)
}
func (r *FilesystemRecorder) MergeSucceededForStep(stepID, laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint, output pipeline.CheckpointArtifact, warnings []contracts.Warning) error {
if err := r.writePayload(lanePayloadPath("merge", stepID, laneID, "output.json"), artifactSingleEnvelope{Output: artifactCheckpointEnvelopeFromOutput(output), Warnings: cloneWarnings(warnings)}); err != nil {
return err
}
manifest := r.laneManifest(StageMerge, StatusSucceeded, laneID, moduleKey, dependencies)
manifest := r.laneManifest(StageMerge, StatusSucceeded, stepID, laneID, moduleKey, dependencies)
manifest.OutputDigests = checkpointFingerprints(artifactOutputDigests([]pipeline.CheckpointArtifact{output}))
manifest.ValidationStatus = validationStatusString(warnings, nil)
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("merge", laneID), MergeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
return r.writeManifest(laneManifestPath("merge", stepID, laneID), MergeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
}
func (r *FilesystemRecorder) MergeRejected(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, rejected contracts.RejectedOutput) error {
manifest := r.laneManifest(StageMerge, StatusSucceededWithRejections, laneID, moduleKey, dependencies)
return r.MergeRejectedForStep("", laneID, moduleKey, dependencies, rejected)
}
func (r *FilesystemRecorder) MergeRejectedForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, rejected contracts.RejectedOutput) error {
manifest := r.laneManifest(StageMerge, StatusSucceededWithRejections, stepID, laneID, moduleKey, dependencies)
manifest.ValidationStatus = "rejected"
manifest.Rejections = rejectionSummaries([]contracts.RejectedOutput{rejected})
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("merge", laneID), MergeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
return r.writeManifest(laneManifestPath("merge", stepID, laneID), MergeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
}
func (r *FilesystemRecorder) MergeFailed(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := r.laneManifest(StageMerge, StatusFailed, laneID, moduleKey, dependencies)
return r.MergeFailedForStep("", laneID, moduleKey, dependencies, err)
}
func (r *FilesystemRecorder) MergeFailedForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := r.laneManifest(StageMerge, StatusFailed, stepID, laneID, moduleKey, dependencies)
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest(laneManifestPath("merge", laneID), MergeLaneManifest{StageManifest: manifest})
return r.writeManifest(laneManifestPath("merge", stepID, laneID), MergeLaneManifest{StageManifest: manifest})
}
func (r *FilesystemRecorder) NormalizeRunning(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := r.laneManifest(StageNormalize, StatusRunning, laneID, moduleKey, dependencies)
return r.NormalizeRunningForStep("", laneID, moduleKey, dependencies)
}
func (r *FilesystemRecorder) NormalizeRunningForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) error {
manifest := r.laneManifest(StageNormalize, StatusRunning, stepID, laneID, moduleKey, dependencies)
manifest.StartedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("normalize", laneID), NormalizeLaneManifest{StageManifest: manifest})
return r.writeManifest(laneManifestPath("normalize", stepID, laneID), NormalizeLaneManifest{StageManifest: manifest})
}
func (r *FilesystemRecorder) NormalizeSucceeded(laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint, output pipeline.CheckpointArtifact, warnings []contracts.Warning) error {
if err := r.writePayload(lanePayloadPath("normalize", laneID, "output.json"), artifactSingleEnvelope{Output: artifactCheckpointEnvelopeFromOutput(output), Warnings: cloneWarnings(warnings)}); err != nil {
return r.NormalizeSucceededForStep("", laneID, moduleKey, dependencies, output, warnings)
}
func (r *FilesystemRecorder) NormalizeSucceededForStep(stepID, laneID, moduleKey string, dependencies []pipeline.CheckpointFingerprint, output pipeline.CheckpointArtifact, warnings []contracts.Warning) error {
if err := r.writePayload(lanePayloadPath("normalize", stepID, laneID, "output.json"), artifactSingleEnvelope{Output: artifactCheckpointEnvelopeFromOutput(output), Warnings: cloneWarnings(warnings)}); err != nil {
return err
}
manifest := r.laneManifest(StageNormalize, StatusSucceeded, laneID, moduleKey, dependencies)
manifest := r.laneManifest(StageNormalize, StatusSucceeded, stepID, laneID, moduleKey, dependencies)
manifest.OutputDigests = checkpointFingerprints(artifactOutputDigests([]pipeline.CheckpointArtifact{output}))
manifest.ValidationStatus = validationStatusString(warnings, nil)
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("normalize", laneID), NormalizeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
return r.writeManifest(laneManifestPath("normalize", stepID, laneID), NormalizeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
}
func (r *FilesystemRecorder) NormalizeRejected(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, rejected contracts.RejectedOutput) error {
manifest := r.laneManifest(StageNormalize, StatusSucceededWithRejections, laneID, moduleKey, dependencies)
return r.NormalizeRejectedForStep("", laneID, moduleKey, dependencies, rejected)
}
func (r *FilesystemRecorder) NormalizeRejectedForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, rejected contracts.RejectedOutput) error {
manifest := r.laneManifest(StageNormalize, StatusSucceededWithRejections, stepID, laneID, moduleKey, dependencies)
manifest.ValidationStatus = "rejected"
manifest.Rejections = rejectionSummaries([]contracts.RejectedOutput{rejected})
manifest.CompletedAt = timePtr(r.timestamp())
return r.writeManifest(laneManifestPath("normalize", laneID), NormalizeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
return r.writeManifest(laneManifestPath("normalize", stepID, laneID), NormalizeLaneManifest{StageManifest: manifest, InputCount: len(dependencies)})
}
func (r *FilesystemRecorder) NormalizeFailed(laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := r.laneManifest(StageNormalize, StatusFailed, laneID, moduleKey, dependencies)
return r.NormalizeFailedForStep("", laneID, moduleKey, dependencies, err)
}
func (r *FilesystemRecorder) NormalizeFailedForStep(stepID, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint, err error) error {
manifest := r.laneManifest(StageNormalize, StatusFailed, stepID, laneID, moduleKey, dependencies)
manifest.CompletedAt = timePtr(r.timestamp())
manifest.Metadata = errorMetadata(err)
return r.writeManifest(laneManifestPath("normalize", laneID), NormalizeLaneManifest{StageManifest: manifest})
return r.writeManifest(laneManifestPath("normalize", stepID, laneID), NormalizeLaneManifest{StageManifest: manifest})
}
func (r *FilesystemRecorder) writeManifest(name string, payload any) error {
@@ -190,8 +234,9 @@ func (r *FilesystemRecorder) newStageManifest(stage StageName, status StageStatu
return manifest
}
func (r *FilesystemRecorder) laneManifest(stage StageName, status StageStatus, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) StageManifest {
func (r *FilesystemRecorder) laneManifest(stage StageName, status StageStatus, stepID string, laneID string, moduleKey string, dependencies []pipeline.CheckpointFingerprint) StageManifest {
manifest := r.newStageManifest(stage, status)
manifest.StepID = stepID
manifest.LaneID = laneID
manifest.ModuleKey = moduleKey
manifest.DependencyFingerprints = checkpointFingerprints(dependencies)
@@ -424,12 +469,15 @@ func errorMetadata(err error) map[string]string {
return map[string]string{"error": err.Error()}
}
func laneManifestPath(stage string, laneID string) string {
return lanePayloadPath(stage, laneID, "manifest.json")
func laneManifestPath(stage string, stepID string, laneID string) string {
return lanePayloadPath(stage, stepID, laneID, "manifest.json")
}
func lanePayloadPath(stage string, laneID string, file string) string {
return path.Join(stage, checkpointPathComponent(laneID), file)
func lanePayloadPath(stage string, stepID string, laneID string, file string) string {
if strings.TrimSpace(stepID) == "" {
return path.Join(stage, checkpointPathComponent(laneID), file)
}
return path.Join(stage, checkpointPathComponent(stepID), checkpointPathComponent(laneID), file)
}
func checkpointPathComponent(value string) string {