Migration Architect

Migration Architect

Tier: POWERFUL
Category: Engineering - Migration Strategy
Purpose: Zero-downtime migration planning, compatibility validation, and rollback strategy generation

Overview

The Migration Architect skill provides comprehensive tools and methodologies for planning, executing, and validating complex system migrations with minimal business impact. This skill combines proven migration patterns with automated planning tools to ensure successful transitions between systems, databases, and infrastructure.

Core Capabilities

1. Migration Strategy Planning

• Phased Migration Planning: Break complex migrations into manageable phases with clear validation gates
• Risk Assessment: Identify potential failure points and mitigation strategies before execution
• Timeline Estimation: Generate realistic timelines based on migration complexity and resource constraints
• Stakeholder Communication: Create communication templates and progress dashboards

2. Compatibility Analysis

• Schema Evolution: Analyze database schema changes for backward compatibility issues
• API Versioning: Detect breaking changes in REST/GraphQL APIs and microservice interfaces
• Data Type Validation: Identify data format mismatches and conversion requirements
• Constraint Analysis: Validate referential integrity and business rule changes

3. Rollback Strategy Generation

• Automated Rollback Plans: Generate comprehensive rollback procedures for each migration phase
• Data Recovery Scripts: Create point-in-time data restoration procedures
• Service Rollback: Plan service version rollbacks with traffic management
• Validation Checkpoints: Define success criteria and rollback triggers

Quick Start — plan → check compatibility → generate rollback

All paths relative to this skill folder; sample inputs in assets/, expected shapes in expected_outputs/.

# 1. Generate the migration plan from a spec (copy assets/sample_database_migration.json)
python3 scripts/migration_planner.py --input migration_spec.json --format json -o migration_plan.json

# 2. Check schema/API compatibility — exits non-zero unless fully compatible (CI gate)
python3 scripts/compatibility_checker.py --before assets/database_schema_before.json --after assets/database_schema_after.json --type database --format json -o compatibility.json

# 3. Generate the rollback runbook from the plan
python3 scripts/rollback_generator.py --input migration_plan.json --format both -o rollback_runbook

Outputs chain: migration_plan.json (phases, risks, estimated_duration_hours) feeds step 3; compatibility.json reports overall_compatibility plus breaking_changes_count / potentially_breaking_count.

Gate: the migration is not approved until (a) compatibility_checker exits 0 (overall_compatibility: compatible) or every breaking/potentially-breaking item is explicitly accepted by the owner in writing, and (b) a rollback runbook exists for every phase in the plan. Re-run both checks after any schema revision.

Migration Patterns

Database Migrations

Schema Evolution Patterns

1. Expand-Contract Pattern

   • Expand: Add new columns/tables alongside existing schema
   • Dual Write: Application writes to both old and new schema
   • Migration: Backfill historical data to new schema
   • Contract: Remove old columns/tables after validation

2. Parallel Schema Pattern

   • Run new schema in parallel with existing schema
   • Use feature flags to route traffic between schemas
   • Validate data consistency between parallel systems
   • Cutover when confidence is high

3. Event Sourcing Migration

   • Capture all changes as events during migration window
   • Apply events to new schema for consistency
   • Enable replay capability for rollback scenarios

Data Migration Strategies

1. Bulk Data Migration

   • Snapshot Approach: Full data copy during maintenance window
   • Incremental Sync: Continuous data synchronization with change tracking
   • Stream Processing: Real-time data transformation pipelines

2. Dual-Write Pattern

   • Write to both source and target systems during migration
   • Implement compensation patterns for write failures
   • Use distributed transactions where consistency is critical

3. Change Data Capture (CDC)

   • Stream database changes to target system
   • Maintain eventual consistency during migration
   • Enable zero-downtime migrations for large datasets

Service Migrations

Strangler Fig Pattern

1. Intercept Requests: Route traffic through proxy/gateway
2. Gradually Replace: Implement new service functionality incrementally
3. Legacy Retirement: Remove old service components as new ones prove stable
4. Monitoring: Track performance and error rates throughout transition

graph TD
    A[Client Requests] --> B[API Gateway]
    B --> C{Route Decision}
    C -->|Legacy Path| D[Legacy Service]
    C -->|New Path| E[New Service]
    D --> F[Legacy Database]
    E --> G[New Database]

Parallel Run Pattern

1. Dual Execution: Run both old and new services simultaneously
2. Shadow Traffic: Route production traffic to both systems
3. Result Comparison: Compare outputs to validate correctness
4. Gradual Cutover: Shift traffic percentage based on confidence

Canary Deployment Pattern

1. Limited Rollout: Deploy new service to small percentage of users
2. Monitoring: Track key metrics (latency, errors, business KPIs)
3. Gradual Increase: Increase traffic percentage as confidence grows
4. Full Rollout: Complete migration once validation passes

Infrastructure Migrations

Cloud-to-Cloud Migration

1. Assessment Phase

   • Inventory existing resources and dependencies
   • Map services to target cloud equivalents
   • Identify vendor-specific features requiring refactoring

2. Pilot Migration

   • Migrate non-critical workloads first
   • Validate performance and cost models
   • Refine migration procedures

3. Production Migration

   • Use infrastructure as code for consistency
   • Implement cross-cloud networking during transition
   • Maintain disaster recovery capabilities

On-Premises to Cloud Migration

1. Lift and Shift

   • Minimal changes to existing applications
   • Quick migration with optimization later
   • Use cloud migration tools and services

2. Re-architecture

   • Redesign applications for cloud-native patterns
   • Adopt microservices, containers, and serverless
   • Implement cloud security and scaling practices

3. Hybrid Approach

   • Keep sensitive data on-premises
   • Migrate compute workloads to cloud
   • Implement secure connectivity between environments

Feature Flags for Migrations

Progressive Feature Rollout

# Example feature flag implementation
class MigrationFeatureFlag:
    def __init__(self, flag_name, rollout_percentage=0):
        self.flag_name = flag_name
        self.rollout_percentage = rollout_percentage
    
    def is_enabled_for_user(self, user_id):
        hash_value = hash(f"{self.flag_name}:{user_id}")
        return (hash_value % 100) < self.rollout_percentage
    
    def gradual_rollout(self, target_percentage, step_size=10):
        while self.rollout_percentage < target_percentage:
            self.rollout_percentage = min(
                self.rollout_percentage + step_size,
                target_percentage
            )
            yield self.rollout_percentage

Circuit Breaker Pattern

Implement automatic fallback to legacy systems when new systems show degraded performance:

class MigrationCircuitBreaker:
    def __init__(self, failure_threshold=5, timeout=60):
        self.failure_count = 0
        self.failure_threshold = failure_threshold
        self.timeout = timeout
        self.last_failure_time = None
        self.state = 'CLOSED'  # CLOSED, OPEN, HALF_OPEN
    
    def call_new_service(self, request):
        if self.state == 'OPEN':
            if self.should_attempt_reset():
                self.state = 'HALF_OPEN'
            else:
                return self.fallback_to_legacy(request)
        
        try:
            response = self.new_service.process(request)
            self.on_success()
            return response
        except Exception as e:
            self.on_failure()
            return self.fallback_to_legacy(request)

Data Validation and Reconciliation

Validation Strategies

1. Row Count Validation

   • Compare record counts between source and target
   • Account for soft deletes and filtered records
   • Implement threshold-based alerting

2. Checksums and Hashing

   • Generate checksums for critical data subsets
   • Compare hash values to detect data drift
   • Use sampling for large datasets

3. Business Logic Validation

   • Run critical business queries on both systems
   • Compare aggregate results (sums, counts, averages)
   • Validate derived data and calculations

Reconciliation Patterns

1. Delta Detection

   -- Example delta query for reconciliation
   SELECT 'missing_in_target' as issue_type, source_id
   FROM source_table s
   WHERE NOT EXISTS (
       SELECT 1 FROM target_table t 
       WHERE t.id = s.id
   )
   UNION ALL
   SELECT 'extra_in_target' as issue_type, target_id
   FROM target_table t
   WHERE NOT EXISTS (
       SELECT 1 FROM source_table s 
       WHERE s.id = t.id
   );

2. Automated Correction

   • Implement data repair scripts for common issues
   • Use idempotent operations for safe re-execution
   • Log all correction actions for audit trails

Rollback Strategies

Database Rollback

1. Schema Rollback

   • Maintain schema version control
   • Use backward-compatible migrations when possible
   • Keep rollback scripts for each migration step

2. Data Rollback

   • Point-in-time recovery using database backups
   • Transaction log replay for precise rollback points
   • Maintain data snapshots at migration checkpoints