Grokking Database Fundamentals for Tech Interviews
Rate this course
Ask Author
Contribute
Back to course home

0% completed

Vote For New Content
Introduction to Database Systems
Course Overview
Overview of Databases
Core Components of Database
Database Architectures
Relational Vs. Non-relational Databases
Data Storage in DBMS
Data Storage Fundamentals
File Organization in DBMS
Data Compression and Encoding
Quiz
Indexing in DBMS
Introduction to Database Indexes
Single Level Indexing
Tree-Based Indexing Techniques
Hash-Based Indexing
Bloom Filters
Quiz
Transaction Management
Understanding the Transaction
Atomicity
Consistency
Isolation
Durability
Quiz
Concurrency Control
Understanding the Concurrency Control
Optimistic vs. Pessimistic Concurrency Control
Lock-Based Concurrency Control
Timestamp-Based Concurrency Control
Multiversion Concurrency Control (MVCC)
Quiz
Distributed Databases, Data Partitioning & Sharding
Fundamentals of Distributed Databases
Partitioning in Databases
Partitioning Types
Sharding in Databases
Distributed Query Processing
Quiz
Data Replication and Consistency Models
Replication in Databases
Replication Topologies
Understanding the Consistency Models in Databases
The CAP Theorem and Its Implications
Quiz
Understanding the Consensus
Consensus algorithms
Leader Election Strategies
Quiz
Understanding the Fault Tolerance
Logging Mechanisms in Databases
Checkpointing and Recovery Basics
Coordinated Recovery in Distributed Systems
High Availability Through Replication and Failover
Ensuring Data Resilience: Redundancy, Mirroring, and Recovery
Quiz
Introduction to NoSQL
Key-Value Stores
Document-Oriented Databases
Column-Family and Wide-Column Stores
Graph Databases
Quiz
Quora System Design & Database Design
TikTok System Design & Database Design
Airbnb System Design & Database Design
Snapchat System Design & Database Design
Replication Topologies

Replication topologies define how data is replicated across nodes in a distributed database system. These topologies determine how read and write operations are handled and how data consistency, availability, and fault tolerance are maintained. Different topologies cater to varying system requirements, offering trade-offs between performance and complexity.

Synchronous vs. Asynchronous Replication

Replication can be classified based on the timing of data synchronization between nodes:

1. Synchronous Replication

In synchronous replication, the primary node waits for acknowledgment from replicas before committing a transaction. This ensures that all replicas have the same data before the transaction is considered complete.

Image
  • Advantages:
    • Guarantees strong consistency as all replicas are up-to-date.
    • Prevents data loss in case of primary node failure.
  • Disadvantages:
    • Increased latency as the primary waits for all replicas.
    • Lower throughput for write-heavy workloads.
  • Use Case: Financial systems where data accuracy is critical, such as transaction processing.

2. Asynchronous Replication

In asynchronous replication, the primary node commits a transaction immediately without waiting for acknowledgment from replicas. Replicas update their data in the background.

Image
  • Advantages:
    • Low latency as the primary doesn’t wait for replicas.
    • High throughput, especially for write-heavy workloads.
  • Disadvantages:
    • Potential for data loss if the primary fails before replicas update.
    • Inconsistent replicas until they catch up with the primary.
  • Use Case: Content delivery systems and applications prioritizing availability over consistency, such as social media platforms.

Types of Replication Topologies

Replication is a fundamental aspect of distributed databases and systems, aiming to enhance data availability, fault tolerance, and read performance. There are three primary replication topologies:

  1. Single-Leader Replication
  2. Multi-Leader Replication
  3. Leaderless Replication

Each topology offers unique advantages and trade-offs, making them suitable for different use cases. Below is an in-depth exploration of each type.

1. Single-Leader Replication

In single-leader replication (also known as master-slave or primary-secondary replication), one node is designated as the leader (or primary). This leader node handles all write operations, ensuring a consistent and authoritative source of truth. The leader then propagates these changes to one or more follower nodes (also called replicas or secondaries), which handle read operations.

Image

How It Works

  1. Write Operations:

    • Clients send all write requests (INSERT, UPDATE, DELETE) to the leader node.
    • The leader executes the write operation, updating its local data.
    • The leader records the changes in a replication log or write-ahead log (WAL).
  2. Replication to Followers:

    • Synchronous Replication: The leader waits for confirmation from followers before acknowledging the write to the client.
    • Asynchronous Replication: The leader immediately acknowledges the write to the client without waiting for followers.
  3. Read Operations:

    • Clients can read data from the leader or any of the follower nodes.
    • Reading from followers can improve read scalability and distribute the load.
  4. Failure Handling:

    • If the leader fails, a failover process is initiated.
    • One of the followers is promoted to be the new leader through an election process.
    • Clients are redirected to the new leader for write operations.

Use Cases

  • Social Media Platforms: Where consistent updates (likes, comments) are critical, but read scalability is also important.
  • Content Management Systems: Requiring strong consistency for content updates with high read availability.
  • Financial Systems: Banking applications where transactional integrity is paramount.

2. Multi-Leader Replication

Multi-leader replication (also known as master-master replication) allows multiple nodes to accept write operations. Each leader node can process writes independently and replicates changes to other leaders and followers. This topology is useful for geographically distributed systems where local writes need to be immediately accepted.

Image

How It Works

  1. Write Operations:

    • Clients can send write requests to any leader node.
    • Each leader processes the write and updates its local data.
  2. Replication Between Leaders:

    • Leaders use replication logs to propagate changes to other leaders.
    • Conflict Detection and Resolution:
      • Conflicts can occur when the same data is modified concurrently on different leaders.
      • Conflict resolution strategies include last-write-wins, custom conflict handlers, or application-level resolution.
  3. Read Operations:

    • Clients can read from any leader or follower node.
    • Followers replicate data from their designated leader.
  4. Failure Handling:

    • If a leader fails, clients can switch to another leader without significant disruption.
    • The system continues to operate with reduced capacity.

Use Cases

  • Collaborative Applications: Tools like document editors where multiple users can edit simultaneously from different locations.
  • Distributed Databases: Systems requiring local write availability in different geographical regions.
  • Mobile and Offline Applications: Apps that need to handle writes while offline and synchronize when connected.

3. Leaderless Replication

In leaderless replication, there is no designated leader node. All nodes are equal, and clients can send read and write requests to any node. Data consistency is managed through consensus protocols and quorum-based techniques, ensuring high availability and fault tolerance.

Image

How It Works

  1. Write Operations:

    • Clients send write requests to multiple nodes (typically a subset of all nodes).
    • Each node independently applies the write operation.
    • Quorum Writes: A write is considered successful when a quorum (minimum number) of nodes acknowledge the write.
  2. Read Operations:

    • Clients read from multiple nodes to ensure they get the most recent data.
    • Read Repair: If discrepancies are found, the system can resolve them during read operations.
  3. Consistency Mechanisms:

    • Quorum Consensus: The sum of the write quorum and read quorum must exceed the total number of nodes to ensure consistency.
    • Vector Clocks: Used to detect conflicting updates and resolve them.
  4. Failure Handling:

    • The system can tolerate node failures without impacting availability.
    • Data is replicated across multiple nodes, ensuring redundancy.

Use Cases

  • Distributed Key-Value Stores: Systems like Amazon DynamoDB and Apache Cassandra that prioritize availability and partition tolerance.
  • Content Delivery Networks (CDNs): Where data is replicated globally, and eventual consistency is acceptable.
  • IoT and Sensor Networks: Handling vast amounts of data with high fault tolerance requirements.

Comparison of Replication Topologies

FeatureSingle-LeaderMulti-LeaderLeaderless
Write ScalabilityLimitedImprovedHigh
Read ScalabilityHigh (with followers)High (with followers)High
ConsistencyStrong (for writes)Variable (conflicts)Eventual
Fault ToleranceModerateHighVery High
ComplexityLowHighHigh
Conflict ResolutionSimpleComplexComplex
Use Case SuitabilityCentralized systemsGeo-distributed writesHigh availability needs

Choosing the Right Topology

The choice of replication topology and synchronization method depends on the specific requirements of the system:

  • Consistency vs. Availability: Systems prioritizing consistency should use single-leader replication with synchronous updates. Those prioritizing availability can use leaderless replication with asynchronous updates.
  • Write Scalability: Multi-leader replication is ideal for write-heavy systems requiring scalability.
  • Fault Tolerance: Leaderless replication offers high fault tolerance and is suitable for systems that must operate during partial failures.
Replication in Databases
Understanding the Consistency Models in Databases
Mark as Completed

On this page

Synchronous vs. Asynchronous Replication

  1. Synchronous Replication
  1. Asynchronous Replication

Types of Replication Topologies

  1. Single-Leader Replication
  1. Multi-Leader Replication
  1. Leaderless Replication

Comparison of Replication Topologies

Choosing the Right Topology