Skip to main content
Aerospike Vector is now live with LangChain integrationTell me more
Loading

Distribution

Overview​

This page describes how the Aerospike Database distribution system is designed for applications that must be available at all times.

This has several implications:

  • Automatic data location detection:
    • The Aerospike client automatically detects data location and handles requests in a single hop. Your application can treat the database as if were stored on a single server. The Aerospike smart client handles cluster distribution.
  • Automatic cluster balancing:
    • When adding capacity, simply add a node to the cluster and the cluster re-balances to include the new node. Throughput and performance scale linearly as you add capacity.
  • No single point of failure:
    • An SSD on a node can fail, a node can fail or be taken offline for maintenance or upgrades, or the entire datacenter can fail without affecting reliability.

Cluster management features​

Aerospike manages clusters with the following features:

  • Data Distribution: Robust partitioning ensures uniform data distribution, which avoids hot spots and automatically balances data without manual intervention.
  • Clustering: The Aerospike clustered database automatically detects failures and heals.
  • Replication: This Aerospike feature includes the following replication abilities to avoid a single point of failure: