Persistent memory-optimized instances adopt Intel Optane DC persistent memory (AEP) to provide large-capacity in-memory databases that are compatible with open source Redis. A persistent memory-optimized instance persists each operation without using disks. Compared with an ApsaraDB for Redis Community Edition instance, it reduces costs by up to 30% and delivers almost the same throughput and latency. This helps improve the reliability of business data.

Instance purchase

Create a persistent memory-optimized or storage-optimized instance of ApsaraDB for Redis Enhanced Edition (Tair)

Background information

The high price and low capacity of memory limit the large-scale use of memory in specific scenarios. Alibaba Cloud began to invest in the research and implementation of Intel AEP in 2018. Intel AEP was applied to the core cluster of e-commerce products with remarkably reduced costs during Double 11 that year. The cluster became the first product in China that officially deployed Intel persistent memory in a production environment.

Maturer cloud environments and improved AEP-related technologies help Alibaba Cloud develop a new engine for data persistence based on AEP. Alibaba Cloud integrates the new engine with ECS bare metal instances and introduces persistent memory-optimized instances of the ApsaraDB for Redis Enterprise Edition (Tair). These instances replace the volatile memory of traditional Redis with the native persistent memory of AEP to significantly reduce the risk of data loss. For more information about ECS bare metal instances, see Overview.

Persistent memory-optimized instances provide not only memory-level access latency and throughput but also data persistence. In addition to reducing costs, persistent memory-optimized instances can simplify the application architecture. The popular architecture that consists of applications, cache, and persistent storage can be simplified to an architecture that consists of applications and persistent memory-optimized instances, as shown in the following figure.

Architecture evolution of persistent memory-optimized instances

Benefits

Persistent memory-optimized instances of the ApsaraDB for Redis Enhanced Edition (Tair) adopt Intel AEP to provide large-capacity in-memory databases that are compatible with open source Redis. A persistent memory-optimized instance persists each operation without using disks. Compared with an ApsaraDB for Redis Community Edition instance, it reduces costs by up to 30% and delivers almost the same throughput and latency. This helps improve the reliability of business data. Persistent memory-optimized instances are applicable to scenarios that store hot and warm data, have high requirements for data persistence, and require compatibility with Redis, large capacity, and stable and controllable jitter.

Item Description
Cost-effectiveness
  • A persistent memory-optimized instance costs about 30% less than an ApsaraDB for Redis Community Edition instance.
  • A persistent memory-optimized instance can provide 90% of the performance of a native Redis database.
Integration with multiple Redis modules
Optimization for high specifications
  • In scenarios where advanced memory specifications are used, issues such as high latency, high network jitter, and slow service data loading during fork operations triggered by AOF rewrites are resolved. You do not need to choose between performance and persistence.
  • The memory size of master-replica instances ranges from 128 GB to 512 GB. The memory size of cluster instances can reach up to 32 TB.
Data loss prevention during power outages
  • Persistent memory-optimized instances support command-level persistence. A response is returned after data persistence is complete for each write operation.
  • If you use open source Redis, you must take the risk of data loss calculated at seconds. Persistent memory-optimized instances are more reliable when the queries per second (QPS) is high.
High compatibility
  • Persistent memory-optimized instances are compatible with the ApsaraDB for Redis database system and support high availability, auto scaling, logging, intelligent diagnostics, and flexible backup and restoration.
  • Persistent memory-optimized instances are compatible with most of the data structures and interfaces of native Redis.

Scenarios

  • Scenarios that require high performance and reduced costs for processing a large amount of data

    Data computing requires high performance. ApsaraDB for Redis Community Edition is costly. Other database types such as HBase cannot meet the performance requirements. Persistent memory-optimized instances not only ensure data persistence but also provide almost the same performance as ApsaraDB for Redis Community Edition instances in terms of throughput and latency. This can help you strike a balance between performance and costs.

  • Scenarios that have high requirements for data persistence

    For gaming services, persistent memory-optimized instances are used for data storage. Compared with the architecture that uses Redis together with MySQL, persistent memory-optimized instances provide a simpler architecture, higher performance, higher cost-effectiveness, and higher data reliability.

Instance types

Persistent memory-optimized instances