All Products
Search
Document Center

Lindorm:Overview

Last Updated:Sep 02, 2022

LindormDFS provides a distributed file storage system to store a large amount of unstructured data. LindormDFS shares storage with the other engines provided by Lindorm. LindormDFS adopts object storage and block storage benefits. Object storage provides benefits such as low cost and high reliability. Block storage provides benefits such as high performance. In addition, LindormDFS uses features such as high-speed tiered storage and low-speed tiered storage, shared-replica deduplication, and intelligent data tiering. These features are provided by LindormDFS that is fully compatible with Hadoop Distributed File System (HDFS) to support elastic, cost-effective, and cloud native big data storage. You can use open source HDFS clients to access LindormDFS.

In scenarios such as computing analysis, backup archiving, and data import, Lindorm allows external systems to access the files that are stored in the underlying storage space of LindormDFS. This makes data reads and writes more efficient. For example, you can create physical files in the data format that is used in an offline computing system. This reduces the negative impact on online services in LindormDFS.

Benefits

  • Cost-effective: The lowest unit price is CNY 0.12/GB/month. The unit price may vary by region. If the unit price is different, the unit price on the buy page prevails. The price can be reduced in the future.

  • File system base: supports high-performance read operations and write operations on metadata. Files can be moved in batches by directory.

  • HDFS protocol compatibility: You can use open source HDFS clients to access LindormDFS without the need to worry about vendor lock-in issues. LindormDFS is compatible with a range of open source and Alibaba Cloud services, such as Hive, Spark, Impala, Presto, Flink, Yarn, Kylin, E-MapReduce (EMR), Data Lake Analytics (DLA), and MaxCompute.

  • Compute-storage separation: You can purchase the storage package based on your business requirements. Computing is decoupled from storage. You do not need to worry about the resource waste that is caused when storage is coupled to computing.

  • Hot data and cold data storage: Hot data and cold data can be stored in the same system. You can specify your data as hot data or cold data by file or folder. You can store hot data and cold data in different types of storage media to reduce storage costs.