[HDFS-5442] Zero loss HDFS data replication for multiple datacenters

• Type: Improvement
• Status: Open
• Priority: Major
• Resolution: Unresolved
• Assignee: Dian Fu
• Reporter: Avik Dey
• Created: 29/Oct/13 13:11
• Updated: 29/Mar/16 01:09

Description

Hadoop is architected to operate efficiently at scale for normal hardware failures within a datacenter. Hadoop is not designed today to handle datacenter failures. Although HDFS is not designed for nor deployed in configurations spanning multiple datacenters, replicating data from one location to another is common practice for disaster recovery and global service availability. There are current solutions available for batch replication using data copy/export tools. However, while providing some backup capability for HDFS data, they do not provide the capability to recover all your HDFS data from a datacenter failure and be up and running again with a fully operational Hadoop cluster in another datacenter in a matter of minutes. For disaster recovery from a datacenter failure, we should provide a fully distributed, zero data loss, low latency, high throughput and secure HDFS data replication solution for multiple datacenter setup.

Design and code for Phase-1 to follow soon.

Issue Links

• is related to: HDFS-9075 Multiple datacenter replication inside one HDFS cluster

Sub-Tasks

• Support "region" in HDFS configurations: Open
• Start primary/mirror services based on configurations: Open
• Add MirrorJournalManager to transfer edits from primary cluster to Mirror cluster: Open
• Add MirrorJournal ( server side implementation) to handle the journals from Primary cluster: Open
• Format mirror cluster with primary cluster's NamespaceInfo in the runtime: Open
• Add Disaster Recovery related metrics: Open
• Disable APIs which may modify the mirror cluster: Open
• Provide configurations to select mode of replication to Mirror cluster: Open
• Transfer data from primary cluster to mirror cluster synchronously: Open