[HDFS-8320] Erasure coding: consolidate striping-related terminologies

• Type: Sub-task
• Status: Resolved
• Priority: Major
• Resolution: Fixed
• Target Version/s: HDFS-7285
• Hadoop Flags: Reviewed
• Assignee: Zhe Zhang
• Reporter: Zhe Zhang
• Created: 04/May/15 22:04
• Updated: 30/Sep/15 19:38
• Resolved: 19/May/15 05:56

Description

Right now we are doing striping-based I/O in a number of places:

1. Client output stream (HDFS-7889)
2. Client input stream
   • pread (HDFS-7782, HDFS-7678)
   • stateful read (HDFS-8033, HDFS-8281, HDFS-8319)
3. DN reconstruction (HDFS-7348)

In each place we use one or multiple of the following terminologies:

1. Cell
2. Stripe
3. Block group
4. Internal block
5. Chunk

This JIRA aims to systematically define these terminologies in relation with each other and in the context of the containing file. For example, a cell belong to stripe i and internal block j can be indexed as (i, j) and its logical index k in the file can be calculated.

With the above consolidation, hopefully we can further consolidate striping I/O codes.