[
https://issues.apache.org/jira/browse/HBASE-20003?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16414120#comment-16414120
]
Anoop Sam John commented on HBASE-20003:
----------------------------------------
bq.What is the advantage to still use HDFS here? Sorry I do not follow the
following words 'we need its data availability maintain mechanism like the re
replication for under replication etc.'...
Ya when the WAL is removed, we use the pmem device for persistence and region
memstore replication for the data availability aspect. But say for the HFiles
also no HDFS, then initially say if all replicas can flush locally, we have the
data replication. When a node is failed, the data is under replicated.. So
again need to re replicate it make the replicas count to be satisfied. None
of that type we plan to change or do.. We can see in case of region memstore
replication, when there is a region failure, the memstore data become under
replicated (3 replica becomes 2).. But the 1st action will be a flush make
again makes the data highly available for all replicas (including the new
replica region being brought up).
> WALLess HBase on Persistent Memory
> ----------------------------------
>
> Key: HBASE-20003
> URL: https://issues.apache.org/jira/browse/HBASE-20003
> Project: HBase
> Issue Type: New Feature
> Reporter: Anoop Sam John
> Assignee: Anoop Sam John
> Priority: Major
>
> This JIRA aims to make use of persistent memory (pmem) technologies in HBase.
> One such usage is to make the Memstore to reside on pmem. Making a persistent
> memstore would remove the need for WAL and paves way for a WALLess HBase.
> The existing region replica feature could be used here and ensure the data
> written to memstores are synchronously replicated to the replicas and ensure
> strong consistency of the data. (pipeline model)
> Advantages :
> - Data Availability : Since the data across replicas are consistent
> (synchronously written) our data is always 100 % available.
> - Lower MTTR : It becomes easier/faster to switch over to the replicas on a
> primary region failure as there is no WAL replay involved. Building the
> memstore map data also is much faster than reading the WAL and replaying the
> WAL.
> - Possibility of bigger memstores : These pmems are designed to have more
> memory than DRAMs so it would also enable us to have bigger sized memstores
> which leads to lesser flushes/compaction IO.
> - Removes the dependency of HDFS on the write path
> Initial PoC has been designed and developed. Testing is underway and we would
> publish the PoC results along with the design doc sooner. The PoC doc will
> talk about the design decisions, the libraries considered to work with these
> pmem devices, pros and cons of those libraries and the performance results.
> Note : Next gen memory technologies using 3DXPoint gives persistent memory
> feature. Such memory DIMMs are soon to appear in the market. The PoC is done
> around Intel's ApachePass (AEP)
--
This message was sent by Atlassian JIRA
(v7.6.3#76005)
