[
https://issues.apache.org/jira/browse/HBASE-16436?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15622392#comment-15622392
]
Anastasia Braginsky commented on HBASE-16436:
---------------------------------------------
Hi Guys,
It looks like I missed all this CellChunkMap discussion here. It looks to me
that we have already seen those question about CellChunkMap and we had some
solution for the Big-Cells issues (those bigger then a MSLAB chunk) only on
paper however, no code. We suggested to allocate big cells on the special
variable-size chunks that are allocated and freed upon request (not going
thorough the pool). All the discussion was at HBASE-14921. Only CellChunkMap
implementation was coded, then we decided to split and continue with
CellArrayMap only. It was a wise decision because we had a lot of work anyway.
Let discuss all those design issues on our meeting related to CellChunkMap.
Thanks,
Anastasia
> Add the CellChunkMap variant
> ----------------------------
>
> Key: HBASE-16436
> URL: https://issues.apache.org/jira/browse/HBASE-16436
> Project: HBase
> Issue Type: Sub-task
> Reporter: ramkrishna.s.vasudevan
>
> This sub-task is specifically to add the CellChunkMap created by [~anastas]
> and [~eshcar] with specific tests and integrate it with the in memory
> flush/compaction flow.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
