[
https://issues.apache.org/jira/browse/HBASE-16205?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15376704#comment-15376704
]
Anoop Sam John commented on HBASE-16205:
----------------------------------------
This jira is applicable only for master.
{quote}
Two case: a request with two cell: cell1=200k, cell2=100k, cell1+cell2>256K,
cell1 and cell2 do not copy to MSLAB.
Three case: a request with two cell: cell1=300k, cell2=1k, cell1>256K, cell1
and cell2 do not copy to MSLAB.
And the two and three case is what i am suggested.
{quote}
No per cell is what we copy to MSLAB. The request might contain cells
corresponding to diff regions itself. So summing up the size of all cells may
not be worth IMO. And here I assume that we will add the feature of read into
BBPool in trunk soon.
> When Cells are not copied to MSLAB, deep clone it while adding to Memstore
> --------------------------------------------------------------------------
>
> Key: HBASE-16205
> URL: https://issues.apache.org/jira/browse/HBASE-16205
> Project: HBase
> Issue Type: Sub-task
> Components: regionserver
> Affects Versions: 2.0.0
> Reporter: Anoop Sam John
> Assignee: Anoop Sam John
> Priority: Critical
> Fix For: 2.0.0
>
> Attachments: HBASE-16205.patch
>
>
> This is imp after HBASE-15180 optimization. After that we the cells flowing
> in write path will be backed by the same byte[] where the RPC read the
> request into. By default we have MSLAB On and so we have a copy operation
> while adding Cells to memstore. This copy might not be there if
> 1. MSLAB is turned OFF
> 2. Cell size is more than a configurable max size. This defaults to 256 KB
> 3. If the operation is Append/Increment.
> In such cases, we should just clone the Cell into a new byte[] and then add
> to memstore. Or else we keep referring to the bigger byte[] chunk for longer
> time.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
