[
https://issues.apache.org/jira/browse/HBASE-15180?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15122488#comment-15122488
]
Enis Soztutar commented on HBASE-15180:
---------------------------------------
This is a good idea. Having all cells in the same RPC share the same byte[].
Is {{CellReadable}} really necessary? Isn't this the same thing as
Codec.Decoder. I mean, from a layering perspective, I thought that we would
instead change the Codec to be aware of byte[] directly, and return a
CellScanner that can return KV's from the same buffer. I was thinking of doing
a Codec at the RPC layer to do something like FAST_DIFF. Can that still be done
with this patch?
Should we default to MSLAB for good? I don't think anybody runs with MSLAB off.
RPCServer reaching this is not right:
{code}
+ this.mslabEnabled = conf.getBoolean(HConstants.USEMSLAB_KEY,
HConstants.USEMSLAB_DEFAULT);
{code}
Can the byte[4]'s be statically allocated?
> Reduce garbage created while reading Cells from Codec Decoder
> -------------------------------------------------------------
>
> Key: HBASE-15180
> URL: https://issues.apache.org/jira/browse/HBASE-15180
> Project: HBase
> Issue Type: Sub-task
> Components: regionserver
> Reporter: Anoop Sam John
> Assignee: Anoop Sam John
> Fix For: 2.0.0
>
> Attachments: HBASE-15180.patch
>
>
> In KeyValueDecoder#parseCell (Default Codec decoder) we use
> KeyValueUtil#iscreate to read cells from the InputStream. Here we 1st create
> a byte[] of length 4 and read the cell length and then an array of Cell's
> length and read in cell bytes into it and create a KV.
> Actually in server we read the reqs into a byte[] and CellScanner is created
> on top of a ByteArrayInputStream on top of this. By default in write path, we
> have MSLAB usage ON. So while adding Cells to memstore, we will copy the Cell
> bytes to MSLAB memory chunks (default 2 MB size) and recreate Cells over that
> bytes. So there is no issue if we create Cells over the RPC read byte[]
> directly here in Decoder. No need for 2 byte[] creation and copy for every
> Cell in request.
> My plan is to make a Cell aware ByteArrayInputStream which can read Cells
> directly from it.
> Same Codec path is used in client side also. There better we can avoid this
> direct Cell create and continue to do the copy to smaller byte[]s path. Plan
> to introduce some thing like a CodecContext associated with every Codec
> instance which can say the server/client context.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
