ramkrishna.s.vasudevan commented on HBASE-16783:

BBPoolManager does not look good here. But later when you use write req buffer 
pool also we can use this class and create buffers as MultiByteBuff. For now I 
can remove it and make use of ByteBufferListoutputStream. 
But for this patch we don't do any sync mechanism. Only that we see if the 
curBuf has enough space for accomodating the header len and if so just use it. 
Or else create ondemand onheap buffer.
May be that new API can be added to BBLOS? But that does not look good too. 
Definitely we will be saving on allocations here. 

> Use ByteBufferPool for the header and message during Rpc response
> -----------------------------------------------------------------
>                 Key: HBASE-16783
>                 URL: https://issues.apache.org/jira/browse/HBASE-16783
>             Project: HBase
>          Issue Type: Improvement
>            Reporter: ramkrishna.s.vasudevan
>            Assignee: ramkrishna.s.vasudevan
>            Priority: Minor
>         Attachments: HBASE-16783.patch, HBASE-16783_1.patch, 
> HBASE-16783_2.patch, HBASE-16783_3.patch
> With ByteBufferPool in place we could avoid the byte[] creation in 
> RpcServer#createHeaderAndMessageBytes and try using the Buffer from the pool 
> rather than creating byte[] every time.

This message was sent by Atlassian JIRA

Reply via email to