[
https://issues.apache.org/jira/browse/HBASE-14921?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15167470#comment-15167470
]
stack commented on HBASE-14921:
-------------------------------
bq. ...using the special KeyValueScanner for the MemStoreSnapshot object.
What will the serialization/format-transform look like (if any)?
bq. After that the Cell object is created and the reference to this Cell is
inserted into the skip-list to accelerate the search.
Yes. This is a copy. Would be good if we did not have to do this.
bq. We want to get a better search by using the binary search and binary search
implies fixed-size elements of an array.
You've seen how we store blocks to hfiles with index blocks and blooms?
What is 'fixed-size' in the above? The arrays of cells? Or the references to
cells kept elsewhere.
bq. Maybe we will see almost no improvement...
I'd imagine you'd have to try really hard to make it so array access is less
performant than CSLM (read-only so no synchronization primitives needed either)
bq. Please note that CellBlocksSegment and off-heaping are really separate
issues and we plan to refer to the second after we finish with the first.
Understood. Main concern is that the base types used align with those being
carried through the read path and looking to see that we minimize (or do
without completely) transforms converting between types or from one backing
storage to another: e.g. from offheap bytebuffer into which we read the request
Cells to MSLAB copied to CSLM then copied to Segment and finally copied to
buffers written out to hfile... not to mind writes to WAL in the midst. Would
be good to we save a few copies/transforms (or have none at all !)
bq. was that MSLAB should be switched from ByteRange to ByteBuffer and support
both on and off-heap.
Ok.
All the rest sounds good.
Thanks.
> Memory optimizations
> --------------------
>
> Key: HBASE-14921
> URL: https://issues.apache.org/jira/browse/HBASE-14921
> Project: HBase
> Issue Type: Sub-task
> Affects Versions: 2.0.0
> Reporter: Eshcar Hillel
>
> Memory optimizations including compressed format representation and offheap
> allocations
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
