[
https://issues.apache.org/jira/browse/HBASE-18294?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=16305579#comment-16305579
]
Anoop Sam John commented on HBASE-18294:
----------------------------------------
Good that all started getting each other and trying to come to same point. :-)
At that time (1st patch) the discussion or disagreement was mainly on a new
HCD setter for offheap flush size.
So we may have to track on heap Data size, off heap data size and heap
overhead. At region level it is ok to do flush decision for both on heap and
off heap based on single condition. ie onHeapDataSize + offHeapDataSize +
overhead >=128 MB. This is ok.
At global level bit change needed as we have the heapOverhead now not the
complete java heap occupancy.
Pls note, every where heapSize means the Java heap size. This might be POJO
overhead alone or overhead + cell size based on where the cell data sits.
What u say? Bigger changes but if u can make am fully agree to that. Will
help with reviews once patch is in :-)
> Reduce global heap pressure: flush based on heap occupancy
> ----------------------------------------------------------
>
> Key: HBASE-18294
> URL: https://issues.apache.org/jira/browse/HBASE-18294
> Project: HBase
> Issue Type: Improvement
> Affects Versions: 3.0.0
> Reporter: Eshcar Hillel
> Assignee: Eshcar Hillel
> Fix For: 2.0.0-beta-2
>
> Attachments: HBASE-18294.01.patch, HBASE-18294.02.patch,
> HBASE-18294.03.patch, HBASE-18294.04.patch, HBASE-18294.05.patch,
> HBASE-18294.06.patch, HBASE-18294.07.patch, HBASE-18294.07.patch,
> HBASE-18294.08.patch, HBASE-18294.09.patch, HBASE-18294.10.patch,
> HBASE-18294.11.patch, HBASE-18294.11.patch, HBASE-18294.12.patch,
> HBASE-18294.13.patch
>
>
> A region is flushed if its memory component exceed a threshold (default size
> is 128MB).
> A flush policy decides whether to flush a store by comparing the size of the
> store to another threshold (that can be configured with
> hbase.hregion.percolumnfamilyflush.size.lower.bound).
> Currently the implementation (in both cases) compares the data size
> (key-value only) to the threshold where it should compare the heap size
> (which includes index size, and metadata).
--
This message was sent by Atlassian JIRA
(v6.4.14#64029)
