[
https://issues.apache.org/jira/browse/HBASE-1845?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12876705#action_12876705
]
Jonathan Gray commented on HBASE-1845:
--------------------------------------
A parallel scan w/ filters _could_ be approaching the same performance as a
MultiGet, but after we implement some performance features we still don't have.
As of now, we are not aggressive with re-seeking during a scan, we basically
will always do full scans of all blocks even if we want to jump to the next row
for example, we'll keep reading through the previous row. See HBASE-1517 and
stuff like HBASE-2517 and HBASE-2450.
The second requirement would be adding more calls into filters to allow them to
push-down seeking information. For example, after every KV passed into the
filter, there could be a call to ask if the scan should re-seek (return null if
it needs to see every KV still, or return the KV to seek to if for example it
knows it's done with the current row and it knows the next row it wants).
So I think we will eventually get to the point where MultiGet and parallel
scans with filters become virtually the same thing... but it's going to be a
while. I think keeping Gets around and adding MultiGet gives us an easy target
for optimization and won't require adding further complexity to filters just
yet.
> MultiGet, MultiDelete, and MultiPut - batched to the appropriate region
> servers
> -------------------------------------------------------------------------------
>
> Key: HBASE-1845
> URL: https://issues.apache.org/jira/browse/HBASE-1845
> Project: HBase
> Issue Type: New Feature
> Reporter: Erik Holstad
> Fix For: 0.21.0
>
> Attachments: batch.patch, hbase-1845_0.20.3.patch,
> hbase-1845_0.20.5.patch, multi-v1.patch
>
>
> I've started to create a general interface for doing these batch/multi calls
> and would like to get some input and thoughts about how we should handle this
> and what the protocol should
> look like.
> First naive patch, coming soon.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
