[
https://issues.apache.org/jira/browse/HBASE-12994?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]
Jonathan Lawlor updated HBASE-12994:
------------------------------------
Description: As [~lhofhansl] has called out in HBASE-11544, RPC is
inefficient when scanning. The way it currently works is the client requests a
buffer worth of results and works through that buffer. Once that buffer of
results is exhausted, the client realizes it has run out of results and then
requests the next buffer. This could be improved by beginning to load the next
buffer on the server while the client is working through the current buffer of
results. (was: As [~lhofhansl] has called out in HBASE-11544, RPC is
inefficient when scanning. The way it currently works is the client requests a
buffer worth of results and works through that buffer. Once that buffer of
results is exhausted, the client realizes it has run out of results and then
requests the next buffer. This could be improved by beginning to load the next
buffer while the client is working through the current buffer of results.)
> Improve network utilization for scanning RPC requests by preloading the next
> set of results on the server
> ---------------------------------------------------------------------------------------------------------
>
> Key: HBASE-12994
> URL: https://issues.apache.org/jira/browse/HBASE-12994
> Project: HBase
> Issue Type: Improvement
> Reporter: Jonathan Lawlor
>
> As [~lhofhansl] has called out in HBASE-11544, RPC is inefficient when
> scanning. The way it currently works is the client requests a buffer worth of
> results and works through that buffer. Once that buffer of results is
> exhausted, the client realizes it has run out of results and then requests
> the next buffer. This could be improved by beginning to load the next buffer
> on the server while the client is working through the current buffer of
> results.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
