[
https://issues.apache.org/jira/browse/HADOOP-2139?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel#action_12540637
]
stack commented on HADOOP-2139:
-------------------------------
Looks good.
On 'Scans vs Cache Flush', if a flush is allowed while an outstanding scanner
is running against a 'snapshot' of hstores and some subset of memcache, for
periods won't we have two copies of data; the memory that is being flushed but
which cannot be let go because it has an outstanding scanner running against it
and then the new flushed hstore on disk.
Accounting will be gnarly. On scanner close, will have to check what of the
memcache we can let go (because its been successfully flushed).
> [hbase] Increase parallelism in region servers
> ----------------------------------------------
>
> Key: HADOOP-2139
> URL: https://issues.apache.org/jira/browse/HADOOP-2139
> Project: Hadoop
> Issue Type: Improvement
> Components: contrib/hbase
> Affects Versions: 0.16.0
> Reporter: Jim Kellerman
> Assignee: Jim Kellerman
> Fix For: 0.16.0
>
>
> There are a number of paths in the region server which block against one
> another including:
> - log rolling
> - cache flushes
> - region splitting
> - updates
> - scanners
> Investigate which can proceed in parallel and mechanisms for making some
> operations that currently do not run in parallel.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
