[
https://issues.apache.org/jira/browse/HBASE-4120?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13142493#comment-13142493
]
Ted Yu commented on HBASE-4120:
-------------------------------
Here is some background for the current implementation provided by Liu Jia:
We have moved the main functionality of table priority (HBASE-4120) to
PriorityFunction and PriorityJobQueue.
PriorityFunction implements Function<Writable, Integer> and is used by the
PriorityJobQueue to decide the priority of each IPC call.
Through this we make the PriorityHBaseServer much simpler.
In current implementation of HBase, there would be one priority for each method:
{code}
for (Method m : HRegionServer.class.getMethods()) {
QosPriority p = m.getAnnotation(QosPriority.class);
{code}
But in our implementation, method can have different priorities for different
HBase tables.
e.g. for tables A and B in the same cluster, table A serves reads mostly while
table B serves writes more often.
we may want to give high priority to get() for table A while giving low
priority to put(). For table B, we may want low priority for get() and high
priority for put().
That's why we introduced ActionPrioriy for the methods (such as get and put).
At the same time, tables have their base priorities.
We believe the above approach is more flexible.
We do not interfere with the current Qos Function,which handles the meta and
root request respectively.
but in the future a more generalized approach is better.
> isolation and allocation
> ------------------------
>
> Key: HBASE-4120
> URL: https://issues.apache.org/jira/browse/HBASE-4120
> Project: HBase
> Issue Type: New Feature
> Components: master, regionserver
> Affects Versions: 0.90.2, 0.90.3, 0.90.4, 0.92.0
> Reporter: Liu Jia
> Assignee: Liu Jia
> Fix For: 0.94.0
>
> Attachments: Design_document_for_HBase_isolation_and_allocation.pdf,
> Design_document_for_HBase_isolation_and_allocation_Revised.pdf,
> HBase_isolation_and_allocation_user_guide.pdf,
> Performance_of_Table_priority.pdf, System Structure.jpg, TablePriority.patch
>
>
> The HBase isolation and allocation tool is designed to help users manage
> cluster resource among different application and tables.
> When we have a large scale of HBase cluster with many applications running on
> it, there will be lots of problems. In Taobao there is a cluster for many
> departments to test their applications performance, these applications are
> based on HBase. With one cluster which has 12 servers, there will be only one
> application running exclusively on this server, and many other applications
> must wait until the previous test finished.
> After we add allocation manage function to the cluster, applications can
> share the cluster and run concurrently. Also if the Test Engineer wants to
> make sure there is no interference, he/she can move out other tables from
> this group.
> In groups we use table priority to allocate resource, when system is busy; we
> can make sure high-priority tables are not affected lower-priority tables
> Different groups can have different region server configurations, some groups
> optimized for reading can have large block cache size, and others optimized
> for writing can have large memstore size.
> Tables and region servers can be moved easily between groups; after changing
> the configuration, a group can be restarted alone instead of restarting the
> whole cluster.
> git entry : https://github.com/ICT-Ope/HBase_allocation .
> We hope our work is helpful.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
