[
https://issues.apache.org/jira/browse/BOOKKEEPER-181?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13271381#comment-13271381
]
Flavio Junqueira commented on BOOKKEEPER-181:
---------------------------------------------
@Sijie With CAS ,one can read, increment, and replace if the value is still the
same. Otherwise the operation fails and the client needs to try again. There is
the potential of starvation (a client continuously tries and fails), but I
suppose we can consider that it is small.
@All I'm not entirely convinced that the identification of ledgers should be
delegated to the metadata store. I agree that we can't keep using sequential
znodes as we are currently doing for a large deployment, but we could introduce
for example the notion of namespaces and have a counter for each namespace. The
value of the counter for each namespace is kept by zookeeper, and we use one
znode per namespace. This solution only works if the number of namespaces is
not large.
Other people have mentioned namespaces, so it might be an interesting feature
to consider.
> Scale hedwig
> ------------
>
> Key: BOOKKEEPER-181
> URL: https://issues.apache.org/jira/browse/BOOKKEEPER-181
> Project: Bookkeeper
> Issue Type: Improvement
> Components: bookkeeper-server, hedwig-server
> Reporter: Sijie Guo
> Assignee: Sijie Guo
> Fix For: 4.2.0
>
> Attachments: hedwigscale.pdf, hedwigscale.pdf
>
>
> Current implementation of Hedwig and BookKeeper is designed to scale to
> hundreds of thousands of topics, but now we are looking at scaling them to
> tens to hundreds of millions of topics, using a scalable key/value store such
> as HBase.
--
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
