[infinispan-issues] [JBoss JIRA] Commented: (ISPN-186) Smart L1 cache invalidation

[Pete Muir (JIRA)]

    [ https://issues.jboss.org/browse/ISPN-186?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12583236#comment-12583236 ] 

Pete Muir commented on ISPN-186:
--------------------------------

My impl of this ends up creating a web of unicasts, sending a command to each owner of a key, requesting them to send invalidation commands as required to each node that has cached the key. Because of this, I don't have a single place at which I know the number of nodes to which invalidation will be sent, so can't implement a simple threshold as Bela proposes. 

Without changing this design (I can't see a lower overhead way to do it, but open to ideas), I think the best way to handle a threshold is to make N = number of invalidations + number of owners but this seems a bit complex. Looking for ideas...

> Smart L1 cache invalidation
> ---------------------------
>
>                 Key: ISPN-186
>                 URL: https://issues.jboss.org/browse/ISPN-186
>             Project: Infinispan
>          Issue Type: Feature Request
>          Components: Distributed Cache
>            Reporter: Manik Surtani
>            Assignee: Pete Muir
>              Labels: l1
>             Fix For: 5.0.0.BETA1, 5.0.0.Final
>
>
> Need to build a mechanism in which L1 invalidation is NOT multicast, but instead is unicast _if necessary_ to specific nodes that may have cached a given entry.  This can be detected by maintaining a list of nodes who have requested a key via a remote get, but this would need to be relayed by all data owners.
> Benefits would be performance by removing unnecessary invalidation where this is not needed, and by reducing noise in network stacks of most nodes.

--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira