[infinispan-issues] [JBoss JIRA] (ISPN-7322) Improve triangle algorithm: ordering by segment

[Radim Vansa (JIRA)]

    [ https://issues.jboss.org/browse/ISPN-7322?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13341507#comment-13341507 ] 

Radim Vansa commented on ISPN-7322:
-----------------------------------

[~belaban] Allocating memory is fast, you pay for that later in GC. Despite of that, I've seen quite a substantial amount of time spent in marshalling (in flame graphs - so the GC overheads was not included), even though these were just byte arrays and strings. I can imagine that with complex objects the cost is higher; in any case, I wouldn't call marshalling effect neglible.

> Improve triangle algorithm: ordering by segment
> -----------------------------------------------
>
>                 Key: ISPN-7322
>                 URL: https://issues.jboss.org/browse/ISPN-7322
>             Project: Infinispan
>          Issue Type: Enhancement
>          Components: Core
>            Reporter: Pedro Ruivo
>            Assignee: Pedro Ruivo
>
> Current triangle algorithm uses regular message (FIFO ordered) between the primary owner and backup owners of a key. While it ensures that the backup owners receives the stream of updates in the same order, it makes everything slower since it doesn't allow different keys to be handled in parallel.
> "Triangle unordered" solves this problem by sending OOB messages (not ordered) between the primary and backup. To keep the consistency, Infinispan introduces the TriangleOrderManager that orders the updates based on the segment of the key.
> While it is not as perfect as ordering per key, the segments are static; this removes the complexity and avoids handling the cluster topology changes and key adding/removal while improves the performance.



--
This message was sent by Atlassian JIRA
(v7.2.3#72005)