[jira] [Commented] (CASSANDRA-7032) Improve vnode allocation

["Benedict (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/CASSANDRA-7032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14573452#comment-14573452 ] 

Benedict commented on CASSANDRA-7032:
-------------------------------------

I've pushed some minor suggestions [here|https://github.com/belliottsmith/cassandra/tree/7032-suggestions]

I think the integration / mechanism for employing this functionality could be improved, but that can be delayed to a follow up ticket.

Before that, though, AFAICT the token ranges we're optimising for in this ticket are not those the cluster actually runs on. They _start_ at the token assigned to each endpoint, instead of _end_

Other than that it LGTM.

> Improve vnode allocation
> ------------------------
>
>                 Key: CASSANDRA-7032
>                 URL: https://issues.apache.org/jira/browse/CASSANDRA-7032
>             Project: Cassandra
>          Issue Type: Improvement
>          Components: Core
>            Reporter: Benedict
>            Assignee: Branimir Lambov
>              Labels: performance, vnodes
>             Fix For: 3.x
>
>         Attachments: TestVNodeAllocation.java, TestVNodeAllocation.java, TestVNodeAllocation.java, TestVNodeAllocation.java, TestVNodeAllocation.java, TestVNodeAllocation.java
>
>
> It's been known for a little while that random vnode allocation causes hotspots of ownership. It should be possible to improve dramatically on this with deterministic allocation. I have quickly thrown together a simple greedy algorithm that allocates vnodes efficiently, and will repair hotspots in a randomly allocated cluster gradually as more nodes are added, and also ensures that token ranges are fairly evenly spread between nodes (somewhat tunably so). The allocation still permits slight discrepancies in ownership, but it is bound by the inverse of the size of the cluster (as opposed to random allocation, which strangely gets worse as the cluster size increases). I'm sure there is a decent dynamic programming solution to this that would be even better.
> If on joining the ring a new node were to CAS a shared table where a canonical allocation of token ranges lives after running this (or a similar) algorithm, we could then get guaranteed bounds on the ownership distribution in a cluster. This will also help for CASSANDRA-6696.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)