[
https://issues.apache.org/jira/browse/CASSANDRA-762?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12831306#action_12831306
]
Stu Hood commented on CASSANDRA-762:
------------------------------------
Hmm... I just verified that 'for-0.5-0001...' applies cleanly to the
cassandra-0.5 branch at git revision 4331781362a16e8ea444fdf478c8c63882af7bb3.
There isn't anything related to gossip in that patch.
Also, the patch for trunk applies (with some offsets), and also doesn't contain
anything related to gossip.
> Load balancing does not account for the load of the moving node
> ---------------------------------------------------------------
>
> Key: CASSANDRA-762
> URL: https://issues.apache.org/jira/browse/CASSANDRA-762
> Project: Cassandra
> Issue Type: Bug
> Components: Core
> Affects Versions: 0.5, 0.6
> Reporter: Stu Hood
> Assignee: Stu Hood
> Priority: Minor
> Fix For: 0.5, 0.6
>
> Attachments:
> 0001-Wait-BROADCAST_INTERVAL-for-load-information-and-cal.patch,
> for-0.5-0001-Wait-BROADCAST_INTERVAL-for-load-information-and-cal.patch
>
>
> Given a node A (with load 10 gb) and a node B (with load 20 gb), running the
> loadbalance command against node A will:
> 1. Remove node A from the ring
> * Recalculates pending ranges so that node B is responsible for the entire
> ring
> 2. Pick the most loaded node
> * node B is still reporting 20 gb load, because that is all it has locally
> 3. Choose a token that divides the range of the most loaded node in half
> Since the token calculation doesn't take into account the load that node B is
> 'inheriting' from node A, the token will divide node B's load in half and
> swap the loads. Instead, the token calculation needs to pretend that B has
> already inherited the 10 gb from node A, for a total of 30 gb. The token that
> should be chosen falls at 15 gb of the total load, or 5 gb into node B's load.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
