[
https://issues.apache.org/jira/browse/HIVE-14589?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=15436060#comment-15436060
]
Sergey Shelukhin edited comment on HIVE-14589 at 8/25/16 1:02 AM:
------------------------------------------------------------------
This basically creates the nodes in ZK for "slots" in the cluster. The nodes
try to take the lowest available slot, starting from 0. Unlike worker-...
nodes, the slots are reused, which is the intent. The nodes are always sorted
by the slot number for splits.
The idea is that as long as the node is running, it will retain the same
position in the ordering, regardless of other nodes restarting, without knowing
about each other, the predecessors location (if restarted in a different
place), or the total count of nodes in the cluster.
The restarting nodes may not take the same positions as their predecessors
(i.e. if two nodes restart they can swap slots) but it shouldn't matter because
they have lost their cache anyway.
I.e. if you have nodes 1-2-3-4 and I nuke and restart 1, 2, and 4, they will
take whatever spots, but 3 will stay the 3rd and retain cache locality.
One case it doesn't handle is permanent cluster size reduction. There will be a
permanent gap if nodes are removed that have the slots in the middle; until
some nodes restart, it will result in misses.
was (Author: sershe):
This basically creates the nodes in ZK for "slots" in the cluster. The nodes
try to take the lowest available slot, starting from 0. Unlike worker-...
nodes, the slots are reused, which is the intent. The nodes are always sort by
the slot number for splits.
The idea is that as long as the node is running, it will retain the same
position in the ordering, regardless of other nodes restarting, without knowing
about each other, their predecessors location, or the total count of nodes in
the cluster.
The restarting nodes may not take the same positions as their predecessors
(i.e. if two nodes restart they can swap slots) but it doesn't matter as much
because they have lost their cache anyway.
I.e. if you have nodes 1-2-3-4 and I nuke and restart 1, 2, and 4, they will
take whatever spots, but 3 will stay 3rd and retain cache locality.
One case it doesn't handle is permanent cluster size reduction. There will be a
permanent gap if nodes are removed that have the slots in the middle; until
some nodes restart, it will result in misses.
> add consistent node replacement to LLAP for splits
> --------------------------------------------------
>
> Key: HIVE-14589
> URL: https://issues.apache.org/jira/browse/HIVE-14589
> Project: Hive
> Issue Type: Bug
> Reporter: Sergey Shelukhin
> Assignee: Sergey Shelukhin
> Attachments: HIVE-14589.01.patch, HIVE-14589.patch
>
>
> See HIVE-14574
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
