[
https://issues.apache.org/jira/browse/HBASE-10993?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13973786#comment-13973786
]
Matteo Bertozzi commented on HBASE-10993:
-----------------------------------------
{quote}Why call getPriority rather than add this new getDeadline call?{quote}
At the moment we have 3 queues, HIGH_QOS (Meta Requests), REPLICATION_QOS,
NORMAL_QOS (all the user requests). Currently getPriority() means more "get
request type" and is used to select the queue.
getDeadline() instead defines how urgent is the request among the requests in
the same queue, and given the fact that we can recognize long scans we can
automatically deprioritize them.
{quote}How we know if it is working – or how you think we will be able to
observe that it is operating well on a cluster?{quote}
The unittest with the cumulative sum shows how the priority queue/deadline
works. A live test is having a large table and a couple of full table scan
together with get/puts. NOTE that if you have less clients (small requests)
than handlers you'll not see any difference.
> Deprioritize long-running scanners
> ----------------------------------
>
> Key: HBASE-10993
> URL: https://issues.apache.org/jira/browse/HBASE-10993
> Project: HBase
> Issue Type: Sub-task
> Reporter: Matteo Bertozzi
> Assignee: Matteo Bertozzi
> Priority: Minor
> Fix For: 1.0.0
>
> Attachments: HBASE-10993-v0.patch, HBASE-10993-v1.patch
>
>
> Currently we have a single call queue that serves all the "normal user"
> requests, and the requests are executed in FIFO.
> When running map-reduce jobs and user-queries on the same machine, we want to
> prioritize the user-queries.
> Without changing too much code, and not having the user giving hints, we can
> add a “vtime” field to the scanner, to keep track from how long is running.
> And we can replace the callQueue with a priorityQueue. In this way we can
> deprioritize long-running scans, the longer a scan request lives the less
> priority it gets.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
