[
https://issues.apache.org/jira/browse/CASSANDRA-2388?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13048622#comment-13048622
]
Mck SembWever commented on CASSANDRA-2388:
------------------------------------------
Then (if i understand you correctly) i would need in cassandra.thrift
{noformat}
/** returns alive endpoints, sorted by proximity, that belong in the same
datacenter as the given endpoint */
list<string> get_endpoints_in_same_datacenter(1: string endpoint, 2: required
list<string> endpoints)
throws (1:InvalidRequestException ire)
{noformat}
Then the API becomes quite specific this usecase. Is the performance gain worth
it? What's the cost of each client.describe_datacenter(..) call, and probably
more important what is the lost performance of writing to the furthest node
that's within the same datacenter?
> ColumnFamilyRecordReader fails for a given split because a host is down, even
> if records could reasonably be read from other replica.
> -------------------------------------------------------------------------------------------------------------------------------------
>
> Key: CASSANDRA-2388
> URL: https://issues.apache.org/jira/browse/CASSANDRA-2388
> Project: Cassandra
> Issue Type: Bug
> Components: Hadoop
> Reporter: Eldon Stegall
> Assignee: Mck SembWever
> Labels: hadoop, inputformat
> Fix For: 0.8.1
>
> Attachments: 0002_On_TException_try_next_split.patch,
> CASSANDRA-2388.patch, CASSANDRA-2388.patch
>
>
> ColumnFamilyRecordReader only tries the first location for a given split. We
> should try multiple locations for a given split.
--
This message is automatically generated by JIRA.
For more information on JIRA, see: http://www.atlassian.com/software/jira
