[ https://issues.apache.org/jira/browse/CASSANDRA-2388?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13057392#comment-13057392 ]
Brandon Williams edited comment on CASSANDRA-2388 at 6/29/11 6:41 PM: ---------------------------------------------------------------------- {quote} This does happen already (i've seen it while testing initial patches that were no good). Problem is that the TT is blacklisted, reducing hadoop's throughput for all jobs running. {quote} If the cassandra node where the TT resides isn't working, then throughput is reduced regardless. bq. I bet too that a fallback to a replica is faster than a fallback to another TT. I doubt that for any significant job. Locality is important. Move the job to the data, not the data to the job. {quote} There is no guarantee that any given TT will have its split accessible via a local c* node - this is only a preference in CFRR. A failed task may just as likely go to a random c* node. At least now we can actually properly limit to the one DC and sort by proximity. {quote} This sounds like the thing we need to fix, then. Ensuring that the TT assigned to the map has a local replica. was (Author: brandon.williams): {quote} This does happen already (i've seen it while testing initial patches that were no good). Problem is that the TT is blacklisted, reducing hadoop's throughput for all jobs running. {quote} If the cassandra node where the TT resides isn't working, then throughput is reduced regardless. bq. I bet too that a fallback to a replica is faster than a fallback to another TT. I doubt that for any significant job. Locality is important. {quote} There is no guarantee that any given TT will have its split accessible via a local c* node - this is only a preference in CFRR. A failed task may just as likely go to a random c* node. At least now we can actually properly limit to the one DC and sort by proximity. {quote} This sounds like the thing we need to fix, then. Ensuring that the TT assigned to the map has a local replica. > 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 > Affects Versions: 0.7.6, 0.8.0 > Reporter: Eldon Stegall > Assignee: Jeremy Hanna > Labels: hadoop, inputformat > Fix For: 0.7.7, 0.8.2 > > Attachments: 0002_On_TException_try_next_split.patch, > CASSANDRA-2388-addition1.patch, CASSANDRA-2388.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