[ https://issues.apache.org/jira/browse/HBASE-6032?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13478252#comment-13478252 ]
Lars Hofhansl commented on HBASE-6032: -------------------------------------- I ran the relevant tests. And also used with some other test cases I have. (The set was with a local HDFS, so I didn't observe any performance benefits) > Port HFileBlockIndex improvement from HBASE-5987 > ------------------------------------------------ > > Key: HBASE-6032 > URL: https://issues.apache.org/jira/browse/HBASE-6032 > Project: HBase > Issue Type: Task > Reporter: Ted Yu > Assignee: Ted Yu > Fix For: 0.96.0 > > Attachments: 6032.094.txt, 6032-ports-5987.txt, > 6032-ports-5987-v2.txt, 6032v3.txt > > > Excerpt from HBASE-5987: > First, we propose to lookahead for one more block index so that the > HFileScanner would know the start key value of next data block. So if the > target key value for the scan(reSeekTo) is "smaller" than that start kv of > next data block, it means the target key value has a very high possibility in > the current data block (if not in current data block, then the start kv of > next data block should be returned. +Indexing on the start key has some > defects here+) and it shall NOT query the HFileBlockIndex in this case. On > the contrary, if the target key value is "bigger", then it shall query the > HFileBlockIndex. This improvement shall help to reduce the hotness of > HFileBlockIndex and avoid some unnecessary IdLock Contention or Index Block > Cache lookup. > This JIRA is to port the fix to HBase trunk, etc. -- This message is automatically generated by JIRA. If you think it was sent incorrectly, please contact your JIRA administrators For more information on JIRA, see: http://www.atlassian.com/software/jira