[
https://issues.apache.org/jira/browse/HBASE-9969?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13946197#comment-13946197
]
Lars Hofhansl commented on HBASE-9969:
--------------------------------------
Then again, the snippet above does that already. Specifically:
{code}
this.comparator.compare(kvNext, topScanner.peek()) >= 0
{code}
is true only when we have exhausted the current scanner. Not sure why I missed
it, especially since it was subject to discussion above.
So upon next we only do a single comparison if the next KV comes from the same
scanner (and with HBASE-10805 we're doing no comparison if only a single
scanner is left), only when that is not the case do we put the scanner back
into the heap.
At least this warrants a comment in the code I think.
I still want to implement this. It's possible that we will see no benefit from
it, though.
> Improve KeyValueHeap using loser tree
> -------------------------------------
>
> Key: HBASE-9969
> URL: https://issues.apache.org/jira/browse/HBASE-9969
> Project: HBase
> Issue Type: Improvement
> Components: Performance, regionserver
> Reporter: Chao Shi
> Assignee: Chao Shi
> Fix For: 0.99.0
>
> Attachments: 9969-0.94.txt, KeyValueHeapBenchmark_v1.ods,
> KeyValueHeapBenchmark_v2.ods, hbase-9969-pq-v1.patch, hbase-9969-pq-v2.patch,
> hbase-9969-v2.patch, hbase-9969-v3.patch, hbase-9969.patch, hbase-9969.patch,
> kvheap-benchmark.png, kvheap-benchmark.txt
>
>
> LoserTree is the better data structure than binary heap. It saves half of the
> comparisons on each next(), though the time complexity is on O(logN).
> Currently A scan or get will go through two KeyValueHeaps, one is merging KVs
> read from multiple HFiles in a single store, the other is merging results
> from multiple stores. This patch should improve the both cases whenever CPU
> is the bottleneck (e.g. scan with filter over cached blocks, HBASE-9811).
> All of the optimization work is done in KeyValueHeap and does not change its
> public interfaces. The new code looks more cleaner and simpler to understand.
--
This message was sent by Atlassian JIRA
(v6.2#6252)
