[
https://issues.apache.org/jira/browse/HBASE-2663?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12893359#action_12893359
]
ryan rawson commented on HBASE-2663:
------------------------------------
So there is another thing here, by deferring the evictions to the
background thread you increase the chance that the block will be
tenured then it must be collected from CMS space, thus radically
increasing the GC complexity of the cache. Originally when the LRU
block cache came in, it made my collections 10x as slow until I
disabled the block cache for compactions.
Unfortunately all these micro-optimizations might be falling under the
GC wayside.
> LRU cache makes needless datastructure copies during eviction
> -------------------------------------------------------------
>
> Key: HBASE-2663
> URL: https://issues.apache.org/jira/browse/HBASE-2663
> Project: HBase
> Issue Type: Improvement
> Components: regionserver
> Reporter: Todd Lipcon
>
> Was browsing the LRU eviction code and came upon some very inefficient code.
> When we do eviction, BlockBucket.free() calls queue.get() which first inserts
> everything from the PriorityQueue<Block> into a LinkedList, then copies that
> entire linked list into an array. We then iterate over usually just a small
> percentage of the array to free some blocks until we have freed the requested
> amount.
> We ought to be able to just pull items out of the PriorityQueue directly and
> avoid all the churn.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
