[jira] [Commented] (HDFS-9053) Support large directories efficiently using B-Tree

["Yi Liu (JIRA)" <ji...@apache.org>]

    [ https://issues.apache.org/jira/browse/HDFS-9053?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14939144#comment-14939144 ] 

Yi Liu commented on HDFS-9053:
------------------------------

{quote}
the new class Node is. There is a "this" reference to the outer class.
{quote}
Good point, Nicholas, I have missed that. I just checked it in the memory layout after you pointed out.
{noformat}
org.apache.hadoop.util.BTree.Node object internals:
 OFFSET  SIZE     TYPE DESCRIPTION                    VALUE
      0    16          (object header)                N/A
     16     4      int Node.elementsSize              N/A
     20     4      int Node.childrenSize              N/A
     24     8 Object[] Node.elements                  N/A
     32     8 Object[] Node.children                  N/A
     40     8    BTree Node.this$0                    N/A
Instance size: 48 bytes (estimated, the sample instance is not available)
{noformat}

Let me change the B-Tree Node class to static, then we can save the reference to outer class. Will update the patch later.

> Support large directories efficiently using B-Tree
> --------------------------------------------------
>
>                 Key: HDFS-9053
>                 URL: https://issues.apache.org/jira/browse/HDFS-9053
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: namenode
>            Reporter: Yi Liu
>            Assignee: Yi Liu
>            Priority: Critical
>         Attachments: HDFS-9053 (BTree with simple benchmark).patch, HDFS-9053 (BTree).patch, HDFS-9053.001.patch, HDFS-9053.002.patch, HDFS-9053.003.patch
>
>
> This is a long standing issue, we were trying to improve this in the past.  Currently we use an ArrayList for the children under a directory, and the children are ordered in the list, for insert/delete, the time complexity is O\(n), (the search is O(log n), but insertion/deleting causes re-allocations and copies of arrays), for large directory, the operations are expensive.  If the children grow to 1M size, the ArrayList will resize to > 1M capacity, so need > 1M * 8bytes = 8M (the reference size is 8 for 64-bits system/JVM) continuous heap memory, it easily causes full GC in HDFS cluster where namenode heap memory is already highly used.  I recap the 3 main issues:
> # Insertion/deletion operations in large directories are expensive because re-allocations and copies of big arrays.
> # Dynamically allocate several MB continuous heap memory which will be long-lived can easily cause full GC problem.
> # Even most children are removed later, but the directory INode still occupies same size heap memory, since the ArrayList will never shrink.
> This JIRA is similar to HDFS-7174 created by [~kihwal], but use B-Tree to solve the problem suggested by [~shv]. 
> So the target of this JIRA is to implement a low memory footprint B-Tree and use it to replace ArrayList. 
> If the elements size is not large (less than the maximum degree of B-Tree node), the B-Tree only has one root node which contains an array for the elements. And if the size grows large enough, it will split automatically, and if elements are removed, then B-Tree nodes can merge automatically (see more: https://en.wikipedia.org/wiki/B-tree).  It will solve the above 3 issues.



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)