[
https://issues.apache.org/jira/browse/HDFS-9053?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14950498#comment-14950498
]
Yi Liu edited comment on HDFS-9053 at 10/9/15 2:51 PM:
-------------------------------------------------------
I find a good approach to improve B-Tree memory overhead to make it only
increase *8 bytes* memory usage comparing with using {{ArrayList}} for small
elements size.
So we don't need to use ArrayList when #children is small (< 4K), and we can
always use the {{BTree}}.
The main idea is to let {{BTree}} extend the BTree Node, then we don't need a
separate root node, since {{BTree}} itself is the root.
{noformat}
java.util.ArrayList object internals:
OFFSET SIZE TYPE DESCRIPTION VALUE
0 16 (object header) N/A
16 4 int AbstractList.modCount N/A
20 4 (alignment/padding gap) N/A
24 4 int ArrayList.size N/A
28 4 (alignment/padding gap) N/A
32 8 Object[] ArrayList.elementData N/A
Instance size: 40 bytes (estimated, the sample instance is not available)
{noformat}
{noformat}
org.apache.hadoop.util.btree.BTree 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 4 int BTree.size N/A
44 4 int BTree.modCount N/A
Instance size: 48 bytes (estimated, the sample instance is not available)
{noformat}
We can see {{BTree}} only increases *8 bytes* comparing with {{ArrayList}} for
a {{INodeDirectory}}.
[~jingzhao], [~szetszwo], please look at the new patch {{006}}.
was (Author: hitliuyi):
I find a good approach to improve B-Tree overhead to make it only increase *8
bytes* memory usage comparing with using {{ArrayList}} for small elements size.
So we don't need to use ArrayList when #children is small (< 4K), and we can
always use the {{BTree}}.
The main idea is to let {{BTree}} extend the BTree Node, then we don't need a
separate root node, since {{BTree}} itself is the root.
{noformat}
java.util.ArrayList object internals:
OFFSET SIZE TYPE DESCRIPTION VALUE
0 16 (object header) N/A
16 4 int AbstractList.modCount N/A
20 4 (alignment/padding gap) N/A
24 4 int ArrayList.size N/A
28 4 (alignment/padding gap) N/A
32 8 Object[] ArrayList.elementData N/A
Instance size: 40 bytes (estimated, the sample instance is not available)
{noformat}
{noformat}
org.apache.hadoop.util.btree.BTree 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 4 int BTree.size N/A
44 4 int BTree.modCount N/A
Instance size: 48 bytes (estimated, the sample instance is not available)
{noformat}
We can see {{BTree}} only increases *8 bytes* comparing with {{ArrayList}} for
a {{INodeDirectory}}.
[~jingzhao], [~szetszwo], please look at the new patch {{006}}.
> 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,
> HDFS-9053.004.patch, HDFS-9053.005.patch, HDFS-9053.006.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)
