[
https://issues.apache.org/jira/browse/HDFS-7174?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14156839#comment-14156839
]
Haohui Mai commented on HDFS-7174:
----------------------------------
I wonder, is it worthwhile to try to store the inodeid as an {{long[]}}
directly? I suspect the performance issues can be related to cache-related
issues.
As a reference, for c++ on modern machines inserting elements in
{{std::vector}} is consistently faster than {{std::list}}
http://channel9.msdn.com/Events/Build/2014/2-661
> Support for more efficient large directories
> --------------------------------------------
>
> Key: HDFS-7174
> URL: https://issues.apache.org/jira/browse/HDFS-7174
> Project: Hadoop HDFS
> Issue Type: Improvement
> Reporter: Kihwal Lee
> Assignee: Kihwal Lee
> Priority: Critical
> Attachments: HDFS-7174.new.patch, HDFS-7174.patch, HDFS-7174.patch
>
>
> When the number of children under a directory grows very large, insertion
> becomes very costly. E.g. creating 1M entries takes 10s of minutes. This is
> because the complexity of an insertion is O\(n\). As the size of a list
> grows, the overhead grows n^2. (integral of linear function). It also causes
> allocations and copies of big arrays.
--
This message was sent by Atlassian JIRA
(v6.3.4#6332)
