hadoop-hdfs-issues mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hairong Kuang (JIRA)" <j...@apache.org>
Subject [jira] Updated: (HDFS-1068) Reduce getFileInfo's impact on GC by avoiding the creation of HdfsFileStatus for each RPC call
Date Thu, 25 Mar 2010 19:20:27 GMT

     [ https://issues.apache.org/jira/browse/HDFS-1068?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel
]

Hairong Kuang updated HDFS-1068:
--------------------------------

      Component/s: name-node
      Description: In our production clusters, getFileInfo is the most frequent operation
that hit NameNode, and its frequency is highly correlated to the GC behavior. HDFS-946 has
already reduced the amount of heap/cpu and the number of temporary objects for each getFileInfo
call. Yet another improvement is to avoid creation of a HdfsFileStatus object for each getFileInfo
call. Instead each RPC handler can have a thread local HdfsFileStatus object. Each getFileInfo
call simply sets values for all fields of the thread local HdfsFileStatus object. 
    Fix Version/s: 0.22.0
         Assignee: Hairong Kuang
          Summary: Reduce getFileInfo's impact on GC by avoiding the creation of HdfsFileStatus
for each RPC call  (was: Reduce get)

> Reduce getFileInfo's impact on GC by avoiding the creation of HdfsFileStatus for each
RPC call
> ----------------------------------------------------------------------------------------------
>
>                 Key: HDFS-1068
>                 URL: https://issues.apache.org/jira/browse/HDFS-1068
>             Project: Hadoop HDFS
>          Issue Type: Improvement
>          Components: name-node
>            Reporter: Hairong Kuang
>            Assignee: Hairong Kuang
>             Fix For: 0.22.0
>
>
> In our production clusters, getFileInfo is the most frequent operation that hit NameNode,
and its frequency is highly correlated to the GC behavior. HDFS-946 has already reduced the
amount of heap/cpu and the number of temporary objects for each getFileInfo call. Yet another
improvement is to avoid creation of a HdfsFileStatus object for each getFileInfo call. Instead
each RPC handler can have a thread local HdfsFileStatus object. Each getFileInfo call simply
sets values for all fields of the thread local HdfsFileStatus object. 

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.


Mime
View raw message