RAgzip: multiple map tasks for a large gzipped file
---------------------------------------------------
Key: HADOOP-4652
URL: https://issues.apache.org/jira/browse/HADOOP-4652
Project: Hadoop Core
Issue Type: Improvement
Components: io, mapred, native
Affects Versions: 0.18.2
Reporter: Daehyun Kim
Currently, the hadoop processes gzipped files with only one map.
We have made a patch that enables multiple map tasks for one large *gzipped*
file. We call the patch RAgzip.
To process multiple map tasks for gzipped file, you may use RAgzip by just
changing InputFormat to RAGZIPInputFormat.
The option used in RAGZIPInputFormat can be found at the javadoc of
RAGZIPInputFormat part.
RAgzip uses zlib's inflatePrime function which supports random access on a
gzipped file.
Since the inflatePrime is supported from the version of 1.2.2.4, it requires
zlib 1.2.2.4 or higher. (We tested on zlib 1.2.3)
RAgzip requires the preprocessing step that creates an access point (.ap) file,
which is like the index of the gzipped file chunks.
The access point(.ap) file is located in same path of the gzipped file.
If there is a "/user/hadoop/test.gz", the .ap file is created with
"/user/hadoop/test.gz.ap".
We made two patches.
1. One makes changes in the source of the hadoop core. This is the main patch.
If the zlib version of the hadoop cluster is greater than 1.2.2.4, you should
use this patch.
2. On the other hand, if there is a computer with zlib version less than
1.2.2.4 in hadoop cluster, you should use the other patch.
This patch uses static link library of the zlib. So if you compile this patch
once at a computer with zlib version greater than 1.2.2.4, RAgzip can be used
in hadoop cluster even if a computer with zlib version less than 1.2.2.4 exists
in the cluster.
As you know, second patch creates jar
file(build/contrib/ragzip/hadoop-x.xx.x-dev-ragzip.jar) as a result of its
installation.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
