Difference between Hadoop Map Reduce and Google Map Reduce

Question

What is the difference between Hadoop Map Reduce and Google Map Reduce?

Is it just Hadoop provides standardization for map reduce and others? what else is amongst the diff.

I am not sure if this question is valid for this place. – KKa Jun 25 '15 at 15:05 — KKa, Jun 25 '15 at 15:05

score 23 · Answer 1 · answered Jul 07 '12 at 17:50

23

Google MapReduce and Hadoop are two different implementations (instances) of the MapReduce framework/concept. Hadoop is open source , Google MapReduce is not and actually there are not so many available details about it.

Since they work with large data sets, they have to rely on distributed file systems. Hadoop uses as a standard distributed file system the HDFS (Hadoop Distributed File Systems) while Google MapReduce uses GFS (Google File System)

Hadooop is implemented in java. Google MapReduce seems to be in C++.

answered Jul 07 '12 at 17:50

Razvan

9,925
6
38
51

1

Thanks Razvan.Hadoop Map Reduce is based in Google Map Reduce.So what is new in Hadoop map Reduce than google map reduce? – Monica Shiralkar Jul 07 '12 at 17:53
1

Hadoop is based on a paper of Google years ago. If you want to know how Google MapReduce currently works you have to join Google and look for yourself. – Thomas Jungblut Jul 07 '12 at 17:57
2

I don't think you should approach like this: what's new in Hadoop as compared to Google Map Reduce. Hadoop is an equivalent open source project of Google Map Reduce. And, I don't think it's based on the Google Map Reduce. The creators of Hadoop read the google paper where the Google Map Reduce concepts were presented and they were inspired to create a java open source variant of the (conceptually) same framework. – Razvan Jul 07 '12 at 17:58
1

Most probably it's not written in java. – Razvan Aug 11 '12 at 11:58
Google MapReduce is written in C++ according the [MapReduce: Simplified Data Processing on Large Clusters](http://static.googleusercontent.com/media/research.google.com/fr//archive/mapreduce-osdi04.pdf) – eliasah Aug 23 '14 at 11:28

score 2 · Answer 2 · answered Sep 05 '12 at 02:09

Google has exposed Map Reduce functionality via their BigQuery webservice. It works like Hadoop with Hive (i.e. using a SQL-like language which generates Map Reduce jobs in the background.) An example, using the browser-based query tool for Big Query is shown below. As is typical with Google's release of their technologies as public offerings, internal details are not exposed, nor can you tune or adjust settings. You simply use the API to call the web service and use Google's infrastructure to return the results to your application.

enter image description here

BigQuery is a public instance of Dremel, which uses specialized query engine rather than MapReduce — Yaroslav Bulatov, Sep 08 '12 at 18:08

score 1 · Answer 3 · answered Jan 04 '13 at 09:18

1

you can see the following link for this:

http://www.linuxforu.com/2011/03/mapreduce-more-power-less-code-hadoop/

answered Jan 04 '13 at 09:18

Ashutosh

2,215
14
27

score 0 · Answer 4 · answered Nov 25 '15 at 07:42

0

Check the below link for HDFS VS GFS

https://sensaran.wordpress.com/2015/11/24/gfs-vs-hdfs/

answered Nov 25 '15 at 07:42

Skumar

21
1

2

Links to external resources are encouraged, but please add context around the link so your fellow users will have some idea what it is and why it’s there. Always quote the most relevant part of an important link, in case the target site is unreachable or goes permanently offline. – Milad Faridnia Nov 25 '15 at 07:46

Difference between Hadoop Map Reduce and Google Map Reduce

4 Answers4