In parallel with my master’s thesis, I have, with the help of a few other people, written a paper for the ACM Symposium On Cloud Computing. The paper describe the methodology, infrastructure and configuration used as well as the results obtained for Cassandra, HBase and mongoDB. It can be downloaded here. The goal of this [...]
As I updated my benchmark to work with a more up to date HBase version, I thought that I had to do the same for the other databases if I wanted to be fair. Moreover I had some problems with the Cassandra implementation of MapReduce on the 0.6.10 version (you can read this post to [...]
As I promised in a previous post, this one will explain how I configured HBase 0.90.0 for the last tests and a few observations about my experience with MapReduce on this HBase version. First on the configuration side there are a few modifications worth noticing : I have increased the memory allowed to HBase to [...]
The first results I published were not in favor of HBase, the performances for both read/update and MapReduce were decreasing with the size of the cluster and were very instable. I spent a lot of time trying to figure out what was the problem and I think I finally have found what could be the [...]
This post explains how I have configured Hadoop and HBase as well as how I store data inside HBase. Please also read this post. To run an HBase cluster you first have to configure the underlying Hadoop HDF that will store the data. The configuration files can be downloaded here. Those are the configuration file [...]
Benchmark are the kind of test that always create discussions because there is often at least one of the tested software that could have been configured in a better way or used in a better environment. Another thing that creates a lot of discussion is the fact that a benchmark (especially very simple ones like [...]
A few people asked me to add support for an easiest way to build the benchmark, this is now the case. Instead of having to download yourself all the dependencies and set them up in Eclipse, Maven will now do all the work for you. Concretely, if you want to test the benchmark all you [...]
As promised when I did my presentation at FOSDEM 2011, here is the code of my simple benchmark inspired by Wikipedia. The code is hosted at github : https://github.com/toflames/Wikipedia-noSQL-Benchmark You can now build this project using Maven. As a few dependencies where not available in any maven repository, I have decided to provide them myself [...]
This post is the second part of this previous post, so please start with this one. If you have already read the first post, this one will be about the details and my experiences with the various MapReduce implementations. The first working implementation was the mongoDB one. There is not much to tell about it as [...]
After my presentation in the Data Analytics devroom at the FOSDEM this year, I felt that I needed to complete the information that I have provided there. This post will try to explain in more details my methodology and the results. But before I start, I would like to say that all of this benchmark [...]