Recently Cloudera announces new storage engine for fast analytics and fast data called Kudu. This is a very interesting piece of code and I couldn’t withstand an attraction of analyzing this technology deeper and going beyond the marketing.
The faster your data warehousing solution runs, the higher would be the business demand related to the speed of new data availability in their reports. Over the last time I’ve seen a number of attempts to build up a cool thing called “online DWH” – a data warehouse that is almost in sync with data sources and has its data marts and reports dynamically updated as new data flows into it. This is a very great and powerful thing, but unfortunately its implementation is not as straightforward as the business wants it to be.
This is my second article about Apache Spark architecture and today I will be more specific and tell you about the shuffle, one of the most interesting topics in the overall Spark design. The previous part was mostly about general Spark architecture and its memory management. It can be accessed here. The next one is about Spark memory management and it is available here.
What is the shuffle in general? Imagine that you have a list of phone call detail records in a table and you want to calculate amount of calls happened each day. This way you would set the “day” as your key, and for each record (i.e. for each call) you would emit “1” as a value. After this you would sum up values for each key, which would be an answer to your question – total amount of records for each day. But when you store the data across the cluster, how can you sum up the values for the same key stored on different machines? The only way to do so is to make all the values for the same key be on the same machine, after this you would be able to sum them up.
Recently Databricks announced availability of DataFrames in Spark , which gives you a great opportunity to write even simpler code that would execute faster, especially if you are heavy Python/R user. In this article I would go a bit deeper than the publicly available benchmark results to show you how it really works.
When you are completely ready to start your “big data” initiative with Hadoop, one of your first questions would be related to the cluster sizing. What is the right hardware to choose in terms of price/performance? How much hardware you need to handle your data and your workload? I will do my best to answer these questions in my article.
Hadoop is known to be an ideal engine for processing unstructured data. But wait, what do you really mean by “unstructured data”? Can anything be considered as a “data” if it does not have a structure? Let’s start by taking a look at the historical brief.