Skip to main content

Approaches to integrating Hadoop and a standard RDBMS Part 1

The next few blogs will try to evaluate the different approaches to integrating Hadoop and a standard RDBMS… so the first thing I’ll try in this post is to suggest a criteria based on some architectural  choices for making the evaluation. Further, I’ll inject a little surprise and make the point by using the criteria to say something about a product that is not an integration of an RDBMS and Hadoop.

For the purposes of this let me clear that by “Hadoop” I mean at least HDFS plus MapReduce… so I will discuss integrating a parallel RDBMS with data stored in HDFS: a massively parallel file system with a programming capability included. By “integration” I mean that queries using the full set of SQL supported by the RDBMS must be available for processing queries that refer to data across the Hadoop-RDBMS divide.

Since we’ve assumed that all SQL functionality is supported the architectural issue left to solve is performance and this issue revolves on one topic: how do we minimize the cost of moving data between the two partners for a given query?

Now to get on with it…
The easiest, but not all that easy, problem involves using parallelism to move data from one system to the other… so the first criteria we will evaluate for each product will consider how parallel is their movement of data.

The next criteria involves intelligence in the RDBMS to push down some execution operators to the data layer. Of course the RDBMS must scan remote data… so in this part of the evaluation we will grade each product’s ability to push processing down to apply predicates and project the minimal amount of data up to the RDBMS.

Finally, a most intelligent product would push more than just predicates down… it would push down joins and aggregation… and the decisions around splitting processing would be fully optimized. A most intelligent product would fully federate the HDFS data into the RDBMS.
So there you have it… I will start evaluating RDBMS-Hadoop architecture by three criteria:
  • how parallel is the data movement between the RDBMS and Hadoop;
  • is there intelligence to minimize data movement by pushing the least data and the associated query plan to one system or another… this requires parallel pipes in both directions; and
  • is there intelligence to build an optimal query plan that splits steps across both systems to completely minimize the movement of data and/or optimize the compute.
And a final word on the relative strength of each criteria:
  • If we imagine a 10-node Hadoop cluster talking to a 10-node RDBMS with 10 parallel pipes and compared it to the same setup with only 1 pipe (not parallel) then we might suggest that the parallel pipes provide a 10X performance increase.
  • If we imagine intelligence that moved 100K rows rather than 10M then we might suggest that intelligent push down might provide a 100X performance increase…
  • If we had even more intelligence and further optimized processing then another 10X-100X might be possible.
So all three criteria are not equal… intelligent query planning trumps wide pipes…
Now for the surprise… in the next blog we’ll look at how Exadata’s architecture maps to these criteria… since it is a two-tiered architecture with an RDBMS tied to a parallel file system… to be continued...

Comments

Post a Comment

Popular posts from this blog

Python and Parquet Performance

In Pandas, PyArrow, fastparquet, AWS Data Wrangler, PySpark and Dask. This post outlines how to use all common Python libraries to read and write Parquet format while taking advantage of  columnar storage ,  columnar compression  and  data partitioning . Used together, these three optimizations can dramatically accelerate I/O for your Python applications compared to CSV, JSON, HDF or other row-based formats. Parquet makes applications possible that are simply impossible using a text format like JSON or CSV. Introduction I have recently gotten more familiar with how to work with  Parquet  datasets across the six major tools used to read and write from Parquet in the Python ecosystem:  Pandas ,  PyArrow ,  fastparquet ,  AWS Data Wrangler ,  PySpark  and  Dask . My work of late in algorithmic trading involves switching between these tools a lot and as I said I often mix up the APIs. I use Pandas and PyArrow for in-RAM comput...
Post a Comment
Read more

Design of Large-Scale Services on Cloud Services PART 2

Decompose the Application by Workload Applications are typically composed of multiple workloads. Different workloads can, and often do, have different requirements, different levels of criticality to the business, and different levels of financial consideration associated with them. By decomposing an application into workloads, an organization provides itself with valuable flexibility. A workload-centric approach provides better controls over costs, more flexibility in choosing technologies best suited to the workload, workload specific approaches to availability and security, flexibility and agility in adding and deploying new capabilities, etc. Scenarios When thinking about resiliency, it’s sometimes helpful to do so in the context of scenarios. The following are examples of typical scenarios: Scenario 1 – Sports Data Service  A customer provides a data service that provides sports information. The service has two primary workloads. The first provides statistics for th...
Post a Comment
Read more

How to construct a File System that lives in Shared Memory.

Shared Memory File System Goals 1. MOUNTED IN SHARED MEMORY The result is a very fast, real time file system. We use Shared Memory so that the file system is public and not private. 2. PERSISTS TO DISK When the file system is unmounted, what happens to it? We need to be able to save the file system so that a system reboot does not destroy it. A great way to achieve this is to save the file system to disk. 3. EXTENSIBLE IN PLACE We want to be able to grow the file system in place. 4. SUPPORTS CONCURRENCY We want multiple users to be able to access the file system at the same time. In fact, we want multiple users to be able to access the same file at the same time. With the goals now in mind we can now talk about the major design issues: FAT File System & Design Issues The  FAT File System  has been around for quite some time. Basically it provides a pretty good file structure. But I have two problems with it: 1. FAT IS NOT EXTENSIBLE IN PLAC...
Post a Comment
Read more