Theory and architecture
Analysis of design choices in databases and database management systems. Related subjects include:
- Any subcategory
- Database diversity
- Explicit support for specific data types
- (in Text Technologies) Text search
The refactoring of everything
I’ll start with three observations:
- Computer systems can’t be entirely tightly coupled — nothing would ever get developed or tested.
- Computer systems can’t be entirely loosely coupled — nothing would ever get optimized, in performance and functionality alike.
- In an ongoing trend, there is and will be dramatic refactoring as to which connections wind up being loose or tight.
As written, that’s probably pretty obvious. Even so, it’s easy to forget just how pervasive the refactoring is and is likely to be. Let’s survey some examples first, and then speculate about consequences. Read more
Notes and comments, July 2, 2013
I’m not having a productive week, part of the reason being a hard drive crash that took out early drafts of what were to be last weekend’s blog posts. Now I’m operating from a laptop, rather than my preferred dual-monitor set-up. So please pardon me if I’m concise even by comparison to my usual standards.
- My recent posts based on surveillance news have been partly superseded by – well, by more news. Some of that news, along with some good discussion, may be found in the comment threads.
- The same goes for my recent Hadoop posts.
- The replay for my recent webinar on real-time analytics is now available. My part ran <25 minutes.
- One of my numerous clients using or considering a “real-time analytics” positioning is Sqrrl, the company behind the NoSQL DBMS Accumulo. Last month, Derrick Harris reported on a remarkable Accumulo success story – multiple US intelligence instances managing 10s of petabytes each, and supporting a variety of analytic (I think mainly query/visualization) approaches.
- Several sources have told me that MemSQL’s Zynga sale is (in part) for Membase replacement. This is noteworthy because Zynga was the original pay-for-some-of-the-development Membase customer.
- More generally, the buzz out of Couchbase is distressing. Ex-employees berate the place; job-seekers check around and then decide not to go there; rivals tell me of resumes coming out in droves. Yes, there’s always some of that, even at obviously prospering companies, but this feels like more than the inevitable low-level buzz one hears anywhere.
- I think the predictive modeling state of the art has become:
- Cluster in some way.
- Model separately on each cluster.
- And if you still want to do something that looks like a regression – linear or otherwise – then you might want to use a tool that lets you shovel training data in WITHOUT a whole lot of preparation* and receive a model back out. Even if you don’t accept that as your final model, it can at least be a great guide to feature selection (in the statistical sense of the phrase) and the like.
- Champion/challenger model testing is also a good idea, at least if you’re in some kind of personalization/recommendation space, and have enough traffic to test like that.**
- Most companies have significant turnover after being acquired, perhaps after a “golden handcuff” period. Vertica is no longer an exception.
- Speaking of my clients at HP Vertica – they’ve done a questionable job of communicating that they’re willing to price their product quite reasonably. (But at least they allowed me to write about $2K/terabyte for hardware/software combined.)
- I’m hearing a little more Amazon Redshift buzz than I expected to. Just a little.
- StreamBase was bought by TIBCO. The rumor says $40 million.
*Basic and unavoidable ETL (Extract/Transform/Load) of course excepted.
**I could call that ABC (Always Be Comparing) or ABT (Always Be Testing), but they each sound like – well, like The Glove and the Lions.
Impala and Parquet
I visited Cloudera Friday for, among other things, a chat about Impala with Marcel Kornacker and colleagues. Highlights included:
- Impala is meant to someday be a competitive MPP (Massively Parallel Processing) analytic RDBMS.
- At the moment, it is not one. For example, Impala lacks any meaningful form of workload management or query optimization.
- While Impala will run against any HDFS (Hadoop Distributed File System) file format, claims of strong performance assume that the data is in Parquet …
- … which is the replacement for the short-lived Trevni …
- … and which for most practical purposes is true columnar.
- Impala is also meant to be more than an RDBMS; Parquet and presumably in the future Impala can accommodate nested data structures.
- Just as Impala runs against most or all HDFS file formats, Parquet files can be used by most Hadoop execution engines, and of course by Pig and Hive.
- The Impala roadmap includes workload management, query optimization, data skipping, user-defined functions, hash distribution, two turtledoves, and a partridge in a pear tree.
Data gets into Parquet via batch jobs only — one reason it’s important that Impala run against multiple file formats — but background format conversion is another roadmap item. A single table can be split across multiple formats — e.g., the freshest data could be in HBase, with the rest is in Parquet.
Where things stand in US government surveillance
Edit: Please see the comment thread below for updates. Please also see a follow-on post about how the surveillance data is actually used.
US government surveillance has exploded into public consciousness since last Thursday. With one major exception, the news has just confirmed what was already thought or known. So where do we stand?
My views about domestic data collection start:
- I’ve long believed that the Feds — specifically the NSA (National Security Agency) — are storing metadata/traffic data on every telephone call and email in the US. The recent news, for example Senator Feinstein’s responses to the Verizon disclosure, just confirms it. That the Feds sometimes claim this has to be “foreign” data or they won’t look at it hardly undermines my opinion.
- Even private enterprises can more or less straightforwardly buy information about every credit card purchase we make. So of course the Feds can get that as well, as the Wall Street Journal seems to have noticed. More generally, I’d assume the Feds have all the financial data they want, via the IRS if nothing else.
- Similarly, many kinds of social media postings are aggregated for anybody to purchase, or can be scraped by anybody who invests in the equipment and bandwidth. Attensity’s service is just one example.
- I’m guessing that web use data (http requests, search terms, etc.) is not yet routinely harvested by the US government.* Ditto deanonymization of same. I guess that way basically because I’ve heard few rumblings to the contrary. Further, the consumer psychographic profiles that are so valuable to online retailers might be of little help to national security analysts anyway.
- Video surveillance seems likely to grow, from fixed cameras perhaps to drones; note for example the various officials who called for more public cameras after that Boston Marathon bombing. But for the present discussion, that’s of lesser concern to me, simply because it’s done less secretively than other kinds of surveillance. If there’s a camera that can see us, often we can see it too.
*Recall that these comments are US-specific. Data retention legislation has been proposed or passed in multiple countries to require recording of, among other things, all URL requests, with the stated goal of fighting either digital piracy or child pornography.
As for foreign data: Read more
| Categories: Hadoop, HP and Neoview, Petabyte-scale data management, Pricing, Surveillance and privacy, Telecommunications, Text, Vertica Systems, Web analytics | 10 Comments |
Dave DeWitt responds to Daniel Abadi
A few days ago I posted Daniel Abadi’s thoughts in a discussion of Hadapt, Microsoft PDW (Parallel Data Warehouse)/PolyBase, Pivotal/Greenplum Hawq, and other SQL-Hadoop combinations. This is Dave DeWitt’s response. Emphasis mine.
Read more
| Categories: Benchmarks and POCs, Cloudera, Clustering, Data warehousing, Greenplum, Hadapt, Hadoop, MapReduce, Microsoft and SQL*Server, PostgreSQL, SQL/Hadoop integration | 6 Comments |
SQL-Hadoop architectures compared
The genesis of this post is:
- Dave DeWitt sent me a paper about Microsoft Polybase.
- I argued with Dave about the differences between Polybase and Hadapt.
- I asked Daniel Abadi for his opinion.
- Dan agreed with Dave, in a long email …
- … that he graciously permitted me to lightly-edit and post.
I love my life.
Per Daniel (emphasis mine): Read more
| Categories: Aster Data, Data warehousing, Greenplum, Hadapt, Hadoop, MapReduce, Microsoft and SQL*Server, SQL/Hadoop integration, Theory and architecture | 13 Comments |
WibiData and its Kiji technology
My clients at WibiData:
- Think they’re an application software company …
- … but actually are talking about what I call analytic application subsystems.
- Haven’t announced or shipped any of those either …
- … but will shortly.
- Have meanwhile shipped some cool enabling technology.
- Name their products after sushi restaurants.
Yeah, I like these guys. 🙂
If you’re building an application that “obviously” calls for a NoSQL database, and which has a strong predictive modeling aspect, then WibiData has thought more cleverly about what you need than most vendors I can think of. More precisely, WibiData has thought cleverly about your data management, movement, crunching, serving, and integration. For pure modeling sophistication, you should look elsewhere — but WibiData will gladly integrate with or execute those models for you.
WibiData’s enabling technology, now called Kiji, is a collection of modules, libraries, and so on — think Spring — running over Hadoop/HBase. Except for some newfound modularity, it is much like what I described at the time of WibiData’s launch or what WibiData further disclosed a few months later. Key aspects include:
- A way to define schemas in HBase, including ones that change as rapidly as consumer-interaction applications require.
- An analytic framework called “Produce/Gather”, which can execute at human real-time speeds (via its own execution engine) or with higher throughput in batch mode (by invoking Hadoop MapReduce).
- Enough load capabilities, Hive interaction, and so on to get data into the proper structure in Kiji in the first place.
| Categories: Hadoop, HBase, NoSQL, Open source, Predictive modeling and advanced analytics, WibiData | 5 Comments |
IBM BLU
I had a good chat with IBM about IBM BLU, aka BLU Accelerator or Acceleration. BLU basics start:
- BLU is a part of DB2.
- BLU works like a columnar analytic DBMS.
- If you want to do a join combining BLU and non-BLU tables, all the BLU tables are joined first, and the result set is joined to the other tables by the rest of DB2.
And yes — that means Oracle is now the only major relational DBMS vendor left without a true columnar story.
BLU’s maturity and scalability basics start:
- BLU is coming out in IBM DB2 10.5, this quarter.
- BLU will initially be single-server, but …
- … IBM claims “near-linear” scalability up to 64 cores, and further says that …
- … scale-out for BLU is coming “soon”.
- IBM already thinks all your analytically-oriented DB2 tables should be in BLU.
- IBM describes the first version of BLU as being optimized for 10 TB databases, but capable of handling 20 TB.
BLU technical highlights include: Read more
| Categories: Columnar database management, Data pipelining, Data warehousing, Database compression, IBM and DB2, Workload management | 20 Comments |
Data skipping
Way back in 2006, I wrote about a cool Netezza feature called the zone map, which in essence allows you to do partition elimination even in the absence of strict range partitioning.
Netezza’s substitute for range partitioning is very simple. Netezza features “zone maps,” which note the minimum and maximum of each column value (if such concepts are meaningful) in each extent. This can amount to effective range partitioning over dates; if data is added over time, there’s a good chance that the data in any particular date range is clustered, and a zone map lets you pick out which data falls in the desired data range.
I further wrote
… that seems to be the primary scenario in which zone maps confer a large benefit.
But I now think that part was too pessimistic. For example, in bulk load scenarios, it’s easy to imagine ways in which data can be clustered or skewed. And in such cases, zone maps can let you skip a large fraction of potential I/O.
Over the years I’ve said that other things were reminiscent of Netezza zone maps, e.g. features of Infobright, SenSage, InfiniDB and even Microsoft SQL Server. But truth be told, when I actually use the phrase “zone map”, people usually give me a blank look.
In a recent briefing about BLU, IBM introduced me to a better term — data skipping. I like it and, unless somebody comes up with a good reason not to, I plan to start using it myself. 🙂
| Categories: Data warehousing, IBM and DB2, Netezza, Theory and architecture | 12 Comments |
Some stuff I’m working on
1. I have some posts up on Strategic Messaging. The most recent are overviews of messaging, pricing, and positioning.
2. Numerous vendors are blending SQL and JSON management in their short-request DBMS. It will take some more work for me to have a strong opinion about the merits/demerits of various alternatives.
The default implementation — one example would be Clustrix’s — is to stick the JSON into something like a BLOB/CLOB field (Binary/Character Large Object), index on individual values, and treat those indexes just like any others for the purpose of SQL statements. Drawbacks include:
- You have to store or retrieve the JSON in whole documents at a time.
- If you are spectacularly careless, you could write JOINs with odd results.
IBM DB2 is one recent arrival to the JSON party. Unfortunately, I forgot to ask whether IBM’s JSON implementation was based on IBM DB2 pureXML when I had the chance, and IBM hasn’t gotten around to answering my followup query.
3. Nor has IBM gotten around to answering my followup queries on the subject of BLU, an interesting-sounding columnar option for DB2.
4. Numerous clients have asked me whether they should be active in DBaaS (DataBase as a Service). After all, Amazon, Google, Microsoft, Rackspace and salesforce.com are all in that business in some form, and other big companies have dipped toes in as well. Read more