Analysis of memory-centric OLTP DBMS. Related subjects include:
I frequently am asked questions that boil down to:
- When should one use NoSQL?
- When should one use a new SQL product (NewSQL or otherwise)?
- When should one use a traditional RDBMS (most likely Oracle, DB2, or SQL Server)?
The details vary with context — e.g. sometimes MySQL is a traditional RDBMS and sometimes it is a new kid — but the general class of questions keeps coming. And that’s just for short-request use cases; similar questions for analytic systems arise even more often.
My general answers start:
- Sometimes something isn’t broken, and doesn’t need fixing.
- Sometimes something is broken, and still doesn’t need fixing. Legacy decisions that you now regret may not be worth the trouble to change.
- Sometimes — especially but not only at smaller enterprises — choices are made for you. If you operate on SaaS, plus perhaps some generic web hosting technology, the whole DBMS discussion may be moot.
In particular, migration away from legacy DBMS raises many issues: Read more
|Categories: Columnar database management, Couchbase, HBase, In-memory DBMS, Microsoft and SQL*Server, NewSQL, NoSQL, OLTP, Oracle, Parallelization, SAP AG||17 Comments|
Memory-centric data management is confusing. And so I’m going to clarify a couple of things about MemSQL 3.0 even though I don’t yet have a lot of details.* They are:
- MemSQL has historically been an in-memory row store, which as of last year scales out.
- It turns out that the MemSQL row store actually has two table types. One is scaled out. The other — called “reference” — is replicated on every node.
- MemSQL has now added a third table type, which is columnar and which resides in flash memory.
- If you want to keep data in, for example, both the scale-out row store and the column store, you’d have to copy/replicate it within MemSQL. And if you wanted to access data from both versions at once (e.g. because different copies cover different time periods), you’d likely have to do a UNION or something like that.
*MemSQL’s first columnar offering sounds pretty basic; for example, there’s no columnar compression yet. (Edit: Oops, that’s not accurate. See comment below.) But at least they actually have one, which puts them ahead of many other row-based RDBMS vendors that come to mind.
And to hammer home the contrast:
- IBM, Oracle and Microsoft, which all sell row-based DBMS meant to run on disk or other persistent storage, have added or will add columnar options that run in RAM.
- MemSQL, which sells a row-based DBMS that runs in RAM, has added a columnar option that runs in persistent solid-state storage.
|Categories: Columnar database management, Database compression, In-memory DBMS, MemSQL, Solid-state memory||12 Comments|
I first wrote about in-memory data management a decade ago. But I long declined to use that term — because there’s almost always a persistence story outside of RAM — and coined “memory-centric” as an alternative. Then I relented 1 1/2 years ago, and defined in-memory DBMS as
DBMS designed under the assumption that substantially all database operations will be performed in RAM (Random Access Memory)
By way of contrast:
Hybrid memory-centric DBMS is our term for a DBMS that has two modes:
- Querying and updating (or loading into) persistent storage.
These definitions, while a bit rough, seem to fit most cases. One awkward exception is Aerospike, which assumes semiconductor memory, but is happy to persist onto flash (just not spinning disk). Another is Kognitio, which is definitely lying when it claims its product was in-memory all along, but may or may not have redesigned its technology over the decades to have become more purely in-memory. (But if they have, what happened to all the previous disk-based users??)
Two other sources of confusion are:
- The broad variety of memory-centric data management approaches.
- The over-enthusiastic marketing of SAP HANA.
With all that said, here’s a little update on in-memory data management and related subjects.
- I maintain my opinion that traditional databases will eventually wind up in RAM.
- At conventional large enterprises — as opposed to for example pure internet companies — production deployments of HANA are probably comparable in number and investment to production deployments of Hadoop. (I’m sorry, but much of my supporting information for that is confidential.)
- Cloudera is emphatically backing Spark. And a key aspect of Spark is that, unlike most of Hadoop, it’s memory-centric.
- It has become common for disk-based DBMS to persist data through a “log-structured” architecture. That’s a whole lot like what you do for persistence in a fundamentally in-memory system.
- I’m also sensing increasing comfort with the strategy of committing writes as soon as they’ve been acknowledged by two or more nodes in RAM.
- I’ve never heard a story about an in-memory DBMS actually losing data. It’s surely happened, but evidently not often.
|Categories: Aerospike, Cloudera, Clustering, Databricks, Spark and BDAS, Hadoop, In-memory DBMS, Kognitio, Market share and customer counts, Memory-centric data management, SAP AG, Theory and architecture||13 Comments|
The 2013 Gartner Magic Quadrant for Operational Database Management Systems is out. “Operational” seems to be Gartner’s term for what I call short-request, in each case the point being that OLTP (OnLine Transaction Processing) is a dubious term when systems omit strict consistency, and when even strictly consistent systems may lack full transactional semantics. As is usually the case with Gartner Magic Quadrants:
- I admire the raw research.
- The opinions contained are generally reasonable (especially since Merv Adrian joined the Gartner team).
- Some of the details are questionable.
- There’s generally an excessive focus on Gartner’s perception of vendors’ business skills, and on vendors’ willingness to parrot all the buzzphrases Gartner wants to hear.
- The trends Gartner highlights are similar to those I see, although our emphasis may be different, and they may leave some important ones out. (Big omission — support for lightweight analytics integrated into operational applications, one of the more genuine forms of real-time analytics.)
Anyhow: Read more
Some subjects just keep coming up. And so I keep saying things like:
Most generalizations about “Big Data” are false. “Big Data” is a horrific catch-all term, with many different meanings.
Most generalizations about Hadoop are false. Reasons include:
- Hadoop is a collection of disparate things, most particularly data storage and application execution systems.
- The transition from Hadoop 1 to Hadoop 2 will be drastic.
- For key aspects of Hadoop — especially file format and execution engine — there are or will be widely varied options.
Hadoop won’t soon replace relational data warehouses, if indeed it ever does. SQL-on-Hadoop is still very immature. And you can’t replace data warehouses unless you have the power of SQL.
Note: SQL isn’t the only way to provide “the power of SQL”, but alternative approaches are just as immature.
Most generalizations about NoSQL are false. Different NoSQL products are … different. It’s not even accurate to say that all NoSQL systems lack SQL interfaces. (For example, SQL-on-Hadoop often includes SQL-on-HBase.)
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
I’m doing a webinar Wednesday, June 26, at 1 pm EST/10 am PST called:
Real-Time Analytics in the Real World
The sponsor is MemSQL, one of my numerous clients to have recently adopted some version of a “real-time analytics” positioning. The webinar sign-up form has an abstract that I reviewed and approved … albeit before I started actually outlining the talk.
Our plan is:
- I’ll review the multiple technologies and use cases that various companies call “real-time analytics”. I’m not planning for this part to be at all MemSQL-focused.*
- MemSQL will review some specific use cases they feel their product — memory-centric scale-out RDBMS — has proven it supports.
*MemSQL is debuting pretty high in my rankings of content sponsors who are cool with vendor neutrality. I sent them a draft of my slides mentioning other tech vendors and not them, and they didn’t blink.
In other news, I’ll be in California over the next week. Mainly I’ll be visiting clients — and 2 non-clients and some family — 10:00 am through dinner, but I did set aside time to stop by GigaOm Structure on Wednesday. I have sniffles/cough/other stuff even before I go. So please don’t expect a lot of posts until I’ve returned, rested up a bit, and also prepared my webinar deck.
Hmm. I probably should have broken this out as three posts rather than one after all. Sorry about that.
Discussions of DBMS performance are always odd, for starters because:
- Workloads and use cases vary greatly.
- In particular, benchmarks such as the YCSB or TPC-H aren’t very helpful.
- It’s common for databases or at least working sets to be entirely in RAM — but it’s not always required.
- Consistency and durability models vary. What’s more, in some systems — e.g. MongoDB — there’s considerable flexibility as to which model you use.
- In particular, there’s an increasingly common choice in which data is written synchronously to RAM on 2 or more servers, then asynchronously to disk on each of them. Performance in these cases can be quite different from when all writes need to be committed to disk. Of course, you need sufficient disk I/O to keep up, so SSDs (Solid-State Drives) can come in handy.
- Many workloads are inherently single node (replication aside). Others are not.
MongoDB and 10gen
I caught up with Ron Avnur at 10gen. Technical highlights included: Read more
It’s hard to make data easy to analyze. While everybody seems to realize this — a few marketeers perhaps aside — some remarks might be useful even so.
Many different technologies purport to make data easy, or easier, to an analyze; so many, in fact, that cataloguing them all is forbiddingly hard. Major claims, and some technologies that make them, include:
- “We get data into a form in which it can be analyzed.” This is the story behind, among others:
- Most of the data integration and ETL (Extract/Transform/Load) industries, software vendors and consulting firms alike.
- Many things that purport to be “analytic applications” or data warehouse “quick starts”.
- “Data reduction” use cases in event processing.*
- Text analytics tools.
- “Forget all that transformation foofarah — just load (or write) data into our thing and start analyzing it immediately.” This at various times has been much of the story behind:
- Relational DBMS, according to their inventor E. F. Codd.
- MOLAP (Multidimensional OnLine Analytic Processing), also according to RDBMS inventor E. F. Codd.
- Any kind of analytic DBMS, or general purpose DBMS used for data warehousing.
- Newer kinds of analytic DBMS that are faster than older kinds.
- The “data mart spin-out” feature of certain analytic DBMS.
- In-memory analytic data stores.
- NoSQL DBMS that have a few analytic features.
- TokuDB, similarly.
- Electronic spreadsheets, from VisiCalc to Datameer.
- “Our tools help you with specific kinds of analyses or analytic displays.” This is the story underlying, among others:
- The business intelligence industry.
- The predictive analytics industry.
- Algorithmic trading use cases in complex event processing.*
- Some analytic applications.
*Complex event/stream processing terminology is always problematic.
My thoughts on all this start: Read more
A consensus has evolved that:
- Columnar compression (i.e., value-based compression) compresses better than block-level compression (i.e., compression of bit strings).
- Columnar compression can be done pretty well in row stores.
Still somewhat controversial is the claim that:
- Columnar compression can be done even better in column stores than in row-based systems.
A strong plausibility argument for the latter point is that new in-memory analytic data stores tend to be columnar — think HANA or Platfora; compression is commonly cited as a big reason for the choice. (Another reason is that I/O bandwidth matters even when the I/O is from RAM, and there are further reasons yet.)
One group that made the in-memory columnar choice is the Spark/Shark guys at UC Berkeley’s AMP Lab. So when I talked with them Thursday (more on that another time, but it sounds like cool stuff), I took some time to ask why columnar stores are better at compression. In essence, they gave two reasons — simplicity, and speed of decompression.
In each case, the main supporting argument seemed to be that finding the values in a column is easier when they’re all together in a column store. Read more
|Categories: Columnar database management, Database compression, Databricks, Spark and BDAS, In-memory DBMS, Netezza||10 Comments|