GemFire 6.0: New innovations in data management

GemStone has unveiled GemFire 6.0 which is the culmination of several years of development and the continuous solving of the hardest data management problems in the world. With this release GemFire touts some of the latest innovative features in data management.

In this release:

- GemFire introduces a resource manager to continuously monitor and protect cache instances from running out of memory, triggering rebalancing to migrate data to less loaded nodes or allow dynamic increase/decrease in the number of nodes hosting data for linear scalability without impeding ongoing operations (no contention points).

- GemFire provides explicit control over when rebalancing can be triggered, on what class of data and even allows the administrator to simulate a "rebalance" operation to quantify the benefits before actually doing it.

- With built in instrumentation that captures throughput and latency metrics, GemFire now enables applications to sense changing performance patterns and proactively provision extra resources and trigger rebalancing. The end result is predictable data access throughput and latency without the need to overprovision capacity.

- We continue down the path of making the product more resilient than ever before - dealing with complex membership issues when operating in large clusters and allowing thresholds to be set in terms of consumption of memory in any server JVM that significantly reduces the probability of "stop the world" garbage collection cycles.

- Advanced Data Partitioning: Applications are no longer restricted by the memory available across the cluster to manage partitioned data. Applications can pool available memory as well as disk and stripe the data across memory and disk across the cluster. When the data fabric is configured as a cache, partitioned data can be expired or evicted so that only the most frequently used data is managed.

- Data-aware application behavior routing: There are several extensions added to the GemFire data-aware function execution service - a simple grid programming model that allows the application to synchronously or asynchronously execute application behavior on the data nodes. Applications invoke functions hinting the data they are dependent on and the service parallelizes the execution of the application function on all the grid nodes where the data is being managed. Applications can now define relationships between different classes of data to colocate all related data sets and application functions when routed to the data nodes can execute complex queries on in-process data. These and other features offered in the 'Function execution service' offers linear scalability for compute and data intensive applications. Simply add more nodes when demand spikes to rebalance data and behavior to increase the overall throughput for your application.

- API additions for C++, C#: Support for continuous querying, client side connection pooling and dynamic load balancing and ability to invoke server side functions.

- Cost based Query optimization: A new compact index to conserve memory utilizaton and enhanced query processor design with cost-based optimization has been introduced as part of this release.

- Developer productivity tools: It can be daunting when developers have to quickly develop and test their clustered application. Developers need the capability to browse the distributed data using ad-hoc queries, apply corrections or monitor resource utilization and performance metrics. A new graphical Data browser permits browsing and editing of data across the entire cluster, execution of ad-hoc queries and even create real-time table views that are continuously kept up-to-date through continuous queries. The GemFire Monitor tool (GFMon) also has several enhancements making the tool much more developer friendly.

For more information on GemFire, view our newly rewritten technical white paper at:


Large-scale Graph Computing at Google

To continue the graph theme Google has got into the act and released information on Pregel. Pregel does not appear to be a new type of potato chip. Pregel is instead a scalable infrastructure... mine a wide range of graphs. In Pregel, programs are expressed as a sequence of iterations. In each iteration, a vertex can, independently of other vertices, receive messages sent to it in the previous iteration, send messages to other vertices, modify its own and its outgoing edges' states, and mutate the graph's topology.

Currently, Pregel scales to billions of vertices and edges, but this limit will keep expanding. Pregel's applicability is harder to quantify, but so far we haven't come across a type of graph or a practical graph computing problem which is not solvable with Pregel. It computes over large graphs much faster than alternatives, and the application programming interface is easy to use. Implementing PageRank, for example, takes only about 15 lines of code. Developers of dozens of Pregel applications within Google have found that "thinking like a vertex," which is the essence of programming in Pregel, is intuitive.

Pregel does not appear to be publicly available, so it's not clear what the purpose of the announcement could be. Maybe it will be a new gmail extension :-)


starting small with growth in mind

Hello all,

I'm working on a web site that might totally flop or it might explode to be the next facebook/flickr/digg/etc. Since I really don't know how popular the site will be I don't want to spend a ton of money on the hardware/hosting right away but I want to be able to scale it easily if it does grow rapidly. With this in mind, what would be the best approach to launch the site?




The first meeting of this Online Gaming High Scalability SIG will be on the 9th of July 2009 in central London, starting at 10 AM and finishing around 5PM.

The main topic of this meeting will be potentials for using cloud and grid technologies in online gaming systems. In addition to experience reports from the community, we have invited some of the leading cloud experts in the UK to discuss the benefits such as resource elasticity and challenges such as storage and security that companies from other industries have experienced. We will have a track for IT managers focused on business opportunities and issues and a track for architects and developers more focused on implementation issues.

The event is free but up-front registration is required for capacity planning, so please let us know in advance, if you are planning to attend by completing the registration form on this page

To propose a talk or for programme enquiries, contact meetings [at] gamingscalability [dot] org.

Note: The event is planned to finish around 5 PM so that people can make their way to Victoria on time for CloudCamp London. CloudCamp is a meeting of the cloud computing community with short talks, is also free but you will have to register for it separately



kngine 'Knowledge Engine' milestone 2

Kngine is Knowledge Web search engine designed to provide meaningful search results, such as: semantic information about the keywords/concepts, answer the user’s questions, discover the relations between the keywords/concepts, and link the different kind of data together, such as: Movies, Subtitles, Photos, Price at sale store, User reviews, and Influenced story


Kngine long-term goal is to make all human beings systematic knowledge and experience accessible to everyone. I aim to collect and organize all objective data, and make it possible and easy to access. Our goal is to build on the advances of Web search engine, semantic web, data representation technologies a new form of Web search engine that will unleash a revolution of new possibilities.

Kngine tries to combine the power of Web search engines with the power of Semantic search and the data representation to provide meaningful search results compromising user needs.


Kngine starts as a research project in October 2008. Over times, I succeeded to collect, represent, and index a lot of human binges systematic knowledge but it is just the start. As of now, Kngine contains 500+ million of pieces of data, for 4,000+ domains. Kngine knowledge base and capabilities already span a great number of domains, such as:

  • 60,000+ Companies
  • 700,000+ Movie
  • 750,000+ Person
  • 400,000+ Location
  • 115,000+ Book
  • About 5,000,000 concepts.


Kngine, as it exists today, is just the beginning. I have both short- and long-term plans to dramatically expand all aspects of Kngine, qualities, broadening and deepening our data, and more.

I just released Kngine Milestone 2 (Our first public release), soon a preview of section called ‘Labs’ that will include a set of new research and technologies to access the knowledge will be presented.

Milestone 2

Milestone 2 is the firsts public release. This release include some useful features that help the users to reach what they want directly, such as:

  • Smart Information
  • Answer your questions
  • Link the data, and view direct data

for more information about milestone 2 Go there.

Check this out:

Hash-Table, The dark knight, When did Toronto-Dominion Bank Tower opened
profession of Alexander the Great, the director of up movie, I 'm Alive lyrics


Neo4j - a Graph Database that Kicks Buttox

Update: Social networks in the database: using a graph database. A nice post on representing, traversing, and performing other common social network operations using a graph database.

If you are Digg or LinkedIn you can build your own speedy graph database to represent your complex social network relationships. For those of more modest means Neo4j, a graph database, is a good alternative.

A graph is a collection nodes (things) and edges (relationships) that connect pairs of nodes. Slap properties (key-value pairs) on nodes and relationships and you have a surprisingly powerful way to represent most anything you can think of. In a graph database "relationships are first-class citizens. They connect two nodes and both nodes and relationships can hold an arbitrary amount of key-value pairs. So you can look at a graph database as a key-value store, with full support for relationships."

A graph looks something like:

For more lovely examples take a look at the Graph Image Gallery.

Here's a good summary by Emil Eifrem, founder of the Neo4j, making the case for why graph databases rule:

Most applications today handle data that is deeply associative, i.e. structured as graphs (networks). The most obvious example of this is social networking sites, but even tagging systems, content management systems and wikis deal with inherently hierarchical or graph-shaped data.

This turns out to be a problem because it’s difficult to deal with recursive data structures in traditional relational databases. In essence, each traversal along a link in a graph is a join, and joins are known to be very expensive. Furthermore, with user-driven content, it is difficult to pre-conceive the exact schema of the data that will be handled. Unfortunately, the relational model requires upfront schemas and makes it difficult to fit this more dynamic and ad-hoc data.

A graph database uses nodes, relationships between nodes and key-value properties instead of tables to represent information. This model is typically substantially faster for associative data sets and uses a schema-less, bottoms-up model that is ideal for capturing ad-hoc and rapidly changing data.

So relational database can't handle complex relationships. Graph systems are opaque, unmaintainable, and inflexible. OO databases loose flexibility by combining logic and data. Key-value stores require the programmer to maintain all relationships. There, everybody sucks :-)

Neo4j's Key Characteristics

  • Dual license: open source and commercial.
  • Well suited for many web use cases such as tagging, metadata annotations, social networks, wikis and other network-shaped or hierarchical data sets.
  • An intuitive graph-oriented model for data representation. Instead of static and rigid tables, rows and columns, you work with a flexible graph network consisting of nodes, relationships and properties.
  • Decent documentation, active and responsive email list, a few releases, good buzz. All a good sign for something that has a chance to last a while.
  • Has bindings for a number of languages Python, Jython, Ruby, and Clojure. No binding for .Net yet. The recommendation is to access using a REST interface.
  • Disk-based, native storage manager completely optimized for storing graph structures for maximum performance and scalability. SSD ready.
  • Massive scalability. Neo4j can handle graphs of several billion nodes/relationships/properties on a single machine.
  • Frequently outperforms relational backends with >1000x for many increasingly important use cases.
  • Powerful traversal framework for high-speed traversals in the node space.
  • Small footprint. Neo4j is a single <500k jar with one dependency (the Java Transaction API).
  • Simple and convenient object-oriented API.
  • Retrieving children is trivial in a graph database.
  • No need to flatten and serialize an object graph as graphs are native to a graph database.
  • Fully transactional like a real database. Supports JTA/JTS, XA, 2PC, Tx recovery, deadlock detection, etc.
  • Current implementation is built to handle large graphs that don't fit in memory with durability. It's not a cache, it's a fully persistent transactional store.
  • No events or triggers. Planned in a future release.
  • No sharding. A suggestion for how one might shard is here.
  • Some common graph calculations are missing. For example, in a social network finding a common friend for a set of users.
  • Separates data and logic with a more "natural" representation than tables. This makes it easy to use Neo4j as the storage tier for OO code while keeping behaviour and state separate.
  • Neo4j traverses depths of 1000 levels and beyond at millisecond speed. That's many orders of magnitude faster than relational systems.

    Neo4j vs Hadoop

    This post makes an illuminating comparison between Neo4j vs Hadoop:

    In principle, Hadoop and other Key-Value stores are mostly concerned with relatively flat data structures. That is, they are extremely fast and scalable regarding retrieval of simple objects, like values, documents or even objects.

    However, if you want to do deeper traversal of e.g. a graph, you will have to retrieve the nodes for every traversal step (very fast) and then match them yourself in some manner (e.g. in Java or so) - slow.

    Neo4j in contrast is build around the concept of "deep" data structures. This gives you almost unlimited flexibility regarding the layout of your data and domain object graph and very fast deep
    traversals (hops over several nodes) since they are handled natively by the Neo4j engine down to the storage layer and not your client code. The drawback is that for huge data amounts (>1Billion nodes) the clustering and partitioning of the graph becomes non-trivial, which is one of the areas we are working on.

    Then of course there are differences in the transaction models, consistency and others, but I hope this gives you a very short philosophical answer :)

    It would have never occurred to me to compare the two, but the comparison shows why we need multiple complementary views of data. Hadoop scales the data grid and the compute grid and is more flexible in how data are queried and combined. Neo4j has far lower latencies for complex navigation problems. It's not a zero-sum game.

    Related Articles

  • Neo4j -- or why graph dbs kick ass
  • The current database debate and graph databases by Anders Nawroth
  • On Building a Stupidly Fast Graph Database by Scott Wheeler and the Hacker News Thread
  • Network Model from wikipedia
  • Databases as a service: FathomDB
  • Using Neo4J to load and query OWL ontologies by Sujit Pal
  • Graph Databases and the Future of Large-Scale Knowledge Management by Marko A. Rodriguez
  • Memo To The Semantic Web: Drop “Semantic” And Become The “Graph Web” by Hank Williams
  • Is the Relational Database Doomed? by Tony Bain
  • Neo Database Introduction
  • Neo4j Email List
  • flare Data Visualization for the Web
  • Giant Global Graph by Tim Berners-Lee
  • Tim Berners-Lee -- Linked Data at TED
  • Drop ACID and Think About Data by Bob Ippolito
  • Analyzing and adapting graph algorithms for large persistent graphs by Larsson, Patrik
  • Thursday

    Yahoo! Distribution of Hadoop

    Many people in the Apache Hadoop community have asked Yahoo! to publish the version of Apache Hadoop they test and deploy across their large Hadoop clusters. As a service to the Hadoop community, Yahoo is releasing the Yahoo! Distribution of Hadoop -- a source code distribution that is based entirely on code found in the Apache Hadoop project.

    This source distribution includes code patches that they have added to improve the stability and performance of their clusters. In all cases, these patches have already been contributed back to Apache, but they may not yet be available in an Apache release of Hadoop.

    Read more and get the Hadoop distribution from Yahoo


    Hive - A Petabyte Scale Data Warehouse using Hadoop

    This post about using Hive and Hadoop for analytics comes straight from Facebook engineers.

    Scalable analysis on large data sets has been core to the functions of a number of teams at Facebook - both engineering and non-engineering. Apart from ad hoc analysis and business intelligence applications used by analysts across the company, a number of Facebook products are also based on analytics.

    These products range from simple reporting applications like Insights for the Facebook Ad Network, to more advanced kind such as Facebook's Lexicon product.

    As a result a flexible infrastructure that caters to the needs of these diverse applications and users and that also scales up in a cost effective manner with the ever increasing amounts of data being generated on Facebook, is critical. Hive and Hadoop are the technologies that we have used to address these requirements at Facebook.

    Read the rest of the article on Engineering @ Facebook's Notes page


    Dealing with multi-partition transactions in a distributed KV solution

    I've been getting asked about this a lot lately so I figured I'd just blog about it. Products like WebSphere eXtreme Scale work by taking a dataset, partitioning it using a key and then assigning those partitions to a number of JVMs. Each partition usually has a primary and a replica. These 'shards' are assigned to JVMs. A transactional application typically interacts with the data on a single partition at a time. This means the transaction is executed in a single JVM. A server box will be able to do M of those transactions per second and it scales because N boxes does MN (M multiplied by N) transactions per second. Increase N, you get more transactions per second. Availability is very good because a transaction only depends on 1 of the N servers that are currently online. Any of the other (N-1) servers can go down or fail with no impact on the transaction. So, single partition transactions can scale indefinitely from a throughput point of view, offer very consistent response times and they are very available because they only point a small part of the grid at once.

    All-partition transactions are different. A simple example might be that we are storing bank accounts in a grid. The account key is the bank account number. The value is an account object with the users online username and their password, address, portal profile, bank account information etc. Almost all access to the account is using the account number. Now, lets look at the login process for the banks portal. The user doesn't login with their account number, they login with the username. We have not partitioned on user name, we partitioned on account and did so for good reason as every other transaction type is keyed on account number.

    So, given we can't easily look up a record using the user name what can we do. Option 1. Lets do a parallel search across all partitions to find account objects whose user name attribute is 'billy'. We can use a MapGridAgent in WebSphere eXtreme Scale to do this. The agent code will be executed in parallel across all partitions. It will run a query within that partition to find any accounts in that partition with a username of 'billy'. One account object should match across the whole grid and the client which called the agent should receive the account number as the result. Problem solved!

    Not so fast. Lets examine this parallel search. How long does it take to run? The client invokes instructs each partition to execute the search code. These searches run in parallel and the client blocks until they all return. So, the client basically waits for the slowest 'partition' or server to return before it continues. How many of these lookup transactions can the grid perform per second? As many as the slowest box can do. If the number of accounts was to double, we could double the size of the grid. This lets us store twice as many accounts but what about the effect on our parallel search? It's true we are searching twice as fast as before (double the CPUs) but there is also twice as much data to search through so we are probably achieving the same response time as before. What about throughput? It's still the same. We can only do as many transactions per second as the slowest machine. Our throughput hasn't changed even though we doubled the size of the grid. Now, we can search twice as many records with the same response time as before, but throughput wise, nothing changed. The grid is scaling in terms of account capacity and records searched/second but the throughput number is not scaling at all.

    Availability is also impacted when compared with single partition transactions. The single partition transactions only used a single partition/server. The every partition transaction needs the whole grid to be up to complete. The failure of a single box will delay the transaction from completing. Now, products like WebSphere eXtreme Scale will very quickly recover from a failure (typically sub second) but on a large enough grid then you'll see response time glitches where maybe a second or so is added if the admins are cycling through servers doing maintenance or something like that. This delay is very unlikely to happen in a single partition transaction case. You'd have a 1/N change of it happening. Much better than the 100% chance with a every partition transaction.

    This lack of throughput scalability for every partition transactions is a problem as login is a operation whose throughput needs to go up as the web site becomes more popular. So, it looks like using parallel search for an operations which need to scale from a throughput point of view is a bad idea. What else can we do?

    We could partition using user name instead of account but now we have the search problem for all the account number based transactions which are the bulk of all transactions and besides, users like being able to change the user name which would be a nightmare if everything was based on usernames.

    We could cache the results of looking up usernames with parallel searches. The cache would be a Map whose key was username and the value was account number. A Loader attached to the Map would do a parallel search with a MapGridAgent if its Loader#get method was called on a cache miss. The problem here is that when we warm up the cache, we'll be getting a lot of cache misses and a lot of parallel searches. Not good either.

    Or, we could maintain a persistent reverse index. This index is a Map which has the user name for the key and the account id for the value. The Map is backed by a database table or other long term persistence mechanism. Now, when a user logs in, we simply do a Map.get("billy") and receive the account id with a single partition transaction and the throughput of those does scale with grid size. We have to maintain this reverse index so that if the user changes their username then we need to make sure the reverse index is updated and so on.

    Login now is a matter of looking up the user name in the reverse index map (revMap.get "billy" returning 1234) and then retrieving the account object using a second get to check the password (accMap.get "1234" returning the account object with the password). This is a much better solution than a parallel search. This is a query cache. Effectively, we are caching the results of the parallel search using a persistent map. We have converted a parallel transaction to a single partition transaction and as a result, our login operation is now throughput scalable.

    Multi-partition transactions can be great for searching large amounts of data in parallel. The search speed/second does increase with the grid size. Larger grids can store larger amounts of data but the throughput typically stays the same as the grid grows (assuming the data size grows linearly with grid size). This means using parallel operations for something whose throughput will grow as your application scales up is a mistake as the throughput of the grid has nothing to do with the grid size, it's limited to the throughput of the slowest box.

    You need to convert that parallel search operation to a single partition get if you want the system to scale from a throughput point of view. Caching the parallel searches OR using a reverse index (effectively this is a disk persistent query cache) is the normal way to handle this conversion.

    How can you make an every partition operation scale from a throughput point of view then if you can't use reverse indexes? Use multiple grids which are all the same and round robin the requests over them. Each grid will be able to do M transactions per second and N grids givens you MN per second. If you need throughput scalable every partition transactions then this is probably the only way to make it scale from a throughput point of view. Ever wonder why google needs millions of servers...

    This article is really talking about transactions that involve every partition like a search. Some transaction may use two partitions for example or some small number of partitions relative to the total number but thats for another blog entry...


    Paper: Graph Databases and the Future of Large-Scale Knowledge Management

    Relational databases, document databases, and distributed hash tables get most of the hype these days, but there's another option: graph databases. Back to the future it seems. Here's a really interesting paper by Marko A. Rodriguez introducing the graph model and it's extension to representing the world wide web of data.

    Modern day open source and commercial graph databases can store on the order of 1 billion relationships with some databases reaching the 10 billion mark. These developments are making the graph database practical for applications that require large-scale knowledge structures. Moreover, with
    the Web of Data standards set forth by the Linked Data community, it is possible to interlink graph databases across the web into a giant global knowledge structure. This talk will discuss graph databases, their underlying data model, their querying mechanisms, and the benefits of the graph data structure for modeling and analysis.