Nati Shalom's Blog

GigaSpaces and GoGrid: Cloud Platform for Enterprise Applications

I had few discussions in the past week with people who asked me about our recent GoGrid announcement and how our cloud offering integrates with the GoGrid environment. I’ll try to answer the most frequently asked questions below. In addition, we’re conducting a webinar where you can ask your specific questions online and watch a live demo – see details at the bottom of this post.

What is the GigaSpaces cloud offering?

GigaSpaces provides a set of cloud-enabled middleware services, namely data grid, messaging and Map/Reduce. These are equivalent to the Amazon SimpleDB, SQS and Map/Reduce, with the the main difference being that it’s implemented entirely in-memory and designed to support existing enterprise applications. On top of that GigaSpaces provides integration of those services into a Platform as a Service solution designed to make the deployment of JEE/Spring or XAP-based applications extremely simple.

What makes it enterprise ready?

Most enterprise applications are based on standard JEE or .Net platforms.  In addition, all enterprise applications are transactional in nature and cannot tolerate any potential inconsistency. Enterprise applications are more sensitive to performance and latency. Our cloud-enabled middleware supports all these requirements. It was designed to leverage memory resources to gain the best performance and latency, and supports large-scale deployments from the get-go. It is based on XAP, which is a mature product with hundreds of deployments in the most mission-critical applications.

What makes your middleware cloud-enabled?

GigaSpaces supports all the key characteristics expected from cloud-enabled middleware, as defined by Gartner below:

How is it different than traditional middleware?

With GigaSpaces all middleware services run on a shared pool of resources. GigaSpaces provides a high level of security to ensure complete isolation between multiple applications. The deployment, provisioning and monitoring is completely automated.

Can your middleware seamlessly shrink and grow dynamically when a machine joins or leave the network?

Yes – let me explain:

There are three components that makes our middleware elastic and thus suitable for a dynamic environment:

1. Service automation and administration – this part takes care of moving the middleware and application services around based on machine, memory, and CPU utilization.
2. Common clustering and state management – this part makes sure that nothing breaks when you start to move around any of the applications or middleware services.
3. API Facade – this part provides a standard interface as well as language binding, for seamless access from existing applications.

What does the integration with GoGrid include?

The integration includes the ability to use any of the middleware services (data-grid, messaging and Map/Reduce), either individually or integrated with our PaaS solution.

Can I use it if I'm not running on GigaSpaces XAP?

Yes. Users can leverage the GigaSpaces images to get deployment automation and improved management for their existing application, as well as add auto scaling and high availability. 

What is unique about the GoGrid cloud offering?

For GigaSpaces users, the main things that you’ll find useful in the GoGrid environment are as follows:

• Enable custom deployment – GoGrid enables enterprise users to customize their environment to fit their specific enterprise standard. This include VPN, network as well as machine hardware configuration if required.
• Native multicast support – makes cluster deployment simple.
• Standard database storage support – makes database high availability simple.

For GigaSpaces windows/.Net users, you’ll find the following useful:

• Built-in .Net support
• Support for Windows and SQL Server 2008
• GoGrid have the same pricing for 64/32 bit

When can I try the GoGrid integration?

The GigaSpaces/GoGrid solution is currently available for limited set of users. Public availability is expected within a month. If you’re interested in early access, or want to be notified when the images will be publicly available, please send an email to <cloud at gigaspaces dot com>.

Is there a live demonstration?

To see a live demonstration, you should register to the Enterprise-Grade Cloud Platform with XAP and GoGrid webinar that will take place on October 14 at 9:00 AM PDT.

How Map/Reduce and the Cloud are Affecting Analytics Applications

Two weeks ago I gave a presentation at the Sun HPCW workshop in beautiful Regensburg, Germany. It was a great chance to meet many of the folks from the Sun Grid Engine team face to face.  It was also a great chance to take a step back and look at the evolution of one of the interesting areas in the industry - analytics. Even though this is one of the more technically challenging areas, I find it odd that relatively little has been discussed about this within the developers community. 

In this post I will try to provide an overview of the different approaches for running analytic applications. I will also examine how patterns like Map/Reduce and a new environment such as the Cloud, drive a new approach that is significantly simpler and more cost effective than many of the existing approaches. There are other models for analytics such as stream based processing or CEP that i chose not to cover in this post as they deserve represent a new paradigm that deserves a separate discussion.

What is Real-Time Analytics (a layman’s definition)?

Here is the simplest and shortest definition I could come up with (probably not the most accurate one, but good still good enough):

· Analytics: The process of manipulating raw data (a.k.a data mining) into a meaningful report.

· Real-Time Analytics: The ability to generate the desired report in near real time.

Analytics in the Finance Industry

It is interesting to note that financial applications within organizations are organized based on the “speed” with which they need to react to the market. The Front-Office for example, would be the trading/market data application that needs to react to the market event in a fraction of a millisecond. The Middle and Back-office is the part of the organization that looks at an aggregated view of the market and tries to draw various trends, based on the current market and history. The algorithm that is used to process that data and generate the required report is referred to as Monte Carlo simulation.   A typical set of reports generated in that model would be P&L (Profit & Loss), VAR (Value at Risk), Reconciliation etc.

In previous years, those reports were generated on a post trade basis, i.e. at the end of the trading day, the data from the current day was aggregated into files or a database, and during the night there was a set of services that processed the data and generated the desired reports. That meant that if there was an event during the trading day that could affect the portfolio, it would only be taken into account the next day. At the same time that the volume of data increased, the window of time to process that data (during the night) became shorter due to globalization (time zone differences shortened the “night”). This led to scenarios where simulation accuracy was limited by these margins.

Analytics Becomes Mainstream

In general you can categorize any application that looks at an aggregated view of a stream of data, as an analytic application. Fraud detection would probably be another good example of analytics, since it tries to continuously monitor user actions in order to determine whether their action is part of a fraud or not. Social networks, Ecommerce and even personalization, such as search engine personalization have become more mainstream. With that, the demand to process vast amounts of data to produce various market trends, user behavior, fraud behavior etc. becomes not just useful, but critical to the success of the business. A search engine would be a good example of that – the quality of the search results is a direct function of how well you are able to aggregate content and user search patterns, and apply it to the way you produce the search results.

The Evolution of Analytic Application Architecture

To make things simple, I will start with a very basic view of the analytical application architecture, which represents the two most common architectures:

Phase 1: First-Generation Analytical Applications

Phase 1-1: Excel spreadsheet

Everyone uses Excel to generate various reports, so the use of Excel and spreadsheets are probably the most common and popular way of generating reports. The way this is done is by loading the data from a file, and then using Excel to generate the graphs and various views of that data.

Phase 1-2: High-End ETL process

Excel works well for small data sets, but for large data sets a batch process is used that is based on ETL (Extract Transfer and Load). It represents a batch process in which the operational data from the production sites is normally aggregated into some sort of data warehouse. In the process of doing so, the data is stored in a format that is optimized for generating reports. The process normally involves extracting the data, transferring it into an optimized format, and loading it into the warehouse for further processing. The ETL process normally happens once per data source. The data processing (a.k.a data mining) is where most of the heavy duty work takes place. In many cases, once the relevant reports and analysis have been produced, the data becomes obsolete and at this point it is common to clear it and store it in a long term archive.

The Need for Real-Time Analytics

You don’t need to be a genius to realize that that if all reports could be generated in real time, this would probably be the ideal world. The only reason this is not done, is purely technical. No way had been found to aggregate all this vast amount of data and process it in real time. Traditional databases had to be tuned completely differently, to deal with real time transaction processing and complex analytics (type of locking, data structure, transactional semantics etc.).

“Real-time data … requires a continuous flow of data, and traditional enterprise data warehouse deployments introduce slow data delivery to BI environments” (Forrester)

The challenge became even worse as the volume of data increased exponentially, and at the same time there was a continuous pressure by businesses to process even more complex analysis at an even lower cost. It was clear that addressing those contracting requirements couldn’t be achieved by just “throwing more hardware” into the problem. That led to the next phase of analytic application architecture, i.e. a grid-based analytic system.

Phase 2: Second-Generation Grid-Based Analytical Applications

Phase 2-1: Speeding up Analytics via Parallel Processing

Phase 2 was not yet trying to get into real-time analytics but was mainly trying to find ways to speed up the process of analytics. The majority of the focus in that area was on the batch processing that in some cases could take days or hours. By introducing grid computing, the processing time could be brought down from days to hours, and from hours to minutes.

With grid computing, the way that processing time is speeded up, is simply by spreading the processing into a large pool of commodity hardware. By splitting a linear process into small chunks that can be processed in parallel, the processing time can be speeded up quite significantly.

Phase 2-2: Adding an In-Memory Data Grid

As the time to process the data went down from hours to minutes, other factors that were previously considered insignificant became much more significant. It became clear that to speed up the analytics beyond the current level, closer to real time, it was necessary to consider ways to speed up the load and data access time, because they became more significant relative to the processing time.

“Real time drives database virtualization - Database virtualization will enable real-time business intelligence through a memory grid that permeates an infrastructure at all levels" (Forrester)

This approach became fairly common during the past few years. There is more information about this approach in one of my previous posts:  Bringing Data Awareness to the Grid

Challenges with Grid-Based Analytical Systems

While technically the combination of Compute and Data Grid were able to bring the time it takes to perform even very complex analytics to near real-time, the adoption of that solution was still marginal. One of the main reasons that this solution was not widely adopted was cost and complexity. Only a few organizations could afford building and maintaining large data centers. The skill set for running and building applications that could run in those environments was fairly rare, and therefore the labor cost was also rather high.

Phase 3: Next-Generation Public/Private Cloud-Based Analytics

The cloud makes a grid-based system affordable. So with the cloud it is possible to reduce the hardware cost, and more importantly it avoids the huge initial investment. The fact that the cloud is more widely adopted also reduces the labor cost and ramp-up time required to build such systems.

Having said that, the fact that anyone, even the smallest startup can have a large data center at a distance, reduces not just the initial investment and the direct hardware cost, but opens up a new set of opportunities for building such applications. For example it is possible to outsource the entire analytic process to someone else and use it as a service.

This was the case with Primatics Financial that provides risk analysis for mortgage portfolios as a service.

The Cloud and Map/Reduce Make Analytics Simple

With grid-based systems that run in the data center, the pool of machines is fixed. One of the main roles of the grid scheduler is to manage the pool of physical resources which belong to that pool. The cloud on the other hand already takes care of most of the resource scheduling part. Virtualization makes it possible to get the isolation required to maintain the separation between multiple jobs. If these two factors can be leveraged, a simpler model can be developed.

One of the ways to simplify the analytic application is to simplify the way that parallelization is handled. Since most of the resource scheduling is dealt with through the Cloud/Virtualization layer, a simple pattern such as Master/Worker, Map/Reduce can be used to parallelize, i.e. to distribute the application across the available machines.

You can read more about the Map/Reduce, Master/Worker approach here, and how it compares with a grid-based system.

Reducing the Number of Moving Parts

Another way to simplify and optimize the application is to reduce the number of moving parts.

Rather than having a different set of services to load the data, hold it in memory, and yet another set of services that computes the analytics, it is possible to bundle the loader, the data and the processing services into one application unit, and have multiple instances of those units running to handle the scale. In this case, each unit handles the entire life cycle (the loading, processing etc.) of the data analytics food chain.

SaaS Enablement through Multitenancy Support

One of the core elements that is required to provide the analytics application as a service is multitenancy. Multitenancy is the ability to run the multiple analytics processes on a shared infrastructure as if they were running on dedicated resources. To add multitenancy to our service, the life cycle (Start, Stop etc.) of each of the analytics needs to be managed independently of the other analytical processes that are running over the network.

There are two possible layers of isolation that can be chosen:

Service-Level Isolation

Service-level isolation provides isolation at the application component level. You can deploy multiple services on the same process/machine; you can run different versions of that same service in the shared environment and maintain them in complete isolation to other services that are running in the same environment.

Since all services share the same machine, they can potentially access shared resources such as the file system, etc. It is also harder to control things like CPU utilization and memory allocation on a per service level.

Machine-Level Isolation

Machine-level isolation is provided through the use of a virtual machine. In this case, each application or group of applications runs on separate virtual machines. Virtual machines provide an additional level of isolation that includes the actual CPU, Disk and Memory resources.

Combining Service-Level and Machine-Level Isolation

Both service-level and machine-level isolation are actually complementary approaches, as each one of them provide a different level of isolation and application packaging granularity. Service-level virtualization tends to be more fine grained, but at the same time provides a lower level of isolation. Therefore, it makes sense to use it in areas where real CPU, Memory and file system isolation are not that critical, but getting better utilization from the existing machines is more important, and vice-versa.

In the diagram above, you can choose to run everything from the same organization at a service level of isolation, and use a VM level of isolation between different customers to ensure that each customer’s application is running in a completely private set of VMs.

Private/Public Cloud

With the introduction of private cloud providers such as VMware with their Vcloud and Vsphere approach, and open source alternatives such as Eucalyptus, you can choose to run the same solution in a hosted environment or locally. You can also use a hybrid approach where some of the processing runs in your local environment and the rest in the hosted environment. Things like the Amazon Virtual Private cloud make such a hybrid deployment model fairly simple, as the local and hosted machine are accessed in the exact same way.

Final Words

The continued demand for processing a growing amount of data in real-time and at a lower cost, drives continuous innovation in the way data is processed.  Grid-based analytics (Compute and Data) addressed the demand for scaling, and also reduced processing time quite significantly, but at a relatively high cost and complexity. The demand for real time analytics by mainstream applications in the social networking media created a drive for a simpler and less costly solution. Cloud computing enables the cost of hardware to be reduced, but at the same time opens up new opportunities for making the analytic processing significantly simpler. You can rely on the cloud for scheduling and managing your resources, and on virtualization for multitenancy. With that, a simplified parallel processing approach, such as Map/Reduce, can be used to handle the parallelization of the application.

“it's quite clear that the business-intelligence/data-warehouse industry is moving toward a new paradigm wherein the optimal data-persistence model will be provisioned automatically to each node based on its deployment role -- and in which data will be written to whatever blend of virtualized memory and disk best suits applications' real-time requirements." (Forrester)

Designing a Scalable Twitter

Guy Nirpaz, Uri Cohen and Shay Banon came up with an interesting exercise as part of the recent partner training that took place at the GigaSpaces office. In this exercise, the students were asked to come up with a scalable design for Twitter, using Space-Based Architecture.

There are some interesting scalability lessons from this exercise, which are applicable to anyone looking to implement new-style real-time web applications such as the ones used for social networking.

In this post I'll  try to summarize the main patterns to put into place and considerations to make when designing such a scalable architecture.

Background:

For those of you who are not yet familiar with the service, Twitter is sort of a SMS-service meets discussion board.  You can post short messages (up to 140 characters) that can be shared with a group of subscribers that are referred to as "followers". The main difference between twitter and other messaging applications is that both SMS and Instant Messaging (IM) applications were designed primarily for one-on-one communications whereis Twitter was designed primarily for broadcast communications (publish/subscribe, or pub/sub). Another aspect that is special about Twitter is that by default anyone can follow anyone else. In other words, it was designed for open communications, not private, as were IM and SMS.

What are Twitter's scalability challenges?

1. Sending a tweet (a message on Twitter is known as a 'tweet') -– The challenge is how to handle an ever-growing volume of tweets and re-tweets and responses that can lead to a viral "message storm"

2. Reading tweets – The challenge is how to handle a large number of concurrent users that continually “listen” for tweets from users (or topics) they follow.

Designing A Scalable Twitter

Choosing the right scalability patterns

Almost every challenge in software architecture has its roots in one of the existing patterns. So the simplest course is to start by looking for those patterns, and choosing the right patterns to scale the application. Looking at many other scalable architectures, we'll begin with a partitioning pattern as the core design principle. By partitioning our Twitter-like application we'll spread the load across a cluster of servers and scale by simply adding more servers (i.e., partitions).  Another important architectural observation about Twitter is that it doesn’t fit into the classic database-centric design that most web applications do. On the flip side, it doesn’t fit well with a messaging-centric design (pub/sub) either. It is a combination of the two.

A pattern that is suitable for this type of collaborative messaging is known as a blackboard pattern.  In our design, we will use those two design patterns -- partitioning and blackboard -- as the foundation for our scalable Twitter application. With the foundation in place, let’s list the requirements and examine how these patterns can be used to scale the app.

Scalability Requirements

We'll assume a relatively extreme scaling requirement:

• Tweet Volume: 10 billion tweets per day
• Tweet Storage: 100 Gigabytes per day (with 10:1 compression)

Additional assumptions:

• Tweets are limited to 140 characters
• Tweets are immutable, i.e., there are no updates, only inserts
• Twitter limits client applications to 70 requests per hour

Now that we have the foundational patterns and clear requirements, we can design the architecture. We'll start first with the blackboard system.

Using an In-Memory Data Grid (IMDG) as a Blackboard System

The are several approaches to building a blackboard system. To maximize performance and scalability, we'll store the data in memory, thus avoiding disk I/O, which is often the main cause for contention. For years, Java has provided a model for designing blackboard systems known as JavaSpaces. More recently, distributed caching has become popular and can provide similar capabilities to those of JavaSpaces. Let's examine two popular distributed caching approaches for our blackboard system:

1. Simple read-mostly caching using memcached
2. Read/write caching, also known as an In-Memory Data Grid (IMDG)

Choosing between memcached and an IMDG

Memcached enables us to to store the data (tweets) in a distributed memory set and read it in a scalable fashion. Having said that, be aware that memcached is not transactionally-safe and is not designed for reliability (i.e., it doesn’t support fail-over and high availability). That means that if we use memcached or something similar, we will have to use a database as the back-end. Every tweet posted will have to be written to both memcached and the database in a synchronous fashion to ensure that no tweet will be lost. This approach may be good enough for scaling read access, however, for writes and updates it offers limited scalability.

Unlike memcached, which was designed for simple read-mostly caching, In-Memory Data Grids  are designed for handling a read/write scenario, and can therefore act as the system-of-record for both write and read operations. We can still use a database for long-term persistence, but because the IMDG maintains its reliability purely in memory, we can write and update the database asynchronously and avoid hitting the database bottleneck.

Todd Hoff, author of highscalability.com wrote an interesting summary that covers the different products in this space in a recent post:  Are Cloud Based Memory Architectures the Next Big Thing?

Todd provide a clear explanation of how an IMDG works (using GigaSpaces):

 

• A POJO (Plain Old Java Object) is written through a proxy using a hash-based data routing mechanism to be stored in a partition on a Processing Unit. Attributes of the object are used as a key. This is straightforward hash based partitioning like you would use with memcached.
• You are operating through GigaSpace's framework/container so they can automatically handle things like messaging, sending change events, replication, failover, master-worker pattern, map-reduce, transactions, parallel processing, parallel query processing, and write-behind to databases.
• Scaling is accomplished by dividing your objects into more partitions and assigning the partitions to Processing Unit instances which run on nodes-- a scale-out strategy. Objects are kept in RAM and the objects contain both state and behavior. A Service Grid component supports the dynamic creation and termination of Processing Units.

Back to our Twitter app: Given the scalability requirements, we will need to scale both reads and writes, and therefore, an IMDG is a more suitable approach to implementing the blackboard system.

Now let’s examine how the use of an IMDG as the blackboard system enables us to scale both sending and reading tweets. Let's start by designing the partitioned cluster.

Designing a partition architecture

One of the main considerations in designing a partition cluster of any kind is determining the partition key, such as a Customer ID in a CRM application or a Trade ID in a trading application. At first glance, it sounds like a trivial decision, but choosing the right partitioning key requires a deep understanding of the application usage patterns and data model.  In the case of Twitter, we could choose to partition the application by the data-type, the user, the tweet itself or the followers. Our first goal is selecting a key that will that will be granular enough to enable scaling the application just by adding more partitions, while making sure that we don't end up with a key that is too fine-grained -- making it sub-optimal for querying purposes.

If we use the timestamp key, for example, our application will be optimized for “inserts” (writes), however, even a simple query such “retrieve the tweets of a certain user” will force us to execute an aggregated query against all partitions. Alternatively, if we partition the data based on user-id, we'll be able to easily spread the load from different users across partitions. Retrieving the tweets of a certain user is going to be resolved in one call to a single partition. We may encounter a problem if a single user generates a significant higher load than average, however, in the case of Twitter, we can assume that this is not very likely. Partitioning by user-id is a good compromise.

Data capacity analysis

With such extreme requirements it is clear that storing all tweets in memory is going to require huge memory capacity. Very quickly this will become economically prohibitive, so we need to devise a scheme in which the IMDG acts as a buffer for most of the load on the system, and then offloads the data and queries to an underlying persistent storage.  In our Twitter example, it is fair to assume that most real-time queries (those that require fast access to the data) will be resolved in data from the last hour or 24 hours. Queries that require older data will need to hit the database for the initial call. However, subsequent access to fetch new updates should be resolved purely in-memory.

Using this approach, we'll need about 10 servers, each holding 10GB of data in memory to accommodate 24 hours of activity. If we also want to back up the data in memory, we will need double the amount of servers.

Choosing the right eviction policy

It's reasonable to assume that recent data is accessed most and older data is rarely used. To ensure that we get the maximum hit ratio on our memory front-end, let's choose a time-based eviction policy, which always holds the most recent updates in memory. When we will reach our memory capacity limit the oldest data will automatically get evicted from memory. The actual window of time in which we will be able to keep in memory is obviously dependent on the size of the cluster. With an IMDG implementation all tweets are stored in a persistent storage, which means that when tweets are evicted they are not deleted from the system.

Scaling tweet writes:

If we select user-id as the partitioning key, each user tweet will be sent to a specific partition. Multiple users may be routed to the same partition. Usually the algorithm to determine which partition fits a certain user is something like:

routing-key.hashCode() % #of partitions

In GigaSpaces, this is done by marking the routing attribute of our tweet class with an @SpaceRouting annotation.

The web front-end application will call space.write( new Tweet(..),..)  to send the tweets. This way there is nothing in our web client code that exposes the fact that the underlying implementation interacts with a cluster of partitions (spaces in GigaSpaces). Those details are abstracted within the space proxy. When the write method is called on the space proxy it parses the field that matches @SpaceRouting from our Tweet() object and uses this field value to calculate the partition it belongs to. It then uses that value to route the Tweet(..) object to the appropriate partition.

With this approach, the web application can be written in a very simple way and can interact with the entire cluster as if it was a single server.

The data from the memory partitions gets stored asynchronously into a persistent storage. The persistent storage could be a database, but it could also be other things, such as an index search engine based on Compass/Lucene.

Scaling tweet reads:

To those familiar with messaging system, at first glance Twitter looks like a classic publish subscribe application. A closer look, however, reveals that any attempt to implement Twitter with something like a JMS message queue is going to fail in achieving a scalable system. This is especially true if you consider that the system needs to maintain a durable queue for each user. That could easily lead to a scenario in which each tweet is published to thousands of subscribers and every re-tweet can potentially lead to a "message storm".

As I discuss above, the right way to think about this type of application is as a blackboard pattern, just as a blackboard (or these days, a whiteboard) is used by a group of people (followers, in the case of Twitter) to share information and collaborate. When someone writes something on the board, everyone sees it and can choose to react. Unlike messaging (take email for example), we don’t need to send separate messages to each subscriber. Instead everyone is looking at the same board. Everything is also copied from the board to paper. When the board runs out of space, we erase it. And we can always page through the paper copy to access the board history. 

In Twitter, this means that each follower that follows a group of people is basically polling for messages posted by those users from the last time he read them. To make things more tangible we can express this type of query with the following SQL syntax:

SELECT * FROM Post WHERE UserID=<id> AND PostedOn > <from date>.

The <from date> will normally be the last few minutes, if we're constantly looking for new messages.

But there's a caveat. Remember that we partitioned the application by user-id? This means that each user's tweets are stored in a separate partition. How can we read all users' posts? If we poll for each user individually, we will end up with a lot of network calls. The simplest approach would be to execute one call that looks for ALL the users we're following and look for updates (new tweets) from those users. The pattern we'll use to perform such this task is mapreduce. One way to do that with GigaSpaces is through the distributed task API:

The distributed task API is a modern version of the stored procedure. The following snippet shows what such a call would look like:

AsyncFuture<Long> future = gigaSpace.execute(new GetTweetsUpdates());
long result = future.get(); // result will be the number of primary spaces

The GetTweetsUpdates() class contains code that will be injected in each partition and will enable us to look for updates from the users we follow in a single call. Because the call runs in-process, and because the data is stored in-memory, executing such a task is extremely fast compared with the equivalent with database and stored procedure operations. Execution is aggregated to the caller implicitly. The caller can use a reducer to aggregate the results into a single result object.

Scaling the web front-end

Nothing really new here. We'll use a classic web front-end, which is comprised of a load-balancer and a cluster of web servers that act as a front end to our IMDG instances. The web application will use a single cluster-aware IMDG proxy to send new tweet posts. The IMDG proxy will be responsible for mapping the tweet with the actual partition that hosting the tweet. That logic is kept completely out of the application code. This allows us to keep our web tier clean and simple.

Keeping the web layer stateless to avoid session stickiness

One common pattern for keeping the web tier scalable is to use a Shared-Nothing Architecture, which basically means that the web tier will be stateless. This requires keeping the user session state external to the web-tier. As previously demonstrated, the IMDG can be used as high-performance, scalable data store for maintaining shared session state information. This allows us to avoid session stickiness and to scale the web tier without being locked in to a specific server throughout the entire session, in case the server is over-loaded.

For more information on how to scale the web tier, as well as other important capabilities such as self-healing and auto-scaling, see the following tutorial: Scaling Your Web Application.

Making it simple and cost-effective using cloud computing

Twitter is yet another example for a situation in which system load is highly variable and the difference between average load and peak load can be quite significant. In such cases, provisioning our system can be fairly hard and costly. This is where cloud computing and SLA-driven deployments can help us scale on demand and pay only for what we use.

Once we figured out a way to partition the application, it's going to be much simpler to package the application into self-sufficient units (referred to in GigaSpaces as processing-units) and scale the application simply by adding or removing these units on demand. You can learn more about this here

Final words

Scaling a real-time web application such as Twitter or Facebook introduces unique challenges that are are quite different from those of a "classic" database-centric application. The most profound difference is the fact that unlike with traditional sites, Twitter is a heavy read/write application, and not read-mostly. This seemingly minor difference can break most existing models for web application scalability. Using a combination of memcached + MySQL is not going to cut it for this type of application. 

The good news is that with the right patterns and set of tools, building a scalable architecture that meets such challenges isn’t that difficult.  There are already plenty of success stories that demonstrate that, such as the following example from highscalability.com: Handle 1 Billion Events Per Day Using a Memory Grid

The proposed architecture is by no means perfect and can be further optimized to meet even better performance and latency, but that will come at the cost of simplicity. I believe that the proposed architecture should get you pretty far as-is. Avoid going through more advanced optimizations until the point they are an absolute must.

References

• Twitter getting bigger - Scaling becomes more of an issue

• Memory-Based Architectures and the Cloud

• Handle 1 Billion Events Per Day Using a Memory Grid

• Are Cloud-Based Memory Architectures the Next Big Thing?

• Scaling Your Web Application

• Persistence on the Cloud – How and Why?

• Scaling twitter presentation by Guy Nirpaz

Latency is Everywhere and it Costs You Sales - How to Crush it - My Take

Over on HighScalability.com Todd Hoff posted one of the comprehensive articles on latency that I've read titled Latency is Everywhere and it Costs You Sales - How to Crush it. It covers almost every aspect of latency, and is a must-read on the subject. Todd provides a good explanation of how Space-Based Architecture helps in reducing latency through collocation of tiers and by utilizing memory to remove the I/O bottleneck:

The thinking is that the primary source of latency in a system centers around accessing disk. So skip the disk and keep everything in memory. Very logical. As memory is an order of magnitude faster than disk it's hard to argue that latency in such a system wouldn't plummet.

Latency is minimized because objects are in kept memory and work requests are directed directly to the machine containing the already in-memory object. The object implements the request behavior on the same machine. There's no pulling data from a disk. There isn't even the hit of accessing a cache server. And since all other object requests are also served from in-memory objects we've minimized the Service Dependency Latency problem as well.

In this post I wanted to summarize my take-aways from Todd’s article and add some of my own thoughts based on my experience with GigaSpaces customers.

Sources for latency – is it the network or the software?

When discussing latency most people fall into one of two main camps: the "networking" camp and the "software architecture" camp. The former tends to think that the impact of software on latency is negligible, especially when it comes to Web applications.

Marc Abrams says "The bulk of this time is the round trip delay, and only a tiny portion is delay at the server. This implies that the bottleneck in accessing pages over the Internet is due to the Internet itself, and not the server speed."

The "software architecture" camp tends to believe that network latency is a given and there is little we can do about it. The bulk of latency that we can control lies within the software/application architecture. Dan Pritchett's Lessons for Managing Latency provides guidelines for an application architecture that addresses latency requirements using loosely-coupled components, asynchronousinterfaces, horizontal scale from the start, active/active architecture and by avoiding ACID and pessimistic transactions.

So is it the network or the software?

The simplest way to answer this question is to run a mockup test that removes the impact of the software on latency from the equation.

Global optimization vs Local optimization

To better understand latency optimization we can use the analogy of a plant production line. We have a big pipeline of things that need to get done and we need to look at each element in the pipeline to optimize our production latency. In an earlier posts - Moving to Extreme Transactions Processing using Lean methodology - I discuss how we can apply the same principles used in manufacturing line optimization, such as the Lean methodology, in software systems. I tried to illustrate the applicability of some of the core principles of lean methodology. Here’s a recap:

In many cases, we can get more bang for the buck by looking at an extended value-stream, as opposed to a localized one. Local optimization means digging into the latency path in a specific component in our system. With global optimization, however, we look at the entire pipeline and optimize at that level.

An example of local optimization would be looking at our messaging system and lowering the latency of sending a message from point A to point B. An example of global optimization would be looking at the end-to-end transaction. Processing a typical transaction involves sending messages through a messaging system, consuming it, and then updating the database. If we collocate the message queue with the data receiver, we can easily eliminate half of the network hops. Additionally, if we’ll use the same storage for messaging and data, we can avoid the 2-phase commit overhead. At the same time, we can analyze the user experience to see how many clicks it takes to perform a given operation. By reducing the number of clicks we can reduce the perceived latency much more then we can by reducing the time it takes to process each click. It’s easy to see how we can get better latency savings by taking the global optimization view. Global optimization often has much more room for optimization than a local one.

If our system is already designed with a scale-out model, adding more machines and spreading the load is much simpler than trying to apply local optimizations.

Scalability as a major source for latency.

One topic that is often missing or less understood in many latency discussions is the impact of scalability on latency.

Todd writes: "We put shards in parallel to increase capacity, but request latency through the system remains the same". This statement is a common fallacy. It assumes that each request is completely independent of the others. In reality, however, if the application is not designed with a scale-out/share-nothing approach then at some point it will hit a shared contention, which makes those supposedly parallel requests dependent on each another. Contention happens when multiple concurrent users or business-requests hit a shared resource at the same time. A shared resource might be a hardware resource -- such as CPU, memory or disk -- or a software resource, such as a shared database lock. Shared resources need to be freed before another request can be processed through them. This contention time is proportional to the number of concurrent attempts to consume the shared resource and the duration in which the resource is locked. This is one of the basic principles of Amdahl’s Law, which shows that to increase processing capacity of a request that spends 10% of its time on a shared lock will require a 100x increase to CPU power. This contention time, therefore, must be added to our “latency path”. In a non-scalable system this will be proportional to the number of concurrent requests, meaning it will rapidly lengthen as the system load increases, up to the point in which the system will face “resource starvation”. (See further discussion of this here ).

Based on my experience, hardware and software contentions are some of the main contributors to latency. This is partly due to the fact that network overhead latency is relatively fixed, while application overhead latency is variable. It is extremely complex to design a fully-optimized software application.

Scalability happens to be one of those things that are often implemented in a non-optimized manner, and as mentioned above, lead to latency. The only way we can reduce the scalability overhead on latency is by reducing the contention points in our application. The typical method for reducing the contention is through “sharding” (partitioning) the access to those resources using a share-nothing approach. Disks are less concurrent than memory, and therefore, removing the dependency on disk access in the critical path of the operation is one of the keys to a latency reduction strategy. This is one of the key principles of Space-Based Architecture:

The impact of peak load provisioning on the latency cost

Another source of latency is related to provisioning. Many web sites uses static provisioning based on peak load. But how do we measure peak load? With the introduction of social networks, and phenomenon such as the Digg Effect, it becomes extremely hard to predict peak loads, as user traffic is subject to “viral behavior” leading to sudden spikes in traffic. The further ahead we try to plan, we increase the chances of missing the target. This will lead to one of two outcomes: 1)Over-Provisioning – in which case latency is not harmed, but we unnecessarily pay the cost of more servers and other resources than we normally need. 2) Under-Provisioning -- in which case our site may significantly slow down or even crash.

Use on-demand scaling to smooth the latency peaks

If we can't predict the peak loads accurately, we need to scale the system rapidly whenever we see it is approaching capacity. If the system was not designed for scale-out (linear scalability), the process of scaling will involve a substantial amount of work and tuning, which is time-consuming and therefore defeats the purpose.

A scale-out approach enables us to scale on demand and smooth out the impact of load spikes on application latency by adding servers when the load is up and removing unnecessary ones whether load is reduced. In this way we can cost-effectively control latency.

Cloud computing and virtualization enable us to build such an “elastic computing” model with significantly less effort than previously necessary. For example, the GigaSpaces Cloud Framework already supports on-demand scalability for web containers.

My colleague Shay Hasidim posted a latency-benchmark that measured how low-latency is maintained by increasing the number of servers.

From the results above we see that as we increase the number of web servers system contention (scalability barrier) grows in terms of the number of concurrent users. With a single server, latency increases starting with 100 concurrent users; with two servers, at 300 concurrent users, and with three servers -- 500 concurrent users.

To ensure linear scalability on the web-tier, we must ensure that the underlying data-tier scales-out at the same level as can be seen in the diagram below. In this case we used GigaSpaces’ In-Memory Data Grid as a front-end to a MySQL.

With the graph above we see that the IMDG scales very close theoretical linear scalability. The above results were achieved with an IMDG running on 2 partitions. Better scalability can be achieved by increasing the number of partitions.

Read more about how to scale-out the data-tier in Scaling-out MySQL.

To enable this level of on-demand scalability we used our new Cloud Framework, which combines the GigaSpaces SLA-driven container as the application deployment virtualization layer, Amazon EC2 as the machine level virtualization layer, and the GigaSpaces application server as the middleware virtualization layer. This way we can provision new machines as soon as the SLA on the web-tier is breached (measuring latency, in this specific case). When such an event happens we launch new machine instances on EC2. A new web container is provisioned on these machines through the GigaSpaces SLA-driven deployment system. An apache load-balancer agent is responsible for synchronizing the load-balancer whenever a new web container joins the cluster. Using this approach we can achieve end-to-end dynamic scalability, starting from the load-balancer, through the web-tier and business-tier, and ending with the data-tier.

It is important to note that while this test was performed on EC2, there is nothing that bounds the solution specifically to the EC2 environment. In fact, we used the same exact model to enable dynamic scaling on private-clouds using GigaSpaces and the Sun Grid Engine, for example. A more detailed description of that is available here.

Data Query latency

Query latency is the time it takes to process a query request and receive the result. There are a few factors that influence query latency:

1. The time it takes to access the data (read it from file in case it is stored on disk)
2. Contention - the time spent on a shared lock to access the data
3. Complexity of the query - the number of calls involved in executing the query

We can address each of those issues as follows:

1. File systems are not optimized for concurrent access. In addition, file systems are stream-based systems that enforce serialization and de-serialization of the data every time we wish to access it. An easy way to eliminate this overhead is to put the data in memory, which enables access to it using a direct reference. (See further details in InfoQ Article - RAM is the new disk).
2. We can reduce contention by partitioning the data, which also results in partitioning the lock. Putting the data in-memory also reduces contention because memory is much more concurrent than disk, and we don't need to inherit global file system locks. Instead, each data item can have its own locking. This will enable much more concurrent access to our data.
3. Collocating the business logic with the data - We can reduce the number of remote calls required for each query using a stored procedure approach, meaning the business logic runs collocated with the data. For partitioned data we will need to use a MapReduce-like pattern to enable execution of the queries on distributed data sources. The fact that our data source is now partitioned enables us to reduce the time it takes to query compared with running the same query in a centralized database for the following reasons:

• The data-set per partition is smaller; and

We can leverage the full capacity of the CPU/memory of each partition to get more power to process the query

Garbage collection impact on latency

Another source of latency that I found missing in Todd article is the impact of Garbage collection. Garbage collection is used in any Java or .Net application. Garbage collection runs as a background thread that cleans all the unused object in the JVM. In early versions of Java the Garbage collection implementation used a synchronized block on the entire memory during the time the garbage collection cleaned those unused objects. This hiccup time is dependent on the size of memory, number of CPU's and number of objects that are freed between each GC cycle. In those early versions of Java it was a common practice to use Object pooling as a way to reduce this hiccup. Object pooling basically bypassed the GC work and we had to take control over object lifecycle in our code. Having said that Object pools themselves became a shared resource and source for contention. As of Java 5 the GC algorithm was improved to enable more concurrent garbage collection. This means that the hiccup time was curved-out over the time therefore had less impact over our application peak performance. This holds true as long as we have enough CPU cycles to spend on the GC cycles. The caveat is that if our application consumes 100% of the CPU all this optimization is not going to help as when the GC hit our system it will compete with our application time and therefore the end result is long hiccups again. Real-time VM aims to address this problem by spreading CPU cycles between the application threads and GC threads in deterministic manner. I.e. it will slow down our application in some cases to ensure that GC gets enough cycles and in that case provide more predictable latency behavior on behalf of throughput.
The JVM comes with different switches that enable better control over the GC behavior and provides means to adjust the GC time. One thing to note about GC optimization is that it tends be close to a voodoo art. it works in certain scenarios and break in others so It is very hard to find the right combination.

Avoiding GC hiccups - Avoid over utilization

Based on my experience, the simplest and most effective way to avoid GC hiccups is to avoid over-utilization. This means that we need to plan our system in a way that wouldn't consume more then 80% of the CPU and memory under peak loads (you can choose a different threshold that may be more appropriate for your organization). For example, if the servers can process up to 500 requests per second at 100% utilization, and we have a requirement to process 1000 requests/sec, it is better to provision three machines, each processing roughly 330 request/sec, rather than two machines that are maxed out at 1000 request/sec. We also need to make sure that we have the right proportion between memory and CPU. For intensive read/write applications, I would go with at least 1CPU/2GB, and if possible, even 1CPU/1GB. These rules of thumb should get you most of what is needed in terms of latency. Obviously if that’s not enough, then you need to dig deeper into the GC flags or consider a Real-Time JVM, but you should use those options as a last resort.

A note 64 Bit VM provisioning:

Lately I've experienced some cases where people thought that they can use 64-bit machines and large memory heap sizes to reduce the cost of the system (mostly due to software license costs and machines maintenance fees). The assumption was that if with 64-bit each process can manage more memory, they can use fewer machines and fewer processers. What they didn't take into account are the considerations I presented above. The number of CPUs needs to be proportional to the amount of memory, and not just to the number of VM processes running the IMDG. This means that using 64-bit VMs can reduce the number of machines, but might have almost no impact on the number of CPUs the system will leverage. As for the amount of memory that each process can handle - that number tends to vary widely, so I don't feel comfortable giving a concrete number other than to say that I know of systems using the GigaSpaces product with 8GBs per process.

The cost of latency

Everything we do has a $ value associated with it. Latency is no different. Todd mentioned in his post some of the issues related to latency cost.

The cost associated with losing users due to a bad user experience – this measurement is typical for e-commerce, social networking and search engines sites: "Amazon found every 100ms of latency cost them 1% in sales. Google found an extra .5 seconds in search page generation time dropped traffic by 20%."

Another cost associated with losing trades – in this case the cost is a measure of the chance of losing business when your competitor can trade faster than you do: “A broker could lose $4 million in revenues per millisecond if his electronic trading platform is 5 milliseconds behind the competition.”

Another aspect that was not mentioned is the operation costs of achieving latency targets. This cost factor applies to latency in the same way it applies to other scalability operational costs.

The cost of over provisioning – if the system was not designed for on-demand scaling then we are probably spending money on over-provisioning. Meaning the system is statically provisioned to have more machines than we actually need on average, and we pay the costs of under-utilization (idle resources waiting for peak loads).

The cost of failure – if the system was under-provisioned, then we are likely to face the cost of downtime. According to a Forester survey conducted with 235 organizations, 33% estimate the hourly cost of downtime at $10k-$100k , 25% at $100k-$500k, and 13% $500k-$1M.

How cloud computing can help to improve latency and save some of the latency cost

1. Built for on-demand scalability – cloud computing is a great enabling infrastructure built for on-demand scaling.
2. Geographically distributed – we can improve latency by running our servers close to the geographical location of the user. Quoting Todd’s article again: "Facebook opened a new datacenter on the east coast in order to save 70 milliseconds "

We can now have data centers spread around the globe at our disposal making it easy to run our applications in those different data center locations and point the user to the closest location at a fraction of the cost.

It is true that all this can be achieved without cloud computing. But cloud computing reduced the barrier to entry so that even the smallest startup can apply these optimizations, previously considered a luxury that only big companies could afford

My 20/80 rules for achieving predictable latency

I'm sure that many readers are aware of the fact that out of the many possible sources of latency, there are some that are beyond our control: Internet routers, for example.  One of the key questions I ask myself in relation to latency is whether there is a 20/80 rule.  What are the 20% of the things I should focus on that will help me reduce 80% of the latency. In this section I'll try to provide the guidelines I use for designing a system for optimum latency.

1. Focus on application architecture and leave hardware and OS optimizations as a last resort. The performance provided by commodity hardware should be good enough for 80% of cases. In addition, the effort of optimizing hardware and Internet routers might involve a huge investment, and therefore, should be used sparingly. If you’re not sure whether the source of latency in your application is the network or the software, run the tests I mentioned above.
2. Start with global optimizations – before you begin to optimize the database, the router and the messaging system, look at the entire pipeline of your business request. By looking at that global level, you may find that parallelizing some part of the request, or changing some of the reliability/consistency requirements, may have a much bigger impact than any local optimization.
3. Use Spaces Based Architecture principles (even if you’re not using GigaSpaces) – quoting Todd again:
   1. Co-location of the tiers (logic, data, messaging, presentation) on the same physical machine (but with a shared-nothing architecture so that there is minimal communication between machines)
      1. Assemble/Collocate your application components based on the runtime/execution flow dependency and not based on their function in the system. For example if each request need to go through various steps such as parsing, validation, matching and execution it doesn't make sense to do each of those steps in separate process/tier. Instead you can make sure that all of those steps will be collocated and split the application into multiple units each containing all those various components. In SBA we refer to those units as processing units. This is probably one of the main difference between Space Based Architecture and Tier based architecture. In tier based approach our application is broken down into presentation tier, business logic and data-tier where in SBA we tend to collocate all of those tier as much as possible and split the application into multiple horizontal units each containing all the tiers to reduce the amount of moving parts and network hops.
   2. Co-location of services on the same machine
   3. Maintaining data in memory (caching)
   4. Asynch communication to a persistent store and across geographical locations 
      1. Avoid calling any disk/database operation at the critical path of the execution. With the addition of data-grid we can use in-memory data as the system of record. This enables us to avoid data or file access during the critical path of the user request and delegate the update to the data base as an asynchronous operation.

2. You can add to Todd summary the other pieces associated with Query optimization such as the use of Map/Reduce and moving the logic to the data is located that I laid out above.
3.  Design your system for dynamic scalability – Dynamic scalability doesn't necessarily means that scaling needs to happen in real time. It means that scaling can be done without changing code and the cycle of scaling is short. In many real-life scenarios “short” could mean a day or even a week.
4. Provision correctly - Avoid over utilization.
5. Other tips for optimizing the architecture:
   1. Decouple application components - Use SOA and EDA to make your application granular enough so that you can easily change the way you assemble the different components of your system without code changes. This flexibility is important as it will allow you to decide at different stages what your business logic pipeline is going to look like. It will allow you to optimize later, such as collocating elements that have strong dependencies among them from a business perspective. 
   2. Abstract your communication layer - Abstracting the network layer enables latency reduction when the components are collocated. This abstraction is also important to enable easy plug-ins of different transports without changing code. Assume that in the future new protocols, transports and other technologies will be introduced. By decoupling your code from the transport you can easily plug them in when they become available.

In most cases, following these steps gets you most of what you need. It also provides a good basis for eliminating many of the factors that make latency optimization on other layers more difficult. For example, if we run the business logic in a collocated in-process mode we isolate the impact on our code from external factors such as routers. It also provides a good model for troubleshooting and optimizing the system in case latency goes wrong. Rather than dealing with latency as a big-bang project, we should break it down into the levels that enable us to deal with the latency problem in a more gradual manner.

Data agregation pattern for effective monitoring

In my previous post I wrote about two patterns for using a GigaSpaces cluster to solve some of the issues involved in managing distributed applications:

• Using the space as a scalable alternative to a directory service. With this approach each service publishes itself to the space directory service and a JMX proxy acts as a wrapper that virtualizes the different managed services from the client accessing them.
• Using the space as a management repository aggregating management data.
  

Steve Colwill from PSJ published a second post on this topic titled Data Aggregation via JMX and the Grid that covers the second option outlined above.  In summary, Steve suggests that each managed agent will report its aggregate statistics to the space. A JMX façade is used to expose the statistics through a standard JMX API as described in the diagram below:

If you think about it, this is yet another proof of the old aphorism by Butler Lampson that "All problems in computer science can be solved by another level of indirection".

The thing about indirection though is that it basically moves the problem from one layer (the application layer or management layer in our specific case) to another layer (infrastructure layer).  Now if that infrastructure layer is not in place, we have to create it ourselves, which makes Butler's statement kind of empty. This is where Space-Based Architecture becomes handy. It serves as a general purpose infrastructure layer that provide a means for solving data distribution, high availability and scalability. In this case we applied the abstraction principle as a way to expose the generic space capabilities through a specific set of APIs (JMX in this case). The combination of the two creates what I often refer to as a middleware virtualization layer. We use the same API, but the implementation of this API is virtualized. In this specific case, our JMX API doesn't point to a physical JMX server, instead it points to a virtualized cloud of servers.

Quoting Steve: 

One of the reasons I'm a fan of GigaSpaces and space-based architectures is that a number of architectural choices that are traditionally hard-wired: transactional/non-transactional, sync or async replication can be changed through configuration only. This enables common design patterns (and therefore components) to be applied to a wide range of application problems, by enabling the data integrity/performance equation to be tweaked at a late stage of application assembly.

 

Summary

The main benefit of this approach compared to the one described in the previous post is that it decouples the client and the managed services. A client doesn't need to maintain direct a connection to the managed service. Most of the logic is kept server-side. In this way we can keep the client-side --  which acts as the management façade -- stateless and thin.

Because the space acts as a distributed data-store, it is easier to build aggregated statistics, as all the statistics are placed in one logical entity - the space.

Decoupling enables us to easily add new services/policies to our system without changing the management service. For example, we can add SLA monitors that can listen to the statistics in the space and take action once a certain threshold is breached. This capability makes the space an ideal solution for those looking to build their next-generation management and monitoring application.

Cloud management frameworks (for Infrastructure-as-a-Service) are ideal candidates for this, as they have the need for proximity of the management information and application behavior. The management layer acts as a loopback mechanism that can tell the application how it is actually behaving. The application can use this information to adjust itself to meet a given SLA without human intervention.

Having said all that, it is also important to note that the two options presented in Steve's posts are not necessarily mutually exclusive. I could easily see how one could use the approach presented in this post for maintaining the managed dashboard information, and the approach in the previous post to invoke specific operations on a managed service, in case you want to drill down to the managed service level. Having one underlying technology that can be used to serve the invocation, virtualization and data virtualization is yet another benefit of using the space.

The impact of cloud computing on build vs. buy behaviour

Last week I took part in an interesting discussion with a group of architects, and the question of build vs. buy came up. It came up specifically in the context of the recent experience with many of new Internet companies. I was wondering why it is that that many of them seem to spend so much in developing their own proprietary infrastructure, when it's clear that their needs are not that unique and that such development is not really part of their core IP. Many of them seem to continuously go through difficult experiences until they get their infrastructure right. And it seems that they all stumble into the same pitfalls along the way.

The typical answers as to why they build vs. buy were:

• It's core to our intellectual property and therefore we have to own all of our infrastructure
• We didn't find a solution that fits our needs since our needs are very unique
• We had a bad experience with Product FooBar which made us reevaluate build vs. buy

I can see how I'd react in exactly the same way; the most basic human instinct, when entering uncharted territory, is to rely only on yourself.

But looking at the amount of repeated failure over the past few years, it's pretty clear that this pattern isn't really proving itself too well either. Even when we choose to build it ourselves, according to our own specific in-house requirements, we still end up falling into the same trap over and over again.

Where to draw the line of build vs. buy?

To answer that question, I looked at Fred Brooks's article "No Silver Bullet" which was pointed out to me again by one of our lead architects few weeks ago.

One of the interesting points was the drastic impact of the economy on the build vs. buy decision pattern:

"The development of the mass market is, I believe, the most profound long-run trend in software engineering. The cost of software has always been development cost, not replication cost. Sharing that cost among even a few users radically cuts the per-user cost. Another way of looking at it is that the use of N copies of a software system effectively multiplies the productivity of its developers by N. That is an enhancement of the productivity of the discipline and of the nation.

The key issue, of course, is applicability. Can I use an available off-the-shelf package to perform my task? A surprising thing has happened here. During the 1950's and 1960's, study after study showed that users would not use off-the-shelf packages for payroll, inventory control, accounts receivable, and so on. The requirements were too specialized, the case-to-case variation too high. During the 1980's, we find such packages in high demand and widespread use. 

What has changed? Not the packages, really. They may be somewhat more generalized and somewhat more customizable than before, but not much. Not the applications, either. If anything, the business and scientific needs of today are more diverse and complicated than those of 20 years ago.

The big change has been in the hardware/software cost ratio. In 1960, the buyer of a two-million dollar machine would have felt that he could afford $250,000 more for a customized payroll program, one that slipped easily and nondisruptively into the computer-hostile social environment. Today, the buyer of a $50,000 office machine cannot conceivably afford a customized payroll program, so he adapts the payroll procedure to the packages available. Computers are now so commonplace, if not yet so beloved, that the adaptations are accepted as a matter of course."

The impact of cloud computing on the buy vs. build decision

I think Fred's analysis above is much more than just a historic curiosity. Exactly the same process is playing out today, with the advent of cloud computing and virtualization techniques that are turning IT infrastructure into a commodity, on the road to becoming a utility, and dramatically reducing its total cost. 

As Fred says in his paper - when the hardware gets cheap, development becomes very expensive. Under these new conditions, we're all going to have to change how we evaluate off-the-shelf products compared to the alternative of developing in-house. Proper TCO measurements need to be put in place at an early stage of the decision making process. 

For example, it will no longer be sufficient to choose a product based on the "best performance" or even "best reliability," because each of those factors has a direct cost associated with it. Instead, we are forced to have a better picture of the business requirements, so that we can choose the right product to meet our business needs, and it's not always going to be that the best product from a technical perspective is the right product - and the cheapest product won't be the right product either.

"The hardest single part of building a software system is deciding precisely what to build. No other part of the conceptual work is as difficult as establishing the detailed technical requirements, including all the interfaces to people, to machines, and to other software systems. No other part of the work so cripples the resulting system if done wrong. No other part is more difficult to rectify later."

It is quite surprising to see how much of the current decision-making process is not based on real business requirements. It is even more surprising to see how little we as architects and business people know about their system requirements and real application behavior.

A good example that was given in the architect meeting is the user experience. One participant in the discussion said that at one point, he was focusing on making the latency of serving his site pages as fast as possible and did a good job at that, but at the end of the day, when measured against a competing site that was performing slower, the impression of the user was that the competing site was performing better - the reason was simple, the other site was focused on user experience which led to less clicks per request and not how much time a single request is being executed.

If using off-the-shelf products can cut costs dramatically, why are there are so many product failures?

Fred provide an interesting answer to that question as well:

"Much of present-day software-acquisition procedure rests upon the assumption that one can specify a satisfactory system in advance, get bids for its construction, have it built, and install it. I think this assumption is fundamentally wrong, and that many software-acquisition problems spring from that fallacy. Hence, they cannot be fixed without fundamental revision--revision that provides for iterative development and specification of prototypes and products."

Final words

You might be thinking by now that these are all new lessons learned from the recent changes in the economy, right? – wrong. Go check when Fred Brooks' article was written.

If anything, I would strongly recommend that everyone reading this post would spend time reading Fred's article from start to finish, because I've only covered a small part of the philosophy behind his paper. I think the paper's viewpoint is extremely relevant today -- perhaps even more relevant today then it was when he originally wrote it.

Managing application on the cloud using a JMX Fabric

One of the challenges of managing application in a distributed environment such as Cloud/Grid is that collecting or finding the management information of each part of the application is a relatively complex task.

JMX provides a standard way to expose the management information (MBean) of a particular server. However, the way the client-side finds all the MBeans that comprise the application, or the way a single client might interact with the distributed parts of the application, is left open.

Steve Colwill from PSJ wrote a detailed blog, JMX for Grid Based Applications,
where he outlines a solution that uses JMX JSR-160 connectors and GigaSpaces to create a JMX Fabric. According to the proposed solution, the managed agent (server side) use the connector to add a reference of each MBean stub to the space. The client uses a FederatedMBeanServerConnection class that picks up those references from the space, connects to them and then delegates operations to the set of Mbean servers, effectively acting as a multiplexer.

Using the space as a JMX directory service

The above diagram illustrates how the model described by Steve works. The client is abstracted from the physical location of each server and can easily discover services that join the network. The connection from the client to the servers uses peer-to-peer communication, which means that once the service is discovered, no additional overhead is needed for communication between the client and the managed service. In this case, the space is used as a directory service. We leverage the fact that it can be distributed and dynamically discovered to simplify the discovery process in a distributed environment.

Using the space as a management data repository

The above model is quite useful for cases in which we want to expose federated services which have an existing remote interface. But this is not always the case. If it isn't, we can use the space as a management data repository, which contains full management information for each agent and exposes that information to the client or to any management application. In this method too, the client application is abstracted from the managed service. But unlike the first option, the client gets the information about the managed entity directly from the space, and doesn't need to maintain a connection with the managed service. The space in this case is used as a distributed database, so the application can not only obtain management information about an individual server but can also gather aggregate statistics and perform other aggregate data queries, directly on the data model.

Summary

Steve's solution to managing application in a distributed environment is an interesting one, as it enables applications that are already using a standard JMX interface to use a new federated model without changing the application and without adding a performance overhead. This is achieved just by plugging a new space-based connector. It is a good example that shows how a space can be used as a distributed directory service. It is important to note this is only one pattern in which a space can be used to solve this type of challenge. There are other ways; using the space as a management data repository, as I suggested in this post, is just one of them. The nice thing is that implementing any of these patterns becomes fairly simple once the space is brought into the picture.

I would like to end this post by thanking Steve specifically and PSJ in general for being a great partner for such a long period of time, and for sharing your experience in such meticulous detail.

Need scalability? Don't forget pricing

In most discussions about scalability, we often approach the topic as a pure technical/architecture challenge, and ignore cost issues. The problem is that when we truly scale our application, and want to benefit from economies of scale, we're going to end up with scale limitations, not because of technical issues, but because of the pricing  and licensing models.

Scalable pricing

Scalable pricing means a pricing scheme that provides the benefits of economies of scale. Below are pricing models commonly used for software products and how they fit in the new dynamically-scalable world.

• Free - while this certainly sounds like the best option (and may very well be) the customer needs to be aware of the following:

- The free license of a software product typically does not include support: not an option for most mission critical applications.
- When you do pay extra for support, you will typically be charged just like any other run-time license on a per CPU basis.
- Make sure that the company behind the product has a sustainable business model, otherwise there is a good chance that it will either die when its funding dries up or change its license model to monetize its user base. That's fine, but all it means is that it's not really a free offering in the long run, and you don't know what the pricing model will be exactly.
- In terms of total cost of ownership (TCO), free products are not necessarily the cheapest option. TCO is dependent on many factors, for example, dependency on other products (and their license costs), the need for integration and maintenance, etc. See my post, Economies of non scale, for more on the topic.

• Subscription model - With a subscription model you pay a fixed periodical fee, typically on an annual basis for infrastructure software, and on a monthly basis for SaaS. Subscription pricing is suitable for on-demand scalability as it provides the flexibility to grow or reduce cost based on the annual use of the product.
• Pay per use - this model is even more flexible then subscription model as it gives you higher granularity. Pay per use is provides in various forms where the usage can be a measure of CPU utilization or bandwidth utilization. Amazon for example charge per machine utilization for its EC2 services and data-utilization for its data services.
• Perpetual license - This model is used to buy licenses in advance and pay for support separately (normally 15-20% on top of the per CPU license). This is the most commonly used model with commercial software products, however, due to the large initial investment required by this model, it doesn't fit well with on-demand environment.
• Enterprise unlimited license - This model enables you to pay premium price in advance (based on potential future usage) and gives you the freedom to use the software without any limit. This model fits to environment where you anticipate that over a fairly short period of time the usage of the product will become wide and therefore the pay-per use or any of the other models mentioned above will become more expensive.

Which model to choose?

Each of the models has pros and cons and therefore the answer depends on your situation. Also, over time, as the situation changes, you will probably realize you need a different license model, and so it becomes equally important that the product you choose will give you the freedom to move from one model to another in the future.

GigaSpaces scalable pricing

With GigaSpaces we continuously look into ways to make our software license cost fit the on-demand world. For example, we launched a free Start-Up program that provides a totally FREE version of GigaSpaces for startups (hundreds of start-ups have already signed up for this program since we launched it last year). We also provide a Pay-Per-Use model for those running on Amazon EC2.

We felt that even though this is a fairly flexible pricing, we could do better. As of our 6.6 release, we added the option to buy our software at a yearly subscription price, and we also launched a new package called XAP Standard Edition, which is sold at a very low price of $9,500k per package (not CPU) where the package includes two servers, 4 GigaSpaces nodes and up to 50 clients or remote servers.

These changes were designed to address the needs of developers looking to start running their applications at a relatively low scale, who need the full functionality of the product, but cannot afford the full XAP price. Another principle that we kept when we designed this package is that moving from Standard to Premium edition wouldn't require any change in your architecture or code - which means that you could always scale to the premium edition just by changing the license key.
More details about the new pricing model is available here

Other references:
GigaSpaces and the Economics of Cloud Computing

Economies of Non-Scale

Cloud Summit Event in Sunny Tel Aviv

Cloud summit event is coming up with lots of interesting lectures from Google, Yahoo, Amazon, eBay
You can see the full program here.

In my presentation "Getting ready for the clouds" I'm going to talk about the steps that can be taken to bring existing application to the cloud and use a live demo that shows a real life demo on how easy it deploy a production ready application with load-balancing, dynamic-scaling, caching and data-base in just few minutes. I'm also going to show what self-healing really means by killing one of the machines and seeing the impact of that failure on the application.

Another nice thing about this event is that its going to happen at perfect timing for those who want to run away from the real winter clouds and enjoy the sun and beaches of Tel Aviv.

Making EDA programming simple with JeeWiz

Event Driven Architecture (EDA) is becoming more popular these days, as the drive for loosely coupled and scalable architecture forces us to break our systems into components and integrate them through some sort of workflow.  Having said that, thinking in asynchronous events is not a trivial concept to deal with, seeing as we used to thinking and programming in a synchronous manner.

Space-Based Architecture lends itself very nicely to EDA, because it provides a means to register for events, manage the state of events and trigger different business logic elements based on state changes.
This makes the programming of EDA relatively simple compared with some of the other options, such as messaging and database systems. The following diagram shows how a typical EDA would look like in a Space-Based world - you can read the full description here.

While Space-Based Architecture makes EDA relatively simple compared with alternatives it can be made even simpler using advanced code generation tools that follows the Model Driven Development pattern.

JeeWiz is one of the leading products in that space: 

"The goal of JeeWiz is to automate software development as much as possible. JeeWiz builds all the code, configuration and build jobs that can be derived from high-level models of a system, achieving unprecedented levels of automation."

Matthew Fowler, Founder and CEO, New Technology/Enterprise Ltd. gave a presentation in our latest London Event introducing GigaSystemBuilder using JeeWiz which enables a model-driven development with GigaSpaces. JeeWiz is an Eclipse-based tool that makes it easy to create an entire project fairly easy. The product itself is highly customized. Users can use the same model to build their own templates, and in this way automate a large part of their development. The following diagram taken from Matthew's presentation, shows how a typical development process would look like with JeeWiz.

Matthew's presentation contains more details about the specific integration with GigaSpaces and what the generated code would look like -- I would highly recommend looking into it. The presentation is available online here. I was also happy to see that the GigaSpacesBuilder Eclipse-plugin is now available for download here. It comes with full documentation and an easy guide to get you through the first steps.

Well done Mathew and the JeeWiz team!