Tuesday, September 27, 2016

The newest IBM Power Systems – more of everything for the hottest environments!

By Bill Moran and Rich Ptak

IBM recently introduced three new Linux-based (LC) Power Systems targeting the hottest workload environments. These POWER8-based, enhanced models are configured to satisfy system cost, performance and processing demands of Big Data, cognitive, GPU, dense computing and memory intensive, high throughput processing. When compared to a Dell system, the newly announced IBM S822LC for HPC achieved 2.5 times the performance with costs of hardware and maintenance 52% lower! Let’s review the details.

IBM’s LC family servers are designed and cost optimized for “scale-out” multi-server cloud and cluster configured environments to satisfy customer preferences for clouds over expanding on-premise data centers.

IBM’s new lineup of LC models includes:

  1. The S822LC for Big Data
  2. The S822LC for Commercial Computing
  3. An S822 LC for High Performance with a new version POWER8 chip and a very high speed link between the CPU and onboard GPUs.
Other family members include:

  1.  An “entry level” S812LC targeting customers with new memory intensive, Big Data workloads.
  2.  An S821LC with 2 POWER8 Sockets (processors) in a 1U form factor for computing in dense database, virtualization and container environments.
We created this table to highlight key features of the different models:

                  Model             # of CPUs       #sockets       Max Cores       # GPUs       Max threads 
8 or 10
16 or 20
S822LC for
Big Data
S822LC for
S822LC for
High Perf.

Ten-core systems have a 2.92 GHZ version of POWER8, while the 8-core systems have a 3.32 GHz chip. All include what IBM calls a 9x5, 3-year warranty with next day service.

IBM’s website[1] has additional details on other system characteristics that may be important to existing or planned applications.

Some Key Considerations

Complementing the scale-out systems are scale-up systems, IBM E870 and IBM E880. These may be more appropriate for some applications. We do not discuss those here.

The S822LC for High Performance system has characteristics worth mentioning. There is the water cooling option which allows a turbo high speed mode to be used extensively. Also, it uses a new version Power8 chip with a special link to the GPUs in the system significantly speeding up the connection between the GPU and the CPU. IBM reports the old GPU-to-CPU connection speed via a PCIe link was 32GB/sec. The new NVLink clocks out at 80 GB/sec. This leads us to a discussion of system performance.

Performance Background

IBM is very clear they believe the X86 has hit a barrier regarding Moore’s law predictions of future performance improvements. Moore’s law relates to technological performance enhancements over time. See this note.[2] As long as the law applies, price/performance improvements were possible. However, physics is invalidating the law for some existing technology. IBM (and others) believe system architecture changes, not raw hardware speeds are the more likely source of necessary future performance improvements[3].

Building on this philosophy, IBM is making changes and adding interfaces to Power Systems to drive greater performance. A recent example is CAPI, which we have written about elsewhere, drives large improvements in applications using in-memory databases, support of many more threads per core than comparable X86 system and allows more to be done, faster. Adding Graphical Processing Units (GPU) NVLink technology to S822LC for High Performance are other examples of improvement.

Of course, such improvements can only benefit those applications able to take advantage of them. IBM identified those applications (emerging and existing) to gain market advantage by providing systems optimized (cost, price and performance) for such applications. This is the strategy to design and optimize systems for significant market segments.  

Performance Data

IBM has released performance and price performance data matching the latest Power Systems to comparable Intel Systems. Details appear at this URL.[4]

Summarizing IBM’s results, the best performing Power8 system, IBM S822LC for HPC, achieved 2.5 times the performance of a comparable Dell system with 52% lower hardware and maintenance costs. The S822LC for Big Data managed 40% better performance than a Comparable HP system with 31% lower hardware and maintenance costs. It appears that with comparable hardware and number of cores, Power8 systems will outperform Intel-based systems and also have a price performance advantage.

There are caveats about these results. The benchmarks are not industry standard. They are not supported by the TPC or Spec. IBM has made the effort to be transparent by documenting what they did. In the past, when we investigated IBM benchmarks of this type; we found them to be honest and accurate. We believe someone could repeat the benchmarks and get the same results. Having said that, it still remains a fact that any vendor-run benchmark will be suspect in the minds of some.

The IBM results are very useful to make a potential purchaser aware of potentially significant advantages of Power Systems. We recommend potential customers examine Power Systems to determine the potential for benefit in their environment.

Other Considerations

Intel holds the dominant position in the generic server market. We believe customers benefit from competition in an open market. We therefore support other options whether ARM-based or from AMD.

POWER8 provides a realistic alternative. We hope it flourishes. We find the growth of the OpenPOWER Foundation to over 260 companies encouraging. Note, we are not saying to blindly choose a non-Intel alternative. We do believe sensible customers should carefully evaluate all options to determine the best architecture for their business. 

IBM Power Systems possess some significant advantages for specific application types and to leverage new technologies, e.g. Big Data, analytics, AI-Cognitive Computing (Watson), etc. where customers are now investing. Take a look, and decide for yourselves. 

[2] An interesting article about Moore’s law (actually more an observation than a law) and its current state is in Wikipedia. Our opinion is that it supports IBM’s position. See

Thursday, September 22, 2016

Red Hat leverages Linux strengths to address Digital Transformation

By Bill Moran and Rich Ptak

Let’s start with an admission that in recent years we have not been following Red Hat in any detail. We had considered them a niche Linux player., and paid little attention thereafter. That, we now realize, was a mistake.

We heard the first inklings at a 2015 Red Hat event, but circumstances prevented any significant follow-up. When Red Hat scheduled an Analyst Event in NY city, we followed up to get the details of its much larger vision and ambitions for the data center. These extend far beyond just new Linux versions. 

Red Hat’s executive speakers at the conference clearly demonstrated that the company had transformed themselves to claim a position of real strength in addressing the challenges of digital transformation currently facing most enterprises today. To us, digital transformation is about adopting a full range of new and emerging technologies that enterprises must adopt to succeed. In particular, it is digital technologies impacting the data center. These include implementation and integration of mobile, a mix of cloud architectures, agile development, cognitive computing, etc. 

Red Hat plans to leverage a solid base of solutions built on its product portfolio, Red Hat Enterprise Linux (RHEL), Red Hat Virtualization, Red Hat OpenStack platform, Red Hat Satellite, etc., along with other emerging technologies. They believe (with good reason – see Figure 1 below) that existing Red Hat customers will want their private cloud or a public cloud to be built on RHEL. They also believe no single cloud version or architecture is likely to satisfy all customer requirements.  

Figure 1 Red Hat's suite of Cloud offerings

 Amazon has carved a solid, growing niche in the development and test world. Common sense indicates that customers with production RHEL will be reluctant and will resist wholesale conversions to Amazon Linux. At the same time, they may well use Amazon Linux for testing or development while in Amazon’s cloud.   Red Hat’s open strategy deals with this situation as their tools, services and management offerings all allow a customer to work in multiple clouds and modes of operation. 

In fact, Red Hat expects that future enterprise customers will have to operate in several modes. These can be characterized as bare metal, virtualized, private cloud, public cloud, and hybrid cloud. Customers will have applications operating in each mode. Red Hat will provide customers the tools and management capability to handle this increasingly complex situation with all based on Red Hat Enterprise Linux.

As a fundamental strategy, this makes excellent sense. Red Hat is building on their strength. Another critical point Red Hat can make. They have many years’ experience as a leading open source player. They understand how the workings of the collaborative development process. When they acquire companies, which they have done quite strategically, they convert any proprietary products to open source. Their experience helps these conversions to succeed. They have made the major investment to rewrite products to make them compatible with their philosophy and existing offerings. 

Red Hat knows that typical open source products go through many releases. Enterprise customers must have production-ready products, including open source ones. They are willing to pay to assure the products are reliable. Red Hat has grown into a multi billion-dollar company based on their ability to supply support and maintenance to assure open source products meet enterprise requirements. 

Here is how the Red Hat methodology works. There is broad interest today in Open Stack technology. So, Red Hat sees a business opportunity and offers support for it. Open Stack developers typically produce a release every six months. However, enterprise customers cannot replace production software every six months. They want production-ready software they can install and use for a significant period, possibly multiple years. Red Hat will analyze the open source code. They will educate their staff so that they can provide maintenance and other support on the release for an extended period.  Red Hat’s educated staff provides the support and reliability that enterprises want.

We did some research into Red Hat’s key product, RHEL. We spoke with a very experienced Linux app developer, who uses RHEL all the time. His opinion is that RHEL is an excellent solution for production systems. He would not use anything else.  Also, any Linux expert would find that the Red Hat offering is exactly what they would want to use.  In some special situations, they (and he) might use another version of Linux. We have already mentioned Amazon Linux as a good example of this situation.  

Based on all that we’ve heard and found out, Red Hat is in a strong position to succeed in the efforts to broaden their market. Even recognizing the limitations of an anecdotal sample, our sense is that they understand the market they are targeting.

Finally, we found Red Hat’s event to be well-organized and informative. Their executives quite ably communicated exactly and what and why the company was doing to succeed in the market.  The Red Hat staff was knowledgeable. We expect to be writing more about Red Hat’s strategy and their portfolio of products and services in support of that strategy. 

We suggest that anyone considering a Digital Transformation should make the effort to investigate and understand Red Hat and its offerings. It seems to us that they would make an excellent partner for this work. Their established record of success with Linux products and services as well as they history in the Open Source world gives them greater credibility than many other in what is becoming a very crowded vendor space.