Modified on by jerberstark
By: Neli Momtaheni. Have you ever gotten the memram error during a Linux installation? Several factors can cause this error, but often it is related to the operating system you previously had installed on your server or logical partition. Based on my experience, I get this error when I try to install Linux on a server that had been running the AIX OS. To correct this error and move on with your installation, simply issue the following commands.
The boot process resumes, and the error is resolved.
By: Anirban Chatterjee.
month, the PowerLinux team is announcing the biggest technology change in PowerLinux servers
since we launched, with the availability of our POWER7+ chips on the platform.
POWER7+ is more than just a speed bump on our POWER7
processors. Our hardware teams have
worked hard to increase the flexibility of the platform, bringing
balanced performance increases while keeping other factors like energy
consumption at bay. Some examples:
doubled the memory capacity in servers like the 7R1 and 7R2. We’ve also doubled the number of virtual
machines you can allocate to a single processor core. This means we’ve dramatically increased
the system’s flexibility when it comes to deploying virtualized workloads
… in many cases, this will eliminate memory as the gating factor, allowing
users to drive utilization rates even higher and boost system efficiency.
reduced the feature size in the chips from 45 nm to 32 nm. This not just a simple die shrink,
though … with every shrink, the chip team has to work even harder to
ensure the computational and thermal stability of the chip while driving
higher clock speeds. In PowerLinux
servers like the 7R2, the new chips now top out at 4.2 GHz.
- Because we have more available chip real estate now that we’ve shrunk the die
size, we’ve bumped up the L3 cache from 4 MB to 10 MB. This significantly boosts performance in
workloads that are memory dependent, like Java and big data applications.
feature additions to POWER7+ allow us to improve chip reliability and
boost energy savings. We’ve added
self-healing capabilities and automatic processor reinitialization to
increase system robustness, and we’ve introduced a new energy saving mode
that saves 45% more energy than before when the processor is idle.
The new performance capabilities afforded by POWER7+ enable
some pretty interesting possibilities when it comes to reducing costs. For example, we’ve found that people
typically need just two dual-socket (16 core) PowerLinux 7R2s to do what it
would take three dual-socket (16 core) Xeon servers to do. Given the already competitive pricing on the
7R2s, this means that you can potentially save north of 40% on your costs of acquisition by choosing PowerLinux.
These changes make PowerLinux an ideal platform for the most
critical workloads your business runs today, like your customer facing web
applications, or your ERP system.
Customers like Kwik Fit (PDF) and IT Informatik (PDF) are already realizing the benefits. Click the links to read the
case studies on these customers.
But PowerLinux is also a great platform for today’s growth
workloads, like development and deployment of mobile and web applications. To make it easier for businesses to create
and launch these types of client experiences, we’re introducing a new solution for WebSphere mobile and web applications that leverages the lightweight
WebSphere Liberty Profile software. This
is a light, easily reconfigured web app environment that makes it simple for
developers to test and deploy applications.
As 2013 progresses, we'll continue to bring you more
announcements that improve the PowerLinux platform's ability to reduce costs while improving
efficiency, enabling new and growth workloads, and giving you a better overall
By: Aravinda Prasad.
Problem determination is
definitely a key area when it comes to systems administrators
(sysadmins). Sysadmins tend to spend hours debugging and trying to
find out what is wrong with the system. Engineers at the IBM Linux
Technology Center around the world are working on ways to simplify the
experience of sysadmins in managing IBM systems.
An outcome of such
an effort is the upcoming facilities like Light Path Diagnostics,
improved diagnostic tools and other features in IBM PowerLinux, which
integrates well with the existing Reliability Availability and
Serviceability (RAS) capabilities. IBM believes that such facilities will help sysadmins to perform the administration tasks easily and
In this article, we emphasize the PowerLinux RAS advantage for
sysadmins in determining and resolving the problem from the
administrator point of view.
A PowerLinux sysadmin
receives a notification alert of a serviceable event. The sysadmin
knowing that the service log infrastructure of RAS on PowerLinux is
capable of sending such notifications, logs into the system and
checks the service log event using the servicelog
tool to get more details about the serviceable event. The detailed
log by servicelog mentions
that one of the Ethernet cards has gone bad, giving additional
information about the location code, device serial number etc.
email@example.com ~]# servicelog --dump
Servicelog ID: 27
Log Timestamp: Fri Nov 30 10:44:02 2012
Event Timestamp: Fri Nov 30 10:44:02 2012
Update Timestamp: Fri Nov 30 10:44:02 2012
Type: Operating System Event
Severity: 6 (ERROR)
Node Name: ras.ibm.com
Reference Code: BF778E00
Serviceable Event: Yes
Predictive Event: No
Disposition: 1 (Unrecoverable)
Call Home Status: 1 (Call Home Candidate)
Kernel Version: #1 SMP Wed Jun 13 18:19:27 EDT 2012
Message forwarded from syslog:
Fri Nov 30 10:44:02 ras kernel: e1000e 0001:00:01.0: Invalid MAC Address
Description: The MAC address read from the adapter's EEPROM is not a valid Ethernet
Action: 1. Execute diagnostics on the adapter, using "ethtool -t".
2. Check the EEPROM level on the failing adapter.
3. Replace the adapter.
<< Callout 1 >>
Procedure Id: see explain_syslog
The clever sysadmin,
knowing the RAS capabilities behind this entire setup, recalls that
the OS running on the PowerLinux server which detected the bad
Ethernet card has logged an error in /var/log/messages,
which was converted into service log event by syslog_to_svclog
tool by logging the event into service log database. The service log
database upon receiving a serviceable event has sent the
notification. The sysadmin also quickly recalls that the serviceable
events are not only restricted to Ethernet devices, but are also
supported on SCSI enclosures for which events are logged to service
log database by diag_encl tool
and RTAS related events, which are logged into the database by
The sysadmin orders a new
Ethernet card after collecting the required information like model,
serial number etc of the bad Ethernet card with the help of the new
-l flag to lscfg
command, which takes location code, which was logged in service log,
as input and prints VPD (Vital Product Data) information.
firstname.lastname@example.org ~]# lscfg -vl U78A5.001.WIH8464-P1
0001:00:01.0 eth1 ethernet U78A5.001.WIH8464-P1
Port 2 - IBM 2 PORT 10/100/1000
Base-TX PCI-X Adapter (14107910)
Machine Type-Model........82546GB Gigabit Ethernet Controller
The sysadmin is also very
happy to know that with the new light path diagnostics facility (coming in RHEL and SLES service pack updates in the future) and the
service log notifier would have notified the light path diagnostics
subsystem lp_diag about the
bad Ethernet card and the light path infrastructure would have
enabled the fault indicator for the bad Ethernet card slot helping in
easy identification of the physical location of the Ethernet card.
The sysadmin replaces the
bad part by identifying the slot with the help of fault indicator
LEDs. The hot-plug facility automatically identifies and initializes
the newly plugged card. The sysadmin closes the serviceable event
using log_repair_action tool
and the service log facility upon closure of serviceable event
notifies the light path infrastructure to turn off the fault
indicators. The sysadmin now updates the VPD using vpdupdate
tool to reflect the changes in the hardware.
The sysadmin appreciates
the RAS capabilities of PowerLinux and its seamless integration with
the OS, which helped in quickly identifying and resolving the
problem. The sysadmin checks for new notifications knowing that the
PowerLinux RAS is not just restricted to identifying faulty devices
but is capable of lot more things and provides many service and
For more information about service and productivity (aka RAS) tools for your PowerLinux system, see the related article
in the Linux Information Center.
By: Jeff Scheel.
As I've often mentioned in my blogs, I like to answer questions which I've been very asked frequently. Today's topic provides more details about our marketing slogan "Industry standard, Tuned to the task". We've worked so hard to eliminate the myth that PowerLinux is different (see my blog What does IBM mean when it says, "PowerLinux?"
) that we're now getting questions like:
- Will my (x86) Linux application just run on PowerLinux?
- Can I use the same DVDs to install my PowerLinux or Power System server as I used for my x86 server?
- Can I migrate a VMWare Linux image to PowerVM?
The short answer to all of these questions is the same, "No".
The technical explanation, stems from a fundamental component of computer architecture -- the processor. Every processor architecture has a different machine language (command set) that it supports. So, even though Linux is built from the same source code, using the same compiler, the final executable system code is different because the compiler "targets" (builds for, generates machine instructions for) the specific processor type.
For some people, this may make perfect sense if we talk simple "Hello world" application. If I compile it on my x86 PC at home, I understand that it would not naturally expect it to run on the Power System at work. In fact, if I build the application in both places, x86 PC and Power System, I will see that even the resulting binary is a different size, demonstrating the machine language between processor architectures are likely different.
Since the Linux operating systems is simply a large collection of programs, the same explanation applies to the operating system. Red Hat and SUSE build their distributions from the same source using the same compiler,s but generate different programs for each processor architecture. Then, they bundle and distribute all the programs for the operating systems on a specific processor architecture into different DVDs -- one set for x86, one for PowerLinux, etc.
Now, let's look at an installed image. Once I get that operating system running with the programs compiled for my architecture, the answer to the final bullet above should become obvious. The executable program is unique to the processor architecture. So, the migration of VMs must naturally stay on the same processor architecture. PowerVM can move VMs (or LPARs as I grew up knowing them) from different versions of the architecture such as POWER6 to POWER7, but it cannot be moved from POWER7 to Nehalem because the executable binaries only understandable to the processor for which they were built.
Hopefully, this now makes perfect sense. But if not, let me try one more analogy. If you and I were identical twins, dressed identically by our mother, and were trained to play the violin for the same number of years by the same teacher, we would play the same piece of music (say Fritz Kriessler's Praeludium and Allegro) differently. Why? Because our brains are different. Even though the source code (written music) is the same, the executable program (our playing of the music) would be different because our processors (brains) have a different architecture even though the computer systems has all the same components like I/O (violin) and chassis (clothes and body structure).
By: Rodrigo Fraxino Araujo.
Many software engineering activities rely on the automated support afforded by tools. In order to maximize their benefits, they are often retrofitted to development environments that enable them to capitalize on facilities provided by compilers, debuggers, and profilers.
In this context, focusing on the integration of a set of mainstream C/C++ development tools (Valgrind, OProfile, Autotools, perf, among others) along with several in-house IBM ones (Advance Toolchain, FDPR, and others), we have used Eclipse as a basis to bring together a SDK comprising the necessary tools to assist in the development and analysis of C/C++ programs for Power Architecture, namely, the IBM® Software Development Kit for PowerLinux™
Two development environments are available:
(i) a native one, to run on Power, and
(ii) a client/server that runs on x86 or Power.
Several technical hurdles we ran into porting such tools into plugins, the workarounds to deal with such issues, and a more detailed description of the available tools and functionalities of the SDK can be found in a paper published on the IEEE portal:
By: Jeff Scheel.
It's been a few weeks since I have posted. I was on-the-road, doing what I affectionately call "dog on pony shows" where I am "just a dog." The trip started with 4 days of business meetings in Birmingham, UK. Most of these included presentations at the IBM STU on PowerLinux Trends and Direction as well as the IBM Software Development Toolkit. Following the event, we met with various customers, business partners, and system integrators in Bracknell, UK; Amsterdam, NL; and Brussells, Belgium.
Let me show my engineering background and provide my thoughts as a list (Sorry, Mom, I know paragraphs are preferred forms of writing, but as you know, I didn't did better in Engineering than English classes):
- The new PowerLinux servers are a great conversation starter. The competitive Total Cost of Acquisition (TCA) story eliminates the largest barrier to starting any discussion. If you have not already priced one out, pick your solution and learn more here.
- Many customers and partners are excited about emerging solutions in the area of Big Data Analytics. While they may not yet be implementing solutions, they all agree they have large volumes of unstructured data from which they will be attempting to learn in the coming years. The knowledge that PowerLinux is already focused on this solution space provides assurance of a roadmap forward.
- PowerLinux has made a program commitment to providing value-add that is resonating with who appear tired of owning the integration and support for separate hardware and software components. IBM's commitment begins with our investment in Linux as a technology lead by the IBM Linux Technology Center. To us in IBM's LTC, Linux is much more than software which runs on IBM HW: Linux is a vibrant community creating industry leading software based on values of open source software. On top of this foundation, PowerLinux delivers additional value to customers and partners through many aspects including delivering systems pre-installed with Linux, providing an optional Installation Toolkit for customers unfamiliar with Linux Installation, maintaining a YUM repository of value-add tooling for Linux-savvy customers, documenting extensively Linux use on Power Systems and PowerLinux servers through the IBM Information Center, facilitating application creation and porting through the PowerLinux Software Development Kit (SDK), supporting PowerLinux with IBM's world-class support capabilities just like our other Power operating systems, and committing to a technical community (this one) where all of these programs can be anchored, organized, and shared.
- The PowerLinux commitment to an SDK will be instrumental to the application ecosystem beyond what even I imagined. Our goal remains to provide a single integration point for PowerLinux application development on x86 hardware that is friendly and recognized to Linux application developers (Eclipse). We've only just begun this journey, but our tools which today are still running natively on PowerLinux are providing such dividends that customers are starting to ask if they should do their Linux and AIX application development with them. So, if you and/or your company have Linux applications (homegrown or formal offerings), be sure to take a look at our toolkit. It's free and we'll take your feedback on the community message board! Here's a link to the session presentation detailing many of the features of the toolkit.
That's all for now. As usual, comments, feedback, and questions are always welcome.
By: Brent Baude.
Fedora has made their alpha release for Fedora 17 on ppc64 available. The release notes
are publicly available and describe where to get the content (.iso). If you are familiar with the Fedora, please make sure you read the release notes because the initial loading of the installation image is significantly different than past releases and impacts things like network-based install.
Fedora 17 is the second release for the ppc64 architecture and is proving to be quite stable. Feel free to grab a copy and give it a try. And, the beta release is right around the corner.
By: Jeff Scheel.
Ever wondered what IBM means when they say "Power Linux"? I get questions all the time like, "How does Power Linux differ from RHEL or SLES?" So, I thought perhaps it might be time to address this in writing, in a common place.
Here's the simple answer: Power Linux generally refers to all supported Linux distributions that run on IBM Power Systems servers. This means that Power Linux includes all Red Hat Enterprise Linux (RHEL) and SUSE Linux Enterprise Server (SLES) versions. We simply say "Power Linux" instead of "RHEL and SLES" each time we wish to refer collectively to these Linux distributions. (What would one expect from us, the master of 3 letter acronyms and abbreviations?)
While this simplification sounds reasonable on the surface, in practice it has created some confusion. People believe that Power Linux is somehow different from SLES and RHEL on other platforms. It is not. Further, RHEL 6.2 for Power Systems is built from common source code, tested at the same time across platforms, made generally available on the same date, and supported the same way as RHEL 6.2 for x86 platforms. These same commonalities apply to other RHEL releases/versions, as well as SLES releases/versions. It is this standardization across multiple hardware platforms that elevates Linux from just another operating system to a multi-platform operating system that enables customers, business partners, and software providers to leverage hardware platform strengths without having to invest in new operating systems.
As my college physics professor used to say: "Is it as transparent as mud?"
By: Brent Baude.
Fedora 16 has now been officially released! The release notes can be found at:
Most of the imperfections mentioned in the release notes are around graphics/video cards. This is something that will be looked at closer in upcoming Fedora releases. Most significantly, this marks the first official Fedora release for ppc64 since the Fedora 12 time frame. Our preliminary feedback on Fedora for ppc64 has been positive. There a number of instances where it is being used heavily in open source projects.
Please feel free to try out the latest Fedora version and the team is always looking for new members who are wiling to hack for the better of Linux ppc64.
By: Brent Baude.
Fedora has announced a ppc64 Fedora 16 beta last week. The announcement can be found at the following URL:
There are many improvements between the Alpha and Beta for ppc64. Many of them revolve around automated console detection for IBM ppc64 hardware. The desktop is also improved and we now have a functioning Firefox.
This is a community-based effort and as
such we encourage folks to participate. The best mechanism to speak
with the team behind this effort is via IRC, where we hang out on
freenode in #fedora-ppc.
Give it a try!
Modified on by jscheel
by Jeff Scheel, IBM Linux on Power Chief Engineer
With LinuxCon North America upon us, I have been thinking a lot lately about the Power proposition of “open”. So, what? How does that help the Enterprise? My thought process around these questions flowed like this: open provides choice, choice enables flexibility, flexibility ensures greater efficiency in solutions, better solutions reduce expense. My conclusion: the Power System strategy around “open” ultimate saves customers money.
As an engineer, I like logical answers. This question about openness lent itself nicely to the mathematical Transitive Property of Equality. Remember it from math class? If a=b and b=c, then a =c. Applying the property to this situation, one idea leads to another through several steps to the final point where we can simplify the whole progression down to a final statement that the first equals the last. For my conclusion on the value of Power openness to hold, we need to evaluate each step in chain.
Assertion #1: open provides choice. Open choices occur both in the software and hardware layers on Power Systems. The opensource Linux operating system has enabled applications to be written with common tools, across multiple hardware platforms such that Enterprises now have open alternatives for many commonly closed environments. Databases provide an excellent example area – the market has traditionally been dominated by big, proprietary products but now has open, general solutions such as PostgreSQL and MariaDB as well as a whole plethora of newer specialized databases such as Redis, MongoDB, and CouchDB.
But open versus closed is not the only software choice. For open software, these additional decisions apply:
How will the software be acquired? It may come in the Linux distribution, be built from scratch, be distributed in binary form in the open source community, or be available from an Enterprise provider.
Who will support the software? You can support yourself, pay your Linux operating system vendor, rely on the community, or enlist the service of a third party like IBM on an Enterprise application provider.
What version of the software will get deployed? While Linux distributions tend to bundle a version they deemed stable at the time of the distribution creation, additional options include the latest and greatest in the community, the last stable version in the community, or just about any version in existence.
How many customization are applied to the software? The range of choices begins with none but also includes a few optimizations to any and all features needed to create a competitive advantage.
Options with software abound!
For hardware, IBM and the OpenPOWER Foundation Partners like Google, nVidia, and Mellanox are all committed to innovating around the Power processor-based systems from the chip level up through the whole platform. Choice has already begun in market with Tyan's 1-socket, 2U "Habenero" platform and new proposals such as the CP1 processor for the China market and the Open Compute Platform for Power from Rackspace both revealed at OpenPOWER Summit earlier this year in San Jose, CA. Thus, open has truly enabled choices not available in a closed world.
Assertion #2: choice enables flexibility. Many of the choices are completely independent. While proprietary software and support generally come from the application vendor, many of the combinations of open source options are independent. For example, as a client you might elect to purchase SUSE Linux Enterprise Server (SLES) 12 from SUSE and run it on IBM Power Servers, pay IBM for support, purchase MariaDB from MariaDB the company and pay them for enterprise support, while highly customizing your own Apache Tomcat webserver pulled directly from the Apache community. Further, if you really wants a certain feature in the Apache webserver, you may design it, implement it, use it, and even offer it back to the community for their benefit. Try that with proprietary software!
Assertion #3: flexibility ensures efficient solutions. When you can tailor the solutions to your needs, even to the point of writing code, solutions become exactly what the business needs. Proprietary software is like buying shoes: you goes to the shoe store, select from a limited set of models, each with a standard set of sizes and a limit number of colors. Open source enables a model of buying the type shoes one wants, in the size you need, and colors you prefer--even designing a custom shoe if so desired. One foot bigger than another? Easy. Feet bigger than a 10 ½ but not quite an 11? No worries. Got two left feet? No problem. Open source allows Enterprises the flexibility to enable what they need or invent it when needs are not met.
Assertion #4: efficiency reduces expense. When Enterprises get what they need, they save money through efficient operations – no unnecessary features, no software that almost does the job but not quite, and fewer hours on the phone understanding errant software behavior. This efficiency continues across hardware platforms as well. PostgreSQL running on a Ubuntu Server 14.04 operating system in a KVM guest behaves the same whether it runs on x86, Power, or another architecture. Further, administration of this environment will be nearly identical with the number of people needing to know the hardware architecture reduced to just a select few. In the “old days”, a different hardware architecture meant a different operating system, a new hypervisor, and maybe even a different application – a whole different IT team. Enterprises cannot afford these expenses. Open solutions keep an IT Staff running efficiently and optimally as they deploy the right solution on the best hardware.
Application of Transitive Property (Conclusion): open means expense reduction. Tying all these steps together, Enterprises have now been empowered through open source software to take control of their choices, implement what solutions they need, and use their operational efficiencies to invest in the next sets of innovation. “Open” saves money. With Power System, you get open choices with hardware and software. Are you getting the benefit of open or are you living in the past?
If you would like to learn more about Linux on Power and how Power Systems delivers choice through openness, look us up at LinuxCon in Seattle the week of August 17th. The IBM Power Team can be found in booth 316 at the Expo. If you did not make it to Seattle, do not hesitate to reach out and let us know how we can help you exploit open.
Modified on by jscheel
There is no doubt the acceptance and growing popularity of Linux on Power is here. With POWER based systems providing advantages over x86 systems in performance, capacity, memory and IO bandwidth, and reliability (I have intentionally left out the CAPI technology and am saying that discussion for another BLOG that can delve into that and the incredible capabilities it provides) and with the latest Linux distributions from RedHat, SUSE, and Ubuntu exploiting POWER8 technology, customers are now looking at hosting mission critical applications on Power Systems with Linux for a better customer experience at a lower TCO. (and Linux is Linux, right??....by the way, not really! But that will be the subject of a different BLOG)
Yes, Linux on Power has great capabilities and will expand rapidly, but I also believe you all have several critical decisions to understand as you start your implementations. As not everyone is actively running production on Linux on Power, I suspect that most all of you will start with a Proof of Concept or a Proof of Technology. And this is where decisions have to start be made and options chosen. In my opinion your decisions have to start at the application layer and then work down to the hardware server selection. Several years ago the choices were much easier since there were only specific elements available such as the virtualization layer (it was only PowerVM), the Linux distribution (previously only SUSE and RedHat were certified), the Cloud (Smart Cloud Entry only), Endianness (Big only), and the hardware support of POWER6 or POWER7 really only differentiated by the SMT levels. Now this has changed with many new options and the IBM support of key Open Sources technologies like OpenStack and KVM. And like Indiana Jones was told by the Grail Knight in the Last Crusade, “Choose wisely”. Your choices should also be chosen wisely and with forethought.
A suggestion, of mine, is to start at the application. First the application must be available (eg complied) for POWER or must be a script or scripting tool or Java application that is ISA neutral or can be compiled to the POWER ISA (PPC) such as Open Source code or your own “home grown” application. Choose whatever application you will (eg Websphere, SAP HANA, TSM, MariaDB, Redis, home grown, etc.) for the POC or POT but you then must determine the Endianness of the application or the Endianness that you will compile for. The reason is that the Endianness of the application MUST match that of the Linux Distribution. So, if you choose SAP, which is Big Endian, you need to choose a BE distribution like RedHat 6.5, RedHat 7.1 BE (not the LE RedHat 7.1 which is a separate SKU), or SLES 11. If you had chosen SLES 12 or Ubuntu you would have a problem since these are Little Endian distributions and your SAP HANA test would fail immediately. Now, skipping forward several choices, we must recognize that Little Endian applications can only run on POWER8 hardware. It can run in a partition, IFL on a POWER8 server (S8xx, E8xx) or on an S8xxL system, but not on POWER7 nor POWER7+ nor POWER6.
Many people ask, “what distribution should I use?”. First you must choose the correct distribution based on LE or BE capabilities. Then the differentiator normally is based on consistency. RedHat, SUSE, Ubuntu, Debian, Fedora, OpenSuse are all based on the Linux kernel for sure. But, they are all at different kernel levels, have different “support packages” included in the distro, have different administrative procedures for such items as tuning, install, management, EUI, support, etc. You should review specific requirements that may lead to a multi distribution environment versus consistency within the environment for a single skill set and single set of procedures. It should be noted that the interface to the Linux OS is consistent for applications, so that is not a major consideration although certain ISV applications may only be certified on specific distributions and releases. An example is that SAP HANA is only supported on SLES 11 at this time.
Another point, though not that significant, is that the different distributions have different prices and T&Cs such as pricing by cores or sockets and/or virtual machines. These should be reviewed and ordered correctly for entitlement compliance.
Now choose the support structure for Linux on Power. You have two choices basically…support from the distributor or support from IBM GTS. Each are good choices as both IBM and the distributor interact for fix resolution but there are differences in costs..eg, IBM charges for support for the entire server at a single price and distributors charge based on the entitlements. Another point is that if Ubuntu support is wanted, it can only be provided by IBM since Ubuntu is normally community support. Again, consistency within the Enterprise should lead to a clear decision here.
Now you need to decide on your virtualization technology. Your choices are PowerVM, KVM, or no virtualization, sometimes called bare metal. Bare metal implies no virtualization and associated overhead and as such can provide the highest performance of Linux applications on POWER8 Systems. If this is what you wish for example with analytics, HPC, etc, you can only run Linux on Power on POWER8 Scale Out systems (S8xx L’s) since only they have a hardware interface layer called OPAL (Open Power Abstraction Layer) that the Linux distributions must be enabled for in order to operate. OPAL as of today only is available on the S8xx L systems and not the Enterprise systems (E8xx) nor POWER7 systems. Also, although it will change soon, only Ubuntu (LE only) and SLES 12 (LE only) are enabled for bare metal (direct interface to OPAL). PowerVM is the tried and true high function virtualization technology for Power Systems. As of the 18.104.22.168 release, PowerVM will support concurrent usage of BE and LE Linux distributions with equally supported functionality. However PowerVM is specific to Power Systems and some customers may wish a consistent virtualization technology between Power and x86 systems. If this is the case, then KVM, specifically the PowerKVM product from IBM, should be considered. PowerKVM needs the OPAL interface to access the hardware and as such will only run on the POWER8 Scale out Linux only servers at this time. So, no running PowerKVM on POWER7 systems nor on Enterprise Power Systems. But if chosen to be the virtualization layer on the POEWR8 Scale Out Linux only servers, PowerKVM will support BE and LE distributions and applications. Since most of the internals are rooted in KVM, consistency with x86 procedures can be implemented both administratively and skill wise. However, if you are going to use RedHat distributions of Linux and RedHat as your Linux support provider, realize that RedHat support does not recognize PowerKVM as a supported environment and you should obtain RedHat Smart Virtualization as the supported by RedHat virtualization Layer.
So far I have a targeted application, Linux distribution, support, and a virtualization layer. Want Cloud enablement for automated provisioning? The Open Source community is working on OpenStack and IBM has embraced this in PowerVC…which is OpenStack productized for Power architecture. PowerVC has replaced the predecessor product VMControl which ran with System Director. OpenStack provides the ability to capture, deploy, and destroy VMs in the Power environment. You can run with PowerVC as your highest level or you can all the self-provisioning capabilities provided by IBM Cloud Manager with OpenStack or IBM Cloud Orchestrator. ICO provides broader platform support and additional business oriented functions. By the way, some people ask about VMware. The answer is no, VMware is only supported running on x86 systems.
Choosing the cloud layer and the virtualization layer also involves some planning. Since ICMOS contains Open Stack, you cannot run both PowerVC and ICMOS on PowerKVM…reason is you cannot have two OpenStacks managing one virtualization layer. But, if you choose to run PowerVM, both ICMOS and PowerVC talk to the APIs of the HMC (which must be at the 8.x.x level) to provide the automated virtualization. Again, plan ahead.
Finally you need to select a hardware platform. POWER7 is perfectly valid but you must recognize that if that is your choice you cannot run LE nor KVM. With POWER7 you will get BE support from SUSE, Redhat, Fedora and Open SUSE, but no Ubuntu (again LE only). As you move to the POWER8 technology, realize that at this time, OPAL is only implemented on the POWER8 ScaleOut systems for Linux only (S8xx-L models). Since OPAL and pHyp are both shipped on the “L” models, you can reboot and switch back and forth to support PowerKVM or PowerVM. If you plan to do this for test environments, it may be easier to order the PowerVM version and order PowerKVM as a MES later since PowerVM requires vet codes and PowerKVM does not.
Modified on by jscheel
by Jeff Scheel, IBM Linux on Power Chief Engineer
A great blog entry floated through my email inbox this week that raised a broader discussion topic for me: folks may have heard about the OpenPOWER Foundation, but may not know where to read the latest information. So, I thought I'd provide a few pointers.
The OpenPOWER Foundation website is the starting point for all information about the foundation. When all else fails, start there.
Under the site "News/Events" link at the top of the page, you will find a "Blogs" subtopic along with other things such as Press releases, Videos, etc.
You will also find main topics on this page such as "Get Involved" and "Technical". Keep your eye on these in the coming months, especially the "Technical" topic as we're in the process of putting in place new tools to facilitate the web presence many of the foundation public working groups need to effectively help grow ecosystem.
Hopefully, you'll find these pointers helpful. Thanks for letting me wax "educational" for a moment.
Now, let's get to the REALLY exciting information: technical information on using GPUs on POWER8 systems. The most recently blog entry on the OpenPOWER Foundation website, Porting GPU-Accelerated Applications to POWER8 Systems, serves as a great place to understand the recent announcements around GPUs on POWER, what they mean, and where to get more information if you want to start exploiting GPUs for your Linux on Power application.
What excites me most about this article is that it was written by Mark Harris from Nvidia (Chief Technologist for GPU Computing) not by IBM. His blog embodies the growing ecosystem around Linux and Power. In this particular case, the blog is a direct result of the OpenPOWER Foundation original partners' -- Nvidia, Google, Mellanox, Tyan, and IBM -- commitment to taking the I/T industry forward with a new generation of innovation around POWER.
This is what's different about Linux on Power this time. This is how we succeed. This is why I'm excited about our future.
Modified on by jscheel
by Jeff Scheel, IBM Linux on Power Chief Engineer
I couldn't resist the urge to use TLAs (three letter acronyms) to dispel the FUD (fear, uncertainty, and doubt) on my favorite topic, LE (little endian).
If you are like most customers (and my mother), the concept of data endianness rarely, if ever, enters your mind. You buy applications, operating systems, and computers. All you care is that the operating systems run your applications on the computer to accomplish your goals. If you have heard that Linux on Power is moving to little endian and are worried, your approach to survival is simple: focus on release planning details for your systems – applications, operating system, and hardware.
Who does care then about data endianness? Programmers, software vendors, hardware vendors and those 1% technology geeks who do development in the IT industry. These are the people who have noticed that the POWER8 hardware can operate with data in either big or little endian mode and for whom I wrote the “Just the FAQs about Little Endian” blog back in June. They appreciate how little endian simplifies their Linux applications running on both x86 and Power systems; they understand how little endian simplifies data sharing on disk or over the network between x86 and Power systems; and they drool over the potential of running GPUs (graphics processing units, sorry couldn't resist another TLA) on their Power Systems to create highly optimized applications common to scientific or analytic workloads.
But for the remaining 99%, what you need to know about LE can be simplified to the following key points:
Existing Linux on Power operating systems will be transitioning from BE (big endian) to LE, most likely at a major release boundary. At this boundary, the process of upgrading will involve more work than previous upgrades because the operating system and all applications will need to make the transition from BE to LE. SUSE has already announced that SLES 12 will be their transition point to LE. Red Hat shipped RHEL 7 as BE and has not announced their LE plans.
Note: Canonical will not be transitioning Ubuntu, because it started as an LE operating system.
Only POWER8 and future generations of POWER processors will be capable of running LE. As the operating system transitions on POWER7 and older systems, you will not be able to upgrade to the new LE releases. Just leave POWER7+ and older systems on the old release. If you want to run SLES 12 or Ubuntu 14.04, you will need a POWER8 system.
IBM plans to support LE operating systems in LPARs (logical partitions) and VMs (virtual machines). POWER8 and newer systems will eventually support intermixing LE and BE operating systems on both PowerVM and KVM, but this support will be a staged delivery with complete intermixing support around mid-year 2015. Completion of all testing of various BE and LE configurations takes time. Your patience is greatly appreciated. The LE FAQ above has some valuable details about current limitations.
Hopefully you now understand that you need not learn about esoteric programming concepts as we head into the brave new world of little endian Linux on Power. Instead, as we progress through this transition, if you simply spend a little more time in planning to double check support for your applications, operating systems, and hardware during each step, you will have success. That's what I'd recommend to my mother – just a little due diligence.
By: Tulio Magno Quites Machado Filho.
A new update release for the 7.0 series is now available.
This release provides many bugfixes, including:
For download links, more information and documentation, please refer to our official documentation page.
Please let us know if you have any questions about this release.
About the IBM Advance Toolchain for PowerLinux
The IBM Advance Toolchain for PowerLinux is a set of open source development tools (compiler, debugger and profiling tools) and runtime libraries that allow users to take leading edge advantage of IBM's latest POWER hardware features on Linux.
For more information about it, visit http://ibm.co/AdvanceToolchain.