Channel 9 - Entries tagged with Reliability

Inside Windows 7: Recovering Windows from System Degradation and Boot Failures

Charles — Mon, 30 Nov 2009 18:58:00 GMT

Windows 7 is capable of certain levels of self-repair, as you've learned. One of the new capabilities in Windows is its ability to recover from serious failures that can impact the OS's ability to boot. How does Windows 7 handle these errors? Can you boot Windows 7 into Safe Mode or to an earlier functional state when something really bad happens? Yes. You can, depending on the nature of the problem. How?

Stephan Doll, Pavan Kasturi, Desmond Lee and Baskar Sridharan make up most of the team that has enabled Windows 7 to be the most recoverable version of Windows to date. By ensuring that every Windows 7 machine has the ability to automatically diagnose and recover from most boot failures with little or no interaction from the user, this team's work promises to greatly reduce—or even eliminate—the impact of a serious issue that would otherwise cause significant pain for Windows 7 users.

Tune in.

Rico Mariani: Inside Visual Studio Beta 2 - Performance and Reliability

Charles — Tue, 20 Oct 2009 15:48:00 GMT

I caught up with the great Rico Mariani, Visual Studio's Chief Software Architect, after his keynote at a VS partner conference held on the Microsoft campus. He tells us all about the improvements in Visual Studio 2010 Beta 2. Rico and team have taken the performance and reliability of Visual Studio to new levels in this release. Gone are the days of synchronous assembly and COM component reference look-ups (woo hoo!!!). Gone are the long start up times. Gone are roughly 90% of the performance bottlenecks that slowed down the development experience inside the VS2010 Beta 1 IDE. The Visual Studio development team worked their tails off to improve perf and reliability across the board. Tune in to learn about what they did and what they will do prior to RTM. Truly excellent engineering goes on in building 42. Well done, team!

Rico also discusses his final blog post in his VS history series, a 5,000 word up to the minute historical piece. After watching Tina's great VS documentary series, Rico decided to add his own perspective in a 10 part blog post blitz. Great stuff!

Enjoy.

Inside Windows 7: RADAR - Windows Automatic Memory Leak Detection

Charles — Tue, 15 Sep 2009 15:29:00 GMT

RADAR is a memory leak detection technology built into Windows 7 and integrated with Watson (error reporting) and AutoBug (automatic bug filing). It allows Microsoft product teams and third parties to discover and fix memory leaks early in the product cycle and after release. Since RADAR runs on customer machines, leaks can be caught during public betas, after release, and by third parties, thus ridding the entire ecosystem of memory leaks. RADAR-shipped components are highly optimized to have no appreciable performance impact.

Meet RADAR developers Stephan Doll, Baskar Sridharan, Anthony Lorelli‎ and Keshava Subramanya. They dig into the architecture, design and implementation of this great technology. RADAR helps make Windows more reliable and stable by automatically pinpointing memory leaks in code that are then packaged up in bug reports that land in the hands of developers responsible for the memory leaking code. This means quicker to market solutions and knowledge gain that will prevent the same bugs from cropping up again: developers learn what went wrong and why so wthey won't make the same mistakes again. You'll learn about the most common mistakes made and you should use this to prevent memory leaks in your own native code.

Tune in. Learn.

Melur Raghuraman: Inside Windows 7 - Diagnostics and Troubleshooting

Charles — Thu, 03 Sep 2009 16:41:00 GMT

Windows Development Manager Melur Raghuraman and team have taken troubleshooting and diagnostics to a whole new level in Windows 7. For one thing, Windows 7 uses managed code "natively" as PowerShell has become the de facto language used for creating diagnostic algorithms that live inside of diagnostic packages. So, when something goes wrong eventually a PowerShell script runs and diagnosis happens.

You've probably already noticed the information flag that appears in your task bar notification area when Windows wants to tell you something important. Well, in order for Windows 7 to inform you of a problem and its solution it must first diagnose the issue and collect troubleshooting steps. Sometimes, and more so than ever before, Windows will simply fix the problem and let you know about it - this is a trend that will only become more common over time and with each iteration of Windows going forward. This troubleshooting fabric has both client and server (cloud) components.

How does this all work, exactly? What's the story?

Tune in. Lots to learn here. The new troubleshooting and diagnostics capabilities in Windows 7 marks a signficant step forward in the evolution of Windows supportability. Of course, you, the human user, can write your own diagnostic scripts - so you'll be more efficient when you need to diganosis and then fix some computer problem.

David Grant and Ryan Kivett: !Analyze - Automatic Root Cause Analysis

Charles — Wed, 02 Sep 2009 17:33:00 GMT

!Analyze is an automatic root cause analysis tool for software failures. For years, it has provided insight to engineers both inside and outside of Microsoft. It is a key enabling technology behind numerous higher-level feedback systems, including Windows Error Reporting and Watson.

!Analyze runs millions of times each day, producing actionable results from reliability telemetry data sent to Microsoft. Ordinary debugging tools report the file and function where a failure ended. !Analyze pinpoints where the failure started.

How does it work, exactly? What's the story behind !Analyze?

Meet two of the Software Developers behind !Analyze, David Grant and Ryan Kivett. They share with us how !Analyze works, it's history and provide a glimpse into it's potential future.Tune in.

Great job, !Analyze team!

David Fields and Bill Karagounis: Inside Windows 7 - Reliability, Performance and PerfTrack

Charles — Mon, 10 Aug 2009 18:31:00 GMT

PerfTrack is the feedback and monitoring system inside of Windows 7 that performs measurements on, well, all things related to the overall performance of the OS, especially as it relates to system responsiveness to user actions. So, when you click on something (an icon, a folder name, etc...), how long does it take for the user to receive an expected reaction from the system? What are the bottlenecks that lead to a poor experience (user-observable latency) when using some feature in Windows? Is the root problem in the design of the feature itself or with the underlying OS? Enter PerfTrack.

Here, Development Manager David Fields and Group Program Manager Bill Karagounis share their wisdom and experience in the world of OS performance analysis. David and Bill explain how PerfTrack works and we digress into an interesting conversation about power management.

PerfTrack is an example of a technology that provides incredibly important real-world information to Windows engineers that can be used to solve performance problems in Windows.

Enjoy!

Michael Fortin: Windows 7 Efficiency

Charles — Wed, 22 Jul 2009 20:42:00 GMT

The Windows 7 project involved very efficient software engineering planning and execution. It is no surprise that an equivalent level of efficiency exists throughout the OS (efficiency in how the OS deals with faults, threads, memory management, power management, process management, window management, graphics, audio, local search, diagnostics, and on and on - truly excellent, and efficient, engineering).

Michael Fortin is a Distinguished Engineer in the Windows Core Operating System Division. His team builds the technologies that help make Windows 7 reliable, stable and performant, which are core ingredients in any highly efficient general purpose operating system. You'll hear us talk about Windows 7 as a very efficient general purpose operating system quite a bit over the coming months. In fact, if I had to sum up Windows 7 in one word it would be Efficient.

Michael's team also builds the troubleshooting and diagnostics systems in Windows, including the internal mechanisms that construct fault data packages and sends them to cloud-based components which receive data from millions of clients running Windows 7. Michael's team is a global team - engineers are located in multiple places around the world including a stellar team of engineers located in Beijing, China (you'll meet them in the future right here on C9).

You may remember Michael from his last interview on Channel 9 that covered his work on Vista's SuperFetch and ReadyBoost technologies. Yep, these great technologies are alive and well in Windows 7 and have evolved to meet the needs of the evolving system and help add to the overall efficiency of Windows. (There, I wrote "efficiency" again...)

Over the past year or so, Michael's team has received, analyzed and acted upon a very large amount of data sent from Windows 7 Beta and RC running on a variety of PCs with a variety of hardware and software configurations in place. This data was used to construct new system features, like the Fault Tolerant Heap, and to engineer updates to existing mechanisms to make them more robust or performant or reliable or stable... You will meet some of his team here on C9 in the future and we will dig into many of the mechanisms Michael touched on in this conversation (Fault Tolerant Heap, Troubleshooting and Diagnostics, etc).

Here, Michael and I chat about the work his team has done, the engineering philosophy that has driven efficiency into Windows at all levels (from the kernel to the shell), the knowledge his team has gained about how Windows is used in the wild, what the most common problems have been and the solutions that are based on this important telemetry data. So, for all of you out there who chose to send fault data from your PC to Microsoft - THANK YOU. You truly have helped, in a fundamental way, to make Windows 7 the most efficient general purpose operating system from Microsoft to date. Yeah. True story.

Enjoy.

Sebastian Burckhardt - Data Race Detection with CHESS

Peli de Halleux — Fri, 12 Jun 2009 18:31:00 GMT

Sebastian Burckhardt gives a short tutorial of some of the new features of CHESS: data race detection and ChessBoard. CHESS is a concurrency testing tool takes a concurrent unit test and executes it with different thread schedules. Sebastian explains us how CHESS can detect data races, a very subtle kind of concurrency bug. You'll also learn how to drill into concurrency issues using the ChessBoard, a little application designed to drill and investigate concurrent tests.

CHESS home page: http://research.microsoft.com/en-us/projects/chess/
CHESS forums: http://social.msdn.microsoft.com/Forums/en-us/chess/threads/

The Research in Software Engineering team (RiSE) coordinates Microsoft's research in Software Engineering in Redmond, USA.

Inside IE 8 RC1 with Dean Hachamovitch and Jason Upton

Charles — Mon, 26 Jan 2009 22:34:00 GMT

IE team General Manager Dean Hachamovitch and IE Test Manager Jason Upton sit down with me to discuss the significance of today's IE 8 RC1 release. What did the IE team learn from the Beta 2 release? What changes did they make in response to customer feedback? Will the IE team still take and act upon fedback now that RC1 is here? With so many browsers on the market today how does IE remain competitive and maintain marketshare? No conversation on IE can be complete, of course, without talking about the web platform and standards so we go there....

Of course, you can expect this discussion to continue at MIX09 (and you'll be a key participant in the conversation with Dean and team in Vegas).

See the IE Blog for more detailed info on what's in IE8 RC1.

Tune in. This is a great conversation with two key leaders behind and in front of IE (Dean is the all up team leader (as you know by now given how many times you've seen him on C9 and at various conferences) and Jason is responsible for overall product quality (he owns the stuff you seldom see or hear about - software testing)).

Gabriel Aul: N-State Chaos and Windows Performance

Charles — Mon, 18 Aug 2008 21:09:00 GMT

Gabriel Aul is a 16 year Microsoft veteran who has always had his hand in the chaotic world of system performance and reliability, from technical product support and testing to being a leader on the Windows performance team. In fact, he was part of the team that developed the original Watson failure reporting tool. He's a dev at heart (once a dev, always a dev) and understands the complexities of Windows as a platform: Windows supports thousands of devices and the thousands of drivers that make them useful to users (devices sometimes have more than one driver, so add that to the complexity quotient...). How can so many devices (drivers) work together successfully (meaning not hosing the system) with so many supported configurations and possibilities for drivers to bring Windows to a screeching halt (think about task scheduling, resource allocation, background processing, foreground processing user mode code execution, kernel mode code execution and the sheer amount of concurrent running code, all over the place, all contending for Windows' attention...).

The world of Windows as platform is incredibly complex (n-state chaotic). It's amazing, actually, that the chaos doesn't lead to more performance and reliability issues. The Windows performance team has some really powerful tools (and an effort called Velocity) that can help ISVs find highly complex performance issues. Gabriel touches on this in this conversation and we address the continued need for more guidance and samples for developers.

One thing is for sure: The developers who write applications and drivers for Windows are great developers. You are craftsman, artists. Windows is a great platform in many ways because of the people who innovate on top of it. You know who you are. Yeah, you. Thank you.

Vince Orgovan: Windows Vista Telemetry

Charles — Mon, 11 Aug 2008 17:21:00 GMT

Windows Vista contains a much improved telemetry system that collects fault data and sends detailed reports to Microsoft that are used in fixing problems that cause apps to hang/crash (of course, this data only reaches us if you choose to send it...). What have we learned so far? What does Microsoft actually do with crash data? How do crash reports turn into bug fixes that make their way up to Windows Update or, more commonly, into third party application updates?

Meet Vince Orgovan. Vince leads the Windows reliability and analysis team who are tasked with analyzing crash data and isolating problems that cause applications to fault on Windows. Vince is very passionate about quality and his team works tirelessly to isolate problems that lead to crashes. Here, we learn about what we've learned from all the telemetry data we've gathered from Vista and Vince provides insights into the state of health of Vista in the wild. This is a great conversation. Enjoy!

Danny Kim: On FullArmor and Partnering with Microsoft

Charles — Wed, 20 Feb 2008 19:12:29 GMT

When FullArmor took up residence in the Microsoft Partner Solutions Center, their relationship with Microsoft rose to a whole new level.

This is a candid interview with FullArmor CTO and founding partner, Danny Kim, as he discusses Group Policy security software, how FullArmor partners with Microsoft beyond the norm, and what insights Danny has for other ISVs who are making their best efforts to work with Microsoft, and perhaps not generating the inroads they’d like to be seeing. Danny’s conversation with us highlights several inventive ways to take your relationship to the next level.

FullArmor is the first company to create and deploy altruistic viruses as a means of securing systems. Very interesting indeed!

Enjoy!

Low res download file.

Check out the Microsoft ISV site for more information related to partnering with Microsoft.

Start the Presentation Revolution - Nick Petterssen - Part 3

SoutheastArchitect — Fri, 12 Oct 2007 18:16:33 GMT

This is Nick's third part of the session from his presentation at Remix 07 Boston.

Italia 9: Alessandro Catorcini e Affidabilita’ del .NET Framework

Charles — Mon, 17 Sep 2007 18:44:33 GMT

Passate le vacanze, ecco puntuale la seconda puntata di Italia 9!

Questa volta Vittorio e’ andato a trovare Alessandro Catorcini, un altro genovese che fa il senior program manager nel common language runtime team. Dopo la chiacchierata di rito sul come sia finito a lavorare in America per Microsoft, Alessandro parla a ruota libera del CLR: si va dal positioning di Silverlight all’hosting del common language runtime in applicazioni ad altissima affidabilita’ come SQL Server. Durante la discussione alessandro cita un paper sull’hosting che puo’ essere scaricato da qui; fa inoltre frequente menzione del blog CLR Inside Out, disponibilie da qui.

Come di consueto, Alessandro terra’ d’occhio i commenti al video: se avete domande non esitate a premere “Reply”.

Arrivederci alla prossima puntata!

And the English version, below:

Italia 9: Alessandro Catorcini and .NET Framework Reliability

Now that vacation time is gone, here there’s the second episode of Italia 9!

This time Vittorio went to visit Alessandro Catorcini, another guy from Genova who works as Senior Program manager in the common language runtime team.After the usual chat about how he ended up working for Microsft in theUS, Alessandro talks about the CLR: the discussion flows from Silverlight positioning to the aspects of hosting the CLR on highly reliable applications such as SQL Server. During the discussion Alessandro quotes a paper about CLR hosting, that can be downloaded from here; furthermore, he often mentions the blog CLR Inside Out (feed here).

As usual, Alessandro will keep an eye on the comments; if you have questions please do not heistate to press on the “Reply button.

See you in the next episode!

Mark Russinovich: From Winternals to Microsoft, On Windows Security, Windows CoreArch

Charles — Fri, 23 Mar 2007 22:21:00 GMT

If you write code on Windows or like to know what goes on under the hood in Windows, then you've no doubt heard of Mark Russinovich. He's an OS kernel expert and a co-founder of Winternals; a company that produced must-have operating system and development utilities for Windows (Winternals is now a Microsoft subsidiary as we purchased them in July, 2006. Yay!).

Mark is now a Technical Fellow in Windows and is a member of the Windows Core Architecture team (you met some of the other big brains on the CoreArch team last year).

Here we talk frankly about Mark's history, his coming to Microsoft, Windows security, what the CoreArch team does, what his role is, etc. Tune in.

Processes Gone Wild: Understanding Windows Vista Reliability Mechanics

Charles — Fri, 16 Mar 2007 20:53:58 GMT

Ever wonder about the physiology of a dying process? How, exactly, does an OS, like Windows Vista for example, know when a process is dying or hung or just out of its mind? What does Vista do, exactly, when it encounters a troubled process?

Well, Kinshuman, a Windows core os dev lead, Cornel Lupu, a Windows core os dev mananger, Jeff Braunstein, a reliability PM, and Siamak Ahari, a reliability test lead, will show you exactly how Windows Vista deals with troubled processes. We also dig into what happens with Dr. Watson data and how Dr. Watson has been improved in Vista. Of course, we spend a good deal of time talking about the complexities of operating system reliability in general. Basically, we have a great conversation about a giant topic.

There are some fundamental architectural changes in how Vista detects and deals with processes that need to be dealt with... You can think of processes as cellular units. In biological systems like you and me, we have powerful regulation mechanisms that deal with cells gone bad. Vista has similar constructs and we dig into them in this interview with some of the folks who built them.

Making Windows Vista Reliable: Introduction to Windows Reliability with Mario Garzia

Charles — Wed, 28 Feb 2007 19:08:54 GMT

One of the characteristics of a great general purpose operating system is simply being reliable - limiting user disruptions. Windows Vista is our most reliable OS to date. How can we say this? Well, this is Vista Week on Channel 9 and here we take this broad question to the development manager for Windows Reliability, Mario Garzia.

Mario and team have done some amazing engineering (you will meet more of the Windows Reliability team in the coming days) and Vista is full of new components that work in concert to make Vista a highly reliable system. Listen in. Learn.

Windows Vista Diagnostics: Moving closer to a self-healing OS

Charles — Tue, 27 Feb 2007 16:39:00 GMT

Sometimes problems occur (system or application level exceptions happen, applications might crash, hard disks fail) in complicated systems like modern personal computers.

In Vista, the system is capable of understanding a wide variety of problems as they occur and, in many cases, fix them without disrupting the user. In certain cases, the system is unable to automatically repair a given problem so Vista will inform the user of actions to take to solve the problem.

Even for hardware critical failures like a hard disk crash, Vista will help the user understand the problem and guide them through a set of steps to get to a working solution (in the case of hard disk failure, obviously the solution is back your data up! Vista will actually run you through a helpful backup "wizard" in this case, but you'll need to get some hardware to store your data...).

Meet Melur Raghuraman, Development Manager, Matthew Kerner, Lead PM, and Jeff Meng, Development Lead. These are some of the people responsible for making Vista our most reliable OS to date. They are members of the Windows Reliability team.

You will meet more of the Reliabiliy People as Vista Week continues here on Channel 9.