Application Performance — 28 June 2013
- Nagraj Seshadri, Director of Product Marketing, Compuware APM Business Unit, says:
Anyone who’s ever managed a complex distributed application knows the pain of identifying the source of application performance problems. It’s not necessarily the “fixing” that’s the challenge … it’s the “finding.” No one wants to spend a lot of time finding problems, and most organizations can’t afford anything less than the most expeditious root-cause identification possible. Moreover, in some cases problems may be almost impossible to pinpoint, hidden away behind all the dynamic complexity.
To this end, Compuware has announced their new PureStackTM Technology. An industry first, Compuware’s PureStack Technology redefines the boundaries of APM by going beyond just monitoring applications, to telling you how user experience and application performance issues are impacted by the underlying infrastructure issues, whether it be a CPU, memory, disk or virtual machine, for example. This helps improve the speed and accuracy with which the root cause of performance problems can be identified, prioritized and fixed.
Traditional application performance management (APM) tools that focus solely on application performance can reveal valuable information alerting IT teams to performance problems. But these tools can be insufficient, because they neglect to address how the underlying infrastructure impacts the application. Put another way, solutions that focus on the performance of an individual application may measure criteria like end-to-end transaction time. But they do not allow for troubleshooting that would indicate why a transaction may be performing poorly within a tier of the infrastructure. They cannot link infrastructure issues to the application performance and user experience.
Exacerbating the problem is the fact that today’s data centers are growing much more complex with virtualized n-tier environments spanning private, public and hybrid clouds. In addition, virtual and physical resources are mixed in many data center environments. The number of spots where potential application performance issues can arise is increasing dramatically, while the number and range of applications considered “mission-critical” is growing. This can lead to excessive guesswork, finger-pointing and longer mean time to repair (MTTR), when every second of a slowdown directly translates to frustrated customers and revenue loss.
Combined with Compuware’s patented dynaTrace PurePath Technology™, PureStack directly correlates guest and host infrastructure health to individual application transactions and affected end users in real-time. This technological breakthrough delivers the industry’s first and only APM solution that enables application operators to quickly gauge the impact of infrastructure problems in the context of user experience and business performance.
PureStack Technology automatically discovers, maps and collects critical system and infrastructure health information along the infrastructure “stack” including hypervisor, operating system, storage, process and CPU. This infrastructure health information is tied directly to each PurePath, which contains cross tier transaction detail, including end-user and code-level context. Together, PureStack and PurePath provide a three-dimensional view of how infrastructure health impacts application performance and availability.
Compuware APM powered by PureStack Technology delivers:
- Smarter APM with Easy Infrastructure Monitoring: The first and only APM solution that monitors all key infrastructure metrics and automatically correlates their impact on individual transactions and end users with 100 percent visibility into all transactions 24/7—from the end user, across all tiers to the database and back, in the most demanding production environments. Compuware APM’s unique and unified agent technology automatically detects and maps linfrastructure to applications without manual configuration.
- Three-Dimensional Root-Cause Analysis: PureStack uniquely complements PurePath Technology to deliver enhanced out-of-the box transaction flow and infrastructure views that provide operators with detailed and highly accurate insights never before possible:
- Top-down Dependency Analysis: PureStack provides exact detail on all infrastructure components including CPU, memory, disk, I/O and other metrics that are necessary to answer a single user request. Even interfering processes not related to the request are discovered.
- Bottom-up Impact Analysis:PureStack shows every single user request as well as all categories of user requests across applications and business transactions that use a specific infrastructure component.
- Session Recordings Eliminates Need to Replicate Problems: Every transaction is recorded along with all system health metrics, and can be “played back” when a performance problem is detected.
- Heterogeneous Infrastructure Support: Unmatched breadth of support across all major operating systems including: Windows, Linux, AIX, Solaris and HPUX. Hypervisors, including VMware and Xen are auto-detected, even in cloud environments. Amazon and Windows Azure public cloud are also supported. Broad environment support covers Java, .Net, PHP, Apache/IIS, big data, database access, C/C++, Message Broker, MQ and mainframe applications.
Where mission-critical applications are concerned, time is money, and issues with user experience and application performance can severely impact the business. Organizations need actionable, prioritized information that pinpoints the issues that have the greatest negative impact as opposed to just more data, and this is what Compuware PureStack Technology delivers. The combination of how PurePath can trace a transaction through a wide variety of application environments and middleware, and the ability to cross-correlate issues with those transaction traces with PureStack infrastructure data, is a differentiating and unique feature of the Compuware APM solution. It makes the lives of IT operators a whole lot easier.