Top 5 Service Performance Challenges in the Cloud
March 16, 2011
Russell Rothstein
Share this

What do Amazon EC2, Microsoft Azure, and Google Apps have in common? They’re all cloud computing services, of course. But they share something else in common — each of these clouds has experienced periods of outages and slowdowns, impacting businesses worldwide that increasingly rely on the cloud for critical operations. And while there’s a great deal of publicity when these prominent public clouds suffer outages, it’s no less damaging to the business when an IT department’s private cloud goes off-line, even if it doesn’t make the news. It’s no wonder that according to analyst firm IDC, two of the top three concerns that CIO’s have about cloud computing are performance and availability.

Moving services to the cloud promises to deliver increased agility at a lower cost − but there are many risks along the way and greater complexity to manage when you get there. The following are five critical hurdles that you may face when implementing and operating a private cloud or hybrid cloud and how you can overcome them.

1. Will it work? How can you tell which applications are suitable for cloud and plan a successful migration?

Not every application is suitable for the cloud. And sometimes one part of an application is cloud-ready while other components are not. You need to identify the most suitable applications and components for migration, identify potential problems such as chattiness and latency that are amplified in the cloud, and create a performance baseline that you can test against after migration. With a clear picture of service dependencies and infrastructure usage, you can create a checklist that will ensure a complete and successful migration.

2. Performance – If you don’t know which physical servers your application is running on, how do you find server-related root causes when performance issues arise?

In fully-dedicated environments, we sometimes use infrastructure metrics and events to diagnose performance issues. But inferring application performance from tier-based statistics becomes challenging – if not impossible – when applications share dynamically allocated physical resources. To manage application performance in the cloud, you need a real-time topological map of service delivery across all tiers. Since the landscape is always changing, it’s essential that the dependency map is dynamically generated and automatically updated for every single transaction and service instance.

3. Chargeback – How do you know how much CPU your application is consuming in order to choose an appropriate chargeback model or verify your bills?

IT needs a new paradigm for assessing resource consumption in order to transition from a resource-focused cost-center to a business-service-focused profit-center. But traditional chargeback and APM tools do not collect resource utilization per transaction to enable business-aligned costing and chargeback paradigms. For the cloud, you need a solution that monitors consumption for every service across multiple applications and tiers, so you can accurately cost services, decide on appropriate chargeback schemes, and tune applications and infrastructure for better resource utilization and lower cost.

4. Not aligned with the business – How do you ensure that services are allocated according to business priority?

Clouds offer us new levels of dynamic resource allocation. However, to ensure that SLAs in the cloud are met, you must be able to prioritize the allocation of resources based on measurements of real end-user performance and an accurate view of where additional resources can truly alleviate SLA risks. To make that possible, you need a clear picture of resource consumption at the transaction level and business intelligence about the impact of each infrastructure tier on performance. Provisioning based on business priorities becomes even more critical as cloud architectures transition to a dynamic auto-provisioning model.

5. Over-provisioning – How can you right-size capacity and prevent over-provisioning that undercuts ROI?

Sharing IT infrastructure can be more efficient and cost-effective – assuming you have an accurate picture of resource usage for each service, an understanding of how that allocation affects SLA compliance, and the ability to prioritize resource allocation. In the cloud, a complete history of all transaction instances, including precise resource utilization metrics and SLAs, is essential for making intelligent decisions about provisioning. And with an accurate picture of resource consumption for each business transaction, cloud owners can plan future capacity requirements accurately.

Russell Rothstein is Founder and CEO, IT Central Station.

Share this

The Latest

June 29, 2022

When it comes to AIOps predictions, there's no question of AI's value in predictive intelligence and faster problem resolution for IT teams. In fact, Gartner has reported that there is no future for IT Operations without AIOps. So, where is AIOps headed in five years? Here's what the vendors and thought leaders in the AIOps space had to share ...

June 27, 2022

A new study by OpsRamp on the state of the Managed Service Providers (MSP) market concludes that MSPs face a market of bountiful opportunities but must prepare for this growth by embracing complex technologies like hybrid cloud management, root cause analysis and automation ...

June 27, 2022

Hybrid work adoption and the accelerated pace of digital transformation are driving an increasing need for automation and site reliability engineering (SRE) practices, according to new research. In a new survey almost half of respondents (48.2%) said automation is a way to decrease Mean Time to Resolution/Repair (MTTR) and improve service management ...

June 23, 2022

Digital businesses don't invest in monitoring for monitoring's sake. They do it to make the business run better. Every dollar spent on observability — every hour your team spends using monitoring tools or responding to what they reveal — should tie back directly to business outcomes: conversions, revenues, brand equity. If they don't? You might be missing the forest for the trees ...

June 22, 2022

Every day, companies are missing customer experience (CX) "red flags" because they don't have the tools to observe CX processes or metrics. Even basic errors or defects in automated customer interactions are left undetected for days, weeks or months, leading to widespread customer dissatisfaction. In fact, poor CX and digital technology investments are costing enterprises billions of dollars in lost potential revenue ...

June 21, 2022

Organizations are moving to microservices and cloud native architectures at an increasing pace. The primary incentive for these transformation projects is typically to increase the agility and velocity of software release and product innovation. These dynamic systems, however, are far more complex to manage and monitor, and they generate far higher data volumes ...

June 16, 2022

Global IT teams adapted to remote work in 2021, resolving employee tickets 23% faster than the year before as overall resolution time for IT tickets went down by 7 hours, according to the Freshservice Service Management Benchmark Report from Freshworks ...

June 15, 2022

Once upon a time data lived in the data center. Now data lives everywhere. All this signals the need for a new approach to data management, a next-gen solution ...

June 14, 2022

Findings from the 2022 State of Edge Messaging Report from Ably and Coleman Parkes Research show that most organizations (65%) that have built edge messaging capabilities in house have experienced an outage or significant downtime in the last 12-18 months. Most of the current in-house real-time messaging services aren't cutting it ...

June 13, 2022
Today's users want a complete digital experience when dealing with a software product or system. They are not content with the page load speeds or features alone but want the software to perform optimally in an omnichannel environment comprising multiple platforms, browsers, devices, and networks. This calls into question the role of load testing services to check whether the given software under testing can perform optimally when subjected to peak load ...