As discussed in our previous blog, cloud computing is commonly heralded as the future, in large part due to the ability to procure and to pay for IT infrastructure resources on demand. The problem is that the cloud does not provide the levels of control or performance that are required by mission-critical applications. In this installment, we will explore in more detail the merits and drawbacks of typical on-premises alternatives to the public cloud.
Traditional Scale-Up Storage
Scale-up storage architectures are the longest standing. These arrays are configured with a fixed number of controllers (typically two). Additional resources, such as disk drives, may be added to the system as capacity requirements increase. Typically, scale-up architectures are ideal for serving point workloads with fairly predictable requirements. They are also typically capable of delivering the fastest levels of performance of per volume performance on fixed workloads. The problem is that workloads are becoming more dynamic and unpredictable, and that the performance of scale-up systems tends to degrade as more capacity is added, because the controller compute resources are not upgradeable and become overwhelmed with Input/Output (IO).
Scale-up storage systems are limited by the maximum levels of drives and performance that the storage controllers can handle. If a system’s limits are exceeded, the controllers either need to be upgraded (if the vendor’s architecture allows) or an entirely new system must be added for additional compute and storage. Silos of data are created, and multiple systems must be purchased, racked, stacked and managed. Additionally, the balance of compute and storage, that was once ideal for the specific workload can quickly become imbalanced; resources can quickly become over or under provisioned.
Scale-out architectures emerged to address some of these pain points. In a scale-out approach, resources (including storage capacity) across multiple systems are aggregated into a centralized, shared pool. The pool of resources is no longer bound by the constraints of a singular system; a new system may be deployed to expand capacity or performance. This creates the opportunity for more flexibility, better system utilization, simplified management, and a stronger ability to run multiple workloads in parallel (also increasingly a requirement for modern businesses).
The problem with the scale-out approach is that a minimum configuration of three nodes is typically required, which may be more than a particular project requires for a long time (if ever). In a scale-out approach, servers are clustered together so that compute, storage capacity and networking may be pooled. These clusters are typically called nodes. Additionally, performance is often impacted by the heavy levels of communication between systems over the network that are required to keep systems in sync and to meet data protection service level agreements. Scale-out storage systems require parallelism to deliver the performance they promise either, through many workloads using the system or workloads that of themselves are innately parallel.
The concept of composable storage is developing, to further boost infrastructure agility and utilization through even more granular and fluid resource allocation. Composable storage virtualizes storage resources into a shared pool, from which virtual storage resources may be created on demand and automatically, according to application or workload requirements. We will define composable storage in more detail in our next blog, but effectively, composable storage stands to bring the enterprise closer to the resource agility that is inherent in the public cloud.
The problem with scale-up, scale-out and composable storage approaches alike when it comes to facilitating a cloud-like model on premises, is that infrastructure still needs to be procured upfront. As we will discuss further in our next blog, composable storage brings the enterprise closer to a highly utilized and agile infrastructure, but storage professionals should look further for the opportunity to pay on a consumption-based approach, as well.
IT professionals are hearing a lot about composable infrastructures and many vendors are claiming to offer a solution, but only a few have truly composable solutions ready for deployment today. To learn more about composable infrastructure join Storage Switzerland and Kaminario on May 31st at 1:00 pm ET /10:00 am PT for our next 15 minute webinar. During this webinar listen in as our panel of experts discuss what composable infrastructures are, how they have evolved and most importantly what to look for in a composable solution.
Sponsored by Kaminario