A higher number of CPU sockets will then constitute a larger system with correspondingly larger memory to handle applications with large memory and compute requirements. Among the applications that benefit from Scale-Up systems are SAP/Hana, transactional databases, scientific simulations, Advanced Analytics, Real-time Streaming, AI, etc. A common requirement for all of those applications is to have access to large amounts of memory across the CPUs in a cache coherent manner. Conceptually, a large number of CPUs are vertically connected with node controllers to achieve 2X performance and more. A scale out NAS architecture can support a single cluster, or multiple clusters with virtually unlimited capacity. Each new device comes bundled with its own set of resources to help optimize the total efficiency of your storage system.
- Scale-up and scale-out are the main ways to add capacity to your infrastructure.
- Eventually, you will run out of space on the rack for the hardware, so you don’t have to worry about some of the same issues as you would with a scale-up architecture.
- By scaling it up you add more RAM and processing capacity to your existing server.
- ADCs host a virtual IP that is the front end to pool members on the back end.
- Erasure Coding – offers similar data protection capabilities as RAID 5 and RAID 6 by creating parity for data sets in order to provide protection against failures .
NVMe/TCP enables a move to disaggregated (i.e. scale out) shared storage. The answer is that scale-up has its drawbacks in certain situations. One issue is that the switch over to a new machine will cause downtime, which does not happen with scale-out. In scale-out, you are, by definition, adding a new instance that enables switchover. Scaling up infrastructure is viable until individual components are impossible to scale anymore — making this a rather short-term solution. By consolidating or eliminating the needs for multiple point products, you can save on training, maintenance and support costs.
Then as business evolves and their storage needs grow, they can incorporate additional capacity – all without tedious forklift upgrades. While scale out storage infrastructures are usually more expensive to deploy upfront, their hassle-free approach to scalability often leads to a more cost effective investment in the end. More significantly, some use cases simply don’t favor the scale-up approach. A workload may not necessarily move faster when it’s on a higher capacity machine, for instance.
In most cases, this is handled by scaling up and/or scaling out . There have been many studies and architecture development around cloud scalability that address many areas of how it works and architecting for emerging “cloud-native” applications. In this article, we are going focus first on comparing scale-up vs scale-out. Scale-up is generally the standard form of the traditional systems of block and file platforms. This system consists of many shelves of drives and a pair of controllers. The problem with this is that once you have reached the maximum capacity or performance limits, you only have the option to add another system next to it. New systems need to be added to grow with your data demands as your business grows.
Lock Ransomware Out with Commvault & Cloudian
One other note about scaling up is that on-demand functionality from platforms like Microsoft Azure or Google Cloud makes these types of changes easy and highly automated. The elasticity of these cloud services might lead companies to be able to innovate how they scale up.
Cloud computing providers, such as Microsoft Azure and Google Cloud, allow you to scale-up your virtual machine with a few clicks. Cut the ties to scale-up and shift to scale-out for a more reliable, cost-effective approach that provides the flexibility you need. Essentially what this means is that the user/application is not aware of which node its data resides – it is just presented with a storage container with a Fully Qualified Domain Name . The object storage system manages the store, retrieval, and protection of the data objects and manages the data placement across all the nodes within the cluster. This technology is older but reliable, and businesses have been using it for a long time. This system is one that companies have grown to trust for their data management needs. However, it may be time to invest in a newer approach that will be more efficient and more effective.
HyperIQ Observability & Analytics
Stackify’s APM tool, Retrace, supports monitoring for both scale-up and scale-out environments with packages to scale either up or out as needed. Troubleshooting and optimizing your code is easy with integrated errors, logs and code level performance insights. Scale-out for cloud-like flexibility to expand capacity as you need it.
Scale-out systems create clusters, which are co-equal nodes that work together. Nodes can be added or removed, which means that things like bandwidth, compute, and throughput will increase or decrease as needed based on these clusters. Upgrading makes it easier to move all users, workloads, and data without any downtime. These systems can learn how to auto-tune and self-heal the resources, allowing the cluster to adjust to the demands of the data system architecture easily. By using the cloud you do not have to purchase new hardware every time you want to upgrade your system to grow it with your business. Scale-Up is done by adding more resources to an existing system or to a compute node to increase the performance of the node. Scaling up provides a large memory foot-print across multiple CPU sockets (8S, 16S, 32S, 64s, etc.).
When to choose scale-up
If you don’t have much money to invest in your data storage right away, you will be better off sticking with scale-up solutions. These solutions are also a good option if you have a small business that may not be growing anytime soon. However, if you do have a considerable amount of money to invest right away—or you predict rapid growth in your business—the scale-out solution could be a better choice. Just be sure to enlist the help of a strong tech professional to ensure that you can get the perfect solution for your individual needs. The scale up concept is even more of a hassle when you need fork-lift upgrades. These are replacements and additions that call for heavy lifting. In many cases you’re forced to copy every piece of data from the old server over to a new machine.