As companies continue to embrace virtualization technology and consolidate their server farms, they may find the technology brings an unexpected, and unwelcome, guest to their data centers: hot spots.
This may come as a surprise given that companies are using virtualization to reduce the number of servers in their data centers, by ratios of 10:1, 20:1 or even higher. If you’re reducing the number of servers in your data center, you should also be decreasing the overall IT load – and thus need less total cooling capacity, not more, right?
Right, but a host server tends to draw more power than a traditional non-virtualized server. As a server is loaded up with more and more virtual machines, its CPU utilization increases. Whereas CPU utilization for a typical non-virtual server is around 5% to 10%, for virtualized servers the figure could be 50% or higher. A server with a 50% utilization rate will draw about 20% more power than one at 5% utilization.
What’s more, hosts often require increased processor and memory resources, which can further raise their individual power requirements.
These bulked up servers tend to get installed and grouped together, creating localized high-density areas. This, of course, can lead to hot spots. The existing air distribution system may not be able to cope or respond sufficiently. This, of course, can then lead to unexpected shutdowns.
Several strategies exist for cooling high-density racks. The two main ones are to simply spread out high-density equipment or to create an isolated high-density pod within the data center with its own dedicated cooling air distribution and containment system.
The idea behind spreading out the high-density loads is to ensure no single rack exceeds the design power density, which will make cooling performance more predictable. The big benefit of this strategy is that you won’t need any new power or cooling infrastructure.
The strategy is not without potential disadvantages, however. They include increased floor space consumption and higher cabling costs. It’s also possible that you’ll see reduced electrical efficiency if air paths aren’t contained. And management typically doesn’t like to see half-filled racks either. Implementing this strategy also means you need to have complete control over where any individual server is placed.
Creating a high-density pod is often a more efficient way to deal with virtualized servers. This involves consolidating all high-density systems down to a single rack or row(s) of racks. Then you bring in a dedicated cooling system or air distribution, such as by using close-coupled, rack or row-based air conditioners. In addition to dedicated cooling, the pod would ideally employ an air containment system . A pod that combines shorter air paths, contained air streams, and variable frequency drive fans best ensures highly virtualized servers and other high density gear are efficiently cooled without risk of creating hot spots.
The advantages of the high-density pod approach include better space utilization and higher efficiencies in addition to maximizing rack density. It’s also possible, if not likely, that the pod would actually add cooling capacity to the rest of the data center. This is particularly likely if hot and cold air streams are well contained.
For a more detailed look at high-density pods, see APC by Schneider Electric white paper number 134, “Deploying High Density Pods in a Low Density Data Center.” To learn more about how virtualization impacts the physical infrastructure, see white paper number 118, “Virtualization and Cloud Computing: Optimized Power, Cooling, and Management Maximizes Benefits.”
IBM Cloud offers a full complement of cloud-based virtualization solutions, spanning public cloud services through to private and hybrid cloud offerings. You can use it to create and run virtual infrastructure and also take advantage of services ranging from cloud-based AI to VMware workload migration with IBM Cloud for VMware Solutions.Terms like “server farm” tend to bring a certain image to mind — a warehouse with row upon row of black boxes with blinking lights. Those are servers, right? Yes, but the top-of-mind image begs one question …
Is a Server Physical or Virtual?
When we picture a server farm or data center, what we’re imagining are physical servers, so called because they are here with us as tangible, physical data center infrastructure. Physical servers are electronic equipment, not so different from our televisions or smartphones.
But not all servers are physical. Today, many organizations rely primarily or exclusively on virtual servers, and those are something different.
Before we jump into the physical versus virtual question, are we clear about what a server is? Because it will come up later.
Just to be sure, a server earned its name because it serves resources to computers over a network. There are various types of servers, typically named for what they do — email servers, application servers, file servers — you get the picture.
The first servers were physical and typically deployed with a single function. As computing power increased per server, we learned that we could virtualize server hardware and perform the same function with fractional hardware resources. Now servers come in both flavors. What is the difference between a physical server and virtual server?
What Is a Physical Server?
A physical server refers to a piece of hardware. It’s a recognizable machine with motherboard, CPU, memory, and the like. Often referred to as “bare metal servers,” physical servers have no gap between the physical hardware and the operating system. A physical server might run Linux, Windows, or some exotic O/S but it will run only one O/S in one instance.
What Is a Virtual Server?
A virtual server is an abstraction of a physical server and emulates those server functions. Multiple virtual servers can be deployed on a single physical server, and that’s one of the key advantages of the technology, as we’ll soon see.
If a physical server can only run one type and one instance of the O/S. If a physical server houses multiple virtual servers, on the other hand, these virtual servers operate like independent servers. Each server runs its own O/S and uses its designated allocation of computing resources, memory, storage and even network components.
Physical Server vs. Virtual Server—When to Use One over the Other
What if you’re considering a virtualization option like VMware vs. physical server technology? Which is best?
Unfortunately, there’s no simple answer. When it comes to physical and virtual servers, neither wins on every count.
- Virtual server vs. physical server performance – that battle goes to the physical server
- Virtual server vs. physical server cost – the virtual server emerges victorious in the end.
As with so many things in technology, it’s a matter of selecting the best option for the particular use case.
Take cost, for example. If you’re starting from nothing, purchasing a physical server plus the software to create virtual servers on it may seem the more difficult and expensive option at first. The balance tips as soon as one needs to upgrade servers or if one is virtualizing an existing environment. It is less expensive to upgrade virtual servers, because you do not necessarily have to purchase new hardware on which to run them. The upgrade migration tends to be easier to complete.
Server virtualization also drives efficiency. Without virtualization, server utilization rates can be quite low. Moving to virtual servers allows an organization to do more with the same number of physical machines, and without increasing the footprint in the data center. In the early days, a single physical server could run 10 or more virtual servers, and capabilities have only increased.
There are typically energy savings as well, because servers are hungry for electricity even when doing nothing. It’s better from an environmental (and electric bill) standpoint to spend that energy to do something. One server running at a high utilization uses less power than 10+ servers loafing along.
Benefits of Virtual Servers and Physical Servers
Physical ServerVirtual ServerCostHigher total cost. Initial purchase may save money on software, but upgrades and scaling are more expensive.Lower cost in the long run. Initial purchase of hardware and software can be more expensive but upgrading and scaling are far more cost-efficient. Virtualizing an existing environment maximizes value of hardware.Space RequirementsLarger physical footprint.Space-efficient because multiple virtual servers can run on a single physical server.PerformanceDedicated resources mean better overall performance.Shared resources reduce efficiency. Stability can be an issue.SecuritySecurity advantages. Configured for each physical server.Centralized for easier management.ImplementationMust be physically installed and configured. Migration can be challenging.Deploy, run, and move easily across the environment.ScalabilityMore difficult to scale; requires additional hardware.Scalable on-demand.Maintenance24/7 monitoring and management are essentialIssues affect only one physical entity which can simplify troubleshooting.
24/7 monitoring and management are essential.Ability to isolate physical failures from the OS/Application can limit risks of downtime.
Business continuityIncreased risk because server exists on-site.Facilitates geographically disparate failover, as virtual servers can be easily replicated in the cloud or colocation facility.Let us sum it up:
- The sheer performance of physical servers makes them the preferred choice for demanding workloads. If processing speed and/or volume are primary considerations, look to physical servers as your workhorses.
- Virtual servers, on the other hand, are masters of scale. Organizations that need to flexibly scale resources up and down will typically do better with virtual servers, especially if budgets are tight. That’s great for startups and SMBs but also fits more variable needs within large enterprises.
Virtual Machine vs. Server—Same or Different?
Remember solving analogies like these in high school?
Physical server: virtual server: physical computer: virtual desktop (VDI)
It’s shorthand for saying the same relationship holds between a physical server and virtual server as between a physical computer and a virtual one (which we call virtual desktops). Both virtual servers and virtual desktops are abstracted (or virtualized) versions of their physical counterparts.
PCs and servers aren’t the same thing, so VDIs and virtual servers aren’t the same, either. PCs provide services, such as software applications, for a user; servers deliver resources to multiple PCs.
You will sometimes read that there is no difference between a virtual server and a virtual desktop, or you’ll stumble across explanations of a virtual vs. physical machine that conflate PCs and servers. In fact, it’s surprising — even a bit upsetting — how frequently the terms are used interchangeably, even by reliable sources on IT topics.
Yes, a server is a type of computer, and a physical PC can be configured to operate as a server, as some IT pros do at home. Functionally speaking, servers and computers are different, as are virtual servers and virtual desktops, and it’s best to keep the terminology straight.
Support Your Physical and Virtual Environments with Park Place Technologies
After learning about these physical and virtual environments, you may have some questions. If physical and virtual servers are two different things, do you need two different support providers to keep your hybrid infrastructure operating at peak performance? Since virtual infrastructure still runs on physical hardware, do you need a virtual maintenance specialist and a physical maintenance provider? Absolutely not!
Park Place Technologies brings together the resources necessary to support, maintain, troubleshoot, and repair physical servers, as well as virtualized servers and the physical hardware on which they, too, run:
- Our third-party hardware maintenance is there for all physical equipment, whether you’re in need of storage, network, or server maintenance. When it breaks, we fix it.
- ParkView Hardware Monitoring™ is the ever-watchful eye overseeing that physical equipment to proactively identify hardware events and alert the maintenance teams so they can immediately resolve the issue.
- Finally, ™ is an agentless installation supporting multiple O/S instances and hypervisors to maximize uptime for both physical servers from one or various OEMs, along with virtual servers of different varieties as well.
Three tools, one infrastructure managed services provider. That’s the way it should be. Because no matter how complex your infrastructure, you’re just one organization. You deserve the convenience of a complete, integrated, optimization support solution.