Server Fault is a question and answer site for system and network administrators. Join them; it only takes a minute:

Sign up
Here's how it works:
  1. Anybody can ask a question
  2. Anybody can answer
  3. The best answers are voted up and rise to the top

Server CPUs cost multiple times more than Desktop CPUs; so do Motherboards and PSUs.

What are the advantages of getting a server system rather than a desktop system?

Stability can be one, but what are others?

share|improve this question

closed as not constructive by Chopper3, Greg Askew, Chris S Jun 14 '12 at 13:07

As it currently stands, this question is not a good fit for our Q&A format. We expect answers to be supported by facts, references, or expertise, but this question will likely solicit debate, arguments, polling, or extended discussion. If you feel that this question can be improved and possibly reopened, visit the help center for guidance.If this question can be reworded to fit the rules in the help center, please edit the question.

Please read our FAQ, this isn't a forum, we're a Q&A site, we don't do discussions. – Chopper3 Jun 14 '12 at 11:33

Usually there are extra features for either remote administration (such as "Integrated Lights-Out Management") or reliability (dual power supplies, use of higher quality components, better heat management). If you're not putting the machine in a datacentre and it doesn't cost you money if it goes down, then it's seldom worth the cost.

share|improve this answer

The choices for fitting desktop mainboards into 1U cases are limited, and usually leave you with a system that cannot take extension cards (especially systems that can take 2 or 3 PCI cards in a 1U case use very specialized form factor mainboards (look at the Supermicro X7DCU or X8DTU for an example...).

A server mainboard usually comes with at least 2 network ports, and uses network chipsets with good performance and low host cpu usage (Intel 8257x are very common on server boards, whereas Realtek is typical for desktop boards).

The power supplies usually come with redundant options and are designed suitable for 24/7 operations (and a server mfg likely cannot afford to build power supplies that can ever short out the mains!, which occasionally happens with Desktop PSUs).

HCLs for server operating systems often only list server grade hardware.

You want ECC memory capability, which is usually only found on server systems.

Server designs tend to avoid small and unreliable fans (passive heatsinks and either very big or very fast fans (one common 40mm counterrotating type is quite capable of blowing papers across the shop, these make far too much of a din though to ever find use in desktops) that cater to ALL these heatsinks in a redundant manner are common).

Managed harddrive backplanes (with hotswap, status LEDs....) also tend to be rare in desktops.

With the CPUs it is probably less a matter of reliability than of workload... many mid end and high end servers are used for virtualization, where you want systems with many cores (multi socket!) and a lot of memory.

Server grade harddrives are optimized for 24/7 operations, withstanding typical vibration stress in a mechanically close array of disks, and error handling that works together well with RAID controllers. They also come in some very low latency variants.

share|improve this answer

Not the answer you're looking for? Browse other questions tagged or ask your own question.