Blade Server Buying Guide

by January 7, 2010 0 comments

Blade Server is a traditional server architecture where multiple individual
servers (blades) plug into a common chassis. Blade servers have a modular design
optimized to minimize the use of physical space. Many traditional server
components are removed and consolidated into the Blade Chassis or Enclosure to
save space and minimize power consumption amongst other considerations. Services
such as power, cooling, networking, various interconnects and management are
provided by the blade enclosure.

Need For Blade Servers
Generally, all IT departments face a typical challenge of increasing number of
servers when different applications require separate infrastructure and
platforms. As a result a lot of space is required to house these servers and
that is where the problem of real estate management comes in as it leads to an
additional financial burden on the company. This is because when you are
expanding physically, you not only need the space but also need the standard
requirements of building a fresh server room/datacenter which consists of power,
cooling, management, etc.
You need a more powerful technology which offers the option of expansion, and is
less power hungry in the server space. Thus, broadly speaking, consolidation
around a lesser number of servers is where blade servers score.

Blade Server Benefits
Reduced Space Requirements – Greater density and better use of the server
form factor highly reduces the total space requirements of the blade server
deployment as compared to tower or rack mounted servers.

Reduced Power Consumption and Improved Power Management — Power
supplied from the blade server chassis highly reduces the total power supply
requirement and also reduces the power required per server.

Lower Management Cost – server consolidation and resource
centralization simplifies server deployment, management and administration and
improves management, redundancy and control.

Simplified Cabling – Blade servers simplify cabling requirements and
facilitate highly reduced wiring. Most of the wiring related interconnects are
inbuilt into the chassis thereby greatly reducing the need for separate wiring.

Ease of upgrade – as new processor, communications, storage and
interconnect technology becomes available, it can be implemented in blades that
install into existing equipment, upgrading server operation at a minimum cost
and with no disruption of basic server functionality.

Easier Physical Deployment — since the chassis is responsible for
providing the once redundant parts of a server,deployment of a blade server
simply involves the placement of the chassis and sliding in the blades.
Redundant power modules and consolidated communication bays simplify integration
into data centers.

Flexibility- Blade systems also provide significant configuration
flexibility, offering a choice among myriad servers, I/O options and other
internal components. The chassis can accommodate a mix of x86 (Intel or AMD
CPUs) and Unix RISC servers, storage blades, workstations and PC blades, as well
as multiple I/O connections per blade.

General Blade Server Architecture
The hardware components of a blade server are the switch blade, chassis (with
fans, temperature sensors, etc), and multiple compute blades. The blades reside
in a standard compute blade slot,but they may functionally be positioned between
the switch blade and the compute blade. The switch card, present on the blade
server, is used to connect to the blade server. The switch card distributes
packets to blades within the blade server. A network management system software
is used to wrap around these components of the blade server. Other functionality
such as onboard graphics and VGA output, and USB connectivity etc are provided
on the blade but this only leads to lesser advantage taken of the blade server

Categories of Blade Servers
Blade servers can be divided into the following categories:

Workstation Consolidators: Workstation consolidators are essentially
the tools to consolidate older RISC workstations into a neat,concise and
centrally managed server. Most of these solutions have single processors, slower
processor speeds (650 MHz) and limited memory capabilities (2 GB).they reduce
econic burden on the enterpise by reducing the datacenter space for the
enterprise,but offer little improvement in terms of operational expense

Repackaged Whiteboxes: Fundamentally the same x86 servers but in a
different form factor with limited processor and memory configurations. Some
differences between the traditional whiteboxes and repackaged whiteboxes are
that some common components (power supplies and fans) are removed from the
individual servers and placed in a common chassis. The blades themselves are
plugged into a common midplane to access these common components.The common
chassis may contain embedded network and storage switches. The applicability of
these products to smaller, less-mission-critical applications is limited.

Enterprise-class Blade Systems: Enterprise-class blade systems are
designed to interoperate in the modern datacenter with established network,
storage, security and management processes and category-leading tools.

Systems that contain embedded switches from different vendors may encounter
compatibility problems. An enterprise system should present a standard network
and storage card interface.

It is crucial for the enterprise-class chassis to appear as a server (host)
to management framework tools. Again, an embedded switch may present differently
to the management and security framework, causing operational challenges.
Enterprise-class systems need to interoperate with leading SNMP-based datacenter
management tools.

Blade chassis showing size of blades that have
been inserted.

Enterprise-class blade systems offer greater resiliency by reducing points of
failure and providing built-in failover, enabling greater application
availability and allowing the system to self-heal(redundancy) if a failure does
occur. An enterprise-class system must leverage internal network technology that
overcomes the latencies of standard Gigabit Ethernet. This allows applications
to respond more quickly and scale more widely.

Enterprise-class systems have anonymous server blades which contain no local
storage and, as a result, do not possess any specific, permanent identity.These
systems also provide greater horizontal application scalability. Because data is
managed outside the blade server, hardware can be brought into service, changed,
replaced or upgraded with limited manual intervention.Instead, the identity, or
state, of the server is hosted on external storage.

Features Of Blade Servers
The different blade manufacturers vary in specific configurations for their
blade servers and chassis, but the focus still remains to strip extraneous
components from the blades so the blades’ components can focus on essential
processing and services. Each blade is a server by itself and generally
dedicated to a single computing task such as file sharing, SSL, data processing,
Web page serving, cache management ,video/audio streaming, or firewall etc.
Blade servers provide greater I/0 connectivity, hot swap drives, and RAID-5

Form factor
1 RU (one rack unit, 19″ [48 cm] wide and 1.75″ [4.45 cm] tall) defines the
minimum possible size of any equipment for a server architecture. So a typical
rack will be able to hold 80-100 servers with space in between for the cable
management units. For Blade servers, densities of 100 computers per rack,
running back to back, are commonplace. This also assists in the power management
and power conditioning where UPS units can accommodate more servers since,
because of the space and power-saving, they are more efficient. The principal
benefit and justification of blade computing relate to lifting this restriction
as to minimum size requirements. As of 2009, densities of up to 128 discrete
servers per rack are achievable with the current generation of blade systems.

In a single blade chassis, you can have different operating systems, different
memory capacities, a mix and match of 32-bit or 64-bit CPUs, and so on. Once you
have these, you can always run virtualization software on top. Also,blades let
you pair your dynamic software with dynamic hardware, making deployment and
management of virtual servers much easier.

Hot Swapping:
Hot swapping is the ability to add, remove and replace units at need without
having to power-off the chassis. Hot swapping can apply to PSUs, network,
management and storage units, and the blade servers themselves. Hot swapping,
coupled with redundancy, can give significant reliability benefits.It also aids
maintenance, because if a blade develops a problem it can be removed and
repaired or replaced without disruption of the other blades in the system.

The blade relies on the chassis to provide Power. In all chassis power switching
balances power load and requirements across the component blades’ demands. The
technology ensures that power isn’t wasted running underused blades, but in
times of high demand there is sufficient power available. Employing power supply
unit redundancy is necessary for critical servers.

A full chassis may generate considerable heat from the activity of component
blades, so high demand blade servers require effective cooling from their
chassis to operate efficiently. The chassis’ internal management systems may
shut down the entire system if the temperature rises above a certain point. It’s
critical, then, to follow the directions of the blade server chassis’
manufacturer when managing the server’s cooling. This might include air space
around the chassis, the use of plugs for empty bays, and environmental demands
for air temperature and humidity. Connectivity At the heart of the chassis’
connectivity will be an Ethernet and/or Fibre Channel switch, connecting each of
the blade servers to the LAN (Local Area Network). There may be more than one
switch unit in a chassis, which can either be used to provide a redundant
connection to a single network, or connection to more than one network. Other
connectivity is also provided by the chassis, but this is typically limited to
USB and VGA for monitor connection, with possibly PS2 connections for I/O with
mouse and keyboard. It’s also likely that a chassis will contain an optical
drive, although at need all of these functions and more can be added to the
chassis through the use of specific blades in the system.

There may be some limited storage on a blade server, and there may be additional
storage provided by a chassis. However, with the use of a SAN ,the chassis and
blades can be completely free of storage, removing the inherent heat, noise, and
reliability problems from the system completely. Everything from booting to data
storage can be done over the SAN, enabling the blade servers to be focused
entirely on processing. This configuration can increase reliability and reduce
space requirements by partitioning storage resources in one centralized location
and computing resources in another. This also eliminates storage Despite the
advantages of storage outside the blade chassis, many blades have the capacity
to take one or two hard drives, usually SATA.

LED Indicators:
Blade servers typically have a front panel containing a number of informational
LEDs, relating to power and system activity. There may additionally be
indicators of system failure, which may be general or specific to blade
components. These optional features will invariably come at a cost premium.

Services and warranty:
Check out the services and warranty provided by the vendor. Are they providing
door services or you need to send the server to them to fix it. The door service
is obviously good. Moreover check out the warranty period they offer, mostly the
3-year warranty period is provided. In addition to this, many vendors provide
enhanced warranty with faster response time. This will cost you some extra penny
but it is worth if you are running mission critical application on it.

However, not all factors are relevant to every organization. The more
customized the blade servers are,the easier it is for the enterprise to take
full advantage of them. It is critical to match the blades you buy with your
application scenario. It could mean the difference between costly confusion or
intelligent integration of blade servers in your enterprise.

Shikhar Mohan Gupta

No Comments so far

Jump into a conversation

No Comments Yet!

You can be the one to start a conversation.

Your data will be safe!Your e-mail address will not be published. Also other data will not be shared with third person.