0% found this document useful (0 votes)
125 views140 pages

Datacentric Networking and System Design

The document discusses key aspects of designing and operating an effective data center. It emphasizes making the data center robust with redundant systems to ensure reliability, making it modular to allow flexible deployment of servers, and standardizing processes to promote efficiency. The data center houses a company's most valuable IT assets and must be carefully architected to secure these assets and allow the business to function effectively.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
125 views140 pages

Datacentric Networking and System Design

The document discusses key aspects of designing and operating an effective data center. It emphasizes making the data center robust with redundant systems to ensure reliability, making it modular to allow flexible deployment of servers, and standardizing processes to promote efficiency. The data center houses a company's most valuable IT assets and must be carefully architected to secure these assets and allow the business to function effectively.
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 140

DATA CENTER

09/09/2022 2

Value of Your Data Center


• Data Centers are specialized environments that safeguard
your company's most valuable equipment and intellectual
property.
• Data Centers house the devices that do the following:
• Process your business transactions
• Host your website
• Process and store your intellectual property
• Maintain your financial records
• Route your e-mails
09/09/2022 3

Data Center === Brain of your company


• Your business' ability to:
• Perceive the world (data connectivity)
• Communicate (e-mail)
• Remember information (data storage)
• Have new ideas (research and development)
• How to:
• Secure the brain
• Help it function efficiently
• Develop its full potential for your business
09/09/2022 4

What is a Data Center?


• a data center is a physical facility that organizations use to
house their critical applications and data.
• A data center's design is based on a network of
computing and storage resources that enable the delivery
of shared applications and data.
• The key components of a data center design include
routers, switches, firewalls, storage systems, servers, and
application-delivery controllers.
5

Data Centers
 Data center (DC) is a physical facility that enterprises use to house computing and storage
infrastructure in a variety of networked formats.

 Main function is to deliver utilities needed


by the equipment and personnel:
• Power
• Cooling
• Shelter
• Security

 Size of typical data centers:


• 500 – 5000 sqm buildings
• 1 MW to 10-20 MW power (avg 5 MW)
6

Example data centers


7

Data Centers
 Traditional data centers
• Host a large number of relatively small- or medium-sized applications, each running on a
dedicated hardware infrastructure that is decoupled and protected from other systems in the same
facility
• Usually for multiple organizational units or companies

 Modern data centers (a.k.a., Warehouse-scale computers)


• Usually belong to a single company to run a small number of large-scale applications
• Google, Facebook, Microsoft, Amazon, Alibaba, etc.
• Use a relatively homogeneous hardware and system software
• Share a common systems management layer
• Sizes can vary depending on needs
09/09/2022 8

What do you need to know?


• Physical design and construction of a Data Center
• How to customize the environment to meet your
company's needs
• How to organize and manage your Data Center effectively
so downtime is minimized, troubleshooting is easier, and
the room's infrastructure is fully used
09/09/2022 9

• So, how much is acceptable to spend on the construction


of your Data Center? That depends. To determine the
answer, you need to know the value of what your Data
Center is protecting.
09/09/2022 10

Types of Data Centers


• There are four main types of data centers:
• Enterprise data centers. These are built, owned, and operated by
companies and are optimized for their end users. ...
• Managed services data centers. ... These data centers are managed by a
third party (or a managed services provider) on behalf of a company. The
company leases the equipment and infrastructure instead of buying it.
• Colocation data centers. ... In colocation ("colo") data centers, a company
rents space within a data center owned by others and located off
company premises. The colocation data center hosts the infrastructure:
building, cooling, bandwidth, security, etc., while the company provides
and manages the components, including servers, storage, and firewalls.
• Cloud data centers. In this off-premises form of data center, data and
applications are hosted by a cloud services provider such as Amazon
Web Services (AWS), Microsoft (Azure), or IBM Cloud or other public
cloud provider.
09/09/2022 11

Shall I simply outsource?


• What is outsource?
• Rent server environment space from an outside company.
• Colocation facility
• Type of data center where equipment space and bandwidth are
available for rental to retail customers. Colocation facilities provide
space, power, cooling, and physical security for the server, storage,
and networking equipment of other firms—and connect them to a
variety of telecommunications and network service providers. (from
wikipedia)
• How much does it cost?
• Costs for an outsourced Data Center are usually dictated by the
amount of floor and rack space your servers occupy, how much
power they draw, and what level of connectivity and staff support
they require.
09/09/2022 12

Things to consider:
• Ownership
• Responsibility
• Access
• Up-front costs
09/09/2022 13

Why not to outsource?


• Server environment contains my company's most
valuable items and handles our business critical functions
so you want your own employees to be its caretakers.
• No one can know your company's server environment
needs like you own people who are dedicated to
supporting it,
• No matter how good an outside vendor is, it does not
have a personal stake in making sure that your Data
Center runs correctly the way that your and your
coworkers do.
09/09/2022 14

Outsource if:
• You have a short-term need for a server environment,
perhaps until a permanent Data Center is constructed
• You want a standby facility ready to take over for a
primary Data Center in the event of a catastrophic event.
09/09/2022 15

Defining Requirements and Roles


• You need to identify the requirements of your data center
• Also, you need to identify the roles and relationship
between different employees.
09/09/2022 16

Purpose of building data center


• Why is your company building this Data Center?
• What needs must it meet?
• What specific functions does it need to perform, and
perform well, to be considered a success?
• What level of availability does your business require?
09/09/2022 17

Roles and relationship


• Delineate which departments and people are responsible
for what tasks
• Who designs the Data Center's electrical infrastructure,
for example?
• An IT person who manages the room and knows about the
incoming server equipment?
• A facilities person experienced with electrical systems?
• An outside architect knowledgeable about regional building codes?
09/09/2022 18

Understanding Client Needs


• Talk to the people who work in the room(your client), and
find out the following:
• What servers they want it to support
• How much connectivity those devices need
• What their power requirements are
• Whether clients see trends among the equipment they are ordering
most commonly
• Focus on current needs along with future needs.
• Clients knows well their current needs.
• Clients may do not have any idea about future needs.
09/09/2022 19

Cross-Functional Support
• Responsibility for a company's Data Center is typically
shared among multiple departments and personnel.
• Example:
• Security manager typically governs physical access into
the Data Center.
• IT manager coordinates where servers are physically
deployed.
• Each one has different point of view with regards to
security access.
• Solution: Foster communication and seek compromise
09/09/2022 20

Architecting a Productive Data Center


• In order to have well designed data center you need to
follow five essential design strategy:
• Make It Robust
• Make It Modular
• Make It Flexible
• Standardize
• Promote Good Habits
09/09/2022 21

Make It Robust
• Above all, your Data Center has to be reliable. Its overarching reason
for existence is safeguarding your company's most critical equipment
and applications. Regardless of what catastrophes happen you want
your Data Center up and running so your business continues to operate.
• Data Center infrastructure must have depth: standby power supplies to
take over when commercial electricity fails, and redundant network
stations to handle the communication needs if a networking device
malfunctions.
• The infrastructure must be configured so there is no single component
or feature that makes it vulnerable. It does little good to have multiple
standby power systems if they are all wired through a single circuit, or to
have redundant data connections if their cable runs all enter the building
at one location.
• In both examples, a malfunction at a single point can bring the entire
Data Center offline.
09/09/2022 22

Make It Modular
• Your Data Center must not only have a depth of infrastructure, it
must also have breadth. You want sufficient power, data, and
cooling throughout the room so that incoming servers can be
deployed according to a logical master plan, not at the mercy of
wherever there happens to be enough electrical outlets or data
ports to support them.
• To achieve this uniform infrastructure, design the room in
interchangeable segments. Stock server cabinet locations with
identical infrastructure and then arrange those locations in identical
rows. Modularity keeps your Data Center infrastructure simple and
scalable. It also provides redundancy, on a smaller scale, as the
standby systems mentioned previously. If a component fails in one
section of the Data Center, users can simply plug in to the same
infrastructure in another area and immediately be operational again.
09/09/2022 23

Make It Flexible
• It is safe to assume that routers, switches, servers, and
data storage devices will advance and change in the
coming years. They may become smaller or bigger.
• Data Centers are not static, so their infrastructure should
not be either. Design for flexibility. Build infrastructure
systems using components that are easily changed or
moved.
• Inflexible infrastructure invariably leads to more expense
down the road.
• Part of a Data Center's flexibility also comes from whether
it has enough of a particular type of infrastructure to
handle an increased need in the future.
09/09/2022 24

Standardize
• Make the Data Center a consistent environment. This provides
stability for the servers and networking equipment it houses, and
increases its usability.
• When building a new facility, it might be tempting to try something
different, to experiment with an alternate design philosophy or
implement new technology. If there are new solutions that truly
provide quantifiable benefits, then by all means use them. Do not
tinker with the design just to tinker, though.
• Once you find a design model or infrastructure component that
provides the functions and features you are looking for, make it
your standard. Avoid variety for variety's sake. The more complex
the environment, the greater the chance that someone will
misunderstand the infrastructure and make a mistake, most likely
in an emergency.
09/09/2022 25

Promote Good Habits


• Data Center should be engineered to encourage desirable
behavior. Incorporating the right conveniences into the
Data Center and eliminating the wrong ones definitely
make the space easier to manage.
• Data Center users are busy people. They are looking for
the fastest solution to their problems.
09/09/2022 26

Examples of Good Habits


• Construct a nearby Build Room where system
administrators can unbox servers to keep the Data Center
free of boxes and pallets
• Make primary Data Center aisles larger than those between
server rows, creating an obvious path for users to follow
when rolling refrigerator-sized servers through the room for
deployment.
• Install wall-mounted telephones with long receiver cords
throughout the Data Center if you are concerned about
interference from cellular phones and want to reduce their
usage.
• Provide pre-tested patch cords to promote standardized
cabling practices.
09/09/2022 27

Data Center Ergonomics


• Make things accessible— This means putting items close by that Data
Center users need to perform their job. It also means designing work
areas, say within an electrical panel or where data cabling terminates, to
be free of clutter.
• Choose simple over complex— The more straightforward a Data Center's
details are, the less chance there is for someone to make a mistake and
perhaps cause an outage. Following this principle can influence how you
arrange server equipment and major infrastructure in the room.
• Remove mystery— If there is a chance someone might not understand an
element of a Data Center, add some form of written instructions—signage,
labeling, or even maps.
• Consider human nature— People typically follow the path of least
resistance. As suggested in the preceding section about making the Data
Center intuitive, take this into account when designing the room. If you
want someone to use a particular type and length patch cord, for example,
you should provide them in the Data Center.
09/09/2022 28

Data Center Components (Preview)


• Basic Data Center facility systems:
• Physical space
• Raised flooring
• In-room electrical
• Standby power
• Data cabling
• Cooling
• Fire suppression
29

Main components of a datacenter

src: The Datacenter as a Computer – Barroso, Clidaras, Holzle


09/09/2022 30

Data Center Components


• Physical Space
• Physical space refers to the footprint that Data Center-related items occupy. This generally applies
to the overall area of the Data Center and its associated spaces, such as electrical rooms or
storage areas. On a smaller scale this might refer to key dimensions within the Data Center, such
as the external measurements of a server cabinet or aisle clearances.
• Raised Flooring
• Raised flooring is an elevated grid system that is frequently installed in large Data Centers. Cooled
air, electrical whips, and data cabling are routed through the space under the raised floor,
promoting better air flow and enabling easier management of power and cable runs. Water pipes,
fire suppressant cylinders, moisture detectors, and smoke detectors may be located here as well.
• Raised flooring can vary in height from a few inches to several feet, or a few centimeters to several
meters. In extreme cases they are as tall as the story of a building, enabling workers to walk upright
under the plenum. Regardless of their height, the floors are typically composed of standard 2 foot
(60 centimeter) square floor tiles. The tiles can vary in weight, strength, and finish depending upon
their use. Tiles featuring either small perforations or large cut-out sections are placed in key
locations to enable pass-through of air and cabling between the areas above and below the floor.
• In-Room Electrical
• In-room electrical refers to all power-related facilities within the Data Center. This normally includes
electrical panels, conduits, and several types of receptacles. Power to this system usually comes
from an outside commercial power source, namely your local utility company, and is likely
conditioned at the company site. Voltage varies from one country to another.
09/09/2022 31

Data Center Components. Cont.


• Standby Power
• Standby power includes all backup power systems responsible for support of the Data Center's electrical load in
the event that normal utility power fails for any reason. This system traditionally includes large batteries, known
as an uninterruptible power source or uninterruptible power supply, and one or more generators.
• Cabling
• The cabling system is all structured cabling within the Data Center. Copper and fiber cabling are the typical
media and are terminated via several types of connectors. Common components include fiber housings, patch
panels, multimedia boxes, and data faceplates. Cabinets, raceways, and other items used to route structured
cabling are also considered part of the cabling system. Users plug servers in to the Data Center's structured
cabling system with pre-terminated patch cords.
• Cooling
• The cooling system refers to the chillers and air handlers used to regulate ambient temperature and control
humidity within the Data Center. This system might incorporate the air conditioning system used to cool regular
office space within the same building, known as house air, or might be independent of it. Individual server
cabinets can also possess their own cooling measures, such as fans or water-cooling.
• Fire Suppression
• Fire suppression includes all devices associated with detecting or extinguishing a fire in the Data Center. The
most obvious components are water-based sprinklers, gaseous fire suppression systems, and hand-held fire
extinguishers. Others can include devices that detect smoke or measure air quality.
• Other Infrastructure Components
• There are also some infrastructure items that do not strictly fall under the prior categories but are commonly
found in server environments. These include leak detection devices, seismic mitigation, and physical security
controls such as card readers and security cameras.
09/09/2022 32

Data Center Design Criteria


• How many layers of infrastructure should your Data
Center possess?
• Will it be the only server environment for your company or
one of several?
• Will the room house production servers and be a
business-critical site or contain a minimum of equipment
for disaster recovery purposes and serve as a failover
location?
• How long is its initial construction expected to meet your
company's needs?
• What is it all going to cost?
09/09/2022 33

Data Center Design Criteria


• Availability
• Infrastructure Tiers
• One Room or Several?
• Life Span
• Budget Decisions
09/09/2022 34

Data Center Design Criteria


• Availability:
• The degree to which Data Center devices function
continuously is known as the room's availability or its
uptime.
• Availability is represented as a percentage of time. How
many days, hours, and minutes is the Data Center's
electrical infrastructure operational and supplying power
over a given time period
09/09/2022 35

Data Center Design Criteria


• Infrastructure Tiers
• The higher the availability you want your Data Center to achieve,
the more layers of infrastructure it must have.
• N capacity is the amount of infrastructure required to support all
servers or networking devices in the Data Center, assuming that
the space is filled to maximum capacity and all devices are
functioning.
• N most commonly used when discussing standby power, cooling,
and the room's network.
• N+1 infrastructure can support the Data Center at full server
capacity and includes an additional component
• Alternately called a 2N or system-plus-system design, it involves
fully doubling the required number of infrastructure components
• Even higher tiers exist or can be created: 3N, 4N, and so on.
09/09/2022 36

Data Center Design Criteria


• One Room or Several?
• One large Data Center is simpler to manage than several
smaller ones.
• Having only one server environment puts all of your eggs
in one basket.
09/09/2022 37

• Life Span
• How long it is expected to support your company's needs
without having to be expanded or retrofitted, or otherwise
undergo major changes.
• The most effective strategy is to design a Data Center
with a projected life span of a few years.
09/09/2022 38

• Budget Decisions
• It is no good to spend millions of dollars on a server
environment to protect your company's assets if that cost
drives your business into bankruptcy.
• The most obvious costs for a Data Center are labor and
materials associated with its initial construction, which,
even for a room smaller than 1000 square feet or 100
square meters, normally runs into hundreds of thousands
of dollars. This includes:
• Initial construction
• Consulting fees
• Real estate
• Ongoing operational expenses
09/09/2022 39

• Budget Decisions
• It depends on the downtime cost
• The cost of a generic employee at your business and then multiply this by the
length of the outage and by how many employees are unable to work during
downtime/
• For example, a generic employee costs your company a total of $150,000 a year.
(Remember, this is all costs combined, not just salary.) That is about $60 an hour,
assuming the employee works a traditional 40-hour work week, and 52-week calendar
year. If your Data Center goes offline for two hours and stops the work of 100 employees
at that site, that is $12,000 for that single outage.
• Or by calculating the revenue:
• Assume that your company typically brings in $1 million a year in online business. If the
website accepts orders around the clock, then divide $1 million by 8760, the number of
hours in a year. That works out to $114 an hour, which means that the four hours of
downtime also disrupted about $500 in sales.
• Most difficult value of all to quantify comes from when a server crashes and
data is destroyed.
• For example, intellectual property has been destroyed.
09/09/2022 40

Managing a Data Center Project


• The Design Package
• A comprehensive Data Center design package template available
at the book website.
09/09/2022 41

Working with Experts


• The facilities manager— This person's specialty includes all mechanical devices within the Data Center
infrastructure, from air handlers and power distribution units to fire sprinklers and standby generators.
• The IT manager— This person is responsible for the servers installed in the Data Center.
• The network engineer— This person designs, supports, and manages the Data Center's network.
• The Data Center manager— This person designs, supports, and manages the Data Center's physical
architecture and oversees the layout and installation of incoming servers.
• The real estate manager or building planner— This person governs how company building space is
used. In a Data Center project.
• The project manager— This person manages the Data Center construction project as a whole,
including its budget, timelines, and supervision of outside contractors.
• The architectural firm— This outside company ensures that your Data Center design complies with
local building codes.
• The general contractor— This person oversees and acts as a single point of contact for all other
contractors on the project.
• The electrical contractor— This contractor installs, labels, and tests all of the Data Center's electrical
and standby equipment.
• The mechanical contractor— This contractor installs and tests all of the Data Center's cooling
equipment. Ducting is typically the contractor's responsibility as well.
• The cabling contractor—This contractor installs and tests all of the Data Center's structured cabling. Its
staff also installs any racks or cabinets that cabling terminates into, and labels the room's cable runs.
09/09/2022 42

Tips for a Successful Project


• Define expectations and communicate them early and
often
• Expect long lead times on infrastructure items
• Establish deadline-based incentives for time-sensitive
projects
• Document everything
• Visit the construction site frequently
09/09/2022 43

content centric networking (CCN)


• , content centric networking (CCN) emphasizes content
by making it directly addressable and routable. Endpoints
communicate based on named data instead of IP
addresses. CCN is characterized by the basic exchange
of content request messages (called "Interests") and
content return messages (called "Content Objects"). It is
considered an information-centric networking (ICN)
architecture.
09/09/2022 44

Content Centric Networking



Network use has evolved since IP was designed

Usage of the Internet is in terms of what not where

CCN: architecure built on named data rather than
named hosts

Provides security, scalability, performance.
09/09/2022 45

Content Centric Networking



Two packet types: Interest and Data

Heirarchical content naming scheme

Allows dynamic content generation: active names

CCN node has 3 components: FIB-
Forwarding Information Base, Content Store and
PIT

FIB: Forwarding table, allows multiple output faces

Content Store: Buffer, also caches Data packets

PIT: Pending Interest Table
09/09/2022 46

CCN Nodes

Processing an Interest:
– Matching Data is found in the Content Store
=> send it and consume Interest
– Pending Interest in PIT
=> add this face to RequestingFaces list
– Use FIB to forward Interest on outgoing faces, add to PIT

Processing Data:

Data follows a chain if PIT entries back to the source

Duplicate and unsolicited Data is discarded
09/09/2022 47
09/09/2022 48

Reliability and Flow Control



Interests serve the role of window advertisements

Each packet is independent => TCP SACK is implicit

Flow balance is maintained at each hop, not end-to-
end like TCP

Thus additional, TCP-like congestion control
mechanisms not required.
09/09/2022 49

Naming Content

Hierarchical content names with a flexible format

Individual name consists of a number of components

Names can be relative to some known name, e.g.
next/previous

Same content can have multiple names! Problems with
caching?

A source of data performs a Register operation for a
prefix
09/09/2022 50

Routing

Routing between CCN nodes can occur over
unmodified OSPF.

Incremental deployment of CCN nodes is possible

Integration with BGP is also possible

Routers do not construct spanning trees

Loops are not possible anyway

Multiple paths can be used
09/09/2022 51

Content Based Security



Security travels with the content, it is not a property of
the connection

CCN authenticates name-content bindings by signing
the name and content in each data packet

Arbitrary key management schemes can be used
over CCN

Keys can be sent over CCN since they are just
another piece of data

If we trust some public keys, we can infer more
09/09/2022 52

Network Security

Sending a malicious packet to a host is difficult
because CCN talks only about content, not to hosts

Data based DoS attacks are impossible because only
one Data packet is forwarded per Interest

Interest flooding:

Multiple Interests for the same content are combined

Limit the forwarding of unsuccesful interests

What if sender and receiver collude?
09/09/2022 53

Evaluation

Transfer time vs Number of Sinks
09/09/2022 54

Evaluation

Failover
09/09/2022 55

An Architecture for Internet Data


Transfer
09/09/2022 56

Data Oriented Transfer Service



Seperate control from data

Control logic is application specific; use DOT for all
data transfer

Benefits:

Transfer techniques can reused and new ones tried

Coding, multi-pass compression, caching etc. can be
applied by the transfer service

Multi-path transfers

Cross application data processors
09/09/2022 57

DOT

DOT provides an API and a plugin architecture

Transfer Plugins: eg. Multi-path, portable storage

Storage Plugins: access to local data, divide data into
chunks, compute hashes

Basic API:

Sender calls put with data, gets back an OID

Receiver uses OID to get data
09/09/2022 58

Evaluation

Multipath Plugin: Using two 100 Mbit/s Ethernet links,
transfer time went down from 3.59 seconds to 1.90
seconds

Modified Postfix mail server to use DOT

Minimal modification: 184 LoC

DOT saves 20% of total message bytes transferred

Duplicated messages

Partial redundancies in messages
09/09/2022 59

Outline
 Motivation
 What is content distribution ?
 Schemes for content distribution
• Web Caching
• Content Distribution Networks
• Peer-to-Peer File sharing (not covered)
CDN Internetworking
What content is/is not suitable for CDNs?
CDNs vs. Caches
09/09/2022 60

CDN
• A content delivery network, or content distribution
network (CDN), is a geographically distributed network of 
proxy servers and their data centers.
• The goal is to provide high availability and performance by
distributing the service spatially relative to end users. CDNs came
into existence in the late 1990s as a means for alleviating the
performance bottlenecks of the Internet[1][2] as the Internet was
starting to become a mission-critical medium for people and
enterprises.
• Since then, CDNs have grown to serve a large portion of the Internet
content today, including web objects (text, graphics and scripts),
downloadable objects (media files, software, documents),
applications (e-commerce, portals), live streaming media, on-demand
streaming media, and social media sites.[3]
09/09/2022 61

CDN
• CDNs are a layer in the internet ecosystem. Content
owners such as media companies and e-commerce
vendors pay CDN operators to deliver their content to
their end users. In turn, a CDN pays 
Internet service providers (ISPs), carriers, and network
operators for hosting its servers in their data centers.
• CDN is an umbrella term spanning different types of
content delivery services: video streaming, software
downloads, web and mobile content acceleration,
licensed/managed CDN, transparent caching, and
services to measure CDN performance, load balancing,
Multi CDN switching and analytics and cloud intelligence. 
09/09/2022 62

CDN
• CDN nodes are usually deployed in multiple
locations, often over multiple Internet backbones.
Benefits include reducing bandwidth costs,
improving page load times, or increasing global
availability of content.
• The number of nodes and servers making up a
CDN varies, depending on the architecture, some
reaching thousands of nodes with tens of
thousands of servers on many remote 
points of presence (PoPs). Others build a global
network and have a small number of
geographical PoPs
09/09/2022 63

Why CDN?
• Over the last few years there has been a huge
increase in the number of Internet users.
YouTube alone has 2 Billion users worldwide,
while Netflix has over 160 million users.
Streaming content to such a wide demographic of
users is no easy task.
• One can think that a straightforward approach to
this can be building a large data center, storing all
the content in the servers, and provide it to the
users worldwide. But there are issues that arise
when this approach is followed-
09/09/2022 64

Why CDN?
• Firstly if the data center is in the USA and the user is in
India there will be slower delivery of content.
• Secondly, a single data center represents a single point of
failure.
• Thirdly, if some content is being accessed frequently from
a remote area then it is likely to follow the same links, and
this, in turn, results in wastage of bandwidth.
09/09/2022 65

What is a CDN?

A CDN is essentially a group of servers that are
strategically placed across the globe with the purpose of
accelerating the delivery of web content. A CDN-
• Manages servers that are geographically distributed over
different locations.
• Stores the web content in its servers.
• Attempts to direct each user to a server that is part of the
CDN so as to deliver content quickly.
09/09/2022 66

How CDN Works


• To minimize the distance between the visitors and your
website’s server, a CDN stores a cached version of
original content in multiple geographical locations (a.k.a.,
points of presence/ PoPs).
• Each PoP contains a number of caching servers known
as edge servers that are responsible for content delivery
to visitors within its proximity. CDN caches content in
many places at once, ensuring quick delivery of content.
09/09/2022 67
09/09/2022 68

With CDN
09/09/2022 69

Example
• Suppose you are hosting a website, wherein your origin
server(server containing the primary source of your
website’s data, where website files are hosted) is located
in Australia and a company XYZ provides you the CDN
service.
When a user in India clicks on a video on your website,
the request goes to the user’s local DNS server(See DNS
), which relays the request to the authoritative DNS server
of your website.
09/09/2022 70

• The authoritative DNS server then identifies that the user is


situated far away and therefore relays the request to its
XYZ’s DNS server. Now the DNS query enters XYZ’s
network which provides the address of the edge server that
is closest to the user to the Local DNS server. The video is
delivered by this edge server.
From this point onwards the local DNS server knows the
address of the edge server. So whenever users within its
network send a request for content from your website, the
local DNS server shall relay the request to the edge server.
CDN thus minimizes the number of hops required to deliver
the data to a user’s browser due to the POPs that are
located near the user.
09/09/2022 71

CDN Security
• CDN providers profit either from direct fees paid by 
content providers using their network, or profit from the
user analytics and tracking data collected as their scripts
are being loaded onto customer's websites inside their 
browser origin.
• As such these services are being pointed out as potential
privacy intrusion for the purpose of behavioral targeting[6]
 and solutions are being created to restore single-origin
serving and caching of resources
09/09/2022 72

Content networking techniques


• The Internet was designed according to the end-to-end principle.[9] This
principle keeps the core network relatively simple and moves the
intelligence as much as possible to the network end-points: the hosts and
clients. As a result, the core network is specialized, simplified, and
optimized to only forward data packets.
• Content Delivery Networks augment the end-to-end transport network by
distributing on it a variety of intelligent applications employing techniques
designed to optimize content delivery. The resulting tightly integrated
overlay uses web caching, server-load balancing, request routing,
and content services.
• Web caches store popular content on servers that have the greatest
demand for the content requested. These shared network appliances
reduce bandwidth requirements, reduce server load, and improve the
client response times for content stored in the cache. Web caches are
populated based on requests from users (pull caching) or based on
preloaded content disseminated from content servers (push caching)
09/09/2022 73

• Server-load balancing uses one or more techniques


including service-based (global load balancing) or
hardware-based (i.e. layer 4–7 switches, also known as a
web switch, content switch, or multilayer switch) to share
traffic among a number of servers or web caches
• . Here the switch is assigned a single virtual IP address.
• Traffic arriving at the switch is then directed to one of the
real web servers attached to the switch. This has the
advantage of balancing load, increasing total capacity,
improving scalability, and providing increased reliability by
redistributing the load of a failed web server and providing
server health checks.
09/09/2022 74

• Request routing directs client requests to the content


source best able to serve the request. This may involve
directing a client request to the service node that is
closest to the client, or to the one with the most capacity.
• A variety of algorithms are used to route the request.
These include Global Server Load Balancing, DNS-based
request routing, Dynamic metafile generation, HTML
rewriting, and anycasting. Proximity—choosing the closest
service node—is estimated using a variety of techniques
including reactive probing, proactive probing, and
connection monitoring.[10]
09/09/2022 75

Content service protocols

• Several protocol suites are designed to provide access to a wide variety


of content services distributed throughout a content network. The
Internet Content Adaptation Protocol (ICAP) was developed in the late
1990s[14][15] to provide an open standard for connecting application
servers.
• A more recently defined and robust solution is provided by the 
Open Pluggable Edge Services (OPES) protocol.[16] This architecture
defines OPES service applications that can reside on the OPES
processor itself or be executed remotely on a Callout Server. 
Edge Side Includes or ESI is a small markup language for edge level
dynamic web content assembly. It is fairly common for websites to have
generated content.
• It could be because of changing content like catalogs or forums, or
because of the personalization. This creates a problem for caching
systems. To overcome this problem, a group of companies created ESI.
09/09/2022 77

Slow Access Time Problem


World Wide Wait
Server Access Network overloaded
CNN
Public Internet network

CNN.com
congested link

low bandwidth link


ren.cis
eecis Client Access Network
09/09/2022 78

Server Farm
Server-1 Server-2 Server-n

Requests = R/n

L4-L7 Switch

Does load balancing

Requests = R
Internet
09/09/2022 79

Client Network without a Web Cache

Total delay =
Internet delay + Internet delay=2 sec
Access delay

Δaccess link = 15x100 Kb/1.5 Mbps = 1 Access delay = HUGE


1.5 Mbps access link
Avg. object size = 100 Kbits
15 requests/sec
ΔLAN = 15x100 Kb/100 Mbps = 0.015
100 Mbps
LAN

Δ – traffic intensity
09/09/2022 80

Web Cache: Basic operation

Web server
GET

Object present ?
No-> Fetch Object
Yes-> Send Object RESPONSE

RESPONSE RESPONSE

GET GET
Cache
Client 1
09/09/2022 81

Web Cache

Internet delay=2 Sec

Total delay =
(2 + .01) x 0.6 = 1.2 Sec delay = tens of milliseconds
ΔAL = 0.6 1.5 Mbps access link
Institutional
cache
Hit rate = 0.4 100 Mbps LAN

Δ – traffic intensity
09/09/2022 82

Content Distribution Network of Caches


Web server Web server

Parent

Child 1 Proactive replication Child 2


09/09/2022 83

Problems with discussed approaches:


Server farms and Caching proxies
Server farms do nothing about problems due to network congestion, or to
improve latency issues due to the network

Caching proxies serve only their clients, not all users on the Internet

Content providers (say, Web servers) cannot rely on existence and


correct implementation of caching proxies

Accounting issues with caching proxies.


For instance, www.cnn.com needs to know the number of hits to the
advertisements displayed on the webpage.
09/09/2022 84

CDN: Basic Idea original content

Replica
congested

Replica

Not congested

Client
09/09/2022 85

Content Distribution Networks


Mechanism for
replicating content on multiple servers in the internet.
providing clients with a means to determine the servers
that can deliver the content fastest.
09/09/2022 86

Terminology
• Content: Any publicly accessible combination of text, images,
applets, frames, MP3, video, flash, virtual reality objects, etc.

• Content Provider: Any individual, organization, or company


that has content that it wishes to make available to users.

• Origin Server: Content providers server , where the content is


first uploaded.

• Surrogate Server: Content distributor’s server, where the


replicated content is kept.
09/09/2022 87

Players of the game


Yahoo,
MSNBC, S en
Content Provider d co
CNN nten
t
Akamai,
Content Digital Island,
Distributor AT&T

ers
v

Ins
ser
s

tal
S ell

ls
erv
Cisco,

er s
Lucent, H/W and S/W
Vendor Exodus
Inktomi, Hosting
CacheFlow Provider
09/09/2022 88

CDN: Distribution
Origin server in
North America

push content
Akamai CDN
CDN distribution node

push content
push content
CDN server in South
America
push
CDN server in Asia
content

CDN server in
Europe
09/09/2022 89

CDN: Functional Components


• Distribution Service
• Redirection Service
• Accounting and Billing system
09/09/2022 90

CDN: Architecture Origin

CDN

Request Distribution
Routing and
Infrastructure Accounting
Infrastructure

Surrogate
Surrogate

Client
09/09/2022 91

CDN: Request Routing Mechanisms


• Best surrogate selected based on some metrics.
• Techniques
• DNS based request routing
• Content Modification (URL rewriting)
• Anycast based
• Transport layer request routing

• Combination of multiple mechanisms


09/09/2022 92

CDN: DNS based Request Routing

t D NS
o c lien www.cnn.com
s ure t
Mea e sults
R Akamai DNS

www.cnn.com

32.22
63.251.132.22
surrogate 63.210.135.39
surrogate
pi

63.251.1
ng

g
pin
Session
www.cnn.com
63.251.132.22

Local DNS Server


128.4.4.12
09/09/2022 93

Content Modification
CNN.com PUT Authoritative DNS server for cdn.com
/ima
g es/*
.g if

GET www.cnn.com/index.html

?
Index.html

om
64.236.24.28

n.c
cd

28 .
ry:
Index.html

.24
g if

q ue
.

236
s/1
...
g e
<img a

64.
S
im

DN
src="http://www.cdn.com
n n/
c
T/ if
/cnn/images/1.gif”>
. g
... GE 1

DNS query: cdn.com ?

64.236.24.28
Client Local DNS server
09/09/2022 94

Metrics
• Network Proximity (Surrogate to Client):
•Network hops (traceroute)
•RTT
•Internet mapping services (NetGeo, IDMaps)
•…
• Surrogate Load:
• Number of active TCP connections
• HTTP request arrival rate
• Other OS metrics
• …
• Bandwidth Availability
09/09/2022 95

Full site delivery vs. Partial Site Delivery


• Full Site Delivery : All the contents are delivered by the
CDN (including HTML, images, and other objects).

• Partial Site delivery: Only images, streaming media and


other bandwidth intensive objects delivered by the CDN.
09/09/2022 96

Content Distribution Internetworking: CDI


• Interconnection of Content Networks – collaboration
between caching proxies and CDNs, as well as
between individual CDNs

• Greater reach, larger scale, higher capacity,


increased fault tolerance

• Basic architecture involves gateways between


various content networks
09/09/2022 97

CDI: Architecture

Digital Island
ATT

Akamai

comcast

Cache network Content Peering Gateway


09/09/2022 98

Content
• Images
Suitable for CDNs
• High-volume e-commerce transactions (thanksgiving sale)
• Streaming media (audio and video) (media events)
• Java Applets
• Virtual Reality Objects
• Flash content

Content NOT Suitable for CDNs


 Personalized content (my.yahoo.com,…)
 Dynamic Content
 Secure Content
09/09/2022 99

CDN vs. Caching Proxies


Caching Proxies CDN
Used by ISP to reduce bandwidth Used by Content Providers to
consumption. increase QoS.

Operate Reactively Operate Proactively

Caching proxies cater to their CDNs cater to the content


users (web clients) and not to providers (web servers) and
content providers (web servers) clients

Caching proxies do not give CDNs do


control of the content to the
content providers.
09/09/2022 100

Summary and References


• Caching
• CDN
• DNS based Request Routing
• CDI

References:
• Michael Rabinovich and Oliver Spatsheck, “Web Caching and
Replication “, Addison-Wesley 2001.
• PPT slides by Janardhan Iyengar on “Overlay Networks”
• PPT slides by Brad Cain on “Interconnection of Content Delivery Networks”
• http://www.cis.udel.edu/~girish/856/cdn-bib.pdf
09/09/2022 101

Proxy deployments
• Non-transparent
 Explicit client configuration
 Browser auto configuration
 Proxy auto discovery
• Transparent
 Connection “Hijacking” or interception.
09/09/2022 102

Transparent proxy deployment:


Connection “Hijacking”

Internet

Other traffic

TCP port 80 traffic ISP

Proxy
09/09/2022 103
Client IP = a1 Proxy IP = a2 Origin Server IP = a3
SYN(a1 to a3)

to a1)
SYN/ACK(a3

ACK/HTTP re
quest (a1 to a3
)
SY
N(a
2 to a
3)

to a2)
CK(a3
/A
SYN

ACK
/HT
TP
requ
est
(a2
to a
3)

to
ta (a3
Da
) a2)
Data (a3 to a1
09/09/2022 104

Requirements of a modern data center


• To create a modern data center, there are some
requirements to fulfill. The first is the use of commodity
hardware. There is not any need to use specialized
hardware because they are not only expensive but also not
flexible.
• A modern data center uses commodity hardware provided
by cloud providers because such hardware can be run with
software. The second is modular design.
• It is true that businesses need more servers for their data
center. However, even though more servers are needed, a
bigger building is not needed. What business owners should
consider is using a modularization. This system allows
them to use one appliance to connect the entire network.
09/09/2022 105

Requirements of a modern data center

• Then, the third requirement is software. A modern data center


uses software to control all systems. This enables automatic
control and reduces the use of specialized hardware.
• In other words, this opportunity gives business owners a
chance to save money on their data center. Furthermore, a
reliably security system is needed because it protects data
center from data breaches.
• The system should be multiple security systems in order to reap
maximum benefits. Moreover, appropriate equipment like
cooling system is required to make sure that the systems work
well and to avoid hardware overheating. The equipment should
also be maintained regularly so that they can function well.
09/09/2022 106

Design for Flexilibility


09/09/2022 107

Design for Flexilibility


• There are many design elements to look for when seeking a building
suitable for housing a flexible, sustainable data center.  Here are several
to keep in mind:
• High ceilings: support almost any power and cooling distribution
scheme, whether fully contained or housed inside shipping containers.
• Concrete floors: required to support the high load requirements of full
racks of equipment, which can weigh thousands of pounds within a 24” x
36” footprint.
• Tall, wide doorways: needed to move racks in and out of the facility, as
well as to support future infrastructure move, add and change work.
• A minimal number of interior columns: allows for flexibility in design
and optimized space planning.  The fewer the columns, the more racks
can be housed in the same space.
• Large power feeds from the utility, preferably from renewable sources:
provide the ability to scale and support growing future electrical loads.
09/09/2022 108

Design for Flexilibility


• Ample external space: for energy sources such as
generators, fuel cells, or solar PV’s.
• Ambient air temperatures that are low: and able to support
free cooling, a key driver for lower PUE.
• Inside, a flexible data center is likely to have these
infrastructure attributes:
• Overhead power busway: provides the ability to dynamically
shift power resources to different racks.
• Overhead cable raceways: segregated fiber and copper
infrastructure is easier to manage here than underfloor.
• Standardized rectangular layouts suitable for standard IT
racks: segmenting floor space into rack-friendly widths and
lengths provides optimal space planning and utilization.
09/09/2022 109

Data Center Scalability


09/09/2022 110

Design for Scalability


• Designing a scalable data center 
• Businesses today are expected to grow fast, which means
that their data centers must grow with them- quickly.
• As a result, data centers are faced with ever-growing
demands; supplying more power within a smaller space
and staying within budget, while maintaining mission-
critical reliability and efficiency. 
• Fortunately, there is new technology that can help firms
grow quickly and efficiently without having to expand the
footprint of the data center. These four innovations can
help businesses create a scalable data center so growth
doesn’t turn into a bad thing:
09/09/2022 111

Design for Scalability


• 1. Data Center Modularity
• Data center modularity is an approach to data center design
where a prefabricated module or a deployment method can
deliver infrastructure in a segmented, quick and flexible
process.
• A modular approach offers a long term sustainable solution
as well as vast flexibility when it comes to data center
expansion. Instead of adding modules with hundreds of
servers, a new addition to a modular data center might only
consist of a few racks which have been assembled remotely.
• As well as aiding data center scalability, modularity has many
other benefits, including cost savings, sustainability,
smaller footprint and quick construction.
09/09/2022 112

Design for Scalability


• 2. Elastic Capacity
• A common pitfall when scaling a data center is server investment-
how many will you need? And when will you need them?
• Spikes in demand are hard to predict. Another predicament is
deciding what to do when you don’t need the additional capacity.
That’s where elastic capacity comes in…
• Data centers can now add, remove or move virtual processors
and memory during periods of spiked usage or maintenance.
Instead of paying for extra capacity, you only have to pay for the
servers needed.
• Data center operators can manually adjust the service levels for
an application as often as they want, then use those service
levels for automation.
09/09/2022 113

Design for Scalability


• 3. Object Storage
• You may be thinking object storage isn’t new? It is an
established technology; however, it is one that has yet to be
widely received.
• When we consider data center scale, traditional file storage is
extremely limiting. File systems are designed for collaboration on
the same data without modifying it at the same time.
• However, locking mechanisms make it complex to scale the file
system because it’s slow whilst it's locked. Take a social
network startup as an example; starting with hundreds or
thousands of users, the system has no issue managing the
volume of images or videos posted. However, if this is
enormously scaled up to millions of users, volume
management will become a major problem.
09/09/2022 114

• The solution? Object storage. It simplifies the file ID


system and manages data as objects, instead of blocks
within sectors or tracks. The ID crosses multiple storage
volumes and refers to where that object is stored, while
metadata is attached to the file to make it searchable.
• There’s no hierarchy or locking mechanism, which makes
scaling easy; the storage system creates data clusters that
scale with growth. Object storage creates a single storage
management system that’s much easier to manage.
• As data scale reaches hundreds of TB, the features of object
storage are invaluable, with continued horizontal scalability
for virtually any quantity of data possible.
09/09/2022 115

Design for Scalability


• 4. Power Distribution Solution
• Power distribution solutions have evolved with modern data centers, to the point
where they are both flexible and adaptable to ever-changing requirements.
• Here are three solutions for scalable power distribution that typically provide the lowest
long-term cost when they work together:
• Overhead busway systems
• Overhead busway systems can be tapped at any location using a variety of plug-in
units. 
•  Intelligent power distribution units (PDU)
• Intelligent PDUs include switched, non-switched and metered PDUs and inline meters
that provide environment and power metering, monitoring and management.
•   Power management software
• Power management software lets you standardize, monitor and report energy usage
and environmental conditions at any level, including data center, rack, department and
equipment type. It also provides centralized monitoring, graceful OS shutdown, outlet
control, powerful analytics of your costs, line capacities, carbon footprint and rack
temperature.
09/09/2022 116

Design for Environment CONTROLS


09/09/2022 117

Design for Environment CONTROLS


• Data Center Environment Controls
• To understand environmental standards that apply to all data centers providing acceptable
operating conditions to the IT equipment they house, consider the following four
environmental controls. It’s also important to note that these controls are largely informed
by the latest data center environmental standards as published by the American Society of
Heating, Refrigerating and Air-Conditioning Engineers — or ASHRAE — such
as ANSI/ASHRAE Standard 90.4-2016, which sets out energy efficiency requirements for
today’s data centers. The four factors are:
• Temperature control: Thermal control will always remain an important issue for data
centers since servers give off heat while in operation but can be crippled by excessive
temperatures. However, due to newer, more robust IT equipment, ASHRAE’s previous
recommended thermal range of 68 to 77 degrees Fahrenheit has recently been
broadened to 65 to 80 degrees. In addition, experienced IT engineers — like the
professionals at DataSpan — have discovered how to optimize the arrangement of servers
to make better use of servers’ fans and other internal cooling mechanisms.
• Humidity control: High humidity and moisture levels can put hardware at risk of failure.
For this reason, cooling and ventilation systems need to detect and control relative
humidity in computer room air. ASHRAE recommends operating within a dew point of 41.9
to 59 degrees Fahrenheit — with a relative humidity of 60 percent maximum.
09/09/2022 118

Data Center Environment Controls

• Electricity monitoring: An unplanned burst of energy in the


form of static electricity discharge might be the greatest threat to
the average data center’s performance. To prevent these types of
incidents from happening, remember that responsible data center
design includes the installation of energy monitors that are
strategically located to spot the buildup of static electricity.
• Security systems: From fire protection and suppression
systems to physical and virtual security measures, safeguarding
the overall data center from attacks and disasters is a must in
the vigilant control of its environment. And like with any security
measure that’s employed in the time of an emergency and/or
threat, these systems must be regularly tested and evaluated to
ensure that their performance and effectiveness are up to par.
09/09/2022 119

Design for Electrical Systems


• More Efficient in UPS Systems – Because uptime is critical, you
want to be sure you have reliable uninterruptible power supply
(UPS). The old lead-acid batteries are being phased out in favor of
lithium-ion batteries.
• As a result, UPS systems are smaller and more efficient. Older
UPSs are designed to deliver 80 to 82 percent under standard load,
while newer units deliver as much as 99 percent.
• Additionally, in the past, UPSs have been oversized to
accommodate larger loads, but new efficiencies 
such as virtualization have reduced the UPS load to decrease the
amount of backup power needed.
• Using a modular design approach to UPS design, you can choose
the best equipment and ensure it is rightly sized for the data center,
so it takes less space, reduces costs and is easier to maintain.
09/09/2022 120

Design for Electrical Systems


• Renewable Power Sources – You can improve your PUE and
power redundancy by adding alternative energy sources to
your data center electrical infrastructure. 
• Solar power, for example, can be used to supplement data
center power.
• A solar array can’t generate enough power 
for most data centers, but it can be useful to offset the amount
of power needed from the grid to reduce utility costs and to
charge energy storage systems. 
• Microgrids are also making their way into data center design,
allowing operators to isolate power for critical systems. As utility
grids age and become less reliable (e.g., the 
rolling blackouts in California), using alternative power sources
will become critical.
09/09/2022 121

Design for Electrical Systems


• Smarter Electrical Infrastructures – Expect to see more
automation and artificial intelligence (AI) being used to manage
power and cooling. Machine learning can optimize power use based
on the applications and hardware in use.
• AI is expected to have a huge impact on 
power consumption for cooling; Google has already demonstrated the
potential of AI on cooling in its own data center, saving up to 40
percent of cooling requirements and energy use. Experts estimate
that using AI to manage data center power can deliver a 
5 percent improvement in energy efficiency.
• The result is lower energy costs, greater reliability and a smaller
carbon footprint. Using IoT performance data will also  be invaluable
for maintenance, powering predictive analytics to monitor
performance and will provide incident data for proactive servicing.
09/09/2022 122

Design for Electrical Systems


• Safer Electrical Distribution Designs – One area in
which the data center electrical infrastructure continues to
improve, is worker safety.
• The design of electrical distribution equipment is safer
with arc chutes, and switch systems have isolated
control compartments for access to meters, relays and
terminal blocks.
• There are also remote switching features that protect
workers from arc flashes.
09/09/2022 123

Design for Electrical Systems


• Eliminate Redundancy – Eighty percent of data center managers
say resiliency is their top priority, so if there is a failure, critical
systems will continue to operate.
• In the past, resiliency meant redundancy—duplicating servers,
storage and power systems that would remain powered up, but idle
until there was a failure. Rather than wasting money and energy on
redundant systems, more data centers are applying fault tolerance
using load balancing, virtualization and other strategies.
• Cloud computing is playing a huge role here, as more resources
are being hosted, which means there is less need for redundant
data center systems. IT managers also are using more Data
Center Infrastructure Management (DCIM) tools to monitor
operations, including the electrical infrastructure, and identify
unnecessary redundancy and potential points of failure. 
09/09/2022 124

Design for backup


• Speeding Up Data Retrieval
• Disk-to-Tape
• Disk-to-Cloud
• Backup Of Mobile Devices
• Backup For Recovery
• Criteria For Backup Software
• Criteria For Recovery Tools
• Cost Considerations
09/09/2022 125

Speeding Up Data Retrieval


• Having one or more redundant copies of critical business data to call upon in the
event of problems is all well and good. But if it takes so much time to restore that
essential information from its backup media that business opportunities are lost or
operations are negatively impacted, then having a backup becomes redundant, in itself. 
• To a large extent, retrieval times will depend on what kind of backups are being
implemented. With incremental backup (where the organization’s data archive
effectively becomes a volume built of mutually dependent “chapters” representing
backups taken at set intervals), more time is needed for a full restoration. Differential
backup strategies (where “last saved” versions of files may be backed up on a
piecemeal basis) require less. 
• For a truly effective backup strategy, it’s necessary to ensure that data retrieval can be
achieved in a timely and efficient manner. Finding the correct balance between
backup software and storage media is key to this. 
• Indexing of files for rapid retrieval is possible using backup solutions which have disk
or SSD storage in the data path. This form of storage may also act as a buffer for data
transfers to slower media, such as magnetic tapes or cloud storage. 
09/09/2022 126

Speeding Up Data Retrieval


• The compression and deduplication of data which disk
or SSD storage can perform before sending information to
the final backup medium can reduce transmission times
and cut the cost of backed-up data by a significant
margin. 
• Finally, with the right software implementation, storage in
the backup path can act as a cache which improves the
quality of service (QoS) of the response to data retrieval
requests.
09/09/2022 127

Disk-to-Tape

• Disk-to-tape backup solutions are most suitable for


offline processes, with alterations to data requiring
manual procedures and offline access.
• Backup strategies involving tape may be readily secured
against physical interference and hacking – as long as
storage sites exercise good inventory control practices.
09/09/2022 128

Disk-to-Cloud

• Disk-to-cloud solutions facilitate the recovery of individual files which may have
been corrupted or accidentally erased – a process that’s unduly time-consuming
with simple tape backups. Recovery times with cloud backup may be in the order of
seconds, rather than the hours or more it might take to sort through tapes.
• Encryption of data at the source helps resolve any nagging issues about the
security of what’s essentially a third-party storage medium. However, the risk
remains of accidental or deliberate corruption of information which is held online.
• Named as a leader in Gartner’s 2016 Magic Quadrant for Data Center Backup &
Recovery for the upper-end mid-market and larger enterprise environments, Veeam
Backup & Replication provides in-place recovery for fast recovery times, in what the
vendor describes as an offering of ‘Availability for the Always-On Enterprise’. It’s
capable of protecting and recovering an entire virtual machine (VM), as well as
individual files.
09/09/2022 129

Backup Of Mobile Devices

• As enterprise networks expand to embrace remote and


distant sites, mobile working, and Bring Your Own
Device (BYOD) policies, allowances must be made for
the backing up of data from a range of mobile or non-
standard hardware devices.
• Under these conditions, much of an organization’s data
may already be resident in the cloud – and backups to
this environment will need to form part of an ecosystem
which also includes more localized deployments of
backup hardware and software.
09/09/2022 130

Backup For Recovery

• Finding a balance between the blanket archiving of everything under the


enterprise hood, and a selected sub-set of information most critical to the survival of
the business is what will tip the scale one way or the other, as regards data
recovery. 
• As a rule of thumb, the data that’s backed up should at minimum be capable of
restarting the enterprise from scratch, should disaster strike. Enough information
needs to be included to satisfy ongoing requirements for regulatory compliance and
other legal obligations, including the ownership of encryption keys. 
• Data sets should be segregated wherever possible, to allow the replacement of
complete servers in one operation. 
• HPE Data Protector is an industry-leading backup solution for more complex
environments and VMs. Its integration with business applications extends server
backup, automated point-in-time recovery, and granular restores to individual
application users, while standardizing protection across physical and virtual
environments, various operating systems, and critical business applications. .
09/09/2022 131

Criteria for Backup Software


• Backup software should allow for data encryption at the source, with
multiple encryption keys under the stewardship of the backup team. 
• Transmission time, storage space, and time to reload may all be
drastically reduced by compression and deduplication features, which
may be deployed in a local storage pool on the server where the
backup gateway is installed, or on an allocated networked space. 
• The number of backup windows may be reduced via a software module
which supports multiple parallel backup operations. 
• WAN optimization tools can ensure data transmission during low
congestion times, or at lower connection tariffs. 
• From the leader in market share for backup and recovery software,
Veritas NetBackup covers Windows, Linux, Unix, and other platforms,
and provides online protection for major databases like Oracle and
Microsoft SQL. The software also has comprehensive integration with
VMware and Hyper-V.
09/09/2022 132

Criteria For Recovery Tools

• The ease with which files, folders and volumes may be recovered is the
litmus test for recovery software. Key metrics to watch for here include:
• RTO (Recovery Time Objective): How long it should take to get
everything back in order
• RPO (Recovery Point Objective): How much data the enterprise can
stand to lose, and still remain viable
• From a user perspective, the software should have controls for
allocating and managing access rights and privileges.
• For virtual desktops, mobile workspaces, or web-server farms and other
systems requiring heavy replication, facilities for compression and
deduplication, together with the capturing of roll-back snapshots
representing stable configurations are also a plus.
09/09/2022 133

Raised floor in data centers


09/09/2022 134
09/09/2022 135

Flooring in data centers


• Raised floor has become an architectural foundation for 
building modern data centers (DC), but their use is not limited only by machine halls of
data centers. Easy upgrade, as well as the ability to quickly add or remove cables,
provided with modern modular system makes attractive use of raised floors and other
premises.
• Today, designers seek to establish Raised floor in different rooms. Raised floor makes it
easy to upgrade the installation of various equipment, including ease of installation of
new redundant cables, redevelopment of premises for other needs and contributes to
their popularity among end users and customers. Raised floor has a broader consumer
market.
• Over the past few years, the SAC upgraded quite significantly, and the construction of
raised floors has remained unchanged. Raised floor makes sense to use when you need
to run a large number of cables. They are more efficient and much less expensive
than systems mounted near the ceiling, using which we must remember that the
temperature near the ceiling is higher than the floor.
• Instead of pulling cables from the ceiling, installers makes it easy to run cables under
raised floors. Existing solutions in this area provide efficient cooling, reducing the
number and extent of hidden cables, consolidation of physical ports, and fewer cords to
connect the equipment.
• Raised floor is a floor consisting of removable tiles that are installed on the supporting
structure, because of which, the flooring and floor-base can fit for different purposes.
09/09/2022 136

Flooring in data Centers

• Raised floor space used for cabling


• Among other things, under raised floors form ventilation system that
provide cooling wind direction where it is needed. Raised floor is
ideal for data centers, where ever there is new equipment or it is
rearranged from one place to another, it is easy to reinstall.
• It also ensure proper maintenance of cable management: The cable
is pulled under the floor, and it can be easily accessed, they are also
easy to upgrade or shift.
• Raised floor can be installed if the customer is implementing or
planning to implement new technologies that requires reconfiguration
of existing equipment or if he would need in the future.
• One of the main characteristics of raised floors is quick and easy
access to cabling. You can quickly raise the deck and get access to
the underground space.
09/09/2022 137

Flooring in data Centers

• The design of raised floor and the types of raised floors :


• Pedestal raised floor construction Floating (movable) raised floor.
• In the pedestal design, it support removable tiles that are used at
column-fixed-height pedestals. Raised floor tiles are usually made of steel,
aluminum or wood treated with flame retardant.
• Flooring should settle at a height of not less than 150-300 mm from the
floor base (concrete floor).
• “Float” design should be built at a height of 460 mm from the floor. Vertical
seismic load is absorbed by the dampers and springs that are installed
inside the support cylinder. With regard to horizontal displacements, they
are neutralized with steel shoes that are Teflon-coated and they are wore
at the base of cylinders. Shoes can skim the surface of tiles and can be
clamped to the floor. In the typical raised floor systems, they use Slub tile
of 0.6 x 0,6 m and 0,36 square area.m size.
09/09/2022 138

Flooring in data Centers

• In order to supply cooling air to the places of high heat in front of the
enclosure, perforated tiles are installed. Tiles for service under the raised
floors systems can be removed from the floor and they can be shifted to
other places.
• Close to the particularly strong heating equipment, the devices that
guides the air flow into the holes of perforated raised floor tiles can be
installed. When the premises have to change something, tiles are
removed from the floor and they are moved to another location.
• In the initial arrangement of the room they all want to ensure optimal, as it
seems, the balance of computer and communications equipment. But
people often do not know at what point they will need this technique in the
future, therefore they do not know what changes need to be made in the
scheme of its deployment. It is therefore desirable to have a solution that
allows you to quickly cost-shift the equipment, introduce new
technologies to replace the equipment. If you are completely sure that you
will never make any changes and do not need to introduce new
technologies, raised floor is not for you.
09/09/2022 139

Flooring in data Centers

• Raised floor is usually associated with data centers, since a


large amount of equipment is much easier to organize the flow
of cooling air under the floor rather than from above. But the
most difficult problem in data centers is the organization of
cooling and access to cables. Often in the field of concentration
equipment arise where equipment is overheating, so-called “hot
spots”.
• This problem is only exacerbated by the extensive use of
blade servers. Typical data centers built before 2000,
calculated on the heat, is equal to 5 kW per rack. Now, in
today’s data centers, this figure could be range from 7 kW to 35
kW per server rack, or even higher because there are a lot of
data centers who place more servers in small area, which give
correspondingly more heat, so they often have hot spots.
09/09/2022 140

Flooring in data Centers


• Design Problems with Raised Floor
• When you install the raised floor system, designers face a number of standard tasks,
including – to set the tiles, to ensure reliable grounding and protection from electrical
interference. In areas that are in front of places of racks, stacked perforated tiles. These
metal surfaces should not be open, we must exclude them into direct contact with
installed equipment. Metal tiles and raised floor is a supporting structure and must be
well grounded. Openings for dragging cables to avoid mechanical damage to the latter
should not have sharp edges.
• When designing the raised floor, you have to make sure that:
• * You have a sufficient powerful air conditioning system for cooling all the equipment;
• * You have to consider the limitations of mechanical load on the raised floor and
concrete floor;
• * You should check that there is enough free space to install the equipments available;
• * You should address the needs of areas for future development
09/09/2022 141

Flooring in data Centers

• When the layout of equipment will be ready on the floor, arrange


appropriate stencils surfaces for installation of equipment and markup
the input and output of cables.
• With the development of cable technology and expanding the scope of
raised floors, designers are facing new challenges. Twenty years ago the
premises of data centers were the largest of those premises, which
used Raised floor.
• Now raised floors are installed in huge halls like a library, “clean rooms”
for different industries. The use of raised floors allows customers to
abandon expensive ceiling mounted systems, cables, besides, it does
not require punching holes in the building constructions to liner cables.
• That is what made Raised floor an attractive technical solution, and
brought them outside the computer rooms of data centers and server
rooms. Now the technology of raised floors, which was developed mainly
for the latter, is largely growing demand from owners of office for general
purposes.

You might also like