CLASSIC DATA CENTER

Copyright © 2011 EMC Corporation. All Rights Reserved. 1

 Classic Data Center (CDC)

Lesson 1: Application, DBMS, Compute, and Storage

Topics covered in this lesson:
• Application and DBMS
• Physical and logical components of a compute system
• Storage device options
• RAID technology and Intelligent storage system

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 2
Classic Data Center (CDC)
CDC

A CDC is a facility containing physical IT resources including compute,

network, and storage

Classic Data Center

Core elements of CDC

Application

Database Management System (DBMS)

Compute

Storage

Network

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 3
Key Requirements of a Data Center

Availability

Data Integrity Performance

Manageability

Security Flexibility

Scalability

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 4
Application
• Commonly deployed applications in a CDC
 Business applications
 E-mail, Enterprise Resource Planning (ERP), Decision Support System
(DSS), Data Warehouse (DW)
 Management applications
 Resource management, performance tuning
 Data protection applications
 Backup, replication
 Security applications
 Authentication, antivirus
• Key I/O characteristics of an application
 Read intensive vs. write intensive
 Sequential vs. random

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 5
Database Management System (DBMS)
• Database is a structured way to store data in logically organized
tables that are interrelated
 Helps to optimize the storage and retrieval of data
• DBMS is a collection of computer programs that control the
creation, maintenance, and use of databases
 Processes an application’s request for data
 Instructs the OS to retrieve the appropriate data from storage
• Popular DBMS examples are MySQL, Oracle RDBMS, SQL Server,
etc.

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 6
Compute
Compute

A resource that runs applications with the help of underlying computing

components

• Compute consists of physical components (hardware devices) and logical

components (software and protocols)
• Physical components of compute are CPU, Memory, and Input/Output (I/O)
devices
• I/O devices facilitate the following types of communication:
 User to compute: Handled by basic I/O devices such as keyboard, mouse, etc.
 Compute to compute/storage: Enabled using host controller or host adapter

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 7
Examples of Compute System
• Examples of compute systems:
 Laptops/Desktops
 Blade servers
 Complex cluster of servers
 Mainframes
• Bladed server technology is commonly used to deploy compute
systems in a CDC
 Consolidates power- and system-level function into a single,
integrated chassis
 Enables the addition of server modules as hot-pluggable
components
 Provides increased server performance and availability without
increase in size, cost, or complexity

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 8
Bladed Servers

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 9
Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 10
Server Clustering
• Multiple servers (nodes ) are brought together in a cluster to
improve availability and performance
 When a failure occurs on one node in a cluster, resources and
workload are redirected to another node
• Exchange heartbeat is a checkup mechanism between two nodes
 To see whether a node is up and running
 A failover is initiated, if heartbeat fails

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 11
Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 12
Logical Components of Compute

Applications

File System

Operating System
Logical Components
Volume Manager

Device Drivers

Storage

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 13
Storage
Storage

It is a resource that stores data persistently for subsequent use.

• Data created by individuals/businesses must be stored for further

processing
• The type of storage device used is based on the type of data and
the rate at which it is created and used
• A storage device may use magnetic, optical, or solid state media
 Examples: Disk drive (magnetic), CD (optical), Flash drive (solid state)

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 14
Storage Device Options

• Low cost solution for long term data storage

Tape Drive • Sequential data access, physical wear and tear,
and storage/retrieval overheads

• Write Once and Read Many (WORM): CD, DVD

Optical Disk • Limited in capacity and speed
• Popular in small, single-user environments

• Random read/write access

• Uses mechanical parts for data access
Disk Drive
• Most popular storage device with large storage
capacity

• Provides ultra high performance required by

Solid State Drive mission-critical applications
• Very low latency per I/O, low power
requirements, and very high throughput per drive

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 15
Redundant Array of Independent Disks (RAID)
RAID

A technology which utilizes multiple disk drives as a set to provide

protection, capacity, and/or performance benefits

• Disk drives are susceptible to failures due to mechanical wear

and tear and other environmental factors. A disk drive failure
could result in data loss. A disk drive has a projected life
expectancy before it fails. Today, data centers house thousands
of disk drives in their storage infrastructures. Greater the
number of disk drives in a storage array, greater the probability
of a disk failure in the array. RAID technology was developed to
mitigate this problem. RAID is an enabling technology that
leverages multiple disks as part of a set.

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 16
Redundant Array of Independent Disks (RAID)
• Overcomes limitations of disk drives
• Improves storage system performance
 By serving I/Os from multiple disks simultaneously
• RAID techniques are:
 Striping, mirroring, and parity

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 17
Redundant Array of Independent Disks (RAID)
• Striping is a technique of spreading data across multiple drives in
order to use the drives in parallel. All read-write heads work
simultaneously. This allows more data to be processed in a
shorter time. Consequently, performance increases, when
compared to writing/retrieving data to/from one disk at a time.
• Mirroring is a technique where data is stored on two different
disk drives, yielding two copies of data. In the event of one drive
failure, the data is intact on the surviving drive, and the
controller continues to service the compute system’s data
requests from the surviving disk of the mirrored pair.
• Mirroring is expensive because it involves duplication of data —
the amount of storage capacity required is twice the amount of
data being stored. Mirroring can be implemented with striped
RAID, by mirroring entire stripes of disk set to stripes on the
other disk set. This is known as nested RAID.
Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 18
Redundant Array of Independent Disks (RAID)
• Parity is a method of protecting striped data from disk failure
without the cost of mirroring. An additional disk drive is added in
the strip set to hold parity, a mathematical construct that allows
re-creation of the missing data. Parity RAID is less expensive than
mirroring because parity overhead is only a fraction of the total
capacity. Parity information can be stored on separate, dedicated
disk drives or distributed across all the drives in a RAID set
• If one of the disks fails in a RAID set, the value of its data is
calculated by using the parity information and the data on the
surviving disks. The value is calculated using XOR operation.
• However, there are some disadvantages of using parity. Parity
information is generated from data on the data disks. As a result,
parity is recalculated every time there is a change in data. This
recalculation takes time and affects the performance during
write operation.

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 19
RAID Techniques

Striping Mirroring Parity

A A A

RAID Controller RAID Controller RAID Controller

A1 A2 A3 A A A1 A2 Ap

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 20
RAID Levels

RAID Levels Definition

RAID 0 Striping with no fault tolerance
RAID 1 Disk mirroring
Nested Combinations of RAID levels; Example: RAID 1 + RAID 0
RAID 3 Parity RAID with dedicated parity disk
RAID 5 Parity RAID with distributed parity across all the disks in the set
RAID 6 Distributed parity RAID with dual parity

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 21
Intelligent Storage System
• Business-critical applications require high levels of performance,
availability, security, and scalability. A disk drive is a core element
of storage that governs the performance of any storage system.
Some of the older disk array technologies could not overcome
performance constraints due to the limitations of a disk drive
and its mechanical components.
• RAID technology made an important contribution to enhance
storage performance and reliability, but disk drives, even with a
RAID implementation could not meet performance requirements
of today’s applications.
• With advancements in technology, a new breed of storage
solutions, known as an Intelligent Storage System, has evolved.

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 22
• These intelligent storage systems are feature-rich RAID arrays
that provide highly optimized I/O processing capabilities.
• These storage systems are configured with a large amount of
memory (called cache) and multiple I/O paths and use
sophisticated algorithms to meet the requirements of
performance-sensitive applications.
• These arrays have an operating environment that:
 intelligently and optimally handles the management, allocation,
and utilization of storage resources.

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 23
 Components of an Intelligent Storage System
• An intelligent storage system consists of four key components: Front-end,
Cache, Back-end, and Physical Disks.

Intelligent Storage System

Compute Front-end Back-end Physical Disks

Cache

Network

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 24
Presenting Storage to Compute System

Intelligent Storage System

LUN 0 Front-end Back-end

Physical Disks

Cache
LUN 0

Network
Compute

LUN 1

LUN 1
Controller RAID Set

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 25
Presenting Storage to Compute System
• In an intelligent storage system, physical disks are logically
grouped together to form a set, called RAID set, on which a
required RAID level is applied.
• The number of drives in the RAID set and the RAID level
determine the availability, capacity, and performance of the RAID
set.
• It is highly recommended that the RAID set be created from the
same type, speed, and capacity drives to ensure the maximum
usable capacity, reliability, and consistent performance. For
example, if drives of different capacities are mixed in a RAID set,
then the capacity of the smallest drive will be used from each
disk in the set to make up for the RAID set’s overall capacity. The
remaining capacity of the larger drives will remain unused.

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 26
Presenting Storage to Compute System
• Likewise, mixing higher Revolutions per minute(RPM) drives with
lower RPM drives lowers the overall RAID set’s performance.

Copyright © 2011 EMC Corporation. All Rights Reserved. Classic Data Center 27