• No results found

Server Virtualization: The Essentials

N/A
N/A
Info
Download
Protected

Academic year: 2021

Share "Server Virtualization: The Essentials"

Copied!
36
0
0

Loading.... (view fulltext now)

Download now ( 36 Page )

Full text

(1)

Server Virtualization: The Essentials

Part 1 of 4

(2)

Agenda

ƒ

Server Virtualization: The Essentials

•

What is virtualization?

•

Why consolidation and virtualization?

•

Advantages of Virtualization

•

Disadvantages of Virtualization

•

Different Approaches

(3)

What is virtualization?

ƒ

Virtualization creates a level of indirection or an abstraction layer

between a physical object and the managing application.

ƒ

Storage virtualization refers to the presentation of a simple file,

logical volume or other storage object (ie. disk drive) to an

application in such a way that allows the physical complexity of the

storage to be hidden from both the storage administrator and the

application.

ƒ

Virtualization involves the process of presenting computing

resources in ways that users and applications can easily get value

out of them, rather than presenting them in a way dictated by their

implementation, geographic location, or physical packaging.

(4)

Why consolidation and virtualization?

ƒ

Mainframes (Centralized Computing)

ƒ

Open Systems (Distributed Computing)

ƒ

Computer Sprawl (Application-driven)

(5)

Advantages of Virtualization

ƒ

Increased server utilization

ƒ

Rapid service deployment

ƒ

Hidden complexity

(6)

Disadvantages of Virtualization

ƒ

Administration complexity

ƒ

Skilled personnel

ƒ

Confusion over different approaches

ƒ

Confusion regarding standard statistics

(7)

Different Approaches

ƒ

IBM (AIX)

ƒ

Hewlett-Packard (HP-UX)

ƒ

Sun Microsystems (Solaris)

ƒ

VMware (ESX)

(8)
(9)

Different Approaches: IBM LPARs

ƒ

Single OS in each LPAR

ƒ

CPUs are not shared across LPARs

ƒ

CPUs are provisioned by whole CPUs

Software

Hardware

Applications

AIX

Applications

AIX

(10)

Different Approaches: Firmware, IBM Micropartitions

Software

Firmware

Hardware

CPU

CPU

(11)

Different Approaches: Firmware, IBM Micropartitions

ƒ

Multiple OSs

ƒ

Partial CPU configuration

ƒ

CPUs can be shared across LPAR

ƒ

AIX sees physical and virtual CPUs

Software

Firmware

Hardware

Applications

Applications

CPU

CPU

CPU

CPU

AIX

AIX

(12)
(13)

Different Approaches: Hardware, NPAR

ƒ

Single OS in each NPAR

ƒ

CPUs are not shared across NPAR

ƒ

CPUs are provisioned by whole CPUs

Software

Hardware

Applications

HPUX

Applications

HPUX

(14)

Different Approaches: Firmware, HP VPAR

Software

Firmware

Hardware

CPU

CPU

Memory

Memory

I/O

I/O

CPU

CPU

Memory

Memory

I/O

I/O

Virtual Partition Monitor

HP 9000 Firmware

Applications

Applications

(15)

Different Approaches: Firmware, HP VPAR

ƒ

Multiple O.S.s

ƒ

No Partial CPU configuration (Core Granularity)

ƒ

CPUs can be shared across VPAR

Software

Firmware

Hardware

Applications

Applications

HPUX

HPUX

(16)
(17)

Different Approaches: Hardware, Sun Domains

ƒ

Single OS in each domain

ƒ

CPUs are not shared across domains

ƒ

CPUs are provisioned by whole CPUs

Software

Hardware

Applications

Solaris

Applications

Solaris

(18)
(19)

Different Approaches

: Software, Solaris Zones

ƒ

Single OS

ƒ

Physical CPUs are visible to the OS

Software

Hardware

Applications

Solaris 10

Applications

CPU

CPU

CPU

CPU

(20)

Different Approaches: Firmware, Solaris LDOMS

Software

Firmware

Hardware

CPU

CPU

(21)

Different Approaches: Firmware, Solaris LDOMS

ƒ

Multiple OSs

ƒ

Partial CPU configuration

ƒ

Solaris sees physical and virtual CPUs

Software

Firmware

Hardware

Applications

Applications

CPU

CPU

CPU

CPU

(22)
(23)

Different Approaches: Software, VMware ESX Server

ƒ

Single “host” OS

ƒ

Physical CPUs visible to the host OS

ƒ

“Guest” OS sees virtual CPUs

Software

Hardware

Applications

VMware ESX

Applications

CPU

CPU

CPU

CPU

(24)

Different Approaches: Software, Windows Virtual Server

Software

Hardware

Windows

CPU

CPU

Memory

Memory

I/O

I/O

CPU

CPU

Memory

Memory

I/O

I/O

Windows Virtual Server

Applications

Applications

(25)

Different Approaches: Software, Windows Virtual Server

ƒ

Single “host” OS

ƒ

Physical CPUs visible to the host OS

ƒ

“Guest” OS sees virtual CPUs

Software

Hardware

Applications

Windows

Applications

CPU

CPU

CPU

CPU

(26)

CPU Measurements

ƒ

Traditional CPU measurements now have

very different meanings

ƒ

CPU measurements are gathered from

operating system APIs

ƒ

Pay close attention to where you look for

CPU resource usage

(27)

Example Configuration – IBM Micropartition

POWER Hypervisor

Shared Pool

Dedicated

Applications

AIX

VCPU

PCPU

VCPU

Applications

AIX

VCPU

Applications

AIX

VCPU VCPU

PCPU

PCPU

VCPU

ƒ

VS1 Configuration

•

2-Virtual CPUs, 1-Entitled Capacity

•

Capped, SMT off, Shared Processor Pool

ƒ

Single process running in VS1 using 45 seconds of a

physical CPU in a 60 second interval

VCPU VCPU

VCPU VCPU

PCPU

(28)

Virtual Processor

POWER Hypervisor

Shared Pool

Dedicated

Applications

AIX

VCPU

CPU:Summary::%busy

The percentage of the virtual processor capacity consumed.

Affected by both SMT and Capping.

PCPU

PCPU

VCPU

Applications

AIX

VCPU VCPU

Applications

AIX

VCPU VCPU

PCPU

PCPU

PCPU

PCPU

PCPU

PCPU

VCPU VCPU

VCPU VCPU

VS3

VS2

VS1

(29)

Entitled Processor

CPU:by LPAR::%entc

The percentage of the entitled processor capacity consumed by

the partition.

POWER Hypervisor

Shared Pool

Dedicated

Applications

AIX

VCPU

PCPU

VCPU

Applications

AIX

VCPU VCPU

Applications

AIX

VCPU VCPU

PCPU

PCPU

PCPU

PCPU

PCPU

PCPU

VCPU VCPU

VCPU VCPU

PCPU

VS3

VS2

(30)

Processor Pool

CPU:by LPAR::%lpar_pool_busy

The percentage of the processor pool capacity consumed by the

partition.

POWER Hypervisor

Shared Pool

Dedicated

Applications

AIX

VCPU

PCPU

PCPU

VCPU

Applications

AIX

VCPU VCPU

Applications

AIX

VCPU VCPU

PCPU

PCPU

PCPU

PCPU

PCPU

PCPU

VCPU VCPU

VCPU VCPU

VS3

VS2

VS1

(31)

All Processors

CPU:by LPAR::%lpar_phys_busy

The percentage of the physical processor capacity consumed by

the partition.

POWER Hypervisor

Shared Pool

Dedicated

Applications

AIX

VCPU

PCPU

PCPU

VCPU

Applications

AIX

VCPU VCPU

Applications

AIX

VCPU VCPU

PCPU

PCPU

PCPU

PCPU

PCPU

PCPU

VCPU VCPU

VCPU VCPU

VS3

VS2

(32)

Processor Pool

CPU:by LPAR::%total_pool_busy

The percentage of the processor pool capacity consumed by all

partitions using the pool.

POWER Hypervisor

Shared Pool

Dedicated

Applications

AIX

VCPU

PCPU

PCPU

VCPU

Applications

AIX

VCPU VCPU

Applications

AIX

VCPU VCPU

PCPU

PCPU

PCPU

PCPU

PCPU

PCPU

VCPU VCPU

VCPU VCPU

VS3

(33)
(34)

Additional Statistics

CPU:by LPAR::physc

The number of physical processors consumed by the

partition.

CPU:by LPAR::app

(35)

Is Capacity Planning Important?

ƒ

What happens to response times when

activity changes?

ƒ

When will my guest get “full”?

ƒ

When will my application activity exceed

my server capacity?

ƒ

When will my application activity exceed

my cluster capacity?

(36)

Conclusion of Part 1

For more discussion on this topic, please contact

Jim Smith at:

[email protected]

To view demos on how to better manage the

capacity of virtualized VMware ESX, Sun Solaris

and IBM AIX server environments, simply close

this video and return to the TeamQuest website

For Capacity Planning solutions please call:

Corporate Offices and Americas Europe, Middle East, Africa Asia Pacific United Kingdom

References

Download now ( PDF - 36 Page - 544.43 KB )

Related documents

Mitigating Insider Threat in Relational Database Systems

Protecting information is as important as protecting other organizational sensitive assets such as money. In this era of rapid revolution in computer technologies and

2. Quality Cost

cost per unit of production of production Measure of quality Measure of quality ( Quality Level) ( Quality Level) Economic Economic  balance  balance Total Total cost cost

Balancing CPU, Storage

Choosing the best server virtualization hardware and storage protocols FAQ: How to select optimal memory, CPU and storage for virtualization Understanding VMware ESX

CON9577 Performance Optimizations for Cloud Infrastructure as a Service

Performance concepts for the cloud and VM environments Oracle VM Server for x86: optimizing CPU, Memory, I/O. Oracle VM Server for SPARC: optimizing CPU, Memory, I/O

Exadata for Oracle DBAs. Longtime Oracle DBA

The Magic #1 CPU Memory Network I/O Controller Disk The communication between CPU and Disk carries the information on the query – columns and predicates. This occurs as a result

Lineer Cebir matris determinant

 A=[a ijij ]] mxp mxp , B=[b , B=[b ijij ]] pxn pxn iki matris olsun. satır vektörü ile  A.B ise bu eleman A nın i. sütun vektörünün skaler çarpımına çarpımına eşittir.

Does antiretroviral treatment increase the infectiousness of smear-positive pulmonary tuberculosis?

Prevalence of TST positivity was compared between household contacts by HIV and ART status of the index case to distinguish those not on ART or on ART for ,1 year from those on ART

Interview with Sir Peter Marshall: Commonwealth Oral History Project

T, when looking through the communiqué of the meeting of CHOGM, said on one occasion, “Haven’t you noticed how much better drafted the economic sections are than the