




版權說明:本文檔由用戶提供并上傳,收益歸屬內容提供方,若內容存在侵權,請進行舉報或認領
文檔簡介
Date
|
City,
Country虛擬化?大數據的?大規(guī)模應?用
IT
at
theSpeed
of
Business*
Source:
Gartner,
2013:
“Hunting
and
Harvesting
in
a
Digital
World:
The
2013
CIO
Agenda”IT
at
the
speed
of
business
IT
Technology
ErasMainframeClient-ServerMobile-Cloud$$$$$$Steady
ITBudgets*
Business
ExpectationsAbility
of
IT
to
Deliver23Software-Defined
Data
CenterAgility,
Efficiency,
Control
and
Choice
in
the
Mobile-Cloud
EraAll
infrastructure
is
virtualized
and
deliveredas
a
service,
enabling
comprehensive
datacenter
management
through
software
and
extensibility
to
cloud
resources
AgilityControlEfficiency
Choice4Software-Defined
Data
CenterAgility,
Efficiency,
Control
and
Choice
in
the
Mobile-Cloud
EraAll
infrastructure
is
virtualized
and
deliveredas
a
service,
enabling
comprehensive
datacenter
management
through
software
and
extensibility
to
cloud
resources
Agility
EfficiencyControlChoice5Unified
Platform
for
Any
ApplicationScale-up,
Scale-out,
and
Everything
in
BetweenScale-UpScale-Outthan
running
bare-metalvSphere
6:
Great
for
Big
Data630
TB
TeraSort
Benchmark
(32-host
cluster,
4
VMs
per
host)Virtualized
Hadoopup
to
12%
faster11Basedon
VMware
internal
tests,
Jan
2015vSphere
6.0
Tests
–
Hardware
LayoutCONFIDENTIAL7CONFIDENTIAL8Virtualizing
Big
Data:
Value
Proposition
Agility??
Infrastructure
on
demand??
Rapid
scaling
of
clusters
Simplified
Management??
Centralized
data
center
management??
Automated
BD
workloads
configuration
and
deployment
with
best
practices
Efficiency??
Resource
pooling??
Server
and
cluster
consolidation
Performance??
Up
to
12%
better
performance??
No
significant
overhead9vSphere
+
Big
Data
ExtensionsAgility
Physical
Timeframe:
Weeks??
Order
Hardware
(Servers,
Storage,
Etc)??
Wait
for
them
to
arrive??
Setup??
Server
Preparation??
OS
Installation??
Disk
Configuration??
Network
configuration??
Hadoop
Install
and
Configuration
Virtual
Timeframe:
Minutes??
Spin
up
a
new
virtual
machine??
Add
virtual
machine
to
cluster1011
OS
Installation
Network
ConfigurationHadoop
Installation
and
ConfigurationHadoop
Cluster
Deployment
on
VMware
On
physical
machines
Server
PreparationOn
VMware
Big
Data
Extensions
for
VM
creation,
configuration,
start-upBig
Data
Extensions
orother
Hadoop
Management
ToolSimplified
Management12??
Familiar
vSphere
Graphical
User
Interface??
Setup
a
flexible
configuration
and
BDE
will
connect
the
dots
behind
the
scenesBDE
Allows
Flexible
Configurations
Storage
configuration
Choice
of
shared
or
localHigh
Availability
optionNumber
of
nodes
andresource
configurationVM
placement
policiesEnable
Hadoop
As
A
Service
On-premvCenter
PluginvCloud
Automation
CenterHadoop
as
a
ServiceEfficiency??
Better
utilization
of
servers??
Efficient
and
rapid
scaling
of
clusters
through
VM
cloning??
Best
practices
for
VM
placement
onto
servers15Hadoop
1Hadoop
2
HBase??
Consolidated
cluster
has
access
to
entire
pool
of
physical
resources??
Take
advantage
of
multi-tenancy
to
increase
utilization
during
non-peak
hours??
Reduce
latency
on
priority
jobs
on
consolidated
clusterIncrease
Utilization
to
Control
CostsVirtualizing
Big
Data:
Value
Proposition
Agility??
Infrastructure
on
demand??
Rapid
scaling
of
clusters
Simplified
Management??
Centralized
data
center
management??
Automated
BD
workloads
configuration
and
deployment
with
best
practices
Efficiency??
Resource
pooling??
Server
and
cluster
consolidation
Performance??
Up
to
12%
better
performance??
No
significant
overhead17vSphere
+
Big
Data
ExtensionsvCenter
Operations
ManagerIntegrated
Solution
for
Big
Data
Infrastructure
ManagementvCloud
Automation
Center
ElasticityConfiguration
IsolationAvailability
vSphere
vCenterBig
Data
Extensions
Deployment
Multi-tenancy
ESXi
ClusterHow
BDE
Works??????BDE
is
a
downloadable
virtual
appliance
integrated
as
a
plug-
in
to
vCenter
server.BDE
requires
a
vSphere
5.0
or
later
license
and
an
Enterprise
or
Enterprise
Plus
license.BDE
clones
VMs
from
the
template
and
controls/configures
VMs
through
vCenterHostHostHostHostHostVirtualization
PlatformHadoop
NodeHadoop
NodevCenterManagement
ServerTemplateVirtual
ApplianceDeployment
Options
with
Big
Data
Extensions20
BDE
OnlyBDE
provisions
VMs
and
installs
the
Hadoop
software
BDE
2.0
BDE
provisions
emptyVMsHadoop
management
tool
installs
software
BDE
2.1
BDE
VMs
and
callsmanagement
tool
APIHadoop
management
tool
installs
software
under
the
hoodSkyscape
Cloud
Services??
A
UK
company
that
provides
cloud
computing
services
to
the
UK
Government’s
G-Cloud
initiative.??
Skyscape
offers
IaaS,
PaaS,
SaaS.??
5
customers
lined
up
at
the
first
day
of
GA.??
Expected
to
expand
to
140
servers
very
soon.??
Skyscape
Hadoop
in
the
Cloud
is
built
on
top
of
BDE.??
Used
our
API
quite
independently.??
Public
Reference
with
case
studyAdobe
Case
Study??
Digital
Marketing
business
unit??
Hadoop
as
a
Service
using
vRA
solution??
Goal
is
to
bring
Hadoop
on
AWS
in-house??
Now
in
production??
Currently
several
BDE
clusters
running
in
Oregon??
Hundreds
nodes
across
6
data
centers
by
VMworld??
Performance
meeting
and
exceeding
expectations??
Public
reference
with
case
studyCONFIDENTIAL2223??Virtualized
??based
onvSphere6.0
and
VMware
Big
Data
Extensions
2.2??
EMC
Isilon
7.2.0.2
with
two
patches
for
HDFS
Storage??
Pivotal
Big
Data
Suite
3.0
for
Hadoop
2.6
andHAWQ
1.3
??
Pivotal
Spring
XD
1.2
for
Data
Ingestion
to
Hadoop??
Alpine
Data
Lab
5.4
for
running
????Deeper
Analytic
FunctionsMachine
Learning
Algorithms
??
HUE
2.6
for
GUI
based
HIVE/PIG
Query
execution
client
VMware
ITThis
Big
Data
Cluster
is
fully
At
VMware
IT,
we
have
established
the
fact
that
an
Enterprise
BigData
Analytics
Platform
can
be
successfully
built
and
run
on
top
of
VMware
Virtual
Infrastructure
with
EMC
Isilon
and
PHD
3.0
-with
great
performance
Take
Away
…Hybrid
storage
model
-
the
best
of
both
worlds
–?Master
nodes–?NameNode,
ResourceManager,
ZooKeeper
etc.
on
shared
storage
??Leverage
vSphere
vMotion,
HA
and
FT–?Worker
nodes
??NodeManager/DataNode
on
local
storage
??Lower
cost,
scalable
bandwidth
??Temp
data
is
written
to
local
storage
for
best
performance
??Scale-out
NAS
storage
for
HDFS
data
is
a
good
alternative
to
local
Shared
Storage
Local
StorageNAS
(Isilon)
for
HDFSCombined
Model
–
Two
Virtual
Machines
on
a
HostVirtualization
HostHadoopVirtualNode
1DataNodeNodeManager
Ext4VMDKShared
storageSAN/NASLocal
disks
Ext4
OS
Image
–
VMDKOS
Image
–
VMDKExt4VMDKExt4
VMDKVMDKHadoopVirtualNode
2DataNode
Ext4VMDKNodeManager
Ext4VMDKExt4VMDKExt4
VMDK
Virtualiza*on
Host
VMDK
Hadoop
Virtual
Node
1
Ext4
Separated
Model
with
VMDK
Isolation
NodeManager
Shared
storage
SAN/NAS
OS
Image
–
VMDK
OS
Image
–
VMDK
Hadoop
Virtual
Node
2
Datanode
VMDK
VMDK
VMDK
Ext4
Ext4
Ext4
VMDK
VMDK
VMDK
Ext4
Ext4
Ext4
Local
disks
for
Temp
Data
JBOD
Local
disks
for
HDFS
Data
JBOD
Tenant
1
Tenant
2Compute
StorageCombined
Compute
andStorage
StorageVMVMVMVMVMVMUnmodi?ed
Hadoop
node
in
a
VM
??
溫馨提示
- 1. 本站所有資源如無特殊說明,都需要本地電腦安裝OFFICE2007和PDF閱讀器。圖紙軟件為CAD,CAXA,PROE,UG,SolidWorks等.壓縮文件請下載最新的WinRAR軟件解壓。
- 2. 本站的文檔不包含任何第三方提供的附件圖紙等,如果需要附件,請聯(lián)系上傳者。文件的所有權益歸上傳用戶所有。
- 3. 本站RAR壓縮包中若帶圖紙,網頁內容里面會有圖紙預覽,若沒有圖紙預覽就沒有圖紙。
- 4. 未經權益所有人同意不得將文件中的內容挪作商業(yè)或盈利用途。
- 5. 人人文庫網僅提供信息存儲空間,僅對用戶上傳內容的表現(xiàn)方式做保護處理,對用戶上傳分享的文檔內容本身不做任何修改或編輯,并不能對任何下載內容負責。
- 6. 下載文件中如有侵權或不適當內容,請與我們聯(lián)系,我們立即糾正。
- 7. 本站不保證下載資源的準確性、安全性和完整性, 同時也不承擔用戶因使用這些下載資源對自己和他人造成任何形式的傷害或損失。
最新文檔
- 2025版戶外鋁合金欄桿生產與安裝項目合同
- 2025版高鐵線路防雷安全保障合同書
- 2025版金融科技公司股權結構優(yōu)化與風險控制合同
- 2025版特色豬欄設計與建設總承包服務合同
- 二零二五年智能家居設備采購與銷售合同
- 2025房地產項目定制化銷售策略與渠道拓展服務合同
- 二零二五年度海洋工程設備租賃與維護服務合同
- 2025版國際工程項目承包合同范本及執(zhí)行細則
- 二零二五年餐廳總經理任期制勞動合同
- 二零二五年新型強化木地板安裝工程合同范本
- 管道閉水試驗(自動計算)
- 借道合同協(xié)議書
- 微專題講義:零點差問題-解析版
- 高速鐵路路基試驗段施工方案
- 數據結構與算法分析-課件-宋霜-最終完整版
- 行政部工作職責、流程、制度
- 林業(yè)專業(yè)知識考試試題及答案
- 1688代運營合同模板
- 中職旅游專業(yè)《中國旅游地理》說課稿
- 常見有毒易燃易爆氣體、粉塵檢測合格標準
- 呋喃西林溶液的毒理學研究
評論
0/150
提交評論