22
CLOSER 2014, April 3 2014, Barcelona Ryousei Takano , Atsuko Takefusa, Hidemoto Nakada, Seiya Yanagita, and Tomohiro Kudoh Informa(on Technology Research Ins(tute, Na(onal Ins(tute of Advanced Industrial Science and Technology (AIST), Japan Iris: Intercloud Resource Integra3on System for Elas3c Cloud Data Center

Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Embed Size (px)

DESCRIPTION

CLOSER 2014@Barcelona

Citation preview

Page 1: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

CLOSER  2014,  April  3  2014,  Barcelona

Ryousei  Takano,  Atsuko  Takefusa,  Hidemoto  Nakada,    Seiya  Yanagita,  and  Tomohiro  Kudoh  

 Informa(on  Technology  Research  Ins(tute,    

Na(onal  Ins(tute  of  Advanced  Industrial  Science  and  Technology  (AIST),  Japan

Iris:  Inter-­‐cloud  Resource  Integra3on  System  for  Elas3c  Cloud  Data  Center�

Page 2: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Background�•  Open  source  Cloud  OS  

–  Private/Public/Hybrid  clouds  –  e.g.,  Apache  CloudStack,  OpenStack  

•  Inter-­‐cloud  federaQon  –  ElasQc  resource  sharing  among  clouds  –  Assured  service  availability  under  disaster  and  failure  

–  Guaranteed  QoS  against  rapid    load  increase  

–  e.g.,  GICTF,  IEEE  P.2302  

2

FederaQon

Page 3: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Two  Inter-­‐cloud  models �A.  Overlay  model:  vIaaS  

–  FederaQon  by  IaaS  users  –  e.g.,  RightScale  

3

DC DC DC

IaaS

VI

IaaS IaaS

DC  (requester)

DC  (provider)

DC  (requester)

VI

VI  (=  IaaS) VI  (=  IaaS)

vIaaS:  VI  as  a  Service HaaS:  Hardware  as  a  Service

federa(on  layer   IaaS  tenant    

     

     

     

     

   

   

   

   

   

Virtual  Infrastructure

B.  Extension  model:  HaaS  –  FederaQon  for  IaaS  

providers  

Page 4: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Goal �•  Goal:  

–  A  Cloud  OS  can  transparently  scale  in  and  out  without  concern  for  the  boundary  of  data  centers.  

•  Requirements:  –  Ease  of  use:  no  modificaQon  for  Cloud  OS  –  Mul3-­‐tenancy:  Cloud  OS-­‐neutral  interface  –  Secure  isola3on:  isolaQon  between  a  HaaS  provider  and  HaaS  users  (IaaS  providers)  

•  SoluQon:  –  Nested  VirtualizaQon  

4

Page 5: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Contribu3on �•  We  propose  a  new  inter-­‐cloud  service  model  HaaS,  which  enable  us  to  implement  “elasQc  data  center.”  

•  We  have  developed  Iris,  which  constructs  a  VI  over  distributed  data  centers  by  using  nested  virtualizaQon  technologies,  including  nested  KVM  and  OpenFlow.  

•  We  demonstrate  Apache  CloudStack  can  seamlessly  manage  resources  over  mulQple  data  centers  on  an  emulated  inter-­‐cloud  environment.

5

Page 6: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Outline �•  IntroducQon  •  Iris:  Inter-­‐cloud  Resource  IntegraQon  System  •  Experiment  •  Conclusion

6

Page 7: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

HaaS:  Hardware  as  a  Service�

7HaaS  Data  Center

IaaS  DC  1  

IaaS  DC  2  

L1  VMs

IaaS  admin

IaaS  tenant

PMs

L1  VMs

L1  VMs

PMs:  Physical  Machines  L1  VMs:  Layer  1  Virtual  Machines  L2  VMs:  Layer  2  Virtual  Machines

L2  VMs

IaaS  tenant

L2  VMs

IaaS  tenant

L1  VMs

IaaS  tenant

IaaS  admin

PMsOpenStack  

PMs

CloudStack  

Page 8: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Iris:  Inter-­‐cloud  resource  integra3on  system�

•  Iris  provides  light-­‐weight  resource  management    with  simple  REST  API  

•  Nested  VirtualizaQon  –  Compute  

•  Nested  VMX  (KVM)  •  KVM  on  LPAR  (Virtage)  

–  Network  •  Full-­‐meshed  overlay  network  for  each  HaaS  tenant  •  OpenFlow  and  GRE  tunnel  

8

Page 9: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Nested  Virtualiza3on  (Nested  VMX)�•  Trap  &  emulate  VMX  instrucQons  

–  To  handle  a  single  L2  exit,  L1  hypervisor  does  many  things:  read  and  write  the  VMCS,  disable  interrupts,  page  table  operaQon,  ...  

–  These  operaQons  can  be  trapped,  leading  to  exit  mulQplicaQon.  –  Eventually,  a  single  L2  exit  causes  many  L1  exits!  

•  ReducQon  of  exit  mulQplicaQon  –  S/W:  EPT  shadowing  –  H/W:  VMCS  shadowing

9

L2

L1

L0

Single  level Two  level

.....VM  Exit

VM  Entry

L2  VM  Exit

Page 10: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Iris  and  GridARS�

10

NW  Manager  

IaaS  Data  Center

Cloud  OS DC  Resource  Manager

Resource  Coordinator

IaaS  admin  (Requester)

NW  Manager

HaaS  Data  Center

IaaS

User  VMs

User  VMs

Iris

1.  Request  HaaS  tenant

2.  Request    resources  

3.  Request  DC  resources  and  a  connecQon  

4.  Configure  HaaS  tenant  over    the  resources

GWGW

GridARS  

Page 11: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Iris  REST  API�•  Build  a  HaaS  tenant  POST  /iris/haas/deploy  =>  <HaaS  ID>  

•  Get  the  status  GET  /iris/haas/<HaaS  ID>  =>  NEW|PREPARED|DESTROYED|ERROR|UNKNOWN  

•  Destroy  the  HaaS  tenant  DELETE  /iris/haas/<HaaS  ID>

11

{    "computer":  [                {"hostName"  :  "host1",                  "cpuNumber"  :  1,                  "cpuSpeed"  :  1000,                  "memory"  :  1048576,                  "disk"  :  5,                  "ipAddress"  :  "192.168.1.11",                  "netmask"  :  "255.255.0.0",                  "gateway"  :  "192.168.1.1",                  "pubkey"  :  "....."},                {"hostName"  :  "host2",                  "cpuNumber"  :  1,                  "cpuSpeed"  :  1000,                  "memory"  :  1048576,                  "disk"  :  5,                  "ipAddress"  :  "192.168.1.12",                  "netmask"  :  "255.255.0.0",                  "gateway"  :  "192.168.1.1",                  "pubkey"  :  "....."}],        "network":  [                {"iaasIPAddress"  :  "123.45.67.89",                  "haasTunnelMode"  :  "star",                  "haasTunnelProtocol"  :  "GRE",                  "interDCTunnelProtocol"  :  "GRE"}]}  

Page 12: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Outline �•  IntroducQon  •  Iris:  Inter-­‐cloud  Resource  IntegraQon  System  •  Experiment  •  Conclusion

12

Page 13: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Experiment�•  Experiments  

–  User  VM  deployment  [AGC]  –  User  VM  migraQon  [AGC]  –  User  VM  performance  [AGC,  HCC]  

•  Experimental  seungs  –  AGC  (AIST  Green  Cloud)  

•  Emulated  inter-­‐cloud  environment  •  Nested  KVM  

–  HCC  (Hitachi  Harmonious  CompuQng  Center)  •  Real  WAN  environment  •  KVM  on  LPAR  (Virtage)  

13

Page 14: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

An  emulated  inter-­‐cloud  on  AGC �

14

 

 

M8024  (L2  switch)  

VLAN  100-­‐200

VLAN  1 VLAN  3

C4948  (L3  switch)  

GtrcNET-­‐1  (WAN  emulaQon)

IaaS  data  center HaaS  data  center

 

GW

GW

Bandwidth:  1  Gbps  Latency:  0  –  100  msec

•  Compute  node:  quad-­‐core  Intel  Xeon  [email protected]  x  2  •  IaaS:  Apache  CloudStack  4.0.2

8  nodes 5  nodes

CloudStack Iris

Page 15: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

User  VM  Deployment�

15

Latency� IaaS� HaaS�0  ms 11.88   11.895  ms -­‐ 15.1910  ms -­‐   18.84100  ms -­‐ 86.50

Result:  Elapsed  Qme  of  user  VM  deployment  [seconds]  

 

 

IaaS  data  center HaaS  data  center

Bandwidth:  1  Gbps  Latency:  0  –  100  msec

 

CloudStack UVM

Experimental  seung:  

VM  images

Page 16: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

User  VM  Migra3on�

16

 

 

IaaS  data  center HaaS  data  center

Bandwidth:  1  Gbps  Latency:  0  –  100  msec

 

CloudStack UVM

Experimental  seung:  

VM  images

UVM

1)  IaaS  -­‐>  IaaS 4)  HaaS  -­‐>  HaaS

3)  HaaS  -­‐>  IaaS2)  IaaS  -­‐>  HaaS

Page 17: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

User  VM  Migra3on�

17

0  

10  

20  

30  

40  

50  

60  

70  

80  

90  

100  

0   20   40   60   80   100  

VM  m

igra3o

n  Time  [secon

ds]

Network  latency  (one-­‐way)  [milliseconds]

IaaS  -­‐>  IaaS  IaaS  -­‐>  HaaS  HaaS  -­‐>  IaaS  HaaS  -­‐>  HaaS  

VM  migraQon  over  WAN

CloudStack  management  communicaQon  over  WANBaseline:  2.6  sec.

Page 18: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

BYTE  UNIX  benchmark  on  AGC �IaaS  UVM� HaaS  UVM�

Dhrystone 77.16   57.07

Whetstone 86.29 70.08

File  copy  256 48.93 37.75

File  copy  1024 45.96 35.51

File  copy  4096 56.87 43.01

Pipe  throughput 49.02 38.49

Context  switching 205.67 9.43

Execl  throughput 157.00   4.71

Process  creaQon 256.80 4.82

Shell  scripts 95.96 4.18

System  call 29.57 22.73

18

The  overhead  of  nested  virtualization  is  high,  especially  process  creation  and  context  switching.

(Relative  performance  normalized  to  the  BM.  Higher  is  better.)

L2  VM

L1  VM

BMKVM

KVMIaaS  UVM

HaaS  UVM

Page 19: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

BYTE  UNIX  benchmark  on  HCC �HaaS  UVM  (Virtage)� HaaS  UVM  (KVM)�

Dhrystone 47.27 48.82

Whetstone 77.24 74.86

File  copy  256 125.71 125.00

File  copy  1024 119.84 119.10

File  copy  4096 113.65 98.05  

Pipe  throughput 128.23 119.91

Context  switching 1146.68 65.21

Execl  throughput 62.44 4.31

Process  creaQon 177.39 3.19

Shell  scripts 71.99 4.71

System  call 165.04 159.55

19

(Relative  performance  normalized  to  the  BM.  Higher  is  better.)

L2  VM  on  Virtage  ≒  L1  VM  on  KVM

⇒Effect  of  EPT  shadowing

L2  VM

L1  VM

BM

HaaS  UVM  (Virtage)

HaaS  UVM  (KVM)

Virtage

KVM

KVM

KVM

Page 20: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Outline �•  IntroducQon  •  Iris:  Inter-­‐cloud  Resource  IntegraQon  System  •  Experiment  •  Conclusion

20

Page 21: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Conclusion  and  Future  Work�•  We  propose  a  new  inter-­‐cloud  service  model,  Hardware  as  a  Service  (HaaS).

•  We  have  developed  Iris  and  demonstrated  the  feasibility  of  our  HaaS  model.    CloudStack  can  seamlessly  deploy  and  migrate  VMs  on  an  inter-­‐cloud  environment.  –  The  impact  on  the  usability  is  acceptable  when  the  latency  is  less  than  10  ms.  

•  Future  Work  –  more  use  cases:  IaaS  migraQon  –  more  evaluaQon  

21

Page 22: Iris: Inter-cloud Resource Integration System for Elastic Cloud Data Center

Thanks  for  your  a\en3on!�

22

Acknowledgement:  This  work  was  partly  funded  by  the  FEderated  Test-­‐beds  for  Large-­‐scale  Infrastructure  eXperiments  (FELIX)  project  of  the  NaQonal  InsQtute  of  InformaQon  and  CommunicaQons  Technology  (NICT),  Japan.  We  would  like  to  thank  the  Hitachi  Harmonious  Compu3ng  Center  for  conducQng  a  performance  evaluaQon  of  nested  virtualizaQon  technologies  on  their  equipment.