Cost-Benefit Analysis of Cloud Computing versus Desktop Grids

(1)

Cost-Benefit Analysis of

Cloud Computing versus

Desktop Grids

Derrick Kondo, Bahman Javadi, Paul Malécot, Franck Cappello INRIA, France

David P. Anderson UC Berkeley, USA

(2)

Cloud Background

•

Vision

•

Hide complexity of hardware and

software management from a user by offering computing as a service

•

Benefits

•

Pay as you go

•

Scale up or down dynamically

•

No hardware management, less software management

(3)

Platform Performance vs. Costs

Cost Performance low low high high

(4)

Platform Performance vs. Costs

Cost Performance Cluster Grid Supercomputer low low high high

(5)

Platform Performance vs. Costs

Cost Performance Cluster Grid Supercomputer low low high high Desktop Grids (DG)

(6)

Platform Performance vs. Costs

(7)

Platform Performance vs. Costs

Cloud What is the relationship? DG + Cloud?

(8)

Outline

•

Performance tradeoffs

•

Monetary tradeoffs

•

Client hosting

(9)

Apples to Apples

Loosely-coupled, high-throughput, compute-intensive applications Tightly-coupled, data-intensive real-time applications

(10)

Apples to Apples

low complexity high complexity

(11)

Apples to Apples

DG’s

(12)

Apples to Apples

DG’s

Clouds

Comparison assuming

(13)

Method

•

Use real performance measurements

•

Exported BOINC (middleware for desktop grids) project data

•

Use real costs

•

Large/small BOINC projects (SETI@home / XtremLab)

(14)

Stages of Project & Application

Platform Construction

(15)

Stages of Project & Application

Platform

(16)

Stages of Project & Application

Platform

(17)

Stages of Project & Application

Platform

(18)

Platform Construction Application Deployment Application Execution Application Completion How long before I

(19)

get X TeraFLOPS? 0 5 10 15 20 25 30 103 104 105 106

Months for registration

Number of cloud nodes

0 5 10 15 20 25 30

101 102 103

(20)

get X TeraFLOPS? 0 5 10 15 20 25 30 103 104 105 106

0 5 10 15 20 25 30

101 102 103

TeraFLOPS

Can get over 20 TeraFLOPS within 6 months

(21)

get X TeraFLOPS? 0 5 10 15 20 25 30 103 104 105 106

0 5 10 15 20 25 30

101 102 103

TeraFLOPS

Can get over 20 TeraFLOPS within 6 months

Strategy:

Add to BOINC project list Press releases

Forum Announcements Google Ad Sense

Respond to users (leverage volunteers)

(22)

Platform Construction Application Deployment Application Execution Application Completion

How long to deploy my batch of tasks

needing

(23)

needing

faster response time?

!"# !"$ !"% !"!! !"" !"! !"& !"' ()*+,-./0.1/2)34,,-.3/5,6 7,82/9*,34.4:*,.;*:3)4,6< . . !"".4=6>6 !""".4=6>6 !"""".4=6>6

(24)

needing

!"# !"$ !"% !"!! !"" !"! !"& !"' ()*+,-./0.1/2)34,,-.3/5,6 7,82/9*,34.4:*,.;*:3)4,6< . . !"".4=6>6 !""".4=6>6 !"""".4=6>6 For 1000 tasks,

(25)

needing

!"# !"$ !"% !"!! !"" !"! !"& !"' ()*+,-./0.1/2)34,,-.3/5,6 7,82/9*,34.4:*,.;*:3)4,6< . . !"".4=6>6 !""".4=6>6 !"""".4=6>6 For 1000 tasks,

~10 minutes with 105_hosts

Strategy:

Specify lower latency bounds

(26)

(27)

Platform Construction Application Deployment Application Execution Application Completion How many volunteer nodes are equivalent to 1 cloud node?

(28)

(29)

2.8 active volunteer hosts per 1 cloud node.

(Total performance still

(30)

2.8 active volunteer hosts per 1 cloud node.

(Total performance still

orders of magnitude better)

Strategy:

Use statistical prediction of

(31)

(32)

Platform Construction Application Deployment Application Execution Application Completion How long should I wait for task completion?

(33)

Platform Construction Application Deployment Application Execution Application Completion How long should I wait for task completion?

(34)

Platform Construction Application Deployment Application Execution Application Completion How long should I wait for task

completion? _{for 3.7 hour work unit (on 3GHz host).}Median project latency bound: 9 days

Ratio of lat. bound / exec time > 5. Good success rates: 96.1%

(35)

Platform Construction Application Deployment Application Execution Application Completion How long should I wait for task completion? Strategy:

See BOINC Catalog for typical deadlines and

compute/comm/mem ratios.

Median project latency bound: 9 days for 3.7 hour work unit (on 3GHz host).

Ratio of lat. bound / exec time > 5. Good success rates: 96.1%

(36)

Monetary Tradeoffs

•

Client hosting on cloud

•

Not worth it and never will

•

Server hosting on the cloud

(37)

(38)

(39)

What about Client

(40)

Cost of Clouds versus DG

How long until DG’s more cost effective than Clouds?

(41)

Cost of Clouds versus DG

! " #! #" $! $" %! #!!#& #!!#" #!!#' #!!#% #!!#$ #!!## ()*+,-./01,/230456 7,8./9,)/:;<( / / =.),>;0? @ABCDE*>, A7$ F#'!'/G*HI8.,,)/8*3,5 2'J&/-H*I3/8*3,56 '"&$/G*HI8.,,)/8*3,5 2#&#$/-H*I3/8*3,56 How long until DG’s more cost effective than Clouds?

(42)

Cost of Clouds versus DG

! " #! #" $! $" %! #!!#& #!!#" #!!#' #!!#% #!!#$ #!!## ()*+,-./01,/230456 7,8./9,)/:;<( / / =.),>;0? @ABCDE*>, A7$ F#'!'/G*HI8.,,)/8*3,5 2'J&/-H*I3/8*3,56 '"&$/G*HI8.,,)/8*3,5 2#&#$/-H*I3/8*3,56 How long until DG’s more cost effective than Clouds? After ~13 days

(43)

What are total costs over time?

(44)

0 5 10 15 20 0 1 2 3 4 5 6 7 8x 10 4

Platform age (days)

Total cost EC2 100n EC2 1000n EC2 10000n XtremLab SETI@home What are total costs over time?

(45)

0 5 10 15 20 0 1 2 3 4 5 6 7 8x 10 4

Platform age (days)

Total cost EC2 100n EC2 1000n EC2 10000n XtremLab SETI@home What are total costs over time?

Cost of Clouds versus DG (2)

After 3 days, DG is cheaper

(46)

Cost of Clouds versus DG (3)

How many months of DG can

X months of Cloud buy me?

(47)

0 5 10 15 20 25 0 500 1000 1500 2000 2500 3000 3500

Months with EC2

Months with VC

Xtremlab / 1000n EC2 SETI@home / 1000n EC2 Xtremlab / 10000n EC2 SETI@home / 10000n EC2

Cost of Clouds versus DG (3)

(48)

0 5 10 15 20 25 0 500 1000 1500 2000 2500 3000 3500

Months with EC2

Months with VC

Xtremlab / 1000n EC2 SETI@home / 1000n EC2 Xtremlab / 10000n EC2 SETI@home / 10000n EC2

Cost of Clouds versus DG (3)

12 months of Cloud

can pay for > 125 DG years. DG way

(49)

Equivalent Clouds given BOINC Costs

Given BOINC costs, what size Cloud can I buy?

(50)

Equivalent Clouds given BOINC Costs

(51)

Equivalent Clouds given BOINC Costs

1.75 TeraFLOPS, 7 TeraBytes

.75 TeraFLOPS, 3 TeraBytes

(52)

Equivalent Clouds given BOINC Costs

2 orders of magnitude

lower than BOINC

1.75 TeraFLOPS, 7 TeraBytes

.75 TeraFLOPS, 3 TeraBytes

(53)

What about Server

Hosting on the Cloud?

(54)

(55)

Number of Hosts over Time

Load variation exits w/ publicity,

projects run out of work, etc.

Clouds take care of server

management. Potential to

exploit clouds.

(56)

Server Costs on a Cloud

How much to host

(57)

Server Costs on a Cloud

How much to host

(58)

Server Costs on a Cloud

How much to host

BOINC server on cloud?

(59)

Server Costs on a Cloud

1.7 - 16.5 times cheaper to host on Cloud,

but bandwidth is expensive.

How much to host

BOINC server on cloud?

(60)

Cloud Resources with Given Budget

How big of a server can I support with given budget?

(61)

Cloud Resources with Given Budget

(62)

Cloud Resources with Given Budget

(63)

Cloud Resources with Given Budget

Many project servers

are sustainable on the cloud

(64)

(65)

Summary

•

(66)

Summary

•

20 DG TeraFLOPS within 6 months

•

Monetary tradeoffs

•

Client hosting

•

After 13 days, DG more cost effective

•

Server hosting

•

DG server on cloud is cost-effective

•

Best for small-medium sized projects

•

Savings of at least 40%

(67)

Summary

•

20 DG TeraFLOPS within 6 months

•

Monetary tradeoffs

•

Client hosting

•

After 13 days, DG more cost effective

•

Server hosting

•

DG server on cloud is cost-effective

•

Best for small-medium sized projects

•

Savings of at least 40%

• http://mescal.imag.fr/membres/derrick.kondo/cloud_calc.xlsx

•

BOINC server image for EC2 / Xen available

(68)

Future Work

•

Clouds@home

•

Statistical and predictive methods for ensuring host availability

•

Lightweight mechanisms for virtual machine migration

(69)

•

wu flop calc

•

bw in cloud