slides - Microsoft Research

advertisement
The Role of Cloudlets in Mobile Computing
Mahadev Satyanarayanan
School of Computer Science
Carnegie Mellon University
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
1
Machine Translation Today
0.85
0.8
Human Scoring Range
0.7289
0.7447
BLEU SCORES
0.7
0.6
0.5551
0.5610
Systran
Spanish
SDL
Spanish
0.5137
0.5
0.4
0.3859
0.3
Google
Google
Chinese
Arabic
(‘06 NIST) (‘05 NIST)
CBMT
Google
Spanish
Spanish
’08 top lang
Based on same Spanish test set
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
2
Face Recognition Today
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
3
What’s The Catch?
These are resource-intensive applications
• State-of-art performance and quality only with room full of servers
• How do we achieve this “in the wild”?
(on resource-poor, energy-limited mobile hardware)
Obvious solution: leverage the cloud!
But your cloud may be far away 
End-to-end latency matters for crisp interaction
• e.g., real-time two-way language translation on mobile devices
• e.g, augmented reality for cognitive assistance via “smart glasses”
•  and many other examples
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
4
Latency Hurts Even If Bandwidth Good
(E.g. QuakeViz interactive benchmark on VNC thin client 100 Mbps)
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
5
Sample Internet2 RTTs (milliseconds)
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
6
Latency on 3G Networks
“The wireless delay in the 3G network dominates the whole
network path delay, e.g., latency to the first pingable hop is around
200ms, which is close to the end-to-end Ping latency to landmark
servers distributed across the U.S.”
from “Anatomizing Application Performance Differences on
Smartphones”, to appear in MobiSys 2010 (Huang et al)
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
7
Solution: Create a Tiny Cloud Nearby
Olympus
Mobile Eye Trek
Wearable
Computer
Android
Phone
WAN to
distant cloud
on Internet
Low-latency
high-bandwidth
1-hop wireless
network
Nokia N810
Tablet
Handtalk
Wearable
Glove
© 2009-2010 M. Satyanarayanan
Coffee shop
Cloudlet
cloudlet = (compute cluster
+ wireless access point
+ wired Internet access
+ no battery limitations)
 “data center in a box”
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
8
Local Wireless Bandwidth
Original motivation for cloudlets was latency
But 1-hop wireless bandwidth to cloudlet also a win
• wireless LAN bw typically 100X wireless WAN bw
e.g. 802.11n ≈ 400 Mbps but HSPDA ≈ 2 Mbps
• shipping large objects within interactive time bounds
e.g. captured images in an augmented reality system
4MB JPEG image takes 80 ms @ 400 Mbps, but 16 seconds @ 2 Mbps
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
9
Cloudlet vs. Cloud
Cloudlet
Cloud
State
Only soft state
Hard and soft state
Management
Appliance model:
self-managed; little
professional attention
Utility model:
professionally administered,
24x7 operator coverage
Environment
“Data center in a box” at
customer premises
Machine room with power
conditioning and cooling
Ownership
Decentralized ownership
by local business
Centralized ownership by
Amazon,Yahoo!, etc.
Network
LAN latency and
bandwidth
Internet latency and
bandwidth
Sharing
Few users at a time
100s to 1000s of users
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
10
Key Challenges
1. Trusting infrastructure
•
tamper-resistant hardware (“first-world infrastructure”)
•
portable device as root of trust (e.g TrustSniffer)
2. Finding the exactly right software on it
uniformity  deployer value
specificity  end-user value
© 2009-2010 M. Satyanarayanan
inherent tension
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
11
Transient Customization
Deliver fully configured virtual machine (VM) to infrastructure
Problem: too large, too slow for transient use
Solution: assemble VM on the fly  dynamic VM synthesis
• prefetch large, relatively static, widely-used piece (“base VM”)
• deliver small patch (“VM overlay”) just before use
• discard VM after use
VM overlay can come from
• mobile device over wireless link, or
• web site under control of mobile device (URL and decryption key)
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
12
Dynamic VM Synthesis
Preload base VM
M
o
b
i
l
e
D
e
v
i
c
e
Discover & negotiate
use of cloudlet
(base + overlay)  launch VM
Execute launch VM
Use
cloudlet
user-driven
device-VM
interactions
C
l
o
u
d
l
e
t
Finish use
Create VM residue
Depart
© 2009-2010 M. Satyanarayanan
Discard VM
Optional: cache VM overlay
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
13
Typical Overlay Sizes
(base VM = 8GB Ubuntu Linux)
Application
Compressed
VM Overlay
Size (MB)
Uncompressed
VM Overlay
Size (MB)
Install Package
Size (MB)
AbiWord
119.5
364.2
10.0
GIMP
141.0
404.7
16.0
Gnumeric
165.3
519.8
16.0
Kpresenter
149.4
426.8
9.1
PathFind
196.6
437.0
36.8
SnapFind
63.7
222.0
8.8
Null
5.9
24.8
0.0
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
14
VM Synthesis Time at 100Mbps
(untuned proof-of-concept prototype)
Other
140
Resume VM
Largest standard deviation is 5.3% of mean
120
Apply VM overlay
Nearly half the total
All in the infrastructure
Potentially optimizable
Decompress VM overlay
Transfer floppy disk
Time in Seconds
100
Compress floppy disk
Transfer VM overlay
80
60
40
20
0
AbiWord
© 2009-2010 M. Satyanarayanan
GIMP
Gnumeric
Kpresenter
PathFind
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
SnapFind
Null
15
When Bandwidth Drops to 10Mbps
Other
350
Resume VM
Largest standard deviation is 3.4% of mean
300
Apply VM overlay
Decompress VM overlay
Time in Seconds
250
Transfer floppy disk
Compress floppy disk
200
Transfer VM overlay
150
100
50
0
AbiWord
© 2009-2010 M. Satyanarayanan
GIMP
Gnumeric
Kpresenter
PathFind
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
SnapFind
Null
16
Some Education is Needed 
“In the discussion of the proposal, several members of
the panel were skeptical about the argument about the
need extremely low latencies for handheld devices.
In particular, handhelds are (historically) remarkably
powerful computers capable of running user interfaces
(the source of most latency sensitivity) locally.
The panel also felt that the case for "cloudlets" was not
compelling in contrast to other distributed system
architectures such as relying alarge-scale cloud based
on conventional data centers and using a
geographically distributed three-layer web service
architecture.”
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
17
In Closing 
Leverage the Cloud!
(but keep the Swiss Army Knife handy for emergencies)
© 2009-2010 M. Satyanarayanan
Microsoft Networking Research Summit, Bellevue, WA, 2010-06-02
18
Download