Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State...
-
Upload
amice-mcdowell -
Category
Documents
-
view
214 -
download
0
Transcript of Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State...
![Page 1: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/1.jpg)
Elastic Cloud Caches for Accelerating Service-Oriented Computations
Gagan AgrawalOhio State UniversityColumbus, OH
David ChiuWashington State UniversityVancouver, WA
![Page 2: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/2.jpg)
2
Cloud Computing
• Pay-As-You-Go Computing‣ Running 1 machine for 10
hours = running 10 machines for 1 hour
• Elasticity‣ Cloud applications can
stretch and contract their resource requirements
• “Infinite resources”
![Page 3: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/3.jpg)
3
Outline
‣Accelerating Data Intensive Services Using the Cloud
•Motivating Application
•Design of an Elastic Cache
‣Performance Evaluation
•Up-Scaling (cache expansion)
•Down-Scaling (cache contraction)
‣Future Work & Conclusion
![Page 4: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/4.jpg)
4
Motivating Application
Data Sources
![Page 5: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/5.jpg)
5
Computing & Storage Resources
Geoinformatics Cyber Infrastructure: Lake Erie
![Page 6: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/6.jpg)
6
Shared/Proprietary Web Services
= Web Service
Geoinformatics Cyber Infrastructure: Lake Erie
![Page 7: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/7.jpg)
7
. . .
Service Interaction with Cyber Infrastructure
Service Infrastructure
![Page 8: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/8.jpg)
8
Service Interaction with Cyber Infrastructure
. . .
invoke
results
Service Infrastructure
![Page 9: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/9.jpg)
9
Problem: Query Intensive Circumstances
. . .
. . .
. . .
Service Infrastructure
![Page 10: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/10.jpg)
10
Outline
‣Accelerating Data Intensive Services Using the Cloud
•Motivating Application
•Design of an Elastic Cache
‣Performance Evaluation
•Up-Scaling (cache expansion)
•Down-Scaling (cache contraction)
‣Future Work & Conclusion
![Page 11: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/11.jpg)
11
Designing an Elastic Cache
Compute Cloud
. . .
Service Infrastructure
A
B
![Page 12: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/12.jpg)
12
Designing an Elastic Cache. .
.
Service Infrastructure
A
BCache
Requests
Inserts
Misses
node = (k mod 2)
![Page 13: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/13.jpg)
13
Eventual Overloading. .
.
Service Infrastructure
A
BCache
Requests
Inserts
Misses
node = (k mod 2)
![Page 14: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/14.jpg)
14
Scaling up to Meet Demand. .
.
Service Infrastructure
A
B
CacheRequests
Compute Cloud
C
node = (k mod 2)
![Page 15: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/15.jpg)
15
Issues with Naive Hashing. .
.
Service Infrastructure
A
B
CacheRequests
node = (k mod 3)
C
How to incorporate node C withleast amount of “disruption?”
![Page 16: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/16.jpg)
16
. . .
A
B
75
25
8
Hash Intervals (buckets)
Distributed Hashtables (DHT)
![Page 17: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/17.jpg)
17
. . .
A
B
75
25
8
invoke:
service(35)
(35 mod 100) = 35Which proxy has the page?h(k) = (k mod 100)
h(35)
Distributed Hashtables (DHT)
![Page 18: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/18.jpg)
A
B
75
25
8
50 COnly records hashing into (25,50] need to be moved
from A to C!
DHT to Minimize Hash Disruption when Scaling
![Page 19: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/19.jpg)
19
That’s Not Completely Elastic
‣What about relaxing the amount of nodes to help save
Cloud save costs?
‣First, we need an eviction scheme
![Page 20: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/20.jpg)
20
Exponential Decay Eviction
‣At eviction time:
•A value, , is calculated for each data record in the
evicted slice
• is higher:
- if was accessed more recently
- if was accessed frequently
•If is lower than some threshold, evict
![Page 21: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/21.jpg)
21
Outline
‣Accelerating Data Intensive Services Using the Cloud
•Motivating Application
•Design of an Elastic Cache
‣Performance Evaluation
•Up-Scaling (cache expansion)
•Down-Scaling (cache contraction)
‣Future Work & Conclusion
![Page 22: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/22.jpg)
22
Experimental Configuration
• Application‣ Shoreline Extraction‣ Takes 23 seconds to
complete without benefits of cache
‣ Executed on a miss
‣Amazon EC2 Cloud
•Each Cloud node:
- Small Instances (Single core 1.2Ghz, 1.7GB, 32bits)
- Ubuntu Linux
•Caches start out cold
•Data stored in memory only
![Page 23: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/23.jpg)
23
Experimental Configuration
‣Our approach exploits an elastic Cloud environment:
‣We compare GBA against statically allocated Cloud
environments:
•2 fixed nodes (static-2)
•4 fixed nodes (static-4)
•8 fixed nodes (static-8)
•Cache overflow --> LRU eviction
![Page 24: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/24.jpg)
24
Relative Speedup
Querying Rate: 255 invocations/sec
![Page 25: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/25.jpg)
25
Cache Expansion/Migration Times
Querying Rate: 255 invocations/sec
![Page 26: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/26.jpg)
26
Experimental Configuration
‣Amazon EC2 Cloud
•Each Cloud node:
- Small Instance (Single core 1.2Ghz, 1.7GB, 32bits)
•Caches start out cold
•Data stored in memory
•When 2 nodes become < 30% capacity, merge
‣Sliding Window Configuration:
•Time Slice: 1 sec
•Size: 100 Time Slices
![Page 27: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/27.jpg)
27
Data Eviction: 50/255/50 queries per sec
Sliding Window Size = 100 sec
50 q/sec 255 q/sec 50 q/sec
![Page 28: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/28.jpg)
28
Cache Contraction: 50/255/50 queries per sec
![Page 29: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/29.jpg)
29
Cache Contraction: 50/255/50 queries per sec
![Page 30: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/30.jpg)
30
Experimental Summary
‣Caching Web service results reduces mean execution
times significantly for our application
‣Cloud node allocation is a huge overhead, but the cost
is amortized over average execution times
‣On average, our approach uses less nodes (and thus,
less cost) than statically allocated schemes
![Page 31: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/31.jpg)
31
Outline
‣Accelerating Data Intensive Services Using the Cloud
•Motivating Application
•Design of an Elastic Cache
‣Performance Evaluation
•Up-Scaling (cache expansion)
•Down-Scaling (cache contraction)
‣Future Work & Conclusion
![Page 32: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/32.jpg)
32
Conclusion
‣We introduced to some challenges in the Cloud:
•Controlling Cost
•Real-time system management (downscaling, upscaling)
‣We saw how the Cloud’s elasticity could be harnessed
to accelerate service-oriented processes
![Page 33: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/33.jpg)
33
Future/Current Work
![Page 34: Elastic Cloud Caches for Accelerating Service-Oriented Computations Gagan Agrawal Ohio State University Columbus, OH David Chiu Washington State University.](https://reader035.fdocuments.net/reader035/viewer/2022081603/5697bfeb1a28abf838cb8231/html5/thumbnails/34.jpg)
34
Thank you
‣Questions and Comments?
•David Chiu - [email protected]
•Gagan Agrawal - [email protected]
In memory of Prof. Yuri Breitbart
(1940 -- 2010)