2011
DOI: 10.14778/3402707.3402740
|View full text |Cite
|
Sign up to set email alerts
|

Where in the world is my data?

Abstract: Users of websites such as Facebook, Ebay and Yahoo! demand fast response times, and these sites replicate data across globally distributed datacenters to achieve this. However, it is not necessary to replicate all data to all locations: if a European user's record is never accessed in Asia, it does not make sense to pay the bandwidth and disk costs to maintain an Asian replica. In this paper, we describe mechanisms for selectively replicating large-scale web databases on a record-by-record basis. We … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
8
0

Year Published

2012
2012
2019
2019

Publication Types

Select...
4
4

Relationship

0
8

Authors

Journals

citations
Cited by 20 publications
(8 citation statements)
references
References 13 publications
0
8
0
Order By: Relevance
“…But version is not an easy parameter to specify, especially in a large-scale sharing scenario where multiple applications access the same data set. Another related work that studies the replication and latency problem controls latency by way of replica locality [26]. Although some NoSQL store like Cassandra [19] provides multiple consistency choices, it actually guarantees strong consistency on the ALL mode and eventual consistency on the other modes through the readrepair mechanism.…”
Section: F Discussionmentioning
confidence: 99%
See 1 more Smart Citation
“…But version is not an easy parameter to specify, especially in a large-scale sharing scenario where multiple applications access the same data set. Another related work that studies the replication and latency problem controls latency by way of replica locality [26]. Although some NoSQL store like Cassandra [19] provides multiple consistency choices, it actually guarantees strong consistency on the ALL mode and eventual consistency on the other modes through the readrepair mechanism.…”
Section: F Discussionmentioning
confidence: 99%
“…There has been abundant research [26], [27] on asynchronous replication exploring the trade-offs between replication frequency, application RPO (recovery point objective) demands, financial outlay by application owners, and possibly even multi-site replication. We are the first to explore the replica consistency versus latency trade-off for operation latency bounding.…”
Section: F Discussionmentioning
confidence: 99%
“…An interesting discussion arises about the solutions on how to replicate data across globally distributed data centres. For instance the idea of replicating all data to all locations requires using huge amounts of resources since users from different locations may have different data consumption needs [ 28 ]. In order to satisfy exceptional requirements of data storage in IoT, the distributed storage systems are crucial.…”
Section: Background On Iot Surveysmentioning
confidence: 99%
“…Metric 3, Number of servers processing a query (query span): Several studies already indicate that minimizing query span also minimizes query latency [2], [3], [4], [5], [6], [7]. In Fig.…”
Section: Motivating Insightsmentioning
confidence: 99%
“…In these systems, the general approach is to use hash-based partitioning and random replication of data. This approach ignores the relations among the data and often leads to redundant replications and significant communication overheads during query processing, which in turn leads to performance degradation [2], [3], [4], [5].…”
Section: Introductionmentioning
confidence: 99%