Caju: A Content Distribution System for Edge Networks

Abstract

More and more, users store their data in the cloud. While the content is then retrieved, the retrieval has to respect quality of service (QoS) constraints. In order to reduce transfer latency, data is replicated. The idea is make data close to users and to take advantage of providers home storage. However to minimize the cost of their platform, cloud providers need to limit the amount of storage usage. This is still more crucial for big contents.This problem is hard, the distribution of the popularity among the stored pieces of data is highly non-uniform: several pieces of data will never be accessed while others may be retrieved thousands of times. Thus, the trade-off between storage usage and QoS of data retrieval has to take into account the data popularity.This report presents our architecture gathering several storage domains composed of small-sized datacenters and edge devices; and it shows the importance of adapting the replication degree to data popularity.Our simulations, using realistic workloads, show that a simple cache mechanism provides a eight-fold decrease in the number of SLA violations, requires up to 10 times less of storage capacity for replicas, and reduces aggregate bandwidth and number of flows by half.

AREN: A Popularity Aware Replication Scheme for Cloud Storage

“…We have omitted further detailed evaluations of uniform replication and caching on edge networks due to space constraints. But they are available on our technical report [16]. These results show that (i) simple caching is much more efficient in replicating popular content on edge networks than uniform approach in terms of number of SLA violations, (ii) caching allows us to reduce network resources consumption, and (iii) it permits edge node to contribute with tiny amounts of storage capacity contribution (2GB) in order to maintain enough replicas for popular content.…”

“…Coordinators interact to each other to share information about availability and location of content and resources. A detailed description of Caju design is available in [16]. • Divide-and-conquer.…”

Performing accurate simulations for deadline-aware applications

“…Last but not least, this modules keeps and exports an address table, including BD to global pseudonetwork address mapping, to easy usage and provide transparency of multihoming network functionality. Evaluations with deadline enforcement and multihoming functionalities have been omitted from this work due to space constraints, but are available on our previous works [8] and [9]. …”

“…More details about its functioning are available on the component repository [3]. Further evaluations and usage details of its functionalities in terms of deadline-aware services and transfer rate enforcement are available on previous works [8] and [9], where we study SLA-based resource allocation in edge networks. The remaining sections are organised as follows.…”