Efficient P2P inspired policy to distribute resource information in large distributed systems
The computational infrastructures are becoming larger and more complex. Their organization and interconnection are acquiring new dimensions with the increasing adoption of Cloud Technology and the establishment of Federations of cloud providers. These large interconnected systems require monitoring...
Guardado en:
| Autor principal: | |
|---|---|
| Publicado: |
2017
|
| Materias: | |
| Acceso en línea: | https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_18650929_v697_n_p3_Verghelet http://hdl.handle.net/20.500.12110/paper_18650929_v697_n_p3_Verghelet |
| Aporte de: |
| id |
paper:paper_18650929_v697_n_p3_Verghelet |
|---|---|
| record_format |
dspace |
| spelling |
paper:paper_18650929_v697_n_p3_Verghelet2023-06-08T16:29:39Z Efficient P2P inspired policy to distribute resource information in large distributed systems Mocskos, Esteban Eduardo Distributed systems Monitoring Resource distribution policy Distributed computer systems Monitoring Bandwidth consumption Computational infrastructure Distributed resources Distributed systems Fundamental component Learning-based methods Peer-to-peer paradigm Resource distribution Peer to peer networks The computational infrastructures are becoming larger and more complex. Their organization and interconnection are acquiring new dimensions with the increasing adoption of Cloud Technology and the establishment of Federations of cloud providers. These large interconnected systems require monitoring at different levels of the infrastructure: from the availability of hardware resources to the effective provision of services and verification of terms of the established agreements. Monitoring becomes a fundamental component of any Cloud Service or Federation, as the up-to-date information about resources in the system is extremely important to be used as an input to the scheduler component. The way in which the different members of such a distributed system obtain and distribute the resource information is what is known as Resource Information Distribution Policy. Moving towards the obtention of a scalable and easy to maintain policy leads to interaction with the Peer to Peer (P2P) paradigm. Some of the proposed policies are based on establishing a ranking according to previous communications between nodes. These policies are known as learning based methods or Best-Neighbor (BN). However, the use of this type of policies shows poor performance and limited scalability compared with defacto Hierarchical or other hybrid policies. In this work, we introduce pBN which is a fully distributed resource information policy based on P2P. We analyze some reasons that could produce the poor performance in standard BN and propose an improvement which shows performance and bandwidth consumption similar to Hierarchical policy and other hybrid variations. To compare the different policies, a specific simulation tool is used with different system sizes and exponential network topology. © Springer International Publishing AG 2017. Fil:Mocskos, E. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. 2017 https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_18650929_v697_n_p3_Verghelet http://hdl.handle.net/20.500.12110/paper_18650929_v697_n_p3_Verghelet |
| institution |
Universidad de Buenos Aires |
| institution_str |
I-28 |
| repository_str |
R-134 |
| collection |
Biblioteca Digital - Facultad de Ciencias Exactas y Naturales (UBA) |
| topic |
Distributed systems Monitoring Resource distribution policy Distributed computer systems Monitoring Bandwidth consumption Computational infrastructure Distributed resources Distributed systems Fundamental component Learning-based methods Peer-to-peer paradigm Resource distribution Peer to peer networks |
| spellingShingle |
Distributed systems Monitoring Resource distribution policy Distributed computer systems Monitoring Bandwidth consumption Computational infrastructure Distributed resources Distributed systems Fundamental component Learning-based methods Peer-to-peer paradigm Resource distribution Peer to peer networks Mocskos, Esteban Eduardo Efficient P2P inspired policy to distribute resource information in large distributed systems |
| topic_facet |
Distributed systems Monitoring Resource distribution policy Distributed computer systems Monitoring Bandwidth consumption Computational infrastructure Distributed resources Distributed systems Fundamental component Learning-based methods Peer-to-peer paradigm Resource distribution Peer to peer networks |
| description |
The computational infrastructures are becoming larger and more complex. Their organization and interconnection are acquiring new dimensions with the increasing adoption of Cloud Technology and the establishment of Federations of cloud providers. These large interconnected systems require monitoring at different levels of the infrastructure: from the availability of hardware resources to the effective provision of services and verification of terms of the established agreements. Monitoring becomes a fundamental component of any Cloud Service or Federation, as the up-to-date information about resources in the system is extremely important to be used as an input to the scheduler component. The way in which the different members of such a distributed system obtain and distribute the resource information is what is known as Resource Information Distribution Policy. Moving towards the obtention of a scalable and easy to maintain policy leads to interaction with the Peer to Peer (P2P) paradigm. Some of the proposed policies are based on establishing a ranking according to previous communications between nodes. These policies are known as learning based methods or Best-Neighbor (BN). However, the use of this type of policies shows poor performance and limited scalability compared with defacto Hierarchical or other hybrid policies. In this work, we introduce pBN which is a fully distributed resource information policy based on P2P. We analyze some reasons that could produce the poor performance in standard BN and propose an improvement which shows performance and bandwidth consumption similar to Hierarchical policy and other hybrid variations. To compare the different policies, a specific simulation tool is used with different system sizes and exponential network topology. © Springer International Publishing AG 2017. |
| author |
Mocskos, Esteban Eduardo |
| author_facet |
Mocskos, Esteban Eduardo |
| author_sort |
Mocskos, Esteban Eduardo |
| title |
Efficient P2P inspired policy to distribute resource information in large distributed systems |
| title_short |
Efficient P2P inspired policy to distribute resource information in large distributed systems |
| title_full |
Efficient P2P inspired policy to distribute resource information in large distributed systems |
| title_fullStr |
Efficient P2P inspired policy to distribute resource information in large distributed systems |
| title_full_unstemmed |
Efficient P2P inspired policy to distribute resource information in large distributed systems |
| title_sort |
efficient p2p inspired policy to distribute resource information in large distributed systems |
| publishDate |
2017 |
| url |
https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_18650929_v697_n_p3_Verghelet http://hdl.handle.net/20.500.12110/paper_18650929_v697_n_p3_Verghelet |
| work_keys_str_mv |
AT mocskosestebaneduardo efficientp2pinspiredpolicytodistributeresourceinformationinlargedistributedsystems |
| _version_ |
1768543297113948160 |