Network management (2nd ed.): a practical perspective
Network management (2nd ed.): a practical perspective
Multidimensional access methods
ACM Computing Surveys (CSUR)
Multidimensional binary search trees used for associative searching
Communications of the ACM
Supporting Service Level Agreements on IP Networks
Supporting Service Level Agreements on IP Networks
SNMP,SNMPV2,Snmpv3,and RMON 1 and 2
SNMP,SNMPV2,Snmpv3,and RMON 1 and 2
The K-D-B-tree: a search structure for large multidimensional dynamic indexes
SIGMOD '81 Proceedings of the 1981 ACM SIGMOD international conference on Management of data
Service-Level Agreements and Commercial Grids
IEEE Internet Computing
Utility computing SLA management based upon business objectives
IBM Systems Journal
Nondeterministic Queries in a Relational Grid Information Service
Proceedings of the 2003 ACM/IEEE conference on Supercomputing
Multidimensional Binary Search Trees in Database Applications
IEEE Transactions on Software Engineering
Computer
The structure and management of service level agreements in networks
IEEE Journal on Selected Areas in Communications
An efficient strategy for storing and searching binary trees in WORM external memory
Journal of Information Science
Hi-index | 0.00 |
The introduction of new computing paradigms in the Internet as well as the increasing size and complexity of services and resources demand the development of new approaches for defining and monitoring service levels. It is often necessary to keep track of multiple concurrent service level requirements. In this paper we present a service level monitoring strategy that allows both online and offline tracking the performance of multiple concurrent resources. Data is collected with SNMP (Simple Network Management Protocol). The strategy is based on building multidimensional search trees. k -d (k -dimensional) trees are employed for online continuous monitoring, and k -d-B trees are employed for offline monitoring, based on logs of monitored data. Searching with the proposed strategy has cost O (logN ) where N is the number of samplings or log size. The strategy allows clients and providers to confirm whether contract specifications were hold or not, and for how long. Experimental results are presented, including a comparison of the proposed approach with a traditional database. A practical tool was implemented and results are shown for a set of monitored Web and Video servers, as well as for monitoring data obtained from a real Telecom billing system.