For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
Web Cache Design and Implementation for Efficient SNMP Monitoring towards Internet-Scale Network Management
Ahmad Kamil ABDUL HAMID Yoshihiro KAWAHARA Tohru ASAMI
IEICE TRANSACTIONS on Communications
Publication Date: 2011/10/01
Online ISSN: 1745-1345
Print ISSN: 0916-8516
Type of Manuscript: PAPER
Category: Network Management/Operation
network management, RESTful active proxy, Web cache,
Full Text: PDF(1MB)
>>Buy this Article
In this paper, we propose an SNMP-aware web cache design that has two main objectives: (1) to avoid overload of network devices by SNMP requests, and (2) guaranteeing the monitoring time granularity of SNMP Object Identifiers (OID) for a large scale network such as the Internet. To meet these objectives, a cache is built into an RESTful active proxy, called Tambourine, which is the gateway for accessing management information through the Internet. Tambourine changes the landscape of traditional SNMP monitoring by allowing the Internet users to monitor closed-domain network devices through translating requests in HTTP into SNMP. However, the typical web cache algorithm can not be used in Tambourine due to two main reasons: (1) SNMP is not a cache-aware protocol and therefore can not provide Tambourine with the caching rules that need to be applied, and (2) the cache in Tambourine needs to accommodate two SNMP monitoring patterns: periodic and on-demand polling. In order for efficient periodic polling, SNMP traffic is reduced by a multi-TTL cache and user (or Manager)-side aggregation. For efficient on-demand polling, four-state transition is used to categorize OIDs into dynamic and static objects, each of which is allocated an optimum TTL. To provide users with a proper time stamp, the cache time stamp is included in the response to the users' request. Our experiments show that our cache design gives the staleness of 0 and a bounded number of SNMP requests even when the number of users' requests goes to infinity.