tailieunhanh - DIADS: Addressing the “My-Problem-or-Yours” Syndrome with Integrated SAN and Database Diagnosis

In the early days of theWeb, static HTML pages predom- inated; a handful of news-oriented Web sites of broad appeal updated their content once or twice a day. Users were by and large able to get all the news they needed by surfing to each site individually and pressing Reload. However, the Web today has experienced an explosion of micronews: highly focused chunks of content, appear- ing frequently and irregularly, scattered across scores of sites. The difference between a news site of 1994 and a weblog of 2004 is its flow: the sheer volume of timely information available from a modern Web site means that an interested user must return not. | DIADS Addressing the My-Problem-or-Yours Syndrome with Integrated SAN and Database Diagnosis Shivnath Babu Duke University shivnath@ Nedyalko Borisov Duke University nedyalko@ Sandeep Uttamchandani IBM Almaden Research Center sandeepu@ Ramani Routray IBM Almaden Research Center routrayr@ Abstract We present Diads an integrated DIAgnosis tool for Databases and Storage area networks SANs . Existing diagnosis tools in this domain have a database-only . 11 or SAN-only . 28 focus. DIADS is a first-of-a-kind framework based on a careful integration of information from the database and SAN subsystems and is not a simple concatenation of database-only and SAN-only modules. This approach not only increases the accuracy of diagnosis but also leads to significant improvements in efficiency. Diads uses a novel combination of non-intrusive machine learning techniques . Kernel Density Estimation and domain knowledge encoded in a new symptoms database design. The machine learning component provides core techniques for problem diagnosis from monitoring data and domain knowledge acts as checks-and-balances to guide the diagnosis in the right direction. This unique system design enables Diads to function effectively even in the presence of multiple concurrent problems as well as noisy data prevalent in production environments. We demonstrate the efficacy of our approach through a detailed experimental evaluation of Di-ADS implemented on a real data center testbed with Post-greSQL databases and an enterprise SAN. 1 Introduction The online transaction processing database myOLTP has a 30 slow down in processing time compared to performance two weeks back. This is a typical problem ticket a database administrator would create for the SAN administrator to analyze and fix. Unless there is an obvious failure or degradation in the storage hardware or the connectivity fabric the response to this problem ticket would be The I O rate for .