|
Poorly performing enterprise applications are the weakest links in a
corporation ’ s management chains, causing delays and disruptions of
critical business functions. In trying to strengthen the links, companies
spend dearly on applications tuning and sizing; unfortunately, the only
deliverables of many of such ventures are lost investment as well as
the ruined credibility of computer professionals who carry out failed
projects.
In my opinion, the root of the problem is twofold. Firstly, the performance
engineering discipline does not treat enterprise applications
as a unifi ed compound object that has to be tuned in its entirety; instead
it targets separate components of enterprise applications (databases,
software, networks, Web servers, application servers, hardware appliances,
Java Virtual Machine, etc.).
Secondly, the body of knowledge for performance engineering
consists of disparate and isolated tips and recipes on bottleneck troubleshooting
and system sizing and is guided by intuitional and “ trial and
error ” approaches. Not surprisingly, the professional community has
categorized it as an art form — you can fi nd a number of books that
prominently place application performance trade in the category of “ art
form, ” based on their titles.
Poorly performing enterprise applications are the weakest links in a corporation's management chain, causing delays and disruptions of critical business functions. This groundbreaking book frames enterprise application performance engineering not as an art but as applied science built on model-based methodological foundation. The book introduces queuing models of enterprise application that visualize, demystify, explain, and solve system performance issues. Analysis of these models will help to discover and clarify unapparent connections and correlations among workloads, hardware architecture, and software parameters. |
|