Enabling what-if explorations in distributed systems

With a large percentage of total system cost going to system
administration tasks, self-management remains a difficult and important
goal in systems. As a step towards the self-management vision, I will
present a framework we have developed that enables systems to be
self-predicting and answer ``what-if'' questions about their behavior
with little or no administrator involvement. We have built a Resource
Advisor inside two real systems: Microsoft's SQL Server database and the
Ursa Minor storage system at Carnegie Mellon University. The Resource
Advisor helps with upgrade and data placement decisions and provides
what-if interfaces to external administrators (and internal tuning
modules). The Resource Advisor is based on efficient system behavioral
models that enable robust predictions in multi-tier systems.

Bio:

Eno Thereska is a PhD student at Carnegie Mellon University working
with Prof. Greg Ganger. Eno has broad research interests in computer
systems.  Currently he is investigating ways to make the management of
distributed systems easier. An approach he is currently pursuing puts
sufficient instrumentation and modeling within the system, enabling it
to answer several important what-if questions without outside
intervention. He is interested in applying methods from queuing analysis
(for components build from scratch) and machine learning (for legacy
components) to this problem. As a testbed he is using Ursa Minor, a
cluster-based storage system being deployed at Carnegie Mellon for
researching system management issues. Concrete what-if questions in this
system are about the effect of resource upgrades, service migration and
data distribution. Eno received the Masters of Science (MS) degree in
Electrical and Computer Engineering in 2003 at Carnegie Mellon
University and the Bachelor of Science (BS) degree in Electrical and
Computer Engineering and Computer Science in 2002 also at CMU.
------------------------------