Skip to main content

Systems Management

 

Several trends in enterprise IT infrastructure, such as IT outsourcing, multi-tenancy and virtualization, SLA driven service delivery, emerging situational and Web2.0 applications etc. have dramatically increased the complexity of IT delivery platforms. The focus of systems management research at IRL is to develop tools and techniques that help to address these trends in the systems management space.

SSystems management is a major inter-disciplinary research area involving: distributed and high performance computing, machine learning, signal processing, programming technologies & software engineering, etc. Some of the key projects in the IRL research group are highlighted below. The underlying theme of the projects is to develop tools and technologies for management of large desktop installations, tightly-coupled enterprise data centers, and loosely coupled grid systems.

The following are our ongoing and recent projects in this area:

  1. eBusiness dependency analysis
  2. Model driven monitoring
  3. Desktop management system (DMS)
  4. Lifecycle management for large scale file systems
  5. Disaster recovery planner
  6. QosMig
  7. Placement algorithms for parallel disks
  8. ADR-RMRS
  9. Grid resource management and scheduling
Publications
  • "Dynamic dependency discovery for problem determination"
    Manish Gupta, Anindya Neogi, Manoj K. Agarwal, Gautam Kar, International Conference on Distributed Systems Operations and Management (DSOM) 2003 Heidelberg Germany (Best Paper Award)
  • "Problem determination using dependency graphs and run-time behavior models"
    Manoj K. Agarwal, Karen Appleby, Manish Gupta, Gautam Kar, Anindya Neogi, Anca Sailer, International Conference on Distributed Systems Operations and Management (DSOM) 2004, UC Davis.
  • "Threshold management for problem determination in transaction based e-commerce systems"
    Manoj K. Agarwal, Karen Appleby, Jamal Faik, Manish Gupta, Gautam Kar, Anindya Neogi, Anca Sailer, 9th International Symposium of Integrated Network Management (IM) 2005, Nice, France
  • "Mining activity data for dynamic dependency extraction in e-business systems"
    Manoj K. Agarwal, Manish Gupta, Gautam Kar, Anindya Neogi, Anca Sailer, eTransactions in Network and Service Management, Fall 2004 issue
  • "Mining activity data for non-intrusive dependency analysis"
    Manoj K. Agarwal, Jie Gao, Manish Gupta, Gautam Kar, Parviz Kermani, Anindya Neogi (IBM Research Report), 2003
  • "QoSMig: adaptive rate- controlled migration of bulk data in storage systems"
    K. Dasgupta, S. Ghosal, R. Jain, U. Sharma, and A. VermaIn Proc. International Conference on Data Engineering (ICDE), 2005
  • "An architecture for lifecycle management in very large file systems"
    A. Verma, U. Sharma, J. Rubas, D. Pease, M. Kaplan, R. Jain, M. Devarakonda, M. Beigi In 22nd IEEE – 13th NASA Goddard Conf on Mass Storage Systems and Technology, MSST2005, April 2005
  • "Policy-based information lifecycle management in large scale file systems"
    M. Beigi, M. Devarakonda, R. Jain, M. Kaplan, D. Pease, J. Rubas, U. Sharma, A. Verma, Policy 2005 - IEEE 6th International Workshop on Policies for Distributed Systems and Networks, Sweden, June 2005
  • "On store placement for response time minimization in parallel disks"
    A. Verma, and A. Anand, In IEEE Int'l Conference on Distributed and High Performance Computing Systems (ICDCS), 2006
  • "Qos-graf: A framework for qos based grid resource allocation with failure provisioning."
    G. Dasgupta, K. Dasgupta, A. Purohit, B. Viswanathan, Proc. of 14th IEEE Int’l Workshop on Quality of Service , 2006

 
Help
Contact
Page help