Version 60 (modified by piontek, 7 years ago) (diff)



!QCG-Broker 2.6 [3 April 2012]
The version 2.6 of the QCG-Broker service has been released and deployed in PL-GRID infrastructure. Main changes include additional form of description of jobs (a simple script with “#QCG” directives) and a set of “qcg-” commands to interact with the infrastructure. The motivation for both extensions was to simplify the process of defining as well as controlling of experiments and to make the process similar to the approach well known and used in queuing systems.

QosCosGrid 2.4 [20 December 2011]
Just before New Year, a new version of QosCosGrid has been published. We hope the extensions and improvements included in this release will importantly contribute to further development of new and existing Grid infrastructures.

The first MAPPER review [24 November 2011]
During the first review of the MAPPER project, the QosCosGrid stack has been successfully presented in the two demanding multiscale scenarios. Within the loosly-coupled scenario, QCG has been utilized to create advance reservations for the efficient workflow execution, while within the tightly-coupled one to create advance reservations and run co-allocated jobs simultaneously on several clusters.

QCG deployments across Europe [18 September 2011]
QosCosGrid stack has been already deployed on 4 production sites being part of the PL-Grid e-Infrastructure in Poland, namely Cyfronet, PSNC, WCNS and TASK. Additional two deployments has been perfomed in Munich on LRZ cluster and London on UCL cluster. Works on further deployments in other places and communities, such as EGI and PRACE, are in an advanced stage.

QosCosGrid at International Supercomputing Conference 2011, Hamburg, Germany [21 June 2011]
During the ISC'11 conference the EU funded MAPPER project has organized a joint meeting with both PRACE and EGI project representatives working together under the MAPPER Task Force. The main aim of the Task Force, established after a series of meetings over the last three months, is to enable a closer collaboration among resource providers and multi-scale application communities at the European level. Another goal is to support the execution and management of multi-scale distributed applications on example production sites. Two distributed multi-scale application scenarios have been selected as pilot jobs for the first MAPPER review, 24th November 2011. The QosCosGrid middleware together with application tools will be deployed on selected production EGI sites in Poland, Germany and UK as well as PRACE sites, SARA and CINECA.

QosCosGrid in Mapper [April 2011]
It was decided to use the QosCosGrid middleware to multi-scale computations in the Mapper project. Installations of the QosCosGrid middleware at production sites in Europe, including EGI and PRACE machines, are currently being discussed.

QCG release 2.0 [16 April 2011]
We are happy to introduce a next relase of QosCosGrid. This is the first release after finishing the QosCosGrid project and takes a number 2.0.

See all news


The QosCosGrid (QCG) middleware is an integrated system offering advanced job and resource management capabilities to deliver to end-users supercomputer-like performance and structure. By connecting many distributed computing resources together, QCG offers highly efficient mapping, execution and monitoring capabilities for variety of applications, such as parameter sweep, workflows, MPI or hybrid MPI-OpenMP. Thanks to QosCosGrid, large-scale applications, multi-scale or complex computing models written in Fortran, C, C++ or Java can be automatically distributed over a network of computing resources with guaranteed QoS. The middleware provides also a set of unique features, such as advance reservation and co-allocation of distributed computing resources.

QCG Middleware

QosCosGrid provides:

  • the most efficient remote access to computational resources in a single cluster or many clusters in Poland and Europe,
  • automatic steering of various types of complex computing experiments ranging from multi-parameter sweep studies to cross-cluster executions of parallel applications,
  • fully transparent integration with parallel programming and execution environments like OpenMPI and ProActive located on many computing clusters,
  • support for Quality of Service (e.g. start time) based on advance reservation mechanisms,
  • shorter waiting times and improved resource utilization by hierarchical grid- and local-level job scheduling,
  • management of input and output files in distributed computing clusters,
  • efficient integration between services and queuing systems ensuring high performance and reliability of the overall system,
  • extensible, open and standard based architecture supporting OGF DRMAA, JSDL, BES and HPC Profile with pluggable modules,
  • secure communication channels using transport level (SSL/TLS, X.509) and message level (SAML2.0) mechanisms,
  • delivered together with command-line, graphical, web-based or even mobile phone tools for end users and administrators,
  • fast and reliable installation procedures.

QosCosGrid consists of the following components:

Component Main function Home Page
QCG-Computing Basic Execution Service (BES) supporting advance reservation   QCG-Computing Home Page
QCG-Notification Notification capabilities based on WS-Notification   QCG-Notification Home Page
QCG-Broker Resource management and brokering service   QCG-Broker Home Page
QCG-OpenMPI Extended version of OpenMPI library supporting cross-cluster job execution   QCG-OpenMPI Home Page
QCG-Core Common library for QosCosGrid components   QCG-Core Home Page
QCG-Tools Various elements extending the QosCosGrid   QCG-Tools Home Page

Interoperability & standards supported

The QosCosGrid implementation is based on the open, widely accepted standards. In general, QosCosGrid supports OGF DRMAA, JSDL, BES, HPC Basic Profile and OASIS WS-Notification.

Further reading


The QosCosGrid Infrastructude middleware is developed by the team of Applications Department of  Poznan Supercomputing and Networking Center

General questions please send to:
Technical questions please send to: