Browse files

intro stuff

  • Loading branch information...
1 parent db94efa commit 4a172da3096d4917267b05c42458da972faf524e @viktoralmqvist viktoralmqvist committed May 8, 2012
Showing with 47 additions and 12 deletions.
  1. +47 −12 thesis/Chapters/Introduction.tex
@@ -14,9 +14,9 @@ \chapter{Introduction}
To run computations effectively on modern supercomputers and computer
-clusters the applications need strong scaling. A limitation like this
-is a problem for the applications as the available resources are not
-used to reach highest possible performance.
+clusters the applications need strong scaling. When this is a
+limitation for applications the available resources are not used to
+reach highest possible performance.
%Copernicus paper
@@ -57,15 +57,25 @@ \section{Background}
and use the system. This means the system can contain different kind
of computation power and the user is not affected. Running molecular
dynamics simulations on a Cloud would need high parallelization, such
-as described above, to benefit of the possible perfomance boost.
+as described above, to achieve a perfomance boost.
+%Cloud Computing and Grid Computing 360-Degree Compared:
%In a Cload, different levels of services can be offered to an end
%user, the user is only exposed to a pre-defined API, and the lower
%level resources are opaque to the user...
+There are a few challenges when using Clouds. Defining an API for
+users to discover, request and use resources provided by the Cloud can
+be difficult. An API needs to have a good way of using the
+computational power to execute the users projects. The users should
+also be able to use all different features available in the Cloud and
+the API needs to be simple enough so that any user can understand it
+without having knowledge of the Cloud system behind the API.
-%Cloud Computing and Grid Computing 360-Degree Compared:
+The Cloud needs to coordinate executions on the available resources
+when the computations are often highly parallel. Executions may even
+need to support different software and hardware.
%In this paper, we show that Clouds and Grids share a lot commonality
%in their vision, architecture and technology, but they also differ in
@@ -78,15 +88,35 @@ \section{Background}
%resources provided by the central facilities; and to implement the
%often highly parallel computations that execute on those resources.
+Monitoring progress and resources is a challenge since the users are
+not in direct contact with the hardware which actually runs the
+application. ``Essentially monitoring in Clouds requires a fine
+balance of business application monitoring, enterprise server
+management, virtual machine monitoring, and hardware maintenance, and
+will be a significant challenge for Cloud Computing as it sees wider
+adoption and deployments.''\citep{foster:2008}
%Another challenge that virtualization brings to Clouds is the
%potention difficulty in fine-control over the monitoring of
-%Provenance refers to the derivation history of a data product,
+Provenance in this context is basically a trace of the computations
+with all the necessary information (data sources, intermediate
+states). This is very important for researchers, in order to track the
+project and be able to recreate the results. Without this the an
+experiment would not be as useful to the researchers as it could be,
+for example to validate their findings. Users can save alot of
+computation hours when having access to provenance information. In
+some cases it is of great use to be able to change something and start
+from an intermediate state of a computation instead of starting from
+scratch. Provenance is a relatively unexplored area within Cloud
+Computing and can be challanging to provide for general applications.
+%``Provenance refers to the derivation history of a data product,
%including all the data sources, intermediate data products, and the
-%procedures that were applied to produce the data product.
+%procedures that were applied to produce the data product.''
%On the other hand, Clouds are becoming the future playground for
%e-science research, and provenance management is extremely important
@@ -100,23 +130,28 @@ \section{Background}
%different software and hardware abstraction layers within one
+One way of programming/using a Cloud can be to use workflow
+systems. The workflow can be represented as a graph of individual
+executions of applications where the edges are dependencies and how
+data are passed between the applications. Users can submit these
+workflow schemes to the Cloud using the API interface.
-%More specifically, a workflow system alloews the composition of
+%More specifically, a workflow system allows the composition of
%individual (single step) components into a complex dependency graph,
%and it governs the flow of a data and/or control through these
%The data Grid...
%In an increasing number of scientific disciplines, large data
%collections are emergin as important community resources.
-There is a solution for parallelizing molecular simulations and it is
-called Copernicus
+There is a Cloud solution for running parallelized molecular
+simulations and it is called Copernicus.

0 comments on commit 4a172da

Please sign in to comment.