Abstract :
[en] SaaS is providing cloud applications like all the normal classes of applications of normal
computing like the web applications, file applications, email applications, real-time
applications, highly interactive applications, massive data analysis applications, high
performance computing applications and mobile cloud applications. Cloud computing
uses the internet data centers to host the applications and data storage and also the
processing power in the addition to the virtualization. Clouds are a huge stack of easily
and usefully virtualized services and resources (Like software, platform and hardware).
These resources are used by people all over the world and dynamically configured to
accommodate more and more load and scale to a huge number of users. This stack of
resources and services is delivered to the customers by a pay-per-use model which verifies
that the services provided by the cloud providers are provided by means of service level
agreements. In this master thesis, we present an assurance to the service level agreement between the cloud users and the cloud services providers by trying to assess and evaluate the
cloud computing data centers services and applications provided to the cloud users. Also
we introduce mathematical test models for the web, file, real time and distributed applications.
We can use these test models to see the behavior of the applications over a long
time. In this master thesis, we classify the cloud applications into 8 different classes of applications
and then identify the failures and problems which affect these cloud applications.
We classify also all failures types which may occur in cloud data centers like network
failures, physical server failures, VM unavailability, individual failures racks and individual
component failures. We got the important metrics for each class of applications and
developed real scenarios for four classes. Then, we introduce different failures to these
scenarios to see what is the impact in the most important metrics of applications. Then,
we simulate these scenarios in Network Simulator 2. Finally, we solved and mitigated
the failures in simulation by using two failure mitigation techniques. The first one is the
virtual machine migration and redundancy. The second technique is the forward error
correction. Experimental results acquired over the course of this master's thesis give an assessment
and verification of the cloud applications services provided by the cloud provider
data centers. And also verify that the cloud data center provider gives their users the
best services performance and high QoS, we use this verification to assure SLA response
times metric and a good quality and performance of services as mentioned inside the
SLA document. This verification will be given to the cloud customers.