The document discusses various load balancing algorithms for cloud computing including round robin, first come first serve (FCFS), and simulated annealing. It provides implementations of each algorithm in CloudSim and compares the results. Round robin and FCFS showed similar overall response times, data center processing times, and maximum/minimum values. Simulated annealing had slightly lower average overall response time. The document proposes using a genetic algorithm for host-side optimization to select the best host for virtual machine requests.
A brief discussion about Cloud computing for a beginner, you can get a clear idea about cloud computing from this slides.Also, discuss cloudsim simulator.
Cloud computing & energy efficiency using cloud to decrease the energy use in...Puru Agrawal
Cloud can be used to decrease the energy use in large companies. This presentation deals with a model which explains as how cloud can be used to decrease the energy uses. This is a field related to green computing and minimum use of energy resources.
Middleware and Middleware in distributed applicationRishikese MR
The seminar discuss about the common middleware concept and middleware in distributed applications .Also we discuss about 4 different types of middleware. MOM( Message oriented Middleware), ORB (object request broker), TP Monitors, Request procedure calls RPC.
The slide also gives the advantages and disadvantages of each.
Cloud computing is using the internet to access someone else's software running on someone else's hardware in someone else's data center.
OUTLINE-
Definitions of Cloud computing
Architecture of Cloud computing
Benefits of Cloud computing
Opportunities of Cloud Computing
Cloud computing – Google Apps
Grid computing vs Cloud computing
Cloud Computing offers an on-demand and scalable access to a shared pool of resources hosted in a data center at providers’ site. It reduces the overheads of up-front investments and financial risks for the end-user. Regardless of the fact that cloud computing offers great advantages to the end users, there are several challenging issues that are mandatory to be addressed.
You can find the first part of this presentation here: https://www.slideshare.net/secret/pAvK8Qd9f07oa
This presentation takes a deep dive into how the Million Song Library, a microservices-based application, was built using the Netflix Stack, Cassandra and Datastax.
To learn more about Million Song Library and its components visit the project on GitHub: https://github.com/kenzanlabs/million-song-library
Lea
A brief discussion about Cloud computing for a beginner, you can get a clear idea about cloud computing from this slides.Also, discuss cloudsim simulator.
Cloud computing & energy efficiency using cloud to decrease the energy use in...Puru Agrawal
Cloud can be used to decrease the energy use in large companies. This presentation deals with a model which explains as how cloud can be used to decrease the energy uses. This is a field related to green computing and minimum use of energy resources.
Middleware and Middleware in distributed applicationRishikese MR
The seminar discuss about the common middleware concept and middleware in distributed applications .Also we discuss about 4 different types of middleware. MOM( Message oriented Middleware), ORB (object request broker), TP Monitors, Request procedure calls RPC.
The slide also gives the advantages and disadvantages of each.
Cloud computing is using the internet to access someone else's software running on someone else's hardware in someone else's data center.
OUTLINE-
Definitions of Cloud computing
Architecture of Cloud computing
Benefits of Cloud computing
Opportunities of Cloud Computing
Cloud computing – Google Apps
Grid computing vs Cloud computing
Cloud Computing offers an on-demand and scalable access to a shared pool of resources hosted in a data center at providers’ site. It reduces the overheads of up-front investments and financial risks for the end-user. Regardless of the fact that cloud computing offers great advantages to the end users, there are several challenging issues that are mandatory to be addressed.
You can find the first part of this presentation here: https://www.slideshare.net/secret/pAvK8Qd9f07oa
This presentation takes a deep dive into how the Million Song Library, a microservices-based application, was built using the Netflix Stack, Cassandra and Datastax.
To learn more about Million Song Library and its components visit the project on GitHub: https://github.com/kenzanlabs/million-song-library
Lea
StackWatch: A prototype CloudWatch service for CloudStackChiradeep Vittal
Presented at CloudStack Collab 2014 in Denver. The presentation explores adding a Cloudwatch service to Apache CloudStack and some of the interesting design decisions and consequences.
Cloud probing, in a way, is the inverse Virtual Network Embedding (VNE) problem. VNE optimizes the deterministic mapping of multiple virtual graphs onto a shared physical topology. However, cloud platforms today rarely offer such a raw level of control to users, instead, offering their own tools which optimize for certain QoS metrics but not the topology. This paper presents a new framework in which VM populations optimize their own topology by probing the cloud platform they run on and triggering migrations of resources. The core advantage here is that applications can set and implement their own topological and performance targets. This paper presents practical but simple usecases while the topic itself expands into a new generation of cloud-specific end-to-end measurement methods and tools.
This presentation is from the Gophercon-India where we talked about how to design a concurrent high performance database client in go language. We talked about how we use goroutines and channels to our advantages. we also talked about how to use pools for efficient memory utilization.
The JVM memory model describes how threads in the Java eco-system interact through memory. While the memory model impact on developing for the JVM may not be obvious, it is the cause for certain number of "anomalies" that are, well, by design.
In this presentation we will explore the aspects of the memory model, including things like reordering of instructions, volatile members, monitors, atomics and JIT.
Real-time Inverted Search in the Cloud Using Lucene and Stormlucenerevolution
Building real-time notification systems is often limited to basic filtering and pattern matching against incoming records. Allowing users to query incoming documents using Solr's full range of capabilities is much more powerful. In our environment we needed a way to allow for tens of thousands of such query subscriptions, meaning we needed to find a way to distribute the query processing in the cloud. By creating in-memory Lucene indices from our Solr configuration, we were able to parallelize our queries across our cluster. To achieve this distribution, we wrapped the processing in a Storm topology to provide a flexible way to scale and manage our infrastructure. This presentation will describe our experiences creating this distributed, real-time inverted search notification framework.
Microservices in action at the Dutch National Police - Bert Jan Schrijver - C...Codemotion
At the Cloud, Big Data and Internet division of the Dutch National Police, 4 DevOps teams use the latest open source technology to build high tech, cloud native web applications using Spring Boot, Angular 5, Spark, Kafka and Jenkins 2. I'll share our experiences and real-world use cases for microservices. I’ll show how 4 teams work together on one product and I’ll talk about how we apply the principles of DevOps and Continuous Delivery. I’ll show how we handle security, build pipelines, test automation, performance tests, service discovery, automated deployments, monitoring and more!
As more OpenStack clouds move into production, the limits of scale and performance of the cloud need to be known as a pre-requisite to building a predictable operations plan. PLUMgrid ONS is based on a fully distributed architecture that is built for scale. Since forwarding decisions are distributed and made at each individual server, every new server added to the cloud increases the cloud’s forwarding capacity. This unique distributed architecture allows any OpenStack cloud built using the PLUMgrid Open Networking Suite to scale to tens of thousands of workloads across multiple racks. This joint PLUMgrid and Ixia session between will highlight the latest scale and performance numbers for PLUMgrid ONS. In addition, it will cover the various scale targets that were achieved, the testing methodology plus the Ixia IxChariot product used to measure them.
Slides from my Planning to Fail talk given at PHP North East conference 2013. This is a slightly longer version of the same talk given at the PHP UK conference. The talk was on how you can build resilient systems by embracing failure.
Using Groovy? Got lots of stuff to do at the same time? Then you need to take a look at GPars (“Jeepers!”), a library providing support for concurrency and parallelism in Groovy. GPars brings powerful concurrency models from other languages to Groovy and makes them easy to use with custom DSLs:
- Actors (Erlang and Scala)
- Dataflow (Io)
- Fork/join (Java)
- Agent (Clojure agents)
In addition to this support, GPars integrates with standard Groovy frameworks like Grails and Griffon.
Background, comparisons to other languages, and motivating examples will be given for the major GPars features.
Surge 2013: Maximizing Scalability, Resiliency, and Engineering Velocity in t...Coburn Watson
Surge 2013 presentation which covers how Netflix maximizes engineering velocity while keeping risks to scalability, reliability, and performance in check.
15. Background
• Load balancing.
• Type of load balancing.
• Static.
• Dynamic.
• Need of load balancing.
• Improving the performance.
• Maintaining the system stability.
• Quality of services.(QoS)
• Building fault tolerance.
16. Algorithm Survey from several Literature
• Proposed several load balancing algorithms
• Scheduling algorithms.
• Round Robin.
• FCFS.
• Soft computing based algorithms.
• Stochastic algorithm.[1]
• Genetic algorithm.[2]
• Ant colony optimization algorithm.[3]
18. Proposed work
• Our proposed algorithm.
• VM allocation optimization using Simulated annealing.
• Host Side optimization.
• Target.
• Balancing load of the virtual nodes and reducing Response Time(RT).
• Progress with the project.
• Using Cloud Sim simulated Data Centers, Virtual Machines, Cloudlets.
• Virtually distributed the load.
20. Proposed work
• Our next move.
• Migrating to Cloud Analyst and implementing our proposed
algorithm.
21. OUR WORK
• The two algorithms implemented are
1) ROUND ROBIN.
2)FCFS.
3)SIMULATED ANNEALING
22. • Round robin is the scheduling algorithm used by the CPU during
execution of the process.
• All processes in this algorithm are kept in the circular queue also
known as ready queue.
• By using this algorithm, CPU makes sure, time slices ( any natural
number ) are assigned to each process in equal portions and in
circular order
23. IMPLEMENTING ROUND ROBIN
public int getNextAvailableVm(){
currVm++;
if (currVm >= vmStatesList.size()){
currVm = 0;
}
allocatedVm(currVm);
return currVm;
}
26. First Come First Serve
• First come, first served (FCFS) is an operating system process
scheduling algorithm and a network routing management
mechanism.
• With first come, first served, what comes first is handled first.
• The next request in line will be executed once the one before it is
complete.
27. IMPLEMENTING FCFS
public int getNextAvailableVm() {
int temp=-1;
if(vmStatesList.size()>0) {
for (Iterator<Integer> itr = vmStatesList.keySet().iterator(); itr.hasNext();) {
temp = itr.next();
VirtualMachineState state = vmStatesList.get(temp);
if(state.equals(VirtualMachineState.AVAILABLE)){
allocatedVm(temp);
break;
}
}
}
return temp;
}
30. Simulated Annealing
• Simulated annealing (SA) is a probabilistic technique.
• VMs are assigned to have probability which tells availability ofVMs.
• Then using function call we checked highest probability and selected the
VM.
• Accordingly decremented the probability.
31. Implementation of Simulated Annealing
•Probability Data Structure
static float[][] anArrayOfFloats = new float[2][999999]; //probability array
•Implementation
private float getHighProbability(){
float high_probability = anArrayOfFloats[1][0];
for(int i = 1; i<vmStatesList.size(); i++) {
if(high_probability<anArrayOfFloats[1][i])
high_probability = anArrayOfFloats[1][i];
}
return high_probability;
}
33. COMPARISON STUDY
Algorithms Over All Response Time Data Center Processing Time
Avg(ms) Min(ms) Max(ms) Avg(ms) Min(ms) Max(ms)
Round Robin 300.06 237.06 369.12 0.34 0.02 0.61
FCFS 300.09 237.06 369.12 0.38 0.08 4.5
Simulated
Annealing
297.87 271.61 346.62 0.48 0.10 0.61
34. Checks
best Host
according
to Fitness
VM
requested
for Host
VM queue
Host 1
Host 2
.
.
.
Host n
Host Side Optimization
Data center
Host information
Request for Host
Info
Best Host
Request for
Host Request for Host
Best Host
Our proposed algorithm to optimize Host selection is Genetic Algorithm
35. References
[1] Avani Kansara, Ronak Patel et al. “AVarious Load BalancingTechniques and
Challenges in Cloud Computing – Survey ” International Journal for
Scientific Research & DevelopmentVol. 2, Issue 10, 2014 ISSN (online): 2321-
0613
[2] Dasgupta, Kousik et al. "A Genetic Algorithm (GA) Based Load Balancing
Strategy For Cloud Computing". ProcediaTechnology 10 (2013): 340-347. Web.
[3] Santanu Dam 1
, Gopa Mandal2
, Kousik Dasgupta3, Paramartha Dutta4 et al.
“An Ant Colony Based Load Balancing Strategy in Cloud Computing “.
Advanced Computing, Networking and InformaticsVolume 2
Smart Innovation, Systems andTechnologiesVolume 28, 2014, pp 403-413