SYNOPSIS ON Going Back and Forth: Efficient Multi deployment and Multi snapshotting on Clouds

SUBMITTED BY
SAMEER BANSOD NIKHIL RATHOD MUKESH BURADKAR KAMLESH ADHAU

UNDER THE GUIDANCE OF MR. SAGAR BADHIYE

DEPARTMENT OF COMPUTER TECHNOLOGY YESHWANTRAO CHAVAN COLLEGE OF ENGINEERING HINGNA ROAD, WANADONGRI, NAGPUR-441110 YEAR 2013-2014

1 Existing System 4.2 Disadvantages 4. 2. 3.1 Advantage 6. High Level Design 6. Problem Definition Abstract Aim & Objective Literature Review 4.1 Data flow diagram 6. 3 4 5 6 7 8 8 9 11 11 12 15 16 17 References . Plan of Action Software & Hardware Requirements Page No.3 Cloud Infrastructure 4.4 Application State 5.Table of Contents Title 1. 8. 4. Scope 5.2 System Architecture 7.

Problem Definition To provide the basic functionalities for the use of Virtual Machine’s (VM’s) over the cloud given as: • Multideployment : The operation of Infrastructure As A Service (IaaS) is the need to deploy a large number of VMs on many nodes of a datacentre at the same time. starting from a set of VM images previously stored in a persistent fashion • Multisnapshotting : Many VM images that were locally modified need to be concurrently transferred to stable storage with the purpose of capturing the VM’s state for later use (e.. .g.1. for check pointing or off-line migration) to another cluster or cloud .

. ensuring high portability for different configurations. This new model raises new challenges in the design and development of IaaS middleware. It is based on a lazy transfer scheme coupled with object versioning that handles snapshotting transparently in a hypervisor-independent fashion. With datacenters growing rapidly and configurations becoming heterogeneous. This paper addresses these challenges by proposing a virtual file system specifically optimized for virtual machine image storage.2. such as suspend-resume and migration. One of those challenges is the need to deploy a large number (hundreds or even thousands) of VM instances simultaneously. Once the VM instances 1are deployed. another challenge is to simultaneously take a snapshot of many images and transfer them to persistent storage to support management tasks.Abstract Infrastructure as a Service (IaaS) cloud computing has transform the way we think of acquiring resources by introducing a simple change: allowing users to lease computational resources from the cloud provider’s datacenter for a short time by deploying virtual machines (VMs) on these resources. it is important to enable efficient concurrent deployment and snapshotting that are at the same time hypervisor independent and ensure a maximum compatibility with different configurations.

for managing numbers of users at the same time and within the context of time slices. One resource can be available to the all the users . Aim and Objectives In this project. A focus on the use of reusable frameworks to provide cost and times benefits.2. we are creating cloud infrastructure which allows users to lease computational resources from cloud provider. restart & suspend operation. Our aim is to create and implement load balancing mechanisms.by anticipating their requirements we provide them without confliction. They’re focused on coming up with solutions that serve customer requirements today and anticipate future needs. . We want to reduce the contention on current system & allow maximum number of user to access VM’s with quick resume.

IaaS leasing is equivalent to purchasing dedicated hardware but without the long-term commitment and cost.[1] Once the VM instances are running. When taking frequent snapshots for a large number of VMs. We refer to this pattern as multisnapshotting. not counting the time to boot the operating system itself. a similar challenge applies to snapshotting the deployment: many VM images that were locally modified need to be concurrently transferred to stable storage with the purpose of capturing the VM state for later use (e. A typical deployment consists of hundreds or even thousands of such images. This problem is particularly acute for VM images used in scientific computing where image sizes are large (from a few gigabytes up to more than 10 GB). This emerging model leads to new challenges relating to the design and development of IaaS systems. this pattern occurs when the user wants to deploy a virtual cluster that executes a distributed application or a set of environments to support a workflow. by using external resources to complement their local resource base. Conventional deployment techniques broadcast the images to the nodes before starting the VM instances. Since the user has complete control over the configuration of the VMs using on-demand deployments. starting from a set of VM images previously stored in a persistent fashion.4. a process that can take tens of minutes to hours. Therefore. which limits the ability to easily migrate VMs among different hypervisors. The on-demand nature of IaaS is critical to making such leases attractive. Literature Survey In recent years. users can lease storage and computation time from large datacentre’s. This can make the response time of the IaaS installation much longer than acceptable and erase the ondemand benefits of cloud computing. One of the commonly occurring patterns in the operation of IaaS is the need to deploy a large number of VMs on many nodes of a datacentre at the same time. Infrastructure as a Service (IaaS) cloud computing has emerged as a viable alternative to the acquisition and management of physical resources.g. Such a large deployment of many VMs at once can take a long time. We refer to this pattern as multideployment. Furthermore. for check pointing or off-line migration to another cluster or cloud). with growing datacentre trends and tendencies to federate clouds. configurations are becoming more and more heterogeneous. Conventional snapshotting techniques rely on custom VM image file formats to store only incremental differences in a new file that depends on the original VM image as the backing file.. Custom image formats are not standardized and can be used with specific hypervisors only. since it enables users to expand or shrink their resources according to their computational needs. multisnapshotting must be handled in a transparent and portable . Leasing of computation time is accomplished by allowing users to deploy virtual machines (VMs) on the datacentre’s resources[1]. With IaaS. For example. which are difficult to manage and which interfere with the ease-of-use rationale behind clouds. such approaches generate a large number of files and interdependencies among them.

3 Cloud infrastructure IaaS platforms are typically built on top of clusters made out of loosely-coupled commodity hardware that minimizes per unit cost and favours low power over maximum speed.BLOBs that can grow to TB) in very large-scale distributed systems while maintaining a very high data throughput for highly concurrent. and network traffic consumption.fashion that hides the interdependencies of incremental differences and exposes standalone VM images. and data and processing outsourcing. Clouds have been defined just as virtualized hardware and software plus the previous monitoring and provisioning technologies. 4. This paper proposes a distributed virtual file system specifically optimized for both the multideployment and multisnapshotting patterns. In addition to incurring significant delays and raising manageability issues. Disk storage (cheap hard-drives with . We addressed several major requirements related to these challenges. It is not possible to build a scalable. raw image files (understood by most hypervisors) to the outside[6]. while keeping maximum portability among different hypervisor configurations. load balancing. high-performance distributed data-storage service that facilitates data sharing at large scale. while handling snapshotting transparently and exposing standalone. provisioning. we investigate them in conjunction. Cloud Computing is a “buzz word” around a wide variety of aspects such as deployment.1 Existing system The huge computational potential offered by large distributed systems is hindered by poor data sharing scalability. The role of virtualization in Clouds is also emphasized by identifying it as a key component. Since the patterns are complementary. 4. these patterns may also generate high network traffic that interferes with the execution of applications on leased resources and generates high utilization costs for the user. fine-grain data accesses [1]. Our proposal offers a good balance between performance. One such requirement is the need to efficiently cope with massive unstructured data (organized as huge sequences of bytes . storage space. 4.2 Disadvantages To give less performance and storage space. Network traffic consumption also very high due to non concentrating on application status. Moreover.

the issue of capturing the global state of the communication channels is difficult and still an open problem. for VM instances that need large amounts of memory. CPU registers. in terms of both hardware and software. In order to provide persistent storage. the general case is usually simplified such that the application state is reduced to the sum of states of the VM instances . in the most general case . The repository is responsible for storing the VM images persistently in a reliable fashion and provides the means for users to manipulate them: upload. Model 2 can further be simplified such that the VM state is represented only by the virtual disk attached to it (Model 3). While several methods have been established in the virtualization community to capture the state of a running VM (CPU registers. saving 2 GB of RAM for 1. In order to avoid this issue. in-transit network packets.compatible between different hypervisors. and (ii) Portability since the VM can be restored on another host without having to worry about restoring the state of hardware devices that are not supported or are in. since the contents of RAM. virtual topology. the necessary storage space can explode to huge sizes. Such an approach has two important practical benefits: (i) Huge reductions in the size of the state. etc.). Even so. such that they are able to host the VMs. which is used to store only minimal information about the state. and the like does not need to be saved. delete. The machines are configured with proper virtualization technology. RAM. saving the application state implies saving both the state of all VM instances and the state of all active communication channels among them. For example. Thus. .point-in-time deployment checkpoint. 4. state of devices. a dedicated repository is deployed either as centralized or as distributed storage service running on dedicated storage nodes.).[5] This information is then later used to reboot and reinitialize the software stack running inside the VM instance. Any in-transit network traffic is discarded. while the machines are interconnected with standard Ethernet links. there is an acute need for scalable storage.4 Application state The state of the VM deployment is defined at each moment in time by two main components: the state of each of the VM instances and the state of the communication channels between them (opened sockets. such as configuration files that describe the environment and temporary files that were generated by the application. Therefore.store communication channels and resend lost information[5]. etc.capacities in the order of several hundred GB) is attached to each machine.000 VMs consumes 2 TB of space. With the recent explosion in cloud computing demands. under the assumption that a fault-tolerant networking protocol is used that is able to re. which is unacceptable for a single one. download. and so forth.

a versioning storage service specifically designed for high throughput under concurrency.1 ADVANTAGE A good balance between performance. Since the patterns are complementary. . To illustrate this point.5. We introduce a series of design principles that optimize multi deployment and multi snapshotting patterns and describe how our design can be integrated with IaaS infrastructures. we describe an implementation on top of Blob Seer. while handling snapshotting transparently and exposing standalone. We show how to realize these design principles by building a virtual file system that leverages versioningbased distributed storage services. Scope A distributed virtual file system specifically optimized for both the multi deployment and multi snapshotting patterns. storage space. 5. storage space. while handling snapshotting transparently and exposing standalone. and network traffic consumption. raw image files (understood by most hypervisors) to the outside[4]. raw image files. and network traffic consumption. Our proposal offers a good balance between performance. we investigate them in conjunction.

High Level Design User system REGISTER GETTING AUTHORIZATION TO STORE RESOURCES DATACENTER CONTROL API HYPERVISOR Request Requesting files LOCAL DISK FIG 1. RESOURCE 2 VM VM CENTRALIZED DATA STORAGE FIG 2.6. SYSTEM ARCITECTURE . SYSTEM FLOW DIAGRAM RESOURCES RESOURCE1.

Since all image snapshots are independent entities. when to create a new image clone (CLONE) [2]. For ex-ample. However. the cloud client interacts with the cloud middleware through a control API that enables a variety of management tasks. which is responsible for ondemand mirroring and snapshotting and relies on both the local disk and the distributed versioning storage service to do so. telling it when to start and stop VMs. A global snapshot of the whole application. This approach enables snapshotting to be leveraged in interesting ways. they can be either collectively or independently analyzed and modified in an attempt to . and snapshotting individual VM instances or the whole set. let’s assume a scenario where a complex. The reads and writes of the hypervisor are trapped by the mirroring module [1]. and when to persistently store its local modifications (COMMIT) [2]. Each compute node runs a hypervisor [1] that is responsible for running the VMs. the application right before the bug happens. A distributed versioning storage service that supports cloning and shadowing is deployed on the compute nodes and consolidates parts of their local disks into a common storage pool. Furthermore. The cloud middleware interacts directly with both the hypervisor. CLONE is broadcast to all mirroring modules. which involves taking a snapshot of all VM instances in parallel. The typical elements found in the cloud are illustrated with a light background. Once a clone is created for each VM instance. telling it what image to mirror from the repository.suing each mirroring module a COMMIT to its corresponding clone. followed by COMMIT. Every uploaded image is automatically striped. dynamically adding or removing compute nodes from that set. and the mirroring module. Running the application repeatedly and waiting for it to reach the point where the bug happens might be prohibitively expensive. Both CLONE and COMMIT are control primitives that result in the generation of a new. The cloud client has direct access to the storage service and is allowed to upload and download images from it. The cloud middleware [2] in turn coordinates the compute nodes to achieve the afore-mentioned management tasks.7. distributed application needs to be debugged. while the elements that are part of our proposal are highlighted by a darker background. fully independent VM image that is globally accessible through the storage service and can be deployed on other compute nodes or manipulated by the client.Plan of Action The simplified architecture of a cloud that integrates our approach is depicted in Figure 1. including deploying an image on a set of compute nodes. subsequent global snapshots are performed by is. CLONE and COMMIT can also be exposed by the cloud middleware at the user level through the control API for fine-grained control over snapshotting. The first time the snap-shot is taken. is performed in the following fashion.

. Such an approach is highly useful in practice at large scale because complex synchronization bugs [3] tend to appear only in large deployments and are usually not triggered during the test phase. which is usually performed at smaller scale. the application can safely resume from the point where it left. If the attempt was not successful. Once this fix is made. the approach can continue iteratively until a fix is found.fix the bug.

Software And Hardware Requirements 8.1 Hardware requirement : CPU type Clock speed Ram size Hard disk capacity : Dual Core : 2.8.6) : MS-Access : Ms-Office .65 GHz : 2 GB : 40 GB 8.2 Software requirement : Operating System: Windows Language Back End Documentation : JAVA(JDK-1.

pdf [2]Mehryar Mohri.fr/docs/00/57/06/82/PDF/final-paper. Lee. the MIT Press ISBNhttp://hal. Griffith. Katz. GA. Keahey and T.pdf [3]M. Claudel.A. A. Joseph. A view of cloud computing. Taktuk. G. Zaharia. and O. A. In HPDC’09: Proceedings of the 18th ACM International Symposium on High Performance Distributed Computing. R. [6] Hypervisor Alternative: http://siliconangle.4. Richard. Huard. Stoica. Rabkin. Fox.inria. 2008. Patterson. 2000. Freeman.I. Science clouds: Early experiences in cloud computing for scientific applications. Afshin Rostamizadeh.53:50 [4]327.Ameet Talwalkar (2012) Foundations of Machine Learning.USENIX Association.org/files/nicolae_hpdc2011. Commun.References : [1]Going Back and Forth: Efficient Multi deployment and Multi snapshotting on Clouds: www. In CCA’08: Proceedings of the 1st Conference on Cloud Computing and Its Applications. ACM. Atlanta.nimbusproject. B. Konwinski.com/blog/2013/09/19/red-hat-teams-up-with-dotcloud-topromote-open-hyperviper-alternative/ . D.A. G. and M. R. pages 91 [5]K. Armbrust.adaptive deployment of remote executions.

Page nos.2” . Right : 1. Subtitles Times New Roman 12. bold.Guidelines 1.02 (Project guide + Project Coordinator) . center. should be at the center of bottom of each page. Number of copies -. The paper should be A4 size with margins: Top: 1”. Bottom : 1. 6.5 Paragraph spacing – 2 lines 4. Left : 1. bold. 2. 3. Report should be spiral bound with white plastic cover pages only. left aligned.5” . Written matter – Times New Roman 12 (justified) Line spacing – 1. Headings in the chapters should have size Times New Roman 14.25” 5.

Seminar report should be as per the guidelines only. .7.

Sign up to vote on this title
UsefulNot useful