Comet Cloud

INTRODUCTION
Different applications may have very different and dynamic quality of service
(QoS) requirements
• One application may require high throughput.
• Another may be constrained by a budget .
• A third may have to balance both throughput and budget.

AN AUTONOMIC CLOUD ENGINE
The overarching goal is to realize a virtual computational cloud with
resizable computing capability
 Integrates local computational environments and public cloud
services on-demand.
Comet Cloud enables policy-based autonomic cloud bridging and cloud
bursting
• Autonomic cloud bridging enables on-the-fly integration of local
computational environments, like data centers and grids, and public
cloud services, like Amazon EC2 and Eucalyptus.

COMET SPACE
In Comet, a tuple is a simple XML string
The first element is the tuple’s tag
This lightweight format is flexible enough to represent the information
for a wide range of applications
Five nodes are indexed using SFC from 0 to 63
• With id shown in solid circle
• The tuple defined as the point (2, 1) is mapped to index 7 on the
SFC
• The tuple defined as the region (23, 15) is mapped to two
segments on the SFC

COMET CLOUD LAYERED ABSTRACTIONS
The infrastructure layer uses the Chord self-organizing overlay
• The Squid information discovery and content-based routing substrate
built on top of Chord.
• Nodes providing resources in the overlay have different roles.
• Provides replication and load balancing services.
• Every node keeps the replica of its successor node’s state.
• If a node fails, the predecessor node merges the replica into its state.
• If a new node joins, the joining node’s predecessor updates its
replica to reflect the joining node’s state.

COMETCLOUD LAYERED ABSTRACTIONS (CONT.)

AUTONOMIC CLOUD BURSTING
The goal of autonomic cloudbursts
• To seamlessly and securely integrate private enterprise clouds and data
centers with public utility clouds on-demand.
• Enables the dynamic deployment of application components onto a
public cloud .
Typical over-provisioning strategies are no longer feasible
• The increasing application and infrastructure scales.
• Their cooling, operation, and management costs.
• Autonomic cloudbursts can leverage utility clouds.
The overall approach for supporting autonomic cloudbursts in Comet Cloud
• Comet Cloud considers three types of clouds.
• Assigns capabilities accordingly.
• The first is a highly trusted, robust, and secure cloud.

AUTONOMIC CLOUDBURSTING (CONT.)

AUTONOMIC CLOUD BRIDGING
Autonomic cloud bridging is meant to connect Comet Cloud and a virtual
cloud
• Consists of public cloud, data center, and grid by the dynamic needs of
the application .
• The clouds in the virtual cloud are heterogeneous.
• The performance of each cloud can change over time by the number of
current users.

AUTONOMIC CLOUDBRIDGING (CONT.)

AUTONOMIC CLOUD BRIDGING (CONT.)
.
Three types of policies :
• Deadline-Based
When an application needs to be completed as soon as possible,
assuming an adequate budget, the maximum required workers are
allocated for the job.
• Budget-Based
When a budget is enforced on the application, the number of workers
allocated must ensure that the budget is not violated.
• Workload-Based
When the application workload changes, the number of workers
explicitly defined by the application is allocated or released.

OTHER AUTONOMIC BEHAVIORS
The overview of replication in the overlay
• Every node has a local space in the service layer.
• When a tuple is inserted or extracted from the local space.
• When a node fails, another node in the overlay detects the
failure notifies it to the predecessor of the failed node .
• The predecessor of the failed node merges the replica space
into the local space.
• The predecessor node makes a new replica for the local
space of its new successor.

OTHER AUTONOMIC BEHAVIORS (CONT.)

Comet Cloud

More Related Content

What's hot (20)

Similar to Comet Cloud (20)

Recently uploaded (20)

Comet Cloud

Editor's Notes