Browse Prior Art Database

System and Method to Accelerate Data Access to Application Development and Testing workloads through VMware vSphere APIs for IO Filtering

IP.com Disclosure Number: IPCOM000249627D
Publication Date: 2017-Mar-08
Document File: 4 page(s) / 100K

Publishing Venue

The IP.com Prior Art Database

Related People

Chirag Dalal: INVENTOR [+2]

Abstract

This method accelerates data access to the Application Development and Testing workloads in the system described here. It provides a content-aware cache that considers the refresh operation of Copy Data Management workloads using VMware vSphere APIs for IO Filtering. It separates the IO interception and data caching logic and works as a Disk IO Filter within the confines of the VMware IO Filter Framework.

This text was extracted from a PDF file.
This is the abbreviated version, containing approximately 39% of the total text.

Chirag Dalal

Vaijayanti Bharadwaj

1

© 2017 Veritas Technologies LLC. All rights reserved. Veritas and the Veritas Logo are trademarks or registered trademarks of Veritas Technologies LLC or its affiliates in the U.S. and other countries. Other names may be trademarks of their respective owners.

System and Method to Accelerate Data Access to 

Application Development and Testing workloads 

through VMware vSphere APIs for IO Filtering 

Abstract

This method accelerates data access to the

Application Development and Testing workloads in

the system described here. It provides a content-

aware cache that considers the refresh operation of

Copy Data Management workloads using VMware

vSphere APIs for IO Filtering. It separates the IO

interception and data caching logic and works as a

Disk IO Filter within the confines of the VMware IO

Filter Framework.

Problem Statement

a) The software development and testing scenarios are one of the largest

consumers of copies of production

data of Copy data management, it is

typically setup is as follows (using

the example of Oracle):

Oracle database files are available

on an appliance. The Oracle

application itself is running within a

virtual machine on an ESX server.

The appliance takes a snapshot of

data files and exports the snapshots

through NFS. The VM mounts the

NFS share and Oracle configuration

files are updated to use the data files

from the mounted NFS share.

The applications run within the VM

and perform transactions on the data

files. These transactions may update

data and those are captured on the

appliance. The appliance has data in

data files for multiple points in time.

The data from the appliance is

accessed through NFS or other

network protocols.

In Copy Data Management, the

refresh operation is performed often

to bring the dataset to a more

current point-in-time. For Velocity,

the change of data between

2

© 2017 Veritas Technologies LLC. All rights reserved. Veritas and the Veritas Logo are trademarks or registered trademarks of Veritas Technologies LLC or its affiliates in the U.S. and other countries. Other names may be trademarks of their respective owners.

refreshes is quite small.

The problems that our invention

solves are:

1. All data, including the updates to

backup dataset, travels over the

network. The data set is refreshed

often and hence the caching within

the VM doesn’t help much.

2. We are taking advantage of the

Flash storage available on the ESX

server to accelerate the workloads

running in VMs.

3. Additionally, we have found VAIO

to be more performant than an

equivalent VSA-based approach.

The VSA-based approach serves

data over NFS, which is slower than

a direct approach like VAIO one.

Publication Description

The goal of Hyper Access is to serve these VMs

with the data faster than what they would get from

NFS. We use the fact that the data set is read-only

with snapshots providing each VM their own

“personalized” copies that are bit different from

each other once they are updated...