This white paper presents a vendor-neutral medical-image archive solution that integrates IBM Scale Out Network Attached Storage (SONAS) and the Acuo Universal Clinical Platform running on IBM x86 servers. It describes the configuration that was used to test the Acuo Universal Clinical Platform with IBM SONAS...
2. Table of contents
Abstract..................................................................................................................................... 1
Introduction .............................................................................................................................. 1
Lab configuration ..................................................................................................................... 2
Servers ..................................................................................................................................................... 3
Storage .................................................................................................................................................... 4
Software tools used ................................................................................................................. 4
Tests performed ....................................................................................................................... 5
Planning the IBM vendor-neutral archive deployment........................................................... 6
Summary ................................................................................................................................... 7
Appendix A: Best practices ..................................................................................................... 8
Appendix B: Resources ........................................................................................................... 9
Appendix C: About the author ............................................................................................... 10
Acknowledgments .................................................................................................................................. 10
Trademarks and special notices ........................................................................................... 11
IBM Scale Out Network Attached Storage (SONAS) using the Acuo Universal Clinical Platform
3. Abstract
This white paper presents a vendor-neutral medical-image archive solution that integrates IBM
Scale Out Network Attached Storage (SONAS) and the Acuo Universal Clinical Platform running
on IBM x86 servers. It describes the configuration that was used to test the Acuo Universal
Clinical Platform with IBM SONAS. The configuration was minimized to ensure that all
components would function with the smallest of configurations. This bundled solution is available
from participating IBM value-added distributors and their networks of IBM Business Partners.
Introduction
In the present clinical environment for health-care providers, a significant portion of the medical-imaging
data is stored in individual silos that must be individually maintained and managed. This type of storage
infrastructure creates a tendency to cause a duplication of some or all of the following resources:
• Available disk space
• Other IT resources
• Environmental resources
When using an infrastructure that contains individual silos, it becomes increasingly difficult for a physician
to view the media from each of the different silos. In most cases, the media has to be accessed indirectly,
through an interface to the individual silo and associated application. This consumes valuable time and
resource and also contributes to rising medical costs.
IBM® and Acuo Technologies have now teamed up to create a tested offering that addresses the data
storage, usage and business needs of health-care providers.
IBM Scale Out Network Attached Storage (SONAS) delivers seamless scalability for the high performance
and massive capacity that health-care providers require. The distributed architecture reduces
management complexity, speeds up processes and removes any single point of failure (SPOF) that might
impede data availability.
The Acuo solution builds on the Acuo Universal Clinical Platform, a standards-based suite of software
applications that scales up to accommodate large centralized repositories and scales out to enable fully
distributed storage grids. It is also designed to enable archiving of medical images in a highly interoperable
fashion. The set of services that Acuo delivers through its Universal Clinical Platform also extends and
virtualizes storage resources.
With this integrated approach to archiving and sharing images, the IBM-Acuo solution frees health-care
providers to acquire storage on an as-needed basis and to implement advanced archiving capabilities
without a costly and lengthy migration process. It also enables image interoperability across departments
and applications (regardless of the number of application vendors involved) and allows streamlined EMR
access to clinical images.
Using this solution permits the management of just one storage platform across all clinical departments.
The IBM Acuo solution reduces the need for redundant free space across multiple silos, management of
individual storage platforms and the overall needs of the environment.
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
1
4. Lab configuration
This section outlines the lab configuration at the time of running the test.
Figure 1: Illustration of configuration used
The hardware definitions (see Figure 1 and Figure 2) are as follows:
• Servers – Two IBM System x3650 M3 servers
• Cisco Catalyst 3750G 24T – This is a 24-port Ethernet switch that provides 1 Gigabit Ethernet
(GbE) connectivity between all the devices in this test configuration.
• SONAS – This is the IBM storage platform. IBM SONAS is a network-attached storage (NAS)
based storage appliance that internally uses IBM General Parallel File System (IBM GPFS™), and
is capable of presenting multiple NAS mounts through multiple NAS protocols. A SONAS can
independently scale capacity (up to 14 PB, all under a single global-name space for ease of
management and implementation) or performance by adding additional interface nodes (up to 30
nodes).
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
2
5. Shared
Working
Storage
Windows Server Windows Server
SQL Database SQL Database
Acuo Software Acuo Software
SONAS
Storage
Figure 2: Block diagram representing data flow with the solution
Servers
Three Intel® based IBM System x3650 M3 servers, with the following standard configuration, were used:
• Intel Xeon® processor X5667 at 3.06 GHz (two processors)
• 32 GB of memory
• One Quad Port Gb Ethernet Adapter
• Microsoft® Windows® Server 2008 R2 (Service Pack 1) Enterprise – 64-bit
• Microsoft SQL Server – 2008 R2
• AcuoMed – DICOM (Digital Imaging and COmmunications in Medicine) and Workflow service.
Sends, receives, routes and prefetches images. It also manages data integrity through realtime
HL7 processing of ADT messages.
• AcuoStore – Storage-virtualization component, interfaces with AcuoMed and is used to store the
studies received from AcuoMed.
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
3
6. The disk configuration for each of the servers varied slightly. The following configurations have been used
for each server.
• Servers – Two 146 GB SAS drives configured as a RAID 1E. This array contains the operating
system (OS) as well as the tools used to run the tests.
• Shared working storage - The remaining disk space was made available to the cluster (presented
through either fiber channel (FC) or iSCSI):
1. Quorum Disk for cluster RAID5
2. Database disk – RAID 10, 50 GB
3. Logs – RAID 10, 50 GB
4. DILIB – RAID 5, 50 GB
Storage
The IBM SONAS includes the following configuration:
• Two internal Ethernet switches
• Two internal InfiniBand switches
• Three interface nodes, each with a dual port 10 GbE Converged Network Adapter (CAN)
• One storage pod, consisting of two storage nodes and one enclosure of 60 2 TB hard drives
Software tool used
The OFFIS DICOM Toolkit (DCMTK) is a collection of libraries and applications that implement large
parts of the DICOM standard. It includes software for examining, constructing and converting DICOM
image files, handling offline media, sending and receiving images over a network connection, as well as
demonstrative image storage and work-list servers. DCMTK is written in a mixture of ANSI C and C++.
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
4
7. Tests performed
Tests were performed for both DICOM receiving and DICOM sending tasks:
DICOM receiving tests
Benchmark 1: The cluster is in standard state. Begin transfer of one concurrent DICOM connection to the
receiver with a file size of 128 KB. Let the test run for seven minutes. Record the rate of moving from
image cache.
Benchmark 2: The cluster is in standard state. Begin transfer of two concurrent DICOM connections to a
receiver with file size of 128 KB. Let the test run for seven minutes. Record the rate of moving from image
cache.
Benchmark 3: The cluster is in standard state. Begin transfer of three concurrent DICOM connections to
the receiver with a file size of 128 KB. Let the test run for seven minutes. Record the rate of moving from
image cache.
Benchmark 4: The cluster is in standard state. Begin the transfer of four concurrent DICOM connections
to the receiver with a file size of 128 KB. Let the test run for seven minutes. Record the rate of moving
from image cache.
Benchmark 5: The cluster is in standard state. Begin the transfer of five concurrent DICOM connections
to the receiver with a file size of 128 KB. Let the test run for seven minutes. Record the rate of moving
from image cache.
Benchmark 6: The cluster is in standard state. Begin the transfer of six concurrent DICOM connections
to the receiver with a file size of 128 KB. Let the test run for seven minutes. Record the rate of moving
from image cache.
DICOM sending tests
Benchmark 1: The cluster is in standard state. Begin the transfer of 10 concurrent DICOM connections to
the system with a file size of 128 KB. Let the test run for five minutes. Record the ingests rate (dilib) and
the rate of moving to image cache (dilib to image cache).
Benchmark 2: The cluster is in standard state. Begin the transfer of 15 concurrent DICOM connections to
the system with a file size of 128 KB. Let the test run for five minutes. Record the ingests rate (dilib) and
the rate of moving to image cache (dilib to image cache).
Benchmark 3: The cluster is in standard state. Begin the transfer of 10 concurrent DICOM connections to
the system with a file size of 256 KB. Let the test run for five minutes. Record ingests rate (dilib) and rate
of moving to image cache (dilib to image cache).
Benchmark 4: The cluster is in standard state. Begin the transfer of 15 concurrent DICOM connections to
the system with a file size of 256 KB. Let the test run for five minutes. Record the ingests rate (dilib) and
the rate of moving to image cache (dilib to image cache).
Benchmark 5: The cluster is in standard state. Begin the transfer of 10 concurrent DICOM connections to
the system with a file size of 512 KB. Let the test run for five minutes. Record the ingests rate (dilib) and
the rate of moving to image cache (dilib to image cache).
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
5
8. Benchmark 6: The cluster is in standard state. Begin the transfer of 15 concurrent DICOM connections to
the system with a file size of 512 KB. Let the test run for five minutes. Record the ingests rate (dilib) and
the rate of moving to image cache (dilib to image cache).
Benchmark 7: The cluster is in standard state. Begin the transfer of 10 concurrent DICOM connections to
the system with a file size of 4 MB. Let the test run for five minutes. Record the ingests rate (dilib) and the
rate of moving to image cache (dilib to image cache).
Benchmark 8: The cluster is in standard state. Begin the transfer of 15 concurrent DICOM connections to
the system with a file size of 4 MB. Let the test run for five minutes. Record the ingests rate (dilib) and the
rate of moving to image cache (dilib to image cache).
Planning the IBM vendor-neutral archive deployment
The SONAS appliance can be configured as a complete Enterprise NAS solution, which can support
multiple purposes, including, but not limited to, email archive, databases, virtual machines and so on. The
SONAS storage that comes with the IBM vendor-neutral archive (VNA) solution is configured only for use
with the VNA application.
For more information about expanding SONAS storage to support additional functions, refer to the SONAS
web site (found in Resources section of this white paper) and contact your authorized IBM Business
Partner for more information.
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
6
9. Summary
The IBM SONAS storage performed as expected, and even when tested with high simultaneous thread
counts, the minimal configuration performed extremely well.
This set of tests shows that, in conjunction with IBM System x3650 M3 hardware and the Acuo Universal
Clinical Platform software, IBM SONAS storage can provide a solid solution for even small-scale users.
For more information, refer to the links in the Resources section of this white paper.
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
7
10. Appendix A: Best practices
Here are some best practices for using IBM SONAS storage:
• Use Common Internet File System (CIFS) as the primary protocol
• Deploy SONAS with version 1.3 at a minimum
• Use the available adaptive-load balancing (ALB) trunking on the SONAS to increase bandwidth, if
more than two application nodes are deployed.
• Put SONAS on a separate subnet or switch with the application servers for increased
performance.
• Integrate SONAS into the active-directory (AD) system for security.
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
8
11. Appendix B: Resources
The following web sites provide useful references to supplement the information contained in this paper:
• IBM Systems on PartnerWorld
ibm.com/partnerworld/systems
• Virtual Loaner Program
ibm.com/systems/vlp
• IBM Redbooks®
ibm.com/redbooks
• IBM Publications Center
www.elink.ibmlink.ibm.com/public/applications/publications/cgibin/pbi.cgi?CTY=US
• IBM Scale Out Network Attached Storage (SONAS)
ibm.com/systems/storage/network/sonas
• Acuo Technologies
acuotech.com
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
9
12. Appendix C: About the author
Dave Curzio is a solutions architect in the IBM Systems and Technology Group ISV Enablement
organization. He has more than 10 years experience working with IBM server hardware, IBM storage
platforms and the healthcare environment. You can contact Dave Curzio at DCurzio@us.ibm.com
Acknowledgments
Thanks to Acuo for their support in performing these test scenarios.
IBM Scale Out Network Attached Storage (SONAS) utilizing the Acuo Universal Clinical Platform
10