DSC861A Emerging TechnologyStorage Virtualization

Team 3 Jennifer Brola-RichardsMohib FanekKathy Larson Donovan Miles Vishu ReddyFran Trees

Presentation OutlineStorage VirtualizationWhat is storage virtualization and why storage virtualization?Storage Evolution and Fundamental ConceptsWhat are innovations and fundamental concepts associated with storage? Storage Virtualization Deep DiveWhat, Where and How of Storage Virtualization?Case StudyResearch Topics in Storage Virtualization What are potential topics of research and dissertation? Summary and Verbal Quiz

Storage Virtualization is the next frontier in Storage Advances that aims to provide a layer of abstraction to reduce complexity. Storage Networking Industry Association (SNIA) defines Storage Virtualization as:The act of abstracting, hiding, or isolating the internal functions of a storage (sub) system or service from applications, host computers, or general network resources, for the purpose of enabling application and network-independent management of storage or data. The application of virtualization to storage services or devices for the purpose of aggregating functions or devices, hiding complexity, or adding new capabilities to lower level storage resources.What is storage virtualization?

Allocate and manage storage in accordance to the Quality of Service (QoS) associated with the data (e. g. Gartner estimates average data center doubling its storage every 18 to 24 months)!)

Provided continuous availability despite exponential growth (e.g. FaceBook- Over 55 billion page views a month, 41 million active users1) Storage Virtualization aims to provide a layer of abstraction to manage storage and reduce complexity !!!Why storage virtualization?Effectively group and manage heterogeneous storage devices & servers (e.g. Estimated number of Google Servers 450,000 2!)Lucas Nealan, php|works, Atlanta September 13, 2007 (2) WikipediaMultiple Storage Software Platforms (e.g. IBM, EMC, HP,..)Mergers and Acquisitions (e.g. Microsoft & Yahoo!)

Client side storage innovations variety of storage device innovations that are smaller, higher capacity and cheaper have helped end users cope with increasing storage requirements!What are the innovations and fundamentals associated with storage?

Server side storage innovations a combination of storage devices, storage interfaces and storage software innovations have helped enterprises cope with exponential growth of data storage requirement !Storage devices have evolved from tapes to hard drives to RAID hard drives increasing capacity and resiliency. What are the innovations and fundamentals associated with storage?

Storage interface innovations have evolved from SCSI to ISCI, Fiber Channel (FCP) and InfiniBand to inter connect devices and transport the data faster.SCSIISCSIFCPInfinibandWhat are the innovations and fundamentals associated with storage?

File level access: Files are accessed by "semantics" instructions [example: Open, Close]. Data inside files is accessed by byte-ranges within the file (example: the first 10 bytes of a file). GFS (Google File System) is an example of a large scale distributed file system.Block level access: Block addresses are used to Read/Write data [Read/Write, Block #] to the storage media. Sample conventional Block Allocation MapStorage Access File level access takes center stage along with conventional Block level access.What are the innovations and fundamentals associated with storage?

Metadata is Data about data; in the context of storage metadata may describe an individual datum, or content item, or a collection of data including multiple content items.

Examples include: file size, who created file, attributes such as read only, free block bitmaps, control data.What are the innovations and fundamentals associated with storage?

Storage Software from simple back-up and restore to advanced storage networks and storage management software functions.(A) Simple Direct Attached Storage (DAS)(B) Storage Area Network (SAN)(C) Network Attached Storage (NAS)What are the innovations and fundamentals associated with storage?

SAN and NAS: Key DifferencesWhat are the innovations and fundamentals associated with storage?

NASSANAccess MethodsFile accessDisk block accessAccess MediumEthernetFiber ChannelArchitectureDecentralizedCentralizedTransport ProtocolLayer over TCP/IPSCSI/FC and SCSI/IPEfficiencyLessMoreSharing and Access ControlGoodPoorTypical ApplicationsWebDatabaseTypical ClientsWorkstationsDatabase servers

File Level VirtualizationStorage Level VirtualizationNetwork VirtualizationHost Level Virtualization** Host aka Server* *** Device=aggregation of Host and Network (Meta Data)2146Device Virtualization53SNIA Storage ModelWhat and Where can Storage be Virtualized?Block VirtualizationPotential Areas of VirtualizationSource: The Storage Networking Tutorials, SNIAVIRT- Page 20 http://www.snia.org/education/tutorials/

File Level VirtualizationStorage Device Level VirtualizationNetwork VirtualizationHost Level Virtualization215Storage Virtualization: Innovations and TrendsHistorical: MainframeRecent development example: VMwareHistorical: RAID Level, SCSI InterfaceRecent Development Examples: Fiber Channel34Block VirtualizationDevice Virtualization6Sub-TechniqueSub-TechniqueHistorical: MainframeRecent development example: NASWhat and Where can Storage be Virtualized?Major innovations continue to emerge even in historical areas of storage virtualizationSymmetrical (aka in-band) and Asymmetrical (aka Out-of-Band) are emerging as key areas of abstraction and virtualization.

How is storage virtualized at the enterprise level?Source: IBM Redbook Page 8http://www.redbooks.ibm.com/redbooks/pdfs/sg246210.pdfMetadata or Storage Volume Controllers (SVC) are placed (in-band) or in the path of data flow.Metadata or Storage Volume Controllers are placed (out of band) outside the path of data flow.Currently Networks are virtualized using Metadata or Storage Volume Controllers. There are two types of network virtualization

In-Band VirtualizationSource: IBM Redbook Page 10http://www.redbooks.ibm.com/redbooks/pdfs/sg246210.pdfMetadata or Storage Volume Controllers (SVC) are placed (in-band) or in the path of data flow.How is storage virtualized at the enterprise level?SVC controls who can get access to the storage devicecontrols, how storage can be accessed, how storage is allocated, etc.SVC are managed through Storage Management Software.123Key Challenge is the potential IO bottlenecks4

Out-of-Band Network VirtualizationMetadata or Storage Volume Controllers (SVC) are placed (in-band) or in the path of data flow.132Host sends Metadata to SVCStorage Pool sends Metadata to SVC4SVC controls who can get access to the storage devicecontrols, how storage can be accessed, how storage is allocated, etc.Source: IBM Redbook Page 12http://www.redbooks.ibm.com/redbooks/pdfs/sg246210.pdfHow is storage virtualized at the enterprise level?

Virtualization Implementation ExampleHow is storage virtualized at enterprise level?

Ethernet

Tower box

Cloud

Monitor

xSeries server

(xxx) xSeries server

(2) Cisco 6509 switch

San Fabric A

Virtualization Engine

(xxx) pSeries server(s)

(xxx) pSeries server(s)

Virtualization Engines

Type 2 SAN Storage_ 40 TB

Type 1 Storage

PRIMARY SITEEnvironment:PROD, DEV, QA, SITApplication:App1, App2

SECONDARY SITEEnvironment:ProdApplication:App1, App2

HIGH LEVEL DIAGRAM _ Typical Primary/Secondary site data replication with Storage Virtualization

Network Appliances

VPN Comm-link for remote support

VPN Comm-link for remote support

San Fabric ADirector

Type 1 SAN Storage with_52TB

San Fabric B

San Fabric ADirector

San Fabric BDirector

SAN Fabric B

(xxx) Blade server(s)

Blade SAN Fabric

DWDM

SAN Fabric A

Library wi LT03 drives

Library wi LTO3drives

Type 2 SAN Storage26TB ea

Type 2 SAN Storage

Virtualization Engine Monitor

Monitor

Network Appliances

Network Appliances

SAN Fabric A

SAN Fabric B

Monitor

D. Miles 06/09/07

Management VLAN _ QA/DEV _ storage, library, director _ 950

PROD_ Blades + Blade Fabric_ 955

Case StudyThe Study Shows that commingling of data and meta-data on a single logical device means that there is no way to achieve different service level objectives for data and meta-data in the same file system, without moving file-system specific knowledge into the logical disk layers.Shows that the standard assumptions underlying the organization of data and meta-data in file systems are no longer valid in virtualized storage environment and hence fail to materialize the full benefits of storage virtualization.

Proposes a different file system organization of data and meta-data designed to exploit the power of virtualized storage.

Case StudyOrganization A Needs No Encryption

Organization B_ Needs EncryptionStores Medical RecordsSecurity requirements for file data is extremely high. Performs nightly indexing operation on file systemsAll directory information and file access times must be read to determine changed state of dataBusiness requirement that all file data be encrypted at rest.File meta data has no security requirementService Level requirements within a single file systemIn Unix fast file system (ffs), a logical disk is divided into collections of blocks called cylinder groups, each of which stores both file data blocks as well as file meta-data

Case StudyResultsClean logical separation between data and metadataAllows file system feature to use virtualization features and achieve different SLOs

Redesign changes Code changePacking the re-located cylinder group header in the first few meta data cylinder groups ensures each header is located @ a fixed, predictable offset from the front of the block deviceUser configurable block address space before which no data stored and after no meta data stored

Case Study5-7% gains on the new file system layout

31-44% for the file lookup and file delete benchmarks, which result in little or no file data i/o, the advantage of data-only encryption become obviousFuture Work Differing SLOs for granular meta data Completely separate fixed/dynamic metadata Separate file data from user defined file attribute data

Sample Research Topics in Storage VirtualizationBayesian analysis for resource management Bayesian analysis for diagnostics Trusted domains for security Storage Virtualization and Metadata Standards Algorithm advances for block, device and other component virtualization techniquesWhat are potential topics of research and dissertation?

Summary and Verbal QuizStorage BasicsWhat type of storage is found in your work station?What type of storage systems may be found in a large enterprise?How is data accessed from storage?Network Attached Storage (NAS) is well suited for what type of applications?Storage Area Network (SAN) is well suited for what type of applications? Storage VirtualizationWhat is Storage Virtualization?Where and What can be virtualized in storage?How is storage virtualized at a network level?How is storage virtualization currently implemented?What are the potential research topics in storage virtualization?

Annotated ReferencesFaibish. S., Fridella S, Bixby P., and Gupta U., Storage Virtualization using a Block-device File System January 2008 ACM SIGOPS Operating Systems Review, Volume 42 Issue 1 Publisher: ACM The Storage Networking Tutorials, SNIAVIRT http://www.snia.org/education/tutorials/http://en.wikipedia.org/wiki/Metadatahttp://www.redbooks.ibm.com/redbooks/pdfs/sg246210.pdfNealan.L., php|works, Atlanta September 13, 2007 http://sizzo.org/wp/wp-content/uploads/2007/09/facebook_performance_caching.pdf6. http://en.wikipedia.org/wiki/Google_platform

Disk are good at bulk sequential data transfersDisk perform poorly when forced to seekLogical contiguous disk address are likely to be physically contiguous

Service Level Objective _Business value the organization associates with a piece of information.Each piece of data may performance requirements and legal requirements.Storage devices offer various levels of reliability, performance and security. Effective information management means storing each piece of information on the least costly device which meets the informations service level objective. The process of automatically mapping a piece of information to its ideal storage device in a transparent and durable manner is one important aspect of storage virtualization.Applications generate information or data which is submitted to file systems for storageMeta data is information generated Meta data_ small files, fragmented files_poor perf vs data