Category: server

Posted on

Open Data Center Alliance (ODCA) BMW Private Cloud Strategy

Storage I/O cloud virtual and big data perspectives

If your organization like StorageIO is a member of the Open Data Center Alliance (ODCA) you may be aware of the resources they make available about cloud, virtualization, security and more. Unlike so many other industry associates or trade groups dominated by vendors, the ODCA has an IT or customer focus including member developed best practices, strategies and templates.

A good example is the recently released ODCA member BMW group private cloud strategy document.

This 24 page document covers BMW groups private cloud strategy that sets stage for phased future hybrid. By being a phased approach, it seems that BMW is leveraging and transitioning for the future while maintaining support for their current environment (including Windows-based) as part of a paradigm shift. This is refreshing and good to see how organizations are looking to use cloud as part of a paradigm or IT service deliver model and not just as a new technology or platform focus.

Topics covered include IaaS along with PaaS for DB, Web, SAP and CSaaS or Corporate Software as a Service based on the NIST cloud model. Also included are roles and integration of CMDB, ITSM, ITIL, orchestration in a business vs. technology driven model. Being business driven, that means there is a mission statement for the BMW cloud strategy, with objectives aligned to support organization enablement vs. using different tools, technologies or trends along with design criteria.

What I like about the BMW strategy is that it is aligned to support the business as opposed to finding ways to use technology to support the business, or justify why a cloud is needed. In other words, something different from those needing for a technology, tool, product, standard or service to be adopted.

Thus while having been a vendor, the ODCA customer focused angle appeals to me from when I was on that side of the table working in IT organizations. Otoh, for some of you reading through the BMW document might result in DejaVu from experiences of web-based, client-server, information utilities and other IT service delivery models or paradigms.

Learn more at the ODCA newsroom

If you have not done, check out and join the ODCA.

Ok nuff said

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Where has the FCoE hype and FUD gone? (with poll)

Storage I/O cloud virtual and big data perspectives

A couple of years ago I did this post about if Is FCoE Struggling to Gain Traction, or on a normal adoption course?

Fast forward to today, has anybody else noticed that there seems to be less hype and fud on Fibre Channel (FC) over Ethernet (FCoE) than a year or two or three ago?

Does this mean that FCoE as the fud or detractors were predicting is in fact stillborn with no adoption, no deployment and dead on arrival?

Does this mean that FCoE as its proponents have said is still maturing, quietly finding adoption and deployment where it fits?

Does this mean that FCoE like its predecessors Fibre Channel and Ethernet are still evolving, expanding from early adopter to a mature technology?

Does this mean that FCoE is simply forgotten with software defined networking (SDN) having over-shadowed it?

Does this mean that FCoE has finally lost out and that iSCSI has finally stepped up and living up to what it was hyped to do ten years ago?

Does this mean that FC itself at either 8GFC or 16GFC is holding its own for now?

Does this mean that InfiniBand is on the rebound?

Does this mean that FCoE is simply not fun or interesting, or a shiny new technology with vendors not spending marketing money so thus people not talking, tweeting or blogging?

Does this mean that those who were either proponents pitching it or detractors despising it have found other things to talk about from SDN to OpenFlow to IOV to Software Defined Storage (what ever, or who ever definition your subscribe to) to cloud, big or little data and the list goes on?

I continue hear of or talk with customers organizations deploying FCoE in addition to iSCSI, FC, NAS and other means of accessing storage for cloud, virtual and physical environments.

Likewise I see some vendor discussions occurring not to mention what gets picked up via google alerts.

However in general, the rhetoric both pro and against, hype and FUD seems to have subsided, or at least for now.

So what gives, what’s your take on FCoE hype and FUD?

Cast your vote and see results here.

 

Ok, nuff said

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

A Pivotal or cloudy moment for EMC and VMware?

Storage I/O cloud virtual and big data perspectives

EMC and VMware (who is majority owned by EMC) have announced a new joint initiative called Pivotal (read more here and here) as part of their software defined data center strategies and architecture.

Image of EMC and VMware Pivotal PaaS cloud

Is this a pivotal moment for both EMC and VMware signaling that they will be going head to head (via their new initiative based company) with Amazon Web Services (AWS), Microsoft Azure, HP Cloud services, Rackspace and a long list of others?

Part of the answer to that question would be based on what is meant by going head to head, and which aspects of those services. For Cloud Platform as a Service (PaaS) along with big data analytics related I would say yes. In terms of other Cloud AaaS or SaaS or IaaS probably not as much so at this time.

On the surface Pivotal appears to at least initially be more of a Platform as a Service (PaaS) play vs. Software as a Service (SaaS) or Application as a Service (AaaS) or Infrastructure as a Service (IaaS) play. Thus it will be interesting to see how Pivotal pivots and evolves into other directions beyond first cloud and big data applications development assistance.

This will not be the first initiative or company jointly formed with VMware following on the heals of VCE that also includes Cisco and Intel as partners.

Pivotal will be headed up by Paul Maritz who has been EMC Chief Strategist and formerly CEO of VMware as well as having spent time at Microsoft. EMC will have 69% ownership with VMware having the balance, it is estimated that about $400 Million US dollars will need to be invested.

The new company or initiative is slated to launch on or about April 1, 2013 (April Fools day) with target 2013 revenues of about $300 Million. Projections are for an annual revenue of around $1 Billion in five years. That revenue will come from the existing assets and business being brought together along with probably some net new business. Doing some quick back of the napkin based math shows an average straight line growth of about 36% over five years.

VMware intellectual property and assets contributed:
Cloudfoundry
Spring source
Cetas

EMC intellectual property and assets continued:
Pivotal labs
Greenplum big data solutions

Thus is this a Pivotal move signaling the entry into new areas that could further disrupt and cloud that status of VMware and EMC as technology suppliers?

Or this clear the clouds a bit to bring clarity to what EMC and VMware are doing along with leveraging various acquisitions?

By clarity, this in theory should help place both EMC and VMware with their customer, partners and prospects as technology (along with associated services) supplier (what some refer to as arms merchants) vs. competing with those entities.

Storage I/O cloud virtual and big data perspectives

IMHO this is pivotal in that it helps to bring clarity for some of the different technologies and business that EMC and VMware has acquired. That clarity will help its own sales teams along with partners avoid creation of revenue prevention teams impacting sales of other solutions.

Likewise there should be good synergy around the various tools, technology and offerings around big data, little data and application development with pivotal. That synergy is a combination of tools, technologies, development techniques. The combination of the tools and new techniques should enable customers to leverage new technologies in new ways, vs. trying to use and deploy in old ways.

Btw, anybody notice Mozy or the lack of that mention keeping in mind that technology was brought back into the EMC backup group fold, while still being operated as a service. Also keep in mind that Mozy was bought by EMC and then transferred to VMware a couple of years ago.

Ok, nuff said (for now).

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Part II: XtremIO, XtremSW and XtremSF EMC flash ssd portfolio redefined

Part one of this two-part post provided a summary of today’s EMC (@EMCflash) announcement around XtremIO and renaming VFCache to XtremSF and associated software as XtremSW.

Storage I/O industry trends and perspectives

Synopsis of announcement

  • Product rollout and selective availability of the new all flash SSD array XtremIO
  • Rename server-side PCIe ssd flash cards from VFCache to XtremSF
  • New XtremSF models including enhanced multi-level cell (eMLC) with larger capacities
  • Rename VFCache caching software to XtremSW (enables cache mode vs. target mode)

Now lets take a closer look at what was announced along with what it means in terms of Industry Trends and Perspectives.

XtremIO  has been in customer beta for some time and now those along with some other early customers are able to acquire the product. In addition, EMC is opening up XtremIO to more prospective customers (Directed Availability) who have requirements or needs that line up with the products target market capabilities.

Storage I/O industry trends and perspectives

What this means is that XtremIO is not being simply put out into the general product population for broad distribution. Instead, it is being put into a controlled release (Directed Availability) to help customers, partners and EMC sales decide where best to use it and thus risk revenue prevention in other areas. The criteria or target opportunity (at least initially) are little-data applications including OLTP, server virtualization (where aggregation can cause aggravation) along with virtual desktop or VDI. In other words, many of the traditional or legacy IOP focused SSD opportunities.

In addition to XtremIO EMC has renamed their VFCache PCIe flash SSD cards (Launched February 2012) to XtremSF along with new models with both SLC and MLC nand flash. Also as part of today’s announcement EMC is renaming the cache software for XtremSF (e.g. VFCache) to be known as XtremSW. Now if that did not prompt the question of if you can now buy XtremSF as a target mode only card without the cache software the answer is yes.

What is XtremIO?

It is a new all flash SSD storage array. XtremIO is a Cluster, grid or collection of nodes called bricks with linear performance scaling providing block based all flash SSD storage. Data services consists of data footprint reduction (DFR) including inline global (across all nodes or bricks) dedupe on 4Kbyte chunks along with thin provisioning. Global dedupe is done on ingest using a combination of flash buffered meta-data (tables, index or dictionary) of what has been seen before along with multi-threaded software to leverage multi-core processors. Using the global dedupe at ingest; only new unique data is saved based on 4 Kbyte chunks.

Performance per EMC scales from one single node to more second node or a fourth node. Note: architecturally more nodes can be added with EMC indicating added models will be available in the future.

In addition to DFR, other data services including writable snapshots, and auto-load balancing when new bricks are added. Note that in a normal running XtremIO, data is automatically spread across the nodes for both performance and resiliency. Data only needs to be moved or load-balanced in the background when new bricks are added. Instant copy snapshots are supported along with writable snapshots. Currently replication is done via external EMC products such as VPLEX or RecoverPoint with statement of directions (SOD) for future enhancements.

Additional attributes of XtremIO include:

  • Each node or brick (X-Brick) has up to 16 (16 was Gen 1 hardware platform, it is now 25 SSD drives)
  • All bricks are involved in IO and storage processing
  • Positioned by EMC as Software Defined (no proprietary hardware)
  • Four x 8Gb Fibre Channel (8GFC) and four x 10Gb Ethernet (iSCSI) per brick
  • Bricks communicate with each other via a separate interconnect network or fabric
  • Bricks have redundant processors (think of as controllers) with multiple sockets and cores
  • 4KB random read IOP’s scale from 250K (one brick), 500K (two bricks) and 1 Million (four bricks). For 4K random write IOPS, the numbers are 100K, 200K and 400K across one, two and four brick configurations with low latency and all data services running (EMC supplied numbers)

In addition to 4K being a commonly used or referred to IO size, it is also the same size as the new industry standard Advanced Format (AF). Today the standard storage block, page or sector size is 512 bytes however AF moves that to a larger 4,096 bytes (e.g. 4KB) to closer align with larger IO sizes. Note that many HDD’s and some SSD’s today support AF and provide 512 byte emulation modes for compatibility.

What is XtremSF?

VFCache is renamed XtremSF with new models using eMLC as companion to existing SLC PCIe  cards and blade server mezzanine cards. EMC is emphasizing performance metrics that matter including IOPs that are relative to customer workloads such as 4K, 8K or larger with mix of reads and writes with low latency. In addition to IOPs with latency, size along with reads or writes for little data, EMC is also showing bandwidth or throughput numbers for big-data and big-bandwidth.

Model
Capacity
Read Transfer GB/sec
Write Transfer GB/sec
Random 4K Read (IOPS)
Random 4K Write (IOPS)

Random 4K Mixed ( IOPS)

Read latency (usec)
Write latency (usec)
2200 (eMLC)
2.2 TB
2.47
1.1
343K
105K
206K
87us
30us
700 (SLC)
700 GB
2.9
1.8
712K
197K
411K
50us
13us
550 (eMLC)
550 GB
1.36
512 MB/s
174K
49K
96K
87us
37us
350 (SLC)
350 GB
2.9
756 MB/s
715K
95K
267K
50us
13us

Sampling of SLC and eMLC XtremSF PCIe SSD cards performance characteristics (via EMC) including latency measured in microseconds). Note performance differences due to some cards being based on SLC and others on eMLC.

Additional attributes, some new and some previously announced include:

  • 8X  PCIe bandwidth lanes for performance
  • No IO impact to applications during garbage collection
  • Supports multi-core processor workloads with parallel design
  • Low CPU overhead by off-loading functions to PCIe card
  • Half-height, half-length PCIe form factor
  • Wear-leveling for nand flash program/erase (P/E) cycle duration
Other storage, server and systems vendors including Cisco, Dell, HP, IBM, NetApp and Oracle offer various PCIe nand flash SSD cards either as target, cache or mixed modes. Manufactures or suppliers of PCIe nand flash SSD cache and target cards include among others FusionIO, Intel, LSI, Micron , OCZ and Virident (who is partnered with Seagate).

What is XtremSW?

Server side flash software (not to be confused with FAST) for using XtremSF as a tier 0 (server-side) ssd cache or target. In target mode the XtremSF functions as a high performance persistent local dedicated direct attached storage (DAS) device. Cache mode enables frequently accessed data to be kept close to the applications off-loading underlying storage systems to be more effectively used. The XtremSW complements back-end storage systems for data protection and persistence along with investment protection of those assets.

Storage I/O industry trends and perspectives

What this all means

SSD is in your future, question is where, when and with what.

Why not just use SSD (DRAM and or nand flash) everywhere?

Keep in mind that in the data center (traditional, virtual or cloud) everything is not the same. Thus the simple answer is that there is not enough of it available at a low enough price point (think closer to Hard Disk Drives (HDD) costs) to fit into customers budget. Sure SSDs provide better performance and productivity benefits, however while there is no such thing as a data or information recession, there are budget constraints.

Another reason why SSD cant simply be used everywhere are physical (and logical) constraints such as amount of memory a server can directly access, or current DDR3 DIMMs (this could change with DDR4 according to Micron) can only address and work with DRAM, PCIe bus physical slot space, operating and hypervisor addressing limits among others.

If SSD (DRAM and or nand flash) were priced were priced low enough (e.g. much closer to HDDs) and available SSD including both DRAM and nand flash (SLC, MLC, eMLC, TLC, etc) along with emerging Phase Change Memory (PCM) are at the convergence of traditional memory and data storage. While some storage (or server) professionals may not agree, storage is an extension of memory and thus part of the traditional server and storage memory hierarchy shown below.

Storage I/O and cache locality of reference

This brings up the locality of reference topic also shown in the following figure where the best IO is the one that does not have to be done. The second best is the one that can be done closest to application to a given level of service. Locality of reference which is important for servers and storage systems including caching refers to how close frequently accessed data is to where it is needed. For some applications this means as much DRAM main memory in a server as possible either clustered, with battery backup or other data persistency protection including onboard HDD or SSD (e.g. towards the top of the hierarchy).

nand flash SSD and storage I/O location options

There are other applications where localized SSD (DRAM or nand flash) are a benefit to compliment main memory or as a persistent cache and target such as PCIe cards or SAS and SATA drives. Further down the stack and for housing larger amounts of storage with performance (reads or writes, random or sequential) along with data services is where all SSD and hybrid (mix of SSD and HDD) fit. Even further down the stack and for a broader segment is where cloud storage services based on SSD such as those from Rackspace (Cloud Block Storage with SSD) and Amazon (provisioned IOPS for EBS) have a play. Lets not forget about SSD in laptop, tablets and workstations, for example I have a Samsung model 830 in my Lenvo X1.

Storage I/O industry trends and perspectives

Some general industry trends include:

  • SSD is like real estate, location can matter, a little can go a long way
  • SSD media options include DRAM and nand flash (SLC, MLC, eMLC, TLC)
  • Portfolios broadening with different products for various needs
  • SSD functionality in servers, appliances, storage systems and cloud services
  • All flash SSD arrays have not killed off all traditional or hybrid storage arrays
  • Focus expanding from Just a Bunch Of SSD (JBOS) to enterprise like functionality
  • Software needs hardware, hardware needs software, the two work better together
  • Comparing meaningful metrics that matter vs. industry marketing metrics

Related items about nand flash, SSD and metrics related themes:

Storage I/O industry trends and perspectives

Some additional thoughts and perspectives

Does this mean traditional storage arrays are now dead?

IMHO, no, there will be some cannibalization of existing storage systems by XtremIO within EMC customers or prospects if not managed, as well as via those from others. Keep in mind that recently EMC announced enhancements to their VMAX including entry-level options for service providers. Some new opportunities opened up will be where traditional all SSD (flash or dram) systems have historically had success.

Traditional SSD and new dedicated SSD systems include Texas Memory Systems (TMS) bought by IBM in 2012, and the recently announced NetApp EF540 (and future FlashRay) along with startups Solidfire, Violin, Whiptail among others. There will be environments where XtremIO may take care of all storage needs for a customer or specific application or piece of it. Then there will be other situations where XtremIO will go-exist with EMC or other vendor’s storage solutions as part of a data infrastructure.

Storage I/O industry trends and perspectives

Who will EMC be competing against with XtremIO?

Certainly the startups or smaller players such as Violin, Whiptail, Purestorage, Solidfire along with IBM/TMS and NetApp EF540 (eventually FlashRay as well) among others.

There will also be some competition with other hybrid storage array vendors that have a mix of HDD and SSD. XtremIO will also compete in some situations on its own vs. other PCIe flash target and cache cards such as FusionIO, however for the most part those will up against XtremSF and XtremSW.

Why the slow or “Directed Availability” rollout?

Why not? By taking a controlled rollout selecting and qualifying customers for XtremIO, EMC gets to manage how the product goes out into production and control how it is used to increase chances of success. Unlike a startup that would be forced to try to put their new technology anywhere, EMC has the luxury of selecting where it goes, not to mention needing to avoid introducing a revenue prevention play for its other products.

Overall, I give an Atta boy and Atta girl to the EMC crew for a Product Defined Announcement (PDA) extending their flash portfolio to complement their different customers and prospects various environment needs. Now watch EMC, NetApp and others step up their flash dance moves to see who will out flash the others in the eXtreme flash games, not to mention emerging software defined marketing moves (SDMM) ;) .

Ok, nuff said.

Cheers Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

XtremIO, XtremSW and XtremSF EMC flash ssd portfolio redefined

EMC (@EMCflash) today announced some new, enhanced, renamed and a rebrand flash solid-state device (SSD) storage portfolio around theme of XtremIO. XtremIO was the startup company with a new all flash SSD storage array that EMC announced they were buying in May 2012. Since that announcement, Project “X” has been used when referring to the product now known as XtremIO (e.g. all flash new storage array).

Synopsis of announcement

  • Product rollout and selective availability of the new all flash SSD array XtremIO
  • Rename server-side PCIe ssd flash cards from VFCache to XtremSF
  • New XtremSF models including enhanced multi-level cell (eMLC) with larger capacities
  • Rename VFCache caching software to XtremSW (enables cache mode vs. target mode)

What was previously announced:

  • Buying the company XtremeIO
  • Productizing  the new all flash array as part of Project “X”
  • It would formally announce the new product in 2013 (which is now)
  • VFCache and later enhancements during 2012.

Storage I/O industry trends and perspectives

Overall, I give an Atta boy and Atta girl to the EMC crew for a Product Defined Announcement (PDA) extending their flash portfolio to complement their different customers and prospects various environment needs. Now let us sit back and watch EMC, NetApp and others step up their flash dance moves to see who will out flash the others in the eXtreme flash games, including software defined storage, software defined data centers, software defined flash, and software defined cache.

Related items about nand flash and metrics related themes:

Read more about XtremIO, XtremSF, XtremSW and flash related items here in part II of this post.

Ok, nuff said (for now).

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

February 2013 Server and StorageIO Update Newsletter

StorageIO News Letter Image
February 2013 News letter

Welcome to the February 2013 edition of the StorageIO Update news letter including a new format and added content.

You can get access to this news letter via various social media venues (some are shown below) in addition to StorageIO web sites and subscriptions.

Click on the following links to view the February 2013 edition as (HTML sent via Email) version, or PDF versions.

Visit the news letter page to view previous editions of the StorageIO Update.

You can subscribe to the news letter by clicking here.

Enjoy this edition of the StorageIO Update news letter, let me know your comments and feedback.

Nuff said for now

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

VMware buys virsto, is it about storage hypervisors?

StorageIO Industry trends and perspectives image

Yesterday VMware announced that it is acquiring the IO performance optimization and acceleration software vendor Virsto for an undisclosed amount.

Some may know Virsto due to their latching and jumping onto the Storage Hypervisor bandwagon as part of storage virtualization and virtual storage. On the other hand, some may know Virsto for their software that plugs into server virtualization Hypervisor  such as VMware and Microsoft Hyper-V. Then there are all of those who either did not or still don’t know of Virsto or their solutions yet they need to learn about it.

Unlike virtual storage arrays (VSAa), or virtual storage appliances, or storage virtualization software that aggregates storage, the Virsto software address the IO performance aggravation caused by aggregation.

Keep in mind that the best IO is the IO that you do not have to do. The second best IO is the one that has the least impact and that is cost effective. A common approach, or preached best practice by some vendors server virtualization and virtual desktop infrastructures (VDI) that result in IO bottlenecks is to throw more SSD or HDD hardware at the problem.

server virtualization aggregation causing aggravation

Turns out that the problem with virtual machines (VMs) is not just aggregation (consolidation) causing aggravation, it’s also the mess of mixed applications and IO profiles. That is where IO optimization and acceleration tools come into play that are plugged into applications, file systems, operating systems, hypervisor’s or storage appliances.

In the case of Virsto (read more about their solution here), their technology plugs into the hypervisor  (e.g. VMware vSphere/ESX or Hyper-V) to group and optimize IO operations.

By using SSD as a persistent cache, tools such as Virsto can help make better use of underlying storage systems including HDD and SSD, while also removing the aggravation as a result of aggregation.

What will be interesting to watch is to see if VMware continues to support other hypervisor’s such as Microsoft Hyper-V or close the technology to VMware only.

It will also be interesting to see how VMware and their parent EMC can leverage Virsto technology to complement virtual SANs as well as VSAs and underlying hardware from VFcache to storage arrays with SSD and SSD appliances as opposed to compete with them.

With the Virsto technology now part of VMware, hopefully there will be less time on talking about storage hypervisor’s and more around server IO optimization and enablement to create broader awareness for the technology.

Congratulations to VMware (and EMC) along with Virsto.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Cloud, virtualization, Storage I/O trends for 2013 and beyond

StorageIO Industry trends and perspectives image

It is still early in 2013, so I can make some cloud, virtualization, storage and IO related predictions, or more aptly, talk about some trends, in addition to those that I made in late 2012, looking forward and back. Common over-riding themes will continue to include convergence (people and technology), valueware, clouds (public, private, hybrid and community) among others.

cloud virtualization storage I/O data center image

Certainly, solid state drives (SSDs) will remain popular, both in terms of industry adoption, and industry deployment. Big-data (and little data) management tools and purpose-build storage systems or solutions continue to be popular, as are those for supporting little data applications. On the cloud storage front, there are many options for various use cases available. Watch for more emphasis on service-level agreements (SLA), service-level objectives (SLO), security, pricing transparency, and tiers of service.

storage I/O rto rpo dcim image

Cloud and object storage will continue to gain in awareness, functionality, and options from various providers in terms of products, solutions, and services. There will be a mix of large-scale solutions and smaller ones, with a mix of open-source and proprietary pieces. Some of these will be for archiving, some for backup or data protection. Others will be for big-data, high-performance computing, or cloud on a local or wide area basis, while others for general file sharing.

Ceph object storage architecture example

Along with cloud and object storage, watch for more options about how those products or services can be accessed using traditional NAS (NFS, CIFS, HDFS and others) along with block, such as iSCSI object API’s, including Amazon S3, REST, HTTP, JSON, XML, iOS and CDMI along with programmatic bindings.

Data protection modernization, including backup/restore, high-availability, business continuity, disaster recovery, archiving, and related technologies for cloud, virtual, and traditional environments will remain popular themes.

cloud and virtual data center image

Expect more Fibre Channel over Ethernet for networking with your servers and storage, PCIe Gen 3 to move data in and out of servers, and Serial-attached SCSI (SAS) as a means of attaching storage to servers or as the back-end storage for larger storage systems and appliances. For those who like to look out over the horizon, keep an eye and ear open for more discussion around PCI gen 3 deployment and gen 4 definitions, not to mention DDR4 and nand flash moving close to the processors.

With VMware buying Virsto, that should keep software defined marketing (SDM) and Storage hypervisors, storage virtualization, virtual storage, virtual storage arrays (VSA’s) active topic themes. Lets also keep in mind for storage space capacity optimization Data footprint reduction (DFR) including archiving, backup and data protection modernization, compression, consolidation, dedupe and data management.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Cloud conversations: Public, Private, Hybrid and Community Clouds? (Part II)

StorageIO Industry trends and perspectives image

This is the second of a two part series, read part I here.

Common community cloud conversation questions include among others:

Who defines the standards for community clouds?
The members or participants, or whoever they hire or get to volunteer to do it.

Who pays for the community cloud?
The members or participants do, think about a co-op or other resource sharing consortium with multi-tenant (shared) capabilities to isolate and keep members along with what they are doing separate.

cloud image

Who are community clouds for, when to use them?
If you cannot justify a private cloud for yourself, or, if you need more resiliency than what can be provided by your site and you know of a peer, partner, member or other with common needs, those could be a fit. Another variation is you are in an industry or agency or district where pooling of resources, yet operating separate has advantages or already being done. These range from medical and healthcare to education along with various small medium businesses (SMBs) that do not want to or cannot use a public facility for various reasons.

What technology is needed for building a community cloud?
Similar to deploying a public or private cloud, you will need various hard products including servers, storage, networking, management software tools for provisioning, orchestration, show back or charge back, multi-tenancy, security and authentication, data protection (backup, bc, dr, ha) along with various middleware and applications.

Storage I/O cloud building block image

What are community clouds used for?
Almost anything, granted there are limits and boundaries based tools, technologies, security and access controls among other constraints. Applications can range from big-data to little-data on all if not most points in between. On the other hand, if they are not safe or secure enough for your needs, then use a private cloud or whatever it is that you are currently using.

What about community cloud security, privacy and compliance regulations?
Those are topics and reasons why like-minded or affected groups might be able to leverage a community cloud. By being like-minded or affected groups, labs, schools, business, entities, agencies, districts, or other organizations that are under common mandates for security, compliance, privacy or other regulations can work together, yet keep their interests separate. What tools or techniques for achieving those goals and objectives would be dependent on those who offer services to those entities now?

data centers, information factories and clouds

Where can you get a community cloud?
Look around using Google or your favorite search tool; also watch the comments section to see how long it takes someone to jump in to say how he or she can help. Also talk with solution providers, business partners and VARs. Note that they may not know the term or phrases per say, so here is what to tell them. Tell them that you would like to deploy a private cloud at some place that will then be used in a multi-tenant way to safely and securely support different members of your consortium.

For those who have been around long enough, you can also just tell them that you want to do something like the co-op or consortium time-sharing type systems from past generations and they may know what you are looking for. If although they look at you with a blank deer in the head-light stare eyes glazed over, just tell them it’s a new lead-edge, software defined new and revolutionary (add some superlatives if you feel inclined) and then they might get excited.  If they still don’t know what to do or help you with, have them get in touch with me and I will explain it to them, or, I’ll put you in touch with those can help.

data centers, information factories and clouds

Where do you put a community cloud?
You could deploy them in your own facility, other member’s locations or both for resiliency. You could also use a safe secure co-lo facility already being used for other purposes.

Do community clouds have organizers?
Perhaps, however they are probably more along the lines of a coordinator, administrator, manager, controller as opposed to a community organizer per say. In other words, do not confuse a community cloud with a cloud community organized, aligned and activated for some particular cause. On the other hand, maybe there is value prop for some cloud activist to be  organized and take up the cause for community clouds in your area of interest ;).

data centers, information factories and clouds

Are community clouds more of a concept vs. a product?
If you have figured out that a community or peer cloud is nothing more than a different way of deploying, using and managing a combination of private, public and hybrid and putting a marketing name on them, congratulations, you are now thinking outside of the box, or outside of the usual cloud conversations.

What about public cloud services for selected audiences such as Amazons GovCloud? On one hand, I guess you could call or think of that as a semi-private public cloud, or a semi-public private cloud, or if you like superlatives an uber gallistic hybrid community cloud.

How you go about building, deploying and managing your community, coop, consortium, and agency, district or peer cloud will be how you leverage various hard and software products. The results of which will be your return on innovation (the new ROI) to address various needs and concerns or also known as valueware. Those results should be able to address or help close gaps and leverage clouds in general as a resource vs. simply as a tool, technology or technique.

Ok, nuff said…

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

In the data center or information factory, not everything is the same

StorageIO Industry trends and perspectives image

Sometimes what should be understood, or that is common sense or that you think everybody should know needs to be stated. After all, there could be somebody who does not know what some assume as common sense or what others know for various reasons. At times, there is simply the need to restate or have a reminder of what should be known.

Storage I/O data center image

Consequently, in the data center or information factory, either traditional, virtual, converged, private, hybrid or public cloud, everything is not the same. When I say not everything is the same, is that different applications with various service level objectives (SLO’s) and service level agreements (SLA’s). These are based on different characteristics from performance, availability, reliability, responsiveness, cost, security, privacy among others. Likewise, there are different size and types of organizations with various requirements from enterprise to SMB, ROBO and SOHO, business or government, education or research.

Various levels of HA, BC and DR

There are also different threat risks for various applications or information services within in an organization, or across different industry sectors. Thus various needs for meeting availability SLA’s, recovery time objectives (RTO’s) and recovery point objectives (RPO’s) for data protection ranging from backup/restore, to high-availability (HA), business continuance (BC), disaster recovery (DR) and archiving. Let us not forget about logical and physical security of information, assets and people, processes and intellectual property.

Storage IO RTO and RPO image

Some data centers or information factories are compute intensive while others are data centric, some are IO or activity intensive with a mix of compute and storage. On the other hand, some data centers such as a communications hub may be network centric with very little data sticking or being stored.

SLA and SLO image

Even within in a data center or information factory, various applications will have different profiles, protection requirements for big data and little data. There can also be a mix of old legacy applications and new systems developed in-house, purchased, open-source based or accessed as a service. The servers and storage may be software defined (a new buzzword that has already jumped the shark), virtualized or operated in a private, hybrid or community cloud if not using a public service.

Here are some related posts tied to everything is not the same:
Optimize Data Storage for Performance and Capacity
Is SSD only for performance?
Cloud conversations: Gaining cloud confidence from insights into AWS outages
Data Center Infrastructure Management (DCIM) and IRM
Saving Money with Green IT: Time To Invest In Information Factories
Everything Is Not Equal in the Datacenter, Part 1
Everything Is Not Equal in the Datacenter, Part 2
Everything Is Not Equal in the Datacenter, Part 3

Storage I/O data center image

Thus, not all things are the same in the data center, or information factories, both those under traditional management paradigms, as well as those supporting public, private, hybrid or community clouds.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

January 2013 Server and StorageIO Update Newsletter

StorageIO News Letter Image
January 2013 News letter

Welcome to the January 2013 edition of the StorageIO Update news letter including a new format and added content.

You can get access to this news letter via various social media venues (some are shown below) in addition to StorageIO web sites and subscriptions.

Click on the following links to view the January 2013 edition as (HTML sent via Email) version, or PDF versions.

Visit the news letter page to view previous editions of the StorageIO Update.

You can subscribe to the news letter by clicking here.

Enjoy this edition of the StorageIO Update news letter, let me know your comments and feedback.

Nuff said for now

Cheers
Gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press), The Green and Virtual Data Center (CRC Press) and Resilient Storage Networks (Elsevier)
twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Putting some VMware ESX storage tips together: (Part II)

In the first part of this post I showed how to use a tip from Dunacn Epping to fake VMware into thinking that a HHDD (Hybrid Hard Disk Drive) was a SSD.

Now lets look at using a tip from Dave Warburton to make an internal SATA HDD into an RDM for one of my Windows-based VMs.

My challenge was that I have a VM with a guest that I wanted to have a Raw Device Mapping (RDM) internal SATA HDD accessible to it, expect the device was an internal SATA device. Given that using the standard tools and reading some of the material available, it would have been easy to give up and quit since the SATA device was not attached to an FC or iSCSI SAN (such as my Iomega IX4 I bought from Amazon.com).

Image of internal RDM with vMware
Image of internal SATA drive being added as a RDM with vClient

Thanks to Dave’s great post that I found, I was able to create a RDM of an internal SATA drive, present it to the existing VM running Windows 7 ultimate and it is now happy, as am I.

Pay close attention to make sure that you get the correct device name for the steps in Dave’s post (link is here).

For the device that I wanted to use, the device name was:

From the ESX command line I found the device I wanted to use which is:

t10.ATA_____ST1500LM0032D9YH148_____Z110S6M5

Then I used the following ESX shell command per Dave’s tip to create an RDM of an internal SATA HDD:

vmkfstools -z /vmfs/devices/disks/ t10.ATA_____ST1500LM0032D9YH148_____Z110S6M5
 /vmfs/volumes/dat1/rdm_ST1500L.vmdk

Then the next steps were to update an existing VM using vSphere client to use the newly created RDM.

Hint, Pay very close attention to your device naming, along with what you name the RDM and where you find it. Also, recommend trying or practicing on a spare or scratch device first, if something is messed up. I practiced on a HDD used for moving files around and after doing the steps in Dave’s post, added the RDM to an existing VM, started the VM and accessed the HDD to verify all was fine (it was). After shutting down the VM, I removed the RDM from it as well as from ESX, and then created the real RDM.

As per Dave’s tip, vSphere Client did not recognize the RDM per say, however telling it to look at existing virtual disks, select browse the data stores, and low and behold, the RDM I was looking for was there. The following shows an example of using vSphere to add the new RDM to one of my existing VMs.

In case you are wondering, why I want to make a non SAN HDD as a RDM vs. doing something else? Simple, the HDD in question is a 1.5TB HDD that has backups on that I want to use as is. The HDD is also bit locker protected and I want the flexibility to remove the device if I have to being accessible via a non-VM based Windows system.


Image of my VMware server with internal RDM and other items

Could I have had accomplished the same thing using a USB attached device accessible to the VM?

Yes, and in fact that is how I do periodic updates to removable media (HDD using Seagate Goflex drives) where I am not as concerned about performance.

While I back up off-site to Rackspace and AWS clouds, I also have a local disk based backup, along with creating periodic full Gold or master off-site copies. The off-site copies are made to removable Seagate Goflex SATA drives using a USB to SATA Goflex cable. I also have the Goflex eSATA to SATA cable that comes in handy to quickly attach a SATA device to anything with an eSATA port including my Lenovo X1.

As a precaution, I used a different HDD that contained data I was not concerned about if something went wrong to test to the process before doing it with the drive containing backup data. Also as a precaution, the data on the backup drive is also backed up to removable media and to my cloud provider.

Thanks again to both Dave and Duncan for their great tips; I hope that you find these and other material on their sites as useful as I do.

Meanwhile, time to get some other things done, as well as continue looking for and finding good work a rounds and tricks to use in my various projects, drop me a note if you see something interesting.

Ok, nuff said for now.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Putting some VMware ESX storage tips together (Part I)

Have you spent time searching the VMware documentation, on-line forums, venues and books to decide how to make a local dedicated direct attached storage (DAS) type device (e.g. SATA or SAS) be Raw Device Mappings (RDM)? Part two of this post looks at how to make an RDM using an internal SATA HDD.

Or how about how to make a Hybrid Hard disk drive (HHDD) that is faster than a regular Hard Disk Drive (HDD) on reads, however more capacity and less cost than a Solid State Device (SSD) actually appear to VMware as a SSD?

Recently I had these and some other questions and spent some time looking around, thus this post highlights some great information I have found for addressing the above VMware challenges and some others.

VMware vExpert image

The SSD solution is via a post I found on fellow VMware vExpert  Duncan Epping’s yellow-brick site which if you are into VMware or server virtualization in general, and particular a fan of high-availability in general or virtual specific, add Duncan’s site to your reading list. Duncan also has some great books to add to your bookshelves including VMware vSphere 5.1 Clustering Deepdive (Volume 1) and VMware vSphere 5 Clustering Technical Deepdive that you can find at Amazon.com.

VMware vSphere 5 Clustering Technical Deepdive book image

Duncan’s post shows how to fake into thinking that a HDD was a SSD for testing or other purposes. Since I have some Seagate Momentus XT HHDDs that combine the capacity of a traditional HDD (and cost) with the read performance closer to a SSD (without the cost or capacity penalty), I was interested in trying Duncan’s tip (here is a link to his tip). Essential Duncan’s tip shows how to use esxcli storage nmp satp and esxcli storage core commands to make a non-SSD look like a SSD.

The commands that were used from the VMware shell per Duncan’s tip:

esxcli storage nmp satp rule add –satp VMW_SATP_LOCAL –device mpx.vmhba0:C0:T1:L0 –option “enable_local enable_ssd”
esxcli storage core claiming reclaim -d mpx.vmhba0:C0:T1:L0
esxcli storage core device list –device=mpx.vmhba0:C0:T1:L0

After all, if the HHDD is actually doing some of the work to boost and thus fool the OS or hypervisor that it is faster than a HDD, why not tell the OS or hypervisor in this case VMware ESX that it is a SSD. So far have not seen nor do I expect to notice anything different in terms of performance as that already occurred going from a 7,200RPM (7.2K) HDD to the HHDD.

If you know how to decide what type of a HDD or SSD a device is by reading its sense code and model number information, you will recognize the circled device as a Seagate Momentus XT HHDD. This particular model is Seagate Momentus XT II 750GB with 8GB SLC nand flash SSD memory integrated inside the 2.5-inch drive device.

Normally the Seagate HHDDs appear to the host operating system or whatever it is attached to as a Momentus 7200 RPM SATA type disk drive. Since there are not special device drivers, controllers, adapters or anything else, essentially the Momentus XT type HHDD are plug and play. After a bit of time they start learning and caching things to boost read performance (read more about boosting read performance including Windows boot testing here).

Image of VMware vSphere vClient storage devices
Screen shot showing Seagate Momentus XT appearing as a SSD

Note that the HHDD (a Seagate Momentus XT II) is a 750GB 2.5” SATA drive that boost read performance with the current firmware. Seagate has hinted that there could be a future firmware version to enable write caching or optimization however, I have waited for a year.

Disclosure: Seagate gave me an evaluation copy of my first HHDD a couple of years ago and I then went on to buy several more from Amazon.com. I have not had a chance to try any Western Digital (WD) HHDDs yet, however I do have some of their HDDs. Perhaps I will hear something from them sometime in the future.

For those who are SSD fans or that actually have them, yes, I know SSD’s are faster all around and that is why I have some including in my Lenovo X1. Thus for write intensive go with a full SSD today if you can afford them as I have with my Lenovo X1 which enables me to save large files faster (less time waiting). However if you want the best of both worlds for lab or other system that is doing more reads vs. writes as well as need as much capacity as possible without breaking the budget, check out the HHDDs.

Thanks for the great tip and information Duncan, in part II of this post, read how to make an RDM using an internal SATA HDD.

 

Ok, nuff said (for now)…

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved

Posted on

Thanks for viewing StorageIO content and top 2012 viewed posts

StorageIO industry trends cloud, virtualization and big data

2012 was a busy year (it was our 7th year in business) along with plenty of activity on StorageIOblog.com as well as on the various syndicate and other sites that pickup our content feed (https://storageioblog.com/RSSfull.xml).

Excluding traditional media venues, columns, articles, web casts and web site visits (StorageIO.com and StorageIO.TV), StorageIO generated content including posts and pod casts have reached over 50,000 views per month (and growing) across StorageIOblog.com and our partner or syndicated sites. Including both public and private, there were about four dozen in-person events and activities not counting attending conferences or vendor briefing sessions, along with plenty of industry commentary. On the twitter front, plenty of activity there as well closing in on 7,000 followers.

Thank you to everyone who have visited the sites where you will find StorageIO generated content, along with industry trends and perspective comments, articles, tips, webinars, live in person events and other activities.

In terms of what was popular on the StorageIOblog.com site, here are the top 20 viewed posts in alphabetical order.

Amazon cloud storage options enhanced with Glacier
Announcing SAS SANs for Dummies book, LSI edition
Are large storage arrays dead at the hands of SSD?
AWS (Amazon) storage gateway, first, second and third impressions
EMC VFCache respinning SSD and intelligent caching
Hard product vs. soft product
How much SSD do you need vs. want?
Oracle, Xsigo, VMware, Nicira, SDN and IOV: IO IO its off to work they go
Is SSD dead? No, however some vendors might be
IT and storage economics 101, supply and demand
More storage and IO metrics that matter
NAD recommends Oracle discontinue certain Exadata performance claims
New Seagate Momentus XT Hybrid drive (SSD and HDD)
PureSystems, something old, something new, something from big blue
Researchers and marketers dont agree on future of nand flash SSD
Should Everything Be Virtualized?
SSD, flash and DRAM, DejaVu or something new?
What is the best kind of IO? The one you do not have to do
Why FC and FCoE vendors get beat up over bandwidth?
Why SSD based arrays and storage appliances can be a good idea

Moving beyond the top twenty read posts on StorageIOblog.com site, the list quickly expands to include more popular posts around clouds, virtualization and data protection modernization (backup/restore, HA, BC, DR, archiving), general IT/ICT industry trends and related themes.

I would like to thank the current StorageIOblog.com site sponsors Solarwinds (management tools including response time monitoring for physical and virtual servers) and Veeam (VMware and Hyper-V virtual server backup and data protection management tools) for their support.

Thanks again to everyone for reading and following these and other posts as well as for your continued support, watch for more content on the above and other related and new topics or themes throughout 2013.

Btw, if you are into Facebook, you can give StorageIO a like at facebook.com/storageio (thanks in advance) along with viewing our newsletter here.

Ok, nuff said.

Cheers gs

Greg Schulz – Author Cloud and Virtual Data Storage Networking (CRC Press, 2011), The Green and Virtual Data Center (CRC Press, 2009), and Resilient Storage Networks (Elsevier, 2004)

twitter @storageio

All Comments, (C) and (TM) belong to their owners/posters, Other content (C) Copyright 2006-2024 Server StorageIO and UnlimitedIO LLC All Rights Reserved