Its US Census time, What about IT Data Centers?

It is that once a decade activity time this year referred to as the US 2010 Census.

With the 2010 census underway, not to mention also time for completing and submitting your income tax returns, if you are in IT, what about measuring, assessing, taking inventory or analyzing your data and data center resources?

US 2010 Cenus formsUS 2010 Cenus forms
Figure 1: IT US 2010 Census forms

Have you recently taken a census of your data, data storage, servers, networks, hardware, software tools, services providers, media, maintenance agreements and licenses not to mention facilities?

Likewise have you figured out what if any taxes in terms of overhead or burden exists in your IT environment or where opportunities to become more optimized and efficient to get an IT resource refund of sorts are possible?

If not, now is a good time to take a census of your IT data center and associated resources in what might also be called an assessment, review, inventory or survey of what you have, how its being used, where and who is using and when along with associated configuration, performance, availability, security, compliance coverage along with costs and energy impact among other items.

IT Data Center Resources
Figure 2: IT Data Center Metrics for Planning and Forecasts

How much storage capacity do you have, how is it allocated along with being used?

What about storage performance, are you meeting response time and QoS objectives?

Lets not forget about availability, that is planned and unplanned downtime, how have your systems been behaving?

From an energy or power and cooling standpoint, what is the consumption along with metrics aligned to productivity and effectiveness. These include IOPS per watt, transactions per watt, videos or email along with web clicks or page views per watt, processor GHz per watt along with data movement bandwidth per watt and capacity stored per watt in a given footprint.

Other items to look into for data centers besides storage include servers, data and I/O networks, hardware, software, tools, services and other supplies along with physical facility with metrics such as PUE. Speaking of optimization, how is your environment doing, that is another advantage of doing a data center census.

For those who have completed and sent in your census material along with your 2009 tax returns, congratulations!

For others in the US who have not done so, now would be a good time to get going on those activities.

Likewise, regardless of what country or region you are in, its always a good time to take a census or inventory of your IT resources instead of waiting every ten years to do so.

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

Virtual Storage and Social Media: What did EMC not Announce?

Synopsis: EMC made a vision statement in a recent multimedia briefing that has a social networking angle as well as storage virtualization, virtual storage, public and private clouds.

Basically EMC provided a vision preview of in a social media networking friendly manner of a vision being refereed to initially as EMC Virtual Storage (aka twitter hash tag #emcvs) which of course sounds similar to a pharmacy chain.

The vision includes stirring up the industry with a new discussion around virtual storage compared to the decade old coverage of storage virtualization.

The underlying theme of this vision is similar to that of virtual serves vs. server virtualization including the ability to move servers around, so to should there be the ability to move data around more freely on a local or global basis and in real or near real time. In other words, breaking the decades long affinity that has existed between data storage and the data that exists on it (Figure 1). Buzzword bingo themes include federated storage, virtual storage, public and private cloud along with global cache coherency among others.


Figure 1: EMC Virtual Storage (EMCVS) Vision

The rest of the story

On Thursday March 11th 2010 Pat Gelsinger (EMC President and COO, Information Infrastructure Products) held an interactive briefing with the global analyst community pertaining to future EMC trajectory or visions. One of the interesting things about this session was that it was not unique to industry analysts nor was it under NDA.

For example, here is a link that if still active, should provide access to the briefing material.

The vision being talked about include those that EMC has talked about in the past such as virtualized data centers, or, putting a spin on the phrase data center virtualization, along with public and private clouds as well as  infrastructure  resource management virtualization (Figure 2):


Figure 2: Public and Private Clouds along with Virtual Data Centers

Figure 2 is a fairly common slide used in many EMC discussions positing public and private clouds along with virtualized data centers.


Figure 3: Tenants of the EMC Virtual Storage (EMCVS) vision


Figure 4: Enabling mobile data, breaking data and storage affinity


Figure 5: Enabling teleporting and virtual storage

Thus setting up the story for the need and benefit of distributed cache coherency, similar to distributed lock management (DLM) used on local and wide area clustered file systems for maintain data integrity.


Figure 6: Leveraging distributed cache coherency

This discussion around distributed cache coherency should ring Dejavu of IBM GDPS (Global Dispersed Parallel Sysplex) for Mainframe, OpenVMS distributed lock management for VAX and Alpha clusters, Oracle RAC, or other parallel and clustered file systems among others. Likewise for those familiar with technology from Yotta Yotta, this should also ring familiar.

However while many are jumping on the Yotta Yotta familiarity bandwagon given comments made by Pat Gelsinger, something that came to mind is what about EMC GDDR? Do not worry if that is an acronym or product you are not up on as an EMC follower as it stands for EMC Geographically Dispersed Disaster (GDDR) solution that is an alternative to IBMs proprietary GDPS. Perhaps there is none, perhaps this is some, however what role if any including lessons learned will come from EMCs experience with GDDR not to mention other clustered file systems?


Figure 7: The EMC vision as presented

One of the interesting things about the vision announcement and perhaps part of floating it out for discussion was a comment made by Pat Gelsinger. That comment was about enabling the wild Wild West for IT, something that perhaps one generation might enjoy, however a notion another would soon forget. Im sure the EMC marke3ting team including their new chief marketing officer (CMO) Jeremy Burton can fine tune with time.
 

More on the social networking and non NDA angle

As is often the case with many other vendors, these types of customer, partner, analyst or media briefings (either online or in person) are under some form of NDA or embargo as they contain forward looking, yet to be announced products, solutions, technologies or other business initiatives. Note, these types of NDA discussions are not typically the same as those that portray or pretend to be NDA in order to sound more important a few days before an announcement that has already been leaked to get extra coverage or what are also known as media embargos.

After some amount of time, usually the information is formerly made public that was covered in advanced briefings, along with additional details. Sometimes material covered under NDA is done so in advanced such that third parties can prepare reports, deep dive analysis or assessment and other content that is made available at announcement or shortly there. The material is often prepared partners, vars, media, analysts, consultants, customers or others outside of the announcing company via different venues ranging from print, online columns, blogs, tweets videos and more.

Lately there has been some confusion in the broader IT as well as other industries as to where and how to classify bloggers, tweeters or other social media practionier. After all, is a blogger an analyst, journalist, free lance writer, advisor, vendor, consultant, customer, var, investor, hobbyist, competitor not to mention how does information get feed to them?

Likewise, NDAs and embargo have joined the list of fodder topics that some do not like for various reasons yet like to complain about for others. There is a time and place for real NDAs that cover and address material, discussions and other information that should not be shared. However all to often NDAs get watered down particularly on the press release games where a vendor or public relations firm (PR) will dangle an announcement briefing a couple of days or perhaps a week or two prior to an announcement under the guise that it not be disclosed prior to formal announcement.

Where these NDAs get tricky is that often they are honored by some and ignored by others, thus, those who honor the agreement get left behind by those who break the story. Personally I do not mind real NDA that are tied to real confidential material, discussion or other information that needs to be kept under wraps for various reasons. However the value or issues of NDA is whole different discussion, for now, lets get back to what EMC did not announce in their recent non-NDA briefing.

Different organizations are addressing social media in various ways, some ignoring it, others embracing it regardless of what it is. EMC is an example of a vendor who has embraced social networking and social media along with traditional means of developing and maintaining relations with the media (media or press relations), customers, partners, vars, consultants, investors (e.g. investor relations) as well as analysts (analyst relations).

For example, EMC works with analysts in traditional ways as they do with the media and other groups, however they also recognize that while some analysts (or media or investors or partners or customers or vars etc) blog and tweet (among other social networking mediums), not all do (as is also the case with media, customers, vars and so forth). Likewise EMC from a social media and networking perspective does not appear to define audiences based on the medium or tool that they use, rather, in a matrix or multi dimensional approach.

That is, an analyst with a blog is a blogger, a var or independent consultant with a blog is a blogger, or a media person including free lance writers, journalist, reporters or publisher with a blog is a blogger as are vars, advisors, partners and competitors with blogs also treated as bloggers.



Some of the 2009 EMC Bloggers Lounge Visitors

Thus at their EMCworld event, admission to the bloggers lounge is as simple and non exclusive as having a blog to join regardless of what your role or usage of a blog happens to be. On the other hand, information is communicated via different channels such as for traditional press via public relations folks, investors through investors relations, analysts via analyst relations, partners and customers through their venues and so forth.

When you think about it, makes sense as after all, EMC sells and attaches storage to mainframes, open systems Windows, UNIX, Linux as well as virtual servers that use different tools, protocols, languages and points of interest. Thus it should not be surprising that their approach to communicating with different audiences leverage various mediums for diverse messages at multiple points in time.

 

What does all of this social media discussion have to do with the March 11 EMC event?

In my opinion, this was an experiment of sorts of EMC to test the waters by floating a new vision to their traditional  pre brief audience in advance of talking with media prior to an actual announcement.

That is, EMC did not announce a new product, technology, initiative, business alliance or customer event, rather a vision and trajectory or signaling what they may be doing in the future.

How this ties to social media and networking is that rather than being an event only for those media, bloggers, tweeters, customers, consultants, vars, free lancers, partners or others who agreed to do so under NDA, EMC used the venue as an advance sounding board of sorts.

That is, by sticking to broad vision vs. propriety and confidential or sensitive topics, the discussion has been put out in advance in the open to stimulate discussion in traditional reports, articles, columns or related venues not to mention in temporal real time via twitter not to mention via blogs and beyond.

Does this mean EMC will be moving away from NDAs anytime soon? I do not think so as there is still very much a need for advanced (and not a couple of weeks prior to announcement) types of discussion around sensitive information. For example with the trajectory or visionary discussion last week by EMC, the short presentation and discussion, limited slides prompt more questions than they address.

Perhaps what we are seeing is a new approach or technique of how organizations can use and bring social networking mediums into the mainstream business process as opposed to being perceived as niche or experimental mediums.

The reason I think it was an experiment is that EMC practices both traditional analyst/media relations along with emerging social media networking relations that includes practioners that span both audiences. For some the social media bloggers and tweeters are a different audience than traditional media, writers, consultants or analysts, that is, they are a separate and unique audience.

Thus, it is in my opinion and like human knees, elbows, feet, hands, ears as well as, well, you get the picture I think that there are many different views or thoughts not to mention interpretations of social media, social networking, blogging, analysts, consultants, advisors, media or press, customers, partners, and so on with diverse roles, functions and needs.

Where this comes back to the topic of last weeks discussion is that of storage virtualization vs. virtual storage. Rest assured in the time since the EMC briefing and certainly in the weeks or months to come, there will be penalty of knees, elbows, hands and other body parts flying and signaling what is a particular view or definition of storage virtualization vs. virtual storage.

Of course, some of these will be more entertaining than others ranging from well rehearsed, in some cases over the past decade or more to new and perhaps even revolutionary ones of what is and what is not storage virtualization vs. virtual storage, let alone cloud vs. cluster vs. grid vs. federated and beyond.

 

Additional Comments and thoughts

In general, I like the trajectory vision EMC is rolling out even if it causes confusion between what is virtual storage vs. storage virtualization, after all, we have been hearing about storage virtualization for over a decade now if not longer. Likewise, there has been plenty of talk about public clouds so it is refreshing to see more discussion and less cloud ware or cloud marketecture and how to actually leverage what you have to adopt private cloud practices.

I suspect that as the EMC competition starts to hear or piece together what they think this vision is or is not, we should also start to hear some interesting stories, spins, counter pitches, debates, twitter fights, blog slams and YouTube videos, all of which also happen to consume more storage.

I also like what EMC is doing with social media and networking as a means or medium for building and maintain relationships as well as for information exchange complimenting traditional means and mediums.  

In other words, EMC is succeeding with social networking by not using it just as another megaphone to talk at or over people, rather, as a means to engage, to get to know, to challenge, to exchange regardless of if you are a so called independent blogger, twitter, analyst, medial, constant, customer, var, investor, partner among others.

If you are not already doing so, here are some EMC folks who actively participate in two way dialogues across different areas with @lendevanna helping to facilitate and leverage the masses of various people and subject matter experts including @chuckhollis @c_weil @cxi @davegraham @gminks @mike_fishman @stevetodd @storageanarchy @storagezilla @Stu and @vcto among many others.

Note that for you non twitter types, the previous are twitter handles (names or addresses) that can be accessed by putting https://twitter.com in place of the @ sign. For example @storageio = https://twitter.com/storageio

 

Additional Comments and thoughts:

Some comments and thoughts among others that I posted via twitter last week during the briefing event:

Here are some twitter comments that I posted last week during the event with hash tag #emcvs:

Is what was presented on the #emcvs #it #storage #virtualization call NDA material = Negative
Is what was presented on the #emcvs #it #storage #virtualization call a product announcement = NOpe
Is what was presented on the #emcvs #it #storage #virtualization call a statement of direction = Kind of
Is what was presented on the #emcvs #it #storage #virtualization call a hint of future functionality = probably
Is what was presented on the #emcvs #it #storage #virtualization call going to be shared with general public = R U reading this?
Is what was presented on the #emcvs #it #storage #virtualization call going to be discussed further = Yup
Is what was presented on the #emcvs #it #storage #virtualization call going to confuse the industry = Maybe
Is what was presented on the #emcvs #it #storage #virtualization call going to confuse customers = Depends on story teller
Is what was presented on the #emcvs #it #storage #virtualization call going to confuse competition = probably
Is what was presented on the #emcvs #it #storage #virtualization call going to provide fodder/fuel for bloggers = Yup
Anything else to add about #emcvs #it #storage #virtualization call today = Stay tuned, watch and listen for more!

Some additional questions and my perspectives on those include:

  • What did EMC announce? Nothing, it was not an announcement; it was a statement of vision.
  • Why did EMC hold a briefing without an NDA and yet nothing was announced? It is my opinion that EMC has a vision that they want to float an idea or direction, thus, sharing a vision to get discussions going without actually announcing a specific product or technology.
  • Is this going to be a repackaged version of the Invista storage virtualization platform? I do not believe so.
  • Is this going to be a repackaged version of the intellectual property (IP) assets that EMC picked up from the defunct startup called Yotta Yotta? Given some references to, along with what some of the themes and discussions center around, it is my guess that there is some Yotta Yotta IP along with other technologies that may be part of any future possible solution.
  • Who or what is YottaYotta? They were a late dot com startup founded in 2000 that went through various incarnations and value propositions with some solutions that shipped. Some of the late era IP included distributed cache coherency and distance enablement of large scale federated storage on a global basis.
  • Can the Yotta Yotta (or here) technology really scale? That remains to be seen, Yotta Yotta had some interesting demos, proof of concept, early adopters and big plans, however they also amounted to Nada Nada, perhaps EMC can make a Lotta Lotta out of it!

 

Other questions are still waiting for answers including among others:

  • Will EMC Virtual Storage (aka emcvs) become a common cure for typical IT infrastructure ailments?
  • Will this restart the debate around the golden rule of virtualization being whoever controls the virtualization controls the gold and thus vendors lock in?
  • Will this be a members only vision where only certain partners can participate?
  • What will other competitors respond with, technology, and marketecture, FUD or something else?
  • What are the specific details of when, where and how the vision is implemented?
  • What will all of this cost, will it work with existing products or is a forklift upgrade needed?
  • Has EMC bitten off more than they can chew or deliver on or is Pat Gelsinger and his crew racing down a mountain and out in front of their skis, or, is this brilliance beyond what we mere mortals can yet comprehend?
  • Can global data cache coherency really be deployed with data integrity on a global and large scale without negatively impacting performance?
  • Can EMC make Lotta Lotta with this vision?

 

Here is what some of the EMC bloggers have had to say so far:

Chuck Hollis aka @chuckhollis had this to say

Stuart Miniman aka @stu had this to say

 

Summing it up for now

Lets see how the rest of the industry responds to this as the vision rolls out and perhaps sooner vs. later becomes technology that gets deployed and used.

Im skeptical until more details are understood, however I also like it and intrigued by it if it can actually jump from Yotta Yotta slide ware to Lotta Lotta deployments.

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 2006-2012 StorageIO and UnlimitedIO All Rights Reserved

I/O Virtualization (IOV) Revisited

Is I/O Virtualization (IOV) a server topic, a network topic, or a storage topic (See previous post)?

Like server virtualization, IOV involves servers, storage, network, operating system, and other infrastructure resource management areas and disciplines. The business and technology value proposition or benefits of converged I/O networks and I/O virtualization are similar to those for server and storage virtualization.

Additional benefits of IOV include:

  • Doing more with what resources (people and technology) already exist or reduce costs
  • Single (or pair for high availability) interconnect for networking and storage I/O
  • Reduction of power, cooling, floor space, and other green efficiency benefits
  • Simplified cabling and reduced complexity for server network and storage interconnects
  • Boosting servers performance to maximize I/O or mezzanine slots
  • reduce I/O and data center bottlenecks
  • Rapid re-deployment to meet changing workload and I/O profiles of virtual servers
  • Scaling I/O capacity to meet high-performance and clustered application needs
  • Leveraging common cabling infrastructure and physical networking facilities

Before going further, lets take a step backwards for a few moments.

To say that I/O and networking demands and requirements are increasing is an understatement. The amount of data being generated, copied, and retained for longer periods of time is elevating the importance of the role of data storage and infrastructure resource management (IRM). Networking and input/output (I/O) connectivity technologies (figure 1) tie facilities, servers, storage tools for measurement and management, and best practices on a local and wide area basis to enable an environmentally and economically friendly data center.

TIERED ACCESS FOR SERVERS AND STORAGE
There is an old saying that the best I/O, whether local or remote, is an I/O that does not have to occur. I/O is an essential activity for computers of all shapes, sizes, and focus to read and write data in and out of memory (including external storage) and to communicate with other computers and networking devices. This includes communicating on a local and wide area basis for access to or over Internet, cloud, XaaS, or managed services providers such as shown in figure 1.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 1 The Big Picture: Data Center I/O and Networking

The challenge of I/O is that some form of connectivity (logical and physical), along with associated software is required along with time delays while waiting for reads and writes to occur. I/O operations that are closest to the CPU or main processor should be the fastest and occur most frequently for access to main memory using internal local CPU to memory interconnects. In other words, fast servers or processors need fast I/O, either in terms of low latency, I/O operations along with bandwidth capabilities.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 2 Tiered I/O and Networking Access

Moving out and away from the main processor, I/O remains fairly fast with distance but is more flexible and cost effective. An example is the PCIe bus and I/O interconnect shown in Figure 2, which is slower than processor-to-memory interconnects but is still able to support attachment of various device adapters with very good performance in a cost effective manner.

Farther from the main CPU or processor, various networking and I/O adapters can attach to PCIe, PCIx, or PCI interconnects for backward compatibility to support various distances, speeds, types of devices, and cost factors.

In general, the faster a processor or server is, the more prone to a performance impact it will be when it has to wait for slower I/O operations.

Consequently, faster servers need better-performing I/O connectivity and networks. Better performing means lower latency, more IOPS, and improved bandwidth to meet application profiles and types of operations.

Peripheral Component Interconnect (PCI)
Having established that computers need to perform some form of I/O to various devices, at the heart of many I/O and networking connectivity solutions is the Peripheral Component Interconnect (PCI) interface. PCI is an industry standard that specifies the chipsets used to communicate between CPUs and memory and the outside world of I/O and networking device peripherals.

Figure 3 shows an example of multiple servers or blades each with dedicated Fibre Channel (FC) and Ethernet adapters (there could be two or more for redundancy). Simply put the more servers and devices to attach to, the more adapters, cabling and complexity particularly for blade servers and dense rack mount systems.
PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 3 Dedicated PCI adapters for I/O and networking devices

Figure 4 shows an example of a PCI implementation including various components such as bridges, adapter slots, and adapter types. PCIe leverages multiple serial unidirectional point to point links, known as lanes, in contrast to traditional PCI, which used a parallel bus design.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)

Figure 4 PCI IOV Single Root Configuration Example

In traditional PCI, bus width varied from 32 to 64 bits; in PCIe, the number of lanes combined with PCIe version and signaling rate determine performance. PCIe interfaces can have 1, 2, 4, 8, 16, or 32 lanes for data movement, depending on card or adapter format and form factor. For example, PCI and PCIx performance can be up to 528 MB per second with a 64 bit, 66 MHz signaling rate, and PCIe is capable of over 4 GB (e.g., 32 Gbit) in each direction using 16 lanes for high-end servers.

The importance of PCIe and its predecessors is a shift from multiple vendors’ different proprietary interconnects for attaching peripherals to servers. For the most part, vendors have shifted to supporting PCIe or early generations of PCI in some form, ranging from native internal on laptops and workstations to I/O, networking, and peripheral slots on larger servers.

The most current version of PCI, as defined by the PCI Special Interest Group (PCISIG), is PCI Express (PCIe). Backwards compatibility exists by bridging previous generations, including PCIx and PCI, off a native PCIe bus or, in the past, bridging a PCIe bus to a PCIx native implementation. Beyond speed and bus width differences for the various generations and implementations, PCI adapters also are available in several form factors and applications.

Traditional PCI was generally limited to a main processor or was internal to a single computer, but current generations of PCI Express (PCIe) include support for PCI Special Interest Group (PCI) I/O virtualization (IOV), enabling the PCI bus to be extended to distances of a few feet. Compared to local area networking, storage interconnects, and other I/O connectivity technologies, a few feet is very short distance, but compared to the previous limit of a few inches, extended PCIe provides the ability for improved sharing of I/O and networking interconnects.

I/O VIRTUALIZATION(IOV)
On a traditional physical server, the operating system sees one or more instances of Fibre Channel and Ethernet adapters even if only a single physical adapter, such as an InfiniBand HCA, is installed in a PCI or PCIe slot. In the case of a virtualized server for example, Microsoft HyperV or VMware ESX/vSphere the hypervisor will be able to see and share a single physical adapter, or multiple adapters, for redundancy and performance to guest operating systems. The guest systems see what appears to be a standard SAS, FC or Ethernet adapter or NIC using standard plug-and-play drivers.

Virtual HBA or virtual network interface cards (NICs) and switches are, as their names imply, virtual representations of a physical HBA or NIC, similar to how a virtual machine emulates a physical machine with a virtual server. With a virtual HBA or NIC, physical NIC resources are carved up and allocated as virtual machines, but instead of hosting a guest operating system like Windows, UNIX, or Linux, a SAS or FC HBA, FCoE converged network adapter (CNA) or Ethernet NIC is presented.

In addition to virtual or software-based NICs, adapters, and switches found in server virtualization implementations, virtual LAN (VLAN), virtual SAN (VSAN), and virtual private network (VPN) are tools for providing abstraction and isolation or segmentation of physical resources. Using emulation and abstraction capabilities, various segments or sub networks can be physically connected yet logically isolated for management, performance, and security purposes. Some form of routing or gateway functionality enables various network segments or virtual networks to communicate with each other when appropriate security is met.

PCI-SIG IOV
PCI SIG IOV consists of a PCIe bridge attached to a PCI root complex along with an attachment to a separate PCI enclosure (Figure 5). Other components and facilities include address translation service (ATS), single-root IOV (SR IOV), and multiroot IOV (MR IOV). ATS enables performance to be optimized between an I/O device and a servers I/O memory management. Single root, SR IOV enables multiple guest operating systems to access a single I/O device simultaneously, without having to rely on a hypervisor for a virtual HBA or NIC.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)

Figure 5 PCI SIG IOV

The benefit is that physical adapter cards, located in a physically separate enclosure, can be shared within a single physical server without having to incur any potential I/O overhead via virtualization software infrastructure. MR IOV is the next step, enabling a PCIe or SR IOV device to be accessed through a shared PCIe fabric across different physically separated servers and PCIe adapter enclosures. The benefit is increased sharing of physical adapters across multiple servers and operating systems not to mention simplified cabling, reduced complexity and resource utilization.

PCI SIG IOV (C) 2009 The Green and Virtual Data Center (CRC)
Figure 6 PCI SIG MR IOV

Figure 6 shows an example of a PCIe switched environment, where two physically separate servers or blade servers attach to an external PCIe enclosure or card cage for attachment to PCIe, PCIx, or PCI devices. Instead of the adapter cards physically plugging into each server, a high performance short-distance cable connects the servers PCI root complex via a PCIe bridge port to a PCIe bridge port in the enclosure device.

In figure 6, either SR IOV or MR IOV can take place, depending on specific PCIe firmware, server hardware, operating system, devices, and associated drivers and management software. For a SR IOV example, each server has access to some number of dedicated adapters in the external card cage, for example, InfiniBand, Fibre Channel, Ethernet, or Fibre Channel over Ethernet (FCoE) and converged networking adapters (CNA) also known as HBAs. SR IOV implementations do not allow different physical servers to share adapter cards. MR IOV builds on SR IOV by enabling multiple physical servers to access and share PCI devices such as HBAs and NICs safely with transparency.

The primary benefit of PCI IOV is to improve utilization of PCI devices, including adapters or mezzanine cards, as well as to enable performance and availability for slot-constrained and physical footprint or form factor-challenged servers. Caveats of PCI IOV are distance limitations and the need for hardware, firmware, operating system, and management software support to enable safe and transparent sharing of PCI devices. Examples of PCIe IOV vendors include Aprius, NextIO and Virtensys among others.

InfiniBand IOV
InfiniBand based IOV solutions are an alternative to Ethernet-based solutions. Essentially, InfiniBand approaches are similar, if not identical, to converged Ethernet approaches including FCoE, with the difference being InfiniBand as the network transport. InfiniBand HCAs with special firmware are installed into servers that then see a Fibre Channel HBA and Ethernet NIC from a single physical adapter. The InfiniBand HCA also attaches to a switch or director that in turn attaches to Fibre Channel SAN or Ethernet LAN networks.

The value of InfiniBand converged networks are that they exist today, and they can be used for consolidation as well as to boost performance and availability. InfiniBand IOV also provides an alternative for those who do not choose to deploy Ethernet.

From a power, cooling, floor-space or footprint standpoint, converged networks can be used for consolidation to reduce the total number of adapters and the associated power and cooling. In addition to removing unneeded adapters without loss of functionality, converged networks also free up or allow a reduction in the amount of cabling, which can improve airflow for cooling, resulting in additional energy efficiency. An example of a vendor using InfiniBand as a platform for I/O virtualization is Xsigo.

General takeaway points include the following:

  • Minimize the impact of I/O delays to applications, servers, storage, and networks
  • Do more with what you have, including improving utilization and performance
  • Consider latency, effective bandwidth, and availability in addition to cost
  • Apply the appropriate type and tiered I/O and networking to the task at hand
  • I/O operations and connectivity are being virtualized to simplify management
  • Convergence of networking transports and protocols continues to evolve
  • PCIe IOV is complimentary to converged networking including FCoE

Moving forward, a revolutionary new technology may emerge that finally eliminates the need for I/O operations. However until that time, or at least for the foreseeable future, several things can be done to minimize the impacts of I/O for local and remote networking as well as to simplify connectivity.

Learn more about IOV, converged networks, LAN, SAN, MAN and WAN related topics in Chapter 9 (Networking with your servers and storage) of The Green and Virtual Data Center (CRC) as well as in Resilient Storage Networks: Designing Flexible Scalable Data Infrastructures (Elsevier).

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

SMB capacity planning; Focusing on energy conservation

Storage I/O trends

Here’s a link to a new tip I wrote that is posted over at SearchSMBStorage on Capacity Planning and energy conservation.

Here are some added links to other recent tips I wrote and posted at a SearchSMBStorage:

Improve your storage energy efficiency

Data protection for virtual server environments

Data footprint reduction for SMBs

Is clustered NAS for SMBs?

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

StorageIO Spring Keynote and Speaking tour V2.008

Several new keynote and speaking engagements involving myself have been added to the StorageIO events page including among others:

April 8th, 2008 – SNW Orlando FL
Beyond Green-Wash:
IT Data Center Power, Cooling, Floor Space and Environmental (PCFE) Topics and Trends V2.008

This talk will move past what are the issues and reasons for going green and get right to the point of what you can do today leveraging various technologies, techniques and best practices to address PCFE and green environmental issues including EHS, low power and economic sustainment in an environmental friendly manner as well as what to include in a long term green strategy for your data center.

Chicago, May 13th-15th – StorageDecisions
Clustered Storage:
From SMB, to Scientific, to Social Networking and Web 2.0

The growth of structured and unstructured data continues at an explosive rate in most environments resulting in a constantly expanding data footprint requiring data and storage management resources. Similarly, the relative ease of use of NFS and Windows CIFS file sharing based storage, also known as Network Attached Storage (NAS), has led to a proliferation of NAS and Windows file servers which are not all that different from how the ease of use of personal computers (PCs) resulted in desktop and server sprawl. With the focus of many IT organizations today to do more with less, or, do more with what you have, clustered storage and clustered file serving have become a popular option to support modular, scalable and flexible growth. Clustered storage including clustered file serving, grid and web 2.0 based storage solutions are no longer confined to the specific high performance scientific applications they are commonly associated. Clustered storage serving is commonly being deployed to support a wide diversity of applications including commercial, entertainment or media, Web 2.0 and social networking along with grid, cloud and traditional scientific needs.

This session takes a look at among other topics:
? Look at what different clustered storage vendors are claiming and how their solutions differ
? Fact vs. Fiction, Myths and Realties of clustered storage
o Grid vs. Clusters, Cluster vs. Grid, what?s the differences
o Clustered storage is only for ultra large environments like Google
o Clustered file serving is only for high performance (HPC) environments
o SMBs and bulk storage applications can not benefit from clustered storage
? What are the caveats to be aware of when deploying clustered storage?
? What are some emerging trends and solutions to keep an eye on for clustered storage
? What are some questions that some vendors do not want you to ask about their solutions!

Green and Environmental Friendly Storage:
Practical Ways to Achieve Energy Efficiency

Green is in-and every storage vendor out there has a green story to tell. Despite the vendor and industry hyperbole about the environmental benefits of their products, there are still no standard metrics by which to measure and compare power consumption or energy efficiency claims. The challenge is sorting out and closing the gap between vendor green messaging and IT data center issues including power, cooling, floor space and other environmental topics including RoHS and e-waste disposal. This session looks at several practical techniques and technologies that you can leverage today to achieve an energy efficiency data center to sustain business growth in an economical and ecological friendly manner.

Topics that will be covered include among others:
? How truthful are vendor claims and what is ?Green wash?
? Facts and Fiction, Myths and Realities:
o Storage is cheaper to buy than to power
o Power avoidance vs. energy efficiency
o Are Solid State Devices (SSD) the silver bullet?
o Dedupe vs. Archive vs. Compression vs. Consolidation
? What?s real and achievable today, what are your options?
? Measuring and determining energy efficiency with emerging metrics
? How to do more with what you have and avoid forklift upgrades
? Who is the ?Greenest of them all? and where to learn more

I will also be keynoting at several TechTarget seminar series events around the U.S. including
StorageIO events page located here.

Cheers
GS

Chargeback for storage

TechTarget SearchStorage recently put out a piece on chargeback for storage that includes some commentary by myself on the topic including some common myths about chargeback of what it is and how it is done.

A common misperception is that chargeback requires actual invoicing and monetizing of IT resource use including servers, storage and networks where in some cases, charge back is not as much about generating invoices as it is for accounting and resource usage tracking.

Granted, if you are in a services oriented environment, rest assured there is monetization needing to take place, however, informational charge back initiatives are also useful for budgeting, planning and awareness of IT services and usage.Have a read here.

Cheers
GS