Networking

  • Virtual Connect overshot the need and created the opportunity for FlexAddress

    Dell's FlexAddress announcement on Tuesday drew this response by Gary Thome of HP.  So what's a poor system admin to do if they want to manage SAN and LAN addresses for their blade systems?  I'd suggest they let their accountants make the decision for them

    Here's the deal.  HP apparently had this elegant old technology from Tandem that used specialized switches to map network IDs to hot-swappable compute modules. They re-introduced this technology as Virtual Connect for their blade servers because they figured it solved the problem of maintaining consistent network IDs when swapping out compute blades. In fact, Virtual Connect works pretty well - all you need to do is buy fault-tolerant pairs of specialized chassis-insertable switches to provide the ID mappings.  That doesn't really force customers to change their network infrastructures, as some would suggest, but it does add a lot of cost to the blade solution.

    Over the years Dell has been criticized for copying the technologies created by other companies.  Brad Anderson, Dell's Senior VP of Business Products said as much last November after Dell announced its acquisition of EqualLogic:

    “It’s fair historically, if you go back a year or so, that you would have thought of Dell as more of a fast follower,” said Brad Anderson, senior vice president of Dell’s business product group. “But we recognize that if we want to solve our customers’ problems and provide leadership, we’re going to need to jump in very early.”  “With Michael coming back, things are a little bit different,” Anderson, said. “Company-wide, we are driving IT simplification very hard. It is our strategy; it is our mission. It’s also driving a cultural change within Dell.”

    In other words, when we see a good idea now, we don't just try to imitate it, but try to figure out how to make it as simple to use and efficient as possible.  And that's what FlexAddress is all about.  HP had done a pretty good job providing a solution, but it was originally designed for mainframe

    Dell engineers

    And one other thing.  HP says that Virtual Connect was designed to enable the system admin to function independently of the network and SAN people.  Oh really?  And how are the proper tie-ins made from the Virtual Connect switching modules to the LAN and SAN switches anyway  - by divination?  C'mon guys - there is no free lunch

    So let's see now.... should I buy one SD card or a pair of expensive switches that cost approximately 10X as much?  Hmmmm.....

  • FlexAddress - Simplifying, Reducing Cost of Blade Management

    Here's a post on new blade technology from Chad Fenner in our sever group....Take it away Chad...

    Having launched the M-Series blades earlier this year, today we’ve introduced Flex Address which is designed as a low cost way to simplify blade server changes - servicing, upgrading or replacing a blade.

    What makes this very different from other blade vendors – is that you don’t have to switch your switch. Unlike some similar implementations from competitors, FlexAddress works with any switch, such as Cisco and Brocade, as well as with any pass through module. 

    It works by locking a server's World Wide Name (WWN for Fibre Channel Fabrics) and Media Access Control (MAC for Ethernet Fabrics) to a blade slot instead of on the blade itself.

    Normally if a server is removed, it loses its storage and ethernet connections, which then have to be re-mapped. That's like being forced to change your phone number because you lost your phone. Point being is that it takes time and effort to get done.

    FlexAddress virtualizes the connection, so if a blade is replaced or upgraded it still maintains the exact same connection. Imagine a boot from SAN implementation – one server could be removed and another inserted and nothing else would need to be done to connect to the same storage LUN!

    Pretty much all network administrators I talk to have been thrilled about this. It saves them time and money. The great thing about Dell's implementation is also how simple it is to implement. All a customer has to do is choose via a single click if they want FlexAddress active in the management software. It's implemented as an SD card on the Chassis Management Controller (CMC).

    NerdBlog, eWeek, and Network World have weighed in…

  • I thought a cluster of tigers was called a “streak”?


    When it comes to clusters, it makes sense that we’d have a few announcements – uh - clustered. And I’m not sorry about the pun. We recently showed the Purdue University team installing its new high-performance computing cluster (HPCC) in just half a day.

    Today, it’s all about Clemson University using a next-generation HPCC to enable a wide range of academic research, from how family migration patterns impact schools and children’s development to the design of wireless communication networks.

    Known as the Palmetto Cluster, it is housed at Clemson’s Information Technology Center and comprises 512 Dell PowerEdge 1950 servers. Currently benchmarked at 31 teraflops (TF), which means it can perform more than 31 trillion operations in one second, it is expected to grow to 100 TF.

    Innovative and cost-effective solutions like the Palmetto Cluster are contributing to Clemson’s steady climb in the competitive U.S. News and World Report rankings for top schools.

    John Mullen, our VP of higher education, recently had the opportunity to visit Clemson and meet with three of the school’s IT leaders: Jim Bottum, CIO and vice provost for Computing and Information Technology; Jim Pepin, CTO; and Jill Gemmill, the executive director  of Cyberinfrastructure Technology Integration. Here's a video of them talking about the cluster and other IT projects underway at Clemson.

    <a href="http://media.dellone2one.com/dell/May2008/Clemson_University.flv"><img src="http://direct2dell.com/photos/videos/images/77653/300x225.aspx" border = "0" width="300" height="225"></a><br /><a href = "http://media.dellone2one.com/dell/May2008/Clemson_University.flv">View Video</a><br />Format: flv<br />Duration: 5:15

    Format: flv
    Duration: 5:15
    Downloads
    WMV  MP4  OGG

    Go Tigers! And FWIW – as an avid golfer myself – best of luck to Clemson sophomore Kyle Stanley who shot six-under-par in a 36-hole qualifier in Columbus, OH on Monday to make it into the field for the 2008 United States Open (June 12-15 at Torrey Pines).

    clip_image001


    clip_image002                             clip_image003

  • Configuring Flow Control on a Cisco 3750 or 2970 Switch

    Flow control is an important network function for iSCSI SANs.  I had a question come up on it at my Storage@work site in a comment and I thought I'd put the same information out here in this blog entry:

    If you have a sample configuration for the iSCSI and Cisco Switch configuration, that would be very helpful. 

    There is a document on our web site listed on this page (under the category of network switching).  You can download after registering.

    http://www.equallogic.com/resources/technicaldocumentsview.aspx?id=364


    There's a lot of stuff in the doc, but the section on flow control has this:

    The following commands shows how to configure Gigabit Ethernet interface 0/1 on switch 1 to
    auto-negotiate the correct Flow Control setting with the device to which it is connected:

    Switch> enable
    Switch# configure terminal
    Switch(config)# interface gigabitethernet1/0/1
    Switch(config-if)# flowcontrol receive desired
    Switch(config-if)# exit
    Switch(config)# exit
    Switch# copy running-config startup-config

    To view or confirm Flow Control status on a port, use the following command:

    Switch# show flowcontrol interface gigabitethernet1/0/1

     

  • Shine on U crazy diamond!

    DevCentral has an great post about the development of HA over the years. And he's a rocker too, which led me to a completely unrelated site that I liked.

    (this post was first made on my Storage @ Work blog)
     

  • Microsoft Management Summit is very hot and Dell is in the buzz

    A Dell employee emailed from the Microsoft Management Summit this morning:

    I am in the opening keynote here at MMS. Being the featured hardware partner for SCCM is awesome. The room is PACKED and attendees are hearing Microsoft talk about how great Dell systems management is.

    Microsoft’s Bob Muglia, MS SVP, highlighted Dell’s preliminary bare metal deployment pack in his keynote. Hubba hubba and hey now.

    Many of our customers use Microsoft’s System Center and Dell’s OpenManage to manage their infrastructure. And who do you think offers the most comprehensive device management through Microsoft’s System Center Suite? (Dell does) And we’re not resting. This week we’re announcing the upcoming availability of the latest Dell Management Packs for Microsoft System Center Operations Manager that will give customers superior monitoring and control of Dell desktops, portables, workstations, rack and tower servers, blades, networked storage devices and even printers.

    Our new plug-ins and our roadmap to integrate Dell Services with Microsoft products means our mutual customers will continue to have industry leading tools to manage their IT infrastructures. All this talk about simplifying IT really means something.

    Thanks for the kind words this morning Bob!

  • Visit the Server Room and Give Blood

    This post also appears here on the Storage@Work blog. 

    The Server Room has to be one of the best forums I've seen.  So if Dell EqualLogic people go there, lets make sure we don't trash it. Put the Name Dell in your sign on to avoid being poachers and don't pimp our stuff.  It's fine to talk about experiences and what we know and all that, but its a tech forum not a drop box for hype - perbole.

    And the rest of you too.  Do your thing and back up your blood type. Somebody might need it for the ultimate restore. 

    <a href="http://blip.tv/file/get/Marcfarley-VisitTheServerRoomAndGiveBlood178.flv"><img src="http://e.static.blip.tv/Marcfarley-VisitTheServerRoomAndGiveBlood574.jpg" border = "0" width="300" height="225"></a><br /><a href = "http://blip.tv/file/get/Marcfarley-VisitTheServerRoomAndGiveBlood178.flv">View Video</a><br />Format: flv<br />Duration: 02:45

    Format: flv
    Duration: 02:45
    Downloads
    WMV  MP4  OGG

  • FCoE is Good, but iSCSI’s Still Better...

    With all the vendor chatter on FCoE at SNW last week, you’d think that it’s poised to become the final protocol for unifying storage and networking. What about iSCSI? Dell’s acquisition of EqualLogic demonstrates our belief that iSCSI is an integral part of the solution for unified fabric in the data center. So, does the emergence of FCoE change that? Not at all.

    FCoE deserves respect as Ethernet’s successor to Fibre Channel (FC). FCoE acknowledges the dominant install base of Fibre Channel and also promises to consolidate LANs and SANs, which is especially valuable for blade server environments. With 10GbE FCoE, customers with 2 and 4 Gbps FC SANs can consolidate their network infrastructures and reduce the number of ports and cables that need managing. Their investment in FC management software and skills is also protected.

    But FCoE needs to be put in perspective. Approximately ½ of the storage capacity shipped each year is still server-resident or external DAS and many SMBs (and enterprise departments) have yet to deploy SANs. For this wave of new SAN deployments, including many application-based deployments where customers already have some FC installed, iSCSI is better. This perspective is gaining traction and has been echoed in recent posts by Matt Baker and Dante Malagrino.  Why?

    · iSCSI is better for virtualization

    · iSCSI is also better for Disaster Recovery because it is built on TCP, is routable and therefore enables less complex, easier to implement DR deployments.

    · FCoE requires new, unique equipment, iSCSI does not:

    · iSCSI runs over any industry standard Ethernet switches. FCoE will require 1) 10GbE DCE-capable switches between the host storage and 2) the addition of an FCoE bridge (or switch with integrated FCoE bridge).

    · iSCSI runs on standard Ethernet adapters. For Windows, FCoE will require customers to buy a 10GbE Converged Network Adapter (CNA) for FCoE and LAN traffic. CNAs are forecast to be higher cost than standard 10Gbps Ethernet Adapters/LOMs and even 10Gbps iSCSI HBAs. I’ll save the discussion about the performance impacts of 10Gbps iSCSI (HBAs, TOEs, SW) vs. FCoE for a later date.

    · Since network bandwidth is rarely the performance bottleneck in storage networks iSCSI can run on less expensive 1 GbE, while FCoE only runs on 10GbE.  For many deployments, this forces customers to pay for bandwidth they don’t need.

    · And finally, FCoE is built on two new and untested technologies (DCE and FCoE). It will take years of testing and qualification to build ultimate acceptance. Storage customers have demonstrated themselves to be among the most conservative in the IT community.

    I agree with the FCoE proponents that maintaining separate networks for storage and networking is complex and inefficient. FCoE is commendable for providing the installed base of FC with an answer to cable sprawl and dedicated infrastructure. But the fact remains; the only technology that allows you to (affordably) unify your storage and network today is iSCSI. The only technology that provides compelling functionality benefits for DR and Virtualization is iSCSI. If you’re deploying a SAN for the first time or even if you are a Fibre Channel shop interested in the network consolidation and cost benefits of FCoE, why wait?

  • More on this FCoE thing

    This FCoE thing is probably going to last for some time as a difference of opinions and perspectives. For those who wished I had kept my mouth shut (or keyboard locked), I was probably a little nastier a year ago with this post on my Storage @ Work blog.  Being a CREATURE OF HABIT,  I responded to last week's news from SNW with my usual open-minded and fair approach. 

    Having said these snide things about FCoE, I am quite sure that it actually will be an excellent solution for lots of FC customers that need a migration path onto something less mortal than Fibre Channel.   The move to Ethernet-based SANs struck me as an obvious evolution a long time ago, after I heard the first FC bigot explain that FC was a channel and Ethernet was a network.  So I guess I shouldn't be too hard on FCoE, because it is a move in the right direction. Being an iSCSI technology bigot, it just seems like a unnecessary, cumbersome step, but to be fair, I tend to see the world through medium-sized business glasses.

    I believe that most of the concerns people have had with iSCSI are based on the implementations that are available. They either don't exploit the iSCSI standard very well or they do not scale up to be a good fit for large-scale data processing.  I'm not buying the protocol arguments for FCoE. At the end of the day, I believe the brute force power of 10Gb Ethernet will be sufficient for iSCSI and that I would rather deal with the rare tuning problems that occur than the crushed-veggie-juice-on-papyrus methods of managing storage in an FC SAN.  I know Greg Ferro (see his comment on Dante's post)  agrees.

    So where the heck do I stand today?  FCoE is as imperfect as FC, but it gets people headed where they need to be, which is Ethernet - and a lot better than FC.  There are going to be situations where taking a leap of faith to iSCSI is going to be a bit like riding a zipline.  You know its safe, but you don't want to attempt too much all at once.

  • Blades @ Dell: Should we listen to customers or competitors?

    Our new M-Series Blades are getting noticed. Maybe it’s because we’re trying very hard to listen. Customers tell us that blading (is that a verb?) a data center isn’t a strategy, but it is a viable technology solution for power, space, cooling management, and performance requirements. More precisely they tell us they want blades that are modular and can be easily re-purposed as their needs change. Competitive blade offerings are designed for specific workloads with a small set of configuration options for memory and processor upgrades, but they don’t address infrastructure changes such as new network interfaces (10 Gig Ethernet) and switch architectures.

    Independent analysts like what they see. Gartner said our “positioning of its blade servers also differentiates it from competitors… Dell supports the premise that blades, racks and towers all demonstrate specific market competencies; it believes that, in the coming years, there will be room for all three. This premise is consistent with Gartner's view of the market.” You can also read what InfoWorld, BladeWatch and The Register said.

    Change is inevitable. The M-Series adapts to it with modular snap-in flexibility down to the switch interconnects. If you need to add more I/O bandwidth or want to upgrade your switches you can add upgrade modules to the M-Series on the fly. That’s the sort of simplicity our customers demand. They also want simple management of blade components. We’ve responded with the most efficient, greenest, lead-free, and fastest-to-deploy blades on the planet. Listen to a podcast describing it in more detail.

    We are trying to do the things that matter most to our customers. It’s our strategy and we are sticking with it.

More Posts Next page »