The real story behind Cisco’s UCS and “One Giant Switch”!
By Tarry Singh at 16 July, 2009, 1:46 am
HP has some hard words for Cisco and this is a sign that HP is gearing up for a big fight. With VMworld keeping HP locked out of the VMworld organizers who obviously will have all of EMC gear now and Cisco’s boxes, HP is desperately looking for means to crack open Cisco’s UCS box and tell us why it still is a pain.
Cisco obviously does not have all parts of the puzzles which HP already has. So where is Cisco really lacking:
- Cisco does not have a SI like HP’s EDS
- Cisco does not have its storage solution [It needs to rely on EMC, NetApp which could means complexity in prices and implementation]
- A POD like solution which HP has and is currently seeking Google, Microsoft as potential customers — so I hear — to buy into their solutions. Many young Cloud start-ups with own Cloud ambitions, could also see financial gains in purchasing HP’s PODs, they may do that obviously to stay out of Amazon’s or Google’s clutches and focus on the local needs of the consumer industry.
Well, Cisco might not need or want to have these and may have a perfectly sound argument to not have them but one thing is a given: The server racket is a rather complex and involves too many hands. A very complex amalgam of human+machine game where a lot is not in your hands.
Anyways my plan was not to write an analysis — since this is not a comprehensive one anyways — on either Cisco or HP. That stuff will come in our IdeationCloud Pro edition where we’ll do a market analysis and also draw SWOT analysis of competing firms within a couple of weeks.
HP’s answer to Cisco’s giant switch approach:
Issue: Ease of Purchase/Installation
Purchasing a Cisco UCS involves specifying a complex set of blade servers, blade chassis, UCS fabric extenders, UCS fabric interconnects1 not to mention associated network and storage infrastructure. It’s no surprise that this complexity has forced Cisco to create new certifications for UCS design and support.2When a customer adds the Cisco Nexus 1000v for VMware vSphere 4 Enterprise Plus with 24×7- 3 year support it adds an additional $1138.70 per processor.3 This extra cost adds up fast, considering that a rack of 48 two-processor servers would cost an additional $109,315.20 just for the Nexus 1000v software.HP BladeSystem Matrix: One platform. One service engagement. One part number.
Our goal was to make the BladeSystem Matrix simple to deploy and expand so you focus on the job at hand, not dealing with all the moving parts Matrix is a converged infrastructure consisting of pools of compute, storage, virtual fabrics, and power and cooling that can be purchased and delivered as “chunks” of capacity as large as racks at a time.
To learn more:
Issue: Complexity
In Cisco’s one-giant-switch model, all traffic must travel over a physical wire to a physical switch for every operation.4 Consequently, it appears that traffic even between two virtual servers running next to each other on the same physical would have to traverse the network, making an elaborate “hairpin turn” within the physical switch, only to traverse the network again before reaching the other virtual server on the same physical machine. Return traffic (or a “response” from the second virtual machine) would have to do the same. Each of these packet traversals logically accounts for multiple interrupts, data copies and delays for your multi-core processor.In a distributed switch model, the packet never leaves the physical server and enables copy avoidance and high performance I/O to be applied.Issue: Control
The Cisco UCS model gives the network admin unprecedented control of the datacenter.5 This change of control does not take into account the roles and responsibilities of different centers of expertise within the data center. With this view, manageability is stripped from everyone, except the networking administrators.In our opinion, Cisco is attempting to make themselves, through the Cisco network, the control point for everything in the datacenter using an unproven proprietary approach requiring massive investments and difficult migrations by customers.When we at HP developed Virtual Connect, we were really thinking of how to simplify the way customers connect their servers to LANs and SANs. HP’s Virtual Connect makes the server administrator self-sufficient by allowing the complete LAN and SAN connection information and physical connections to be moved with the workload from one server bay to another without impacting the LAN or SAN.
Related posts:
- Will VMware let Cisco in its virtual switch development? Well this blogger seems to guess, that it certainly will....
- VMware on Virtual Switch Security In the article, Wolf said, “one significant issue with virtual...
- Cisco dishes out Rack mountable servers with extensive memory UCS C 250M1 It’s got Slashdotted as well. Cisco VP of Marketing...
- Data Center Commoditization: Did Cisco wake up the sleeping giants? Chris (at El Reg) has written a nice piece,...
- HP+Alcatel 10 Yr Deal: Should Cisco worry or hurry? One analyst said the alliance was a smart move...
- Nexus, FCoE and ESX 4.0: Cool deployment diagram I guess consultants would really get horny looking at...
- Cisco UCS and VMware vSwitch design for vSphere: Another great sample design! Brad’s done it again! Take a look. What I...
- Logicalis to sell Cisco UCS boxes in UK Slough, 10 June 2009 – Logicalis UK announced today that...
No comments yet.