I`ve got a question for you…I´ve got a Nexus 5000 and I´m trying to connect to a Cisco 4948E. The transceivers are:

Nexus 5000: SFP-10G-SR=

Cisco 4948: X2-10GB-SR

That´s possible?

Should I do another configuration?

Thanks a lot.

Actually to be honest with you, one shouldnt care if the FCX series is still in its lifecycle, still supported and runs ok. To be honest with you all I would care is the latency, switching throughput, power consumption values for a ToR switch. ın terms of this, FCX is very promising compared to N2Ks. however I have no idea about the list prices though. BTW, it seems like one could not see the latency values of Nexus 2Ks anywhere in datasheets. In fact first statement I have come across has been in this blog by Brad (he stated 15-20 microseconds)) So latency values play an important role when it comes for two end hosts using the capacity of a 1G interface. With 3microsec latency and 15 microsecond latency value difference the bandwidth that can be use most in a second differs dramatically.

Before the advent of 10GE, iSCSI was viewed as an up and coming storage technology that was largely relegated to SMB environments. But in the last 5 years, iSCSI has developed tremendously and offers a robust set of storage solutions. And with 40GE coming within the next 18 months or so, I think the FC people are damn worried.

iSCSI has advantages over FC in that it runs natively over Ethernet; is routable across WANs without any gateways or protocol encapsulation; can transfer data at 9K Byte frames, not just 2.5K;; and its cheaper.

My thoughts…

I wouldn’t put the FCX in the same category as the Nexus by any stretch of the imagination. That’s an old Foundry switch that was mediocre at best before Brocade bought it. Moreover, in terms of features and architectural implications, it’s just in a separate planet.

The VDX, however, is a totally different story. That is a true Brocade product and it sounds very promising. That is a true data center solution for the next generation data center.

I would seriously look into that. Brocade has an interesting story to tell.

It has a drawback in that it does not have native FC ports for unified fabric applications. It will in about 6 months or so, they say. But to be honest, I dont think FCoE is an architecture I would bet the family farm on now anyway. it’s immature and the enabling technologies are not fully developed either. I wouldn’t touch it with a 10-foot pole for at least another 3 to 5 years, if ever. And there is absolutely no reason to buy into it now anyway. What’s the rush? Traveling down the path of unified fabrics is a long journey and the evolution to FCoE is a slow process and the endgame is permanent. So, if there is indeed value in a tried and proven FCoE architecture 5 years from now, then you may want to consider it at that time. Until then, I wouldn’t worry about it too much.

Just my thoughts on that one….

Thanks

I am a Cisco oriented (but also worked hands on and designed Nortel, Juniper, Enterasys, HP infrastructures ) networking consultant who has been in this area for 7 years.

It seems like you really get angry if people hide their identity so Ive tried my best Just kidding ….

We are on the verge of setting up a new Data Center including almost 100 cabinets.
We recently had a meeting with Cisco. Cisco proposal included 2 N7Ks (One vPC); 14 N5Ks (7 vPCs); and 70 N2Ks.

Today Brocade visited us. They have emphasized the power dissipation of N5K and N2Ks compared to Brocade FCX and VDX series.

Also the same topic here in this blog entry, which is N2K does not support local switching. This really pushes us to rethinking the solution again and again…. How can someone be really sure or design an infrastructure out of a sctrach that no local switching will be needed between two ESX or physical servers in the same cabinet ? Doesnt this design process involves every, NW, Storage, Application guys ?

Thanks in advance.

Couple of interens

If you need storage over ethernet and don’t yet have support for fcoe in your storage or server products take a look at a recent VMware document on Exchange performance using iSCSI and NFS – http://blogs.vmware.com/performance/2009/07/exchange-performs-well-using-fibre-channel-iscsi-and-nfs-on-vsphere.html

The testing used generic Intel nics vs dedicated fiber HBAs and showed iSCSI and NFS ( our interest is iSCSI which unlike FC CAN be port channeled and run over distance greater than FCOE distance limit of 300m) to be very close in performance. If the testing had used hardware iSCSI adapters it likely would have beaten native Fiber Channel.

From your postings … the N5K & FEXes don’t seem to be candidates your environment – a couple of 3750Gs would probably be ideal and they could handle limited ethernet over IP in whatever fashion you needed now.

Can’t I make “the cloud” with traditional switches (4948 for example)? As I’ve said before, my only concern is that I’ll loose A LOT of access ports on Nexus 5000 that could be used by servers with 10GE/FCoE. Again, the only reasons you are giving me to use this design is “management facility” and vPC.

So, putting it in a balance I see more losses than benefits. What’s the big problem on connecting to another device to manage it? Is this really a big loss? It’ll take 5 minutes more to make a service. I don’t think that this is the best benefit of this design. I would really appreciate to have all switches of the same series managed by the same program (cisco DCNM), unfortunally I think we are going the other way. Loosing 20 access interfaces, isn’t a good option for me…

I’m not talking about a huge datacenter. I will only need 10 1G switch for the next years, so “big L2 domain” for me isn’t to much trouble. If you could explain better this problem maybe I change my mind…

I’m expecting that 10G(with FCoE on some cases) will dominate the servers design, so my loss will be huge. I’ll maintain 1Gbps only for backward compatibility (10 years? hehehe).

If Nexux 2000 could be attached directly to an Nexus 7000 (it is not quite difficult to make that works) the deisgn would perfect fit for our needs…

I’ll send this to the list too.

By the way,
Nice blog.
[]‘s

Cheers,
Brad