L3 routing to to the host. An idea whose time has come, again.
For the last 20 years, L2 tree-based network topologies meant that the only practical design methodology was to buy large, vertically scaled switch chassis for the core of the data centre. This limitation was largely due to the tree-structure forced on LAN networking by Spanning Tree Protocol. For every new device at point Access/1 we […]
Facebook has telling people more about it’s in-house designed and developed whitebox Ethernet switching based on Broadcom silicon (not sure if it’s Trident2 or Arad), their own Linux distribution and OpenCompute standards.
Overlay networking has been around for a year or so now and the ideas behind it are well established. It was about 3/4 weeks ago while researching VTEP functionality in Dell and Arista switches that I realised I could build manually configured tunnels with VXLAN and get the same results as an EoMPLS x-connect with almost zero effort. More importantly, I don’t have to pay for expensive hardware that has MPLS functions or pay again for software licenses to upgrade with MPLS features.
Ivan Peplnjak posts an outstanding summary of the myriad networking challenges when designing a dual Data Centre . Complete with cynical commentary and live action diagrams, he explains the problem and some suggestions for the solution. Recommended for everyone! We have a network with two data centers (connected with a DCI link). How could we […]
I attended the Brocade Analyst and Tech Day last week as a guest of Brocade where I got to learn more about product, technology and strategy. In particular, the event was led by the launch of the Brocade VDX 8770.
TL:DR version: I have a better understanding of Brocade’s market strategy, insight into the technology and believe that Brocade has a a good product here. The proof will be in the delivery, and whether Brocade can let go of it’s storage legacy (FibreChannel) and properly commit to Ethernet. They will need to convince networking professionals that their product managers understand the market and requirements to get them to switch to Brocade. At this time, I think Brocade has a chance of making that happen based on the emphasis of VCS Fabric and Automation.
Where I’m less comfortable is that Brocade will rely on external parties to deliver the software automation – that’s a strategy that has NOT worked in the last 20 years. There is no reason to believe this anything has changed.
Contains pictures and words.
Short version – I’d like you to read just these if nothing else.
- A data centre uses a lot of electricity. It’s dangerous.
- Just in case you didn’t pay attention – Electricity is really dangerous. Right, can we move on ?
- You should be scared of being electrocuted. That will keep you safe.
- When electrocution happens, the muscles in your limbs contract. This causes arms and hands to wrap around or clench objects.
- Someone who is being electrocuted can’t let go because of this
- If you touch a person being electrocuted, you will get an electric shock too, and may also be injured.
- The BEST thing to do is to turn the power off.
- Know where the power kill switch is for Data Centre. Or at least the breaker for the area that you are in.
- Don’t work in the Data Centre alone.
- Learn resuscitation. People who have been electrocuted are likely to have breathing problems and heart failure.
People shouldn’t die at work. Think seriously about going home everyday and what you can do to make that happen.
I’ve talked bit about the problems of using Category 6 copper cabling in the data centre. The sheer size and weight of the cable is a serious problem. Here are some photos showing the comparison of Category 5 and Category 6 cable bundles.
In this post, I’m looking at network designs with ECMP cores using TRILL or SPB, I’m realising that STP is equally improved in terms of risk and performance by reducing the STP domain size which leads to better stability, reduced risk and impact mitigation
I’m responding to Brad Hedlund’s post “On optimizing traffic for network virtualization” where he seems to missed a key point. It’s about cost of ownership in terms of ability to troubleshoot.