In this blog post I’ll make an attempt to summarise Overlay Networking in a couple of paragraphs to act as reference for upcoming blog posts that discuss the nature of Tunnel Fabrics in Physical Network environments. It also has pictures.
In the process of building cloud networks over the last 3 months, it has become clear that a lot of people have problems accepting that Overlay Networking is a viable technology. The current1 version of the future in Software Defined Networking (SDN) in the Data Centre will use overlay networks using technologies like VXLAN, NVGRE […]
I’ve been quiet for some time because I’ve been working on a couple of eBooks. Today, I pleased to publicly announce my first ever eBook called “The Arse First Method of Technical Blogging”.. I wrote this book to answer the question that I get asked a lot – “How do you write so many blog posts?”. So I started to write a blog post until I realised it would take too long. A year later I have taken it far enough to release an eBook.
I woke up at three o’clock this morning with a thought racing around my brain – am I building a Hosting Cathedral or Cloud Bazaar ? My data centre is like a cathedral – regimented rows of seats, full of disciplined and controlled resources all looking towards the technical priests for inspiration and direction. Each […]
I was reviewing some presentations on monitoring and visual charts from the monitorama conference. This caught my eye for a 3D representation for unicast, Multicast and Broadcast traffic (using Barycentric co-ordinates if I understand correctly). Barycentric representation uses 3D-coordinate system. Presentation can be found here Monitoring for Humans Can’t remember how I found this link Monitoring […]
Join our webinar about the nCloudX controller abstracts commonly deployed network routers, switches, firewalls and application delivery controllers, along with traditional tools like BGP, OSPF, MPLS and VRFs. Cloud operators and as well as cloud consumers can provision the network using predefined templates that remove the need to individually configure the underlying network hardware.
Looking at using SDN & OpenFlow to perform a firewall migration on a rule by rule basis instead of using any of the other nasty, crufty hacks. Very useful when you want to find an easier and low risk way to get rid of those pesky CheckPoint firewall products.
Google has decided to end their Reader product that provided an interface to RSS. On the whole, it’s a good thing even though I’m unhappy that I have to change. I’m confident that something better will arrive so I will wait peacefully & patiently for the Internet to provide. Take a deep breath nerds. The […]
Comparing the pricing strategies of Cloud Services to Project Budgets isn’t that hard. Lets cover that here. A common theme in cloud based service is “per user” pricing. A service to provide a VPN authentication service like Pertino looks quite attractive at USD$10 per user. Most engineers will intuitively know that “per user” pricing is always more expensive than “own it yourself” solution but it can be hard to justify.
I was going to call this article “Ethernet Switches for Virtualisation Engineers” but, really, everyone should have some understanding of the internals of an Ethernet switch. But particularly I want to focus on how multicast and broadcasts are handled in a high speed, low latency environment like a Data Centre Network.
It’s vital to understand that latency is critical to your application performance. It is common for a single transaction to take hundreds of round trips so a small increase in latency on each round trip has a large impact on the perceived performance. The client will send a chunk of data and wait for acknowledgement. Even setting up the TCP connection takes a few round trip – remember that TCP sessions are setup, and each data transfer is confirmed.
A modern network switch will have latency around 10 microseconds. The Cisco Nexus 7000 is about 8 microseconds & Brocade VDX 8770 claims less than 4 microseconds. There are many reasons why a switch can be faster or slower but I’ll look at a specific example
Remember, the latency interval is the time taken to receive a packet, decode the address, lookup the forwarding table, switch the packet (and copy it if needed) and transmit out of an Ethernet interface. That’s really fast processing. How does an Ethernet switch do this ?