Recently I made the observation that Fixed switches continue to outpace Chassis switches in both power and space efficiency. Simply put, with Fixed switches you can cram more ports into fewer RUs, and each port will draw less power when compared to Chassis switches. Those are the indisputable facts. A common objection when these facts are [...]
Comparing fabric efficiencies of Fixed vs Chassis based designs, non-blocking
May 17, 2012 By 7 Comments
Comparing efficiencies of Fixed vs Chassis switches
May 10, 2012 By 20 Comments
When building a fabric for a cluster of servers and storage in the data center, how should you architect the network? There are several ways to approach this. The architecture you choose probably depends on your preconceived notions of what a network should look like and addressing the things that you care about. For example, [...]
A network that Doesn’t Suck for cloud and Big Data: Interop 2012 session teaser
April 30, 2012 By 3 Comments
Considering 10GE Hadoop clusters and the network
March 26, 2012 By 4 Comments
Does 10GE Hadoop make any sense? And if so, how might you design the cluster? Let’s discuss some rationale for and against 10gig Hadoop and then look at some potential network setups for 10G clusters. If you need a quick into or refresher, read this post on the basics of Hadoop clusters and the network, [...]
Construct a Leaf Spine design with 40G or 10G? An observation in scaling the fabric.
January 25, 2012 By 33 Comments
Should you construct a Leaf/Spine fabric with 10G or 40G? In this post I’ll make the simple observation that using 10G interfaces in your leaf/spine fabric scales to more servers than using 40G interfaces, all with the same hardware, bandwidth, and oversubscription. Let’s suppose you’ve decided to build a Leaf/Spine fabric for your data center [...]
On optimizing traffic for network virtualization
December 22, 2011 By 13 Comments
The era of network virtualization and software overlays is coming (read: VXLAN, OpenFlow, SDN, etc.) and with it the role of the physical network and what we define as “the network”, is all about to change. How does this change the way application flows map to traffic on the network and servers? How does this change [...]
Network Virtualization is like a big virtual chassis
October 12, 2011 By 20 Comments
This is something I’ve been chewing on for a while now and here’s my first rough attempt at writing it down: Network Virtualization is the new chassis switch, only much bigger. (and a lot less proprietary) The x86 server is the new Linecard The network switch is the new ASIC VXLAN (or NVGRE) is the new [...]
Understanding Hadoop Clusters and the Network
September 10, 2011 By 25 Comments
This article is Part 1 in series that will take a closer look at the architecture and methods of a Hadoop cluster, and how it relates to the network and server infrastructure. The content presented here is largely based on academic work and conversations I’ve had with customers running real production clusters. If you run production [...]
On “Why TRILL wont work for the data center”
June 15, 2011 By 26 Comments
Today I came across “Why TRILL won’t work for data center network architecture” by Anjan Venkatramani of Juniper. Anjan’s article makes a few myopic and flawed arguments in slamming TRILL, setting up a sale for QFabric. The stated problems with TRILL include FCoE, L3 multi-pathing, VLAN scale, and large failure domains. The one and only Ivan Pepelnjak has already tackled the [...]
Recent Comments