Russ

Author Archives: Russ

Policing, Shaping, and Performance

Policing traffic and shaping traffic are two completely different things, but it is hard to know, in the wild, what the impact of one or the other will have on a particular traffic flow, or on the performance of applications in general. While the paper under review here, An Internet-Wide Analysis of Traffic Policing, is largely focused on the global ‘net, specifically from a content provider’s perspective, it contains lessons for just about every network operator who needs to manage Quality of Service (QoS) in a sane and meaningful way.

Flach, Tobias, Pavlos Papageorge, Andreas Terzis, Luis Pedrosa, Yuchung Cheng, Tayeb Karim, Ethan Katz-Bassett, and Ramesh Govindan. 2016. “An Internet-Wide Analysis of Traffic Policing.” In Proceedings of the 2016 ACM SIGCOMM Conference, 468–482. SIGCOMM ’16. New York, NY, USA: ACM. https://doi.org/10.1145/2934872.2934873.

Traffic policing involves setting up a queue with a pool of tokens. For some unit of traffic—assume a packet here—received, a token is consumed. When a packet is transmitted, the token is added back to the pool. If the pool is sized correctly, short bursts in the traffic stream will be allowed through, but if the application attempts to establish a session using more bandwidth Continue reading

Reaction: The importance of diversity of sources

If you are like the rest of the world in the way you consume news, you are probably reading this because you followed a link in social media. If this is true, I have a request: set up an RSS reader, and start following technical and social content through feeds rather than exclusively through social networks. Why?

On Wednesday, Digg announced that it will be shutting down Digg Reader on March 26. The RSS reader, for me and likely many others, was a godsend after the 2013 shuttering of Google Reader. The rest of Digg is safe, rest assured, and the site gave no reason for discontinuing Digg Reader, but it’s likely as simple as “that’s not how people consume the internet anymore.”

Don’t get me wrong—I believe social media networks are important. Social media networks are a great place to keep up with people and products, with larger movements discovered by neural networks and put on your RADAR through a news feed.

But social media networks should not be the only place you learn about network engineering—or anything else of importance in your life. It is a bit like when I used to have a collection of Continue reading

What’s wrong with the IETF. And what’s right

I have not counted the IETF’s I have attended; I only know the first RFC on which I’m listed as a co-author was published in 2000, so this must be close to 20 years of interacting with the IETF community, and I’m pretty certain I’ve attended at least two meetings a year across that time, and three meetings a year in most of those years. Across that time, there has never been a time when I have not been told, at least once, “the IETF is broken.” And there has not been a single time I cannot remember agreeing with the sentiment.

So, how is the IETF broken? The trend that bothers me the most right now is the gold rush syndrome. A new technology is brought into the IETF, and if it looks like it might somehow be “important,” there is a “land rush” as people stake out new drafts, find use cases, find corner cases, and work to develop drafts and communities around those drafts. This generally results in a sort of ossification process, where there are clear insiders and outsiders, an entirely new vocabulary is developed, and the drafts fly so fast and furious there is Continue reading

1 61 62 63 64 65 162