Notes on Network Signal Congestion Control
“The test of first-rate intelligence is the ability to hold two opposing ideas in mind at the same time and still retain the ability to function.” - F. Scott Fitzgerald
Dip Singh
Latest posts
Notes on Active Queue Management Techniques
“When you can measure what you are speaking about, and express it in numbers, you know something about it” - Lord Kelvin
Notes on Flow Control for High Speed Networks
“In theory, there is no difference between theory and practice. In practice, there is.” - Jan L. A. van de Snepscheut
Packet Classification for High Speed Packet Processing
“We are drowning in information but starved for knowledge.” - John Naisbitt
Hashing Strategies for Packet Processing
“It is not easy to become an educated person.” - Richard Hamming
Transistor Advances - From Planar MOSFETs to CFET Stacks
“No exponential is forever, but we can delay ‘forever’.” — Gordon Moore
Network Traffic Modeling Approaches
The greatest value of a picture is when it forces us to notice what we never expected to see. - John Tukey
Lagrangian Methods in Constrained Optimization
An expert is a person who has made all the mistakes that can be made in a very narrow field. - Niles Bohr
Quantile Regression
The Median Isn’t the Message - Stephen Jay Gould
Optimal and Heuristic Approaches to Disjoint Path Routing
Two roads diverged in a wood, and I–I took the one less traveled by, And that has made all the difference.- Robert Frost
Balancing MMLU With The Shortest Path Cost Constraints
MMLU in Network Flow Optimization
In a previous post, I discussed how Maximum Flow problems can be used for network optimization. We focused on a scenario where demands were already routed in the network, and our objective was to determine the maximum demand that could be handled between a given source and a destination metro. We solved this problem by calculating the residual bandwidth for the graph, creating fake demand nodes…
Keeping the Pipe Just Full
In this post, I will be discussing a paper published by the Internet pioneer Leonard Kleinrock, titled “Keep the Pipe Just Full, But No Fuller”. The paper’s conclusion is that it is best to keep the internet “pipe” full, without overloading it. This idea is a take on Einstein’s famous quote, “Make everything as simple as possible, but not simpler.”
Flow Distribution Across ECMP Paths
ECMP is crucial for scaling and performance in modern data centers and wide-area networks, which rely on hash-based path selection. It leverages path diversity and keeps a flow’s packets on the same path, preventing reordering with useful properties like stateless operation and no reordering.
Striking a Balance: Exploring Fairness in Buffer Allocation and Packet Scheduling
Recently, I’ve been contemplating the concept of fairness, and I see interesting parallels between being a parent and being a network professional. As human beings, we have an inherent, intuitive sense of fairness that manifests itself in various everyday situations. Let me illustrate this idea with a couple of hypothetical scenarios:
Back to Basics: A Primer on Communication Fundamentals
Motivation In our rapidly advancing world, communication speeds are increasing at a fast pace. Transceiver speeds have evolved from 100G to 400G, 800G, and soon even 1.6T. Similarly, Optical systems are evolving to keep up with the pace. If we dig deeper, we will discover that many concepts are shared across various domains, such as Wi-Fi, optical communications, transceivers, etc. Still, without…
Gravity Model
Motivation I recently read Google’s latest sigcomm paper: Jupiter Evolving on their Datacenter fabric evolution. It is an excellent paper with tons of good information, and the depth and width show what an engineering thought process should look like. The central theme talks about the challenges faced with deploying and scaling Clos fabrics and how they have evolved by replacing the spine layer…
Routing Protocol Implementation Evaluation in Fat-Trees
Network design discussions often involve anecdotal evidence, and the arguments for preferring something follow up with “We should do X because at Y place, we did this.”. This is alright in itself as we want to bring the experience to avoid repeating past mistakes in the future. Still, more often than not, it feels like we have memorized the answers, and without reading and understanding the…
Steady State Markov Process
A Markov chain or Markov process is a stochastic model describing a sequence of possible events in which the probability of each event depends only on the state attained in the previous event. It is named after the Russian mathematician Andrey Markov.