---
title: "Nathanael FETUE (@nathanael-fetue) | Hashnode"
description: "From Cameroon to Cloud Engineering at ISAE-SUPAERO/ENSEEIHT |DeepTech & Distributed Systems. Read the latest articles by Nathanael FETUE on Hashnode."
url: "https://hashnode.com/@nathanael-fetue"
---

@nathanael-fetue

# Nathanael FETUE

@nathanael-fetue · Toulouse · Joined December 2025

From Cameroon to Cloud Engineering at ISAE-SUPAERO/ENSEEIHT |DeepTech & Distributed Systems

## Comments

[Maybe in part 15.](https://hashnode.com/posts/busy-polling-or-events-timing-one-rdma-write-and-why-perftest-says-half/6af159d1709e0bfcfc8f45f1/comment/6af1c872db22570f0bdfd50b#reply-6af25d68c15324d27885b6a7)

Reply · Article · 4d ago · 1 · [Busy polling or events ? Timing one RDMA write, and why perftest says half](https://hashnode.com/posts/busy-polling-or-events-timing-one-rdma-write-and-why-perftest-says-half/6af159d1709e0bfcfc8f45f1)

[Thanks, good catch. They weren't pinned: both modes ran on the same three-vCPU VM with the scheduler free to place the client, the server and the rxe softirq work. So part of that 7.7 µs may be placement rather than the wake-up itself. A pinned rerun (timer on one CPU, softirqs on another) would separate the two; if I run it, the result will be in a later post on CPU cost.](https://hashnode.com/posts/busy-polling-or-events-timing-one-rdma-write-and-why-perftest-says-half/6af159d1709e0bfcfc8f45f1/comment/6af1c872db22570f0bdfd50b#reply-6af25d47329931c7e4fa78ad)

Reply · Article · 4d ago · 1 · [Busy polling or events ? Timing one RDMA write, and why perftest says half](https://hashnode.com/posts/busy-polling-or-events-timing-one-rdma-write-and-why-perftest-says-half/6af159d1709e0bfcfc8f45f1)

[Thanks, you picked the three parts that taught me the most. The third reader surprised me: two threads' guarantees don't carry over to a third, so it needed its own reasoning. And the speed question stays open on purpose. No number until there's a benchmark behind it, and TSan doesn't replace a model checker either.](https://hashnode.com/posts/a-lock-free-queue-broken-on-purpose-to-prove-it-works/6ae14fb46a57529b5756a1a3/comment/6aeec79ddc68ccee77d3e080#reply-6af15c1abf36fdf837b4963d)

Reply · Article · 5d ago · 1 · [A lock-free queue, broken on purpose to prove it works](https://hashnode.com/posts/a-lock-free-queue-broken-on-purpose-to-prove-it-works/6ae14fb46a57529b5756a1a3)

[Thanks for reading so closely. "Nothing has raised an alert yet" was hard to write, but a dashboard someone watches is not detection, and I'd rather be trustworthy than impressive. And yes, checking where the probe sits is the lesson I'll reuse most. Next up: four links and a timer for every RDMA write, still on Soft-RoCE, limits included.](https://hashnode.com/posts/week-2-from-a-sensor-to-an-agent/6ae7cce438877bcd79edc645/comment/6aee6fef93c75ceeabcdf68d#reply-6af15ad74d0a81207a10d396)

Reply · Article · 5d ago · [Week 2: from a sensor to an agent](https://hashnode.com/posts/week-2-from-a-sensor-to-an-agent/6ae7cce438877bcd79edc645)

[Great work !](https://hashnode.com/posts/not-root-proving-an-xdp-agent-needs-exactly-three-capabilities/6ad1818ceec3044d0b2772ef/comment/6ad18684d6d79b83412c2bf2)

Comment · Article · Oct 16 · [Not root: proving an XDP agent needs exactly three capabilities](https://hashnode.com/posts/not-root-proving-an-xdp-agent-needs-exactly-three-capabilities/6ad1818ceec3044d0b2772ef)

[It\`s a great idea , trust me !](https://hashnode.com/posts/my-roce-testbed-passed-it-was-lying/6ac5a323a97d85f79be4f6e2/comment/6ac5a3747ca79c2017e01731)

Comment · Article · Oct 7 · 1 · [My RoCE testbed passed. It was lying](https://hashnode.com/posts/my-roce-testbed-passed-it-was-lying/6ac5a323a97d85f79be4f6e2)

[J'ai bien le contenu.](https://hashnode.com/posts/day-1-aws-journey-begins/692e1427304108244f3d12d5/comment/692e173acb12a517d75f4b93)

Comment · Article · Dec 1, 2025 · [Building the Stack — Zero to AWS Certified in 6 Weeks - The Journey Begins](https://hashnode.com/posts/day-1-aws-journey-begins/692e1427304108244f3d12d5)