Tech

In the 22nd session we took a look at io_uring - a new Kernel interface for asynchronous I/O. Tyler, who is currently implementing an io_uring library in Rust [4] for his database sled [7] guided us through the concepts as well as a bunch of source code. Tyler started off introducing the status quo of I/O interfaces within the Linux Kernel like read, pread and preadv, jumped over to asynchronous I/O like aio and eventually helped us develop a sense of what the perfect asynchronous I/O interface of the future could look like. For alll of this he used Jens Axboe’s slides from a Kernel Recipes 2019 talk [1]. ...

We started the new year with a session on epidemic / gossip protocols. To decide what to read I compiled the following list of papers that I either enjoyed reading in the past, or that were recommended to me. The Swim (Scalable failure detection and membership protocol) paper won the poll. Das, Abhinandan, Indranil Gupta, and Ashish Motivala. “Swim: Scalable weakly-consistent infection-style process group membership protocol.” Proceedings International Conference on Dependable Systems and Networks. IEEE, 2002. ...

Last Tuesday we meet again to discuss different attacks and possible countermeasures for distributed hash tables. More in particular we looked at Kademlia and its security extension S/Kademlia [1], possible eclipse attacks on the Ethereum network [2], a novel approach of hiding its own connection buckets as well as using an existing social graph as a network topology in the Whanau paper[3], security extensions to the Chord DHT [4], as well as a larger study of different security techniques for DHTs [5]. ...

I have been organizing a distributed systems paper reading group in Berlin for the last year. We meet every other week discussing a paper in the distributed systems space. This could be anything from Chandy–Lamport’s algorithm for global distributed snapshots [1] to things like conflict free replicated datatypes [2]. The event is open for anyone interested. I only ask people to come prepared. In the last meeting (19th) we covered distributed hash tables. They play a crucial role in e.g. decentralized file sharing networks for example as directory services, simple key-value stores, or peer-to-peer membership management protocols. ...

Within my work at Red Hat and Kubernetes SIG instrumentation I have been working on kube-state-metrics , a Prometheus exporter exposing the state of a Kubernetes cluster to a Prometheus monitoring system. In particular I have focused on performance optimizing metric rendering for both latency as well as resource usage. Below I want to describe our approach of metric driven performance tuning, using Prometheus to monitor kube-state-metrics on top of Kubernetes, which in itself enables Prometheus to monitor Kubernetes. ...

What If Component xxx Dies? Introducing Self-Healing Kubernetes Kubernetes promises healing your application on all kinds of failure scenarios, but why not self-heal Kubernetes itself? This talk introduces self-hosted Kubernetes (K8s inside itself) to autonomously recover from failure scenarios with the help of e.g. itself, systemd and checkpointing. We will ask and answer questions like “What happens when xxx dies”. The theory will be followed by a demo on a live cluster showcasing what happens when we kill central Kubernetes components, like the API-Server. Let’s see how well Kubernetes recovers. ...