Ops

I designed a rudimentary k8s persistentvolumeclaims solution myself, using Moosefs on the backend as a distributed data store. The principle is based on the kubernetes events mechanism, when a create pvc message is received, the backend control application will create the corresponding pv on moosefs and bind the corresponding pvc, in order to facilitate the application to move between nodes, I mount the moosefs file system to each worker node, here a problem arises: how to keep the moosefs master high availability! ...

After I joined the sparkpool team with the job of Devops in 2018, I broadened my knowledge of digital cryptocurrencies, and in these close to four years of work, I learned about digital finance and traditional financial system, what is a sound monetary system, the difference between cryptocurrencies and traditional currencies, so to speak, at sparkpool I learned a lot of financial knowledge, and also taught myself the technology related to cutting-edge such as deep learning and quantitative trading after work, although I haven’t made a complete set of related products myself, but I have been working hard in this direction. I am very glad to join the sparkpool family, and I would like to thank the two founders of sparkpool. The last of the last, the gathering is a fire and the scattering is full of stars. ...

Reference TIDB architecture Why use TIDB the architecture used by the machine is ARM64. 2. trying to use a distributed database architecture. solve the high availability problem, when a Raspberry Pi database node is down, it will not affect the data writing. compared vitess and TIDB, TIDB is more compatible with ARM64, easy to start experimenting. prepare for the financial trading system later. Architecture Components and functions TIDB Server TIDB Server is a stateless application, it does not store data itself, load balancing can be placed in front, external application requests to nodes in TIDB Cluster, TIDB server will analyze and calculate the SQL requested by the application and forward the request to the underlying data store TiKV. ...

Introduction volcano is a kubernets-based container batch engine for high-performance workload scenarios. Application scenarios: machine learning and deep learning biological and genetic computing big data applications Concepts Queue Queue holding a set of podgroups apiVersion: scheduling.volcano.sh/v1beta1 kind: Queue metadata: name: distcc spec: weight: 1 reclaimable: false capability: cpu: 50 field: weight -> The proportion of the queue in the cluster resource division, the proportion of resources occupied by the queue is: (weight / total-weight) * total-resource, soft resource constraint. ...

Kubernets Wiki Recently read [Large-scale cluster management at Google with Borg](https://static.googleusercontent.com/media/research.google.com/en//pubs/ archive/43438.pdf), Borg is Google’s own internal development of a set of cluster management system, and then the open source community slowly began to incubate and launch the Kubernets cluster management system, k8s and Borg has a very deep relationship of origin. Starting with Kubernets, let’s look at the components of K8s: Kubelet Kubelet runs on every node and manages the containers on the node. ...