GithubHelp home page GithubHelp logo

styx's Introduction

STYX: A Transactional Deterministic SFAAS System running on Dataflows

Instructions

To run Styx quickly without needing a Kubernetes cluster, follow the following instructions.

NOTE: Styx requires Kafka as a replayable fault-tolerant ingress/egress and Minio to store the snapshots.

Kafka

To run kafka: docker-compose -f docker-compose-kafka.yml up

To clear kafka: docker-compose -f docker-compose-kafka.yml down --volumes

Minio

To run minio: docker-compose -f docker-compose-minio.yml up

To clear minio: docker-compose -f docker-compose-minio.yml down --volumes

Styx

To run Styx: docker-compose up --build --scale worker=2. Specify the number of workers required in the scale parameter.

To clear Styx: docker-compose down --volumes

Demo Instructions

Now that all the Styx required components are up for a simple demo, go to the demo folder. First, run the kafka_output_comsumer.py (rerun it if it throws a warning on topic creation), then run the pure_kafka_demo.py To get performance metrics, kill the kafka_output_comsumer.py and then run calculate_metrics.py. This will Run the shopping cart demo within Styx.

For the NSDI 2024 submission, enter the benchmark folder and run the kafka_output_comsumer.py as in the previous example. To run the workload, run the client.py with varying amounts in the messages_per_second, sleeps_per_second, sleep_time and seconds parameters to generate a stable input throughput (a dry run to find the correct values is required) and change the zipf_const to emulate the different scenarios.

Folder structure
  • benchmark The benchmark we used for the experiments for the NSDI 2024 submission regarding the bank transfer workload

  • coordinator Styx coordinator containerized python service code

  • demo Demo code with the "typical shopping cart application" the Styx application logic code can be found within the functions folder

  • demo-deathstar-hotel-reservation The benchmark we used for the experiments for the NSDI 2024 submission regarding the hotel reservation Deathstar workload

  • demo-deathstar-movie-review The benchmark we used for the experiments for the NSDI 2024 submission regarding the movie review Deathstar workload

  • demo-tpc-c The benchmark we used for the experiments for the NSDI 2024 submission regarding the TPC-C workload. For data generation, we used this open source TPC-C generator https://github.com/alexandervanrenen/tpcc-generator

  • demo-ycsb Demo code with an implementation of the YCSB benchmark

  • env-example env folder example for the docker-compose Minio container

  • helm-config Configurations for the helm charts needed for the Styx deployment

  • ingress Deprecated! (we now use Kafka) TCP ingress to the Styx cluster

  • k8s The Kubernetes deployment files for the Styx cluster

  • k8s-ingress Changes to the Kubernetes ingress since Styx requires opened TCP ports

  • locust-loadtest Locust load test for the shopping cart demo application

  • styx-package The Styx framework Python package

  • tests Tests for the worker components of Styx

  • worker Styx worker containerized python service code

styx's People

Contributors

dataflowsfaas avatar

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.