文件列表:

_config.yml (26, 2023-04-06)
dfaasagent.env (871, 2023-04-06)
dfaasagent (0, 2023-04-06)
dfaasagent\agent (0, 2023-04-06)
dfaasagent\agent\agent.go (6313, 2023-04-06)
dfaasagent\agent\communication (0, 2023-04-06)
dfaasagent\agent\communication\communication.go (2679, 2023-04-06)
dfaasagent\agent\config (0, 2023-04-06)
dfaasagent\agent\config\config.go (2354, 2023-04-06)
dfaasagent\agent\constants (0, 2023-04-06)
dfaasagent\agent\constants\constants.go (215, 2023-04-06)
dfaasagent\agent\discovery (0, 2023-04-06)
dfaasagent\agent\discovery\kademlia (0, 2023-04-06)
dfaasagent\agent\discovery\kademlia\kademlia.go (5250, 2023-04-06)
dfaasagent\agent\discovery\mdns (0, 2023-04-06)
dfaasagent\agent\discovery\mdns\mdns.go (2218, 2023-04-06)
dfaasagent\agent\hacfgupd (0, 2023-04-06)
dfaasagent\agent\hacfgupd\hacfgupd.go (2089, 2023-04-06)
dfaasagent\agent\infogath (0, 2023-04-06)
dfaasagent\agent\infogath\hasock (0, 2023-04-06)
dfaasagent\agent\infogath\hasock\hasock.go (1992, 2023-04-06)
dfaasagent\agent\infogath\offuncs (0, 2023-04-06)
dfaasagent\agent\infogath\offuncs\offuncs.go (3637, 2023-04-06)
dfaasagent\agent\infogath\ofpromq (0, 2023-04-06)
dfaasagent\agent\infogath\ofpromq\ofpromq.go (12254, 2023-04-06)
dfaasagent\agent\infogath\ofpromq\resptypes.go (4211, 2023-04-06)
dfaasagent\agent\logging (0, 2023-04-06)
dfaasagent\agent\logging\logging.go (2457, 2023-04-06)
dfaasagent\agent\logic (0, 2023-04-06)
dfaasagent\agent\logic\dbglogging.go (7586, 2023-04-06)
dfaasagent\agent\logic\haupd.go (4277, 2023-04-06)
dfaasagent\agent\logic\logic.go (1803, 2023-04-06)
dfaasagent\agent\logic\msgtypes.go (810, 2023-04-06)
dfaasagent\agent\logic\recalc.go (15067, 2023-04-06)
dfaasagent\agent\logic\reception.go (2489, 2023-04-06)
dfaasagent\agent\nodestbl (0, 2023-04-06)
... ...

# DFaaS: Decentralized Function-as-a-Service for Federated Edge This repository holds DFaaS, a novel decentralized FaaS-based architecture designed to automatically and autonomously balance the traffic load across edge nodes belonging to federated Edge Computing ecosystems. DFaaS implementation relies on an overlay peer-to-peer network and a distributed control algorithm that takes decisions on load redistribution. Although preliminary, our results confirm the feasibility of the approach, showing that the system can transparently redistribute the load across edge nodes when they become overloaded. Our prototype is based on OpenFaaS and implements the control logic within Go P2P agents. This research work is conducted by the INteraction and SemantIcs for Innovation with Data & Services (INSID&S) Laboratory of the University of Milano - Bicocca. If you wish to reuse this source code, please consider citing our article describing the first prototype: > Michele Ciavotta, Davide Motterlini, Marco Savi, Alessandro Tundo
> [**DFaaS: Decentralized Function-as-a-Service for Federated Edge Computing**](https://doi.org/10.1109/CloudNet53349.2021.9657141),
> 2021 IEEE 10th International Conference on Cloud Networking (CloudNet), DOI: 10.1109/CloudNet53349.2021.9657141. ## Scenario  The above figure depicts the considered network scenario. A set of geographically-distributed _FaaS-enabled edge nodes_ (or simply _edge nodes_) is deployed at the edge of the access network. Each of these nodes deploys a _DFaaS platform_ for the execution of _serverless functions_, and is connected to a wireless or wired _access point_ (e.g. a base station, a broadband network gateway, a WiFi access point, etc.). The edge node can receive functions' execution _requests_, in the form of HTTP requests, generated by the _users_ served by the access point. ## Architecture  ## Prototype This prototype relies on [HAProxy](https://www.haproxy.org/) to implement the proxy component, and on [fa*** 0.16.0](https://github.com/openfaas/fa***) (a lightweight version of OpenFaaS) to implement the FaaS platform. Also, we exploit [Sysbox](https://github.com/nestybox/sysbox), an open-source and free container runtime (a specialized "runc") that enhances containers in two key ways: - improves container isolation - enables containers to run same workloads as VMs Thanks to Sysbox we are able to run our prototype as a standalone Docker container that executes our agent, the HAProxy and fa*** all together. This way, we can run several emulated edge nodes by simply executing multiple Docker containers. ### Requirements - Ubuntu 20.04 LTS - containerd 1.*** - Docker CE 20.10.16 - Sysbox CE 0.5.2 #### Setup environment using the convenience script The script has 3 arguments: - 1st arg: Sysbox CE version - 2nd arg: shiftfs branch > This scripts assumes you are using Ubuntu 20.04 LTS with kernel version 5.4. ```shell ./setup-environment 0.5.2 k5.4 ``` #### Manual _Docker CE v20.10.16_ You can follow the [official user guide](https://docs.docker.com/engine/install/). _Sysbox CE 0.5.2_ You can follow the [official user guide](https://github.com/nestybox/sysbox/blob/master/docs/user-guide/install-package.md). > We do not recommend to set up `sysbox-runc` as your default container, you can skip that part of the guide. > > We instead recommend installing [shiftfs](https://github.com/nestybox/sysbox/blob/master/docs/user-guide/install-package.md#installing-shiftfs) > according to your kernel version as suggested by the Sysbox CE user guide. ### Build Docker images ```shell # Paths assume you are executing from the project root directory docker build -t dfaas-agent-builder:latest -f docker/dfaas-agent-builder.dockerfile dfaasagent docker build -t dfaas-node:latest -f docker/dfaas-node.dockerfile docker ``` ### Run a 3 nodes network via Docker Compose See the provided [docker-compose.yml](docker-compose.yml) file for technical details. ```shell docker compose up -d ``` ### Deploy functions This script deploy the same set of functions on each of the nodes by using [docker/files/deploy_functions.sh](docker/files/deploy_functions.sh). The [deploy_functions.sh](docker/files/deploy_functions.sh) script waits for the OpenFaaS gateway to be up (max 20 retries, 10s delay), then deploys 3 functions (ocr, shasum, figlet) from the OpenFaas store. The script has 3 arguments: - 1st arg: number of nodes (e.g., `3`) - 2nd arg: node name prefix (e.g., `dfaas-node-`) - 3rd arg: node name suffix (e.g., `-1`) The resulting node name (container) will be `dfaas-node-1-1`, that is, the default name you get when using the provided docker-compose.yml file. ```shell ./utils/deploy-functions-to-nodes.sh 3 "dfaas-node-" "-1" ``` ### Invoke a function Each node exposes port `808x:80` (e.g., `node-1` exposed port is `8081:80`), where port `80` is the HAProxy port. This example assumes you run DFaaS nodes via Docker Compose with the provided [docker-compose.yml](docker-compose.yml) file. You can invoke a function (i.e., via the first node) by simply contact the proxy on `http://localhost:8081/function/{function_name}`. ```shell curl http://localhost:8081/function/figlet -d 'Hello DFaaS world!' ``` ### Execute workload to a node using [vegeta](https://github.com/tsenart/vegeta) We provide an example that use [vegeta](https://github.com/tsenart/vegeta) HTTP load testing tool to run workload on a node and demonstrate the load distribution over the federation. You can install vegeta by executing the following commands: ```shell wget https://github.com/tsenart/vegeta/releases/download/v12.8.4/vegeta_12.8.4_linux_amd***.tar.gz tar -xf vegeta_12.8.4_linux_amd***.tar.gz && rm vegeta_12.8.4_linux_amd***.tar.gz sudo mv vegeta /usr/local/bin/ ``` This example uses the [vegeta json format](https://github.com/tsenart/vegeta#json-format) and requires [jq](https://stedolan.github.io/jq/). In a nutshell: - it runs a vegeta attack (duration: `5 minutes`, rate: `50 req/s`) to the `figlet` function on the first node - it saves the results and produces report ever 200ms ```shell # Create the vegeta results directory mkdir -p vegeta-results export VEGFOLDER="vegeta-results/$(date +%Y-%m-%d-%H%M%S)" mkdir -p $VEGFOLDER jq -ncM '{method: "GET", url: "http://localhost:8081/function/figlet", body: "Hello DFaaS world!" | @base***, header: {"Content-Type": ["text/plain"]}}' | \ vegeta attack -duration=5m -rate=50 -format=json | \ tee $VEGFOLDER/results.bin | \ vegeta report -every=200ms ``` ### Create plots from vegeta results You can produce some plots from vegeta results by exploiting the `vegeta plot` command or our [utils/plot.py](utils/plot.py) script. To use our script, you need to install the required Python packages listed in [utils/plot-requirements.txt](utils/plot-requirements.txt). ```shell # Encode results as JSON cat $VEGFOLDER/results.bin | vegeta encode > $VEGFOLDER/results.json # Create plot with vegeta cat cat $VEGFOLDER/results.bin | vegeta plot > $VEGFOLDER/plot.html # 1st arg: path int results.json # 2nd arg: path output plot # 3rd arg: rate req/s used for the attack ./utils/plot.py $VEGFOLDER/results.json $VEGFOLDER/plot.png 50 ``` ### Forwarding traffic as a malicious node You can impersonate a malicious node that is not part of the federation by adding the header `Dfaas-Node-Id` with a value that is not a valid peer id of the network (e.g., `Dfaas-Node-Id: malicious-id`). All of its requests will be rejected. ### Troubleshooting ```shell # Substitute the CONTAINER_NAME value with the desired container name export CONTAINER_NAME="dfaas-node-1-1" docker exec -it ${CONTAINER_NAME} bash journalctl --follow --unit dfaasagent # ...or whatever you prefer to inspect (e.g., haproxy, fa***, fa***-provider) ``` ## Emulator For a complex setup running several emulated edge nodes with different topologies see [emulator directory](emulator). We provide instructions and examples to execute DFaaS nodes via [Containernet emulator](https://containernet.github.io/). ## Simulator We also provide a simulator to test and compare different load balancing techniques. The simulation code is available into the [simulation directory](simulation). Data gathered by the DFaaS system used for simulation are available [here](simulation/data). For more information read associated [README](simulation/README.md) file.

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：