Repository: WhatDaFox/nestjs-cloud-run-poc
Configure Google Cloud
To be able to build and deploy, you will need a Google Cloud project, with a billing account set up, as well as
the Google Cloud CLI installed.
Then you will need to create a configuration for your project:
$ gcloud config configurations create cloud-run
$ gcloud auth login # and follow the steps
$ gcloud config set project YOUR_PROJECT_ID
Create the project
For this proof of concept, I will only use the default NestJS application, that contains a single endpoint / returning Hello world!:
$ npm i -g @nestjs/cli
$ nest new cloud-run
Cloud Run will decide the port of our application, so we have to update the main.ts file to reference the PORT environment variable, like so:
import { NestFactory } from '@nestjs/core';
import { AppModule } from './app.module';
async function bootstrap() {
const app = await NestFactory.create(AppModule);
app.enableCors();
await app.listen(process.env.PORT || 3000);
}
bootstrap();
Now we are ready to create the Dockerfile.
Create the Dockerfile
We need to containerize our application to be able to run on Cloud Run. Create a Dockerfile at the root of your project and copy/paste the following:
For better performance, I decided to build the app beforehand and run the
start:prodcommand.
# Use the official lightweight Node.js 12 image.
# https://hub.docker.com/_/node
FROM node:12-alpine
# Create and change to the app directory.
WORKDIR /usr/src/app
# Copy application dependency manifests in the container image.
# A wildcard is used to ensure both package.json AND package-lock.json are copied.
# Copying this separately prevents re-running npm install on every code change.
COPY package*.json ./
# Install dependencies
RUN npm install
# Copy local code to the container image.
COPY . ./
# Build the application
RUN npm run build
# Run the web service on container startup.
CMD [ "npm", "run", "start:prod" ]
Build & Deploy
Now, we can use Cloud Build to build our docker image. Cloud Build will automatically detect our Dockerfile, build,
and push our image in Google Container Registry:
$ gcloud builds submit --tag gcr.io/YOUR_PROJECT/helloworld
Once that's done, we can run the following command to deploy our new revision to Cloud Run:
$ gcloud run deploy --image gcr.io/YOUR_PROJECT/helloworld --platform managed
Benchmark
When testing, I ran a small (to avoid crazy costs) benchmark with Apache Benchmark.
Here is the command I ran:
$ ab -n 1000 -c 80 https://cloud-run-url/
Here are the results:
This is ApacheBench, Version 2.3 <$Revision: 1843412 $>
Copyright 1996 Adam Twiss, Zeus Technology Ltd, http://www.zeustech.net/
Licensed to The Apache Software Foundation, http://www.apache.org/
Benchmarking cloud-run-url (be patient)
Completed 100 requests
Completed 200 requests
Completed 300 requests
Completed 400 requests
Completed 500 requests
Completed 600 requests
Completed 700 requests
Completed 800 requests
Completed 900 requests
Completed 1000 requests
Finished 1000 requests
Server Software: Google
Server Hostname: cloud-run-url
Server Port: 443
SSL/TLS Protocol: TLSv1.2,ECDHE-RSA-CHACHA20-POLY1305,2048,256
Server Temp Key: ECDH X25519 253 bits
TLS Server Name: cloud-run-url
Document Path: /
Document Length: 12 bytes
Concurrency Level: 80
Time taken for tests: 8.624 seconds
Complete requests: 1000
Failed requests: 0
Total transferred: 486004 bytes
HTML transferred: 12000 bytes
Requests per second: 115.95 [#/sec] (mean)
Time per request: 689.939 [ms] (mean)
Time per request: 8.624 [ms] (mean, across all concurrent requests)
Transfer rate: 55.03 [Kbytes/sec] received
Connection Times (ms)
min mean[+/-sd] median max
Connect: 61 402 219.1 375 2652
Processing: 29 207 117.5 192 1328
Waiting: 24 168 114.6 146 1279
Total: 163 609 236.4 567 2819
Percentage of the requests served within a certain time (ms)
50% 567
66% 622
75% 681
80% 714
90% 804
95% 920
98% 1221
99% 1754
100% 2819 (longest request)
Conclusion
It is pretty straightforward to build and deploy a container to Cloud Run. The response time can sometimes be pretty slow,
but overall, if the container is small and quick to start, it should run pretty smoothly.
Top comments (0)