Massive node_modules in production issue

Sometimes node_modules become massive that it makes hard and longer to deploy codes to the production environment. In this blog, I want to cover a few things that can be done to reduce node_modules size.

npm commands

• When deploying codes to production, devDependencies should be excluded as dependencies under that property literally for development purposes Eg. jest, typescript references etc.

Run npm ci --production command to exclude devDependencies from node_modules

• Sometimes after npm install, npm list shows the dependency tree which isn't necessarily the same as the node_modules file tree. However, this can be simplified by running

Run npm dedupe

Unify sub dependencies version

Sometimes developer faces a situation where multiple dependencies require sub-dependency but npm install multiple as they use different versions from each other. Eg axios, aws-sdk.

• In case, those dependencies are client libraries from your side, then you can simply update package.json in client libraries to use the same dependency version Eg. Below will install 2 aws-sdk packages into node_modules

library-a
 |-----> aws-sdk@2.1.0
library-b
 |-----> aws-sdk@2.2.0

Below will install 1 aws-sdk package as there's only one version

library-a
 |-----> aws-sdk@2.2.0
library-b
 |-----> aws-sdk@2.2.0

• Usage of overrides property from package.json can also resolve multiple versions issue. Eg.

{
  ...,
  "dependencies": {
    "library-a": "1.0.0",
    "library-b": "1.0.5",
    ...
  },
  "overrides": {
    "library-a": {
      "aws-sdk: "2.2.0"
    },
    "library-b": {
      "aws-sdk: "2.2.0"
    }
  }
}

Remove unnecessary packages

Sometimes developers tend to solve problems with npm packages and sometimes it's not good practice as it will pile up the size of node_modules quickly.
Common examples are lodash, ramda, and etc.
Try to avoid using these kind of libraries. If you can create it relatively quickly then just do it. Don't be lazy

Use cases

• The most useful use case is AWS lambda. AWS lambda has a size limitation (250mb unzip size) thus, having too many packages or duplicated dependencies may be a big cause of the issue.