debian-mirror-gitlab/doc/administration/static_objects_external_storage.md

222 lines
7.7 KiB
Markdown
Raw Normal View History

2019-12-04 20:38:33 +05:30
# Static objects external storage
2020-03-09 13:42:32 +05:30
> [Introduced](https://gitlab.com/gitlab-org/gitlab-foss/-/merge_requests/31025) in GitLab 12.3.
2019-12-04 20:38:33 +05:30
2020-04-08 14:13:33 +05:30
GitLab can be configured to serve repository static objects (for example, archives or raw blobs) from an external
storage, such as a Content Delivery Network (CDN).
2019-12-04 20:38:33 +05:30
## Configuring
To configure external storage for static objects:
1. Navigate to **Admin Area > Settings > Repository**.
1. Expand the **Repository static objects** section.
2020-04-08 14:13:33 +05:30
1. Enter the base URL and an arbitrary token. When you [set up external storage](#set-up-external-storage),
you'll use a script that uses these values as `ORIGIN_HOSTNAME` and `STORAGE_TOKEN`.
2019-12-04 20:38:33 +05:30
The token is required to distinguish requests coming from the external storage, so users don't
circumvent the external storage and go for the application directly. The token is expected to be
set in the `X-Gitlab-External-Storage-Token` header in requests originating from the external
storage.
## Serving private static objects
GitLab will append a user-specific token for static object URLs that belong to private projects,
so an external storage can be authenticated on behalf of the user. When processing requests originating
from the external storage, GitLab will look for the token in the `token` query parameter or in
the `X-Gitlab-Static-Object-Token` header to check the user's ability to access the requested object.
## Requests flow example
The following example shows a sequence of requests and responses between the user,
GitLab, and the CDN:
```mermaid
sequenceDiagram
User->>GitLab: GET /project/-/archive/master.zip
GitLab->>User: 302 Found
Note over User,GitLab: Location: https://cdn.com/project/-/archive/master.zip?token=secure-user-token
User->>CDN: GET /project/-/archive/master.zip?token=secure-user-token
alt object not in cache
CDN->>GitLab: GET /project/-/archive/master.zip
Note over CDN,GitLab: X-Gitlab-External-Storage-Token: secure-cdn-token<br/>X-Gitlab-Static-Object-Token: secure-user-token
GitLab->>CDN: 200 OK
CDN->>User: master.zip
else object in cache
CDN->>GitLab: GET /project/-/archive/master.zip
Note over CDN,GitLab: X-Gitlab-External-Storage-Token: secure-cdn-token<br/>X-Gitlab-Static-Object-Token: secure-user-token<br/>If-None-Match: etag-value
GitLab->>CDN: 304 Not Modified
CDN->>User: master.zip
end
```
2020-04-08 14:13:33 +05:30
## Set up external storage
While this procedure uses [CloudFlare Workers](https://workers.cloudflare.com) for external storage,
other CDNs or Function as a Service (FaaS) systems should work using the same principles.
1. Choose a CloudFlare Worker domain if you haven't done so already.
1. In the following script, set the following values for the first two constants:
- `ORIGIN_HOSTNAME`: the hostname of your GitLab installation.
- `STORAGE_TOKEN`: any arbitrary secure token (e.g. you can get one by running
`pwgen -cn1 64` on a UNIX machine). Save this token for the admin panel, as
described in the [configuring](#configuring) section.
2020-05-24 23:13:21 +05:30
```javascript
2020-04-08 14:13:33 +05:30
const ORIGIN_HOSTNAME = 'gitlab.installation.com' // FIXME: SET CORRECT VALUE
const STORAGE_TOKEN = 'very-secure-token' // FIXME: SET CORRECT VALUE
const CACHE_PRIVATE_OBJECTS = false
const CORS_HEADERS = {
'Access-Control-Allow-Origin': '*',
'Access-Control-Allow-Methods': 'GET, HEAD, OPTIONS',
'Access-Control-Allow-Headers': 'X-Csrf-Token, X-Requested-With',
}
self.addEventListener('fetch', event => event.respondWith(handle(event)))
async function handle(event) {
try {
let response = await verifyAndHandle(event);
// responses returned from cache are immutable, so we recreate them
// to set CORS headers
response = new Response(response.body, response)
response.headers.set('Access-Control-Allow-Origin', '*')
return response
} catch (e) {
return new Response('An error occurred!', {status: e.statusCode || 500})
}
}
async function verifyAndHandle(event) {
if (!validRequest(event.request)) {
return new Response(null, {status: 400})
}
if (event.request.method === 'OPTIONS') {
return handleOptions(event.request)
}
return handleRequest(event)
}
function handleOptions(request) {
// Make sure the necessary headers are present
// for this to be a valid pre-flight request
if (
request.headers.get('Origin') !== null &&
request.headers.get('Access-Control-Request-Method') !== null &&
request.headers.get('Access-Control-Request-Headers') !== null
) {
// Handle CORS pre-flight request
return new Response(null, {
headers: CORS_HEADERS,
})
} else {
// Handle standard OPTIONS request
return new Response(null, {
headers: {
Allow: 'GET, HEAD, OPTIONS',
},
})
}
}
async function handleRequest(event) {
let cache = caches.default
let url = new URL(event.request.url)
let static_object_token = url.searchParams.get('token')
let headers = new Headers(event.request.headers)
url.host = ORIGIN_HOSTNAME
url = normalizeQuery(url)
headers.set('X-Gitlab-External-Storage-Token', STORAGE_TOKEN)
if (static_object_token !== null) {
headers.set('X-Gitlab-Static-Object-Token', static_object_token)
}
let request = new Request(url, { headers: headers })
let cached_response = await cache.match(request)
let is_conditional_header_set = headers.has('If-None-Match')
if (cached_response) {
return cached_response
}
// We don't want to override If-None-Match that is set on the original request
if (cached_response && !is_conditional_header_set) {
headers.set('If-None-Match', cached_response.headers.get('ETag'))
}
let response = await fetch(request, {
headers: headers,
redirect: 'manual'
})
if (response.status == 304) {
if (is_conditional_header_set) {
return response
} else {
return cached_response
}
} else if (response.ok) {
response = new Response(response.body, response)
// cache.put will never cache any response with a Set-Cookie header
response.headers.delete('Set-Cookie')
if (CACHE_PRIVATE_OBJECTS) {
response.headers.delete('Cache-Control')
}
event.waitUntil(cache.put(request, response.clone()))
}
return response
}
function normalizeQuery(url) {
let searchParams = url.searchParams
url = new URL(url.toString().split('?')[0])
if (url.pathname.includes('/raw/')) {
let inline = searchParams.get('inline')
if (inline == 'false' || inline == 'true') {
url.searchParams.set('inline', inline)
}
} else if (url.pathname.includes('/-/archive/')) {
let append_sha = searchParams.get('append_sha')
let path = searchParams.get('path')
if (append_sha == 'false' || append_sha == 'true') {
url.searchParams.set('append_sha', append_sha)
}
if (path) {
url.searchParams.set('path', path)
}
}
return url
}
function validRequest(request) {
let url = new URL(request.url)
let path = url.pathname
if (/^(.+)(\/raw\/|\/-\/archive\/)/.test(path)) {
return true
}
return false
}
```
1. Create a new worker with this script.
1. Copy your values for `ORIGIN_HOSTNAME` and `STORAGE_TOKEN`.
Use those values [to configure external storage for static objects](#configuring).