Verify the whole request.
A useful CDN test checks the response, its freshness, and the visitor experience as well as timing. Work through this checklist on a site you operate or are authorized to test. Record the conditions and expected behavior so repeated checks can reveal configuration changes and regressions.
Prepare a small, representative test set
Choose a public HTML page, a versioned asset, a frequently updated file, and a missing URL. Add a private page or transactional flow if the application has one. Write down the expected status code, content, and cache behavior for each. Save the current configuration and a baseline before changing rules.
Run the delivery checklist
- Inspect the destination. Open browser developer tools before loading the page. In the Network panel, select the request and record its full URL, redirect chain, status, and response content. Confirm that the expected hostname and final resource are being used.
- Read the policy. Inspect
Cache-Control, relevant validators, and the provider's documented cache-status headers. Check for unexpected cookies or response variations. Compare the delivered headers with the origin's intended policy. - Separate browser and edge caching. Record when the browser serves a local copy. Test ordinary repeated network requests as well as a fresh browser context. Hard reloads or cache-disabling controls can alter request behavior, so label those tests instead of treating them as ordinary visits.
- Test an update. Publish a visible change through the normal release process. Verify that new content appears within the intended freshness window, that referenced assets exist, and that the previous release can be restored coherently.
- Check private state. Use separate authorized sessions to confirm that one visitor's account, preview, or cart response is never reused for another. Check logout and return visits where relevant.
- Check failures and timing. Verify missing-page status codes and error freshness. Repeat timing checks from representative locations under comparable conditions, recording cache state and important request stages.
Keep a result you can act on
For each failure, record the exact URL, time, expected result, actual result, and relevant response headers. Redact session credentials and private content before sharing evidence. A reproducible observation is more useful than an isolated score. Use the cache header reference to interpret policy differences and the performance guides to investigate delays that occur after the content arrives.