What exactly was cached and what invalidation rules were used?

In Go projects, I cached the results of expensive computations and responses to frequently repeated database queries to reduce load and speed up service response times.

Cache invalidation rules depend on the data type:

• For data that updates on a schedule, I used TTL (time-to-live), after which the cache automatically resets.
• For data that changes based on events, I implemented invalidation upon receiving a change notification (e.g., via pub/sub or webhook).
• In some cases, I applied a write-through strategy, where the cache is updated simultaneously with the database.

Example of TTL invalidation:

cache.Set(key, value, 5*time.Minute) // cache with a 5-minute lifespan

This approach helps maintain a balance between data relevance and performance.