For a query like this:
Do i need to handle the threadPool? and is this optmizaed acc to the relational model for convex db?
#Db optimizations
cosmic saddle
regal ironBOT
Hi @cosmic saddle. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:
For a query that fetches posts and their associated tags (or similar relational data), you do not need to manually handle a thread pool in Convex. Convex's backend is designed to efficiently parallelize and optimize these kinds of queries for you. Using Promise.all (or Convex's asyncMap helper) to fetch related data in parallel is idiomatic and supported. Convex ensures proper throughput and prevents overwhelming the backend with too many simultaneous queries, so you don't need to manage concurrency at this level yourself.
However, you should be mindful of the potential size of your result set. If you have a very large number of posts or tags, you may need to implement pagination or otherwise limit the number of records returned to avoid exceeding Convex's query limits or running into performance issues. Also, make sure to use indexes (e.g., .withIndex('by_post', ...)) for efficient lookups on association tables, as this is key to performance in Convex's relational model.
In summary:
- No need to handle thread pools manually.
- Convex optimizes parallel queries for you.
- Use indexes for efficient relational lookups.
- Paginate or limit large queries to avoid performance issues.