Local deployment usage

[charred forum]

Does local deployment usage affect usage limits that are billed?

[carmine thistle]

Hi @charred forum. I'm kapa.ai, your friendly support bot. I will try to answer your question by searching through the knowledge base. :wave:

---

No. Usage from local deployments does not count against the billed quotas for your Convex plan.

When you run a local deployment, the backend runs on your own machine, and:

“Since the deployment is running locally, code sync is faster and means resources like functions calls and database bandwidth don't count against [the quotas for your Convex plan].” [Local deployments]

So function calls, database bandwidth, and similar usage on a local deployment are not billed and do not consume your plan’s limits.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon:

@charred forum Kapa.ai is still learning and improving, please let me know how I did by reacting below.

[charred forum]

@carmine thistle how can I see where all my db read bandwidth is being spent?

[carmine thistle]

Let me check the knowledge base for you again. One moment! :books:

---

You have a few tools for this:

1. Per-function breakdown in the dashboard

   • Go to Team → Usage for your team.
   • On the Usage page, scroll down to the graphs; the last graph has a dropdown.
   • Select “Database bandwidth” to see which functions are consuming the most DB bandwidth (reads + writes). [Team usage; DB bandwidth thread]

2. Per-function metrics on a deployment

   • In the dashboard, open Deployment → Functions.
   • For each function you can see metrics like Invocations, Errors, Execution Time, and Cache Hit Rate; this helps spot hot or uncached queries that might drive reads. [Functions metrics]

3. Health → Insights (for inefficient queries)

   • In Deployment → Health, check the Insights section.
   • Convex surfaces functions that are reading too many bytes or too many documents in a single transaction, with charts and function names so you can target them. [Health insights]

4. Log Streams for detailed per-call usage

• Enable a Log Stream integration (e.g. Axiom, Datadog).
  • Each function_execution event includes usage.database_read_bytes, database_read_documents, etc., so you can graph and aggregate DB reads by function or over time. [Log streams schema]
  • Example Axiom query to see DB bandwidth by function: [Log streams usage]

    your_dataset
    | where ['data.topic'] == "function_execution"
    | extend databaseBandwithKb = (todouble(['data.usage.database_read_bytes']) + todouble(['data.usage.database_write_bytes'])) / 1024
    | summarize sum(databaseBandwithKb) by ['data.function.path'], bin_auto(_time)
    

These together let you answer “which functions” and “which individual calls” are using most of your DB read bandwidth.

Note: you can ask me a follow up question by @ mentioning me again :speech_balloon: