Why do mirror sync create tables in connected database?

Hi Robin Y., Please stand by as I search the Mixpanel knowledge base for an AI-powered answer. I normally take about 15 seconds or so. In case AI cannot answer your question, feel free to reach out to Mixpanel support at mixpanel.com/get-support. If you have follow-up questions for this thread, please tag me again with your question: @kapa.ai <follow-up question> 👋

Based on the knowledge sources provided, I can explain why Mirror sync creates tables in the connected database: Mirror sync creates tables or uses existing structures in the connected database to track changes and maintain synchronization between the data warehouse and Mixpanel. The specific implementation varies depending on the data warehouse being used: 1. For Snowflake: Mirror uses Snowflake Streams to track changes. Mixpanel creates and manages the necessary STREAM objects in a MIXPANEL schema within your Snowflake database. These streams are used to efficiently track changes to tables or views.2. For BigQuery: Mirror uses table snapshots to track changes. These snapshots are stored in a mixpanel dataset created in your BigQuery instance. The snapshots allow Mixpanel to compute the change stream between two snapshots.3. For Databricks: Mirror uses Databricks Change Data Feed to track changes. This feature needs to be enabled on the tables you want to sync.4. For Redshift: Mirror takes Redshift table snapshots and stores them in a staging schema created in your Redshift database.These additional tables or structures are created to enable efficient change tracking and synchronization. They allow Mixpanel to identify which rows have been inserted, modified, or deleted in your data warehouse, and then send only the changed data to Mixpanel. This approach minimizes data transfer and ensures that Mixpanel stays in perfect sync with your data warehouse.Sources: Docs Tracking-methods > Warehouse Connectors: Sync data from your data warehouse into Mixpanel > Sync Modes > Mirror Part 1> Docs Tracking-methods > Warehouse Connectors: Sync data from your data warehouse into Mixpanel > Sync Modes > Mirror Part 2> Docs Tracking-methods > Warehouse Connectors: Sync data from your data warehouse into Mixpanel > Sync Modes > Mirror Part 3> Docs Tracking-methods > Warehouse Connectors: Sync data from your data warehouse into Mixpanel > Sync Modes > Mirror Part 4>

ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.

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

Based on the information provided in the knowledge sources, there isn't a direct way to stop Mirror sync from creating tables or structures in your connected database. These tables and structures are essential for the Mirror sync functionality to work correctly.The creation of these tables or structures (like Snowflake Streams, BigQuery snapshots, or Databricks Change Data Feed) is an integral part of how Mirror sync operates to efficiently track and sync changes between your data warehouse and Mixpanel. They are necessary for: 1. Detecting changes in your data 2. Ensuring data accuracy 3. Minimizing data transfer by only sending changed dataWithout these structures, Mirror sync would not be able to perform its core function of keeping Mixpanel perfectly in sync with your warehouse data.If you're concerned about the impact of these additional tables or structures, you might consider: 1. Using a different sync mode like Append or Full, which have different requirements. However, these modes don't offer the same level of synchronization as Mirror.2. Discussing your specific concerns with Mixpanel's support team to see if there are any alternatives or workarounds that might meet your needs while still allowing for efficient data synchronization.Remember that while these additional structures do take up some space in your database, they are designed to be efficient and are automatically managed by Mixpanel to minimize their impact.Docs Tracking-methods > Warehouse Connectors: Sync data from your data warehouse into Mixpanel > Sync Modes> If you have specific concerns about database management or storage, it would be best to reach out to Mixpanel's support for more tailored advice.

ℹ️ Tip: Mention @kapa.ai in the thread for follow-ups or DM the app for 1-to-1 help.