How does cold start work?

Checkout my attached image. the purple bar is the execution time from a BuildShip workflow from start to end (I record the timings within the workflow itself). The green bars are measurements from the frontend you can disregard (though the BuildShip latency adds to this frontend latency). Is a workflow ALWAYS starting cold or does it start cold after a certain period of time if the workflow was not being used? Furthermore I wonder why the workflow itself runs slower at the beginning and faster in the end in my statistics. Since I am measuring the times directly in the workflow I thought the cold start would not affect the speed of the workflow but rather the starting time.

Solution

Hey @Brian We checked the workflow you shared for issues with latency even after no-cold start purchase, the initial request.
According to the 22 execution logs and metrics, all the initial startup requests are under 2-3ms (you can check the request time to call the trigger) only one request - 2025-02-2620:09:32 which took 4.01s also worked without any cold start under 2ms, the time is consumed by the Groq Chat (detailed) - 2.29s and Get Document Query node - 1.48.
The server performance for no cold start is consistent with the initial request without startup latency for requests within 2ms.

Also sent you an email.