@Marvin How can you get the time taken for a flow to run from the flow_run state?

To assist you with this question, could you please confirm which version of Prefect you are using? Prefect 2.x or 3.x? This will help me provide you with the most accurate information.

@Marvin Its Prefect 2.x

To determine the time taken for a flow to run from the

flow_run

state in Prefect 2.x, you'll generally need to calculate the difference between the start time and the end time of the flow run. Unfortunately, there isn't a direct attribute in the Prefect 2.x API that gives you the flow duration. However, you can execute the following steps to compute it: 1. Access the Flow Run State: You'll retrieve the

flow_run

object using Prefect’s client if necessary. 2. Calculate the Duration: Subtract the

start_time

from the

end_time

for the flow run. Here's a basic idea of how you might achieve this using Python:

python
from prefect import get_client
from datetime import timedelta

async def get_flow_run_duration(flow_run_id):
    async with get_client() as client:
        flow_run = await client.get_flow_run(flow_run_id)
        start_time = flow_run.start_time
        end_time = flow_run.end_time
        duration = end_time - start_time
        return duration

# Usage
# duration = await get_flow_run_duration('your-flow-run-id')

For more detailed documentation on using the Prefect client, you can check out the Prefect 2.x Guide. Also, take a look at some GitHub discussions to understand user experiences and feature requests related to tracking flow durations: - Discussions on run durations over time: GitHub Issue #9509 - Sorting and filtering by duration: GitHub Issue #8582 Remember, clocking the durations might seem simple, but understanding why some runs take longer can sometimes make one feel a bit like a detective in a time warp!