Is it possible to encounter a race condition when using asyncio in Python?

Yes, when using asyncio in Python, you can encounter a race condition. Although asyncio runs in a single thread and uses cooperative multitasking, a race condition occurs when multiple coroutines access and modify a shared resource simultaneously without proper synchronization.

For example, if two coroutines read and modify a shared dictionary or counter at the same time, the result can be unpredictable.

To prevent such situations, asyncio uses synchronization mechanisms, such as asyncio.Lock:

import asyncio

counter = 0
lock = asyncio.Lock()

async def increment():
    global counter
    async with lock:
        temp = counter
        await asyncio.sleep(0)  # simulate context switch
        counter = temp + 1

async def main():
    await asyncio.gather(increment(), increment())
    print(counter)  # Expected 2

asyncio.run(main())

Without using lock, the result can be less than expected due to the race condition.