In what cases does data race occur in Python when working with multithreading?

Data race condition in Python occurs when multiple threads access and modify shared mutable data simultaneously without proper synchronization. For example, if two threads increment a shared counter at the same time, the final value may be incorrect due to operation interruption.

This happens because read and write operations are not atomic, and context switching between threads can lead to lost updates.

To prevent data races, synchronization mechanisms such as Lock and RLock from the threading module are used:

import threading

counter = 0
lock = threading.Lock()

def increment():
    global counter
    with lock:
        temp = counter
        temp += 1
        counter = temp

threads = [threading.Thread(target=increment) for _ in range(1000)]
for t in threads:
    t.start()
for t in threads:
    t.join()

print(counter)  # Should be 1000

Without the lock, the final value can be less than expected due to race conditions.