How do I implement distributed locks in Redis?

How do I implement distributed locks in Redis?

To implement distributed locks in Redis, you can use the SET command with the NX and PX options. This ensures that the lock is only set if it does not already exist and has an expiration time.

Can you provide a code example for that?

Sure! Here's a simple example in Python using the redis-py library:

import redis

client = redis.StrictRedis(host='localhost', port=6379, db=0)
lock_key = 'my_lock'

# Try to acquire the lock
if client.set(lock_key, 'locked', nx=True, px=10000):
    try:
        # Critical section of code
        print('Lock acquired!')
    finally:
        # Release the lock
        client.delete(lock_key)
else:
    print('Could not acquire lock, already in use.')

What happens if the process crashes while holding the lock?

If the process crashes while holding the lock, the lock will be released automatically after the expiration time (PX) you set. This prevents deadlocks.

Are there any alternatives to using Redis for distributed locks?

Yes, alternatives include using databases like PostgreSQL with advisory locks, or other distributed systems like Zookeeper or etcd.