In a server, it takes 20 msec to get a request to work, dispatch and do the rest of the necessary processing, when the data needed are in the block cache. On average, every three block cache accesses is followed by one hard disk access when the data required is not in the block cache. During hard disk access operation, an additional 80 msec is required and the thread sleeps. How many requests per second can the above server handle if it is a multi-threaded process? [2 marks]