Lock Convoys

When the arrival rate at a lock is consistently high compared to its lock acquisition rate, a lock convoy may result. In the extreme, there are more threads waiting at a lock than can be serviced, leading to a catastrophe. This is more common on server-side programs where certain locks protecting data structures needed by most clients can get unusually hot.


Critical sections as implemented in Microsoft Windows operating systems provide a good example of how lock convoys can occur. In Windows, critical sections use a combination of a spinlock and a kernel synchronization object called an "event" to ensure mutual exclusion. For low-contention critical sections, the spinlock will provide mutual exclusion most of the time, falling back on the event only when a thread fails to acquire the spinlock within a certain amount of time. When contention is high, however, it is possible for many threads to fail to acquire the spinlock and enter a waiting state, all waiting on the same event.


0 komentarze:

Prześlij komentarz

Tomasz Kulig