* Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx> wrote: > Ingo, > > I tried MCS locking to order the writers but it didn't make much > difference on my particular workload. After thinking about this some > more, a likely explanation of the performance difference between mutex > and rwsem performance is: > > 1) Jobs acquiring mutex put itself on the wait list only after > optimistic spinning. That's only 2% of the time on my test workload so > they access the wait list rarely. > > 2) Jobs acquiring rw-sem for write *always* put itself on the wait list > first before trying lock stealing and optimistic spinning. This creates > a bottleneck at the wait list, and also more cache bouncing. Indeed ... > One possible optimization is to delay putting the writer on the wait > list till after optimistic spinning, but we may need to keep track of > the number of writers waiting. We could add a WAIT_BIAS to count for > each write waiter and remove the WAIT_BIAS each time a writer job > completes. This is tricky as I'm changing the semantics of the count > field and likely will require a number of changes to rwsem code. Your > thoughts on a better way to do this? Why not just try the delayed addition approach first? The spinning is time limited AFAICS, so we don't _have to_ recognize those as writers per se, only if the spinning fails and it wants to go on the waitlist. Am I missing something? It will change patterns, it might even change the fairness balance - but is a legit change otherwise, especially if it helps performance. Thanks, Ingo -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@xxxxxxxxx. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>