Re: [RESEND PATCH 1/5] lib/dlock-list: Distributed and lock-protected lists

From: Waiman Long
Date: Mon Jul 11 2016 - 13:37:59 EST


On 06/07/2016 04:13 PM, Andi Kleen wrote:
On Tue, Jun 07, 2016 at 03:35:51PM -0400, Waiman Long wrote:
Linked list is used everywhere in the Linux kernel. However, if many
threads are trying to add or delete entries into the same linked list,
it can create a performance bottleneck.

This patch introduces a new list APIs that provide a set of distributed
lists (one per CPU), each of which is protected by its own spinlock.
One thing I don't like is that it is per CPU. One per CPU is almost
certainly overkill and not needed for true scalability, especially
on systems using SMT. Also it makes the case where everything has to
be walked more and more expensive, because all these locks have to
be taken. Even when not contended this will add up.

When iterating the lists, the lock shouldn't be taken when a list is empty.

It would be better to do this per every Nth CPU. Now I don't have
a clear answer what the best N is, but I'm pretty sure it's> 1.
For example at least on SMT systems only per core instead of per
thread. Likely even more coarse grained, although per socket
may be not good enough.

-Andi

I have just sent out an updated patch to mapped 2 cores to each list. Maybe you can take a look to see if that is good enough from your point of view.

Cheers,
Longman