Re: [PATCH 1/2] sched/wait: Break up long wake list walk

From: Linus Torvalds <torvalds@linux-foundation.org>
To: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Andi Kleen <ak@linux.intel.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Ingo Molnar <mingo@elte.hu>, Kan Liang <kan.liang@intel.com>,
	Andrew Morton <akpm@linux-foundation.org>,
	Johannes Weiner <hannes@cmpxchg.org>, Jan Kara <jack@suse.cz>,
	linux-mm <linux-mm@kvack.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH 1/2] sched/wait: Break up long wake list walk
Date: Tue, 15 Aug 2017 12:47:54 -0700	[thread overview]
Message-ID: <CA+55aFymcZHH+MrFsum9JG89D5YZegNP19zYeF7v11PxuTsXnA@mail.gmail.com> (raw)
In-Reply-To: <CA+55aFymeC-s6rkGk4==3RjZu6nyyj2R9c5TBzpwTwJd4yjf2A@mail.gmail.com>

On Tue, Aug 15, 2017 at 12:41 PM, Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> So if we have unnecessarily collisions because we have waiters looking
> at different bits of the same page, we could just hash in the bit
> number that we're waiting for too.

Oh, nope, we can't do that, because we only have one "PageWaters" bit
per page, and it is shared across all bits we're waiting for on that
page.

So collisions between different bits on the same page are inevitable,
and we just need to make sure the hash table is big enough that we
don't get unnecessary collisions between different pages.

                Linus

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>