[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]

To: Andrea Arcangeli <andrea@e-mind.com>
Subject: Re: [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]
From: Ingo Molnar <mingo@chiara.csoma.elte.hu>
Date: Wed, 7 Apr 1999 15:47:50 +0200 (CEST)
cc: Mark Hemment <markhe@sco.COM>, Chuck Lever <cel@monkey.org>, linux-kernel@vger.rutgers.edu, linux-mm@kvack.org, Linus Torvalds <torvalds@transmeta.com>, "Stephen C. Tweedie" <sct@redhat.com>
In-Reply-To: <Pine.LNX.4.05.9904070243310.222-100000@laser.random>
Sender: owner-linux-mm@kvack.org

On Wed, 7 Apr 1999, Andrea Arcangeli wrote:

>  void prune_dcache(int count)
>  {
> +	gfp_sleeping_cookie++;

this can be done via an existing variable, kstat.ctxsw, no need to add yet
another 'have we scheduled' flag. But the whole approach is quite flawed
and volatile, it simply relies on us having the big kernel lock. With more
finegrained SMP locking in that area we will have big problems preserving
that solution.

-- mingo

--
To unsubscribe, send a message with 'unsubscribe linux-mm my@address'
in the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://humbolt.geo.uu.nl/Linux-MM/

Follow-Ups:
- Re: [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]
  - From: Andrea Arcangeli <andrea@e-mind.com>

References:
- [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]
  - From: Andrea Arcangeli <andrea@e-mind.com>

Prev by Date: Re: [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]
Next by Date: Re: [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]
Prev by thread: Re: [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]
Next by thread: Re: [patch] only-one-cache-query [was Re: [patch] arca-vm-2.2.5]
Index(es):
- Date
- Thread