Date: Fri, 29 Jun 2007 23:39:22 +0100
From: Alan Cox <alan@lxorguk.ukuu.org.uk>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: David Miller <davem@davemloft.net>, clameter@sgi.com, hugh@veritas.com,
       James.Bottomley@steeleye.com, rmk+lkml@arm.linux.org.uk,
       linux-kernel@vger.kernel.org
Subject: Re: [PATCH] Containment measures for slab objects on scatter gather
 lists
Message-ID: <20070629233922.689865ca@the-village.bc.nu>
In-Reply-To: <20070629134529.3e12a131.akpm@linux-foundation.org>
References: <Pine.LNX.4.64.0706282128570.11739@schroedinger.engr.sgi.com>
	<20070628.220606.112621271.davem@davemloft.net>
	<20070628222424.4cbae90c.akpm@linux-foundation.org>
	<20070628.223734.21928089.davem@davemloft.net>
	<20070628224519.1a3319c3.akpm@linux-foundation.org>
	<20070629131657.5ecc3baa@the-village.bc.nu>
	<20070629134529.3e12a131.akpm@linux-foundation.org>
Organization: Red Hat UK Cyf., Amberley Place, 107-111 Peascod Street,
 Windsor, Berkshire, SL4 1TE, Y Deyrnas Gyfunol. Cofrestrwyd yng Nghymru a
 Lloegr o'r rhif cofrestru 3798903
Mime-Version: 1.0
Content-Type: text/plain; charset=US-ASCII
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1367
Lines: 32

On Fri, 29 Jun 2007 13:45:29 -0700
Andrew Morton <akpm@linux-foundation.org> wrote:

> On Fri, 29 Jun 2007 13:16:57 +0100
> Alan Cox <alan@lxorguk.ukuu.org.uk> wrote:
> 
> > > If those operations involve modifying that slab page's pageframe then what
> > > stops concurrent dma'ers from stomping on each other's changes?  As in:
> > > why aren't we already buggy?
> > 
> > Or DMA operations falling out with CPU operations in the same memory
> > area. Not all platforms have hardware consistency and some will blat the
> > entire page out of cache.
> 
> Is that just a performance problem, or can data be lost here?  It depends
> on the meaning of "blat": writeback?  invalidate?  More details, please.

Invalidate. Sorry didn't realise it they hadn't discovered that word down
under.

If you've got something packing objects in tight we are going
to have fun with cache handling simply because the CPU cache granularity
may mean that the invalidate also invalidates a few bytes on (ie a 12
byte object will invalidate 16 bytes of memory) and you've just removed
any CPU held changes in the start of the next object.

Alan
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/