Message-ID: <47AC7093.1070003@linux.intel.com>
Date: Fri, 08 Feb 2008 07:09:07 -0800
From: Arjan van de Ven <arjan@linux.intel.com>
User-Agent: Thunderbird 1.5.0.14 (Windows/20071210)
MIME-Version: 1.0
To: David Miller <davem@davemloft.net>
CC: torvalds@linux-foundation.org, mingo@elte.hu, jens.axboe@oracle.com,
       linux-kernel@vger.kernel.org, Alan.Brunelle@hp.com, dgc@sgi.com,
       npiggin@suse.de, akpm@linux-foundation.org, vegard.nossum@gmail.com,
       penberg@gmail.com
Subject: Re: [patch] block layer: kmemcheck fixes
References: <20080207103136.GG15220@kernel.dk>	<20080207104901.GF16735@elte.hu>	<alpine.LFD.1.00.0802070940230.2883@woody.linux-foundation.org> <20080207.172246.31415231.davem@davemloft.net>
In-Reply-To: <20080207.172246.31415231.davem@davemloft.net>
Content-Type: text/plain; charset=ISO-8859-1; format=flowed
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1448
Lines: 37

David Miller wrote:
> From: Linus Torvalds <torvalds@linux-foundation.org>
> Date: Thu, 7 Feb 2008 09:42:56 -0800 (PST)
> 
>> Can we please just stop doing these one-by-one assignments, and just do 
>> something like
>>
>> 	memset(rq, 0, sizeof(*rq));
>> 	rq->q = q;
>> 	rq->ref_count = 1;
>> 	INIT_HLIST_NODE(&rq->hash);
>> 	RB_CLEAR_NODE(&rq->rb_node);
>>
>> instead?
>>
>> The memset() is likely faster and smaller than one-by-one assignments 
>> anyway, even if the one-by-ones can avoid initializing some field or there 
>> ends up being a double initialization..
> 
> The problem is store buffer compression.  At least a few years
> ago this made a huge difference in sk_buff initialization in the
> networking.
> 
> Maybe cpus these days have so much store bandwith that doing
> things like the above is OK, but I doubt it :-)

on modern x86 cpus the memset may even be faster if the memory isn't in cache;
the "explicit" method ends up doing Write Allocate on the cache lines
(so read them from memory) even though they then end up being written entirely.
With memset the CPU is told that the entire range is set to a new value, and
the WA can be avoided for the whole-cachelines in the range.

--
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/