From: "Frantisek Rysanek" <Frantisek.Rysanek@post.cz>
To: "=?ISO-8859-2?Q?J=F6rn_Engel?=" <joern@logfs.org>,
       linux-kernel@vger.kernel.org
Date: Mon, 07 Jan 2008 16:51:22 +0100
MIME-Version: 1.0
Subject: Re: [noob q. on block layer] block IO read-ahead during sequential *write*?
Message-ID: <4782588A.3856.1B9C57D9@localhost>
In-reply-to: <20080107124952.GA8201@lazybastard.org>
References: <47822835.4182.1ADF8AE7@localhost>
Content-type: text/plain; charset=ISO-8859-2
Content-transfer-encoding: 8BIT
Content-description: Mail message body
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 806
Lines: 23

On 7 Jan 2008 at 13:49, J?rn Engel wrote:
>
> If you retry the dd with bs=4096 (or whatever your architecture's page
> size happens to be), does this still occur?
> 
> Jörn
> 
wow, thanks, it works, this is so obvious.
I tend to use values like bs=512000 or suchlike, but probably never
stroke this particular value when I was looking at iostat.
Must've missed that modulo 4096 somehow.

Seems like cp is using 512B per transaction, judging by how slow the
transfer goes. If I use bs=500000 or even bs=1024, it goes faster.

Have a nice day :-}

Frank Rysanek
--
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/