From mboxrd@z Thu Jan 1 00:00:00 1970 From: Phillip Lougher Subject: Re: [announce] Squashfs2.0-alpha released (compressed filesystem) Date: Fri, 21 May 2004 16:53:51 +0100 Sender: linux-fsdevel-owner@vger.kernel.org Message-ID: References: <1085153863.6103.35.camel@patibmrh9> Mime-Version: 1.0 Content-Type: text/plain; charset=US-ASCII Content-Transfer-Encoding: 7bit Cc: linux-fsdevel@vger.kernel.org Return-path: Received: from rproxy.gmail.com ([64.233.170.204]:52088 "HELO mproxy.gmail.com") by vger.kernel.org with SMTP id S265909AbUEUPxw (ORCPT ); Fri, 21 May 2004 11:53:52 -0400 Received: by mproxy.gmail.com with SMTP id 65so65197rnd for ; Fri, 21 May 2004 08:53:51 -0700 (PDT) To: Pat LaVarre In-Reply-To: <1085153863.6103.35.camel@patibmrh9> List-Id: linux-fsdevel.vger.kernel.org On 21 May 2004 09:37:43 -0600, Pat LaVarre wrote: > > > http://squashfs.sourceforge.net > > increased the block size to 64K ... > > An aligned 64 KiB, as DVD/ CD-RW rewards in thruput? > Alignment to 64K block boundaries would impair compression. All filesystem objects (data, metadata etc). are packed together on a bye alignment to maximize compression. The increase to 64K blocks do increase I/O throughput by the simple fact there's more data read per seek. For CD/DVD the fragments also tend to help by minimizing seeking to read adjacent files. > Pat LaVarre > >