From mboxrd@z Thu Jan  1 00:00:00 1970
From: Shaohua Li <shli@kernel.org>
Subject: Re: [PATCH 0/2] md: Add support for Multiple PPLs
Date: Fri, 25 Aug 2017 14:53:00 -0700
Message-ID: <20170825215300.xgkdklgi4lxvhxrx@kernel.org>
References: <20170816151346.23382-1-pawel.baldysiak@intel.com>
 <20170817180331.baxoqhgbqi5q6fvx@kernel.org>
 <4e72946d-3bdc-8a69-0b44-591570aae3a2@intel.com>
 <20170821161426.of5z62r45unlh2en@kernel.org>
 <c9d77b2c-f1ab-bcce-5441-5b8fa9bede13@intel.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <linux-raid-owner@vger.kernel.org>
Content-Disposition: inline
In-Reply-To: <c9d77b2c-f1ab-bcce-5441-5b8fa9bede13@intel.com>
Sender: linux-raid-owner@vger.kernel.org
To: Pawel Baldysiak <pawel.baldysiak@intel.com>
Cc: linux-raid@vger.kernel.org
List-Id: linux-raid.ids

On Fri, Aug 25, 2017 at 10:02:07PM +0200, Pawel Baldysiak wrote:
> On 08/21/2017 06:14 PM, Shaohua Li wrote> Can you elaborate more?
> > 
> Storage presented to the host may have a RAID on the back-end. For NVMe
> SSDs, the 1.3 specification provided a field to advertise chunk
> boundaries: Identify Namespace NOIOB. We need to span the entire stripe
> to utilize the total available capacity, otherwise we'll repeatedly
> write to only a subset, increasing write amplification factor. The new
> PPL approach is designed to access the full capacity.

Ok, this makes sense. The 1MB area looks arbitrary though. What if the
chunk is 2MB? Could we make it configurable?

Thanks,
Shaohua