[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20200626082603.GB23888@lst.de>
Date: Fri, 26 Jun 2020 10:26:03 +0200
From: Christoph Hellwig <hch@....de>
To: Baolin Wang <baolin.wang@...ux.alibaba.com>
Cc: Christoph Hellwig <hch@....de>, kbusch@...nel.org, axboe@...com,
sagi@...mberg.me, baolin.wang7@...il.com,
linux-nvme@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 1/2] nvme: Add Arbitration Burst support
On Wed, Jun 24, 2020 at 03:58:54PM +0800, Baolin Wang wrote:
> On Wed, Jun 24, 2020 at 08:52:58AM +0200, Christoph Hellwig wrote:
> > On Wed, Jun 24, 2020 at 02:49:57PM +0800, Baolin Wang wrote:
> > > >From the NVMe spec, "In order to make efficient use of the non-volatile
> > > memory, it is often advantageous to execute multiple commands from a
> > > Submission Queue in parallel. For Submission Queues that are using
> > > weighted round robin with urgent priority class or round robin
> > > arbitration, host software may configure an Arbitration Burst setting".
> > > Thus add Arbitration Burst setting support.
> >
> > What is the value add of doing this in the kernel? Wouldn't a nvme-cli
> > subcommand to just set the arbitration burst to the recommended value,
> > either as a saved or current value be both more useful and also cause
> > less kernel bloat?
>
> Yes, that's another way to configure the RAB, but for some simple and
> frequently-used usage cases, we just want to use the recommanded arbitration
> burst as default without bothering the nvme-cli tool every reset time.
Please look up how saved features work in nvme.
Powered by blists - more mailing lists