[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190315133017.lnr5cvtapo5nxilu@MacBook-Pro-91.local>
Date: Fri, 15 Mar 2019 09:30:18 -0400
From: Josef Bacik <josef@...icpanda.com>
To: Christoph Hellwig <hch@....de>
Cc: Jianchao Wang <jianchao.w.wang@...cle.com>, axboe@...nel.dk,
jthumshirn@...e.de, hare@...e.de, josef@...icpanda.com,
bvanassche@....org, sagi@...mberg.me, keith.busch@...el.com,
jsmart2021@...il.com, linux-block@...r.kernel.org,
linux-nvme@...ts.infradead.org, linux-kernel@...r.kernel.org
Subject: Re: [PATCH 0/8]: blk-mq: use static_rqs to iterate busy tags
On Fri, Mar 15, 2019 at 10:20:20AM +0100, Christoph Hellwig wrote:
> On Fri, Mar 15, 2019 at 04:57:36PM +0800, Jianchao Wang wrote:
> > Hi Jens
> >
> > As we know, there is a risk of accesing stale requests when iterate
> > in-flight requests with tags->rqs[] and this has been talked in following
> > thread,
> > [1] https://marc.info/?l=linux-scsi&m=154511693912752&w=2
> > [2] https://marc.info/?l=linux-block&m=154526189023236&w=2
>
> I'd rather take one step back and figure out why we are iterating
> the busy requests. There really shouldn't be any reason why a driver
> is even doings that (vs some error handling helpers in the core
> block code that can properly synchronize).
I use it in NBD to error out any pending requests for forced disconnects. I'd
be happy to use some other blessed interface, I'm not married to this one.
Thanks,
Josef
Powered by blists - more mailing lists