[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20181105120153.GD12367@ming.t460p>
Date: Mon, 5 Nov 2018 20:01:54 +0800
From: Ming Lei <ming.lei@...hat.com>
To: Johannes Thumshirn <jthumshirn@...e.de>
Cc: Jens Axboe <axboe@...com>,
Linux Block Layer Mailinglist <linux-block@...r.kernel.org>,
Hannes Reinecke <hare@...e.de>,
Linux Kernel Mailinglist <linux-kernel@...r.kernel.org>,
Jan Kara <jack@...e.cz>, Sagi Grimberg <sagi@...mberg.me>
Subject: Re: [PATCH] block: respect virtual boundary mask in bvecs
On Mon, Nov 05, 2018 at 12:50:50PM +0100, Johannes Thumshirn wrote:
> On 05/11/2018 11:55, Ming Lei wrote:
> > On Mon, Nov 05, 2018 at 11:23:01AM +0100, Johannes Thumshirn wrote:
> >> With drivers like iSer we are seeing a lot of bio splitting and smaller I/Os
> >> being submitted to the driver.
> >>
> >> The root cause of this issue that the virtual boundary mask code does not take
> >> into consideration that some of the memory segments in the SG list may have
> >> come from a huge memory page that is being managed in the SG list as 4K
> >
> > I guess you mean something like 64K PAGE_SIZE, instead of huge page.
>
> No I mean like a 2M page from an upper layer.
If you mean the real huge page, this patch shouldn't have made a difference
because bio_vec->bv_offset is in [0, PAGE_SIZE), and iSer sets virt
boundary as 4K - 1.
However, things will change after multipage bvec is introduced.
Thanks,
Ming
Powered by blists - more mailing lists