[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CACVXFVNOAc1HEPmfu9n8vMjqY2hK8fVqe4Em-g+dvSRLavpO8w@mail.gmail.com>
Date: Tue, 6 Nov 2018 22:56:52 +0800
From: Ming Lei <tom.leiming@...il.com>
To: Johannes Thumshirn <jthumshirn@...e.de>
Cc: Ming Lei <ming.lei@...hat.com>, Jens Axboe <axboe@...com>,
linux-block <linux-block@...r.kernel.org>,
Hannes Reinecke <hare@...e.de>,
Linux Kernel Mailing List <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 Tue, Nov 6, 2018 at 8:35 PM Johannes Thumshirn <jthumshirn@...e.de> wrote:
>
> On 05/11/2018 13:01, Ming Lei wrote:
> > 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.
>
>
> Hi Ming,
>
> I've received a blktrace from our customer showing the issue [1].
>
> In this example trace they've submitted (contiguous) 64K I/Os and
> without this patch, they're seeing a lot of splits as indicated by the
> trace.
>
> With the patch applied the I/O is directly issued to the LLDD without
> the splits.
>
> [1] http://beta.suse.com/private/jthumshirn/blktrace.txt
blktrace won't help on this issue because .bv_offset isn't recorded.
This patch makes sense on >4KB PAGE_SIZE. If your issue happens on
ARCH with 4K PAGE_SIZE, maybe you should root cause why it makes a
difference on iSer. And it is highly possible there is bug somewhere.
As I mentioned, the description of huge page part in the commit log is
misleading,
and it has to be fixed. Otherwise, the patch itself is fine:
Reviewed-by: Ming Lei <ming.lei@...hat.com>
Thanks
Ming Lei
Powered by blists - more mailing lists