Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
Subject: Re: [RFC] mm: optimise generic_file_read_iter
To:     Al Viro <viro@zeniv.linux.org.uk>,
        Pavel Begunkov <asml.silence@gmail.com>
Cc:     Andrew Morton <akpm@linux-foundation.org>, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
References: <07bd408d6cad95166b776911823b40044160b434.1628248975.git.asml.silence@gmail.com>
 <YQ09tqMda2ke2qHy@zeniv-ca.linux.org.uk>
From:   Jens Axboe <axboe@kernel.dk>
Message-ID: <cd31510a-2065-6078-468d-bbff816f818d@kernel.dk>
Date:   Fri, 6 Aug 2021 11:18:28 -0600
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101
 Thunderbird/68.10.0
MIME-Version: 1.0
In-Reply-To: <YQ09tqMda2ke2qHy@zeniv-ca.linux.org.uk>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Precedence: bulk

On 8/6/21 7:48 AM, Al Viro wrote:
> On Fri, Aug 06, 2021 at 12:42:43PM +0100, Pavel Begunkov wrote:
>> Unless direct I/O path of generic_file_read_iter() ended up with an
>> error or a short read, it doesn't use inode. So, load inode and size
>> later, only when they're needed. This cuts two memory reads and also
>> imrpoves code generation, e.g. loads from stack.
> 
> ... and the same question here.
> 
>> NOTE: as a side effect, it reads inode->i_size after ->direct_IO(), and
>> I'm not sure whether that's valid, so would be great to get feedback
>> from someone who knows better.
> 
> Ought to be safe, I think, but again, how much effect have you observed
> from the patch?

Ran a quick test here, doing polled IO (~3.3M IOPS) and we reduce the
overhead of generic_file_read_iter() from 1.5% of the runtime to 1.2%.
Noticeable. Will improve once we stop digging into the inode on the
io_uring side.

Anyway, just one data point, perhaps Pavel has some too.


-- 
Jens Axboe