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: [PATCH 0/2] task_put batching
To:     Pavel Begunkov <asml.silence@gmail.com>, io-uring@vger.kernel.org,
        linux-kernel@vger.kernel.org
References: <cover.1595021626.git.asml.silence@gmail.com>
 <cf209c59-547e-0a69-244d-7c1fec00a978@kernel.dk>
 <edd8e7e4-efcf-0af1-c5d6-104635b65eb3@gmail.com>
From:   Jens Axboe <axboe@kernel.dk>
Message-ID: <a2eaec48-8211-07e2-2d8a-edc8af755ebc@kernel.dk>
Date:   Sun, 19 Jul 2020 12:49:57 -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: <edd8e7e4-efcf-0af1-c5d6-104635b65eb3@gmail.com>
Content-Type: text/plain; charset=utf-8
Content-Language: en-US
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 7/19/20 5:15 AM, Pavel Begunkov wrote:
> On 18/07/2020 17:37, Jens Axboe wrote:
>> On 7/18/20 2:32 AM, Pavel Begunkov wrote:
>>> For my a bit exaggerated test case perf continues to show high CPU
>>> cosumption by io_dismantle(), and so calling it io_iopoll_complete().
>>> Even though the patch doesn't yield throughput increase for my setup,
>>> probably because the effect is hidden behind polling, but it definitely
>>> improves relative percentage. And the difference should only grow with
>>> increasing number of CPUs. Another reason to have this is that atomics
>>> may affect other parallel tasks (e.g. which doesn't use io_uring)
>>>
>>> before:
>>> io_iopoll_complete: 5.29%
>>> io_dismantle_req:   2.16%
>>>
>>> after:
>>> io_iopoll_complete: 3.39%
>>> io_dismantle_req:   0.465%
>>
>> Still not seeing a win here, but it's clean and it _should_ work. For
> 
> Well, if this thing is useful, it'd be hard to quantify, because active
> polling would hide it. I think, it'd need to apply a lot of isolated

It should be very visible in my setup, as we're CPU limited, not device
limited. Hence it makes it very easy to show CPU gains, as they directly
translate into improved performance.

> pressure on cache synchronisation (e.g. spam with barriers), or try to
> create and measure an atomic heavy task pinned to another core. Don't
> worth the effort IMHO.
> `
> Just out of curiosity, let me ask how do you test it?
> - is it a VM?
> - how many cores and threads do you use?
> - how many io_uring instances you have? Per thread?
> - Is it all goes to a single NVMe SSD?

It's not a VM, it's a normal box. I'm using just one CPU, one thread,
and just one NVMe device. That's my goto test for seeing if we reclaimed
some CPU cycles.

-- 
Jens Axboe