From: Chaitanya Kulkarni <chaitanyak@nvidia.com>
To: Guixin Liu <kanie@linux.alibaba.com>
Cc: "linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>,
"hch@lst.de" <hch@lst.de>, "sagi@grimberg.me" <sagi@grimberg.me>
Subject: Re: [PATCH] nvmet: make nvmet_wq visible in sysfs
Date: Wed, 30 Oct 2024 06:33:58 +0000 [thread overview]
Message-ID: <e666ea1d-2b6b-45dd-8903-2269e2143c95@nvidia.com> (raw)
In-Reply-To: <a6718c68-6b0e-4a5e-af3a-c8ee98911ce3@linux.alibaba.com>
On 10/29/24 18:44, Guixin Liu wrote:
>
> 在 2024/10/30 03:52, Chaitanya Kulkarni 写道:
>> On 10/28/24 23:46, Guixin Liu wrote:
>>> 在 2024/10/29 13:04, Chaitanya Kulkarni 写道:
>>>> On 10/28/24 18:49, Guixin Liu wrote:
>>>>> Make nvmet_wq visible in sysfs, allowing for tuning the it's attr
>>>>> through sysfs.
>>>>>
>>>>> Signed-off-by: Guixin Liu<kanie@linux.alibaba.com>
>>>>> ---
>>>> do you happened have a usecase for this?
>>>>
>>>> -ck
>>> Sometimes, in order to respond promptly to certain events or
>>>
>>> manage commands, we need to reserve resources and partition
>>>
>>> the CPU cores. For example, if there are 4 cores available,
>>>
>>> we can initially allocate them by dedicating one core for
>>>
>>> management while the remaining 3 cores are specifically for handling
>>> IO.
>>>
>>> Best Regards,
>>>
>>> Guixin Liu
>>>
>> I'm aware of exposing tunables through sysfs and it's benefits, my
>> question
>> was do you have a setup where this setting is needed currently ?
>>
>> I've always been asked to for the usecase on a patch when we expose
>> something
>> out of kernel that is solving the problem in the deployment ...
>>
>> -ck
>
> I need serverve some cpu core to do other things, such as handle events
>
> and managements, so that the nvmet_wq can't running on all cpu cores,
>
> currently, I restrict it by setting the cpumask of nvmet_wq(that's why
>
> I expose nvmet_wq to sysfs).
>
> Best Regards,
>
> Guixin Liu
>
>>
Can you please explain your setup ? e.g. transport tcp/rdma/fc, device
backend file/block etc ?
so nvmet_wq's CPU consumption is so high, that it doesn't have bandwidth
to handle events and managements ?
Can you please explain the workload and what kind of events and managements
handling is needed where you need to restrict the nvmet_wq with CPUMASK ?
The only reason I'm asking that I've not seen this scenario so far in
the many
many deployments since we've added the nvmet_wq and I'd really like to learn
about scenario.
-ck
next prev parent reply other threads:[~2024-10-30 6:36 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-29 1:49 [PATCH] nvmet: make nvmet_wq visible in sysfs Guixin Liu
2024-10-29 5:04 ` Chaitanya Kulkarni
2024-10-29 6:46 ` Guixin Liu
2024-10-29 19:52 ` Chaitanya Kulkarni
2024-10-30 0:49 ` Chaitanya Kulkarni
2024-10-30 1:44 ` Guixin Liu
2024-10-30 5:53 ` hch
2024-10-30 6:44 ` Guixin Liu
2024-10-30 6:33 ` Chaitanya Kulkarni [this message]
2024-10-30 11:20 ` Guixin Liu
2024-10-30 18:38 ` Chaitanya Kulkarni
2024-10-31 2:01 ` Guixin Liu
2024-10-31 2:45 ` Chaitanya Kulkarni
2024-10-31 6:39 ` Chaitanya Kulkarni
2024-10-31 6:55 ` Guixin Liu
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=e666ea1d-2b6b-45dd-8903-2269e2143c95@nvidia.com \
--to=chaitanyak@nvidia.com \
--cc=hch@lst.de \
--cc=kanie@linux.alibaba.com \
--cc=linux-nvme@lists.infradead.org \
--cc=sagi@grimberg.me \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox