linux-scsi.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Bart Van Assche <bvanassche@acm.org>
To: Zhu Yanjun <yanjun.zhu@linux.dev>,
	Bob Pearson <rpearsonhpe@gmail.com>,
	Leon Romanovsky <leon@kernel.org>,
	zyjzyj2000@gmail.com, jgg@ziepe.ca, linux-rdma@vger.kernel.org,
	matsuda-daisuke@fujitsu.com, shinichiro.kawasaki@wdc.com,
	linux-scsi@vger.kernel.org, Zhu Yanjun <yanjun.zhu@intel.com>
Subject: Re: [PATCH 1/1] Revert "RDMA/rxe: Add workqueue support for rxe tasks"
Date: Wed, 4 Oct 2023 10:43:20 -0700	[thread overview]
Message-ID: <552f2342-e800-43bc-b859-d73297ce940f@acm.org> (raw)
In-Reply-To: <2fcef3c8-808e-8e6a-b23d-9f1b3f98c1f9@linux.dev>

On 10/3/23 20:41, Zhu Yanjun wrote:
> 在 2023/9/27 4:24, Bart Van Assche 写道:
>> diff --git a/drivers/infiniband/sw/rxe/rxe_task.c 
>> b/drivers/infiniband/sw/rxe/rxe_task.c
>> index 1501120d4f52..6cd5d5a7a316 100644
>> --- a/drivers/infiniband/sw/rxe/rxe_task.c
>> +++ b/drivers/infiniband/sw/rxe/rxe_task.c
>> @@ -10,7 +10,7 @@ static struct workqueue_struct *rxe_wq;
>>
>>   int rxe_alloc_wq(void)
>>   {
>> -       rxe_wq = alloc_workqueue("rxe_wq", WQ_UNBOUND, WQ_MAX_ACTIVE);
>> +       rxe_wq = alloc_workqueue("rxe_wq", WQ_UNBOUND, 1);
>>          if (!rxe_wq)
>>                  return -ENOMEM;
> 
> Hi, Bart
> 
> With the above commit, I still found a similar problem. But the problem 
> occurs very rarely. With the following, to now, the problem does not occur.
> 
> diff --git a/drivers/infiniband/sw/rxe/rxe_task.c 
> b/drivers/infiniband/sw/rxe/rxe_task.c
> index 1501120d4f52..3189c3705295 100644
> --- a/drivers/infiniband/sw/rxe/rxe_task.c
> +++ b/drivers/infiniband/sw/rxe/rxe_task.c
> @@ -10,7 +10,7 @@ static struct workqueue_struct *rxe_wq;
> 
>   int rxe_alloc_wq(void)
>   {
> -       rxe_wq = alloc_workqueue("rxe_wq", WQ_UNBOUND, WQ_MAX_ACTIVE);
> +       rxe_wq = alloc_workqueue("rxe_wq", WQ_HIGHPRI | WQ_UNBOUND, 1);
>          if (!rxe_wq)
>                  return -ENOMEM;
> 
> 
> And with the tasklet, this problem also does not occur.
> 
> With "alloc_workqueue("rxe_wq", WQ_HIGHPRI | WQ_UNBOUND, 1);", an 
> ordered workqueue with high priority is allocated.
> 
> To the same number of work item, the ordered workqueue has the same 
> runing time with the tasklet. But the tasklet is based on softirq. Its 
> overhead on scheduling is less than workqueue. So in theory, tasklet's 
> performance should be better than the ordered workqueue.

Hi Zhu,

Thank you for having reported this. I'm OK with integrating the above 
change in my patch. However, code changes must be motivated. Do you 
perhaps have an explanation of why WQ_HIGHPRI makes the issue disappear 
that you observed?

Regarding tasklets: tasklets are a nightmare from the point of view of
the Linux kernel scheduler. As an example, these may make it impossible
for the scheduler to schedule real-time threads in time.

Thanks,

Bart.


  reply	other threads:[~2023-10-04 17:43 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-09-22 16:32 [PATCH 1/1] Revert "RDMA/rxe: Add workqueue support for rxe tasks" Zhu Yanjun
2023-09-22 16:42 ` Bart Van Assche
2023-09-26  9:43   ` Leon Romanovsky
2023-09-26  9:43 ` Leon Romanovsky
2023-09-26 14:06   ` Leon Romanovsky
2023-09-26 17:05     ` Bart Van Assche
2023-09-26 18:34       ` Bob Pearson
2023-09-26 20:24         ` Bart Van Assche
2023-09-27  0:08           ` Rain River
2023-09-27 16:36           ` Bob Pearson
2023-09-27 16:51           ` Bob Pearson
2023-10-01  6:30             ` Leon Romanovsky
2023-10-04 17:44               ` Bart Van Assche
2023-10-04  3:41           ` Zhu Yanjun
2023-10-04 17:43             ` Bart Van Assche [this message]
2023-10-04 18:38               ` Jason Gunthorpe
2023-10-05  9:25                 ` Zhu Yanjun
2023-10-05 14:21                   ` Jason Gunthorpe
2023-10-05 14:50                     ` Bart Van Assche
2023-10-05 15:56                       ` Jason Gunthorpe
2023-10-06 15:58                         ` Bob Pearson
2023-10-07  0:35                           ` Zhu Yanjun
2023-10-08 16:01                       ` Zhu Yanjun
2023-10-08 17:09                         ` Leon Romanovsky
2023-10-10  4:53                         ` Daisuke Matsuda (Fujitsu)
2023-10-10 16:09                           ` Jason Gunthorpe
2023-10-10 21:29                             ` Bart Van Assche
2023-10-11 15:51                               ` Jason Gunthorpe
2023-10-11 20:14                                 ` Bart Van Assche
2023-10-11 23:12                                   ` Jason Gunthorpe
2023-10-12 11:49                                     ` Zhu Yanjun
2023-10-12 15:38                                       ` Bob Pearson

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=552f2342-e800-43bc-b859-d73297ce940f@acm.org \
    --to=bvanassche@acm.org \
    --cc=jgg@ziepe.ca \
    --cc=leon@kernel.org \
    --cc=linux-rdma@vger.kernel.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=matsuda-daisuke@fujitsu.com \
    --cc=rpearsonhpe@gmail.com \
    --cc=shinichiro.kawasaki@wdc.com \
    --cc=yanjun.zhu@intel.com \
    --cc=yanjun.zhu@linux.dev \
    --cc=zyjzyj2000@gmail.com \
    /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;
as well as URLs for NNTP newsgroup(s).