All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jens Axboe <jaxboe@fusionio.com>
To: Jeff Moyer <jmoyer@redhat.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	Zach Brown <zab@redhat.com>
Subject: Re: [patch,v2] bdi: add a user-tunable cpu_list for the bdi flusher threads
Date: Tue, 4 Dec 2012 21:27:05 +0100	[thread overview]
Message-ID: <50BE5C99.6070703@fusionio.com> (raw)
In-Reply-To: <x498v9dpnwu.fsf@segfault.boston.devel.redhat.com>

On 2012-12-04 21:23, Jeff Moyer wrote:
> Jens Axboe <jaxboe@fusionio.com> writes:
> 
>> On 2012-12-03 19:53, Jeff Moyer wrote:
>>> Hi,
>>>
>>> In realtime environments, it may be desirable to keep the per-bdi
>>> flusher threads from running on certain cpus.  This patch adds a
>>> cpu_list file to /sys/class/bdi/* to enable this.  The default is to tie
>>> the flusher threads to the same numa node as the backing device (though
>>> I could be convinced to make it a mask of all cpus to avoid a change in
>>> behaviour).
>>
>> Looks sane, and I think defaulting to the home node is a sane default.
>> One comment:
>>
>>> +	ret = cpulist_parse(buf, newmask);
>>> +	if (!ret) {
>>> +		spin_lock(&bdi->wb_lock);
>>> +		task = wb->task;
>>> +		if (task)
>>> +			get_task_struct(task);
>>> +		spin_unlock(&bdi->wb_lock);
>>
>> bdi->wb_lock needs to be bh safe. The above should have caused lockdep
>> warnings for you.
> 
> No lockdep complaints.  I'll double check that's enabled (but I usually
> have it enabled...).
> 
>>> @@ -437,6 +488,14 @@ static int bdi_forker_thread(void *ptr)
>>>  				spin_lock_bh(&bdi->wb_lock);
>>>  				bdi->wb.task = task;
>>>  				spin_unlock_bh(&bdi->wb_lock);
>>> +				mutex_lock(&bdi->flusher_cpumask_mutex);
>>> +				ret = set_cpus_allowed_ptr(task,
>>> +							bdi->flusher_cpumask);
>>> +				mutex_unlock(&bdi->flusher_cpumask_mutex);
>>
>> It'd be very useful if we had a kthread_create_cpu_on_cpumask() instead
>> of a _node() variant, since the latter could easily be implemented on
>> top of the former. But not really a show stopper for the patch...
> 
> Hmm, if it isn't too scary, I might give this a try.

Should not be, pretty much just removing the node part of the create
struct passed in and making it a cpumask. And for the on_node() case,
cpumask_of_ndoe() will do the trick.

-- 
Jens Axboe

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

WARNING: multiple messages have this Message-ID (diff)
From: Jens Axboe <jaxboe@fusionio.com>
To: Jeff Moyer <jmoyer@redhat.com>
Cc: "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	Zach Brown <zab@redhat.com>
Subject: Re: [patch,v2] bdi: add a user-tunable cpu_list for the bdi flusher threads
Date: Tue, 4 Dec 2012 21:27:05 +0100	[thread overview]
Message-ID: <50BE5C99.6070703@fusionio.com> (raw)
In-Reply-To: <x498v9dpnwu.fsf@segfault.boston.devel.redhat.com>

On 2012-12-04 21:23, Jeff Moyer wrote:
> Jens Axboe <jaxboe@fusionio.com> writes:
> 
>> On 2012-12-03 19:53, Jeff Moyer wrote:
>>> Hi,
>>>
>>> In realtime environments, it may be desirable to keep the per-bdi
>>> flusher threads from running on certain cpus.  This patch adds a
>>> cpu_list file to /sys/class/bdi/* to enable this.  The default is to tie
>>> the flusher threads to the same numa node as the backing device (though
>>> I could be convinced to make it a mask of all cpus to avoid a change in
>>> behaviour).
>>
>> Looks sane, and I think defaulting to the home node is a sane default.
>> One comment:
>>
>>> +	ret = cpulist_parse(buf, newmask);
>>> +	if (!ret) {
>>> +		spin_lock(&bdi->wb_lock);
>>> +		task = wb->task;
>>> +		if (task)
>>> +			get_task_struct(task);
>>> +		spin_unlock(&bdi->wb_lock);
>>
>> bdi->wb_lock needs to be bh safe. The above should have caused lockdep
>> warnings for you.
> 
> No lockdep complaints.  I'll double check that's enabled (but I usually
> have it enabled...).
> 
>>> @@ -437,6 +488,14 @@ static int bdi_forker_thread(void *ptr)
>>>  				spin_lock_bh(&bdi->wb_lock);
>>>  				bdi->wb.task = task;
>>>  				spin_unlock_bh(&bdi->wb_lock);
>>> +				mutex_lock(&bdi->flusher_cpumask_mutex);
>>> +				ret = set_cpus_allowed_ptr(task,
>>> +							bdi->flusher_cpumask);
>>> +				mutex_unlock(&bdi->flusher_cpumask_mutex);
>>
>> It'd be very useful if we had a kthread_create_cpu_on_cpumask() instead
>> of a _node() variant, since the latter could easily be implemented on
>> top of the former. But not really a show stopper for the patch...
> 
> Hmm, if it isn't too scary, I might give this a try.

Should not be, pretty much just removing the node part of the create
struct passed in and making it a cpumask. And for the on_node() case,
cpumask_of_ndoe() will do the trick.

-- 
Jens Axboe


  reply	other threads:[~2012-12-04 20:27 UTC|newest]

Thread overview: 30+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-12-03 18:53 [patch,v2] bdi: add a user-tunable cpu_list for the bdi flusher threads Jeff Moyer
2012-12-03 18:53 ` Jeff Moyer
2012-12-04  2:34 ` Dave Chinner
2012-12-04  2:34   ` Dave Chinner
2012-12-04 14:42   ` Jeff Moyer
2012-12-04 14:42     ` Jeff Moyer
2012-12-04 20:35     ` Dave Chinner
2012-12-04 20:35       ` Dave Chinner
2012-12-04 20:14 ` Jens Axboe
2012-12-04 20:14   ` Jens Axboe
2012-12-04 20:23   ` Jeff Moyer
2012-12-04 20:23     ` Jeff Moyer
2012-12-04 20:27     ` Jens Axboe [this message]
2012-12-04 20:27       ` Jens Axboe
2012-12-04 22:26       ` Jeff Moyer
2012-12-04 22:26         ` Jeff Moyer
2012-12-05  7:43         ` Jens Axboe
2012-12-05  7:43           ` Jens Axboe
2012-12-06 18:01         ` Tejun Heo
2012-12-06 18:01           ` Tejun Heo
2012-12-06 18:08           ` Jeff Moyer
2012-12-06 18:08             ` Jeff Moyer
2012-12-06 18:13             ` Tejun Heo
2012-12-06 18:13               ` Tejun Heo
2012-12-06 18:19           ` Jens Axboe
2012-12-06 18:19             ` Jens Axboe
2012-12-06 18:22             ` Tejun Heo
2012-12-06 18:22               ` Tejun Heo
2012-12-06 18:33               ` Jeff Moyer
2012-12-06 18:33                 ` Jeff Moyer

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=50BE5C99.6070703@fusionio.com \
    --to=jaxboe@fusionio.com \
    --cc=jmoyer@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=zab@redhat.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.