LKML Archive on lore.kernel.org
 help / color / Atom feed
From: John Garry <john.garry@huawei.com>
To: Ming Lei <ming.lei@redhat.com>, <maz@kernel.org>
Cc: <tglx@linutronix.de>, <chenxiang66@hisilicon.com>,
	<bigeasy@linutronix.de>, <linux-kernel@vger.kernel.org>,
	<hare@suse.com>, <hch@lst.de>, <axboe@kernel.dk>,
	<bvanassche@acm.org>, <peterz@infradead.org>, <mingo@redhat.com>
Subject: Re: [PATCH RFC 1/1] genirq: Make threaded handler use irq affinity for managed interrupt
Date: Tue, 10 Dec 2019 09:45:45 +0000
Message-ID: <28424a58-1159-c3f9-1efb-f1366993afcf@huawei.com> (raw)
In-Reply-To: <20191210014335.GA25022@ming.t460p>

On 10/12/2019 01:43, Ming Lei wrote:
> On Mon, Dec 09, 2019 at 02:30:59PM +0000, John Garry wrote:
>> On 07/12/2019 08:03, Ming Lei wrote:
>>> On Fri, Dec 06, 2019 at 10:35:04PM +0800, John Garry wrote:
>>>> Currently the cpu allowed mask for the threaded part of a threaded irq
>>>> handler will be set to the effective affinity of the hard irq.
>>>>
>>>> Typically the effective affinity of the hard irq will be for a single cpu. As such,
>>>> the threaded handler would always run on the same cpu as the hard irq.
>>>>
>>>> We have seen scenarios in high data-rate throughput testing that the cpu
>>>> handling the interrupt can be totally saturated handling both the hard
>>>> interrupt and threaded handler parts, limiting throughput.
>>>

Hi Ming,

>>> Frankly speaking, I never observed that single CPU is saturated by one storage
>>> completion queue's interrupt load. Because CPU is still much quicker than
>>> current storage device.
>>>
>>> If there are more drives, one CPU won't handle more than one queue(drive)'s
>>> interrupt if (nr_drive * nr_hw_queues) < nr_cpu_cores.
>>
>> Are things this simple? I mean, can you guarantee that fio processes are
>> evenly distributed as such?
> 
> That is why I ask you for the details of your test.
> 
> If you mean hisilicon SAS,

Yes, it is.

  the interrupt load should have been distributed
> well given the device has multiple reply queues for distributing interrupt
> load.
> 
>>
>>>
>>> So could you describe your case in a bit detail? Then we can confirm
>>> if this change is really needed.
>>
>> The issue is that the CPU is saturated in servicing the hard and threaded
>> part of the interrupt together - here's the sort of thing which we saw
>> previously:
>> Before:
>> CPU	%usr	%sys	%irq	%soft	%idle
>> all	2.9	13.1	1.2	4.6	78.2				
>> 0	0.0	29.3	10.1	58.6	2.0
>> 1	18.2	39.4	0.0	1.0	41.4
>> 2	0.0	2.0	0.0	0.0	98.0
>>
>> CPU0 has no effectively no idle.
> 
> The result just shows the saturation, we need to root cause it instead
> of workaround it via random changes.
> 
>>
>> Then, by allowing the threaded part to roam:
>> After:
>> CPU	%usr	%sys	%irq	%soft	%idle
>> all	3.5	18.4	2.7	6.8	68.6
>> 0	0.0	20.6	29.9	29.9	19.6
>> 1	0.0	39.8	0.0	50.0	10.2
>>
>> Note: I think that I may be able to reduce the irq hard part load in the
>> endpoint driver, but not that much such that we see still this issue.
>>
>>>
>>>>
>>>> For when the interrupt is managed, allow the threaded part to run on all
>>>> cpus in the irq affinity mask.
>>>
>>> I remembered that performance drop is observed by this approach in some
>>> test.
>>
>>  From checking the thread about the NVMe interrupt swamp, just switching to
>> threaded handler alone degrades performance. I didn't see any specific
>> results for this change from Long Li - https://lkml.org/lkml/2019/8/21/128
> 
> I am pretty clear the reason for Azure, which is caused by aggressive interrupt
> coalescing, and this behavior shouldn't be very common, and it can be
> addressed by the following patch:
> 
> http://lists.infradead.org/pipermail/linux-nvme/2019-November/028008.html
> 
> Then please share your lockup story, such as, which HBA/drivers, test steps,
> if you complete IOs from multiple disks(LUNs) on single CPU, if you have
> multiple queues, how many active LUNs involved in the test, ...

There is no lockup, just a potential performance boost in this change.

My colleague Xiang Chen can provide specifics of the test, as he is the 
one running it.

But one key bit of info - which I did not think most relevant before - 
that is we have 2x SAS controllers running the throughput test on the 
same host.

As such, the completion queue interrupts would be spread identically 
over the CPUs for each controller. I notice that ARM GICv3 ITS interrupt 
controller (which we use) does not use the generic irq matrix allocator, 
which I think would really help with this.

Hi Marc,

Is there any reason for which we couldn't utilise of the generic irq 
matrix allocator for GICv3?

Thanks,
John

  reply index

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-12-06 14:35 [PATCH RFC 0/1] Threaded handler uses irq affinity for when the interrupt is managed John Garry
2019-12-06 14:35 ` [PATCH RFC 1/1] genirq: Make threaded handler use irq affinity for managed interrupt John Garry
2019-12-06 15:22   ` Marc Zyngier
2019-12-06 16:16     ` John Garry
2019-12-07  8:03   ` Ming Lei
2019-12-09 14:30     ` John Garry
2019-12-09 15:09       ` Hannes Reinecke
2019-12-09 15:17         ` Marc Zyngier
2019-12-09 15:25           ` Hannes Reinecke
2019-12-09 15:36             ` Marc Zyngier
2019-12-09 15:49           ` Qais Yousef
2019-12-09 15:55             ` Marc Zyngier
2019-12-10  1:43       ` Ming Lei
2019-12-10  9:45         ` John Garry [this message]
2019-12-10 10:06           ` Ming Lei
2019-12-10 10:28           ` Marc Zyngier
2019-12-10 10:59             ` John Garry
2019-12-10 11:36               ` Marc Zyngier
2019-12-10 12:05                 ` John Garry
2019-12-10 18:32                   ` Marc Zyngier
2019-12-11  9:41                     ` John Garry
2019-12-13 10:07                       ` John Garry
2019-12-13 10:31                         ` Marc Zyngier
2019-12-13 12:08                           ` John Garry
2019-12-14 10:59                             ` Marc Zyngier
2019-12-11 17:09         ` John Garry
2019-12-12 22:38           ` Ming Lei
2019-12-13 11:12             ` John Garry
2019-12-13 13:18               ` Ming Lei
2019-12-13 15:43                 ` John Garry
2019-12-13 17:12                   ` Ming Lei
2019-12-13 17:50                     ` John Garry
2019-12-14 13:56                   ` Marc Zyngier
2019-12-16 10:47                     ` John Garry
2019-12-16 11:40                       ` Marc Zyngier
2019-12-16 14:17                         ` John Garry
2019-12-16 18:00                           ` Marc Zyngier
2019-12-16 18:50                             ` John Garry
2019-12-20 11:30                               ` John Garry
2019-12-20 14:43                                 ` Marc Zyngier
2019-12-20 15:38                                   ` John Garry
2019-12-20 16:16                                     ` Marc Zyngier
2019-12-20 23:31                                     ` Ming Lei
2019-12-23  9:07                                       ` Marc Zyngier
2019-12-23 10:26                                         ` John Garry
2019-12-23 10:47                                           ` Marc Zyngier
2019-12-23 11:35                                             ` John Garry
2019-12-24  1:59                                             ` Ming Lei
2019-12-24 11:20                                               ` Marc Zyngier
2019-12-25  0:48                                                 ` Ming Lei
2020-01-02 10:35                                                   ` John Garry
2020-01-03  0:46                                                     ` Ming Lei
2020-01-03 10:41                                                       ` John Garry
2020-01-03 11:29                                                         ` Ming Lei
2020-01-03 11:50                                                           ` John Garry
2020-01-04 12:03                                                             ` Ming Lei
2020-05-30  7:46 ` [tip: irq/core] irqchip/gic-v3-its: Balance initial LPI affinity across CPUs tip-bot2 for Marc Zyngier

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=28424a58-1159-c3f9-1efb-f1366993afcf@huawei.com \
    --to=john.garry@huawei.com \
    --cc=axboe@kernel.dk \
    --cc=bigeasy@linutronix.de \
    --cc=bvanassche@acm.org \
    --cc=chenxiang66@hisilicon.com \
    --cc=hare@suse.com \
    --cc=hch@lst.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=ming.lei@redhat.com \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /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

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git