Linux-PCI Archive on lore.kernel.org
 help / color / Atom feed
From: Jacob Keller <jacob.e.keller@intel.com>
To: Jakub Kicinski <kuba@kernel.org>, Thomas Gleixner <tglx@linutronix.de>
Cc: Nitesh Narayan Lal <nitesh@redhat.com>,
	linux-kernel@vger.kernel.org, netdev@vger.kernel.org,
	linux-pci@vger.kernel.org, intel-wired-lan@lists.osuosl.org,
	frederic@kernel.org, mtosatti@redhat.com, sassmann@redhat.com,
	jesse.brandeburg@intel.com, lihong.yang@intel.com,
	helgaas@kernel.org, jeffrey.t.kirsher@intel.com,
	jlelli@redhat.com, hch@infradead.org, bhelgaas@google.com,
	mike.marciniszyn@intel.com, dennis.dalessandro@intel.com,
	thomas.lendacky@amd.com, jiri@nvidia.com, mingo@redhat.com,
	peterz@infradead.org, juri.lelli@redhat.com,
	vincent.guittot@linaro.org, lgoncalv@redhat.com,
	Dave Miller <davem@davemloft.net>,
	Magnus Karlsson <magnus.karlsson@intel.com>,
	Saeed Mahameed <saeedm@nvidia.com>
Subject: Re: [PATCH v4 4/4] PCI: Limit pci_alloc_irq_vectors() to housekeeping CPUs
Date: Wed, 21 Oct 2020 17:27:21 -0700
Message-ID: <a1c6cdcd-7f89-5ed3-c869-ffec05929786@intel.com> (raw)
In-Reply-To: <20201021170224.55aea948@kicinski-fedora-pc1c0hjn.dhcp.thefacebook.com>



On 10/21/2020 5:02 PM, Jakub Kicinski wrote:
> On Wed, 21 Oct 2020 22:25:48 +0200 Thomas Gleixner wrote:
>> On Tue, Oct 20 2020 at 20:07, Thomas Gleixner wrote:
>>> On Tue, Oct 20 2020 at 12:18, Nitesh Narayan Lal wrote:  
>>>> However, IMHO we would still need a logic to prevent the devices from
>>>> creating excess vectors.  
>>>
>>> Managed interrupts are preventing exactly that by pinning the interrupts
>>> and queues to one or a set of CPUs, which prevents vector exhaustion on
>>> CPU hotplug.
>>>
>>> Non-managed, yes that is and always was a problem. One of the reasons
>>> why managed interrupts exist.  
>>
>> But why is this only a problem for isolation? The very same problem
>> exists vs. CPU hotplug and therefore hibernation.
>>
>> On x86 we have at max. 204 vectors available for device interrupts per
>> CPU. So assumed the only device interrupt in use is networking then any
>> machine which has more than 204 network interrupts (queues, aux ...)
>> active will prevent the machine from hibernation.
>>
>> Aside of that it's silly to have multiple queues targeted at a single
>> CPU in case of hotplug. And that's not a theoretical problem.  Some
>> power management schemes shut down sockets when the utilization of a
>> system is low enough, e.g. outside of working hours.
>>
>> The whole point of multi-queue is to have locality so that traffic from
>> a CPU goes through the CPU local queue. What's the point of having two
>> or more queues on a CPU in case of hotplug?
>>
>> The right answer to this is to utilize managed interrupts and have
>> according logic in your network driver to handle CPU hotplug. When a CPU
>> goes down, then the queue which is associated to that CPU is quiesced
>> and the interrupt core shuts down the relevant interrupt instead of
>> moving it to an online CPU (which causes the whole vector exhaustion
>> problem on x86). When the CPU comes online again, then the interrupt is
>> reenabled in the core and the driver reactivates the queue.
> 
> I think Mellanox folks made some forays into managed irqs, but I don't
> remember/can't find the details now.
> 

I remember looking into this a few years ago, and not getting very far
either.

> For networking the locality / queue per core does not always work,
> since the incoming traffic is usually spread based on a hash. Many
> applications perform better when network processing is done on a small
> subset of CPUs, and application doesn't get interrupted every 100us. 
> So we do need extra user control here.
> 
> We have a bit of a uAPI problem since people had grown to depend on
> IRQ == queue == NAPI to configure their systems. "The right way" out
> would be a proper API which allows associating queues with CPUs rather
> than IRQs, then we can use managed IRQs and solve many other problems.
> 

I think we (Intel) hit some of the same issues you mention.

I know I personally would like to see something that lets a lot of the
current driver-specific policy be moved out. I think it should be
possible to significantly simplify the abstraction used by the drivers.

> Such new API has been in the works / discussions for a while now.
> 
> (Magnus keep me honest here, if you disagree the queue API solves this.)
>

  reply index

Thread overview: 55+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-09-28 18:35 [PATCH v4 0/4] isolation: limit msix vectors " Nitesh Narayan Lal
2020-09-28 18:35 ` [PATCH v4 1/4] sched/isolation: API to get number of " Nitesh Narayan Lal
2020-09-28 18:35 ` [PATCH v4 2/4] sched/isolation: Extend nohz_full to isolate managed IRQs Nitesh Narayan Lal
2020-10-23 13:25   ` Peter Zijlstra
2020-10-23 13:29     ` Frederic Weisbecker
2020-10-23 13:57       ` Nitesh Narayan Lal
2020-10-23 13:45     ` Nitesh Narayan Lal
2020-09-28 18:35 ` [PATCH v4 3/4] i40e: Limit msix vectors to housekeeping CPUs Nitesh Narayan Lal
2020-09-28 18:35 ` [PATCH v4 4/4] PCI: Limit pci_alloc_irq_vectors() " Nitesh Narayan Lal
2020-09-28 21:59   ` Bjorn Helgaas
2020-09-29 17:46     ` Christoph Hellwig
2020-10-16 12:20   ` Peter Zijlstra
2020-10-18 18:14     ` Nitesh Narayan Lal
2020-10-19 11:11       ` Peter Zijlstra
2020-10-19 14:00         ` Marcelo Tosatti
2020-10-19 14:25           ` Nitesh Narayan Lal
2020-10-20  7:30           ` Peter Zijlstra
2020-10-20 13:00             ` Nitesh Narayan Lal
2020-10-20 13:41               ` Peter Zijlstra
2020-10-20 14:39                 ` Nitesh Narayan Lal
2020-10-22 17:47                   ` Nitesh Narayan Lal
2020-10-23  8:58                     ` Peter Zijlstra
2020-10-23 13:10                       ` Nitesh Narayan Lal
2020-10-23 21:00                         ` Thomas Gleixner
2020-10-26 13:35                           ` Nitesh Narayan Lal
2020-10-26 13:57                             ` Thomas Gleixner
2020-10-26 17:30                           ` Marcelo Tosatti
2020-10-26 19:00                             ` Thomas Gleixner
2020-10-26 19:11                               ` Marcelo Tosatti
2020-10-26 19:21                               ` Jacob Keller
2020-10-26 20:11                                 ` Thomas Gleixner
2020-10-26 21:11                                   ` Jacob Keller
2020-10-26 21:50                                     ` Thomas Gleixner
2020-10-26 22:13                                       ` Jakub Kicinski
2020-10-26 22:46                                         ` Thomas Gleixner
2020-10-26 22:52                                         ` Jacob Keller
2020-10-26 22:22                                       ` Nitesh Narayan Lal
2020-10-26 22:49                                         ` Thomas Gleixner
2020-10-26 23:08                                           ` Jacob Keller
2020-10-27 14:28                                             ` Thomas Gleixner
2020-10-27 11:47                                         ` Marcelo Tosatti
2020-10-27 14:43                                           ` Thomas Gleixner
2020-10-19 14:21         ` Frederic Weisbecker
2020-10-20 14:16   ` Thomas Gleixner
2020-10-20 16:18     ` Nitesh Narayan Lal
2020-10-20 18:07       ` Thomas Gleixner
2020-10-21 20:25         ` Thomas Gleixner
2020-10-21 21:04           ` Nitesh Narayan Lal
2020-10-22  0:02           ` Jakub Kicinski
2020-10-22  0:27             ` Jacob Keller [this message]
2020-10-22  8:28             ` Thomas Gleixner
2020-10-22 12:28           ` Marcelo Tosatti
2020-10-22 22:39             ` Thomas Gleixner
2020-10-01 15:49 ` [PATCH v4 0/4] isolation: limit msix vectors " Frederic Weisbecker
2020-10-08 21:40   ` Nitesh Narayan Lal

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=a1c6cdcd-7f89-5ed3-c869-ffec05929786@intel.com \
    --to=jacob.e.keller@intel.com \
    --cc=bhelgaas@google.com \
    --cc=davem@davemloft.net \
    --cc=dennis.dalessandro@intel.com \
    --cc=frederic@kernel.org \
    --cc=hch@infradead.org \
    --cc=helgaas@kernel.org \
    --cc=intel-wired-lan@lists.osuosl.org \
    --cc=jeffrey.t.kirsher@intel.com \
    --cc=jesse.brandeburg@intel.com \
    --cc=jiri@nvidia.com \
    --cc=jlelli@redhat.com \
    --cc=juri.lelli@redhat.com \
    --cc=kuba@kernel.org \
    --cc=lgoncalv@redhat.com \
    --cc=lihong.yang@intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=magnus.karlsson@intel.com \
    --cc=mike.marciniszyn@intel.com \
    --cc=mingo@redhat.com \
    --cc=mtosatti@redhat.com \
    --cc=netdev@vger.kernel.org \
    --cc=nitesh@redhat.com \
    --cc=peterz@infradead.org \
    --cc=saeedm@nvidia.com \
    --cc=sassmann@redhat.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=vincent.guittot@linaro.org \
    /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

Linux-PCI Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-pci/0 linux-pci/git/0.git

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

Example config snippet for mirrors

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


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