mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Yunsheng Lin <linyunsheng@huawei.com>
To: "Jesper Dangaard Brouer" <hawk@kernel.org>,
	"Toke Høiland-Jørgensen" <toke@redhat.com>,
	davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com
Cc: <zhangkun09@huawei.com>, <fanghaiqing@huawei.com>,
	<liuyonglong@huawei.com>, Robin Murphy <robin.murphy@arm.com>,
	Alexander Duyck <alexander.duyck@gmail.com>,
	IOMMU <iommu@lists.linux.dev>,
	Andrew Morton <akpm@linux-foundation.org>,
	Eric Dumazet <edumazet@google.com>,
	Ilias Apalodimas <ilias.apalodimas@linaro.org>,
	<linux-mm@kvack.org>, <linux-kernel@vger.kernel.org>,
	<netdev@vger.kernel.org>,
	kernel-team <kernel-team@cloudflare.com>
Subject: Re: [PATCH net-next v3 3/3] page_pool: fix IOMMU crash when driver has already unbound
Date: Sat, 26 Oct 2024 15:33:28 +0800	[thread overview]
Message-ID: <204272e7-82c3-4437-bb0d-2c3237275d1f@huawei.com> (raw)
In-Reply-To: <0c146fb8-4c95-4832-941f-dfc3a465cf91@kernel.org>

On 2024/10/25 22:07, Jesper Dangaard Brouer wrote:

...

> 
>>> You and Jesper seems to be mentioning a possible fact that there might
>>> be 'hundreds of gigs of memory' needed for inflight pages, it would be nice
>>> to provide more info or reasoning above why 'hundreds of gigs of memory' is
>>> needed here so that we don't do a over-designed thing to support recording
>>> unlimited in-flight pages if the driver unbound stalling turns out impossible
>>> and the inflight pages do need to be recorded.
>>
>> I don't have a concrete example of a use that will blow the limit you
>> are setting (but maybe Jesper does), I am simply objecting to the
>> arbitrary imposing of any limit at all. It smells a lot of "640k ought
>> to be enough for anyone".
>>
> 
> As I wrote before. In *production* I'm seeing TCP memory reach 24 GiB
> (on machines with 384GiB memory). I have attached a grafana screenshot
> to prove what I'm saying.
> 
> As my co-worker Mike Freemon, have explain to me (and more details in
> blogposts[1]). It is no coincident that graph have a strange "sealing"
> close to 24 GiB (on machines with 384GiB total memory).  This is because
> TCP network stack goes into a memory "under pressure" state when 6.25%
> of total memory is used by TCP-stack. (Detail: The system will stay in
> that mode until allocated TCP memory falls below 4.68% of total memory).
> 
>  [1] https://blog.cloudflare.com/unbounded-memory-usage-by-tcp-for-receive-buffers-and-how-we-fixed-it/

Thanks for the info.

> 
> 
>>> I guess it is common sense to start with easy one until someone complains
>>> with some testcase and detailed reasoning if we need to go the hard way as
>>> you and Jesper are also prefering waiting over having to record the inflight
>>> pages.
>>
>> AFAIU Jakub's comment on his RFC patch for waiting, he was suggesting
>> exactly this: Add the wait, and see if the cases where it can stall turn
>> out to be problems in practice.
> 
> +1
> 
> I like Jakub's approach.

As mentioned in Toke's comment, I am still not convinced that there is some
easy way of waiting here, doing the kick in the kernel space is hard enough,
I am not even sure if kick need to be done or how it can be done in the user
space if some page_pool owned page is held from user space for the cases of zero
rx copy, io_uring and devmem tcp? killing the userspace app?

If you and Toke still think the waiting is the way out for the problem here, maybe
we should wait for jakub's opinion and let him decide if he want to proceed with
his waiting patch.

> 
> --Jesper

  reply	other threads:[~2024-10-26  7:33 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-10-22  3:22 [PATCH net-next v3 0/3] fix two bugs related to page_pool Yunsheng Lin
2024-10-22  3:22 ` [PATCH net-next v3 1/3] page_pool: introduce page_pool_to_pp() API Yunsheng Lin
2024-10-22  3:22 ` [PATCH net-next v3 2/3] page_pool: fix timing for checking and disabling napi_local Yunsheng Lin
2024-11-07  6:17   ` Xuan Zhuo
2024-10-22  3:22 ` [PATCH net-next v3 3/3] page_pool: fix IOMMU crash when driver has already unbound Yunsheng Lin
2024-10-22 16:40   ` Simon Horman
2024-10-22 18:14   ` Jesper Dangaard Brouer
2024-10-23  8:59     ` Yunsheng Lin
2024-10-24 14:40       ` Toke Høiland-Jørgensen
2024-10-25  3:20         ` Yunsheng Lin
2024-10-25 11:16           ` Toke Høiland-Jørgensen
2024-10-25 14:07             ` Jesper Dangaard Brouer
2024-10-26  7:33               ` Yunsheng Lin [this message]
2024-11-06 13:25                 ` Jesper Dangaard Brouer
2024-11-06 15:57                   ` Jesper Dangaard Brouer
2024-11-06 19:55                     ` Alexander Duyck
2024-11-07 11:10                       ` Yunsheng Lin
2024-11-07 11:09                     ` Yunsheng Lin
2024-11-11 11:31                 ` Yunsheng Lin
2024-11-11 18:51                   ` Toke Høiland-Jørgensen
2024-11-12 12:22                     ` Yunsheng Lin
2024-11-12 14:19                       ` Jesper Dangaard Brouer
2024-11-13 12:21                         ` Yunsheng Lin
2024-11-18  9:08                         ` Yunsheng Lin
2024-11-18 15:11                           ` Jesper Dangaard Brouer
2024-10-26  7:32             ` Yunsheng Lin
2024-10-29 13:58               ` Toke Høiland-Jørgensen
2024-10-30 11:30                 ` Yunsheng Lin
2024-10-30 11:57                   ` Toke Høiland-Jørgensen
2024-10-31 12:17                     ` Yunsheng Lin
2024-10-31 16:18                       ` Toke Høiland-Jørgensen
2024-11-01 11:11                         ` Yunsheng Lin
2024-11-05 20:11                           ` Jesper Dangaard Brouer
2024-11-06 10:56                             ` Yunsheng Lin
2024-11-06 14:17                               ` Robin Murphy
2024-11-07  8:41                               ` Christoph Hellwig

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=204272e7-82c3-4437-bb0d-2c3237275d1f@huawei.com \
    --to=linyunsheng@huawei.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexander.duyck@gmail.com \
    --cc=davem@davemloft.net \
    --cc=edumazet@google.com \
    --cc=fanghaiqing@huawei.com \
    --cc=hawk@kernel.org \
    --cc=ilias.apalodimas@linaro.org \
    --cc=iommu@lists.linux.dev \
    --cc=kernel-team@cloudflare.com \
    --cc=kuba@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=liuyonglong@huawei.com \
    --cc=netdev@vger.kernel.org \
    --cc=pabeni@redhat.com \
    --cc=robin.murphy@arm.com \
    --cc=toke@redhat.com \
    --cc=zhangkun09@huawei.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

all inboxes | Powered by JetHome®