From: Michal Hocko <mhocko@suse.com>
To: Oscar Salvador <osalvador@suse.de>
Cc: david@redhat.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org, Hannes Reinecke <hare@kernel.org>
Subject: Re: [RFC] Disable auto_movable_ratio for selfhosted memmap
Date: Mon, 28 Jul 2025 10:48:31 +0200 [thread overview]
Message-ID: <aIc5XxgkbAwF6wqE@tiehlicka> (raw)
In-Reply-To: <aIcxs2nk3RNWWbD6@localhost.localdomain>
On Mon 28-07-25 10:15:47, Oscar Salvador wrote:
> Hi,
>
> Currently, we have several mechanisms to pick a zone for the new memory we are
> onlining.
> Eventually, we will land on zone_for_pfn_range() which will pick the zone.
>
> Two of these mechanisms are 'movable_node' and 'auto-movable' policy.
> The former will put every single hotpluggled memory in ZONE_MOVABLE
> (unless we can keep zones contiguous by not doing so), while the latter
> will put it in ZONA_MOVABLE IFF we are within the established ratio
> MOVABLE:KERNEL.
>
> It seems, the later doesn't play well with CXL memory where CXL cards hold really
> large amounts of memory, making the ratio fail, and since CXL cards must be removed
> as a unit, it can't be done if any memory block fell within
> !ZONE_MOVABLE zone.
I suspect this is just an example of how our existing memory hotplug
interface based on memory blocks is just suoptimal and it doesn't fit
new usecases. We should start thinking about how a new v2 api should
look like. I am not sure how that should look like but I believe we
should be able to express a "device" as whole rather than having a very
loosely bound generic memblocks. Anyway this is likely for a longer
discussion and a long term plan rather than addressing this particular
issue.
> One way to tackle this would be update the ratio every time a new CXL
> card gets inserted, but this seems suboptimal.
I do not think this is a usable interface.
> Another way is that since CXL memory works with selfhosted memmap, we could relax
> the check when 'auto-movable' and only look at the ratio if we aren't
> working with selfhosted memmap.
This is likely the only choice we have with the current interface. We
either need a way to disable the ratio altogether or make it more
automagic and treat self hosted memory differently because that memory
doesn't eat up ZONE_NORMAL memory and therefore cannot deplete it for
ZONE_MOVABLE.
Lowmem (ZONE_NORMAL) oom problems are still possible but kinda
unavoidable no matter what the hotplug interface is as the CXL usecase
really needs its memory to be movable to operate it as desired AFAIU.
> Something like the following (acthung: it's just a PoC)
> Comments? Ideas?
>
> diff --git a/drivers/base/memory.c b/drivers/base/memory.c
> index 5c6c1d6bb59f..ff87cfb3881a 100644
> --- a/drivers/base/memory.c
> +++ b/drivers/base/memory.c
> @@ -234,7 +234,7 @@ static int memory_block_online(struct memory_block *mem)
> return -EHWPOISON;
>
> zone = zone_for_pfn_range(mem->online_type, mem->nid, mem->group,
> - start_pfn, nr_pages);
> + start_pfn, nr_pages, mem->altmap);
Shouldn't this be a more descriptive (enum like) argument?
ONLINE_MOVABLE, ONLINE_AUTO etc..
--
Michal Hocko
SUSE Labs
next prev parent reply other threads:[~2025-07-28 8:48 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-07-28 8:15 Oscar Salvador
2025-07-28 8:44 ` David Hildenbrand
2025-07-28 9:28 ` Hannes Reinecke
2025-07-28 9:42 ` David Hildenbrand
2025-07-28 8:48 ` Michal Hocko [this message]
2025-07-28 8:53 ` David Hildenbrand
2025-07-28 9:04 ` Michal Hocko
2025-07-28 9:10 ` David Hildenbrand
2025-07-28 9:37 ` Hannes Reinecke
2025-07-28 13:06 ` Michal Hocko
2025-07-28 13:08 ` David Hildenbrand
2025-07-29 7:24 ` Hannes Reinecke
2025-07-29 9:19 ` Michal Hocko
2025-07-29 9:29 ` David Hildenbrand
2025-07-29 9:33 ` Hannes Reinecke
2025-07-29 11:58 ` Michal Hocko
2025-07-29 13:52 ` Hannes Reinecke
2025-07-28 15:15 ` David Hildenbrand
2025-07-28 12:17 ` Michal Hocko
2025-07-28 12:27 ` David Hildenbrand
2025-07-28 12:27 ` David Hildenbrand
2025-07-28 13:00 ` Michal Hocko
2025-07-28 13:03 ` David Hildenbrand
2025-07-28 12:54 ` Michal Hocko
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=aIc5XxgkbAwF6wqE@tiehlicka \
--to=mhocko@suse.com \
--cc=david@redhat.com \
--cc=hare@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=osalvador@suse.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
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