From: <dan.j.williams@intel.com>
To: "David Hildenbrand (Red Hat)" <david@kernel.org>,
Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: Li Zhe <lizhe.67@bytedance.com>, <akpm@linux-foundation.org>,
<ankur.a.arora@oracle.com>, <fvdl@google.com>,
<joao.m.martins@oracle.com>, <linux-kernel@vger.kernel.org>,
<linux-mm@kvack.org>, <mhocko@suse.com>, <mjguzik@gmail.com>,
<muchun.song@linux.dev>, <osalvador@suse.de>,
<raghavendra.kt@amd.com>, <linux-cxl@vger.kernel.org>,
Davidlohr Bueso <dave@stgolabs.net>,
Gregory Price <gourry@gourry.net>,
Dan Williams <dan.j.williams@intel.com>, <zhanjie9@hisilicon.com>,
<wangzhou1@hisilicon.com>
Subject: Re: [PATCH v2 0/8] Introduce a huge-page pre-zeroing mechanism
Date: Thu, 15 Jan 2026 12:16:06 -0800 [thread overview]
Message-ID: <69694b06835e_34d2a100b3@dwillia2-mobl4.notmuch> (raw)
In-Reply-To: <23513e86-0769-4f3f-b90b-22273343a03c@kernel.org>
David Hildenbrand (Red Hat) wrote:
[..]
> > Give me a list of 1Gig pages and this stuff becomes much more efficient
> > than anything the CPU can do.
>
> Right, and ideally we'd implement any such mechanisms in a way that more
> parts of the kernel can benefit, and not just an unloved in-memory
> file-system that most people just want to get rid of as soon as we can :)
CPUs have tended to eat the value of simple DMA offload operations like
copy/zero over time.
In the case of this patch there is no async-offload benefit because
userspace is already charged with spawning more threads if it wants more
parallelism.
For sync-offload one engine may be able to beat a single CPU, but now
you have created bandwidth contention problems with a component that is
less responsive to the scheduler.
Call me skeptical.
Signed, someone with async_tx and dmaengine battle scars.
next prev parent reply other threads:[~2026-01-15 20:16 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-01-07 11:31 Li Zhe
2026-01-07 11:31 ` [PATCH v2 1/8] mm/hugetlb: add pre-zeroed framework Li Zhe
2026-01-07 11:31 ` [PATCH v2 2/8] mm/hugetlb: convert to prep_account_new_hugetlb_folio() Li Zhe
2026-01-07 11:31 ` [PATCH v2 3/8] mm/hugetlb: move the huge folio to the end of the list during enqueue Li Zhe
2026-01-07 11:31 ` [PATCH v2 4/8] mm/hugetlb: introduce per-node sysfs interface "zeroable_hugepages" Li Zhe
2026-01-07 11:31 ` [PATCH v2 5/8] mm/hugetlb: simplify function hugetlb_sysfs_add_hstate() Li Zhe
2026-01-07 11:31 ` [PATCH v2 6/8] mm/hugetlb: relocate the per-hstate struct kobject pointer Li Zhe
2026-01-07 11:31 ` [PATCH v2 7/8] mm/hugetlb: add epoll support for interface "zeroable_hugepages" Li Zhe
2026-01-07 11:31 ` [PATCH v2 8/8] mm/hugetlb: limit event generation frequency of function do_zero_free_notify() Li Zhe
2026-01-07 16:19 ` [PATCH v2 0/8] Introduce a huge-page pre-zeroing mechanism Andrew Morton
2026-01-12 11:25 ` Li Zhe
2026-01-09 6:05 ` Muchun Song
2026-01-12 11:27 ` Li Zhe
2026-01-12 19:52 ` David Hildenbrand (Red Hat)
2026-01-13 6:37 ` Li Zhe
2026-01-13 10:15 ` David Hildenbrand (Red Hat)
2026-01-13 12:41 ` Li Zhe
2026-01-14 10:41 ` David Hildenbrand (Red Hat)
2026-01-14 11:36 ` Li Zhe
2026-01-14 11:55 ` David Hildenbrand (Red Hat)
2026-01-14 12:11 ` Mateusz Guzik
2026-01-14 12:33 ` David Hildenbrand (Red Hat)
2026-01-14 12:41 ` David Hildenbrand (Red Hat)
2026-01-14 13:06 ` Mateusz Guzik
2026-01-14 17:21 ` David Hildenbrand (Red Hat)
2026-01-15 9:36 ` Li Zhe
2026-01-15 11:08 ` David Hildenbrand (Red Hat)
2026-01-15 11:57 ` Jonathan Cameron
2026-01-15 17:08 ` David Hildenbrand (Red Hat)
2026-01-15 20:16 ` dan.j.williams [this message]
2026-01-15 20:22 ` David Hildenbrand (Red Hat)
2026-01-15 22:30 ` Ankur Arora
2026-01-20 6:27 ` Li Zhe
2026-01-20 9:47 ` David Laight
2026-01-20 10:39 ` Li Zhe
2026-01-20 18:18 ` Gregory Price
2026-01-20 18:38 ` Gregory Price
2026-01-20 19:30 ` David Laight
2026-01-20 19:52 ` Gregory Price
2026-01-21 8:03 ` Li Zhe
2026-01-21 12:41 ` David Hildenbrand (Red Hat)
2026-01-21 12:32 ` David Hildenbrand (Red Hat)
2026-01-12 22:00 ` Ankur Arora
2026-01-13 6:39 ` Li Zhe
2026-01-12 22:01 ` Ankur Arora
2026-01-13 6:41 ` Li Zhe
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=69694b06835e_34d2a100b3@dwillia2-mobl4.notmuch \
--to=dan.j.williams@intel.com \
--cc=akpm@linux-foundation.org \
--cc=ankur.a.arora@oracle.com \
--cc=dave@stgolabs.net \
--cc=david@kernel.org \
--cc=fvdl@google.com \
--cc=gourry@gourry.net \
--cc=joao.m.martins@oracle.com \
--cc=jonathan.cameron@huawei.com \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lizhe.67@bytedance.com \
--cc=mhocko@suse.com \
--cc=mjguzik@gmail.com \
--cc=muchun.song@linux.dev \
--cc=osalvador@suse.de \
--cc=raghavendra.kt@amd.com \
--cc=wangzhou1@hisilicon.com \
--cc=zhanjie9@hisilicon.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