From: Jerome Glisse <jglisse@redhat.com>
To: Bob Liu <liubo95@huawei.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
John Hubbard <jhubbard@nvidia.com>,
David Nellans <dnellans@nvidia.com>,
Dan Williams <dan.j.williams@intel.com>,
Balbir Singh <bsingharora@gmail.com>,
Michal Hocko <mhocko@kernel.org>
Subject: Re: [PATCH 0/6] Cache coherent device memory (CDM) with HMM v5
Date: Tue, 18 Jul 2017 11:38:16 -0400 [thread overview]
Message-ID: <20170718153816.GA3135@redhat.com> (raw)
In-Reply-To: <2d534afc-28c5-4c81-c452-7e4c013ab4d0@huawei.com>
On Tue, Jul 18, 2017 at 11:26:51AM +0800, Bob Liu wrote:
> On 2017/7/14 5:15, Jerome Glisse wrote:
> > Sorry i made horrible mistake on names in v4, i completly miss-
> > understood the suggestion. So here i repost with proper naming.
> > This is the only change since v3. Again sorry about the noise
> > with v4.
> >
> > Changes since v4:
> > - s/DEVICE_HOST/DEVICE_PUBLIC
> >
> > Git tree:
> > https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-cdm-v5
> >
> >
> > Cache coherent device memory apply to architecture with system bus
> > like CAPI or CCIX. Device connected to such system bus can expose
> > their memory to the system and allow cache coherent access to it
> > from the CPU.
> >
> > Even if for all intent and purposes device memory behave like regular
> > memory, we still want to manage it in isolation from regular memory.
> > Several reasons for that, first and foremost this memory is less
> > reliable than regular memory if the device hangs because of invalid
> > commands we can loose access to device memory. Second CPU access to
> > this memory is expected to be slower than to regular memory. Third
> > having random memory into device means that some of the bus bandwith
> > wouldn't be available to the device but would be use by CPU access.
> >
> > This is why we want to manage such memory in isolation from regular
> > memory. Kernel should not try to use this memory even as last resort
> > when running out of memory, at least for now.
> >
>
> I think set a very large node distance for "Cache Coherent Device Memory"
> may be a easier way to address these concerns.
Such approach was discuss at length in the past see links below. Outcome
of discussion:
- CPU less node are bad
- device memory can be unreliable (device hang) no way for application
to understand that
- application and driver NUMA madvise/mbind/mempolicy ... can conflict
with each other and no way the kernel can figure out which should
apply
- NUMA as it is now would not work as we need further isolation that
what a large node distance would provide
Probably few others argument i forget.
https://lists.gt.net/linux/kernel/2551369
https://groups.google.com/forum/#!topic/linux.kernel/Za_e8C3XnRs%5B1-25%5D
https://lwn.net/Articles/720380/
Cheers,
Jerome
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
next prev parent reply other threads:[~2017-07-18 15:38 UTC|newest]
Thread overview: 43+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-07-13 21:15 [PATCH 0/6] Cache coherent device memory (CDM) with HMM v5 Jérôme Glisse
2017-07-13 21:15 ` [PATCH 1/6] mm/zone-device: rename DEVICE_PUBLIC to DEVICE_HOST Jérôme Glisse
2017-07-17 9:09 ` Balbir Singh
2017-07-13 21:15 ` [PATCH 2/6] mm/device-public-memory: device memory cache coherent with CPU v4 Jérôme Glisse
2017-07-13 23:01 ` Balbir Singh
2017-07-13 21:15 ` [PATCH 3/6] mm/hmm: add new helper to hotplug CDM memory region v3 Jérôme Glisse
2017-07-13 21:15 ` [PATCH 4/6] mm/memcontrol: allow to uncharge page without using page->lru field Jérôme Glisse
2017-07-17 9:10 ` Balbir Singh
2017-07-13 21:15 ` [PATCH 5/6] mm/memcontrol: support MEMORY_DEVICE_PRIVATE and MEMORY_DEVICE_PUBLIC v3 Jérôme Glisse
2017-07-17 9:15 ` Balbir Singh
2017-07-13 21:15 ` [PATCH 6/6] mm/hmm: documents how device memory is accounted in rss and memcg Jérôme Glisse
2017-07-14 13:26 ` Michal Hocko
2017-07-18 3:26 ` [PATCH 0/6] Cache coherent device memory (CDM) with HMM v5 Bob Liu
2017-07-18 15:38 ` Jerome Glisse [this message]
2017-07-19 1:46 ` Bob Liu
2017-07-19 2:25 ` Jerome Glisse
2017-07-19 9:09 ` Bob Liu
2017-07-20 15:03 ` Jerome Glisse
2017-07-21 1:15 ` Bob Liu
2017-07-21 1:41 ` Jerome Glisse
2017-07-21 2:10 ` Bob Liu
2017-07-21 12:01 ` Bob Liu
2017-07-21 15:21 ` Jerome Glisse
2017-07-21 3:48 ` Dan Williams
2017-07-21 15:22 ` Jerome Glisse
2017-09-05 19:36 ` Jerome Glisse
2017-09-09 23:22 ` Bob Liu
2017-09-11 23:36 ` Jerome Glisse
2017-09-12 1:02 ` Bob Liu
2017-09-12 16:17 ` Jerome Glisse
2017-09-26 9:56 ` Bob Liu
2017-09-26 16:16 ` Jerome Glisse
2017-09-30 2:57 ` Bob Liu
2017-09-30 22:49 ` Jerome Glisse
2017-10-11 13:15 ` Bob Liu
2017-10-12 15:37 ` Jerome Glisse
2017-11-16 2:10 ` chet l
2017-11-16 2:44 ` Jerome Glisse
2017-11-16 3:23 ` chetan L
2017-11-16 3:29 ` chetan L
2017-11-16 21:29 ` Jerome Glisse
2017-11-16 22:41 ` chetan L
2017-11-16 23:11 ` Jerome Glisse
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=20170718153816.GA3135@redhat.com \
--to=jglisse@redhat.com \
--cc=bsingharora@gmail.com \
--cc=dan.j.williams@intel.com \
--cc=dnellans@nvidia.com \
--cc=jhubbard@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=liubo95@huawei.com \
--cc=mhocko@kernel.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
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;
as well as URLs for NNTP newsgroup(s).