From: David Hildenbrand <david@redhat.com>
To: Pavel Tatashin <pasha.tatashin@soleen.com>,
Jason Gunthorpe <jgg@ziepe.ca>
Cc: Joonsoo Kim <js1304@gmail.com>,
LKML <linux-kernel@vger.kernel.org>,
linux-mm <linux-mm@kvack.org>,
Andrew Morton <akpm@linux-foundation.org>,
Vlastimil Babka <vbabka@suse.cz>, Michal Hocko <mhocko@suse.com>,
Oscar Salvador <osalvador@suse.de>,
Dan Williams <dan.j.williams@intel.com>,
Sasha Levin <sashal@kernel.org>,
Tyler Hicks <tyhicks@linux.microsoft.com>,
mike.kravetz@oracle.com, Steven Rostedt <rostedt@goodmis.org>,
Ingo Molnar <mingo@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Mel Gorman <mgorman@suse.de>,
Matthew Wilcox <willy@infradead.org>,
David Rientjes <rientjes@google.com>,
John Hubbard <jhubbard@nvidia.com>
Subject: Re: [PATCH 0/6] prohibit pinning pages in ZONE_MOVABLE
Date: Fri, 4 Dec 2020 19:01:58 +0100 [thread overview]
Message-ID: <593822e5-4e1a-fdca-5500-4138d0f2b728@redhat.com> (raw)
In-Reply-To: <CA+CK2bCGGoBXg7FbhGMDdWRnePKFgvtsM_PJmA2qtMNsvPMZbg@mail.gmail.com>
On 04.12.20 18:50, Pavel Tatashin wrote:
>>> Yes, this indeed could be a problem for some configurations. I will
>>> add your comment to the commit log of one of the patches.
>>
>> It sounds like there is some inherent tension here, breaking THP's
>> when doing pin_user_pages() is a really nasty thing to do. DMA
>> benefits greatly from THP.
>>
>> I know nothing about ZONE_MOVABLE, is this auto-setup or an admin
>> option? If the result of this patch is standard systems can no longer
>> pin > 80% of their memory I have some regression concerns..
>
> ZONE_MOVABLE can be configured via kernel parameter, or when memory
> nodes are onlined after hot-add; so this is something that admins
> configure. ZONE_MOVABLE is designed to gurantee memory hot-plug
> functionality, and not availability of THP, however, I did not know
> about the use case where some admins might configure ZONE_MOVABLE to
> increase availability of THP because pages are always migratable in
> them. The thing is, if we fragment ZONE_MOVABLE by pinning pages in
> it, the availability of THP also suffers. We can migrate pages in
> ZONE_NORMAL, just not guaranteed, so we can create THP in ZONE_NORMAL
> as well, which is the usual case.
Right, we should document this at some place to make admins aware of
this. Something like
"Techniques that rely on long-term pinnings of memory (especially, RDMA
and vfio) are fundamentally problematic with ZONE_MOVABLE and,
therefore, memory hotunplug. Pinned pages cannot reside on ZONE_MOVABLE,
to guarantee that memory can still get hotunplugged - be aware that
pinning can fail even if there is plenty of free memory in ZONE_MOVABLE.
In addition, using ZONE_MOVABLE might make page pinning more expensive,
because pages have to be migrated off that zone first."
BTW, you might also want to update the comment for ZONE_MOVABLE in
include/linux/mmzone.h at the end of this series, removing the special
case of pinned pages (1.) and maybe adding what happens when trying to
pin pages on ZONE_MOVABLE.
--
Thanks,
David / dhildenb
next prev parent reply other threads:[~2020-12-04 18:02 UTC|newest]
Thread overview: 67+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-12-02 5:23 [PATCH 0/6] prohibit pinning pages in ZONE_MOVABLE Pavel Tatashin
2020-12-02 5:23 ` [PATCH 1/6] mm/gup: perform check_dax_vmas only when FS_DAX is enabled Pavel Tatashin
2020-12-02 16:22 ` Ira Weiny
2020-12-02 18:15 ` Pavel Tatashin
2020-12-02 16:29 ` Jason Gunthorpe
2020-12-02 18:16 ` Pavel Tatashin
2020-12-03 7:59 ` John Hubbard
2020-12-03 14:52 ` Pavel Tatashin
2020-12-02 5:23 ` [PATCH 2/6] mm/gup: don't pin migrated cma pages in movable zone Pavel Tatashin
2020-12-02 16:31 ` David Hildenbrand
2020-12-02 18:17 ` Pavel Tatashin
2020-12-03 8:01 ` John Hubbard
2020-12-03 8:46 ` Michal Hocko
2020-12-03 14:58 ` Pavel Tatashin
2020-12-02 5:23 ` [PATCH 3/6] mm/gup: make __gup_longterm_locked common Pavel Tatashin
2020-12-02 16:31 ` Ira Weiny
2020-12-02 16:33 ` Ira Weiny
2020-12-02 18:19 ` Pavel Tatashin
2020-12-03 0:03 ` Pavel Tatashin
2020-12-03 8:03 ` John Hubbard
2020-12-03 15:02 ` Pavel Tatashin
2020-12-02 5:23 ` [PATCH 4/6] mm cma: rename PF_MEMALLOC_NOCMA to PF_MEMALLOC_NOMOVABLE Pavel Tatashin
2020-12-03 8:04 ` John Hubbard
2020-12-03 15:02 ` Pavel Tatashin
2020-12-03 8:57 ` Michal Hocko
2020-12-03 15:02 ` Pavel Tatashin
2020-12-02 5:23 ` [PATCH 5/6] mm: honor PF_MEMALLOC_NOMOVABLE for all allocations Pavel Tatashin
2020-12-03 8:17 ` John Hubbard
2020-12-03 15:06 ` Pavel Tatashin
2020-12-03 16:51 ` John Hubbard
2020-12-03 9:17 ` Michal Hocko
2020-12-03 15:15 ` Pavel Tatashin
2020-12-04 8:43 ` Michal Hocko
2020-12-04 8:54 ` Michal Hocko
2020-12-04 16:07 ` Pavel Tatashin
2020-12-02 5:23 ` [PATCH 6/6] mm/gup: migrate pinned pages out of movable zone Pavel Tatashin
2020-12-02 16:35 ` Jason Gunthorpe
2020-12-03 0:19 ` Pavel Tatashin
2020-12-03 1:08 ` Jason Gunthorpe
2020-12-03 1:34 ` Pavel Tatashin
2020-12-03 14:17 ` Jason Gunthorpe
2020-12-03 16:40 ` Pavel Tatashin
2020-12-03 16:59 ` Jason Gunthorpe
2020-12-03 17:14 ` Pavel Tatashin
2020-12-03 19:15 ` Pavel Tatashin
2020-12-03 19:36 ` Jason Gunthorpe
2020-12-04 16:24 ` Pavel Tatashin
2020-12-04 17:06 ` Jason Gunthorpe
2020-12-04 20:05 ` Daniel Jordan
2020-12-04 20:16 ` Pavel Tatashin
2020-12-08 2:27 ` Daniel Jordan
2020-12-04 20:52 ` Jason Gunthorpe
2020-12-08 2:48 ` Daniel Jordan
2020-12-08 13:24 ` Jason Gunthorpe
2020-12-03 8:22 ` John Hubbard
2020-12-03 15:55 ` Pavel Tatashin
2020-12-04 4:13 ` Joonsoo Kim
2020-12-04 17:43 ` Pavel Tatashin
2020-12-07 7:13 ` Joonsoo Kim
2020-12-04 4:02 ` [PATCH 0/6] prohibit pinning pages in ZONE_MOVABLE Joonsoo Kim
2020-12-04 15:55 ` Pavel Tatashin
2020-12-04 16:10 ` Jason Gunthorpe
2020-12-04 17:50 ` Pavel Tatashin
2020-12-04 18:01 ` David Hildenbrand [this message]
2020-12-04 18:10 ` Pavel Tatashin
2020-12-07 7:12 ` Joonsoo Kim
2020-12-07 12:13 ` 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=593822e5-4e1a-fdca-5500-4138d0f2b728@redhat.com \
--to=david@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=dan.j.williams@intel.com \
--cc=jgg@ziepe.ca \
--cc=jhubbard@nvidia.com \
--cc=js1304@gmail.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=mingo@redhat.com \
--cc=osalvador@suse.de \
--cc=pasha.tatashin@soleen.com \
--cc=peterz@infradead.org \
--cc=rientjes@google.com \
--cc=rostedt@goodmis.org \
--cc=sashal@kernel.org \
--cc=tyhicks@linux.microsoft.com \
--cc=vbabka@suse.cz \
--cc=willy@infradead.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).