From: Michal Hocko <mhocko@suse.com>
To: "Huang, Ying" <ying.huang@intel.com>
Cc: Feng Tang <feng.tang@intel.com>,
Andrew Morton <akpm@linux-foundation.org>,
Johannes Weiner <hannes@cmpxchg.org>,
Matthew Wilcox <willy@infradead.org>,
Mel Gorman <mgorman@suse.de>,
dave.hansen@intel.com, linux-mm@kvack.org,
linux-kernel@vger.kernel.org
Subject: Re: [RFC PATCH 0/2] mm: fix OOMs for binding workloads to movable zone only node
Date: Fri, 6 Nov 2020 08:43:46 +0100 [thread overview]
Message-ID: <20201106074346.GA7247@dhcp22.suse.cz> (raw)
In-Reply-To: <87zh3vp0k3.fsf@yhuang-dev.intel.com>
On Fri 06-11-20 12:32:44, Huang, Ying wrote:
> Michal Hocko <mhocko@suse.com> writes:
>
> > On Thu 05-11-20 09:40:28, Feng Tang wrote:
> >> On Wed, Nov 04, 2020 at 09:53:43AM +0100, Michal Hocko wrote:
> >>
> >> > > > As I've said in reply to your second patch. I think we can make the oom
> >> > > > killer behavior more sensible in this misconfigured cases but I do not
> >> > > > think we want break the cpuset isolation for such a configuration.
> >> > >
> >> > > Do you mean we skip the killing and just let the allocation fail? We've
> >> > > checked the oom killer code first, when the oom happens, both DRAM
> >> > > node and unmovable node have lots of free memory, and killing process
> >> > > won't improve the situation.
> >> >
> >> > We already do skip oom killer and fail for lowmem allocation requests already.
> >> > This is similar in some sense. Another option would be to kill the
> >> > allocating context which will have less corner cases potentially because
> >> > some allocation failures might be unexpected.
> >>
> >> Yes, this can avoid the helpless oom killing to kill a good process(no
> >> memory pressure at all)
> >>
> >> And I think the important thing is to judge whether this usage (binding
> >> docker like workload to unmovable node) is a valid case :)
> >
> > I am confused. Why wouldbe an unmovable node a problem. Movable
> > allocations can be satisfied from the Zone Normal just fine. It is other
> > way around that is a problem.
> >
> >> Initially, I thought it invalid too, but later think it still makes some
> >> sense for the 2 cases:
> >> * user want to bind his workload to one node(most of user space
> >> memory) to avoid cross-node traffic, and that node happens to
> >> be configured as unmovable
> >
> > See above
> >
> >> * one small DRAM node + big PMEM node, and memory latency insensitive
> >> workload could be bound to the cheaper unmovable PMEM node
> >
> > Please elaborate some more. As long as you have movable and normal nodes
> > then this should be possible with a deal of care - most notably the
> > movable:kernel ratio memory shouldn't be too big.
> >
> > Besides that why does PMEM node have to be MOVABLE only in the first
> > place?
>
> The performance of PMEM is much worse than that of DRAM. If we found
> that some pages on PMEM are accessed frequently (hot), we may want to
> move them to DRAM to optimize the system performance. If the unmovable
> pages are allocated on PMEM and hot, it's possible that we cannot move
> the pages to DRAM unless rebooting the system. So we think we should
> make the PMEM nodes to be MOVABLE only.
That is fair but then you really need a fallback node too. So this is
mere optimization rather than a fundamental restriction.
--
Michal Hocko
SUSE Labs
prev parent reply other threads:[~2020-11-06 7:43 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-04 6:10 [RFC PATCH 0/2] mm: fix OOMs for binding workloads to movable zone only node Feng Tang
2020-11-04 6:10 ` [RFC PATCH 1/2] mm, oom: dump meminfo for all memory nodes Feng Tang
2020-11-04 7:18 ` Michal Hocko
2020-11-04 6:10 ` [RFC PATCH 2/2] mm, page_alloc: loose the node binding check to avoid helpless oom killing Feng Tang
2020-11-04 7:23 ` Michal Hocko
2020-11-04 7:13 ` [RFC PATCH 0/2] mm: fix OOMs for binding workloads to movable zone only node Michal Hocko
2020-11-04 7:38 ` Feng Tang
2020-11-04 7:58 ` Michal Hocko
2020-11-04 8:40 ` Feng Tang
2020-11-04 8:53 ` Michal Hocko
2020-11-05 1:40 ` Feng Tang
2020-11-05 12:08 ` Michal Hocko
2020-11-05 12:53 ` Vlastimil Babka
2020-11-05 12:58 ` Michal Hocko
2020-11-05 13:07 ` Feng Tang
2020-11-05 13:12 ` Michal Hocko
2020-11-05 13:43 ` Feng Tang
2020-11-05 16:16 ` Michal Hocko
2020-11-06 7:06 ` Feng Tang
2020-11-06 8:10 ` Michal Hocko
2020-11-06 9:08 ` Feng Tang
2020-11-06 10:35 ` Michal Hocko
2020-11-05 13:14 ` Vlastimil Babka
2020-11-05 13:19 ` Michal Hocko
2020-11-05 13:34 ` Vlastimil Babka
2020-11-06 4:32 ` Huang, Ying
2020-11-06 7:43 ` Michal Hocko [this message]
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=20201106074346.GA7247@dhcp22.suse.cz \
--to=mhocko@suse.com \
--cc=akpm@linux-foundation.org \
--cc=dave.hansen@intel.com \
--cc=feng.tang@intel.com \
--cc=hannes@cmpxchg.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mgorman@suse.de \
--cc=willy@infradead.org \
--cc=ying.huang@intel.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;
as well as URLs for NNTP newsgroup(s).