linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Benjamin Herrenschmidt <benh@kernel.crashing.org>
To: Michal Hocko <mhocko@suse.com>, Balbir Singh <bsingharora@gmail.com>
Cc: linux-mm@kvack.org, akpm@linux-foundation.org,
	khandual@linux.vnet.ibm.com, aneesh.kumar@linux.vnet.ibm.com,
	paulmck@linux.vnet.ibm.com, srikar@linux.vnet.ibm.com,
	haren@linux.vnet.ibm.com, jglisse@redhat.com,
	mgorman@techsingularity.net, arbab@linux.vnet.ibm.com,
	vbabka@suse.cz, cl@linux.com
Subject: Re: [RFC 0/4] RFC - Coherent Device Memory (Not for inclusion)
Date: Thu, 04 May 2017 17:49:21 +0200	[thread overview]
Message-ID: <1493912961.25766.379.camel@kernel.crashing.org> (raw)
In-Reply-To: <20170504125250.GH31540@dhcp22.suse.cz>

On Thu, 2017-05-04 at 14:52 +0200, Michal Hocko wrote:
> But the direct reclaim would be effective only _after_ all other nodes
> are full.
> 
> I thought that kswapd reclaim is a problem because the HW doesn't
> support aging properly but as the direct reclaim works then what is the
> actual problem?

Ageing isn't isn't completely broken. The ATS MMU supports
dirty/accessed just fine.

However the TLB invalidations are quite expensive with a GPU so too
much harvesting is detrimental, and the GPU tends to check pages out
using a special "read with intend to write" mode, which means it almost
always set the dirty bit if the page is writable to begin with.

Cheers,
Ben.

--
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>

  reply	other threads:[~2017-05-04 15:49 UTC|newest]

Thread overview: 45+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-04-19  7:52 [RFC 0/4] RFC - Coherent Device Memory (Not for inclusion) Balbir Singh
2017-04-19  7:52 ` [RFC 1/4] mm: create N_COHERENT_MEMORY Balbir Singh
2017-04-27 18:42   ` Reza Arbab
2017-04-28  5:07     ` Balbir Singh
2017-04-19  7:52 ` [RFC 2/4] arch/powerpc/mm: add support for coherent memory Balbir Singh
2017-04-19  7:52 ` [RFC 3/4] mm: Integrate N_COHERENT_MEMORY with mempolicy and the rest of the system Balbir Singh
2017-04-19  7:52 ` [RFC 4/4] mm: Add documentation for coherent memory Balbir Singh
2017-04-19 19:02 ` [RFC 0/4] RFC - Coherent Device Memory (Not for inclusion) Christoph Lameter
2017-04-20  1:25   ` Balbir Singh
2017-04-20 15:29     ` Christoph Lameter
2017-04-20 21:26       ` Benjamin Herrenschmidt
2017-04-21 16:13         ` Christoph Lameter
2017-04-21 21:15           ` Benjamin Herrenschmidt
2017-04-24 13:57             ` Christoph Lameter
2017-04-24  0:20       ` Balbir Singh
2017-04-24 14:00         ` Christoph Lameter
2017-04-25  0:52           ` Balbir Singh
2017-05-01 20:41 ` John Hubbard
2017-05-01 21:04   ` Reza Arbab
2017-05-01 21:56     ` John Hubbard
2017-05-01 23:51       ` Reza Arbab
2017-05-01 23:58         ` John Hubbard
2017-05-02  0:04           ` Reza Arbab
2017-05-02  1:29   ` Balbir Singh
2017-05-02  5:47     ` John Hubbard
2017-05-02  7:23       ` Balbir Singh
2017-05-02 17:50         ` John Hubbard
2017-05-02 14:36 ` Michal Hocko
2017-05-04  5:26   ` Balbir Singh
2017-05-04 12:52     ` Michal Hocko
2017-05-04 15:49       ` Benjamin Herrenschmidt [this message]
2017-05-04 17:33         ` Dave Hansen
2017-05-05  3:17           ` Balbir Singh
2017-05-05 14:51             ` Dave Hansen
2017-05-05  7:49           ` Benjamin Herrenschmidt
2017-05-05 14:52         ` Michal Hocko
2017-05-05 15:57           ` Benjamin Herrenschmidt
2017-05-05 17:48             ` Jerome Glisse
2017-05-05 17:59               ` Benjamin Herrenschmidt
2017-05-09 11:36             ` Michal Hocko
2017-05-09 13:43               ` Benjamin Herrenschmidt
2017-05-15 12:55                 ` Michal Hocko
2017-05-15 15:53                   ` Christoph Lameter
2017-05-10 23:04               ` Balbir Singh
2017-05-09  7:51           ` Balbir Singh

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=1493912961.25766.379.camel@kernel.crashing.org \
    --to=benh@kernel.crashing.org \
    --cc=akpm@linux-foundation.org \
    --cc=aneesh.kumar@linux.vnet.ibm.com \
    --cc=arbab@linux.vnet.ibm.com \
    --cc=bsingharora@gmail.com \
    --cc=cl@linux.com \
    --cc=haren@linux.vnet.ibm.com \
    --cc=jglisse@redhat.com \
    --cc=khandual@linux.vnet.ibm.com \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=mhocko@suse.com \
    --cc=paulmck@linux.vnet.ibm.com \
    --cc=srikar@linux.vnet.ibm.com \
    --cc=vbabka@suse.cz \
    /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).