From: Mel Gorman <mgorman@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>,
Han Pingtian <hanpt@linux.vnet.ibm.com>,
linux-kernel@vger.kernel.org, Michal Hocko <mhocko@suse.cz>,
linux-mm@kvack.org, Dave Hansen <dave.hansen@intel.com>
Subject: Re: [RFC] mm: show message when updating min_free_kbytes in thp
Date: Wed, 15 Jan 2014 15:22:18 +0000 [thread overview]
Message-ID: <20140115152218.GL4963@suse.de> (raw)
In-Reply-To: <20140114163533.ab191e118e82ca7b4d499551@linux-foundation.org>
On Tue, Jan 14, 2014 at 04:35:33PM -0800, Andrew Morton wrote:
> > Would it be overkill to save the kernel default both with and without thp
> > and then doing a WARN_ON_ONCE() if a user-written value is ever less?
>
> Well, min_free_kbytes is a userspace thing, not a kernel thing - maybe
> THP shouldn't be dinking with it. What effect is THP trying to achieve
> and can we achieve it by other/better means?
It moved logic from hugeadm where few people knew about it to the
kernel. The value is related to anti-fragmentation. With the recommended
setting the probability of mixing pages of different mobility within a
single pageblock is reduced. Very very superficially, it reduces the
number of instances the mm_page_alloc_extfrag tracepoint is triggered
with parameters that are considered to be severely fragmenting.
--
Mel Gorman
SUSE Labs
--
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>
WARNING: multiple messages have this Message-ID (diff)
From: Mel Gorman <mgorman@suse.de>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: David Rientjes <rientjes@google.com>,
Han Pingtian <hanpt@linux.vnet.ibm.com>,
linux-kernel@vger.kernel.org, Michal Hocko <mhocko@suse.cz>,
linux-mm@kvack.org, Dave Hansen <dave.hansen@intel.com>
Subject: Re: [RFC] mm: show message when updating min_free_kbytes in thp
Date: Wed, 15 Jan 2014 15:22:18 +0000 [thread overview]
Message-ID: <20140115152218.GL4963@suse.de> (raw)
In-Reply-To: <20140114163533.ab191e118e82ca7b4d499551@linux-foundation.org>
On Tue, Jan 14, 2014 at 04:35:33PM -0800, Andrew Morton wrote:
> > Would it be overkill to save the kernel default both with and without thp
> > and then doing a WARN_ON_ONCE() if a user-written value is ever less?
>
> Well, min_free_kbytes is a userspace thing, not a kernel thing - maybe
> THP shouldn't be dinking with it. What effect is THP trying to achieve
> and can we achieve it by other/better means?
It moved logic from hugeadm where few people knew about it to the
kernel. The value is related to anti-fragmentation. With the recommended
setting the probability of mixing pages of different mobility within a
single pageblock is reduced. Very very superficially, it reduces the
number of instances the mm_page_alloc_extfrag tracepoint is triggered
with parameters that are considered to be severely fragmenting.
--
Mel Gorman
SUSE Labs
next prev parent reply other threads:[~2014-01-15 15:22 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2014-01-01 0:29 [RFC] mm: show message when updating min_free_kbytes in thp Han Pingtian
2014-01-01 0:29 ` Han Pingtian
2014-01-02 18:05 ` Dave Hansen
2014-01-02 18:05 ` Dave Hansen
2014-01-02 21:58 ` David Rientjes
2014-01-02 21:58 ` David Rientjes
2014-01-02 22:10 ` Dave Hansen
2014-01-02 22:10 ` Dave Hansen
2014-01-02 23:36 ` David Rientjes
2014-01-02 23:36 ` David Rientjes
2014-01-02 23:48 ` Dave Hansen
2014-01-02 23:48 ` Dave Hansen
2014-01-03 3:33 ` Han Pingtian
2014-01-03 3:33 ` Han Pingtian
2014-01-03 18:17 ` Dave Hansen
2014-01-03 18:17 ` Dave Hansen
2014-01-05 0:35 ` Han Pingtian
2014-01-05 0:35 ` Han Pingtian
2014-01-06 16:46 ` Michal Hocko
2014-01-06 16:46 ` Michal Hocko
2014-01-08 3:59 ` Han Pingtian
2014-01-08 3:59 ` Han Pingtian
2014-01-08 8:20 ` Han Pingtian
2014-01-08 8:20 ` Han Pingtian
2014-01-08 10:16 ` Michal Hocko
2014-01-08 10:16 ` Michal Hocko
2014-01-09 7:32 ` Han Pingtian
2014-01-09 7:32 ` Han Pingtian
2014-01-09 9:02 ` Michal Hocko
2014-01-09 9:02 ` Michal Hocko
2014-01-09 21:15 ` David Rientjes
2014-01-09 21:15 ` David Rientjes
2014-01-10 8:05 ` Michal Hocko
2014-01-10 8:05 ` Michal Hocko
2014-01-10 8:13 ` Andrew Morton
2014-01-10 8:13 ` Andrew Morton
2014-01-10 8:17 ` Michal Hocko
2014-01-10 8:17 ` Michal Hocko
2014-01-11 3:27 ` Han Pingtian
2014-01-11 3:27 ` Han Pingtian
2014-01-14 20:07 ` Han Pingtian
2014-01-14 20:07 ` Han Pingtian
2014-01-14 23:52 ` Andrew Morton
2014-01-14 23:52 ` Andrew Morton
2014-01-15 0:25 ` David Rientjes
2014-01-15 0:25 ` David Rientjes
2014-01-15 0:35 ` Andrew Morton
2014-01-15 0:35 ` Andrew Morton
2014-01-15 0:52 ` David Rientjes
2014-01-15 0:52 ` David Rientjes
2014-01-15 15:22 ` Mel Gorman [this message]
2014-01-15 15:22 ` Mel Gorman
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=20140115152218.GL4963@suse.de \
--to=mgorman@suse.de \
--cc=akpm@linux-foundation.org \
--cc=dave.hansen@intel.com \
--cc=hanpt@linux.vnet.ibm.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=mhocko@suse.cz \
--cc=rientjes@google.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.