All of lore.kernel.org
 help / color / mirror / Atom feed
From: Dave Chinner <david@fromorbit.com>
To: Matthew Wilcox <matthew@wil.cx>
Cc: Mel Gorman <mgorman@suse.de>,
	James Bottomley <James.Bottomley@HansenPartnership.com>,
	"linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org>,
	Chris Mason <clm@fb.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-ide@vger.kernel.org" <linux-ide@vger.kernel.org>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"lsf-pc@lists.linux-foundation.org"
	<lsf-pc@lists.linux-foundation.org>,
	"rwheeler@redhat.com" <rwheeler@redhat.com>
Subject: Re: [Lsf-pc] [LSF/MM TOPIC] really large storage sectors - going beyond 4096 bytes
Date: Thu, 30 Jan 2014 17:01:03 +1100	[thread overview]
Message-ID: <20140130060103.GF13997@dastard> (raw)
In-Reply-To: <20140130045245.GH20939@parisc-linux.org>

On Wed, Jan 29, 2014 at 09:52:46PM -0700, Matthew Wilcox wrote:
> On Fri, Jan 24, 2014 at 10:57:48AM +0000, Mel Gorman wrote:
> > So far on the table is
> > 
> > 1. major filesystem overhawl
> > 2. major vm overhawl
> > 3. use compound pages as they are today and hope it does not go
> >    completely to hell, reboot when it does
> 
> Is the below paragraph an exposition of option 2, or is it an option 4,
> change the VM unit of allocation?  Other than the names you're using,
> this is basically what I said to Kirill in an earlier thread; either
> scrap the difference between PAGE_SIZE and PAGE_CACHE_SIZE, or start
> making use of it.

Christoph Lamater's compound page patch set scrapped PAGE_CACHE_SIZE
and made it a variable that was set on the struct address_space when
it was instantiated by the filesystem. In effect, it allowed
filesystems to specify the unit of page cache allocation on a
per-inode basis.

> The fact that EVERYBODY in this thread has been using PAGE_SIZE when they
> should have been using PAGE_CACHE_SIZE makes me wonder if part of the
> problem is that the split in naming went the wrong way.  ie use PTE_SIZE
> for 'the amount of memory pointed to by a pte_t' and use PAGE_SIZE for
> 'the amount of memory described by a struct page'.

PAGE_CACHE_SIZE was never distributed sufficiently to be used, and
if you #define it to something other than PAGE_SIZE stuff will
simply break.

> (we need to remove the current users of PTE_SIZE; sparc32 and powerpc32,
> but that's just a detail)
> 
> And we need to fix all the places that are currently getting the
> distinction wrong.  SMOP ... ;-)  What would help is correct typing of
> variables, possibly with sparse support to help us out.  Big Job.

Yes, that's what the Christoph's patchset did.

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

--
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: Dave Chinner <david@fromorbit.com>
To: Matthew Wilcox <matthew@wil.cx>
Cc: Mel Gorman <mgorman@suse.de>,
	James Bottomley <James.Bottomley@HansenPartnership.com>,
	"linux-scsi@vger.kernel.org" <linux-scsi@vger.kernel.org>,
	Chris Mason <clm@fb.com>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	"linux-mm@kvack.org" <linux-mm@kvack.org>,
	"linux-ide@vger.kernel.org" <linux-ide@vger.kernel.org>,
	"linux-fsdevel@vger.kernel.org" <linux-fsdevel@vger.kernel.org>,
	"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
	"lsf-pc@lists.linux-foundation.org" 
	<lsf-pc@lists.linux-foundation.org>,
	"rwheeler@redhat.com" <rwheeler@redhat.com>
Subject: Re: [Lsf-pc] [LSF/MM TOPIC] really large storage sectors - going beyond 4096 bytes
Date: Thu, 30 Jan 2014 17:01:03 +1100	[thread overview]
Message-ID: <20140130060103.GF13997@dastard> (raw)
In-Reply-To: <20140130045245.GH20939@parisc-linux.org>

On Wed, Jan 29, 2014 at 09:52:46PM -0700, Matthew Wilcox wrote:
> On Fri, Jan 24, 2014 at 10:57:48AM +0000, Mel Gorman wrote:
> > So far on the table is
> > 
> > 1. major filesystem overhawl
> > 2. major vm overhawl
> > 3. use compound pages as they are today and hope it does not go
> >    completely to hell, reboot when it does
> 
> Is the below paragraph an exposition of option 2, or is it an option 4,
> change the VM unit of allocation?  Other than the names you're using,
> this is basically what I said to Kirill in an earlier thread; either
> scrap the difference between PAGE_SIZE and PAGE_CACHE_SIZE, or start
> making use of it.

Christoph Lamater's compound page patch set scrapped PAGE_CACHE_SIZE
and made it a variable that was set on the struct address_space when
it was instantiated by the filesystem. In effect, it allowed
filesystems to specify the unit of page cache allocation on a
per-inode basis.

> The fact that EVERYBODY in this thread has been using PAGE_SIZE when they
> should have been using PAGE_CACHE_SIZE makes me wonder if part of the
> problem is that the split in naming went the wrong way.  ie use PTE_SIZE
> for 'the amount of memory pointed to by a pte_t' and use PAGE_SIZE for
> 'the amount of memory described by a struct page'.

PAGE_CACHE_SIZE was never distributed sufficiently to be used, and
if you #define it to something other than PAGE_SIZE stuff will
simply break.

> (we need to remove the current users of PTE_SIZE; sparc32 and powerpc32,
> but that's just a detail)
> 
> And we need to fix all the places that are currently getting the
> distinction wrong.  SMOP ... ;-)  What would help is correct typing of
> variables, possibly with sparse support to help us out.  Big Job.

Yes, that's what the Christoph's patchset did.

Cheers,

Dave.
-- 
Dave Chinner
david@fromorbit.com

  reply	other threads:[~2014-01-30  6:01 UTC|newest]

Thread overview: 121+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-12-20  9:30 LSF/MM 2014 Call For Proposals Mel Gorman
2013-12-20  9:30 ` Mel Gorman
2013-12-20  9:30 ` [Lsf-pc] " Mel Gorman
2014-01-06 22:20 ` [LSF/MM TOPIC] [ATTEND] persistent memory progress, management of storage & file systems Ric Wheeler
2014-01-06 22:20   ` Ric Wheeler
2014-01-06 22:32   ` faibish, sorin
2014-01-06 22:32     ` faibish, sorin
2014-01-07 19:44     ` Joel Becker
2014-01-07 19:44       ` Joel Becker
2014-01-21  7:00 ` LSF/MM 2014 Call For Proposals Michel Lespinasse
2014-01-21  7:00   ` Michel Lespinasse
2014-01-22  3:04 ` [LSF/MM TOPIC] really large storage sectors - going beyond 4096 bytes Ric Wheeler
2014-01-22  3:04   ` Ric Wheeler
2014-01-22  5:20   ` Joel Becker
2014-01-22  5:20     ` Joel Becker
2014-01-22  7:14     ` Hannes Reinecke
2014-01-22  7:14       ` Hannes Reinecke
2014-01-22  7:14       ` Hannes Reinecke
2014-01-22  9:34   ` [Lsf-pc] " Mel Gorman
2014-01-22  9:34     ` Mel Gorman
2014-01-22 14:10     ` Ric Wheeler
2014-01-22 14:10       ` Ric Wheeler
2014-01-22 14:34       ` Mel Gorman
2014-01-22 14:34         ` Mel Gorman
2014-01-22 14:58         ` Ric Wheeler
2014-01-22 14:58           ` Ric Wheeler
2014-01-22 15:19           ` Mel Gorman
2014-01-22 15:19             ` Mel Gorman
2014-01-22 17:02             ` Chris Mason
2014-01-22 17:02               ` Chris Mason
2014-01-22 17:21               ` James Bottomley
2014-01-22 17:21                 ` James Bottomley
2014-01-22 18:02                 ` Chris Mason
2014-01-22 18:02                   ` Chris Mason
2014-01-22 18:13                   ` James Bottomley
2014-01-22 18:13                     ` James Bottomley
2014-01-22 18:17                     ` Ric Wheeler
2014-01-22 18:17                       ` Ric Wheeler
2014-01-22 18:35                       ` James Bottomley
2014-01-22 18:35                         ` James Bottomley
2014-01-22 18:39                         ` Ric Wheeler
2014-01-22 18:39                           ` Ric Wheeler
2014-01-22 19:30                           ` James Bottomley
2014-01-22 19:30                             ` James Bottomley
2014-01-22 19:50                             ` Andrew Morton
2014-01-22 19:50                               ` Andrew Morton
2014-01-22 20:13                               ` Chris Mason
2014-01-22 20:13                                 ` Chris Mason
2014-01-23  2:46                                 ` David Lang
2014-01-23  2:46                                   ` David Lang
2014-01-23  5:21                                   ` Theodore Ts'o
2014-01-23  5:21                                     ` Theodore Ts'o
2014-01-23  8:35                               ` Dave Chinner
2014-01-23  8:35                                 ` Dave Chinner
2014-01-23 12:55                                 ` Theodore Ts'o
2014-01-23 12:55                                   ` Theodore Ts'o
2014-01-23 19:49                                   ` Dave Chinner
2014-01-23 19:49                                     ` Dave Chinner
2014-01-23 21:21                                   ` Joel Becker
2014-01-23 21:21                                     ` Joel Becker
2014-01-22 20:57                             ` Martin K. Petersen
2014-01-22 20:57                               ` Martin K. Petersen
2014-01-22 20:57                               ` Martin K. Petersen
2014-01-22 18:37                     ` Chris Mason
2014-01-22 18:37                       ` Chris Mason
2014-01-22 18:40                       ` Ric Wheeler
2014-01-22 18:40                         ` Ric Wheeler
2014-01-22 18:47                       ` James Bottomley
2014-01-22 18:47                         ` James Bottomley
2014-01-23 21:27                         ` Joel Becker
2014-01-23 21:27                           ` Joel Becker
2014-01-23 21:34                           ` Chris Mason
2014-01-23 21:34                             ` Chris Mason
2014-01-23  8:27                     ` Dave Chinner
2014-01-23  8:27                       ` Dave Chinner
2014-01-23 15:47                       ` James Bottomley
2014-01-23 15:47                         ` James Bottomley
2014-01-23 16:44                         ` Mel Gorman
2014-01-23 16:44                           ` Mel Gorman
2014-01-23 19:55                           ` James Bottomley
2014-01-23 19:55                             ` James Bottomley
2014-01-24 10:57                             ` Mel Gorman
2014-01-24 10:57                               ` Mel Gorman
2014-01-30  4:52                               ` Matthew Wilcox
2014-01-30  4:52                                 ` Matthew Wilcox
2014-01-30  6:01                                 ` Dave Chinner [this message]
2014-01-30  6:01                                   ` Dave Chinner
2014-01-30 10:50                                 ` Mel Gorman
2014-01-30 10:50                                   ` Mel Gorman
2014-01-23 20:34                           ` Dave Chinner
2014-01-23 20:34                             ` Dave Chinner
2014-01-23 20:54                         ` Christoph Lameter
2014-01-23 20:54                           ` Christoph Lameter
2014-01-23  8:24                 ` Dave Chinner
2014-01-23  8:24                   ` Dave Chinner
2014-01-23 20:48             ` Christoph Lameter
2014-01-23 20:48               ` Christoph Lameter
2014-01-22 20:47           ` Martin K. Petersen
2014-01-22 20:47             ` Martin K. Petersen
2014-01-23  8:21         ` Dave Chinner
2014-01-23  8:21           ` Dave Chinner
2014-01-22 15:14     ` Chris Mason
2014-01-22 15:14       ` Chris Mason
2014-01-22 16:03       ` James Bottomley
2014-01-22 16:03         ` James Bottomley
2014-01-22 16:45         ` Ric Wheeler
2014-01-22 16:45           ` Ric Wheeler
2014-01-22 17:00           ` James Bottomley
2014-01-22 17:00             ` James Bottomley
2014-01-22 21:05             ` Jan Kara
2014-01-22 21:05               ` Jan Kara
2014-01-23 20:47     ` Christoph Lameter
2014-01-23 20:47       ` Christoph Lameter
2014-01-24 11:09       ` Mel Gorman
2014-01-24 11:09         ` Mel Gorman
2014-01-24 15:44         ` Christoph Lameter
2014-01-24 15:44           ` Christoph Lameter
2014-01-22 15:54   ` James Bottomley
2014-01-22 15:54     ` James Bottomley
2014-03-14  9:02 ` Update on LSF/MM [was Re: LSF/MM 2014 Call For Proposals] James Bottomley
2014-03-14  9:02   ` James Bottomley

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=20140130060103.GF13997@dastard \
    --to=david@fromorbit.com \
    --cc=James.Bottomley@HansenPartnership.com \
    --cc=akpm@linux-foundation.org \
    --cc=clm@fb.com \
    --cc=linux-fsdevel@vger.kernel.org \
    --cc=linux-ide@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux-scsi@vger.kernel.org \
    --cc=lsf-pc@lists.linux-foundation.org \
    --cc=matthew@wil.cx \
    --cc=mgorman@suse.de \
    --cc=rwheeler@redhat.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.