All of lore.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@linux-foundation.org>
To: Pavel Machek <pavel@suse.cz>
Cc: mtk.manpages@gmail.com, Hugh Dickins <hugh@veritas.com>,
	kernel list <linux-kernel@vger.kernel.org>,
	"Rafael J. Wysocki" <rjw@sisk.pl>
Subject: Re: sync_file_range(SYNC_FILE_RANGE_WRITE) blocks?
Date: Sun, 1 Jun 2008 15:47:36 -0700	[thread overview]
Message-ID: <20080601154736.2e9f5905.akpm@linux-foundation.org> (raw)
In-Reply-To: <20080601222202.GA2255@elf.ucw.cz>

On Mon, 2 Jun 2008 00:22:02 +0200 Pavel Machek <pavel@suse.cz> wrote:

> Hi!
> 
> > > > I expect major users of this system call will be applications which do
> > > > small-sized overwrites into large files, mainly databases.  That is,
> > > > once the application developers discover its existence.  I'm still
> > > > getting expressions of wonder from people who I tell about the
> > > > five-year-old fadvise().
> > > 
> > > Hey, you have one user now, its called s2disk. But for this call to be
> > > useful, we'd need asynchronous variant... is there such thing?
> > 
> > Well if you're asking the syscall to shove more data into the block
> > layer than it can concurrently handle, sure, the block layer will
> > block.  It's tunable...
> 
> No, no, I don't want to overload block layer. All I want is ...
> 
> > > Okay, I can fork and do the call from another process, but...
> > 
> > I sense a strangeness.  What are you actually trying to do with all of this?
> 
> Okay, so I have around 400MB of data, I want it compressed, optionally
> encrypted and written to partition.
> 
> Now, if I do it "naturally", I do writes, followed by fsync.
> 
> That's bad, because kernel does not start write out immediately, and
> we waste time with idle disk. (If data compress really well, or
> encryption is off, this is significant).
> 
> So we improve on this, by doing sync_file_range(SYNC_FILE_RANGE_WRITE)
> periodically. That keeps the disk busy, but occassionaly blocks the
> cpu... wasting time (which mostly hurts in compression+encryption
> case).

yep.  That's another use of sync_file_range(): to allow smart userspace
to optimise the kernel's IO scheduling decisions.

> So... how can I keep _both_ cpu and disk busy?

pthread_create() ;)

How about this:

- Add a new SYNC_FILE_RANGE_NON_BLOCKING

- If userspace set that flag, turn on writeback_control.nonblocking
  in __filemap_fdatawrite_range().

- test it a lot.

It will be userspace's responsibility to avoid burning huge amounts of
CPU repeatedly calling sync_file_range() and having it not actually write
anything.



  reply	other threads:[~2008-06-01 22:48 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2008-05-30 10:26 sync_file_range(SYNC_FILE_RANGE_WRITE) blocks? Pavel Machek
2008-05-30 13:58 ` Hugh Dickins
2008-05-30 20:43   ` Pavel Machek
2008-05-31 18:44     ` Hugh Dickins
2008-06-01  0:39       ` Andrew Morton
2008-06-01  7:23         ` Hugh Dickins
2008-06-01  8:15           ` Andrew Morton
2008-06-01 11:40             ` Pavel Machek
2008-06-01 20:37               ` Andrew Morton
2008-06-01 22:00                 ` Rafael J. Wysocki
2008-06-01 22:22                 ` Pavel Machek
2008-06-01 22:47                   ` Andrew Morton [this message]
2008-06-01 23:00                     ` Pavel Machek
2008-06-01 23:11                       ` Andrew Morton
2008-06-02  8:43                         ` Hugh Dickins
2008-06-02 11:18                           ` Rafael J. Wysocki
2008-06-02 12:11                             ` Hugh Dickins
2008-06-02 11:43                 ` Jens Axboe
2008-06-02 12:40                   ` Hugh Dickins
2008-06-16 20:53                     ` Rik van Riel
2008-06-17  4:54                       ` Andrew Morton
2008-06-17 13:38                         ` Rik van Riel
2008-06-02 16:50                   ` Andrew Morton
2008-06-03  8:01               ` Michael Kerrisk
2008-06-03  8:05                 ` Pavel Machek

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=20080601154736.2e9f5905.akpm@linux-foundation.org \
    --to=akpm@linux-foundation.org \
    --cc=hugh@veritas.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mtk.manpages@gmail.com \
    --cc=pavel@suse.cz \
    --cc=rjw@sisk.pl \
    /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.