qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: Fam Zheng <famz@redhat.com>
To: Peter Lieven <pl@kamp.de>
Cc: kwolf@redhat.com, qemu-devel@nongnu.org, stefanha@redhat.com,
	shadowsor@gmail.com, pbonzini@redhat.com
Subject: Re: [Qemu-devel] [PATCHv2] block: introduce BDRV_O_SEQUENTIAL
Date: Mon, 24 Mar 2014 17:18:39 +0800	[thread overview]
Message-ID: <20140324091839.GB32359@T430.nay.redhat.com> (raw)
In-Reply-To: <1395402552-22366-1-git-send-email-pl@kamp.de>

On Fri, 03/21 12:49, Peter Lieven wrote:
> this patch introduces a new flag to indicate that we are going to sequentially
> read from a file and do not plan to reread/reuse the data after it has been read.
> 
> The current use of this flag is to open the source(s) of a qemu-img convert
> process. If a protocol from block/raw-posix.c is used posix_fadvise is utilized
> to advise to the kernel that we are going to read sequentially from the
> file and a POSIX_FADV_DONTNEED advise is issued after each write to indicate
> that there is no advantage keeping the blocks in the buffers.
> 
> Consider the following test case that was created to confirm the behaviour of
> the new flag:
> 
> A 10G logical volume was created and filled with random data.
> Then the logical volume was exported via qemu-img convert to an iscsi target.
> Before the export was started all caches of the linux kernel where dropped.
> 
> Old behavior:
>  - The convert process took 3m45s and the buffer cache grew up to 9.67 GB close
>    to the end of the conversion. After qemu-img terminated all the buffers were
>    freed by the kernel.
> 
> New behavior with the -N switch:
>  - The convert process took 3m43s and the buffer cache grew up to 15.48 MB close
>    to the end with some small peaks up to 30 MB durine the conversion.

s/durine/during/

The patch looks OK, and I have no objection with this flag. But I'm still
curious about the use case: Host page cache growing is not the real problem,
I'm not fully persudaded by commit message because I still don't know _what_
useful cache would be dropped (if you don't empty the kernel cache before
starting). I don't think all 9.67 GB buffer will be filled by data from this
volume, so the question is how to measure the real, effective performance
impact?

> 
> Signed-off-by: Peter Lieven <pl@kamp.de>
> ---
> v1->v2: - added test example to commit msg
>         - added -N knob to qemu-img
> 
>  block/raw-posix.c     |   14 ++++++++++++++
>  include/block/block.h |    1 +
>  qemu-img-cmds.hx      |    4 ++--
>  qemu-img.c            |   16 +++++++++++++---
>  qemu-img.texi         |    9 ++++++++-
>  5 files changed, 38 insertions(+), 6 deletions(-)
> 
> diff --git a/block/raw-posix.c b/block/raw-posix.c
> index 1688e16..08f7209 100644
> --- a/block/raw-posix.c
> +++ b/block/raw-posix.c
> @@ -444,6 +444,13 @@ static int raw_open_common(BlockDriverState *bs, QDict *options,
>      }
>  #endif
>  
> +#ifdef POSIX_FADV_SEQUENTIAL
> +    if (bs->open_flags & BDRV_O_SEQUENTIAL &&
> +        !(bs->open_flags & BDRV_O_NOCACHE)) {
> +        posix_fadvise(s->fd, 0, 0, POSIX_FADV_SEQUENTIAL);
> +    }
> +#endif
> +
>      ret = 0;
>  fail:
>      qemu_opts_del(opts);
> @@ -913,6 +920,13 @@ static int aio_worker(void *arg)
>              ret = aiocb->aio_nbytes;
>          }
>          if (ret == aiocb->aio_nbytes) {
> +#ifdef POSIX_FADV_DONTNEED
> +            if (aiocb->bs->open_flags & BDRV_O_SEQUENTIAL &&
> +                !(aiocb->bs->open_flags & BDRV_O_NOCACHE)) {
> +                posix_fadvise(aiocb->aio_fildes, aiocb->aio_offset,
> +                              aiocb->aio_nbytes, POSIX_FADV_DONTNEED);
> +            }
> +#endif

I'm not familiar with posix_fadvise, can we do this on the whole file in once
in raw_open_common like POSIX_FADV_SEQUENTIAL?

Thanks,
Fam

  parent reply	other threads:[~2014-03-24  9:18 UTC|newest]

Thread overview: 6+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-03-21 11:49 [Qemu-devel] [PATCHv2] block: introduce BDRV_O_SEQUENTIAL Peter Lieven
2014-03-21 12:06 ` Paolo Bonzini
2014-03-21 12:42   ` Peter Lieven
2014-03-28 10:02   ` Peter Lieven
2014-03-24  9:18 ` Fam Zheng [this message]
2014-03-24 14:02   ` Peter Lieven

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=20140324091839.GB32359@T430.nay.redhat.com \
    --to=famz@redhat.com \
    --cc=kwolf@redhat.com \
    --cc=pbonzini@redhat.com \
    --cc=pl@kamp.de \
    --cc=qemu-devel@nongnu.org \
    --cc=shadowsor@gmail.com \
    --cc=stefanha@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 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).