mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Maxim Patlasov <mpatlasov@parallels.com>
To: miklos@szeredi.hu
Cc: fuse-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org,
	devel@openvz.org
Subject: [PATCH v2 00/11] fuse: optimize scatter-gather direct IO
Date: Wed, 19 Sep 2012 20:31:10 +0400	[thread overview]
Message-ID: <20120919161559.29482.55120.stgit@maximpc.sw.ru> (raw)

Hi,

Existing fuse implementation processes scatter-gather direct IO in suboptimal
way: fuse_direct_IO passes iovec[] to fuse_loop_dio and the latter calls
fuse_direct_read/write for each iovec from iovec[] array. Thus we have as many
submitted fuse-requests as the number of elements in iovec[] array. This is
pure waste of resources and affects performance negatively especially for the
case of many small chunks (e.g. page-size) packed in one iovec[] array.

The patch-set amends situation in a natural way: let's simply pack as
many iovec[] segments to every fuse-request as possible.

To estimate performance improvement I used slightly modified fusexmp over
tmpfs (clearing O_DIRECT bit from fi->flags in xmp_open). The test opened
a file with O_DIRECT, then called readv/writev in a loop. An iovec[] for
readv/writev consisted of 32 segments of 4K each. The throughput on some
commodity (rather feeble) server was (in MB/sec):

        original / patched
writev: ~107     / ~480
readv:  ~114     / ~569

We're exploring possibility to use fuse for our own distributed storage
implementation and big iovec[] arrays of many page-size chunks is typical
use-case for device virtualization thread performing i/o on behalf of
virtual-machine it serves.

Changed in v2:
 - inline array of page pointers req->pages[] is replaced with dynamically
   allocated one; the number of elements is calculated a bit more
   intelligently than being equal to FUSE_MAX_PAGES_PER_REQ; this is done
   for the sake of memory economy.
 - a dynamically allocated array of so-called 'page descriptors' - an offset
   in page plus the length of fragment - is added to fuse_req; this is done
   to simplify processing fuse requests covering several iov-s.

Thanks,
Maxim

---

Maxim Patlasov (11):
      fuse: general infrastructure for pages[] of variable size
      fuse: categorize fuse_get_req()
      fuse: rework fuse_retrieve()
      fuse: rework fuse_readpages()
      fuse: rework fuse_perform_write()
      fuse: rework fuse_do_ioctl()
      fuse: add per-page descriptor <offset, length> to fuse_req
      fuse: use req->page_descs[] for argpages cases
      fuse: pass iov[] to fuse_get_user_pages()
      fuse: optimize fuse_get_user_pages()
      fuse: optimize __fuse_direct_io()


 fs/fuse/cuse.c   |    3 -
 fs/fuse/dev.c    |   96 ++++++++++++++-------
 fs/fuse/dir.c    |   39 ++++----
 fs/fuse/file.c   |  250 ++++++++++++++++++++++++++++++++++++------------------
 fs/fuse/fuse_i.h |   47 ++++++++--
 fs/fuse/inode.c  |    6 +
 6 files changed, 296 insertions(+), 145 deletions(-)

-- 
Signature

             reply	other threads:[~2012-09-19 16:31 UTC|newest]

Thread overview: 23+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-09-19 16:31 Maxim Patlasov [this message]
2012-09-19 16:31 ` [PATCH 01/11] fuse: general infrastructure for pages[] of variable size Maxim Patlasov
2012-10-24 16:09   ` Miklos Szeredi
2012-09-19 16:31 ` [PATCH 02/11] fuse: categorize fuse_get_req() Maxim Patlasov
2012-10-24 16:26   ` Miklos Szeredi
2012-09-19 16:32 ` [PATCH 03/11] fuse: rework fuse_retrieve() Maxim Patlasov
2012-09-19 16:32 ` [PATCH 04/11] fuse: rework fuse_readpages() Maxim Patlasov
2012-09-19 16:32 ` [PATCH 05/11] fuse: rework fuse_perform_write() Maxim Patlasov
2012-09-19 16:32 ` [PATCH 06/11] fuse: rework fuse_do_ioctl() Maxim Patlasov
2012-09-19 16:32 ` [PATCH 07/11] fuse: add per-page descriptor <offset, length> to fuse_req Maxim Patlasov
2012-10-01 11:20   ` [PATCH 07/11] fuse: add per-page descriptor <offset, length> to fuse_req (v2) Maxim Patlasov
2012-10-25 13:24     ` Miklos Szeredi
2012-10-25 13:39       ` Maxim V. Patlasov
2012-09-19 16:33 ` [PATCH 08/11] fuse: use req->page_descs[] for argpages cases Maxim Patlasov
2012-10-25 14:05   ` Miklos Szeredi
2012-10-25 15:38     ` Maxim V. Patlasov
2012-09-19 16:33 ` [PATCH 09/11] fuse: pass iov[] to fuse_get_user_pages() Maxim Patlasov
2012-10-25 14:29   ` Miklos Szeredi
2012-09-19 16:33 ` [PATCH 10/11] fuse: optimize fuse_get_user_pages() Maxim Patlasov
2012-10-15 12:03   ` [PATCH 10/11] fuse: optimize fuse_get_user_pages() - v2 Maxim Patlasov
2012-10-25 14:50     ` Miklos Szeredi
2012-09-19 16:33 ` [PATCH 11/11] fuse: optimize __fuse_direct_io() Maxim Patlasov
2012-10-16 17:32 ` [PATCH v2 00/11] fuse: optimize scatter-gather direct IO Maxim V. Patlasov

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=20120919161559.29482.55120.stgit@maximpc.sw.ru \
    --to=mpatlasov@parallels.com \
    --cc=devel@openvz.org \
    --cc=fuse-devel@lists.sourceforge.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=miklos@szeredi.hu \
    /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

Powered by JetHome