qemu-devel.nongnu.org archive mirror
 help / color / mirror / Atom feed
From: "Denis V. Lunev" <den@openvz.org>
Cc: Kevin Wolf <kwolf@redhat.com>, "Denis V. Lunev" <den@openvz.org>,
	Peter Lieven <pl@kamp.de>,
	qemu-devel@nongnu.org, Stefan Hajnoczi <stefanha@redhat.com>
Subject: [Qemu-devel] [PATCH 7/8] block/raw-posix: call plain fallocate in handle_aiocb_write_zeroes
Date: Tue, 30 Dec 2014 12:20:49 +0300	[thread overview]
Message-ID: <1419931250-19259-8-git-send-email-den@openvz.org> (raw)
In-Reply-To: <1419931250-19259-1-git-send-email-den@openvz.org>

There is a possibility that we are extending our image and thus writing
zeroes beyond end of the file. In this case we do not need to care
about the hole to make sure that there is no data in the file under
this offset (pre-condition to fallocate(0) to work). We could simply call
fallocate(0).

This improves the performance of writing zeroes even on really old
platforms which do not have even FALLOC_FL_PUNCH_HOLE.

Signed-off-by: Denis V. Lunev <den@openvz.org>
CC: Kevin Wolf <kwolf@redhat.com>
CC: Stefan Hajnoczi <stefanha@redhat.com>
CC: Peter Lieven <pl@kamp.de>
---
 block/raw-posix.c | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/block/raw-posix.c b/block/raw-posix.c
index 96a8678..57b94ad 100644
--- a/block/raw-posix.c
+++ b/block/raw-posix.c
@@ -60,7 +60,7 @@
 #define FS_NOCOW_FL                     0x00800000 /* Do not cow file */
 #endif
 #endif
-#if defined(CONFIG_FALLOCATE_PUNCH_HOLE) || defined(CONFIG_FALLOCATE_ZERO_RANGE)
+#ifdef CONFIG_FALLOCATE
 #include <linux/falloc.h>
 #endif
 #if defined (__FreeBSD__) || defined(__FreeBSD_kernel__)
@@ -903,7 +903,7 @@ static int translate_err(int err)
     return err;
 }
 
-#if defined(CONFIG_FALLOCATE_PUNCH_HOLE) || defined(CONFIG_FALLOCATE_ZERO_RANGE)
+#ifdef CONFIG_FALLOCATE
 static int do_fallocate(int fd, int mode, off_t offset, off_t len)
 {
     do {
@@ -957,6 +957,12 @@ static ssize_t handle_aiocb_write_zeroes(RawPosixAIOData *aiocb)
 
     s = aiocb->bs->opaque;
 
+#ifdef CONFIG_FALLOCATE
+    if (aiocb->aio_offset >= aiocb->bs->total_sectors << BDRV_SECTOR_BITS) {
+        return do_fallocate(s->fd, 0, aiocb->aio_offset, aiocb->aio_nbytes);
+    }
+#endif
+
 #ifdef CONFIG_FALLOCATE_ZERO_RANGE
     if (s->has_write_zeroes) {
         int ret = do_fallocate(s->fd, FALLOC_FL_ZERO_RANGE,
-- 
1.9.1

  parent reply	other threads:[~2014-12-30  9:21 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-12-30  9:20 [Qemu-devel] [PATCH v3 0/8] eliminate data write in bdrv_write_zeroes on Linux in raw-posix.c Denis V. Lunev
2014-12-30  9:20 ` [Qemu-devel] [PATCH 1/8] block: prepare bdrv_co_do_write_zeroes to deal with large bl.max_write_zeroes Denis V. Lunev
2015-01-05  7:34   ` Peter Lieven
2015-01-05 11:06     ` Denis V. Lunev
2015-01-05 11:23       ` Peter Lieven
2015-01-05 11:48         ` Denis V. Lunev
2015-01-05 12:26         ` [Qemu-devel] [PATCH v2 1/1] " Denis V. Lunev
2015-01-05 12:32           ` [Qemu-devel] [PATCH v3 " Denis V. Lunev
2014-12-30  9:20 ` [Qemu-devel] [PATCH 2/8] block: use fallocate(FALLOC_FL_ZERO_RANGE) in handle_aiocb_write_zeroes Denis V. Lunev
2014-12-30  9:20 ` [Qemu-devel] [PATCH 3/8] block/raw-posix: create do_fallocate helper Denis V. Lunev
2014-12-30  9:20 ` [Qemu-devel] [PATCH 4/8] block/raw-posix: create translate_err helper to merge errno values Denis V. Lunev
2015-01-05  6:46   ` Fam Zheng
2015-01-05 11:17     ` Denis V. Lunev
2014-12-30  9:20 ` [Qemu-devel] [PATCH 5/8] block/raw-posix: refactor handle_aiocb_write_zeroes a bit Denis V. Lunev
2015-01-05  6:57   ` Fam Zheng
2015-01-05 11:07     ` Denis V. Lunev
2014-12-30  9:20 ` [Qemu-devel] [PATCH 6/8] block: use fallocate(FALLOC_FL_PUNCH_HOLE) & fallocate(0) to write zeroes Denis V. Lunev
2015-01-05  7:02   ` Fam Zheng
2015-01-05 11:14     ` Denis V. Lunev
2014-12-30  9:20 ` Denis V. Lunev [this message]
2014-12-30  9:20 ` [Qemu-devel] [PATCH 8/8] block/raw-posix: set max_write_zeroes to INT_MAX for regular files Denis V. Lunev
2014-12-30 10:55 ` [Qemu-devel] [PATCH v3 0/8] eliminate data write in bdrv_write_zeroes on Linux in raw-posix.c Peter Lieven
2014-12-30 11:07   ` Denis V. Lunev
2015-01-05  6:55     ` 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=1419931250-19259-8-git-send-email-den@openvz.org \
    --to=den@openvz.org \
    --cc=kwolf@redhat.com \
    --cc=pl@kamp.de \
    --cc=qemu-devel@nongnu.org \
    --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).