All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kevin Wolf <kwolf@redhat.com>
To: anthony@codemonkey.ws
Cc: kwolf@redhat.com, qemu-devel@nongnu.org
Subject: [Qemu-devel] [PATCH 1/6] block: Change bdrv_commit to handle multiple sectors at once
Date: Tue,  3 Aug 2010 16:44:25 +0200	[thread overview]
Message-ID: <1280846670-27063-2-git-send-email-kwolf@redhat.com> (raw)
In-Reply-To: <1280846670-27063-1-git-send-email-kwolf@redhat.com>

bdrv_commit copies the image to its backing file sector by sector, which
is (surprise!) relatively slow. Let's take a larger buffer and handle more
sectors at once if possible.

With a 1G qcow2 file, this brought the time bdrv_commit takes down from
5:06 min to 1:14 min for me.

Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block.c |   39 ++++++++++++++++++++-------------------
 1 files changed, 20 insertions(+), 19 deletions(-)

diff --git a/block.c b/block.c
index 452ae94..c4d6814 100644
--- a/block.c
+++ b/block.c
@@ -739,14 +739,16 @@ int bdrv_check(BlockDriverState *bs, BdrvCheckResult *res)
     return bs->drv->bdrv_check(bs, res);
 }
 
+#define COMMIT_BUF_SECTORS 2048
+
 /* commit COW file into the raw image */
 int bdrv_commit(BlockDriverState *bs)
 {
     BlockDriver *drv = bs->drv;
-    int64_t i, total_sectors;
-    int n, j, ro, open_flags;
+    int64_t sector, total_sectors;
+    int n, ro, open_flags;
     int ret = 0, rw_ret = 0;
-    unsigned char sector[BDRV_SECTOR_SIZE];
+    uint8_t *buf;
     char filename[1024];
     BlockDriverState *bs_rw, *bs_ro;
 
@@ -789,22 +791,20 @@ int bdrv_commit(BlockDriverState *bs)
     }
 
     total_sectors = bdrv_getlength(bs) >> BDRV_SECTOR_BITS;
-    for (i = 0; i < total_sectors;) {
-        if (drv->bdrv_is_allocated(bs, i, 65536, &n)) {
-            for(j = 0; j < n; j++) {
-                if (bdrv_read(bs, i, sector, 1) != 0) {
-                    ret = -EIO;
-                    goto ro_cleanup;
-                }
+    buf = qemu_malloc(COMMIT_BUF_SECTORS * BDRV_SECTOR_SIZE);
 
-                if (bdrv_write(bs->backing_hd, i, sector, 1) != 0) {
-                    ret = -EIO;
-                    goto ro_cleanup;
-                }
-                i++;
-	    }
-	} else {
-            i += n;
+    for (sector = 0; sector < total_sectors; sector += n) {
+        if (drv->bdrv_is_allocated(bs, sector, COMMIT_BUF_SECTORS, &n)) {
+
+            if (bdrv_read(bs, sector, buf, n) != 0) {
+                ret = -EIO;
+                goto ro_cleanup;
+            }
+
+            if (bdrv_write(bs->backing_hd, sector, buf, n) != 0) {
+                ret = -EIO;
+                goto ro_cleanup;
+            }
         }
     }
 
@@ -821,6 +821,7 @@ int bdrv_commit(BlockDriverState *bs)
         bdrv_flush(bs->backing_hd);
 
 ro_cleanup:
+    qemu_free(buf);
 
     if (ro) {
         /* re-open as RO */
-- 
1.7.2

  reply	other threads:[~2010-08-03 14:44 UTC|newest]

Thread overview: 14+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-08-03 14:44 [Qemu-devel] [PULL 0/6] Block patches Kevin Wolf
2010-08-03 14:44 ` Kevin Wolf [this message]
2010-08-03 14:44 ` [Qemu-devel] [PATCH 2/6] loadvm: improve tests before bdrv_snapshot_goto() Kevin Wolf
2011-04-14  9:10   ` [Qemu-devel] [BUG] Re: [2/6] " Philipp Hahn
2011-04-14  9:29     ` Kevin Wolf
2011-08-09 22:35       ` [Qemu-devel] [libvirt] " Eric Blake
2010-08-03 14:44 ` [Qemu-devel] [PATCH 3/6] block migration: replace tabs by spaces Kevin Wolf
2010-08-03 14:44 ` [Qemu-devel] [PATCH 4/6] block: Fix bdrv_has_zero_init Kevin Wolf
2010-08-03 14:44 ` [Qemu-devel] [PATCH 5/6] block: Change bdrv_eject() not to drop the image Kevin Wolf
2010-08-03 14:44 ` [Qemu-devel] [PATCH 6/6] ide: Avoid canceling IDE DMA Kevin Wolf
2011-03-18 11:19   ` Christoph Hellwig
2011-03-18 11:34     ` Kevin Wolf
2011-03-18 14:10       ` Christoph Hellwig
2010-08-09 13:41 ` [Qemu-devel] [PULL 0/6] Block patches Anthony Liguori

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=1280846670-27063-2-git-send-email-kwolf@redhat.com \
    --to=kwolf@redhat.com \
    --cc=anthony@codemonkey.ws \
    --cc=qemu-devel@nongnu.org \
    /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.