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 03/30] block: add cache=directsync parameter to -drive
Date: Mon, 29 Aug 2011 16:53:11 +0200	[thread overview]
Message-ID: <1314629618-8308-4-git-send-email-kwolf@redhat.com> (raw)
In-Reply-To: <1314629618-8308-1-git-send-email-kwolf@redhat.com>

From: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>

This patch adds -drive cache=directsync for O_DIRECT | O_SYNC host file
I/O with no disk write cache presented to the guest.

This mode is useful when guests may not be sending flushes when
appropriate and therefore leave data at risk in case of power failure.
When cache=directsync is used, write operations are only completed to
the guest when data is safely on disk.

This new mode is like cache=writethrough but it bypasses the host page
cache.

Signed-off-by: Stefan Hajnoczi <stefanha@linux.vnet.ibm.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block.c         |    6 ++++--
 qemu-config.c   |    3 ++-
 qemu-img.c      |    3 ++-
 qemu-options.hx |    8 ++++++--
 4 files changed, 14 insertions(+), 6 deletions(-)

diff --git a/block.c b/block.c
index dbef3ae..4186a2f 100644
--- a/block.c
+++ b/block.c
@@ -448,6 +448,8 @@ int bdrv_parse_cache_flags(const char *mode, int *flags)
 
     if (!strcmp(mode, "off") || !strcmp(mode, "none")) {
         *flags |= BDRV_O_NOCACHE | BDRV_O_CACHE_WB;
+    } else if (!strcmp(mode, "directsync")) {
+        *flags |= BDRV_O_NOCACHE;
     } else if (!strcmp(mode, "writeback")) {
         *flags |= BDRV_O_CACHE_WB;
     } else if (!strcmp(mode, "unsafe")) {
@@ -1188,8 +1190,8 @@ int bdrv_pwrite_sync(BlockDriverState *bs, int64_t offset,
         return ret;
     }
 
-    /* No flush needed for cache=writethrough, it uses O_DSYNC */
-    if ((bs->open_flags & BDRV_O_CACHE_MASK) != 0) {
+    /* No flush needed for cache modes that use O_DSYNC */
+    if ((bs->open_flags & BDRV_O_CACHE_WB) != 0) {
         bdrv_flush(bs);
     }
 
diff --git a/qemu-config.c b/qemu-config.c
index 1eb6b9a..139e077 100644
--- a/qemu-config.c
+++ b/qemu-config.c
@@ -55,7 +55,8 @@ static QemuOptsList qemu_drive_opts = {
         },{
             .name = "cache",
             .type = QEMU_OPT_STRING,
-            .help = "host cache usage (none, writeback, writethrough, unsafe)",
+            .help = "host cache usage (none, writeback, writethrough, "
+                    "directsync, unsafe)",
         },{
             .name = "aio",
             .type = QEMU_OPT_STRING,
diff --git a/qemu-img.c b/qemu-img.c
index 5e203c2..10a3a8b 100644
--- a/qemu-img.c
+++ b/qemu-img.c
@@ -66,7 +66,8 @@ static void help(void)
            "  'filename' is a disk image filename\n"
            "  'fmt' is the disk image format. It is guessed automatically in most cases\n"
            "  'cache' is the cache mode used to write the output disk image, the valid\n"
-           "    options are: 'none', 'writeback' (default), 'writethrough' and 'unsafe'\n"
+           "    options are: 'none', 'writeback' (default), 'writethrough', 'directsync'\n"
+           "    and 'unsafe'\n"
            "  'size' is the disk image size in bytes. Optional suffixes\n"
            "    'k' or 'K' (kilobyte, 1024), 'M' (megabyte, 1024k), 'G' (gigabyte, 1024M)\n"
            "    and T (terabyte, 1024G) are supported. 'b' is ignored.\n"
diff --git a/qemu-options.hx b/qemu-options.hx
index d86815d..35d95d1 100644
--- a/qemu-options.hx
+++ b/qemu-options.hx
@@ -133,7 +133,7 @@ ETEXI
 DEF("drive", HAS_ARG, QEMU_OPTION_drive,
     "-drive [file=file][,if=type][,bus=n][,unit=m][,media=d][,index=i]\n"
     "       [,cyls=c,heads=h,secs=s[,trans=t]][,snapshot=on|off]\n"
-    "       [,cache=writethrough|writeback|none|unsafe][,format=f]\n"
+    "       [,cache=writethrough|writeback|none|directsync|unsafe][,format=f]\n"
     "       [,serial=s][,addr=A][,id=name][,aio=threads|native]\n"
     "       [,readonly=on|off]\n"
     "                use 'file' as a drive image\n", QEMU_ARCH_ALL)
@@ -164,7 +164,7 @@ These options have the same definition as they have in @option{-hdachs}.
 @item snapshot=@var{snapshot}
 @var{snapshot} is "on" or "off" and allows to enable snapshot for given drive (see @option{-snapshot}).
 @item cache=@var{cache}
-@var{cache} is "none", "writeback", "unsafe", or "writethrough" and controls how the host cache is used to access block data.
+@var{cache} is "none", "writeback", "unsafe", "directsync" or "writethrough" and controls how the host cache is used to access block data.
 @item aio=@var{aio}
 @var{aio} is "threads", or "native" and selects between pthread based disk I/O and native Linux AIO.
 @item format=@var{format}
@@ -199,6 +199,10 @@ The host page cache can be avoided entirely with @option{cache=none}.  This will
 attempt to do disk IO directly to the guests memory.  QEMU may still perform
 an internal copy of the data.
 
+The host page cache can be avoided while only sending write notifications to
+the guest when the data has been reported as written by the storage subsystem
+using @option{cache=directsync}.
+
 Some block drivers perform badly with @option{cache=writethrough}, most notably,
 qcow2.  If performance is more important than correctness,
 @option{cache=writeback} should be used with qcow2.
-- 
1.7.6

  parent reply	other threads:[~2011-08-29 14:50 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2011-08-29 14:53 [Qemu-devel] [PULL 00/30] Block patches Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 01/30] coroutine: Add CoRwlock support Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 02/30] block: parse cache mode flags in a single place Kevin Wolf
2011-08-29 14:53 ` Kevin Wolf [this message]
2011-08-29 14:53 ` [Qemu-devel] [PATCH 04/30] qcow2: Fix DEBUG_* compilation Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 05/30] qemu-img: Use qemu_blockalign Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 06/30] qcow2: fix typo in documentation for qcow2_get_cluster_offset() Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 07/30] qcow: initialize coroutine mutex Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 08/30] qemu-img: print error codes when convert fails Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 09/30] block/curl: Handle failed reads gracefully Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 10/30] block: include flush requests in info blockstats Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 11/30] posix-aio-compat: fix latency issues Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 12/30] qcow/qcow2: Allocate QCowAIOCB structure using stack Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 13/30] qcow: QCowAIOCB field cleanup Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 14/30] qcow: move some blocks of code to avoid useless variable initialization Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 15/30] qcow: Remove QCowAIOCB Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 16/30] qcow: remove old #undefined code Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 17/30] qcow2: Removed unused AIOCB fields Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 18/30] qcow2: removed cur_nr_sectors field in QCowAIOCB Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 19/30] qcow2: remove l2meta from QCowAIOCB Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 20/30] qcow2: remove cluster_offset " Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 21/30] qcow2: remove common " Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 22/30] qcow2: reindent and use while before the big jump Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 23/30] qcow2: Removed QCowAIOCB entirely Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 24/30] qcow2: remove memory leak Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 25/30] sheepdog: use coroutines Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 26/30] qcow2: use always stderr for debugging Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 27/30] qcow2: remove unused qcow2_create_refcount_update function Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 28/30] block: explicit I/O accounting Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 29/30] block: latency accounting Kevin Wolf
2011-08-29 14:53 ` [Qemu-devel] [PATCH 30/30] qemu-img: Require larger zero areas for sparse handling Kevin Wolf
2011-08-29 19:15 ` [Qemu-devel] [PULL 00/30] 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=1314629618-8308-4-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.