Re: [Qemu-devel] [PATCH] Add cache=unsafe parameter to -drive

[Aurelien Jarno]

On Wed, May 26, 2010 at 05:51:49PM +0200, Alexander Graf wrote:
> Usually the guest can tell the host to flush data to disk. In some cases we
> don't want to flush though, but try to keep everything in cache.
> 
> So let's add a new cache value to -drive that allows us to set the cache
> policy to most aggressive, disabling flushes. We call this mode "unsafe",
> as guest data is not guaranteed to survive host crashes anymore.
> 
> This patch also adds a noop function for aio, so we can do nothing in AIO
> fashion.
> 
> Signed-off-by: Alexander Graf <address@hidden>

It seems we finally reached a consensus here, so I have applied the
patch.

> ---
> 
> v2 -> v3:
> 
>   - Add description of cache=volatile
>   - Squash aio noop noop patch into this one
> 
> v3 -> v4:
> 
>   - Rename cache=volatile to cache=unsafe
> ---
>  block.c         |   28 ++++++++++++++++++++++++++++
>  block.h         |    1 +
>  qemu-config.c   |    2 +-
>  qemu-options.hx |   13 ++++++++++---
>  vl.c            |    3 +++
>  5 files changed, 43 insertions(+), 4 deletions(-)
> 
> diff --git a/block.c b/block.c
> index 0b0966c..3c0249b 100644
> --- a/block.c
> +++ b/block.c
> @@ -50,6 +50,8 @@ static BlockDriverAIOCB 
> *bdrv_aio_writev_em(BlockDriverState *bs,
>          BlockDriverCompletionFunc *cb, void *opaque);
>  static BlockDriverAIOCB *bdrv_aio_flush_em(BlockDriverState *bs,
>          BlockDriverCompletionFunc *cb, void *opaque);
> +static BlockDriverAIOCB *bdrv_aio_noop_em(BlockDriverState *bs,
> +        BlockDriverCompletionFunc *cb, void *opaque);
>  static int bdrv_read_em(BlockDriverState *bs, int64_t sector_num,
>                          uint8_t *buf, int nb_sectors);
>  static int bdrv_write_em(BlockDriverState *bs, int64_t sector_num,
> @@ -1312,6 +1314,10 @@ const char *bdrv_get_device_name(BlockDriverState *bs)
>  
>  void bdrv_flush(BlockDriverState *bs)
>  {
> +    if (bs->open_flags & BDRV_O_NO_FLUSH) {
> +        return;
> +    }
> +
>      if (bs->drv && bs->drv->bdrv_flush)
>          bs->drv->bdrv_flush(bs);
>  }
> @@ -2099,6 +2105,10 @@ BlockDriverAIOCB *bdrv_aio_flush(BlockDriverState *bs,
>  {
>      BlockDriver *drv = bs->drv;
>  
> +    if (bs->open_flags & BDRV_O_NO_FLUSH) {
> +        return bdrv_aio_noop_em(bs, cb, opaque);
> +    }
> +
>      if (!drv)
>          return NULL;
>      return drv->bdrv_aio_flush(bs, cb, opaque);
> @@ -2214,6 +2224,24 @@ static BlockDriverAIOCB 
> *bdrv_aio_flush_em(BlockDriverState *bs,
>      return &acb->common;
>  }
>  
> +static BlockDriverAIOCB *bdrv_aio_noop_em(BlockDriverState *bs,
> +        BlockDriverCompletionFunc *cb, void *opaque)
> +{
> +    BlockDriverAIOCBSync *acb;
> +
> +    acb = qemu_aio_get(&bdrv_em_aio_pool, bs, cb, opaque);
> +    acb->is_write = 1; /* don't bounce in the completion hadler */
> +    acb->qiov = NULL;
> +    acb->bounce = NULL;
> +    acb->ret = 0;
> +
> +    if (!acb->bh)
> +        acb->bh = qemu_bh_new(bdrv_aio_bh_cb, acb);
> +
> +    qemu_bh_schedule(acb->bh);
> +    return &acb->common;
> +}
> +
>  /**************************************************************/
>  /* sync block device emulation */
>  
> diff --git a/block.h b/block.h
> index 278259c..24efeb6 100644
> --- a/block.h
> +++ b/block.h
> @@ -33,6 +33,7 @@ typedef struct QEMUSnapshotInfo {
>  #define BDRV_O_CACHE_WB    0x0040 /* use write-back caching */
>  #define BDRV_O_NATIVE_AIO  0x0080 /* use native AIO instead of the thread 
> pool */
>  #define BDRV_O_NO_BACKING  0x0100 /* don't open the backing file */
> +#define BDRV_O_NO_FLUSH    0x0200 /* disable flushing on this disk */
>  
>  #define BDRV_O_CACHE_MASK  (BDRV_O_NOCACHE | BDRV_O_CACHE_WB)
>  
> diff --git a/qemu-config.c b/qemu-config.c
> index aa376d4..5a4e61b 100644
> --- a/qemu-config.c
> +++ b/qemu-config.c
> @@ -54,7 +54,7 @@ QemuOptsList qemu_drive_opts = {
>          },{
>              .name = "cache",
>              .type = QEMU_OPT_STRING,
> -            .help = "host cache usage (none, writeback, writethrough)",
> +            .help = "host cache usage (none, writeback, writethrough, 
> unsafe)",
>          },{
>              .name = "aio",
>              .type = QEMU_OPT_STRING,
> diff --git a/qemu-options.hx b/qemu-options.hx
> index 03e95fd..cea9b72 100644
> --- a/qemu-options.hx
> +++ b/qemu-options.hx
> @@ -118,8 +118,9 @@ 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][,format=f][,serial=s]\n"
> -    "       [,addr=A][,id=name][,aio=threads|native][,readonly=on|off]\n"
> +    "       [,cache=writethrough|writeback|unsafe|none][,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)
>  STEXI
>  @item -drive @var{option}[,@var{option}[,@var{option}[,...]]]
> @@ -148,7 +149,7 @@ These options have the same definition as they have in 
> @option{-hdachs}.
>  @item address@hidden
>  @var{snapshot} is "on" or "off" and allows to enable snapshot for given 
> drive (see @option{-snapshot}).
>  @item address@hidden
> address@hidden is "none", "writeback", or "writethrough" and controls how the 
> host cache is used to access block data.
> address@hidden is "none", "writeback", "unsafe", or "writethrough" and 
> controls how the host cache is used to access block data.
>  @item address@hidden
>  @var{aio} is "threads", or "native" and selects between pthread based disk 
> I/O and native Linux AIO.
>  @item address@hidden
> @@ -180,6 +181,12 @@ 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.
>  
> +In case you don't care about data integrity over host failures, use
> +cache=unsafe. This option tells qemu that it never needs to write any data
> +to the disk but can instead keeps things in cache. If anything goes wrong,
> +like your host losing power, the disk storage getting disconnected 
> accidently,
> +etc. you're image will most probably be rendered unusable.
> +
>  Instead of @option{-cdrom} you can use:
>  @example
>  qemu -drive file=file,index=2,media=cdrom
> diff --git a/vl.c b/vl.c
> index 328395e..bc15dd7 100644
> --- a/vl.c
> +++ b/vl.c
> @@ -913,6 +913,9 @@ DriveInfo *drive_init(QemuOpts *opts, void *opaque,
>              bdrv_flags |= BDRV_O_NOCACHE;
>          } else if (!strcmp(buf, "writeback")) {
>              bdrv_flags |= BDRV_O_CACHE_WB;
> +        } else if (!strcmp(buf, "unsafe")) {
> +            bdrv_flags |= BDRV_O_CACHE_WB;
> +            bdrv_flags |= BDRV_O_NO_FLUSH;
>          } else if (!strcmp(buf, "writethrough")) {
>              /* this is the default */
>          } else {
> -- 
> 1.6.0.2
> 
> 
> 

-- 
Aurelien Jarno                          GPG: 1024D/F1BCDB73
address@hidden                 http://www.aurel32.net