Patchwork [v2,2/2] sheepdog: support user-defined redundancy option

login
register
mail settings
Submitter namei.unix@gmail.com
Date Oct. 29, 2013, 8:25 a.m.
Message ID <1383035152-14924-3-git-send-email-namei.unix@gmail.com>
Download mbox | patch
Permalink /patch/286758/
State New
Headers show

Comments

namei.unix@gmail.com - Oct. 29, 2013, 8:25 a.m.
Sheepdog support two kinds of redundancy, full replication and erasure coding.

# create a fully replicated vdi with x copies
 -o redundancy=x (1 <= x <= SD_MAX_COPIES)

# create a erasure coded vdi with x data strips and y parity strips
 -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)

E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme

$ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test

Cc: Kevin Wolf <kwolf@redhat.com>
Cc: Stefan Hajnoczi <stefanha@redhat.com>
Signed-off-by: Liu Yuan <namei.unix@gmail.com>
---
 block/sheepdog.c          |   78 ++++++++++++++++++++++++++++++++++++++++++++-
 include/block/block_int.h |    1 +
 2 files changed, 78 insertions(+), 1 deletion(-)
Benoît Canet - Oct. 29, 2013, 8:40 p.m.
Le Tuesday 29 Oct 2013 à 16:25:52 (+0800), Liu Yuan a écrit :
> Sheepdog support two kinds of redundancy, full replication and erasure coding.
> 
> # create a fully replicated vdi with x copies
>  -o redundancy=x (1 <= x <= SD_MAX_COPIES)
> 
> # create a erasure coded vdi with x data strips and y parity strips
>  -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)
> 
> E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
> 
> $ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
> 
> Cc: Kevin Wolf <kwolf@redhat.com>
> Cc: Stefan Hajnoczi <stefanha@redhat.com>
> Signed-off-by: Liu Yuan <namei.unix@gmail.com>
> ---
>  block/sheepdog.c          |   78 ++++++++++++++++++++++++++++++++++++++++++++-
>  include/block/block_int.h |    1 +
>  2 files changed, 78 insertions(+), 1 deletion(-)
> 
> diff --git a/block/sheepdog.c b/block/sheepdog.c
> index e66d2f8..bd7cfd6 100644
> --- a/block/sheepdog.c
> +++ b/block/sheepdog.c
> @@ -91,6 +91,14 @@
>  #define SD_NR_VDIS   (1U << 24)
>  #define SD_DATA_OBJ_SIZE (UINT64_C(1) << 22)
>  #define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS)
> +/*
> + * For erasure coding, we use at most SD_EC_MAX_STRIP for data strips and
> + * (SD_EC_MAX_STRIP - 1) for parity strips
> + *
> + * SD_MAX_COPIES is sum of number of dats trips and parity strips.
> + */
> +#define SD_EC_MAX_STRIP 16
> +#define SD_MAX_COPIES (SD_EC_MAX_STRIP * 2 - 1)
>  
>  #define SD_INODE_SIZE (sizeof(SheepdogInode))
>  #define CURRENT_VDI_ID 0
> @@ -1446,6 +1454,65 @@ out:
>      return ret;
>  }
>  
> +static int64_t is_numeric(const char *s)
> +{
> +    char *end;
> +    return strtosz_suffix(s, &end, STRTOSZ_DEFSUFFIX_B);
> +}
> +
> +/*
> + * Sheepdog support two kinds of redundancy, full replication and erasure
> + * coding.
> + *
> + * # create a fully replicated vdi with x copies
> + * -o redundancy=x (1 <= x <= SD_MAX_COPIES)
> + *
> + * # create a erasure coded vdi with x data strips and y parity strips
> + * -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)
> + */
> +static int parse_redundancy(BDRVSheepdogState *s, const char *opt)
> +{
> +    struct SheepdogInode *inode = &s->inode;
> +    const char *n1, *n2;
> +    uint8_t copy, parity;
> +    char p[10];
> +
> +    strncpy(p, opt, sizeof(p));
> +    n1 = strtok(p, ":");
> +    n2 = strtok(NULL, ":");
> +
> +    if ((n1 && !is_numeric(n1)) || (n2 && !is_numeric(n2))) {
> +        return -EINVAL;
> +    }
> +
> +    copy = strtol(n1, NULL, 10);
> +    if (copy > SD_MAX_COPIES) {
> +        return -EINVAL;
> +    }
> +    if (!n2) {
> +        inode->copy_policy = 0;
> +        inode->nr_copies = copy;
> +    }
> +
> +    if (copy != 2 && copy != 4 && copy != 8 && copy != 16) {
> +        return -EINVAL;
> +    }
> +
> +    parity = strtol(n2, NULL, 10);
> +    if (parity >= SD_EC_MAX_STRIP || parity == 0) {
> +        return -EINVAL;
> +    }
> +
> +    /*
> +     * 4 bits for parity and 4 bits for data.
> +     * We have to compress upper data bits because it can't represent 16
> +     */
> +    inode->copy_policy = ((copy / 2) << 4) + parity;
> +    inode->nr_copies = copy + parity;
> +
> +    return 0;
> +}
> +
>  static int sd_create(const char *filename, QEMUOptionParameter *options,
>                       Error **errp)
>  {
> @@ -1486,6 +1553,11 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
>                  ret = -EINVAL;
>                  goto out;
>              }
> +        } else if (!strcmp(options->name, BLOCK_OPT_REDUNDANCY)) {
> +            ret = parse_redundancy(s, options->value.s);
> +            if (ret < 0) {
> +                goto out;
> +            }
>          }
>          options++;
>      }
> @@ -1528,7 +1600,6 @@ static int sd_create(const char *filename, QEMUOptionParameter *options,
>          bdrv_unref(bs);
>      }
>  
> -    /* TODO: allow users to specify copy number */
>      ret = do_sd_create(s, &vid, 0);
>      if (!prealloc || ret) {
>          goto out;
> @@ -2332,6 +2403,11 @@ static QEMUOptionParameter sd_create_options[] = {
>          .type = OPT_STRING,
>          .help = "Preallocation mode (allowed values: off, full)"
>      },
> +    {
> +        .name = BLOCK_OPT_REDUNDANCY,
> +        .type = OPT_STRING,
> +        .help = "Redundancy of the image"
> +    },
>      { NULL }
>  };
>  
> diff --git a/include/block/block_int.h b/include/block/block_int.h
> index a48731d..b90862f 100644
> --- a/include/block/block_int.h
> +++ b/include/block/block_int.h
> @@ -53,6 +53,7 @@
>  #define BLOCK_OPT_COMPAT_LEVEL      "compat"
>  #define BLOCK_OPT_LAZY_REFCOUNTS    "lazy_refcounts"
>  #define BLOCK_OPT_ADAPTER_TYPE      "adapter_type"
> +#define BLOCK_OPT_REDUNDANCY        "redundancy"
>  
>  typedef struct BdrvTrackedRequest {
>      BlockDriverState *bs;
> -- 
> 1.7.9.5
> 
> 

Hi,

Perhaps it would be better to implement theses options with the new block driver
options mechanism that Kevin implemented.

From a user perspective it look like this.
  -drive if=virtio,file.driver=quorum,\
    file.children.0.file.filename=1.qcow2,\
    file.children.1.file.filename=2.qcow2,\
    file.children.2.file.filename=3.qcow2,\
    file.vote_threshold=3

I don't know if it would work with protocols but that would uniformize the
options passing style accross multiple block drivers.

I have an under review patch on the list using this mechanism, see:
"[PATCH V9 11/11] quorum: Add quorum_open() and quorum_close()."

Best regards

Benoît
MORITA Kazutaka - Oct. 30, 2013, 7:41 p.m.
At Tue, 29 Oct 2013 16:25:52 +0800,
Liu Yuan wrote:
> 
> Sheepdog support two kinds of redundancy, full replication and erasure coding.
> 
> # create a fully replicated vdi with x copies
>  -o redundancy=x (1 <= x <= SD_MAX_COPIES)
> 
> # create a erasure coded vdi with x data strips and y parity strips
>  -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)
> 
> E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
> 
> $ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
> 
> Cc: Kevin Wolf <kwolf@redhat.com>
> Cc: Stefan Hajnoczi <stefanha@redhat.com>
> Signed-off-by: Liu Yuan <namei.unix@gmail.com>
> ---
>  block/sheepdog.c          |   78 ++++++++++++++++++++++++++++++++++++++++++++-
>  include/block/block_int.h |    1 +
>  2 files changed, 78 insertions(+), 1 deletion(-)
> 
> diff --git a/block/sheepdog.c b/block/sheepdog.c
> index e66d2f8..bd7cfd6 100644
> --- a/block/sheepdog.c
> +++ b/block/sheepdog.c
> @@ -91,6 +91,14 @@
>  #define SD_NR_VDIS   (1U << 24)
>  #define SD_DATA_OBJ_SIZE (UINT64_C(1) << 22)
>  #define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS)
> +/*
> + * For erasure coding, we use at most SD_EC_MAX_STRIP for data strips and
> + * (SD_EC_MAX_STRIP - 1) for parity strips
> + *
> + * SD_MAX_COPIES is sum of number of dats trips and parity strips.
> + */
> +#define SD_EC_MAX_STRIP 16
> +#define SD_MAX_COPIES (SD_EC_MAX_STRIP * 2 - 1)
>  
>  #define SD_INODE_SIZE (sizeof(SheepdogInode))
>  #define CURRENT_VDI_ID 0
> @@ -1446,6 +1454,65 @@ out:
>      return ret;
>  }
>  
> +static int64_t is_numeric(const char *s)
> +{
> +    char *end;
> +    return strtosz_suffix(s, &end, STRTOSZ_DEFSUFFIX_B);
> +}

I think the type of the return value should be bool.

Thanks,

Kazutaka
namei.unix@gmail.com - Oct. 31, 2013, 3:07 a.m.
On Thu, Oct 31, 2013 at 04:41:05AM +0900, MORITA Kazutaka wrote:
> At Tue, 29 Oct 2013 16:25:52 +0800,
> Liu Yuan wrote:
> > 
> > Sheepdog support two kinds of redundancy, full replication and erasure coding.
> > 
> > # create a fully replicated vdi with x copies
> >  -o redundancy=x (1 <= x <= SD_MAX_COPIES)
> > 
> > # create a erasure coded vdi with x data strips and y parity strips
> >  -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)
> > 
> > E.g, to convert a vdi into sheepdog vdi 'test' with 8:3 erasure coding scheme
> > 
> > $ qemu-img convert -o redundancy=8:3 linux-0.2.img sheepdog:test
> > 
> > Cc: Kevin Wolf <kwolf@redhat.com>
> > Cc: Stefan Hajnoczi <stefanha@redhat.com>
> > Signed-off-by: Liu Yuan <namei.unix@gmail.com>
> > ---
> >  block/sheepdog.c          |   78 ++++++++++++++++++++++++++++++++++++++++++++-
> >  include/block/block_int.h |    1 +
> >  2 files changed, 78 insertions(+), 1 deletion(-)
> > 
> > diff --git a/block/sheepdog.c b/block/sheepdog.c
> > index e66d2f8..bd7cfd6 100644
> > --- a/block/sheepdog.c
> > +++ b/block/sheepdog.c
> > @@ -91,6 +91,14 @@
> >  #define SD_NR_VDIS   (1U << 24)
> >  #define SD_DATA_OBJ_SIZE (UINT64_C(1) << 22)
> >  #define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS)
> > +/*
> > + * For erasure coding, we use at most SD_EC_MAX_STRIP for data strips and
> > + * (SD_EC_MAX_STRIP - 1) for parity strips
> > + *
> > + * SD_MAX_COPIES is sum of number of dats trips and parity strips.
> > + */
> > +#define SD_EC_MAX_STRIP 16
> > +#define SD_MAX_COPIES (SD_EC_MAX_STRIP * 2 - 1)
> >  
> >  #define SD_INODE_SIZE (sizeof(SheepdogInode))
> >  #define CURRENT_VDI_ID 0
> > @@ -1446,6 +1454,65 @@ out:
> >      return ret;
> >  }
> >  
> > +static int64_t is_numeric(const char *s)
> > +{
> > +    char *end;
> > +    return strtosz_suffix(s, &end, STRTOSZ_DEFSUFFIX_B);
> > +}
> 
> I think the type of the return value should be bool.
> 

Actually I copied from cvtnum() it returns negative to indicate errors. Either
way I found a bug in this version. I'll try another approach to test if it is
numbers in next version.

Thanks
Yuan

Patch

diff --git a/block/sheepdog.c b/block/sheepdog.c
index e66d2f8..bd7cfd6 100644
--- a/block/sheepdog.c
+++ b/block/sheepdog.c
@@ -91,6 +91,14 @@ 
 #define SD_NR_VDIS   (1U << 24)
 #define SD_DATA_OBJ_SIZE (UINT64_C(1) << 22)
 #define SD_MAX_VDI_SIZE (SD_DATA_OBJ_SIZE * MAX_DATA_OBJS)
+/*
+ * For erasure coding, we use at most SD_EC_MAX_STRIP for data strips and
+ * (SD_EC_MAX_STRIP - 1) for parity strips
+ *
+ * SD_MAX_COPIES is sum of number of dats trips and parity strips.
+ */
+#define SD_EC_MAX_STRIP 16
+#define SD_MAX_COPIES (SD_EC_MAX_STRIP * 2 - 1)
 
 #define SD_INODE_SIZE (sizeof(SheepdogInode))
 #define CURRENT_VDI_ID 0
@@ -1446,6 +1454,65 @@  out:
     return ret;
 }
 
+static int64_t is_numeric(const char *s)
+{
+    char *end;
+    return strtosz_suffix(s, &end, STRTOSZ_DEFSUFFIX_B);
+}
+
+/*
+ * Sheepdog support two kinds of redundancy, full replication and erasure
+ * coding.
+ *
+ * # create a fully replicated vdi with x copies
+ * -o redundancy=x (1 <= x <= SD_MAX_COPIES)
+ *
+ * # create a erasure coded vdi with x data strips and y parity strips
+ * -o redundancy=x:y (x must be one of {2,4,8,16} and 1 <= y < SD_EC_MAX_STRIP)
+ */
+static int parse_redundancy(BDRVSheepdogState *s, const char *opt)
+{
+    struct SheepdogInode *inode = &s->inode;
+    const char *n1, *n2;
+    uint8_t copy, parity;
+    char p[10];
+
+    strncpy(p, opt, sizeof(p));
+    n1 = strtok(p, ":");
+    n2 = strtok(NULL, ":");
+
+    if ((n1 && !is_numeric(n1)) || (n2 && !is_numeric(n2))) {
+        return -EINVAL;
+    }
+
+    copy = strtol(n1, NULL, 10);
+    if (copy > SD_MAX_COPIES) {
+        return -EINVAL;
+    }
+    if (!n2) {
+        inode->copy_policy = 0;
+        inode->nr_copies = copy;
+    }
+
+    if (copy != 2 && copy != 4 && copy != 8 && copy != 16) {
+        return -EINVAL;
+    }
+
+    parity = strtol(n2, NULL, 10);
+    if (parity >= SD_EC_MAX_STRIP || parity == 0) {
+        return -EINVAL;
+    }
+
+    /*
+     * 4 bits for parity and 4 bits for data.
+     * We have to compress upper data bits because it can't represent 16
+     */
+    inode->copy_policy = ((copy / 2) << 4) + parity;
+    inode->nr_copies = copy + parity;
+
+    return 0;
+}
+
 static int sd_create(const char *filename, QEMUOptionParameter *options,
                      Error **errp)
 {
@@ -1486,6 +1553,11 @@  static int sd_create(const char *filename, QEMUOptionParameter *options,
                 ret = -EINVAL;
                 goto out;
             }
+        } else if (!strcmp(options->name, BLOCK_OPT_REDUNDANCY)) {
+            ret = parse_redundancy(s, options->value.s);
+            if (ret < 0) {
+                goto out;
+            }
         }
         options++;
     }
@@ -1528,7 +1600,6 @@  static int sd_create(const char *filename, QEMUOptionParameter *options,
         bdrv_unref(bs);
     }
 
-    /* TODO: allow users to specify copy number */
     ret = do_sd_create(s, &vid, 0);
     if (!prealloc || ret) {
         goto out;
@@ -2332,6 +2403,11 @@  static QEMUOptionParameter sd_create_options[] = {
         .type = OPT_STRING,
         .help = "Preallocation mode (allowed values: off, full)"
     },
+    {
+        .name = BLOCK_OPT_REDUNDANCY,
+        .type = OPT_STRING,
+        .help = "Redundancy of the image"
+    },
     { NULL }
 };
 
diff --git a/include/block/block_int.h b/include/block/block_int.h
index a48731d..b90862f 100644
--- a/include/block/block_int.h
+++ b/include/block/block_int.h
@@ -53,6 +53,7 @@ 
 #define BLOCK_OPT_COMPAT_LEVEL      "compat"
 #define BLOCK_OPT_LAZY_REFCOUNTS    "lazy_refcounts"
 #define BLOCK_OPT_ADAPTER_TYPE      "adapter_type"
+#define BLOCK_OPT_REDUNDANCY        "redundancy"
 
 typedef struct BdrvTrackedRequest {
     BlockDriverState *bs;