Re: reshaping raid6 in-place

[Frank Corrao <fcorrao@xxxxxxxxxxx>]

On Thu, 13 May 2010, Neil Brown wrote:

> On Wed, 12 May 2010 19:10:35 -0400 (EDT)
> Frank Corrao <fcorrao@xxxxxxxxxxx> wrote:
>
> > I have a 5-disk raid5 array which I recently reshaped to raid6 while
> > simultaneously adding a 6th disk.  mdadm (3.1.1) reported that the
> > kernel I was running at the time (2.6.30) wasn't safe to perform the
> > in-place portion of the reshaping.  The array was partitionally
> > converted to raid6, but I believe the Q blocks are all on the last
> > device I added.  mdadm seems to report the algorithm as
> > left-symmetric-6 as opposed to left-symmetric.  Today I upgraded to
> > 2.6.32 and mdadm 3.1.2 and attempted to complete the re-shaping but ran
> > into a snag:
> >
> > $ sudo ./mdadm -v --grow /dev/md2 -l 6 -n 6 -p left-symmetric
> > mdadm: /dev/md2: Something wrong - reshape aborted
> >
> > Is my syntax correct?
> >
> > Frank
>
> This is a 32bit host isn't it???  You would have thought I would have learned
> by now, but it seems not.  'blocks' in Grow.c is "unsigned long" and should
> really be "unsigned long long".

Actually no - its x86_64.  I applied the patch, corrected the fprintf() 
call on line 961 and recompiled but I still get the same error.


> Also your syntax is incomplete.  You need a backup-file for that reshape.
> mdadm would have told you that if it hadn't confused itself first.

No change when adding the --backup-file option:

$ sudo ./mdadm -v --grow /dev/md2 -l 6 -n 6 -p left-symmetric --backup-file=/root/md2.backup
mdadm: /dev/md2: Something wrong - reshape aborted


Frank




> This patch should help you.
>
> NeilBrown
>
> diff --git a/Grow.c b/Grow.c
> index 0916c5d..d1a7b63 100644
> --- a/Grow.c
> +++ b/Grow.c
> @@ -418,15 +418,15 @@ int bsb_csum(char *buf, int len)
> 	return __cpu_to_le32(csum);
> }
>
> -static int child_grow(int afd, struct mdinfo *sra, unsigned long blocks,
> +static int child_grow(int afd, struct mdinfo *sra, unsigned long long blocks,
> 		      int *fds, unsigned long long *offsets,
> 		      int disks, int chunk, int level, int layout, int data,
> 		      int dests, int *destfd, unsigned long long *destoffsets);
> -static int child_shrink(int afd, struct mdinfo *sra, unsigned long blocks,
> +static int child_shrink(int afd, struct mdinfo *sra, unsigned long long blocks,
> 			int *fds, unsigned long long *offsets,
> 			int disks, int chunk, int level, int layout, int data,
> 			int dests, int *destfd, unsigned long long *destoffsets);
> -static int child_same_size(int afd, struct mdinfo *sra, unsigned long blocks,
> +static int child_same_size(int afd, struct mdinfo *sra, unsigned long long blocks,
> 			   int *fds, unsigned long long *offsets,
> 			   unsigned long long start,
> 			   int disks, int chunk, int level, int layout, int data,
> @@ -514,7 +514,7 @@ int Grow_reshape(char *devname, int fd, int quiet, char *backup_file,
> 	int nrdisks;
> 	int err;
> 	int frozen;
> -	unsigned long a,b, blocks, stripes;
> +	unsigned long long a,b, blocks, stripes;
> 	int cache;
> 	unsigned long long array_size;
> 	int changed = 0;
> @@ -1262,7 +1262,7 @@ int Grow_reshape(char *devname, int fd, int quiet, char *backup_file,
> /* FIXME return status is never checked */
> int grow_backup(struct mdinfo *sra,
> 		unsigned long long offset, /* per device */
> -		unsigned long stripes, /* per device */
> +		unsigned long long stripes, /* per device */
> 		int *sources, unsigned long long *offsets,
> 		int disks, int chunk, int level, int layout,
> 		int dests, int *destfd, unsigned long long *destoffsets,
> @@ -1522,7 +1522,7 @@ static void validate(int afd, int bfd, unsigned long long offset)
> 	}
> }
>
> -static int child_grow(int afd, struct mdinfo *sra, unsigned long stripes,
> +static int child_grow(int afd, struct mdinfo *sra, unsigned long long stripes,
> 		      int *fds, unsigned long long *offsets,
> 		      int disks, int chunk, int level, int layout, int data,
> 		      int dests, int *destfd, unsigned long long *destoffsets)
> @@ -1550,7 +1550,7 @@ static int child_grow(int afd, struct mdinfo *sra, unsigned long stripes,
> 	return 1;
> }
>
> -static int child_shrink(int afd, struct mdinfo *sra, unsigned long stripes,
> +static int child_shrink(int afd, struct mdinfo *sra, unsigned long long stripes,
> 			int *fds, unsigned long long *offsets,
> 			int disks, int chunk, int level, int layout, int data,
> 			int dests, int *destfd, unsigned long long *destoffsets)
> @@ -1586,14 +1586,14 @@ static int child_shrink(int afd, struct mdinfo *sra, unsigned long stripes,
> 	return 1;
> }
>
> -static int child_same_size(int afd, struct mdinfo *sra, unsigned long stripes,
> +static int child_same_size(int afd, struct mdinfo *sra, unsigned long long stripes,
> 			   int *fds, unsigned long long *offsets,
> 			   unsigned long long start,
> 			   int disks, int chunk, int level, int layout, int data,
> 			   int dests, int *destfd, unsigned long long *destoffsets)
> {
> 	unsigned long long size;
> -	unsigned long tailstripes = stripes;
> +	unsigned long long tailstripes = stripes;
> 	int part;
> 	char *buf;
> 	unsigned long long speed;
> @@ -1960,7 +1960,7 @@ int Grow_continue(int mdfd, struct supertype *st, struct mdinfo *info,
> 	int backup_list[1];
> 	unsigned long long backup_offsets[1];
> 	int odisks, ndisks, ochunk, nchunk,odata,ndata;
> -	unsigned long a,b,blocks,stripes;
> +	unsigned long long a,b,blocks,stripes;
> 	int backup_fd;
> 	int *fds;
> 	unsigned long long *offsets;
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-raid" in
> the body of a message to majordomo@xxxxxxxxxxxxxxx
> More majordomo info at  http://vger.kernel.org/majordomo-info.html
--
To unsubscribe from this list: send the line "unsubscribe linux-raid" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html