On Wed, 20 May 2015 11:20:37 +0800 Guoqing Jiang <gqjiang@xxxxxxxx> wrote:
> A clustered disk is added by the traditional --add sequence.
> However, other nodes need to acknowledge that they can "see"
> the device. This is done by --cluster-confirm:
>
> --cluster-confirm SLOTNUM:/dev/whatever (if disk is found)
> or
> --cluster-confirm SLOTNUM:missing (if disk is not found)
>
> The node initiating the --add, has the disk state tagged with
> MD_DISK_CLUSTER_ADD and the one confirming tag the disk with
> MD_DISK_CANDIDATE.
>
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@xxxxxxxx>
> Signed-off-by: Guoqing Jiang <gqjiang@xxxxxxxx>
> ---
> Manage.c | 33 +++++++++++++++++++++++++++++----
> ReadMe.c | 1 +
> md_p.h | 7 +++++++
> md_u.h | 1 +
> mdadm.8.in | 9 +++++++++
> mdadm.c | 4 ++++
> mdadm.h | 2 ++
> util.c | 10 ++++++++++
> 8 files changed, 63 insertions(+), 4 deletions(-)
>
> diff --git a/Manage.c b/Manage.c
> index d3cfb55..4c3d451 100644
> --- a/Manage.c
> +++ b/Manage.c
> @@ -690,7 +690,8 @@ skip_re_add:
> int Manage_add(int fd, int tfd, struct mddev_dev *dv,
> struct supertype *tst, mdu_array_info_t *array,
> int force, int verbose, char *devname,
> - char *update, unsigned long rdev, unsigned long long array_size)
> + char *update, unsigned long rdev, unsigned long long array_size,
> + int raid_slot)
> {
> unsigned long long ldsize;
> struct supertype *dev_st = NULL;
> @@ -879,7 +880,10 @@ int Manage_add(int fd, int tfd, struct mddev_dev *dv,
> }
> disc.major = major(rdev);
> disc.minor = minor(rdev);
> - disc.number =j;
> + if (raid_slot < 0)
> + disc.number = j;
> + else
> + disc.number = raid_slot;
> disc.state = 0;
> if (array->not_persistent==0) {
> int dfd;
> @@ -920,6 +924,14 @@ int Manage_add(int fd, int tfd, struct mddev_dev *dv,
> }
> free(used);
> }
> +
> + if (array->state & (1 << MD_SB_CLUSTERED)) {
> + if (dv->disposition == 'c')
> + disc.state |= (1 << MD_DISK_CANDIDATE);
> + else
> + disc.state |= (1 << MD_DISK_CLUSTER_ADD);
> + }
> +
> if (dv->writemostly == 1)
> disc.state |= (1 << MD_DISK_WRITEMOSTLY);
> if (tst->ss->external) {
> @@ -1239,6 +1251,7 @@ int Manage_subdevs(char *devname, int fd,
> * variant on 'A'
> * 'F' - Another variant of 'A', where the device was faulty
> * so must be removed from the array first.
> + * 'c' - confirm the device as found (for clustered environments)
> *
> * For 'f' and 'r', the device can also be a kernel-internal
> * name such as 'sdb'.
> @@ -1254,6 +1267,7 @@ int Manage_subdevs(char *devname, int fd,
> struct mdinfo info;
> int frozen = 0;
> int busy = 0;
> + int raid_slot = -1;
>
> if (ioctl(fd, GET_ARRAY_INFO, &array)) {
> pr_err("Cannot get array info for %s\n",
> @@ -1282,6 +1296,11 @@ int Manage_subdevs(char *devname, int fd,
> int rv;
> int mj,mn;
>
> + raid_slot = -1;
> + if (dv->disposition == 'c')
> + parse_cluster_confirm_arg(dv->devname, &dv->devname,
> + &raid_slot);
> +
This function returns -1 if it couldn't successfully parse dv->devname, but
you aren't catching that error and reporting it.
NeilBrown
>
> +int parse_cluster_confirm_arg(char *input, char **devname, int *slot)
> +{
> + char *dev;
> + *slot = strtoul(input, &dev, 10);
> + if (dev == input || dev[0] != ':')
> + return -1;
> + *devname = dev+1;
> + return 0;
> +}
> +
Attachment:
pgpyWhRvoeDJq.pgp
Description: OpenPGP digital signature
