diff options
author | 2011-12-23 10:17:51 +1100 | |
---|---|---|
committer | 2011-12-23 10:17:51 +1100 | |
commit | 2d78f8c451785f030ac1676a18691896b59c69d8 (patch) | |
tree | 4dfe69115b2ca2fb8be2a671e7c8399c3925fcb9 /drivers/md/md.h | |
parent | md: change hot_remove_disk to take an rdev rather than a number. (diff) | |
download | linux-dev-2d78f8c451785f030ac1676a18691896b59c69d8.tar.xz linux-dev-2d78f8c451785f030ac1676a18691896b59c69d8.zip |
md: create externally visible flags for supporting hot-replace.
hot-replace is a feature being added to md which will allow a
device to be replaced without removing it from the array first.
With hot-replace a spare can be activated and recovery can start while
the original device is still in place, thus allowing a transition from
an unreliable device to a reliable device without leaving the array
degraded during the transition. It can also be use when the original
device is still reliable but it not wanted for some reason.
This will eventually be supported in RAID4/5/6 and RAID10.
This patch adds a super-block flag to distinguish the replacement
device. If an old kernel sees this flag it will reject the device.
It also adds two per-device flags which are viewable and settable via
sysfs.
"want_replacement" can be set to request that a device be replaced.
"replacement" is set to show that this device is replacing another
device.
The "rd%d" links in /sys/block/mdXx/md only apply to the original
device, not the replacement. We currently don't make links for the
replacement - there doesn't seem to be a need.
Signed-off-by: NeilBrown <neilb@suse.de>
Diffstat (limited to 'drivers/md/md.h')
-rw-r--r-- | drivers/md/md.h | 80 |
1 files changed, 48 insertions, 32 deletions
diff --git a/drivers/md/md.h b/drivers/md/md.h index 670c10e6b484..44c63dfeeb2b 100644 --- a/drivers/md/md.h +++ b/drivers/md/md.h @@ -72,34 +72,7 @@ struct md_rdev { * This reduces the burden of testing multiple flags in many cases */ - unsigned long flags; -#define Faulty 1 /* device is known to have a fault */ -#define In_sync 2 /* device is in_sync with rest of array */ -#define WriteMostly 4 /* Avoid reading if at all possible */ -#define AutoDetected 7 /* added by auto-detect */ -#define Blocked 8 /* An error occurred but has not yet - * been acknowledged by the metadata - * handler, so don't allow writes - * until it is cleared */ -#define WriteErrorSeen 9 /* A write error has been seen on this - * device - */ -#define FaultRecorded 10 /* Intermediate state for clearing - * Blocked. The Fault is/will-be - * recorded in the metadata, but that - * metadata hasn't been stored safely - * on disk yet. - */ -#define BlockedBadBlocks 11 /* A writer is blocked because they - * found an unacknowledged bad-block. - * This can safely be cleared at any - * time, and the writer will re-check. - * It may be set at any time, and at - * worst the writer will timeout and - * re-check. So setting it as - * accurately as possible is good, but - * not absolutely critical. - */ + unsigned long flags; /* bit set of 'enum flag_bits' bits. */ wait_queue_head_t blocked_wait; int desc_nr; /* descriptor index in the superblock */ @@ -152,6 +125,44 @@ struct md_rdev { sector_t size; /* in sectors */ } badblocks; }; +enum flag_bits { + Faulty, /* device is known to have a fault */ + In_sync, /* device is in_sync with rest of array */ + WriteMostly, /* Avoid reading if at all possible */ + AutoDetected, /* added by auto-detect */ + Blocked, /* An error occurred but has not yet + * been acknowledged by the metadata + * handler, so don't allow writes + * until it is cleared */ + WriteErrorSeen, /* A write error has been seen on this + * device + */ + FaultRecorded, /* Intermediate state for clearing + * Blocked. The Fault is/will-be + * recorded in the metadata, but that + * metadata hasn't been stored safely + * on disk yet. + */ + BlockedBadBlocks, /* A writer is blocked because they + * found an unacknowledged bad-block. + * This can safely be cleared at any + * time, and the writer will re-check. + * It may be set at any time, and at + * worst the writer will timeout and + * re-check. So setting it as + * accurately as possible is good, but + * not absolutely critical. + */ + WantReplacement, /* This device is a candidate to be + * hot-replaced, either because it has + * reported some faults, or because + * of explicit request. + */ + Replacement, /* This device is a replacement for + * a want_replacement device with same + * raid_disk number. + */ +}; #define BB_LEN_MASK (0x00000000000001FFULL) #define BB_OFFSET_MASK (0x7FFFFFFFFFFFFE00ULL) @@ -482,15 +493,20 @@ static inline char * mdname (struct mddev * mddev) static inline int sysfs_link_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - sprintf(nm, "rd%d", rdev->raid_disk); - return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); + if (!test_bit(Replacement, &rdev->flags)) { + sprintf(nm, "rd%d", rdev->raid_disk); + return sysfs_create_link(&mddev->kobj, &rdev->kobj, nm); + } else + return 0; } static inline void sysfs_unlink_rdev(struct mddev *mddev, struct md_rdev *rdev) { char nm[20]; - sprintf(nm, "rd%d", rdev->raid_disk); - sysfs_remove_link(&mddev->kobj, nm); + if (!test_bit(Replacement, &rdev->flags)) { + sprintf(nm, "rd%d", rdev->raid_disk); + sysfs_remove_link(&mddev->kobj, nm); + } } /* |