linux/drivers/md/md.h
Robert Becker 1e50915fe0 raid: improve MD/raid10 handling of correctable read errors.
We've noticed severe lasting performance degradation of our raid
arrays when we have drives that yield large amounts of media errors.
The raid10 module will queue each failed read for retry, and also
will attempt call fix_read_error() to perform the read recovery.
Read recovery is performed while the array is frozen, so repeated
recovery attempts can degrade the performance of the array for
extended periods of time.

With this patch I propose adding a per md device max number of
corrected read attempts.  Each rdev will maintain a count of
read correction attempts in the rdev->read_errors field (not
used currently for raid10). When we enter fix_read_error()
we'll check to see when the last read error occurred, and
divide the read error count by 2 for every hour since the
last read error. If at that point our read error count
exceeds the read error threshold, we'll fail the raid device.

In addition in this patch I add sysfs nodes (get/set) for
the per md max_read_errors attribute, the rdev->read_errors
attribute, and added some printk's to indicate when
fix_read_error fails to repair an rdev.

For testing I used debugfs->fail_make_request to inject
IO errors to the rdev while doing IO to the raid array.

Signed-off-by: Robert Becker <Rob.Becker@riverbed.com>
Signed-off-by: NeilBrown <neilb@suse.de>
2009-12-14 12:51:41 +11:00

476 lines
16 KiB
C

/*
md_k.h : kernel internal structure of the Linux MD driver
Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
This program is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 2, or (at your option)
any later version.
You should have received a copy of the GNU General Public License
(for example /usr/src/linux/COPYING); if not, write to the Free
Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/
#ifndef _MD_MD_H
#define _MD_MD_H
#include <linux/blkdev.h>
#include <linux/kobject.h>
#include <linux/list.h>
#include <linux/mm.h>
#include <linux/mutex.h>
#include <linux/timer.h>
#include <linux/wait.h>
#include <linux/workqueue.h>
#define MaxSector (~(sector_t)0)
typedef struct mddev_s mddev_t;
typedef struct mdk_rdev_s mdk_rdev_t;
/*
* MD's 'extended' device
*/
struct mdk_rdev_s
{
struct list_head same_set; /* RAID devices within the same set */
sector_t sectors; /* Device size (in 512bytes sectors) */
mddev_t *mddev; /* RAID array if running */
int last_events; /* IO event timestamp */
struct block_device *bdev; /* block device handle */
struct page *sb_page;
int sb_loaded;
__u64 sb_events;
sector_t data_offset; /* start of data in array */
sector_t sb_start; /* offset of the super block (in 512byte sectors) */
int sb_size; /* bytes in the superblock */
int preferred_minor; /* autorun support */
struct kobject kobj;
/* A device can be in one of three states based on two flags:
* Not working: faulty==1 in_sync==0
* Fully working: faulty==0 in_sync==1
* Working, but not
* in sync with array
* faulty==0 in_sync==0
*
* It can never have faulty==1, in_sync==1
* 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 BarriersNotsupp 5 /* BIO_RW_BARRIER is not supported */
#define AllReserved 6 /* If whole device is reserved for
* one array */
#define AutoDetected 7 /* added by auto-detect */
#define Blocked 8 /* An error occured on an externally
* managed array, don't allow writes
* until it is cleared */
#define StateChanged 9 /* Faulty or Blocked has changed during
* interrupt, so it needs to be
* notified by the thread */
wait_queue_head_t blocked_wait;
int desc_nr; /* descriptor index in the superblock */
int raid_disk; /* role of device in array */
int saved_raid_disk; /* role that device used to have in the
* array and could again if we did a partial
* resync from the bitmap
*/
sector_t recovery_offset;/* If this device has been partially
* recovered, this is where we were
* up to.
*/
atomic_t nr_pending; /* number of pending requests.
* only maintained for arrays that
* support hot removal
*/
atomic_t read_errors; /* number of consecutive read errors that
* we have tried to ignore.
*/
struct timespec last_read_error; /* monotonic time since our
* last read error
*/
atomic_t corrected_errors; /* number of corrected read errors,
* for reporting to userspace and storing
* in superblock.
*/
struct work_struct del_work; /* used for delayed sysfs removal */
struct sysfs_dirent *sysfs_state; /* handle for 'state'
* sysfs entry */
};
struct mddev_s
{
void *private;
struct mdk_personality *pers;
dev_t unit;
int md_minor;
struct list_head disks;
unsigned long flags;
#define MD_CHANGE_DEVS 0 /* Some device status has changed */
#define MD_CHANGE_CLEAN 1 /* transition to or from 'clean' */
#define MD_CHANGE_PENDING 2 /* superblock update in progress */
int suspended;
atomic_t active_io;
int ro;
struct gendisk *gendisk;
struct kobject kobj;
int hold_active;
#define UNTIL_IOCTL 1
#define UNTIL_STOP 2
/* Superblock information */
int major_version,
minor_version,
patch_version;
int persistent;
int external; /* metadata is
* managed externally */
char metadata_type[17]; /* externally set*/
int chunk_sectors;
time_t ctime, utime;
int level, layout;
char clevel[16];
int raid_disks;
int max_disks;
sector_t dev_sectors; /* used size of
* component devices */
sector_t array_sectors; /* exported array size */
int external_size; /* size managed
* externally */
__u64 events;
char uuid[16];
/* If the array is being reshaped, we need to record the
* new shape and an indication of where we are up to.
* This is written to the superblock.
* If reshape_position is MaxSector, then no reshape is happening (yet).
*/
sector_t reshape_position;
int delta_disks, new_level, new_layout;
int new_chunk_sectors;
struct mdk_thread_s *thread; /* management thread */
struct mdk_thread_s *sync_thread; /* doing resync or reconstruct */
sector_t curr_resync; /* last block scheduled */
/* As resync requests can complete out of order, we cannot easily track
* how much resync has been completed. So we occasionally pause until
* everything completes, then set curr_resync_completed to curr_resync.
* As such it may be well behind the real resync mark, but it is a value
* we are certain of.
*/
sector_t curr_resync_completed;
unsigned long resync_mark; /* a recent timestamp */
sector_t resync_mark_cnt;/* blocks written at resync_mark */
sector_t curr_mark_cnt; /* blocks scheduled now */
sector_t resync_max_sectors; /* may be set by personality */
sector_t resync_mismatches; /* count of sectors where
* parity/replica mismatch found
*/
/* allow user-space to request suspension of IO to regions of the array */
sector_t suspend_lo;
sector_t suspend_hi;
/* if zero, use the system-wide default */
int sync_speed_min;
int sync_speed_max;
/* resync even though the same disks are shared among md-devices */
int parallel_resync;
int ok_start_degraded;
/* recovery/resync flags
* NEEDED: we might need to start a resync/recover
* RUNNING: a thread is running, or about to be started
* SYNC: actually doing a resync, not a recovery
* RECOVER: doing recovery, or need to try it.
* INTR: resync needs to be aborted for some reason
* DONE: thread is done and is waiting to be reaped
* REQUEST: user-space has requested a sync (used with SYNC)
* CHECK: user-space request for check-only, no repair
* RESHAPE: A reshape is happening
*
* If neither SYNC or RESHAPE are set, then it is a recovery.
*/
#define MD_RECOVERY_RUNNING 0
#define MD_RECOVERY_SYNC 1
#define MD_RECOVERY_RECOVER 2
#define MD_RECOVERY_INTR 3
#define MD_RECOVERY_DONE 4
#define MD_RECOVERY_NEEDED 5
#define MD_RECOVERY_REQUESTED 6
#define MD_RECOVERY_CHECK 7
#define MD_RECOVERY_RESHAPE 8
#define MD_RECOVERY_FROZEN 9
unsigned long recovery;
int recovery_disabled; /* if we detect that recovery
* will always fail, set this
* so we don't loop trying */
int in_sync; /* know to not need resync */
/* 'open_mutex' avoids races between 'md_open' and 'do_md_stop', so
* that we are never stopping an array while it is open.
* 'reconfig_mutex' protects all other reconfiguration.
* These locks are separate due to conflicting interactions
* with bdev->bd_mutex.
* Lock ordering is:
* reconfig_mutex -> bd_mutex : e.g. do_md_run -> revalidate_disk
* bd_mutex -> open_mutex: e.g. __blkdev_get -> md_open
*/
struct mutex open_mutex;
struct mutex reconfig_mutex;
atomic_t active; /* general refcount */
atomic_t openers; /* number of active opens */
int changed; /* true if we might need to reread partition info */
int degraded; /* whether md should consider
* adding a spare
*/
int barriers_work; /* initialised to true, cleared as soon
* as a barrier request to slave
* fails. Only supported
*/
struct bio *biolist; /* bios that need to be retried
* because BIO_RW_BARRIER is not supported
*/
atomic_t recovery_active; /* blocks scheduled, but not written */
wait_queue_head_t recovery_wait;
sector_t recovery_cp;
sector_t resync_min; /* user requested sync
* starts here */
sector_t resync_max; /* resync should pause
* when it gets here */
struct sysfs_dirent *sysfs_state; /* handle for 'array_state'
* file in sysfs.
*/
struct sysfs_dirent *sysfs_action; /* handle for 'sync_action' */
struct work_struct del_work; /* used for delayed sysfs removal */
spinlock_t write_lock;
wait_queue_head_t sb_wait; /* for waiting on superblock updates */
atomic_t pending_writes; /* number of active superblock writes */
unsigned int safemode; /* if set, update "clean" superblock
* when no writes pending.
*/
unsigned int safemode_delay;
struct timer_list safemode_timer;
atomic_t writes_pending;
struct request_queue *queue; /* for plugging ... */
atomic_t write_behind; /* outstanding async IO */
unsigned int max_write_behind; /* 0 = sync */
struct bitmap *bitmap; /* the bitmap for the device */
struct {
struct file *file; /* the bitmap file */
loff_t offset; /* offset from superblock of
* start of bitmap. May be
* negative, but not '0'
* For external metadata, offset
* from start of device.
*/
loff_t default_offset; /* this is the offset to use when
* hot-adding a bitmap. It should
* eventually be settable by sysfs.
*/
struct mutex mutex;
unsigned long chunksize;
unsigned long daemon_sleep; /* how many seconds between updates? */
unsigned long max_write_behind; /* write-behind mode */
int external;
} bitmap_info;
atomic_t max_corr_read_errors; /* max read retries */
struct list_head all_mddevs;
/* Generic barrier handling.
* If there is a pending barrier request, all other
* writes are blocked while the devices are flushed.
* The last to finish a flush schedules a worker to
* submit the barrier request (without the barrier flag),
* then submit more flush requests.
*/
struct bio *barrier;
atomic_t flush_pending;
struct work_struct barrier_work;
};
static inline void rdev_dec_pending(mdk_rdev_t *rdev, mddev_t *mddev)
{
int faulty = test_bit(Faulty, &rdev->flags);
if (atomic_dec_and_test(&rdev->nr_pending) && faulty)
set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
}
static inline void md_sync_acct(struct block_device *bdev, unsigned long nr_sectors)
{
atomic_add(nr_sectors, &bdev->bd_contains->bd_disk->sync_io);
}
struct mdk_personality
{
char *name;
int level;
struct list_head list;
struct module *owner;
int (*make_request)(struct request_queue *q, struct bio *bio);
int (*run)(mddev_t *mddev);
int (*stop)(mddev_t *mddev);
void (*status)(struct seq_file *seq, mddev_t *mddev);
/* error_handler must set ->faulty and clear ->in_sync
* if appropriate, and should abort recovery if needed
*/
void (*error_handler)(mddev_t *mddev, mdk_rdev_t *rdev);
int (*hot_add_disk) (mddev_t *mddev, mdk_rdev_t *rdev);
int (*hot_remove_disk) (mddev_t *mddev, int number);
int (*spare_active) (mddev_t *mddev);
sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
int (*resize) (mddev_t *mddev, sector_t sectors);
sector_t (*size) (mddev_t *mddev, sector_t sectors, int raid_disks);
int (*check_reshape) (mddev_t *mddev);
int (*start_reshape) (mddev_t *mddev);
void (*finish_reshape) (mddev_t *mddev);
/* quiesce moves between quiescence states
* 0 - fully active
* 1 - no new requests allowed
* others - reserved
*/
void (*quiesce) (mddev_t *mddev, int state);
/* takeover is used to transition an array from one
* personality to another. The new personality must be able
* to handle the data in the current layout.
* e.g. 2drive raid1 -> 2drive raid5
* ndrive raid5 -> degraded n+1drive raid6 with special layout
* If the takeover succeeds, a new 'private' structure is returned.
* This needs to be installed and then ->run used to activate the
* array.
*/
void *(*takeover) (mddev_t *mddev);
};
struct md_sysfs_entry {
struct attribute attr;
ssize_t (*show)(mddev_t *, char *);
ssize_t (*store)(mddev_t *, const char *, size_t);
};
extern struct attribute_group md_bitmap_group;
static inline char * mdname (mddev_t * mddev)
{
return mddev->gendisk ? mddev->gendisk->disk_name : "mdX";
}
/*
* iterates through some rdev ringlist. It's safe to remove the
* current 'rdev'. Dont touch 'tmp' though.
*/
#define rdev_for_each_list(rdev, tmp, head) \
list_for_each_entry_safe(rdev, tmp, head, same_set)
/*
* iterates through the 'same array disks' ringlist
*/
#define rdev_for_each(rdev, tmp, mddev) \
list_for_each_entry_safe(rdev, tmp, &((mddev)->disks), same_set)
#define rdev_for_each_rcu(rdev, mddev) \
list_for_each_entry_rcu(rdev, &((mddev)->disks), same_set)
typedef struct mdk_thread_s {
void (*run) (mddev_t *mddev);
mddev_t *mddev;
wait_queue_head_t wqueue;
unsigned long flags;
struct task_struct *tsk;
unsigned long timeout;
} mdk_thread_t;
#define THREAD_WAKEUP 0
#define __wait_event_lock_irq(wq, condition, lock, cmd) \
do { \
wait_queue_t __wait; \
init_waitqueue_entry(&__wait, current); \
\
add_wait_queue(&wq, &__wait); \
for (;;) { \
set_current_state(TASK_UNINTERRUPTIBLE); \
if (condition) \
break; \
spin_unlock_irq(&lock); \
cmd; \
schedule(); \
spin_lock_irq(&lock); \
} \
current->state = TASK_RUNNING; \
remove_wait_queue(&wq, &__wait); \
} while (0)
#define wait_event_lock_irq(wq, condition, lock, cmd) \
do { \
if (condition) \
break; \
__wait_event_lock_irq(wq, condition, lock, cmd); \
} while (0)
static inline void safe_put_page(struct page *p)
{
if (p) put_page(p);
}
extern int register_md_personality(struct mdk_personality *p);
extern int unregister_md_personality(struct mdk_personality *p);
extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev),
mddev_t *mddev, const char *name);
extern void md_unregister_thread(mdk_thread_t *thread);
extern void md_wakeup_thread(mdk_thread_t *thread);
extern void md_check_recovery(mddev_t *mddev);
extern void md_write_start(mddev_t *mddev, struct bio *bi);
extern void md_write_end(mddev_t *mddev);
extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
extern int mddev_congested(mddev_t *mddev, int bits);
extern void md_barrier_request(mddev_t *mddev, struct bio *bio);
extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
sector_t sector, int size, struct page *page);
extern void md_super_wait(mddev_t *mddev);
extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
struct page *page, int rw);
extern void md_do_sync(mddev_t *mddev);
extern void md_new_event(mddev_t *mddev);
extern int md_allow_write(mddev_t *mddev);
extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors);
extern int md_check_no_bitmap(mddev_t *mddev);
extern int md_integrity_register(mddev_t *mddev);
extern void md_integrity_add_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
extern int strict_strtoul_scaled(const char *cp, unsigned long *res, int scale);
extern void restore_bitmap_write_access(struct file *file);
#endif /* _MD_MD_H */