/* * Copyright (C) 2010-2011 Neil Brown * Copyright (C) 2010-2011 Red Hat, Inc. All rights reserved. * * This file is released under the GPL. */ #include <linux/slab.h>#include <linux/module.h> #include "md.h"#include "raid1.h"#include "raid5.h"#include "bitmap.h" #include <linux/device-mapper.h> #define DM_MSG_PREFIX "raid" /* * The following flags are used by dm-raid.c to set up the array state. * They must be cleared before md_run is called. */#define FirstUse 10 /* rdev flag */ struct raid_dev { /* * Two DM devices, one to hold metadata and one to hold the * actual data/parity. The reason for this is to not confuse * ti->len and give more flexibility in altering size and * characteristics. * * While it is possible for this device to be associated * with a different physical device than the data_dev, it * is intended for it to be the same. * |--------- Physical Device ---------| * |- meta_dev -|------ data_dev ------| */ struct dm_dev *meta_dev; struct dm_dev *data_dev; struct md_rdev rdev;}; /* * Flags for rs->print_flags field. */#define DMPF_SYNC 0x1#define DMPF_NOSYNC 0x2#define DMPF_REBUILD 0x4#define DMPF_DAEMON_SLEEP 0x8#define DMPF_MIN_RECOVERY_RATE 0x10#define DMPF_MAX_RECOVERY_RATE 0x20#define DMPF_MAX_WRITE_BEHIND 0x40#define DMPF_STRIPE_CACHE 0x80#define DMPF_REGION_SIZE 0X100struct raid_set { struct dm_target *ti; uint32_t bitmap_loaded; uint32_t print_flags; struct mddev md; struct raid_type *raid_type; struct dm_target_callbacks callbacks; struct raid_dev dev[0];}; /* Supported raid types and properties. */static struct raid_type { const char *name; /* RAID algorithm. */ const char *descr; /* Descriptor text for logging. */ const unsigned parity_devs; /* # of parity devices. */ const unsigned minimal_devs; /* minimal # of devices in set. */ const unsigned level; /* RAID level. */ const unsigned algorithm; /* RAID algorithm. */} raid_types[] = { {"raid1", "RAID1 (mirroring)", 0, 2, 1, 0 /* NONE */}, {"raid4", "RAID4 (dedicated parity disk)", 1, 2, 5, ALGORITHM_PARITY_0}, {"raid5_la", "RAID5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC}, {"raid5_ra", "RAID5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC}, {"raid5_ls", "RAID5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC}, {"raid5_rs", "RAID5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC}, {"raid6_zr", "RAID6 (zero restart)", 2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART}, {"raid6_nr", "RAID6 (N restart)", 2, 4, 6, ALGORITHM_ROTATING_N_RESTART}, {"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE}}; static struct raid_type *get_raid_type(char *name){ int i; for (i = 0; i < ARRAY_SIZE(raid_types); i++) if (!strcmp(raid_types[i].name, name)) return &raid_types[i]; return NULL;} static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *raid_type, unsigned raid_devs){ unsigned i; struct raid_set *rs; sector_t sectors_per_dev; if (raid_devs <= raid_type->parity_devs) { ti->error = "Insufficient number of devices"; return ERR_PTR(-EINVAL); } sectors_per_dev = ti->len; if ((raid_type->level > 1) && sector_div(sectors_per_dev, (raid_devs - raid_type->parity_devs))) { ti->error = "Target length not divisible by number of data devices"; return ERR_PTR(-EINVAL); } rs = kzalloc(sizeof(*rs) + raid_devs * sizeof(rs->dev[0]), GFP_KERNEL); if (!rs) { ti->error = "Cannot allocate raid context"; return ERR_PTR(-ENOMEM); } mddev_init(&rs->md); rs->ti = ti; rs->raid_type = raid_type; rs->md.raid_disks = raid_devs; rs->md.level = raid_type->level; rs->md.new_level = rs->md.level; rs->md.dev_sectors = sectors_per_dev; rs->md.layout = raid_type->algorithm; rs->md.new_layout = rs->md.layout; rs->md.delta_disks = 0; rs->md.recovery_cp = 0; for (i = 0; i < raid_devs; i++) md_rdev_init(&rs->dev[i].rdev); /* * Remaining items to be initialized by further RAID params: * rs->md.persistent * rs->md.external * rs->md.chunk_sectors * rs->md.new_chunk_sectors */ return rs;} static void context_free(struct raid_set *rs){ int i; for (i = 0; i < rs->md.raid_disks; i++) { if (rs->dev[i].meta_dev) dm_put_device(rs->ti, rs->dev[i].meta_dev); md_rdev_clear(&rs->dev[i].rdev); if (rs->dev[i].data_dev) dm_put_device(rs->ti, rs->dev[i].data_dev); } kfree(rs);} /* * For every device we have two words * <meta_dev>: meta device name or '-' if missing * <data_dev>: data device name or '-' if missing * * The following are permitted: * - - * - <data_dev> * <meta_dev> <data_dev> * * The following is not allowed: * <meta_dev> - * * This code parses those words. If there is a failure, * the caller must use context_free to unwind the operations. */static int dev_parms(struct raid_set *rs, char **argv){ int i; int rebuild = 0; int metadata_available = 0; int ret = 0; for (i = 0; i < rs->md.raid_disks; i++, argv += 2) { rs->dev[i].rdev.raid_disk = i; rs->dev[i].meta_dev = NULL; rs->dev[i].data_dev = NULL; /* * There are no offsets, since there is a separate device * for data and metadata. */ rs->dev[i].rdev.data_offset = 0; rs->dev[i].rdev.mddev = &rs->md; if (strcmp(argv[0], "-")) { ret = dm_get_device(rs->ti, argv[0], dm_table_get_mode(rs->ti->table), &rs->dev[i].meta_dev); rs->ti->error = "RAID metadata device lookup failure"; if (ret) return ret; rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL); if (!rs->dev[i].rdev.sb_page) return -ENOMEM; } if (!strcmp(argv[1], "-")) { if (!test_bit(In_sync, &rs->dev[i].rdev.flags) && (!rs->dev[i].rdev.recovery_offset)) { rs->ti->error = "Drive designated for rebuild not specified"; return -EINVAL; } rs->ti->error = "No data device supplied with metadata device"; if (rs->dev[i].meta_dev) return -EINVAL; continue; } ret = dm_get_device(rs->ti, argv[1], dm_table_get_mode(rs->ti->table), &rs->dev[i].data_dev); if (ret) { rs->ti->error = "RAID device lookup failure"; return ret; } if (rs->dev[i].meta_dev) { metadata_available = 1; rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev; } rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev; list_add(&rs->dev[i].rdev.same_set, &rs->md.disks); if (!test_bit(In_sync, &rs->dev[i].rdev.flags)) rebuild++; } if (metadata_available) { rs->md.external = 0; rs->md.persistent = 1; rs->md.major_version = 2; } else if (rebuild && !rs->md.recovery_cp) { /* * Without metadata, we will not be able to tell if the array * is in-sync or not - we must assume it is not. Therefore, * it is impossible to rebuild a drive. * * Even if there is metadata, the on-disk information may * indicate that the array is not in-sync and it will then * fail at that time. * * User could specify 'nosync' option if desperate. */ DMERR("Unable to rebuild drive while array is not in-sync"); rs->ti->error = "RAID device lookup failure"; return -EINVAL; } return 0;} /* * validate_region_size * @rs * @region_size: region size in sectors. If 0, pick a size (4MiB default). * * Set rs->md.bitmap_info.chunksize (which really refers to 'region size'). * Ensure that (ti->len/region_size < 2^21) - required by MD bitmap. * * Returns: 0 on success, -EINVAL on failure. */static int validate_region_size(struct raid_set *rs, unsigned long region_size){ unsigned long min_region_size = rs->ti->len / (1 << 21); if (!region_size) { /* * Choose a reasonable default. All figures in sectors. */ if (min_region_size > (1 << 13)) { DMINFO("Choosing default region size of %lu sectors", region_size); region_size = min_region_size; } else { DMINFO("Choosing default region size of 4MiB"); region_size = 1 << 13; /* sectors */ } } else { /* * Validate user-supplied value. */ if (region_size > rs->ti->len) { rs->ti->error = "Supplied region size is too large"; return -EINVAL; } if (region_size < min_region_size) { DMERR("Supplied region_size (%lu sectors) below minimum (%lu)", region_size, min_region_size); rs->ti->error = "Supplied region size is too small"; return -EINVAL; } if (!is_power_of_2(region_size)) { rs->ti->error = "Region size is not a power of 2"; return -EINVAL; } if (region_size < rs->md.chunk_sectors) { rs->ti->error = "Region size is smaller than the chunk size"; return -EINVAL; } } /* * Convert sectors to bytes. */ rs->md.bitmap_info.chunksize = (region_size << 9); return 0;} /* * Possible arguments are... * <chunk_size> [optional_args] * * Argument definitions * <chunk_size> The number of sectors per disk that * will form the "stripe" * [[no]sync] Force or prevent recovery of the * entire array * [rebuild <idx>] Rebuild the drive indicated by the index * [daemon_sleep <ms>] Time between bitmap daemon work to * clear bits * [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization * [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization * [write_mostly <idx>] Indicate a write mostly drive via index * [max_write_behind <sectors>] See '-write-behind=' (man mdadm) * [stripe_cache <sectors>] Stripe cache size for higher RAIDs * [region_size <sectors>] Defines granularity of bitmap */static int parse_raid_params(struct raid_set *rs, char **argv, unsigned num_raid_params){ unsigned i, rebuild_cnt = 0; unsigned long value, region_size = 0; char *key; /* * First, parse the in-order required arguments * "chunk_size" is the only argument of this type. */ if ((strict_strtoul(argv[0], 10, &value) < 0)) { rs->ti->error = "Bad chunk size"; return -EINVAL; } else if (rs->raid_type->level == 1) { if (value) DMERR("Ignoring chunk size parameter for RAID 1"); value = 0; } else if (!is_power_of_2(value)) { rs->ti->error = "Chunk size must be a power of 2"; return -EINVAL; } else if (value < 8) { rs->ti->error = "Chunk size value is too small"; return -EINVAL; } rs->md.new_chunk_sectors = rs->md.chunk_sectors = value; argv++; num_raid_params--; /* * We set each individual device as In_sync with a completed * 'recovery_offset'. If there has been a device failure or * replacement then one of the following cases applies: * * 1) User specifies 'rebuild'. * - Device is reset when param is read. * 2) A new device is supplied. * - No matching superblock found, resets device. * 3) Device failure was transient and returns on reload. * - Failure noticed, resets device for bitmap replay. * 4) Device hadn't completed recovery after previous failure. * - Superblock is read and overrides recovery_offset. * * What is found in the superblocks of the devices is always * authoritative, unless 'rebuild' or '[no]sync' was specified. */ for (i = 0; i < rs->md.raid_disks; i++) { set_bit(In_sync, &rs->dev[i].rdev.flags); rs->dev[i].rdev.recovery_offset = MaxSector; } /* * Second, parse the unordered optional arguments */ for (i = 0; i < num_raid_params; i++) { if (!strcasecmp(argv[i], "nosync")) { rs->md.recovery_cp = MaxSector; rs->print_flags |= DMPF_NOSYNC; continue; } if (!strcasecmp(argv[i], "sync")) { rs->md.recovery_cp = 0; rs->print_flags |= DMPF_SYNC; continue; } /* The rest of the optional arguments come in key/value pairs */ if ((i + 1) >= num_raid_params) { rs->ti->error = "Wrong number of raid parameters given"; return -EINVAL; } key = argv[i++]; if (strict_strtoul(argv[i], 10, &value) < 0) { rs->ti->error = "Bad numerical argument given in raid params"; return -EINVAL; } if (!strcasecmp(key, "rebuild")) { rebuild_cnt++; if (((rs->raid_type->level != 1) && (rebuild_cnt > rs->raid_type->parity_devs)) || ((rs->raid_type->level == 1) && (rebuild_cnt > (rs->md.raid_disks - 1)))) { rs->ti->error = "Too many rebuild devices specified for given RAID type"; return -EINVAL; } if (value > rs->md.raid_disks) { rs->ti->error = "Invalid rebuild index given"; return -EINVAL; } clear_bit(In_sync, &rs->dev[value].rdev.flags); rs->dev[value].rdev.recovery_offset = 0; rs->print_flags |= DMPF_REBUILD; } else if (!strcasecmp(key, "write_mostly")) { if (rs->raid_type->level != 1) { rs->ti->error = "write_mostly option is only valid for RAID1"; return -EINVAL; } if (value >= rs->md.raid_disks) { rs->ti->error = "Invalid write_mostly drive index given"; return -EINVAL; } set_bit(WriteMostly, &rs->dev[value].rdev.flags); } else if (!strcasecmp(key, "max_write_behind")) { if (rs->raid_type->level != 1) { rs->ti->error = "max_write_behind option is only valid for RAID1"; return -EINVAL; } rs->print_flags |= DMPF_MAX_WRITE_BEHIND; /* * In device-mapper, we specify things in sectors, but * MD records this value in kB */ value /= 2; if (value > COUNTER_MAX) { rs->ti->error = "Max write-behind limit out of range"; return -EINVAL; } rs->md.bitmap_info.max_write_behind = value; } else if (!strcasecmp(key, "daemon_sleep")) { rs->print_flags |= DMPF_DAEMON_SLEEP; if (!value || (value > MAX_SCHEDULE_TIMEOUT)) { rs->ti->error = "daemon sleep period out of range"; return -EINVAL; } rs->md.bitmap_info.daemon_sleep = value; } else if (!strcasecmp(key, "stripe_cache")) { rs->print_flags |= DMPF_STRIPE_CACHE; /* * In device-mapper, we specify things in sectors, but * MD records this value in kB */ value /= 2; if (rs->raid_type->level < 5) { rs->ti->error = "Inappropriate argument: stripe_cache"; return -EINVAL; } if (raid5_set_cache_size(&rs->md, (int)value)) { rs->ti->error = "Bad stripe_cache size"; return -EINVAL; } } else if (!strcasecmp(key, "min_recovery_rate")) { rs->print_flags |= DMPF_MIN_RECOVERY_RATE; if (value > INT_MAX) { rs->ti->error = "min_recovery_rate out of range";Lines 1–500 of 1297. Load more
/* * Copyright (C) 2010-2011 Neil Brown * Copyright (C) 2010-2011 Red Hat, Inc. All rights reserved. * * This file is released under the GPL. */ #include <linux/slab.h> #include <linux/module.h> #include "md.h" #include "raid1.h" #include "raid5.h" #include "bitmap.h" #include <linux/device-mapper.h> #define DM_MSG_PREFIX "raid" /* * The following flags are used by dm-raid.c to set up the array state. * They must be cleared before md_run is called. */ #define FirstUse 10 /* rdev flag */ struct raid_dev { /* * Two DM devices, one to hold metadata and one to hold the * actual data/parity. The reason for this is to not confuse * ti->len and give more flexibility in altering size and * characteristics. * * While it is possible for this device to be associated * with a different physical device than the data_dev, it * is intended for it to be the same. * |--------- Physical Device ---------| * |- meta_dev -|------ data_dev ------| */ struct dm_dev *meta_dev; struct dm_dev *data_dev; struct md_rdev rdev; }; /* * Flags for rs->print_flags field. */ #define DMPF_SYNC 0x1 #define DMPF_NOSYNC 0x2 #define DMPF_REBUILD 0x4 #define DMPF_DAEMON_SLEEP 0x8 #define DMPF_MIN_RECOVERY_RATE 0x10 #define DMPF_MAX_RECOVERY_RATE 0x20 #define DMPF_MAX_WRITE_BEHIND 0x40 #define DMPF_STRIPE_CACHE 0x80 #define DMPF_REGION_SIZE 0X100 struct raid_set { struct dm_target *ti; uint32_t bitmap_loaded; uint32_t print_flags; struct mddev md; struct raid_type *raid_type; struct dm_target_callbacks callbacks; struct raid_dev dev[0]; }; /* Supported raid types and properties. */ static struct raid_type { const char *name; /* RAID algorithm. */ const char *descr; /* Descriptor text for logging. */ const unsigned parity_devs; /* # of parity devices. */ const unsigned minimal_devs; /* minimal # of devices in set. */ const unsigned level; /* RAID level. */ const unsigned algorithm; /* RAID algorithm. */ } raid_types[] = { {"raid1", "RAID1 (mirroring)", 0, 2, 1, 0 /* NONE */}, {"raid4", "RAID4 (dedicated parity disk)", 1, 2, 5, ALGORITHM_PARITY_0}, {"raid5_la", "RAID5 (left asymmetric)", 1, 2, 5, ALGORITHM_LEFT_ASYMMETRIC}, {"raid5_ra", "RAID5 (right asymmetric)", 1, 2, 5, ALGORITHM_RIGHT_ASYMMETRIC}, {"raid5_ls", "RAID5 (left symmetric)", 1, 2, 5, ALGORITHM_LEFT_SYMMETRIC}, {"raid5_rs", "RAID5 (right symmetric)", 1, 2, 5, ALGORITHM_RIGHT_SYMMETRIC}, {"raid6_zr", "RAID6 (zero restart)", 2, 4, 6, ALGORITHM_ROTATING_ZERO_RESTART}, {"raid6_nr", "RAID6 (N restart)", 2, 4, 6, ALGORITHM_ROTATING_N_RESTART}, {"raid6_nc", "RAID6 (N continue)", 2, 4, 6, ALGORITHM_ROTATING_N_CONTINUE} }; static struct raid_type *get_raid_type(char *name) { int i; for (i = 0; i < ARRAY_SIZE(raid_types); i++) if (!strcmp(raid_types[i].name, name)) return &raid_types[i]; return NULL; } static struct raid_set *context_alloc(struct dm_target *ti, struct raid_type *raid_type, unsigned raid_devs) { unsigned i; struct raid_set *rs; sector_t sectors_per_dev; if (raid_devs <= raid_type->parity_devs) { ti->error = "Insufficient number of devices"; return ERR_PTR(-EINVAL); } sectors_per_dev = ti->len; if ((raid_type->level > 1) && sector_div(sectors_per_dev, (raid_devs - raid_type->parity_devs))) { ti->error = "Target length not divisible by number of data devices"; return ERR_PTR(-EINVAL); } rs = kzalloc(sizeof(*rs) + raid_devs * sizeof(rs->dev[0]), GFP_KERNEL); if (!rs) { ti->error = "Cannot allocate raid context"; return ERR_PTR(-ENOMEM); } mddev_init(&rs->md); rs->ti = ti; rs->raid_type = raid_type; rs->md.raid_disks = raid_devs; rs->md.level = raid_type->level; rs->md.new_level = rs->md.level; rs->md.dev_sectors = sectors_per_dev; rs->md.layout = raid_type->algorithm; rs->md.new_layout = rs->md.layout; rs->md.delta_disks = 0; rs->md.recovery_cp = 0; for (i = 0; i < raid_devs; i++) md_rdev_init(&rs->dev[i].rdev); /* * Remaining items to be initialized by further RAID params: * rs->md.persistent * rs->md.external * rs->md.chunk_sectors * rs->md.new_chunk_sectors */ return rs; } static void context_free(struct raid_set *rs) { int i; for (i = 0; i < rs->md.raid_disks; i++) { if (rs->dev[i].meta_dev) dm_put_device(rs->ti, rs->dev[i].meta_dev); md_rdev_clear(&rs->dev[i].rdev); if (rs->dev[i].data_dev) dm_put_device(rs->ti, rs->dev[i].data_dev); } kfree(rs); } /* * For every device we have two words * <meta_dev>: meta device name or '-' if missing * <data_dev>: data device name or '-' if missing * * The following are permitted: * - - * - <data_dev> * <meta_dev> <data_dev> * * The following is not allowed: * <meta_dev> - * * This code parses those words. If there is a failure, * the caller must use context_free to unwind the operations. */ static int dev_parms(struct raid_set *rs, char **argv) { int i; int rebuild = 0; int metadata_available = 0; int ret = 0; for (i = 0; i < rs->md.raid_disks; i++, argv += 2) { rs->dev[i].rdev.raid_disk = i; rs->dev[i].meta_dev = NULL; rs->dev[i].data_dev = NULL; /* * There are no offsets, since there is a separate device * for data and metadata. */ rs->dev[i].rdev.data_offset = 0; rs->dev[i].rdev.mddev = &rs->md; if (strcmp(argv[0], "-")) { ret = dm_get_device(rs->ti, argv[0], dm_table_get_mode(rs->ti->table), &rs->dev[i].meta_dev); rs->ti->error = "RAID metadata device lookup failure"; if (ret) return ret; rs->dev[i].rdev.sb_page = alloc_page(GFP_KERNEL); if (!rs->dev[i].rdev.sb_page) return -ENOMEM; } if (!strcmp(argv[1], "-")) { if (!test_bit(In_sync, &rs->dev[i].rdev.flags) && (!rs->dev[i].rdev.recovery_offset)) { rs->ti->error = "Drive designated for rebuild not specified"; return -EINVAL; } rs->ti->error = "No data device supplied with metadata device"; if (rs->dev[i].meta_dev) return -EINVAL; continue; } ret = dm_get_device(rs->ti, argv[1], dm_table_get_mode(rs->ti->table), &rs->dev[i].data_dev); if (ret) { rs->ti->error = "RAID device lookup failure"; return ret; } if (rs->dev[i].meta_dev) { metadata_available = 1; rs->dev[i].rdev.meta_bdev = rs->dev[i].meta_dev->bdev; } rs->dev[i].rdev.bdev = rs->dev[i].data_dev->bdev; list_add(&rs->dev[i].rdev.same_set, &rs->md.disks); if (!test_bit(In_sync, &rs->dev[i].rdev.flags)) rebuild++; } if (metadata_available) { rs->md.external = 0; rs->md.persistent = 1; rs->md.major_version = 2; } else if (rebuild && !rs->md.recovery_cp) { /* * Without metadata, we will not be able to tell if the array * is in-sync or not - we must assume it is not. Therefore, * it is impossible to rebuild a drive. * * Even if there is metadata, the on-disk information may * indicate that the array is not in-sync and it will then * fail at that time. * * User could specify 'nosync' option if desperate. */ DMERR("Unable to rebuild drive while array is not in-sync"); rs->ti->error = "RAID device lookup failure"; return -EINVAL; } return 0; } /* * validate_region_size * @rs * @region_size: region size in sectors. If 0, pick a size (4MiB default). * * Set rs->md.bitmap_info.chunksize (which really refers to 'region size'). * Ensure that (ti->len/region_size < 2^21) - required by MD bitmap. * * Returns: 0 on success, -EINVAL on failure. */ static int validate_region_size(struct raid_set *rs, unsigned long region_size) { unsigned long min_region_size = rs->ti->len / (1 << 21); if (!region_size) { /* * Choose a reasonable default. All figures in sectors. */ if (min_region_size > (1 << 13)) { DMINFO("Choosing default region size of %lu sectors", region_size); region_size = min_region_size; } else { DMINFO("Choosing default region size of 4MiB"); region_size = 1 << 13; /* sectors */ } } else { /* * Validate user-supplied value. */ if (region_size > rs->ti->len) { rs->ti->error = "Supplied region size is too large"; return -EINVAL; } if (region_size < min_region_size) { DMERR("Supplied region_size (%lu sectors) below minimum (%lu)", region_size, min_region_size); rs->ti->error = "Supplied region size is too small"; return -EINVAL; } if (!is_power_of_2(region_size)) { rs->ti->error = "Region size is not a power of 2"; return -EINVAL; } if (region_size < rs->md.chunk_sectors) { rs->ti->error = "Region size is smaller than the chunk size"; return -EINVAL; } } /* * Convert sectors to bytes. */ rs->md.bitmap_info.chunksize = (region_size << 9); return 0; } /* * Possible arguments are... * <chunk_size> [optional_args] * * Argument definitions * <chunk_size> The number of sectors per disk that * will form the "stripe" * [[no]sync] Force or prevent recovery of the * entire array * [rebuild <idx>] Rebuild the drive indicated by the index * [daemon_sleep <ms>] Time between bitmap daemon work to * clear bits * [min_recovery_rate <kB/sec/disk>] Throttle RAID initialization * [max_recovery_rate <kB/sec/disk>] Throttle RAID initialization * [write_mostly <idx>] Indicate a write mostly drive via index * [max_write_behind <sectors>] See '-write-behind=' (man mdadm) * [stripe_cache <sectors>] Stripe cache size for higher RAIDs * [region_size <sectors>] Defines granularity of bitmap */ static int parse_raid_params(struct raid_set *rs, char **argv, unsigned num_raid_params) { unsigned i, rebuild_cnt = 0; unsigned long value, region_size = 0; char *key; /* * First, parse the in-order required arguments * "chunk_size" is the only argument of this type. */ if ((strict_strtoul(argv[0], 10, &value) < 0)) { rs->ti->error = "Bad chunk size"; return -EINVAL; } else if (rs->raid_type->level == 1) { if (value) DMERR("Ignoring chunk size parameter for RAID 1"); value = 0; } else if (!is_power_of_2(value)) { rs->ti->error = "Chunk size must be a power of 2"; return -EINVAL; } else if (value < 8) { rs->ti->error = "Chunk size value is too small"; return -EINVAL; } rs->md.new_chunk_sectors = rs->md.chunk_sectors = value; argv++; num_raid_params--; /* * We set each individual device as In_sync with a completed * 'recovery_offset'. If there has been a device failure or * replacement then one of the following cases applies: * * 1) User specifies 'rebuild'. * - Device is reset when param is read. * 2) A new device is supplied. * - No matching superblock found, resets device. * 3) Device failure was transient and returns on reload. * - Failure noticed, resets device for bitmap replay. * 4) Device hadn't completed recovery after previous failure. * - Superblock is read and overrides recovery_offset. * * What is found in the superblocks of the devices is always * authoritative, unless 'rebuild' or '[no]sync' was specified. */ for (i = 0; i < rs->md.raid_disks; i++) { set_bit(In_sync, &rs->dev[i].rdev.flags); rs->dev[i].rdev.recovery_offset = MaxSector; } /* * Second, parse the unordered optional arguments */ for (i = 0; i < num_raid_params; i++) { if (!strcasecmp(argv[i], "nosync")) { rs->md.recovery_cp = MaxSector; rs->print_flags |= DMPF_NOSYNC; continue; } if (!strcasecmp(argv[i], "sync")) { rs->md.recovery_cp = 0; rs->print_flags |= DMPF_SYNC; continue; } /* The rest of the optional arguments come in key/value pairs */ if ((i + 1) >= num_raid_params) { rs->ti->error = "Wrong number of raid parameters given"; return -EINVAL; } key = argv[i++]; if (strict_strtoul(argv[i], 10, &value) < 0) { rs->ti->error = "Bad numerical argument given in raid params"; return -EINVAL; } if (!strcasecmp(key, "rebuild")) { rebuild_cnt++; if (((rs->raid_type->level != 1) && (rebuild_cnt > rs->raid_type->parity_devs)) || ((rs->raid_type->level == 1) && (rebuild_cnt > (rs->md.raid_disks - 1)))) { rs->ti->error = "Too many rebuild devices specified for given RAID type"; return -EINVAL; } if (value > rs->md.raid_disks) { rs->ti->error = "Invalid rebuild index given"; return -EINVAL; } clear_bit(In_sync, &rs->dev[value].rdev.flags); rs->dev[value].rdev.recovery_offset = 0; rs->print_flags |= DMPF_REBUILD; } else if (!strcasecmp(key, "write_mostly")) { if (rs->raid_type->level != 1) { rs->ti->error = "write_mostly option is only valid for RAID1"; return -EINVAL; } if (value >= rs->md.raid_disks) { rs->ti->error = "Invalid write_mostly drive index given"; return -EINVAL; } set_bit(WriteMostly, &rs->dev[value].rdev.flags); } else if (!strcasecmp(key, "max_write_behind")) { if (rs->raid_type->level != 1) { rs->ti->error = "max_write_behind option is only valid for RAID1"; return -EINVAL; } rs->print_flags |= DMPF_MAX_WRITE_BEHIND; /* * In device-mapper, we specify things in sectors, but * MD records this value in kB */ value /= 2; if (value > COUNTER_MAX) { rs->ti->error = "Max write-behind limit out of range"; return -EINVAL; } rs->md.bitmap_info.max_write_behind = value; } else if (!strcasecmp(key, "daemon_sleep")) { rs->print_flags |= DMPF_DAEMON_SLEEP; if (!value || (value > MAX_SCHEDULE_TIMEOUT)) { rs->ti->error = "daemon sleep period out of range"; return -EINVAL; } rs->md.bitmap_info.daemon_sleep = value; } else if (!strcasecmp(key, "stripe_cache")) { rs->print_flags |= DMPF_STRIPE_CACHE; /* * In device-mapper, we specify things in sectors, but * MD records this value in kB */ value /= 2; if (rs->raid_type->level < 5) { rs->ti->error = "Inappropriate argument: stripe_cache"; return -EINVAL; } if (raid5_set_cache_size(&rs->md, (int)value)) { rs->ti->error = "Bad stripe_cache size"; return -EINVAL; } } else if (!strcasecmp(key, "min_recovery_rate")) { rs->print_flags |= DMPF_MIN_RECOVERY_RATE; if (value > INT_MAX) { rs->ti->error = "min_recovery_rate out of range";