| Message ID | 20190823101036.796932-4-naohiro.aota@wdc.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | btrfs zoned block device support | expand |
On 23/08/2019 12:10, Naohiro Aota wrote: > HMZONED mode cannot be used together with the RAID5/6 profile for now. > Introduce the function btrfs_check_hmzoned_mode() to check this. This > function will also check if HMZONED flag is enabled on the file system and > if the file system consists of zoned devices with equal zone size. > > Additionally, as updates to the space cache are in-place, the space cache > cannot be located over sequential zones and there is no guarantees that the > device will have enough conventional zones to store this cache. Resolve > this problem by disabling completely the space cache. This does not completely disabling ~^ > introduces any problems with sequential block groups: all the free space is introduce ~^ > located after the allocation pointer and no free space before the pointer. is located? ~^ > There is no need to have such cache. > > For the same reason, NODATACOW is also disabled. > > Also INODE_MAP_CACHE is also disabled to avoid preallocation in the > INODE_MAP_CACHE inode. > > In summary, HMZONED will disable: > > | Disabled features | Reason | > |-------------------+-----------------------------------------------------| > | RAID5/6 | 1) Non-full stripe write cause overwriting of | > | | parity block | > | | 2) Rebuilding on high capacity volume (usually with | > | | SMR) can lead to higher failure rate | > |-------------------+-----------------------------------------------------| > | space_cache (v1) | In-place updating | > | NODATACOW | In-place updating | > |-------------------+-----------------------------------------------------| > | tree-log | Partial write out of metadata creates write holes | > |-------------------+-----------------------------------------------------| > | fallocate | Reserved extent will be a write hole | > | INODE_MAP_CACHE | Need pre-allocation. (and will be deprecated?) | > |-------------------+-----------------------------------------------------| > | MIXED_BG | Allocated metadata region will be write holes for | > | | data writes | > | async checksum | Not to mix up bios by multiple workers | > > Signed-off-by: Damien Le Moal <damien.lemoal@wdc.com> > Signed-off-by: Naohiro Aota <naohiro.aota@wdc.com> > --- > fs/btrfs/ctree.h | 3 ++ > fs/btrfs/dev-replace.c | 8 +++++ > fs/btrfs/disk-io.c | 8 +++++ > fs/btrfs/hmzoned.c | 67 ++++++++++++++++++++++++++++++++++++++++++ > fs/btrfs/hmzoned.h | 18 ++++++++++++ > fs/btrfs/super.c | 1 + > fs/btrfs/volumes.c | 5 ++++ > 7 files changed, 110 insertions(+) > > diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h > index 94660063a162..221259737703 100644 > --- a/fs/btrfs/ctree.h > +++ b/fs/btrfs/ctree.h > @@ -712,6 +712,9 @@ struct btrfs_fs_info { > struct btrfs_root *uuid_root; > struct btrfs_root *free_space_root; > > + /* Zone size when in HMZONED mode */ > + u64 zone_size; > + > /* the log root tree is a directory of all the other log roots */ > struct btrfs_root *log_root_tree; > > diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c > index 6b2e9aa83ffa..2cc3ac4d101d 100644 > --- a/fs/btrfs/dev-replace.c > +++ b/fs/btrfs/dev-replace.c > @@ -20,6 +20,7 @@ > #include "rcu-string.h" > #include "dev-replace.h" > #include "sysfs.h" > +#include "hmzoned.h" > > static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, > int scrub_ret); > @@ -201,6 +202,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, > return PTR_ERR(bdev); > } > > + if (!btrfs_check_device_zone_type(fs_info, bdev)) { > + btrfs_err(fs_info, > + "zone type of target device mismatch with the filesystem!"); > + ret = -EINVAL; > + goto error; > + } > + > sync_blockdev(bdev); > > devices = &fs_info->fs_devices->devices; > diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c > index 97beb351a10c..3f5ea92f546c 100644 > --- a/fs/btrfs/disk-io.c > +++ b/fs/btrfs/disk-io.c > @@ -40,6 +40,7 @@ > #include "compression.h" > #include "tree-checker.h" > #include "ref-verify.h" > +#include "hmzoned.h" > > #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ > BTRFS_HEADER_FLAG_RELOC |\ > @@ -3121,6 +3122,13 @@ int open_ctree(struct super_block *sb, > > btrfs_free_extra_devids(fs_devices, 1); > > + ret = btrfs_check_hmzoned_mode(fs_info); > + if (ret) { > + btrfs_err(fs_info, "failed to init hmzoned mode: %d", > + ret); > + goto fail_block_groups; > + } > + > ret = btrfs_sysfs_add_fsid(fs_devices, NULL); > if (ret) { > btrfs_err(fs_info, "failed to init sysfs fsid interface: %d", > diff --git a/fs/btrfs/hmzoned.c b/fs/btrfs/hmzoned.c > index 23bf58d3d7bb..ca58eee08a70 100644 > --- a/fs/btrfs/hmzoned.c > +++ b/fs/btrfs/hmzoned.c > @@ -157,3 +157,70 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, > > return 0; > } > + > +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info) > +{ > + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; > + struct btrfs_device *device; > + u64 hmzoned_devices = 0; > + u64 nr_devices = 0; > + u64 zone_size = 0; > + int incompat_hmzoned = btrfs_fs_incompat(fs_info, HMZONED); > + int ret = 0; > + > + /* Count zoned devices */ > + list_for_each_entry(device, &fs_devices->devices, dev_list) { > + if (!device->bdev) > + continue; > + if (bdev_zoned_model(device->bdev) == BLK_ZONED_HM || > + (bdev_zoned_model(device->bdev) == BLK_ZONED_HA && > + incompat_hmzoned)) { > + hmzoned_devices++; > + if (!zone_size) { > + zone_size = device->zone_info->zone_size; > + } else if (device->zone_info->zone_size != zone_size) { > + btrfs_err(fs_info, > + "Zoned block devices must have equal zone sizes"); > + ret = -EINVAL; > + goto out; > + } > + } > + nr_devices++; > + } > + > + if (!hmzoned_devices && incompat_hmzoned) { > + /* No zoned block device found on HMZONED FS */ > + btrfs_err(fs_info, "HMZONED enabled file system should have zoned devices"); > + ret = -EINVAL; > + goto out; > + } > + > + if (!hmzoned_devices && !incompat_hmzoned) > + goto out; > + > + fs_info->zone_size = zone_size; > + > + if (hmzoned_devices != nr_devices) { > + btrfs_err(fs_info, > + "zoned devices cannot be mixed with regular devices"); > + ret = -EINVAL; > + goto out; > + } > + > + /* > + * stripe_size is always aligned to BTRFS_STRIPE_LEN in > + * __btrfs_alloc_chunk(). Since we want stripe_len == zone_size, > + * check the alignment here. > + */ > + if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) { > + btrfs_err(fs_info, > + "zone size is not aligned to BTRFS_STRIPE_LEN"); > + ret = -EINVAL; > + goto out; > + } > + > + btrfs_info(fs_info, "HMZONED mode enabled, zone size %llu B", > + fs_info->zone_size); > +out: > + return ret; > +} > diff --git a/fs/btrfs/hmzoned.h b/fs/btrfs/hmzoned.h > index ffc70842135e..29cfdcabff2f 100644 > --- a/fs/btrfs/hmzoned.h > +++ b/fs/btrfs/hmzoned.h > @@ -9,6 +9,8 @@ > #ifndef BTRFS_HMZONED_H > #define BTRFS_HMZONED_H > > +#include <linux/blkdev.h> > + > struct btrfs_zoned_device_info { > /* > * Number of zones, zone size and types of zones if bdev is a > @@ -25,6 +27,7 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, > struct blk_zone *zone, gfp_t gfp_mask); > int btrfs_get_dev_zone_info(struct btrfs_device *device); > void btrfs_destroy_dev_zone_info(struct btrfs_device *device); > +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info); While we're at it, shouldn't all the functions in hmzoned.[ch] have a !CONFIG_BLK_DEV_ZONED compat wrapper and hmzoned.o is dependent on CONFIG_BLK_DEV_ZONED?
On Fri, Aug 23, 2019 at 02:07:05PM +0200, Johannes Thumshirn wrote: >On 23/08/2019 12:10, Naohiro Aota wrote: >> HMZONED mode cannot be used together with the RAID5/6 profile for now. >> Introduce the function btrfs_check_hmzoned_mode() to check this. This >> function will also check if HMZONED flag is enabled on the file system and >> if the file system consists of zoned devices with equal zone size. >> >> Additionally, as updates to the space cache are in-place, the space cache >> cannot be located over sequential zones and there is no guarantees that the >> device will have enough conventional zones to store this cache. Resolve >> this problem by disabling completely the space cache. This does not >completely disabling ~^ > >> introduces any problems with sequential block groups: all the free space is >introduce ~^ > >> located after the allocation pointer and no free space before the pointer. > is located? ~^ >> There is no need to have such cache. Thanks. >> @@ -25,6 +27,7 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, >> struct blk_zone *zone, gfp_t gfp_mask); >> int btrfs_get_dev_zone_info(struct btrfs_device *device); >> void btrfs_destroy_dev_zone_info(struct btrfs_device *device); >> +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info); > > >While we're at it, shouldn't all the functions in hmzoned.[ch] have a >!CONFIG_BLK_DEV_ZONED compat wrapper and hmzoned.o is dependent on >CONFIG_BLK_DEV_ZONED? Exactly. It was broken on !CONFIG_BLK_DEV_ZONED as the bot pointed out... I'll push them behind CONFIG_BLK_DEV_ZONED in the next version. >-- >Johannes Thumshirn SUSE Labs Filesystems >jthumshirn@suse.de +49 911 74053 689 >SUSE LINUX GmbH, Maxfeldstr. 5, 90409 Nürnberg >GF: Felix Imendörffer, Mary Higgins, Sri Rasiah >HRB 21284 (AG Nürnberg) >Key fingerprint = EC38 9CAB C2C4 F25D 8600 D0D0 0393 969D 2D76 0850
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 94660063a162..221259737703 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -712,6 +712,9 @@ struct btrfs_fs_info { struct btrfs_root *uuid_root; struct btrfs_root *free_space_root; + /* Zone size when in HMZONED mode */ + u64 zone_size; + /* the log root tree is a directory of all the other log roots */ struct btrfs_root *log_root_tree; diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c index 6b2e9aa83ffa..2cc3ac4d101d 100644 --- a/fs/btrfs/dev-replace.c +++ b/fs/btrfs/dev-replace.c @@ -20,6 +20,7 @@ #include "rcu-string.h" #include "dev-replace.h" #include "sysfs.h" +#include "hmzoned.h" static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info, int scrub_ret); @@ -201,6 +202,13 @@ static int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info, return PTR_ERR(bdev); } + if (!btrfs_check_device_zone_type(fs_info, bdev)) { + btrfs_err(fs_info, + "zone type of target device mismatch with the filesystem!"); + ret = -EINVAL; + goto error; + } + sync_blockdev(bdev); devices = &fs_info->fs_devices->devices; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 97beb351a10c..3f5ea92f546c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -40,6 +40,7 @@ #include "compression.h" #include "tree-checker.h" #include "ref-verify.h" +#include "hmzoned.h" #define BTRFS_SUPER_FLAG_SUPP (BTRFS_HEADER_FLAG_WRITTEN |\ BTRFS_HEADER_FLAG_RELOC |\ @@ -3121,6 +3122,13 @@ int open_ctree(struct super_block *sb, btrfs_free_extra_devids(fs_devices, 1); + ret = btrfs_check_hmzoned_mode(fs_info); + if (ret) { + btrfs_err(fs_info, "failed to init hmzoned mode: %d", + ret); + goto fail_block_groups; + } + ret = btrfs_sysfs_add_fsid(fs_devices, NULL); if (ret) { btrfs_err(fs_info, "failed to init sysfs fsid interface: %d", diff --git a/fs/btrfs/hmzoned.c b/fs/btrfs/hmzoned.c index 23bf58d3d7bb..ca58eee08a70 100644 --- a/fs/btrfs/hmzoned.c +++ b/fs/btrfs/hmzoned.c @@ -157,3 +157,70 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, return 0; } + +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info) +{ + struct btrfs_fs_devices *fs_devices = fs_info->fs_devices; + struct btrfs_device *device; + u64 hmzoned_devices = 0; + u64 nr_devices = 0; + u64 zone_size = 0; + int incompat_hmzoned = btrfs_fs_incompat(fs_info, HMZONED); + int ret = 0; + + /* Count zoned devices */ + list_for_each_entry(device, &fs_devices->devices, dev_list) { + if (!device->bdev) + continue; + if (bdev_zoned_model(device->bdev) == BLK_ZONED_HM || + (bdev_zoned_model(device->bdev) == BLK_ZONED_HA && + incompat_hmzoned)) { + hmzoned_devices++; + if (!zone_size) { + zone_size = device->zone_info->zone_size; + } else if (device->zone_info->zone_size != zone_size) { + btrfs_err(fs_info, + "Zoned block devices must have equal zone sizes"); + ret = -EINVAL; + goto out; + } + } + nr_devices++; + } + + if (!hmzoned_devices && incompat_hmzoned) { + /* No zoned block device found on HMZONED FS */ + btrfs_err(fs_info, "HMZONED enabled file system should have zoned devices"); + ret = -EINVAL; + goto out; + } + + if (!hmzoned_devices && !incompat_hmzoned) + goto out; + + fs_info->zone_size = zone_size; + + if (hmzoned_devices != nr_devices) { + btrfs_err(fs_info, + "zoned devices cannot be mixed with regular devices"); + ret = -EINVAL; + goto out; + } + + /* + * stripe_size is always aligned to BTRFS_STRIPE_LEN in + * __btrfs_alloc_chunk(). Since we want stripe_len == zone_size, + * check the alignment here. + */ + if (!IS_ALIGNED(zone_size, BTRFS_STRIPE_LEN)) { + btrfs_err(fs_info, + "zone size is not aligned to BTRFS_STRIPE_LEN"); + ret = -EINVAL; + goto out; + } + + btrfs_info(fs_info, "HMZONED mode enabled, zone size %llu B", + fs_info->zone_size); +out: + return ret; +} diff --git a/fs/btrfs/hmzoned.h b/fs/btrfs/hmzoned.h index ffc70842135e..29cfdcabff2f 100644 --- a/fs/btrfs/hmzoned.h +++ b/fs/btrfs/hmzoned.h @@ -9,6 +9,8 @@ #ifndef BTRFS_HMZONED_H #define BTRFS_HMZONED_H +#include <linux/blkdev.h> + struct btrfs_zoned_device_info { /* * Number of zones, zone size and types of zones if bdev is a @@ -25,6 +27,7 @@ int btrfs_get_dev_zone(struct btrfs_device *device, u64 pos, struct blk_zone *zone, gfp_t gfp_mask); int btrfs_get_dev_zone_info(struct btrfs_device *device); void btrfs_destroy_dev_zone_info(struct btrfs_device *device); +int btrfs_check_hmzoned_mode(struct btrfs_fs_info *fs_info); static inline bool btrfs_dev_is_sequential(struct btrfs_device *device, u64 pos) { @@ -76,4 +79,19 @@ static inline void btrfs_dev_clear_zone_empty(struct btrfs_device *device, btrfs_dev_set_empty_zone_bit(device, pos, false); } +static inline bool btrfs_check_device_zone_type(struct btrfs_fs_info *fs_info, + struct block_device *bdev) +{ + u64 zone_size; + + if (btrfs_fs_incompat(fs_info, HMZONED)) { + zone_size = (u64)bdev_zone_sectors(bdev) << SECTOR_SHIFT; + /* Do not allow non-zoned device */ + return bdev_is_zoned(bdev) && fs_info->zone_size == zone_size; + } + + /* Do not allow Host Manged zoned device */ + return bdev_zoned_model(bdev) != BLK_ZONED_HM; +} + #endif diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 78de9d5d80c6..d7879a5a2536 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -43,6 +43,7 @@ #include "free-space-cache.h" #include "backref.h" #include "space-info.h" +#include "hmzoned.h" #include "tests/btrfs-tests.h" #include "qgroup.h" diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index a8c550562057..ffa4de09666d 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2572,6 +2572,11 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path if (IS_ERR(bdev)) return PTR_ERR(bdev); + if (!btrfs_check_device_zone_type(fs_info, bdev)) { + ret = -EINVAL; + goto error; + } + if (fs_devices->seeding) { seeding_dev = 1; down_write(&sb->s_umount);