From 4246a0b63bd8f56a1469b12eafeb875b1041a451 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 20 Jul 2015 15:29:37 +0200 Subject: block: add a bi_error field to struct bio Currently we have two different ways to signal an I/O error on a BIO: (1) by clearing the BIO_UPTODATE flag (2) by returning a Linux errno value to the bi_end_io callback The first one has the drawback of only communicating a single possible error (-EIO), and the second one has the drawback of not beeing persistent when bios are queued up, and are not passed along from child to parent bio in the ever more popular chaining scenario. Having both mechanisms available has the additional drawback of utterly confusing driver authors and introducing bugs where various I/O submitters only deal with one of them, and the others have to add boilerplate code to deal with both kinds of error returns. So add a new bi_error field to store an errno value directly in struct bio and remove the existing mechanisms to clean all this up. Signed-off-by: Christoph Hellwig Reviewed-by: Hannes Reinecke Reviewed-by: NeilBrown Signed-off-by: Jens Axboe --- fs/btrfs/disk-io.c | 35 +++++++++++++++++++---------------- 1 file changed, 19 insertions(+), 16 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index a9aadb2ad525..a8c0de888a9d 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -703,7 +703,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror) return -EIO; /* we fixed nothing */ } -static void end_workqueue_bio(struct bio *bio, int err) +static void end_workqueue_bio(struct bio *bio) { struct btrfs_end_io_wq *end_io_wq = bio->bi_private; struct btrfs_fs_info *fs_info; @@ -711,7 +711,7 @@ static void end_workqueue_bio(struct bio *bio, int err) btrfs_work_func_t func; fs_info = end_io_wq->info; - end_io_wq->error = err; + end_io_wq->error = bio->bi_error; if (bio->bi_rw & REQ_WRITE) { if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) { @@ -808,7 +808,8 @@ static void run_one_async_done(struct btrfs_work *work) /* If an error occured we just want to clean up the bio and move on */ if (async->error) { - bio_endio(async->bio, async->error); + async->bio->bi_error = async->error; + bio_endio(async->bio); return; } @@ -908,8 +909,10 @@ static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio, * submission context. Just jump into btrfs_map_bio */ ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1); - if (ret) - bio_endio(bio, ret); + if (ret) { + bio->bi_error = ret; + bio_endio(bio); + } return ret; } @@ -960,10 +963,13 @@ static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio, __btree_submit_bio_done); } - if (ret) { + if (ret) + goto out_w_error; + return 0; + out_w_error: - bio_endio(bio, ret); - } + bio->bi_error = ret; + bio_endio(bio); return ret; } @@ -1735,16 +1741,15 @@ static void end_workqueue_fn(struct btrfs_work *work) { struct bio *bio; struct btrfs_end_io_wq *end_io_wq; - int error; end_io_wq = container_of(work, struct btrfs_end_io_wq, work); bio = end_io_wq->bio; - error = end_io_wq->error; + bio->bi_error = end_io_wq->error; bio->bi_private = end_io_wq->private; bio->bi_end_io = end_io_wq->end_io; kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq); - bio_endio(bio, error); + bio_endio(bio); } static int cleaner_kthread(void *arg) @@ -3323,10 +3328,8 @@ static int write_dev_supers(struct btrfs_device *device, * endio for the write_dev_flush, this will wake anyone waiting * for the barrier when it is done */ -static void btrfs_end_empty_barrier(struct bio *bio, int err) +static void btrfs_end_empty_barrier(struct bio *bio) { - if (err) - clear_bit(BIO_UPTODATE, &bio->bi_flags); if (bio->bi_private) complete(bio->bi_private); bio_put(bio); @@ -3354,8 +3357,8 @@ static int write_dev_flush(struct btrfs_device *device, int wait) wait_for_completion(&device->flush_wait); - if (!bio_flagged(bio, BIO_UPTODATE)) { - ret = -EIO; + if (bio->bi_error) { + ret = bio->bi_error; btrfs_dev_stat_inc_and_print(device, BTRFS_DEV_STAT_FLUSH_ERRS); } -- cgit v1.2.3 From e44163e177960ee60e32a73bffdd53c3a5827406 Mon Sep 17 00:00:00 2001 From: Jeff Mahoney Date: Mon, 15 Jun 2015 09:41:18 -0400 Subject: btrfs: explictly delete unused block groups in close_ctree and ro-remount The cleaner thread may already be sleeping by the time we enter close_ctree. If that's the case, we'll skip removing any unused block groups queued for removal, even during a normal umount. They'll be cleaned up automatically at next mount, but users expect a umount to be a clean synchronization point, especially when used on thin-provisioned storage with -odiscard. We also explicitly remove unused block groups in the ro-remount path for the same reason. Signed-off-by: Jeff Mahoney Reviewed-by: Filipe Manana Tested-by: Filipe Manana Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 9 +++++++++ fs/btrfs/super.c | 11 +++++++++++ 2 files changed, 20 insertions(+) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 84cbbb2d562e..053109ba26b7 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3767,6 +3767,15 @@ void close_ctree(struct btrfs_root *root) cancel_work_sync(&fs_info->async_reclaim_work); if (!(fs_info->sb->s_flags & MS_RDONLY)) { + /* + * If the cleaner thread is stopped and there are + * block groups queued for removal, the deletion will be + * skipped when we quit the cleaner thread. + */ + mutex_lock(&root->fs_info->cleaner_mutex); + btrfs_delete_unused_bgs(root->fs_info); + mutex_unlock(&root->fs_info->cleaner_mutex); + ret = btrfs_commit_super(root); if (ret) btrfs_err(fs_info, "commit super ret %d", ret); diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cd7ef34d2dce..a1077e0ffaa8 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1650,6 +1650,17 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data) sb->s_flags |= MS_RDONLY; + /* + * Setting MS_RDONLY will put the cleaner thread to + * sleep at the next loop if it's already active. + * If it's already asleep, we'll leave unused block + * groups on disk until we're mounted read-write again + * unless we clean them up here. + */ + mutex_lock(&root->fs_info->cleaner_mutex); + btrfs_delete_unused_bgs(fs_info); + mutex_unlock(&root->fs_info->cleaner_mutex); + btrfs_dev_replace_suspend_for_unmount(fs_info); btrfs_scrub_cancel(fs_info); btrfs_pause_balance(fs_info); -- cgit v1.2.3 From 78fa177029802f7f10953d357067171f39a79b81 Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Mon, 20 Jul 2015 17:54:50 +0800 Subject: btrfs: Show detail information when mount failed on missing devices When mount failed because missing device, we can see following dmesg: [ 1060.267743] BTRFS: too many missing devices, writeable mount is not allowed [ 1060.273158] BTRFS: open_ctree failed This patch add missing_device_number and tolerated_missing_device_number to above output, to let user know what really happened, and helps bug-report and debug. dmesg after patch: [ 127.050367] BTRFS: missing devices(1) exceeds the limit(0), writeable mount is not allowed [ 127.056099] BTRFS: open_ctree failed Changelog v1->v2: 1: Changed to more clear description, suggested-by: Anand Jain Suggested-by: Anand Jain Signed-off-by: Zhao Lei Reviewed-by: Anand Jain Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f556c3732c2c..e49ae5ea9040 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2950,8 +2950,9 @@ retry_root_backup: if (fs_info->fs_devices->missing_devices > fs_info->num_tolerated_disk_barrier_failures && !(sb->s_flags & MS_RDONLY)) { - printk(KERN_WARNING "BTRFS: " - "too many missing devices, writeable mount is not allowed\n"); + pr_warn("BTRFS: missing devices(%llu) exceeds the limit(%d), writeable mount is not allowed\n", + fs_info->fs_devices->missing_devices, + fs_info->num_tolerated_disk_barrier_failures); goto fail_sysfs; } -- cgit v1.2.3 From a4027a20c57a2c8779e17a61425737634bb7163d Mon Sep 17 00:00:00 2001 From: Byongho Lee Date: Fri, 10 Jul 2015 13:10:26 +0900 Subject: Btrfs: remove unused mutex from struct 'btrfs_fs_info' The code using 'ordered_extent_flush_mutex' mutex has removed by below commit. - 8d875f95da43c6a8f18f77869f2ef26e9594fecc btrfs: disable strict file flushes for renames and truncates But the mutex still lives in struct 'btrfs_fs_info'. So, this patch removes the mutex from struct 'btrfs_fs_info' and its initialization code. Signed-off-by: Byongho Lee Reviewed-by: David Sterba Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 6 ------ fs/btrfs/disk-io.c | 1 - 2 files changed, 7 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index f335c18bd263..d4042c89d29b 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1518,12 +1518,6 @@ struct btrfs_fs_info { */ struct mutex ordered_operations_mutex; - /* - * Same as ordered_operations_mutex except this is for ordered extents - * and not the operations. - */ - struct mutex ordered_extent_flush_mutex; - struct rw_semaphore commit_root_sem; struct rw_semaphore cleanup_work_sem; diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index e49ae5ea9040..f7536bcf7cee 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -2608,7 +2608,6 @@ int open_ctree(struct super_block *sb, mutex_init(&fs_info->ordered_operations_mutex); - mutex_init(&fs_info->ordered_extent_flush_mutex); mutex_init(&fs_info->tree_log_mutex); mutex_init(&fs_info->chunk_mutex); mutex_init(&fs_info->transaction_kthread_mutex); -- cgit v1.2.3 From da2f0f74cf7d074e5a8918c8efdf6aba4a989b4a Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 2 Jul 2015 13:57:22 -0700 Subject: Btrfs: add support for blkio controllers This attaches accounting information to bios as we submit them so the new blkio controllers can throttle on btrfs filesystems. Not much is required, we're just associating bios with blkcgs during clone, calling wbc_init_bio()/wbc_account_io() during writepages submission, and attaching the bios to the current context during direct IO. Finally if we are splitting bios during btrfs_map_bio, this attaches accounting information to the split. The end result is able to throttle nicely on single disk filesystems. A little more work is required for multi-device filesystems. Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 1 + fs/btrfs/extent_io.c | 16 +++++++++++++--- fs/btrfs/inode.c | 6 +++++- fs/btrfs/super.c | 1 + fs/btrfs/volumes.c | 8 ++++++++ 5 files changed, 28 insertions(+), 4 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index f7536bcf7cee..230546b45474 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1724,6 +1724,7 @@ static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi) bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE; bdi->congested_fn = btrfs_congested_fn; bdi->congested_data = info; + bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK; return 0; } diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 02d05817cbdf..b9755ce98218 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2730,6 +2730,9 @@ struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask) btrfs_bio->csum = NULL; btrfs_bio->csum_allocated = NULL; btrfs_bio->end_io = NULL; + /* FIXME, put this into bio_clone_bioset */ + if (bio->bi_css) + bio_associate_blkcg(new, bio->bi_css); } return new; } @@ -2790,6 +2793,7 @@ static int merge_bio(int rw, struct extent_io_tree *tree, struct page *page, } static int submit_extent_page(int rw, struct extent_io_tree *tree, + struct writeback_control *wbc, struct page *page, sector_t sector, size_t size, unsigned long offset, struct block_device *bdev, @@ -2826,6 +2830,8 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, } bio = NULL; } else { + if (wbc) + wbc_account_io(wbc, page, page_size); return 0; } } @@ -2841,6 +2847,10 @@ static int submit_extent_page(int rw, struct extent_io_tree *tree, bio_add_page(bio, page, page_size, offset); bio->bi_end_io = end_io_func; bio->bi_private = tree; + if (wbc) { + wbc_init_bio(wbc, bio); + wbc_account_io(wbc, page, page_size); + } if (bio_ret) *bio_ret = bio; @@ -3051,7 +3061,7 @@ static int __do_readpage(struct extent_io_tree *tree, } pnr -= page->index; - ret = submit_extent_page(rw, tree, page, + ret = submit_extent_page(rw, tree, NULL, page, sector, disk_io_size, pg_offset, bdev, bio, pnr, end_bio_extent_readpage, mirror_num, @@ -3446,7 +3456,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode, page->index, cur, end); } - ret = submit_extent_page(write_flags, tree, page, + ret = submit_extent_page(write_flags, tree, wbc, page, sector, iosize, pg_offset, bdev, &epd->bio, max_nr, end_bio_extent_writepage, @@ -3749,7 +3759,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb, clear_page_dirty_for_io(p); set_page_writeback(p); - ret = submit_extent_page(rw, tree, p, offset >> 9, + ret = submit_extent_page(rw, tree, wbc, p, offset >> 9, PAGE_CACHE_SIZE, 0, bdev, &epd->bio, -1, end_bio_extent_buffer_writepage, 0, epd->bio_flags, bio_flags); diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 79a73645346e..bda3c41dc9d5 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7987,7 +7987,11 @@ static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev, u64 first_sector, gfp_t gfp_flags) { int nr_vecs = bio_get_nr_vecs(bdev); - return btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags); + struct bio *bio; + bio = btrfs_bio_alloc(bdev, first_sector, nr_vecs, gfp_flags); + if (bio) + bio_associate_current(bio); + return bio; } static inline int btrfs_lookup_and_bind_dio_csum(struct btrfs_root *root, diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index cd7ef34d2dce..d366dd4664d0 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -1033,6 +1033,7 @@ static int btrfs_fill_super(struct super_block *sb, sb->s_flags |= MS_POSIXACL; #endif sb->s_flags |= MS_I_VERSION; + sb->s_iflags |= SB_I_CGROUPWB; err = open_ctree(sb, fs_devices, (char *)data); if (err) { printk(KERN_ERR "BTRFS: open_ctree failed\n"); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index fb9abf1678d0..88e2fe931bde 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -5942,6 +5942,14 @@ again: if (!bio) return -ENOMEM; + if (first_bio->bi_ioc) { + get_io_context_active(first_bio->bi_ioc); + bio->bi_ioc = first_bio->bi_ioc; + } + if (first_bio->bi_css) { + css_get(first_bio->bi_css); + bio->bi_css = first_bio->bi_css; + } while (bvec <= (first_bio->bi_io_vec + first_bio->bi_vcnt - 1)) { if (bio_add_page(bio, bvec->bv_page, bvec->bv_len, bvec->bv_offset) < bvec->bv_len) { -- cgit v1.2.3 From 2c4580454fffbf184fdb9292aa19ab1ffc224add Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Thu, 16 Jul 2015 15:00:46 +0800 Subject: btrfs: Cleanup for btrfs_calc_num_tolerated_disk_barrier_failures 1: Use ARRAY_SIZE(types) to replace a static-value variant: int num_types = 4; 2: Use 'continue' on condition to reduce one level tab if (!XXX) { code; ... } -> if (XXX) continue; code; ... 3: Put setting 'num_tolerated_disk_barrier_failures = 2' to (num_tolerated_disk_barrier_failures > 2) condition to make make logic neat. if (num_tolerated_disk_barrier_failures > 0 && XXX) num_tolerated_disk_barrier_failures = 0; else if (num_tolerated_disk_barrier_failures > 1) { if (XXX) num_tolerated_disk_barrier_failures = 1; else if (XXX) num_tolerated_disk_barrier_failures = 2; -> if (num_tolerated_disk_barrier_failures > 0 && XXX) num_tolerated_disk_barrier_failures = 0; if (num_tolerated_disk_barrier_failures > 1 && XXX) num_tolerated_disk_barrier_failures = ; if (num_tolerated_disk_barrier_failures > 2 && XXX) num_tolerated_disk_barrier_failures = 2; 4: Remove comment of: num_mirrors - 1: if RAID1 or RAID10 is configured and more than 2 mirrors are used. which is not fit with code. Signed-off-by: Zhao Lei Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 73 ++++++++++++++++++++++++------------------------------ 1 file changed, 33 insertions(+), 40 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index cc15514b4a76..51192d94c90c 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3449,13 +3449,12 @@ int btrfs_calc_num_tolerated_disk_barrier_failures( BTRFS_BLOCK_GROUP_SYSTEM, BTRFS_BLOCK_GROUP_METADATA, BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA}; - int num_types = 4; int i; int c; int num_tolerated_disk_barrier_failures = (int)fs_info->fs_devices->num_devices; - for (i = 0; i < num_types; i++) { + for (i = 0; i < ARRAY_SIZE(types); i++) { struct btrfs_space_info *tmp; sinfo = NULL; @@ -3473,44 +3472,38 @@ int btrfs_calc_num_tolerated_disk_barrier_failures( down_read(&sinfo->groups_sem); for (c = 0; c < BTRFS_NR_RAID_TYPES; c++) { - if (!list_empty(&sinfo->block_groups[c])) { - u64 flags; - - btrfs_get_block_group_info( - &sinfo->block_groups[c], &space); - if (space.total_bytes == 0 || - space.used_bytes == 0) - continue; - flags = space.flags; - /* - * return - * 0: if dup, single or RAID0 is configured for - * any of metadata, system or data, else - * 1: if RAID5 is configured, or if RAID1 or - * RAID10 is configured and only two mirrors - * are used, else - * 2: if RAID6 is configured, else - * num_mirrors - 1: if RAID1 or RAID10 is - * configured and more than - * 2 mirrors are used. - */ - if (num_tolerated_disk_barrier_failures > 0 && - ((flags & (BTRFS_BLOCK_GROUP_DUP | - BTRFS_BLOCK_GROUP_RAID0)) || - ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) - == 0))) - num_tolerated_disk_barrier_failures = 0; - else if (num_tolerated_disk_barrier_failures > 1) { - if (flags & (BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID10)) { - num_tolerated_disk_barrier_failures = 1; - } else if (flags & - BTRFS_BLOCK_GROUP_RAID6) { - num_tolerated_disk_barrier_failures = 2; - } - } - } + u64 flags; + + if (list_empty(&sinfo->block_groups[c])) + continue; + + btrfs_get_block_group_info(&sinfo->block_groups[c], + &space); + if (space.total_bytes == 0 || space.used_bytes == 0) + continue; + flags = space.flags; + /* + * return + * 0: if dup, single or RAID0 is configured for + * any of metadata, system or data, else + * 1: if RAID5 is configured, or if RAID1 or + * RAID10 is configured and only two mirrors + * are used, else + * 2: if RAID6 is configured + */ + if (num_tolerated_disk_barrier_failures > 0 && + ((flags & (BTRFS_BLOCK_GROUP_DUP | + BTRFS_BLOCK_GROUP_RAID0)) || + ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0))) + num_tolerated_disk_barrier_failures = 0; + else if (num_tolerated_disk_barrier_failures > 1 && + (flags & (BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID5 | + BTRFS_BLOCK_GROUP_RAID10))) + num_tolerated_disk_barrier_failures = 1; + else if (num_tolerated_disk_barrier_failures > 2 && + (flags & BTRFS_BLOCK_GROUP_RAID6)) + num_tolerated_disk_barrier_failures = 2; } up_read(&sinfo->groups_sem); } -- cgit v1.2.3 From 943c6e9925d90dc80207322b5799d95fb90ffec0 Mon Sep 17 00:00:00 2001 From: Zhao Lei Date: Wed, 19 Aug 2015 15:54:15 +0800 Subject: btrfs: Add raid56 support for updating num_tolerated_disk_barrier_failures in btrfs_balance Code for updating fs_info->num_tolerated_disk_barrier_failures in btrfs_balance() lacks raid56 support. Reason: Above code was wroten in 2012-08-01, together with btrfs_calc_num_tolerated_disk_barrier_failures()'s first version. Then, btrfs_calc_num_tolerated_disk_barrier_failures() got updated later to support raid56, but code in btrfs_balance() was not updated together. Fix: Merge above similar code to a common function: btrfs_get_num_tolerated_disk_barrier_failures() and make it support both case. It can fix this bug with a bonus of cleanup, and make these code never in above no-sync state from now on. Suggested-by: Anand Jain Signed-off-by: Zhao Lei Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 47 +++++++++++++++++++++++++---------------------- fs/btrfs/disk-io.h | 1 + fs/btrfs/volumes.c | 21 ++++----------------- 3 files changed, 30 insertions(+), 39 deletions(-) (limited to 'fs/btrfs/disk-io.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 51192d94c90c..0b658d0230f0 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -3440,6 +3440,26 @@ static int barrier_all_devices(struct btrfs_fs_info *info) return 0; } +int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags) +{ + if ((flags & (BTRFS_BLOCK_GROUP_DUP | + BTRFS_BLOCK_GROUP_RAID0 | + BTRFS_AVAIL_ALLOC_BIT_SINGLE)) || + ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0)) + return 0; + + if (flags & (BTRFS_BLOCK_GROUP_RAID1 | + BTRFS_BLOCK_GROUP_RAID5 | + BTRFS_BLOCK_GROUP_RAID10)) + return 1; + + if (flags & BTRFS_BLOCK_GROUP_RAID6) + return 2; + + pr_warn("BTRFS: unknown raid type: %llu\n", flags); + return 0; +} + int btrfs_calc_num_tolerated_disk_barrier_failures( struct btrfs_fs_info *fs_info) { @@ -3482,28 +3502,11 @@ int btrfs_calc_num_tolerated_disk_barrier_failures( if (space.total_bytes == 0 || space.used_bytes == 0) continue; flags = space.flags; - /* - * return - * 0: if dup, single or RAID0 is configured for - * any of metadata, system or data, else - * 1: if RAID5 is configured, or if RAID1 or - * RAID10 is configured and only two mirrors - * are used, else - * 2: if RAID6 is configured - */ - if (num_tolerated_disk_barrier_failures > 0 && - ((flags & (BTRFS_BLOCK_GROUP_DUP | - BTRFS_BLOCK_GROUP_RAID0)) || - ((flags & BTRFS_BLOCK_GROUP_PROFILE_MASK) == 0))) - num_tolerated_disk_barrier_failures = 0; - else if (num_tolerated_disk_barrier_failures > 1 && - (flags & (BTRFS_BLOCK_GROUP_RAID1 | - BTRFS_BLOCK_GROUP_RAID5 | - BTRFS_BLOCK_GROUP_RAID10))) - num_tolerated_disk_barrier_failures = 1; - else if (num_tolerated_disk_barrier_failures > 2 && - (flags & BTRFS_BLOCK_GROUP_RAID6)) - num_tolerated_disk_barrier_failures = 2; + + num_tolerated_disk_barrier_failures = min( + num_tolerated_disk_barrier_failures, + btrfs_get_num_tolerated_disk_barrier_failures( + flags)); } up_read(&sinfo->groups_sem); } diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h index d4cbfeeeedd4..bdfb479ea859 100644 --- a/fs/btrfs/disk-io.h +++ b/fs/btrfs/disk-io.h @@ -139,6 +139,7 @@ struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans, u64 objectid); int btree_lock_page_hook(struct page *page, void *data, void (*flush_fn)(void *)); +int btrfs_get_num_tolerated_disk_barrier_failures(u64 flags); int btrfs_calc_num_tolerated_disk_barrier_failures( struct btrfs_fs_info *fs_info); int __init btrfs_end_io_wq_init(void); diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 69520dfa8960..644e070b3bd2 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -3585,23 +3585,10 @@ int btrfs_balance(struct btrfs_balance_control *bctl, } while (read_seqretry(&fs_info->profiles_lock, seq)); if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) { - int num_tolerated_disk_barrier_failures; - u64 target = bctl->sys.target; - - num_tolerated_disk_barrier_failures = - btrfs_calc_num_tolerated_disk_barrier_failures(fs_info); - if (num_tolerated_disk_barrier_failures > 0 && - (target & - (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID0 | - BTRFS_AVAIL_ALLOC_BIT_SINGLE))) - num_tolerated_disk_barrier_failures = 0; - else if (num_tolerated_disk_barrier_failures > 1 && - (target & - (BTRFS_BLOCK_GROUP_RAID1 | BTRFS_BLOCK_GROUP_RAID10))) - num_tolerated_disk_barrier_failures = 1; - - fs_info->num_tolerated_disk_barrier_failures = - num_tolerated_disk_barrier_failures; + fs_info->num_tolerated_disk_barrier_failures = min( + btrfs_calc_num_tolerated_disk_barrier_failures(fs_info), + btrfs_get_num_tolerated_disk_barrier_failures( + bctl->sys.target)); } ret = insert_balance_item(fs_info->tree_root, bctl); -- cgit v1.2.3