From a555f810af6d63ea5960abaed88e150ad95c3011 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 28 Jan 2010 16:18:15 -0500 Subject: [PATCH 1/8] Btrfs: Add mount -o compress-force The default btrfs mount -o compress mode will quickly back off compressing a file if it notices that compression does not reduce the size of the data being written. This can save considerable CPU because all future writes to the file go through uncompressed. But some files are both very large and have mixed data stored in them. In that case, we want to add the ability to always try compressing data before writing it. This commit adds mount -o compress-force. A later commit will add a new inode flag that does the same thing. Signed-off-by: Chris Mason --- fs/btrfs/ctree.h | 1 + fs/btrfs/inode.c | 3 ++- fs/btrfs/super.c | 9 ++++++++- 3 files changed, 11 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9f806dd04c27..2aa8ec6a0981 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1161,6 +1161,7 @@ struct btrfs_root { #define BTRFS_MOUNT_SSD_SPREAD (1 << 8) #define BTRFS_MOUNT_NOSSD (1 << 9) #define BTRFS_MOUNT_DISCARD (1 << 10) +#define BTRFS_MOUNT_FORCE_COMPRESS (1 << 11) #define btrfs_clear_opt(o, opt) ((o) &= ~BTRFS_MOUNT_##opt) #define btrfs_set_opt(o, opt) ((o) |= BTRFS_MOUNT_##opt) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index b330e27c2d8b..f46c57276844 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -483,7 +483,8 @@ again: nr_pages_ret = 0; /* flag the file so we don't compress in the future */ - BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; + if (!btrfs_test_opt(root, FORCE_COMPRESS)) + BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS; } if (will_compress) { *num_added += 1; diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c index 3f9b45704fcd..8a1ea6e64575 100644 --- a/fs/btrfs/super.c +++ b/fs/btrfs/super.c @@ -66,7 +66,8 @@ enum { Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow, Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier, Opt_ssd, Opt_nossd, Opt_ssd_spread, Opt_thread_pool, Opt_noacl, - Opt_compress, Opt_notreelog, Opt_ratio, Opt_flushoncommit, + Opt_compress, Opt_compress_force, Opt_notreelog, Opt_ratio, + Opt_flushoncommit, Opt_discard, Opt_err, }; @@ -82,6 +83,7 @@ static match_table_t tokens = { {Opt_alloc_start, "alloc_start=%s"}, {Opt_thread_pool, "thread_pool=%d"}, {Opt_compress, "compress"}, + {Opt_compress_force, "compress-force"}, {Opt_ssd, "ssd"}, {Opt_ssd_spread, "ssd_spread"}, {Opt_nossd, "nossd"}, @@ -173,6 +175,11 @@ int btrfs_parse_options(struct btrfs_root *root, char *options) printk(KERN_INFO "btrfs: use compression\n"); btrfs_set_opt(info->mount_opt, COMPRESS); break; + case Opt_compress_force: + printk(KERN_INFO "btrfs: forcing compression\n"); + btrfs_set_opt(info->mount_opt, FORCE_COMPRESS); + btrfs_set_opt(info->mount_opt, COMPRESS); + break; case Opt_ssd: printk(KERN_INFO "btrfs: use ssd allocation scheme\n"); btrfs_set_opt(info->mount_opt, SSD); From b8d9bfeb18f9af794020d96e9bee984d18a8d737 Mon Sep 17 00:00:00 2001 From: Miao Xie Date: Tue, 15 Dec 2009 06:54:17 +0000 Subject: [PATCH 2/8] Btrfs: remove tree_search() in extent_map.c This patch removes tree_search() in extent_map.c because it is not called by anything. Signed-off-by: Miao Xie Signed-off-by: Chris Mason --- fs/btrfs/extent_map.c | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c index ccbdcb54ec5d..5a4f73b79b75 100644 --- a/fs/btrfs/extent_map.c +++ b/fs/btrfs/extent_map.c @@ -155,20 +155,6 @@ static struct rb_node *__tree_search(struct rb_root *root, u64 offset, return NULL; } -/* - * look for an offset in the tree, and if it can't be found, return - * the first offset we can find smaller than 'offset'. - */ -static inline struct rb_node *tree_search(struct rb_root *root, u64 offset) -{ - struct rb_node *prev; - struct rb_node *ret; - ret = __tree_search(root, offset, &prev, NULL); - if (!ret) - return prev; - return ret; -} - /* check to see if two extent_map structs are adjacent and safe to merge */ static int mergable_maps(struct extent_map *prev, struct extent_map *next) { From d1ea6a61454e7d7ff0873d0ad1ae27d5807da0d3 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 20 Jan 2010 07:28:54 +0000 Subject: [PATCH 3/8] Btrfs: Use correct values when updating inode i_size on fallocate commit f2bc9dd07e3424c4ec5f3949961fe053d47bc825 Author: Aneesh Kumar K.V Date: Wed Jan 20 12:57:53 2010 +0530 Btrfs: Use correct values when updating inode i_size on fallocate Even though we allocate more, we should be updating inode i_size as per the arguments passed Signed-off-by: Aneesh Kumar K.V Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f46c57276844..5606361b5f04 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -5800,7 +5800,7 @@ out_fail: } static int prealloc_file_range(struct inode *inode, u64 start, u64 end, - u64 alloc_hint, int mode) + u64 alloc_hint, int mode, loff_t actual_len) { struct btrfs_trans_handle *trans; struct btrfs_root *root = BTRFS_I(inode)->root; @@ -5809,6 +5809,7 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end, u64 cur_offset = start; u64 num_bytes = end - start; int ret = 0; + u64 i_size; while (num_bytes > 0) { alloc_size = min(num_bytes, root->fs_info->max_extent); @@ -5847,8 +5848,12 @@ static int prealloc_file_range(struct inode *inode, u64 start, u64 end, BTRFS_I(inode)->flags |= BTRFS_INODE_PREALLOC; if (!(mode & FALLOC_FL_KEEP_SIZE) && cur_offset > inode->i_size) { - i_size_write(inode, cur_offset); - btrfs_ordered_update_i_size(inode, cur_offset, NULL); + if (cur_offset > actual_len) + i_size = actual_len; + else + i_size = cur_offset; + i_size_write(inode, i_size); + btrfs_ordered_update_i_size(inode, i_size, NULL); } ret = btrfs_update_inode(trans, root, inode); @@ -5941,7 +5946,7 @@ static long btrfs_fallocate(struct inode *inode, int mode, !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { ret = prealloc_file_range(inode, cur_offset, last_byte, - alloc_hint, mode); + alloc_hint, mode, offset+len); if (ret < 0) { free_extent_map(em); break; From f858153c367a397235d3e81136741e40e44faf1d Mon Sep 17 00:00:00 2001 From: Yang Hongyang Date: Tue, 26 Jan 2010 00:48:23 +0000 Subject: [PATCH 4/8] Btrfs: fix a memory leak in btrfs_init_acl In btrfs_init_acl() cloned acl is not released Signed-off-by: Yang Hongyang Signed-off-by: Chris Mason --- fs/btrfs/acl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c index fa44e92e9b8f..da3133c69830 100644 --- a/fs/btrfs/acl.c +++ b/fs/btrfs/acl.c @@ -269,6 +269,7 @@ int btrfs_init_acl(struct btrfs_trans_handle *trans, ACL_TYPE_ACCESS); } } + posix_acl_release(clone); } failed: posix_acl_release(acl); From e3acc2a6850efff647f1c5458524eb3a8bcba20a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 26 Jan 2010 14:30:53 +0000 Subject: [PATCH 5/8] Btrfs: run orphan cleanup on default fs root This patch revert's commit 6c090a11e1c403b727a6a8eff0b97d5fb9e95cb5 Since it introduces this problem where we can run orphan cleanup on a volume that can have orphan entries re-added. Instead of my original fix, Yan Zheng pointed out that we can just revert my original fix and then run the orphan cleanup in open_ctree after we look up the fs_root. I have tested this with all the tests that gave me problems and this patch fixes both problems. Thanks, Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/disk-io.c | 6 ++++++ fs/btrfs/inode.c | 6 ------ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 009e3bd18f23..87b25543d7d1 100644 --- a/fs/btrfs/disk-io.c +++ b/fs/btrfs/disk-io.c @@ -1993,6 +1993,12 @@ struct btrfs_root *open_ctree(struct super_block *sb, if (!fs_info->fs_root) goto fail_trans_kthread; + if (!(sb->s_flags & MS_RDONLY)) { + down_read(&fs_info->cleanup_work_sem); + btrfs_orphan_cleanup(fs_info->fs_root); + up_read(&fs_info->cleanup_work_sem); + } + return tree_root; fail_trans_kthread: diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5606361b5f04..8cd109972fa6 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3797,12 +3797,6 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry) if (location.type == BTRFS_INODE_ITEM_KEY) { inode = btrfs_iget(dir->i_sb, &location, root); - if (unlikely(root->clean_orphans) && - !(inode->i_sb->s_flags & MS_RDONLY)) { - down_read(&root->fs_info->cleanup_work_sem); - btrfs_orphan_cleanup(root); - up_read(&root->fs_info->cleanup_work_sem); - } return inode; } From f48b90756bd834dda852ff514f2690d3175b1f44 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 27 Jan 2010 02:07:59 +0000 Subject: [PATCH 6/8] Btrfs: do not mark the chunk as readonly if in degraded mode If a RAID setup has chunks that span multiple disks, and one of those disks has failed, btrfs_chunk_readonly will return 1 since one of the disks in that chunk's stripes is dead and therefore not writeable. So instead if we are in degraded mode, return 0 so we can go ahead and allocate stuff. Without this patch all of the block groups in a RAID1 setup will end up read-only, which will mean we can't add new disks to the array since we won't be able to make allocations. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 220dad5db017..66122bdf8bbf 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -2538,6 +2538,11 @@ int btrfs_chunk_readonly(struct btrfs_root *root, u64 chunk_offset) if (!em) return 1; + if (btrfs_test_opt(root, DEGRADED)) { + free_extent_map(em); + return 0; + } + map = (struct map_lookup *)em->bdev; for (i = 0; i < map->num_stripes; i++) { if (!map->stripes[i].dev->writeable) { From 7f59203abeaf18bf3497b308891f95a4489810ad Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 27 Jan 2010 02:09:00 +0000 Subject: [PATCH 7/8] Btrfs: check return value of open_bdev_exclusive properly Hit this problem while testing RAID1 failure stuff. open_bdev_exclusive returns ERR_PTR(), not NULL. So change the return value properly. This is important if you accidently specify a device that doesn't exist when trying to add a new device to an array, you will panic the box dereferencing bdev. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 66122bdf8bbf..5eb7459e3782 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1434,8 +1434,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) return -EINVAL; bdev = open_bdev_exclusive(device_path, 0, root->fs_info->bdev_holder); - if (!bdev) - return -EIO; + if (IS_ERR(bdev)) + return PTR_ERR(bdev); if (root->fs_info->fs_devices->seeding) { seeding_dev = 1; From 035fe03a7ad56982b30ab3a522b7b08d58feccd0 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Wed, 27 Jan 2010 02:09:38 +0000 Subject: [PATCH 8/8] Btrfs: check total number of devices when removing missing If you have a disk failure in RAID1 and then add a new disk to the array, and then try to remove the missing volume, it will fail. The reason is the sanity check only looks at the total number of rw devices, which is just 2 because we have 2 good disks and 1 bad one. Instead check the total number of devices in the array to make sure we can actually remove the device. Tested this with a failed disk setup and with this test we can now run btrfs-vol -r missing /mount/point and it works fine. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/volumes.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 5eb7459e3782..41ecbb2347f2 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -1135,7 +1135,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) root->fs_info->avail_metadata_alloc_bits; if ((all_avail & BTRFS_BLOCK_GROUP_RAID10) && - root->fs_info->fs_devices->rw_devices <= 4) { + root->fs_info->fs_devices->num_devices <= 4) { printk(KERN_ERR "btrfs: unable to go below four devices " "on raid10\n"); ret = -EINVAL; @@ -1143,7 +1143,7 @@ int btrfs_rm_device(struct btrfs_root *root, char *device_path) } if ((all_avail & BTRFS_BLOCK_GROUP_RAID1) && - root->fs_info->fs_devices->rw_devices <= 2) { + root->fs_info->fs_devices->num_devices <= 2) { printk(KERN_ERR "btrfs: unable to go below two " "devices on raid1\n"); ret = -EINVAL;