From 406266ab9ac8ed8b085c58aacd9e3161480dc5d5 Mon Sep 17 00:00:00 2001 From: Jan Engelhardt Date: Wed, 9 Dec 2009 22:00:38 +0000 Subject: btrfs: fix missing last-entry in readdir(3) parent 49313cdac7b34c9f7ecbb1780cfc648b1c082cd7 (v2.6.32-1-g49313cd) commit ff48c08e1c05c67e8348ab6f8a24de8034e0e34d Author: Jan Engelhardt Date: Wed Dec 9 22:57:36 2009 +0100 Btrfs: fix missing last-entry in readdir(3) When one does a 32-bit readdir(3), the last entry of a directory is missing. This is however not due to passing a large value to filldir, but it seems to have to do with glibc doing telldir or something quirky. In any case, this patch fixes it in practice. Signed-off-by: Jan Engelhardt Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 5440bab2363..d5aa9731094 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3995,7 +3995,11 @@ skip: /* Reached end of directory/root. Bump pos past the last item. */ if (key_type == BTRFS_DIR_INDEX_KEY) - filp->f_pos = INT_LIMIT(off_t); + /* + * 32-bit glibc will use getdents64, but then strtol - + * so the last number we can serve is this. + */ + filp->f_pos = 0x7fffffff; else filp->f_pos++; nopos: -- cgit v1.2.3-70-g09d2 From 6c090a11e1c403b727a6a8eff0b97d5fb9e95cb5 Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Fri, 15 Jan 2010 20:08:22 +0000 Subject: Btrfs: fix regression in orphan cleanup Currently orphan cleanup only ever gets triggered if we cross subvolumes during a lookup, which means that if we just mount a plain jane fs that has orphans in it, they will never get cleaned up. This results in panic's like these http://www.kerneloops.org/oops.php?number=1109085 where adding an orphan entry results in -EEXIST being returned and we panic. In order to fix this, we check to see on lookup if our root has had the orphan cleanup done, and if not go ahead and do it. This is easily reproduceable by running this testcase #include #include #include #include #include #include int main(int argc, char **argv) { char data[4096]; char newdata[4096]; int fd1, fd2; memset(data, 'a', 4096); memset(newdata, 'b', 4096); while (1) { int i; fd1 = creat("file1", 0666); if (fd1 < 0) break; for (i = 0; i < 512; i++) write(fd1, data, 4096); fsync(fd1); close(fd1); fd2 = creat("file2", 0666); if (fd2 < 0) break; ftruncate(fd2, 4096 * 512); for (i = 0; i < 512; i++) write(fd2, newdata, 4096); close(fd2); i = rename("file2", "file1"); unlink("file1"); } return 0; } and then pulling the power on the box, and then trying to run that test again when the box comes back up. I've tested this locally and it fixes the problem. Thanks to Tomas Carnecky for helping me track this down initially. Signed-off-by: Josef Bacik Signed-off-by: Chris Mason --- fs/btrfs/inode.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index d5aa9731094..b330e27c2d8 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3796,6 +3796,12 @@ 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; } -- cgit v1.2.3-70-g09d2 From a555f810af6d63ea5960abaed88e150ad95c3011 Mon Sep 17 00:00:00 2001 From: Chris Mason Date: Thu, 28 Jan 2010 16:18:15 -0500 Subject: 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(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 9f806dd04c2..2aa8ec6a098 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 b330e27c2d8..f46c5727684 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 3f9b45704fc..8a1ea6e6457 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); -- cgit v1.2.3-70-g09d2 From d1ea6a61454e7d7ff0873d0ad1ae27d5807da0d3 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Wed, 20 Jan 2010 07:28:54 +0000 Subject: 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(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index f46c5727684..5606361b5f0 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; -- cgit v1.2.3-70-g09d2 From e3acc2a6850efff647f1c5458524eb3a8bcba20a Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Tue, 26 Jan 2010 14:30:53 +0000 Subject: 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(-) (limited to 'fs/btrfs/inode.c') diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c index 009e3bd18f2..87b25543d7d 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 5606361b5f0..8cd109972fa 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; } -- cgit v1.2.3-70-g09d2